diff --git a/ChangeLog b/ChangeLog index 48297e31..6a9f277e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,11 @@ +Tue Mar 14 19:11:29 CET 2000 Daniel Veillard + + * all: tagged LIB_XML_1_X + * *.c *.h : updated from W3C CVS tree + * configure.in : 2.0.0-beta + * libxml.spec.in : libxml2 package nam + * result/* : new version of the tests output + Mon Mar 6 09:34:52 CET 2000 Daniel Veillard * doc/xml.html, doc/update.html: updated docs, 1.8.7 diff --git a/HTMLparser.c b/HTMLparser.c index 080b9ed3..aafaec6d 100644 --- a/HTMLparser.c +++ b/HTMLparser.c @@ -121,36 +121,81 @@ PUSH_AND_POP(extern, xmlChar*, name) * COPY(to) copy one char to *to, increment CUR_PTR and to accordingly */ -#define CUR (*ctxt->input->cur) +#define CUR ((int) (*ctxt->input->cur)) + #define UPPER (toupper(*ctxt->input->cur)) + #define SKIP(val) ctxt->nbChars += (val),ctxt->input->cur += (val) + #define NXT(val) ctxt->input->cur[(val)] + #define UPP(val) (toupper(ctxt->input->cur[(val)])) + #define CUR_PTR ctxt->input->cur + #define SHRINK xmlParserInputShrink(ctxt->input) + #define GROW xmlParserInputGrow(ctxt->input, INPUT_CHUNK) -#define SKIP_BLANKS \ - while (IS_BLANK(*(ctxt->input->cur))) NEXT +#define CURRENT ((int) (*ctxt->input->cur)) -#ifndef USE_UTF_8 -#define CURRENT (*ctxt->input->cur) -#define NEXT { \ - if ((*ctxt->input->cur == 0) && \ - (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) { \ - xmlPopInput(ctxt); \ - } else { \ - if (*(ctxt->input->cur) == '\n') { \ - ctxt->input->line++; ctxt->input->col = 1; \ - } else ctxt->input->col++; \ - ctxt->input->cur++; \ - ctxt->nbChars++; \ - if (*ctxt->input->cur == 0) \ - xmlParserInputGrow(ctxt->input, INPUT_CHUNK); \ - }} +#define NEXT htmlNextChar(ctxt); -#else -#endif +#define SKIP_BLANKS htmlSkipBlankChars(ctxt); + +/** + * htmlNextChar: + * @ctxt: the HTML parser context + * + * Skip to the next char input char. + */ + +void +htmlNextChar(htmlParserCtxtPtr ctxt) { + if ((*ctxt->input->cur == 0) && + (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) { + xmlPopInput(ctxt); + } else { + if (*(ctxt->input->cur) == '\n') { + ctxt->input->line++; ctxt->input->col = 1; + } else ctxt->input->col++; + ctxt->input->cur++; + ctxt->nbChars++; + if (*ctxt->input->cur == 0) + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + } +} + +/** + * htmlSkipBlankChars: + * @ctxt: the HTML parser context + * + * skip all blanks character found at that point in the input streams. + * + * Returns the number of space chars skipped + */ + +int +htmlSkipBlankChars(xmlParserCtxtPtr ctxt) { + int res = 0; + + while (IS_BLANK(*(ctxt->input->cur))) { + if ((*ctxt->input->cur == 0) && + (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) { + xmlPopInput(ctxt); + } else { + if (*(ctxt->input->cur) == '\n') { + ctxt->input->line++; ctxt->input->col = 1; + } else ctxt->input->col++; + ctxt->input->cur++; + ctxt->nbChars++; + if (*ctxt->input->cur == 0) + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + } + res++; + } + return(res); +} @@ -475,7 +520,7 @@ htmlAutoCloseTag(htmlDocPtr doc, const xmlChar *name, htmlNodePtr elem) { if (elem == NULL) return(1); if (!xmlStrcmp(name, elem->name)) return(0); if (htmlCheckAutoClose(elem->name, name)) return(1); - child = elem->childs; + child = elem->children; while (child != NULL) { if (htmlAutoCloseTag(doc, name, child)) return(1); child = child->next; @@ -499,7 +544,7 @@ htmlIsAutoClosed(htmlDocPtr doc, htmlNodePtr elem) { htmlNodePtr child; if (elem == NULL) return(1); - child = elem->childs; + child = elem->children; while (child != NULL) { if (htmlAutoCloseTag(doc, elem->name, child)) return(1); child = child->next; @@ -1275,7 +1320,7 @@ htmlNewDoc(const xmlChar *URI, const xmlChar *ExternalID) { else xmlCreateIntSubset(cur, BAD_CAST "HTML", ExternalID, URI); cur->name = NULL; - cur->root = NULL; + cur->children = NULL; cur->extSubset = NULL; cur->oldNs = NULL; cur->encoding = NULL; @@ -1285,7 +1330,6 @@ htmlNewDoc(const xmlChar *URI, const xmlChar *ExternalID) { cur->refs = NULL; #ifndef XML_WITHOUT_CORBA cur->_private = NULL; - cur->vepv = NULL; #endif return(cur); } @@ -1667,7 +1711,8 @@ htmlParseSystemLiteral(htmlParserCtxtPtr ctxt) { } } else { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) - ctxt->sax->error(ctxt->userData, "SystemLiteral \" or ' expected\n"); + ctxt->sax->error(ctxt->userData, + "SystemLiteral \" or ' expected\n"); ctxt->wellFormed = 0; } diff --git a/HTMLtree.c b/HTMLtree.c index 19bee532..fe9c0ae3 100644 --- a/HTMLtree.c +++ b/HTMLtree.c @@ -80,7 +80,7 @@ htmlAttrDump(xmlBufferPtr buf, xmlDocPtr doc, xmlAttrPtr cur) { } xmlBufferWriteChar(buf, " "); xmlBufferWriteCHAR(buf, cur->name); - value = xmlNodeListGetString(doc, cur->val, 0); + value = xmlNodeListGetString(doc, cur->children, 0); if (value) { xmlBufferWriteChar(buf, "="); xmlBufferWriteQuotedString(buf, value); @@ -212,7 +212,7 @@ htmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur) { } return; } - if ((cur->content == NULL) && (cur->childs == NULL)) { + if ((cur->content == NULL) && (cur->children == NULL)) { if ((info != NULL) && (info->endTag != 0)) xmlBufferWriteChar(buf, ">"); else { @@ -242,15 +242,15 @@ htmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur) { xmlFree(buffer); } } - if (cur->childs != NULL) { - if ((cur->childs->type != HTML_TEXT_NODE) && - (cur->childs->type != HTML_ENTITY_REF_NODE) && - (cur->childs != cur->last)) + if (cur->children != NULL) { + if ((cur->children->type != HTML_TEXT_NODE) && + (cur->children->type != HTML_ENTITY_REF_NODE) && + (cur->children != cur->last)) xmlBufferWriteChar(buf, "\n"); - htmlNodeListDump(buf, doc, cur->childs); + htmlNodeListDump(buf, doc, cur->children); if ((cur->last->type != HTML_TEXT_NODE) && (cur->last->type != HTML_ENTITY_REF_NODE) && - (cur->childs != cur->last)) + (cur->children != cur->last)) xmlBufferWriteChar(buf, "\n"); } if (!htmlIsAutoClosed(doc, cur)) { @@ -307,8 +307,8 @@ htmlDocContentDump(xmlBufferPtr buf, xmlDocPtr cur) { xmlBufferWriteChar(buf, ""); } - if (cur->root != NULL) { - htmlNodeListDump(buf, cur, cur->root); + if (cur->children != NULL) { + htmlNodeListDump(buf, cur, cur->children); } xmlBufferWriteChar(buf, "\n"); cur->type = type; diff --git a/SAX.c b/SAX.c index 35d80131..10c6a835 100644 --- a/SAX.c +++ b/SAX.c @@ -158,66 +158,112 @@ internalSubset(void *ctx, const xmlChar *name, name, ExternalID, SystemID); #endif xmlCreateIntSubset(ctxt->myDoc, name, ExternalID, SystemID); +} + +/** + * externalSubset: + * @ctx: the user data (XML parser context) + * + * Callback on external subset declaration. + */ +void +externalSubset(void *ctx, const xmlChar *name, + const xmlChar *ExternalID, const xmlChar *SystemID) +{ + xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) ctx; +#ifdef DEBUG_SAX + fprintf(stderr, "SAX.externalSubset(%s, %s, %s)\n", + name, ExternalID, SystemID); +#endif if (((ExternalID != NULL) || (SystemID != NULL)) && (ctxt->validate && ctxt->wellFormed && ctxt->myDoc)) { /* * Try to fetch and parse the external subset. */ - xmlDtdPtr ret = NULL; - xmlParserCtxtPtr dtdCtxt; + xmlParserInputPtr oldinput; + int oldinputNr; + int oldinputMax; + xmlParserInputPtr *oldinputTab; + int oldwellFormed; xmlParserInputPtr input = NULL; xmlCharEncoding enc; - dtdCtxt = xmlNewParserCtxt(); - if (dtdCtxt == NULL) return; - /* * Ask the Entity resolver to load the damn thing */ - if ((ctxt->directory != NULL) && (dtdCtxt->directory == NULL)) - dtdCtxt->directory = (char *) xmlStrdup(BAD_CAST ctxt->directory); - - if ((dtdCtxt->sax != NULL) && (dtdCtxt->sax->resolveEntity != NULL)) - input = dtdCtxt->sax->resolveEntity(dtdCtxt->userData, ExternalID, + if ((ctxt->sax != NULL) && (ctxt->sax->resolveEntity != NULL)) + input = ctxt->sax->resolveEntity(ctxt->userData, ExternalID, SystemID); if (input == NULL) { - xmlFreeParserCtxt(dtdCtxt); return; } + xmlNewDtd(ctxt->myDoc, name, ExternalID, SystemID); + /* - * plug some encoding conversion routines here. !!! + * make sure we won't destroy the main document context */ - xmlPushInput(dtdCtxt, input); - enc = xmlDetectCharEncoding(dtdCtxt->input->cur); - xmlSwitchEncoding(dtdCtxt, enc); + oldinput = ctxt->input; + oldinputNr = ctxt->inputNr; + oldinputMax = ctxt->inputMax; + oldinputTab = ctxt->inputTab; + oldwellFormed = ctxt->wellFormed; + + ctxt->inputTab = (xmlParserInputPtr *) + xmlMalloc(5 * sizeof(xmlParserInputPtr)); + if (ctxt->inputTab == NULL) { + ctxt->errNo = XML_ERR_NO_MEMORY; + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "externalSubset: out of memory\n"); + ctxt->errNo = XML_ERR_NO_MEMORY; + ctxt->input = oldinput; + ctxt->inputNr = oldinputNr; + ctxt->inputMax = oldinputMax; + ctxt->inputTab = oldinputTab; + return; + } + ctxt->inputNr = 0; + ctxt->inputMax = 5; + ctxt->input = NULL; + xmlPushInput(ctxt, input); + + /* + * On the fly encoding conversion if needed + */ + enc = xmlDetectCharEncoding(ctxt->input->cur, 4); + xmlSwitchEncoding(ctxt, enc); if (input->filename == NULL) input->filename = (char *) xmlStrdup(SystemID); input->line = 1; input->col = 1; - input->base = dtdCtxt->input->cur; - input->cur = dtdCtxt->input->cur; + input->base = ctxt->input->cur; + input->cur = ctxt->input->cur; input->free = NULL; /* * let's parse that entity knowing it's an external subset. */ - xmlParseExternalSubset(dtdCtxt, ExternalID, SystemID); + xmlParseExternalSubset(ctxt, ExternalID, SystemID); - if (dtdCtxt->myDoc != NULL) { - if (dtdCtxt->wellFormed) { - ret = dtdCtxt->myDoc->intSubset; - dtdCtxt->myDoc->intSubset = NULL; - } else { - ret = NULL; - } - xmlFreeDoc(dtdCtxt->myDoc); - dtdCtxt->myDoc = NULL; - } - xmlFreeParserCtxt(dtdCtxt); - - ctxt->myDoc->extSubset = ret; + /* + * Free up the external entities + */ + + while (ctxt->inputNr > 1) + xmlPopInput(ctxt); + xmlFreeInputStream(ctxt->input); + xmlFree(ctxt->inputTab); + + /* + * Restore the parsing context of the main entity + */ + ctxt->input = oldinput; + ctxt->inputNr = oldinputNr; + ctxt->inputMax = oldinputMax; + ctxt->inputTab = oldinputTab; + /* ctxt->wellFormed = oldwellFormed; */ } } @@ -316,13 +362,23 @@ entityDecl(void *ctx, const xmlChar *name, int type, fprintf(stderr, "SAX.entityDecl(%s, %d, %s, %s, %s)\n", name, type, publicId, systemId, content); #endif - xmlAddDocEntity(ctxt->myDoc, name, type, publicId, systemId, content); + if (ctxt->inSubset == 1) + xmlAddDocEntity(ctxt->myDoc, name, type, publicId, + systemId, content); + else if (ctxt->inSubset == 2) + xmlAddDtdEntity(ctxt->myDoc, name, type, publicId, + systemId, content); + else { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt, + "SAX.entityDecl(%s) called while not in subset\n", name); + } } /** * attributeDecl: * @ctx: the user data (XML parser context) - * @name: the attribute name + * @fullname: the attribute name * @type: the attribute type * @publicId: The public ID of the attribute * @systemId: The system ID of the attribute @@ -331,24 +387,40 @@ entityDecl(void *ctx, const xmlChar *name, int type, * An attribute definition has been parsed */ void -attributeDecl(void *ctx, const xmlChar *elem, const xmlChar *name, +attributeDecl(void *ctx, const xmlChar *elem, const xmlChar *fullname, int type, int def, const xmlChar *defaultValue, xmlEnumerationPtr tree) { xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) ctx; xmlAttributePtr attr; + xmlChar *name = NULL, *prefix = NULL; #ifdef DEBUG_SAX fprintf(stderr, "SAX.attributeDecl(%s, %s, %d, %d, %s, ...)\n", - elem, name, type, def, defaultValue); + elem, fullname, type, def, defaultValue); #endif - attr = xmlAddAttributeDecl(&ctxt->vctxt, ctxt->myDoc->intSubset, elem, - name, type, def, defaultValue, tree); + name = xmlSplitQName(ctxt, fullname, &prefix); + if (ctxt->inSubset == 1) + attr = xmlAddAttributeDecl(&ctxt->vctxt, ctxt->myDoc->intSubset, elem, + name, prefix, type, def, defaultValue, tree); + else if (ctxt->inSubset == 2) + attr = xmlAddAttributeDecl(&ctxt->vctxt, ctxt->myDoc->extSubset, elem, + name, prefix, type, def, defaultValue, tree); + else { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt, + "SAX.attributeDecl(%s) called while not in subset\n", name); + return; + } if (attr == 0) ctxt->valid = 0; if (ctxt->validate && ctxt->wellFormed && ctxt->myDoc && ctxt->myDoc->intSubset) ctxt->valid &= xmlValidateAttributeDecl(&ctxt->vctxt, ctxt->myDoc, attr); + if (prefix != NULL) + xmlFree(prefix); + if (name != NULL) + xmlFree(name); } /** @@ -367,16 +439,26 @@ elementDecl(void *ctx, const xmlChar *name, int type, xmlElementContentPtr content) { xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) ctx; - xmlElementPtr elem; + xmlElementPtr elem = NULL; #ifdef DEBUG_SAX fprintf(stderr, "SAX.elementDecl(%s, %d, ...)\n", - name, type); + fullname, type); #endif - elem = xmlAddElementDecl(&ctxt->vctxt, ctxt->myDoc->intSubset, + if (ctxt->inSubset == 1) + elem = xmlAddElementDecl(&ctxt->vctxt, ctxt->myDoc->intSubset, name, type, content); - if (elem == 0) ctxt->valid = 0; + else if (ctxt->inSubset == 2) + elem = xmlAddElementDecl(&ctxt->vctxt, ctxt->myDoc->extSubset, + name, type, content); + else { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt, + "SAX.elementDecl(%s) called while not in subset\n", name); + return; + } + if (elem == NULL) ctxt->valid = 0; if (ctxt->validate && ctxt->wellFormed && ctxt->myDoc && ctxt->myDoc->intSubset) ctxt->valid &= xmlValidateElementDecl(&ctxt->vctxt, ctxt->myDoc, elem); @@ -396,15 +478,25 @@ notationDecl(void *ctx, const xmlChar *name, const xmlChar *publicId, const xmlChar *systemId) { xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) ctx; - xmlNotationPtr nota; + xmlNotationPtr nota = NULL; #ifdef DEBUG_SAX fprintf(stderr, "SAX.notationDecl(%s, %s, %s)\n", name, publicId, systemId); #endif - nota = xmlAddNotationDecl(&ctxt->vctxt, ctxt->myDoc->intSubset, name, + if (ctxt->inSubset == 1) + nota = xmlAddNotationDecl(&ctxt->vctxt, ctxt->myDoc->intSubset, name, publicId, systemId); - if (nota == 0) ctxt->valid = 0; + else if (ctxt->inSubset == 2) + nota = xmlAddNotationDecl(&ctxt->vctxt, ctxt->myDoc->intSubset, name, + publicId, systemId); + else { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt, + "SAX.notationDecl(%s) called while not in subset\n", name); + return; + } + if (nota == NULL) ctxt->valid = 0; if (ctxt->validate && ctxt->wellFormed && ctxt->myDoc && ctxt->myDoc->intSubset) ctxt->valid &= xmlValidateNotationDecl(&ctxt->vctxt, ctxt->myDoc, @@ -518,6 +610,7 @@ attribute(void *ctx, const xmlChar *fullname, const xmlChar *value) xmlAttrPtr ret; xmlChar *name; xmlChar *ns; + xmlChar *nval; xmlNsPtr namespace; /**************** @@ -528,7 +621,15 @@ attribute(void *ctx, const xmlChar *fullname, const xmlChar *value) /* * Split the full name into a namespace prefix and the tag name */ - name = xmlSplitQName(fullname, &ns); + name = xmlSplitQName(ctxt, fullname, &ns); + + /* + * Do the last stave of the attribute normalization + */ + nval = xmlValidNormalizeAttributeValue(ctxt->myDoc, + ctxt->node, fullname, value); + if (nval != NULL) + value = nval; /* * Check whether it's a namespace definition @@ -540,15 +641,28 @@ attribute(void *ctx, const xmlChar *fullname, const xmlChar *value) xmlNewNs(ctxt->node, value, NULL); if (name != NULL) xmlFree(name); + if (nval != NULL) + xmlFree(nval); return; } if ((ns != NULL) && (ns[0] == 'x') && (ns[1] == 'm') && (ns[2] == 'l') && (ns[3] == 'n') && (ns[4] == 's') && (ns[5] == 0)) { + /* + * Validate also for namespace decls, they are attributes from + * an XML-1.0 perspective + TODO ... doesn't map well with current API + if (ctxt->validate && ctxt->wellFormed && + ctxt->myDoc && ctxt->myDoc->intSubset) + ctxt->valid &= xmlValidateOneAttribute(&ctxt->vctxt, ctxt->myDoc, + ctxt->node, ret, value); + */ /* a standard namespace definition */ xmlNewNs(ctxt->node, value, name); xmlFree(ns); if (name != NULL) xmlFree(name); + if (nval != NULL) + xmlFree(nval); return; } @@ -562,17 +676,52 @@ attribute(void *ctx, const xmlChar *fullname, const xmlChar *value) ret = xmlNewNsProp(ctxt->node, namespace, name, NULL); if (ret != NULL) { - if ((ctxt->replaceEntities == 0) && (!ctxt->html)) - ret->val = xmlStringGetNodeList(ctxt->myDoc, value); - else - ret->val = xmlNewDocText(ctxt->myDoc, value); + if ((ctxt->replaceEntities == 0) && (!ctxt->html)) { + xmlNodePtr tmp; + + ret->children = xmlStringGetNodeList(ctxt->myDoc, value); + tmp = ret->children; + while (tmp != NULL) { + tmp->parent = (xmlNodePtr) ret; + if (tmp->next == NULL) + ret->last = tmp; + tmp = tmp->next; + } + } else { + ret->children = xmlNewDocText(ctxt->myDoc, value); + ret->last = ret->children; + if (ret->children != NULL) + ret->children->parent = (xmlNodePtr) ret; + } } if (ctxt->validate && ctxt->wellFormed && - ctxt->myDoc && ctxt->myDoc->intSubset) - ctxt->valid &= xmlValidateOneAttribute(&ctxt->vctxt, ctxt->myDoc, + ctxt->myDoc && ctxt->myDoc->intSubset) { + + /* + * If we don't substitute entities, the validation should be + * done on a value with replaced entities anyway. + */ + if (!ctxt->replaceEntities) { + xmlChar *val; + + ctxt->depth++; + val = xmlStringDecodeEntities(ctxt, value, XML_SUBSTITUTE_REF, + 0,0,0); + ctxt->depth--; + if (val == NULL) + ctxt->valid &= xmlValidateOneAttribute(&ctxt->vctxt, + ctxt->myDoc, ctxt->node, ret, value); + else { + ctxt->valid &= xmlValidateOneAttribute(&ctxt->vctxt, + ctxt->myDoc, ctxt->node, ret, val); + xmlFree(val); + } + } else { + ctxt->valid &= xmlValidateOneAttribute(&ctxt->vctxt, ctxt->myDoc, ctxt->node, ret, value); - else { + } + } else { /* * when validating, the ID registration is done at the attribute * validation level. Otherwise we have to do specific handling here. @@ -583,6 +732,8 @@ attribute(void *ctx, const xmlChar *fullname, const xmlChar *value) xmlAddRef(&ctxt->vctxt, ctxt->myDoc, value, ret); } + if (nval != NULL) + xmlFree(nval); if (name != NULL) xmlFree(name); if (ns != NULL) @@ -634,7 +785,7 @@ startElement(void *ctx, const xmlChar *fullname, const xmlChar **atts) /* * Split the full name into a namespace prefix and the tag name */ - name = xmlSplitQName(fullname, &prefix); + name = xmlSplitQName(ctxt, fullname, &prefix); /* @@ -644,13 +795,13 @@ startElement(void *ctx, const xmlChar *fullname, const xmlChar **atts) */ ret = xmlNewDocNode(ctxt->myDoc, NULL, name, NULL); if (ret == NULL) return; - if (ctxt->myDoc->root == NULL) { + if (ctxt->myDoc->children == NULL) { #ifdef DEBUG_SAX_TREE fprintf(stderr, "Setting %s as root\n", name); #endif - ctxt->myDoc->root = ret; + xmlAddChild((xmlNodePtr) ctxt->myDoc, (xmlNodePtr) ret); } else if (parent == NULL) { - parent = ctxt->myDoc->root; + parent = ctxt->myDoc->children; } /* @@ -679,6 +830,15 @@ startElement(void *ctx, const xmlChar *fullname, const xmlChar **atts) } } + /* + * If it's the Document root, finish the Dtd validation and + * check the document root element for validity + */ + if ((ctxt->validate) && (ctxt->vctxt.finishDtd == 0)) { + ctxt->valid &= xmlValidateDtdFinal(&ctxt->vctxt, ctxt->myDoc); + ctxt->valid &= xmlValidateRoot(&ctxt->vctxt, ctxt->myDoc); + ctxt->vctxt.finishDtd = 1; + } /* * process all the attributes whose name start with "xml" */ @@ -790,7 +950,10 @@ reference(void *ctx, const xmlChar *name) #ifdef DEBUG_SAX fprintf(stderr, "SAX.reference(%s)\n", name); #endif - ret = xmlNewReference(ctxt->myDoc, name); + if (name[0] == '#') + ret = xmlNewCharRef(ctxt->myDoc, name); + else + ret = xmlNewReference(ctxt->myDoc, name); #ifdef DEBUG_SAX_TREE fprintf(stderr, "add reference %s to %s \n", name, ctxt->node->name); #endif @@ -884,30 +1047,34 @@ processingInstruction(void *ctx, const xmlChar *target, ret = xmlNewPI(target, data); if (ret == NULL) return; - ret->doc = ctxt->myDoc; - if (ctxt->myDoc->root == NULL) { + parent = ctxt->node; + + if (ctxt->inSubset == 1) { + xmlAddChild((xmlNodePtr) ctxt->myDoc->intSubset, ret); + return; + } else if (ctxt->inSubset == 2) { + xmlAddChild((xmlNodePtr) ctxt->myDoc->extSubset, ret); + return; + } + if ((ctxt->myDoc->children == NULL) || (parent == NULL)) { #ifdef DEBUG_SAX_TREE fprintf(stderr, "Setting PI %s as root\n", target); #endif - ctxt->myDoc->root = ret; - } else if (parent == NULL) { - parent = ctxt->myDoc->root; + xmlAddChild((xmlNodePtr) ctxt->myDoc, (xmlNodePtr) ret); + return; } - if (parent != NULL) { - if (parent->type == XML_ELEMENT_NODE) { + if (parent->type == XML_ELEMENT_NODE) { #ifdef DEBUG_SAX_TREE - fprintf(stderr, "adding PI child %s to %s\n", target, parent->name); + fprintf(stderr, "adding PI %s child to %s\n", target, parent->name); #endif - xmlAddChild(parent, ret); - } else { + xmlAddChild(parent, ret); + } else { #ifdef DEBUG_SAX_TREE - fprintf(stderr, "adding PI sibling %s to ", target); - xmlDebugDumpOneNode(stderr, parent, 0); + fprintf(stderr, "adding PI %s sibling to ", target); + xmlDebugDumpOneNode(stderr, parent, 0); #endif - xmlAddSibling(parent, ret); - } + xmlAddSibling(parent, ret); } - } /** @@ -1064,27 +1231,31 @@ comment(void *ctx, const xmlChar *value) ret = xmlNewDocComment(ctxt->myDoc, value); if (ret == NULL) return; - if (ctxt->myDoc->root == NULL) { + if (ctxt->inSubset == 1) { + xmlAddChild((xmlNodePtr) ctxt->myDoc->intSubset, ret); + return; + } else if (ctxt->inSubset == 2) { + xmlAddChild((xmlNodePtr) ctxt->myDoc->extSubset, ret); + return; + } + if ((ctxt->myDoc->children == NULL) || (parent == NULL)) { #ifdef DEBUG_SAX_TREE fprintf(stderr, "Setting comment as root\n"); #endif - ctxt->myDoc->root = ret; - } else if (parent == NULL) { - parent = ctxt->myDoc->root; + xmlAddChild((xmlNodePtr) ctxt->myDoc, (xmlNodePtr) ret); + return; } - if (parent != NULL) { - if (parent->type == XML_ELEMENT_NODE) { + if (parent->type == XML_ELEMENT_NODE) { #ifdef DEBUG_SAX_TREE - fprintf(stderr, "adding comment child to %s\n", parent->name); + fprintf(stderr, "adding comment child to %s\n", parent->name); #endif - xmlAddChild(parent, ret); - } else { + xmlAddChild(parent, ret); + } else { #ifdef DEBUG_SAX_TREE - fprintf(stderr, "adding comment sibling to "); - xmlDebugDumpOneNode(stderr, parent, 0); + fprintf(stderr, "adding comment sibling to "); + xmlDebugDumpOneNode(stderr, parent, 0); #endif - xmlAddSibling(parent, ret); - } + xmlAddSibling(parent, ret); } } @@ -1148,6 +1319,7 @@ xmlSAXHandler xmlDefaultSAXHandler = { xmlParserError, getParameterEntity, cdataBlock, + externalSubset, }; /** @@ -1159,6 +1331,7 @@ void xmlDefaultSAXHandlerInit(void) { xmlDefaultSAXHandler.internalSubset = internalSubset; + xmlDefaultSAXHandler.externalSubset = externalSubset; xmlDefaultSAXHandler.isStandalone = isStandalone; xmlDefaultSAXHandler.hasInternalSubset = hasInternalSubset; xmlDefaultSAXHandler.hasExternalSubset = hasExternalSubset; @@ -1181,7 +1354,10 @@ xmlDefaultSAXHandlerInit(void) xmlDefaultSAXHandler.ignorableWhitespace = ignorableWhitespace; xmlDefaultSAXHandler.processingInstruction = processingInstruction; xmlDefaultSAXHandler.comment = comment; - xmlDefaultSAXHandler.warning = xmlParserWarning; + if (xmlGetWarningsDefaultValue == 0) + xmlDefaultSAXHandler.warning = NULL; + else + xmlDefaultSAXHandler.warning = xmlParserWarning; xmlDefaultSAXHandler.error = xmlParserError; xmlDefaultSAXHandler.fatalError = xmlParserError; } @@ -1216,6 +1392,7 @@ xmlSAXHandler htmlDefaultSAXHandler = { xmlParserError, getParameterEntity, NULL, + NULL, }; /** @@ -1227,6 +1404,7 @@ void htmlDefaultSAXHandlerInit(void) { htmlDefaultSAXHandler.internalSubset = NULL; + htmlDefaultSAXHandler.externalSubset = NULL; htmlDefaultSAXHandler.isStandalone = NULL; htmlDefaultSAXHandler.hasInternalSubset = NULL; htmlDefaultSAXHandler.hasExternalSubset = NULL; diff --git a/configure.in b/configure.in index d0555070..55d67a9d 100644 --- a/configure.in +++ b/configure.in @@ -3,9 +3,9 @@ AC_PREREQ(2.2) AC_INIT(entities.h) AM_CONFIG_HEADER(config.h) -LIBXML_MAJOR_VERSION=1 -LIBXML_MINOR_VERSION=8 -LIBXML_MICRO_VERSION=7 +LIBXML_MAJOR_VERSION=2 +LIBXML_MINOR_VERSION=0 +LIBXML_MICRO_VERSION=0 LIBXML_VERSION=$LIBXML_MAJOR_VERSION.$LIBXML_MINOR_VERSION.$LIBXML_MICRO_VERSION LIBXML_VERSION_INFO=`expr $LIBXML_MAJOR_VERSION + $LIBXML_MINOR_VERSION`:$LIBXML_MICRO_VERSION:$LIBXML_MINOR_VERSION @@ -15,7 +15,7 @@ AC_SUBST(LIBXML_MICRO_VERSION) AC_SUBST(LIBXML_VERSION) AC_SUBST(LIBXML_VERSION_INFO) -VERSION=$LIBXML_VERSION +VERSION=$LIBXML_VERSION-beta AM_INIT_AUTOMAKE(libxml, $VERSION) diff --git a/debugXML.c b/debugXML.c index 802f45e2..a872e88c 100644 --- a/debugXML.c +++ b/debugXML.c @@ -22,6 +22,7 @@ #include "xmlmemory.h" #include "tree.h" #include "parser.h" +#include "valid.h" #include "debugXML.h" #include "HTMLtree.h" #include "HTMLparser.h" @@ -38,6 +39,315 @@ void xmlDebugDumpString(FILE *output, const xmlChar *str) { fprintf(output, "..."); } +void xmlDebugDumpDtd(FILE *output, xmlDtdPtr dtd, int depth) { + int i; + char shift[100]; + + for (i = 0;((i < depth) && (i < 25));i++) + shift[2 * i] = shift[2 * i + 1] = ' '; + shift[2 * i] = shift[2 * i + 1] = 0; + + fprintf(output, shift); + + if (dtd->type != XML_DTD_NODE) { + fprintf(output, "PBM: not a DTD\n"); + return; + } + if (dtd->name != NULL) + fprintf(output, "DTD(%s)", dtd->name); + else + fprintf(output, "DTD"); + if (dtd->ExternalID != NULL) + fprintf(output, ", PUBLIC %s", dtd->ExternalID); + if (dtd->SystemID != NULL) + fprintf(output, ", SYSTEM %s", dtd->SystemID); + fprintf(output, "\n"); + /* + * Do a bit of checking + */ + if (dtd->parent == NULL) + fprintf(output, "PBM: Dtd has no parent\n"); + if (dtd->doc == NULL) + fprintf(output, "PBM: Dtd has no doc\n"); + if ((dtd->parent != NULL) && (dtd->doc != dtd->parent->doc)) + fprintf(output, "PBM: Dtd doc differs from parent's one\n"); + if (dtd->prev == NULL) { + if ((dtd->parent != NULL) && (dtd->parent->children != (xmlNodePtr)dtd)) + fprintf(output, "PBM: Dtd has no prev and not first of list\n"); + } else { + if (dtd->prev->next != (xmlNodePtr) dtd) + fprintf(output, "PBM: Dtd prev->next : back link wrong\n"); + } + if (dtd->next == NULL) { + if ((dtd->parent != NULL) && (dtd->parent->last != (xmlNodePtr) dtd)) + fprintf(output, "PBM: Dtd has no next and not last of list\n"); + } else { + if (dtd->next->prev != (xmlNodePtr) dtd) + fprintf(output, "PBM: Dtd next->prev : forward link wrong\n"); + } +} + +void xmlDebugDumpAttrDecl(FILE *output, xmlAttributePtr attr, int depth) { + int i; + char shift[100]; + + for (i = 0;((i < depth) && (i < 25));i++) + shift[2 * i] = shift[2 * i + 1] = ' '; + shift[2 * i] = shift[2 * i + 1] = 0; + + fprintf(output, shift); + + if (attr->type != XML_ATTRIBUTE_DECL) { + fprintf(output, "PBM: not a Attr\n"); + return; + } + if (attr->name != NULL) + fprintf(output, "ATTRDECL(%s)", attr->name); + else + fprintf(output, "PBM ATTRDECL noname!!!"); + if (attr->elem != NULL) + fprintf(output, " for %s", attr->elem); + else + fprintf(output, " PBM noelem!!!"); + switch (attr->atype) { + case XML_ATTRIBUTE_CDATA: + fprintf(output, " CDATA"); + break; + case XML_ATTRIBUTE_ID: + fprintf(output, " ID"); + break; + case XML_ATTRIBUTE_IDREF: + fprintf(output, " IDREF"); + break; + case XML_ATTRIBUTE_IDREFS: + fprintf(output, " IDREFS"); + break; + case XML_ATTRIBUTE_ENTITY: + fprintf(output, " ENTITY"); + break; + case XML_ATTRIBUTE_ENTITIES: + fprintf(output, " ENTITIES"); + break; + case XML_ATTRIBUTE_NMTOKEN: + fprintf(output, " NMTOKEN"); + break; + case XML_ATTRIBUTE_NMTOKENS: + fprintf(output, " NMTOKENS"); + break; + case XML_ATTRIBUTE_ENUMERATION: + fprintf(output, " ENUMERATION"); + break; + case XML_ATTRIBUTE_NOTATION: + fprintf(output, " NOTATION "); + break; + } + if (attr->tree != NULL) { + int i; + xmlEnumerationPtr cur = attr->tree; + + for (i = 0;i < 5; i++) { + if (i != 0) + fprintf(output, "|%s", cur->name); + else + fprintf(output, " (%s", cur->name); + cur = cur->next; + if (cur == NULL) break; + } + if (cur == NULL) + fprintf(output, ")"); + else + fprintf(output, "...)"); + } + switch (attr->def) { + case XML_ATTRIBUTE_NONE: + break; + case XML_ATTRIBUTE_REQUIRED: + fprintf(output, " REQUIRED"); + break; + case XML_ATTRIBUTE_IMPLIED: + fprintf(output, " IMPLIED"); + break; + case XML_ATTRIBUTE_FIXED: + fprintf(output, " FIXED"); + break; + } + if (attr->defaultValue != NULL) { + fprintf(output, "\""); + xmlDebugDumpString(output, attr->defaultValue); + fprintf(output, "\""); + } + printf("\n"); + + /* + * Do a bit of checking + */ + if (attr->parent == NULL) + fprintf(output, "PBM: Attr has no parent\n"); + if (attr->doc == NULL) + fprintf(output, "PBM: Attr has no doc\n"); + if ((attr->parent != NULL) && (attr->doc != attr->parent->doc)) + fprintf(output, "PBM: Attr doc differs from parent's one\n"); + if (attr->prev == NULL) { + if ((attr->parent != NULL) && (attr->parent->children != (xmlNodePtr)attr)) + fprintf(output, "PBM: Attr has no prev and not first of list\n"); + } else { + if (attr->prev->next != (xmlNodePtr) attr) + fprintf(output, "PBM: Attr prev->next : back link wrong\n"); + } + if (attr->next == NULL) { + if ((attr->parent != NULL) && (attr->parent->last != (xmlNodePtr) attr)) + fprintf(output, "PBM: Attr has no next and not last of list\n"); + } else { + if (attr->next->prev != (xmlNodePtr) attr) + fprintf(output, "PBM: Attr next->prev : forward link wrong\n"); + } +} + +void xmlDebugDumpElemDecl(FILE *output, xmlElementPtr elem, int depth) { + int i; + char shift[100]; + + for (i = 0;((i < depth) && (i < 25));i++) + shift[2 * i] = shift[2 * i + 1] = ' '; + shift[2 * i] = shift[2 * i + 1] = 0; + + fprintf(output, shift); + + if (elem->type != XML_ELEMENT_DECL) { + fprintf(output, "PBM: not a Elem\n"); + return; + } + if (elem->name != NULL) + fprintf(output, "ELEMDECL(%s)", elem->name); + else + fprintf(output, "PBM ELEMDECL noname!!!"); + switch (elem->etype) { + case XML_ELEMENT_TYPE_EMPTY: + fprintf(output, ", EMPTY"); + break; + case XML_ELEMENT_TYPE_ANY: + fprintf(output, ", ANY"); + break; + case XML_ELEMENT_TYPE_MIXED: + fprintf(output, ", MIXED "); + break; + case XML_ELEMENT_TYPE_ELEMENT: + fprintf(output, ", MIXED "); + break; + } + if (elem->content != NULL) { + char buf[1001]; + + buf[0] = 0; + xmlSprintfElementContent(buf, elem->content, 1); + buf[1000] = 0; + fprintf(output, "%s", buf); + } + printf("\n"); + + /* + * Do a bit of checking + */ + if (elem->parent == NULL) + fprintf(output, "PBM: Elem has no parent\n"); + if (elem->doc == NULL) + fprintf(output, "PBM: Elem has no doc\n"); + if ((elem->parent != NULL) && (elem->doc != elem->parent->doc)) + fprintf(output, "PBM: Elem doc differs from parent's one\n"); + if (elem->prev == NULL) { + if ((elem->parent != NULL) && (elem->parent->children != (xmlNodePtr)elem)) + fprintf(output, "PBM: Elem has no prev and not first of list\n"); + } else { + if (elem->prev->next != (xmlNodePtr) elem) + fprintf(output, "PBM: Elem prev->next : back link wrong\n"); + } + if (elem->next == NULL) { + if ((elem->parent != NULL) && (elem->parent->last != (xmlNodePtr) elem)) + fprintf(output, "PBM: Elem has no next and not last of list\n"); + } else { + if (elem->next->prev != (xmlNodePtr) elem) + fprintf(output, "PBM: Elem next->prev : forward link wrong\n"); + } +} + +void xmlDebugDumpEntityDecl(FILE *output, xmlEntityPtr ent, int depth) { + int i; + char shift[100]; + + for (i = 0;((i < depth) && (i < 25));i++) + shift[2 * i] = shift[2 * i + 1] = ' '; + shift[2 * i] = shift[2 * i + 1] = 0; + + fprintf(output, shift); + + if (ent->type != XML_ENTITY_DECL) { + fprintf(output, "PBM: not a Entity decl\n"); + return; + } + if (ent->name != NULL) + fprintf(output, "ENTITYDECL(%s)", ent->name); + else + fprintf(output, "PBM ENTITYDECL noname!!!"); + switch (ent->etype) { + case XML_INTERNAL_GENERAL_ENTITY: + fprintf(output, ", internal\n"); + break; + case XML_EXTERNAL_GENERAL_PARSED_ENTITY: + fprintf(output, ", external parsed\n"); + break; + case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: + fprintf(output, ", unparsed\n"); + break; + case XML_INTERNAL_PARAMETER_ENTITY: + fprintf(output, ", parameter\n"); + break; + case XML_EXTERNAL_PARAMETER_ENTITY: + fprintf(output, ", external parameter\n"); + break; + case XML_INTERNAL_PREDEFINED_ENTITY: + fprintf(output, ", predefined\n"); + break; + } + if (ent->ExternalID) { + fprintf(output, shift); + fprintf(output, "ExternalID=%s\n", ent->ExternalID); + } + if (ent->SystemID) { + fprintf(output, shift); + fprintf(output, "SystemID=%s\n", ent->SystemID); + } + if (ent->content) { + fprintf(output, shift); + fprintf(output, "content="); + xmlDebugDumpString(output, ent->content); + fprintf(output, "\n"); + } + + /* + * Do a bit of checking + */ + if (ent->parent == NULL) + fprintf(output, "PBM: Ent has no parent\n"); + if (ent->doc == NULL) + fprintf(output, "PBM: Ent has no doc\n"); + if ((ent->parent != NULL) && (ent->doc != ent->parent->doc)) + fprintf(output, "PBM: Ent doc differs from parent's one\n"); + if (ent->prev == NULL) { + if ((ent->parent != NULL) && (ent->parent->children != (xmlNodePtr)ent)) + fprintf(output, "PBM: Ent has no prev and not first of list\n"); + } else { + if (ent->prev->next != (xmlNodePtr) ent) + fprintf(output, "PBM: Ent prev->next : back link wrong\n"); + } + if (ent->next == NULL) { + if ((ent->parent != NULL) && (ent->parent->last != (xmlNodePtr) ent)) + fprintf(output, "PBM: Ent has no next and not last of list\n"); + } else { + if (ent->next->prev != (xmlNodePtr) ent) + fprintf(output, "PBM: Ent next->prev : forward link wrong\n"); + } +} + void xmlDebugDumpNamespace(FILE *output, xmlNsPtr ns, int depth) { int i; char shift[100]; @@ -74,7 +384,7 @@ void xmlDebugDumpEntity(FILE *output, xmlEntityPtr ent, int depth) { shift[2 * i] = shift[2 * i + 1] = 0; fprintf(output, shift); - switch (ent->type) { + switch (ent->etype) { case XML_INTERNAL_GENERAL_ENTITY: fprintf(output, "INTERNAL_GENERAL_ENTITY "); break; @@ -91,7 +401,7 @@ void xmlDebugDumpEntity(FILE *output, xmlEntityPtr ent, int depth) { fprintf(output, "EXTERNAL_PARAMETER_ENTITY "); break; default: - fprintf(output, "ENTITY_%d ! ", ent->type); + fprintf(output, "ENTITY_%d ! ", ent->etype); } fprintf(output, "%s\n", ent->name); if (ent->ExternalID) { @@ -119,9 +429,31 @@ void xmlDebugDumpAttr(FILE *output, xmlAttrPtr attr, int depth) { shift[2 * i] = shift[2 * i + 1] = 0; fprintf(output, shift); + fprintf(output, "ATTRIBUTE %s\n", attr->name); - if (attr->val != NULL) - xmlDebugDumpNodeList(output, attr->val, depth + 1); + if (attr->children != NULL) + xmlDebugDumpNodeList(output, attr->children, depth + 1); + + /* + * Do a bit of checking + */ + if (attr->parent == NULL) + fprintf(output, "PBM: Attr has no parent\n"); + if (attr->doc == NULL) + fprintf(output, "PBM: Attr has no doc\n"); + if ((attr->parent != NULL) && (attr->doc != attr->parent->doc)) + fprintf(output, "PBM: Attr doc differs from parent's one\n"); + if (attr->prev == NULL) { + if ((attr->parent != NULL) && (attr->parent->properties != attr)) + fprintf(output, "PBM: Attr has no prev and not first of list\n"); + } else { + if (attr->prev->next != attr) + fprintf(output, "PBM: Attr prev->next : back link wrong\n"); + } + if (attr->next != NULL) { + if (attr->next->prev != attr) + fprintf(output, "PBM: Attr next->prev : forward link wrong\n"); + } } void xmlDebugDumpAttrList(FILE *output, xmlAttrPtr attr, int depth) { @@ -139,9 +471,9 @@ void xmlDebugDumpOneNode(FILE *output, xmlNodePtr node, int depth) { shift[2 * i] = shift[2 * i + 1] = ' '; shift[2 * i] = shift[2 * i + 1] = 0; - fprintf(output, shift); switch (node->type) { case XML_ELEMENT_NODE: + fprintf(output, shift); fprintf(output, "ELEMENT "); if (node->ns != NULL) fprintf(output, "%s:%s\n", node->ns->prefix, node->name); @@ -149,40 +481,63 @@ void xmlDebugDumpOneNode(FILE *output, xmlNodePtr node, int depth) { fprintf(output, "%s\n", node->name); break; case XML_ATTRIBUTE_NODE: + fprintf(output, shift); fprintf(output, "Error, ATTRIBUTE found here\n"); break; case XML_TEXT_NODE: + fprintf(output, shift); fprintf(output, "TEXT\n"); break; case XML_CDATA_SECTION_NODE: + fprintf(output, shift); fprintf(output, "CDATA_SECTION\n"); break; case XML_ENTITY_REF_NODE: - fprintf(output, "ENTITY_REF\n"); + fprintf(output, shift); + fprintf(output, "ENTITY_REF(%s)\n", node->name); break; case XML_ENTITY_NODE: + fprintf(output, shift); fprintf(output, "ENTITY\n"); break; case XML_PI_NODE: + fprintf(output, shift); fprintf(output, "PI %s\n", node->name); break; case XML_COMMENT_NODE: + fprintf(output, shift); fprintf(output, "COMMENT\n"); break; case XML_DOCUMENT_NODE: case XML_HTML_DOCUMENT_NODE: + fprintf(output, shift); fprintf(output, "Error, DOCUMENT found here\n"); break; case XML_DOCUMENT_TYPE_NODE: + fprintf(output, shift); fprintf(output, "DOCUMENT_TYPE\n"); break; case XML_DOCUMENT_FRAG_NODE: + fprintf(output, shift); fprintf(output, "DOCUMENT_FRAG\n"); break; case XML_NOTATION_NODE: fprintf(output, "NOTATION\n"); break; + case XML_DTD_NODE: + xmlDebugDumpDtd(output, (xmlDtdPtr) node, depth); + return; + case XML_ELEMENT_DECL: + xmlDebugDumpElemDecl(output, (xmlElementPtr) node, depth); + return; + case XML_ATTRIBUTE_DECL: + xmlDebugDumpAttrDecl(output, (xmlAttributePtr) node, depth); + return; + case XML_ENTITY_DECL: + xmlDebugDumpEntityDecl(output, (xmlEntityPtr) node, depth); + return; default: + fprintf(output, shift); fprintf(output, "NODE_%d\n", node->type); } if (node->doc == NULL) { @@ -210,12 +565,35 @@ void xmlDebugDumpOneNode(FILE *output, xmlNodePtr node, int depth) { if (ent != NULL) xmlDebugDumpEntity(output, ent, depth + 1); } + /* + * Do a bit of checking + */ + if (node->parent == NULL) + fprintf(output, "PBM: Node has no parent\n"); + if (node->doc == NULL) + fprintf(output, "PBM: Node has no doc\n"); + if ((node->parent != NULL) && (node->doc != node->parent->doc)) + fprintf(output, "PBM: Node doc differs from parent's one\n"); + if (node->prev == NULL) { + if ((node->parent != NULL) && (node->parent->children != node)) + fprintf(output, "PBM: Node has no prev and not first of list\n"); + } else { + if (node->prev->next != node) + fprintf(output, "PBM: Node prev->next : back link wrong\n"); + } + if (node->next == NULL) { + if ((node->parent != NULL) && (node->parent->last != node)) + fprintf(output, "PBM: Node has no next and not last of list\n"); + } else { + if (node->next->prev != node) + fprintf(output, "PBM: Node next->prev : forward link wrong\n"); + } } void xmlDebugDumpNode(FILE *output, xmlNodePtr node, int depth) { xmlDebugDumpOneNode(output, node, depth); - if (node->childs != NULL) - xmlDebugDumpNodeList(output, node->childs, depth + 1); + if (node->children != NULL) + xmlDebugDumpNodeList(output, node->children, depth + 1); } void xmlDebugDumpNodeList(FILE *output, xmlNodePtr node, int depth) { @@ -306,8 +684,8 @@ void xmlDebugDumpDocument(FILE *output, xmlDocPtr doc) { xmlDebugDumpDocumentHead(output, doc); if (((doc->type == XML_DOCUMENT_NODE) || (doc->type == XML_HTML_DOCUMENT_NODE)) && - (doc->root != NULL)) - xmlDebugDumpNodeList(output, doc->root, 1); + (doc->children != NULL)) + xmlDebugDumpNodeList(output, doc->children, 1); } void xmlDebugDumpEntities(FILE *output, xmlDocPtr doc) { @@ -368,27 +746,27 @@ void xmlDebugDumpEntities(FILE *output, xmlDocPtr doc) { doc->intSubset->entities; fprintf(output, "Entities in internal subset\n"); for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; + cur = table->table[i]; fprintf(output, "%d : %s : ", i, cur->name); - switch (cur->type) { + switch (cur->etype) { case XML_INTERNAL_GENERAL_ENTITY: - fprintf(output, "INTERNAL GENERAL"); + fprintf(output, "INTERNAL GENERAL, "); break; case XML_EXTERNAL_GENERAL_PARSED_ENTITY: - fprintf(output, "EXTERNAL PARSED"); + fprintf(output, "EXTERNAL PARSED, "); break; case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: - fprintf(output, "EXTERNAL UNPARSED"); + fprintf(output, "EXTERNAL UNPARSED, "); break; case XML_INTERNAL_PARAMETER_ENTITY: - fprintf(output, "INTERNAL PARAMETER"); + fprintf(output, "INTERNAL PARAMETER, "); break; case XML_EXTERNAL_PARAMETER_ENTITY: - fprintf(output, "EXTERNAL PARAMETER"); + fprintf(output, "EXTERNAL PARAMETER, "); break; default: fprintf(output, "UNKNOWN TYPE %d", - cur->type); + cur->etype); } if (cur->ExternalID != NULL) fprintf(output, "ID \"%s\"", cur->ExternalID); @@ -407,27 +785,27 @@ void xmlDebugDumpEntities(FILE *output, xmlDocPtr doc) { doc->extSubset->entities; fprintf(output, "Entities in external subset\n"); for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; + cur = table->table[i]; fprintf(output, "%d : %s : ", i, cur->name); - switch (cur->type) { + switch (cur->etype) { case XML_INTERNAL_GENERAL_ENTITY: - fprintf(output, "INTERNAL GENERAL"); + fprintf(output, "INTERNAL GENERAL, "); break; case XML_EXTERNAL_GENERAL_PARSED_ENTITY: - fprintf(output, "EXTERNAL PARSED"); + fprintf(output, "EXTERNAL PARSED, "); break; case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: - fprintf(output, "EXTERNAL UNPARSED"); + fprintf(output, "EXTERNAL UNPARSED, "); break; case XML_INTERNAL_PARAMETER_ENTITY: - fprintf(output, "INTERNAL PARAMETER"); + fprintf(output, "INTERNAL PARAMETER, "); break; case XML_EXTERNAL_PARAMETER_ENTITY: - fprintf(output, "EXTERNAL PARAMETER"); + fprintf(output, "EXTERNAL PARAMETER, "); break; default: fprintf(output, "UNKNOWN TYPE %d", - cur->type); + cur->etype); } if (cur->ExternalID != NULL) fprintf(output, "ID \"%s\"", cur->ExternalID); @@ -449,14 +827,14 @@ static int xmlLsCountNode(xmlNodePtr node) { switch (node->type) { case XML_ELEMENT_NODE: - list = node->childs; + list = node->children; break; case XML_DOCUMENT_NODE: case XML_HTML_DOCUMENT_NODE: - list = ((xmlDocPtr) node)->root; + list = ((xmlDocPtr) node)->children; break; case XML_ATTRIBUTE_NODE: - list = ((xmlAttrPtr) node)->val; + list = ((xmlAttrPtr) node)->children; break; case XML_TEXT_NODE: case XML_CDATA_SECTION_NODE: @@ -475,6 +853,10 @@ static int xmlLsCountNode(xmlNodePtr node) { case XML_ENTITY_NODE: case XML_DOCUMENT_FRAG_NODE: case XML_NOTATION_NODE: + case XML_DTD_NODE: + case XML_ELEMENT_DECL: + case XML_ATTRIBUTE_DECL: + case XML_ENTITY_DECL: ret = 1; break; } @@ -621,9 +1003,9 @@ xmlShellList(xmlShellCtxtPtr ctxt, char *arg, xmlNodePtr node, if ((node->type == XML_DOCUMENT_NODE) || (node->type == XML_HTML_DOCUMENT_NODE)) { - cur = ((xmlDocPtr) node)->root; - } else if (node->childs != NULL) { - cur = node->childs; + cur = ((xmlDocPtr) node)->children; + } else if (node->children != NULL) { + cur = node->children; } else { xmlLsOneNode(stdout, node); return(0); @@ -910,10 +1292,10 @@ xmlShellDu(xmlShellCtxtPtr ctxt, char *arg, xmlNodePtr tree, if ((node->type == XML_DOCUMENT_NODE) || (node->type == XML_HTML_DOCUMENT_NODE)) { - node = ((xmlDocPtr) node)->root; - } else if (node->childs != NULL) { + node = ((xmlDocPtr) node)->children; + } else if (node->children != NULL) { /* deep first */ - node = node->childs; + node = node->children; indent++; } else if ((node != tree) && (node->next != NULL)) { /* then siblings */ @@ -1008,7 +1390,7 @@ xmlShellPwd(xmlShellCtxtPtr ctxt, char *buffer, xmlNodePtr node, } else if (cur->type == XML_ATTRIBUTE_NODE) { sep = '@'; name = (const char *) (((xmlAttrPtr) cur)->name); - next = ((xmlAttrPtr) cur)->node; + next = ((xmlAttrPtr) cur)->parent; } else { next = cur->parent; } diff --git a/encoding.c b/encoding.c index 12eed70f..f02f1978 100644 --- a/encoding.c +++ b/encoding.c @@ -35,14 +35,11 @@ #include #endif #include "encoding.h" -#ifdef HAVE_UNICODE_H -#include -#endif #include "xmlmemory.h" -#ifdef HAVE_UNICODE_H +xmlCharEncodingHandlerPtr xmlUTF16LEHandler = NULL; +xmlCharEncodingHandlerPtr xmlUTF16BEHandler = NULL; -#else /* ! HAVE_UNICODE_H */ /* * From rfc2044: encoding of the Unicode values on UTF-8: * @@ -54,6 +51,50 @@ * I hope we won't use values > 0xFFFF anytime soon ! */ +/** + * xmlCheckUTF8: Check utf-8 string for legality. + * @utf: Pointer to putative utf-8 encoded string. + * + * Checks @utf for being valid utf-8. @utf is assumed to be + * null-terminated. This function is not super-strict, as it will + * allow longer utf-8 sequences than necessary. Note that Java is + * capable of producing these sequences if provoked. Also note, this + * routine checks for the 4-byte maxiumum size, but does not check for + * 0x10ffff maximum value. + * + * Return value: true if @utf is valid. + **/ +int +xmlCheckUTF8(const unsigned char *utf) +{ + int ix; + unsigned char c; + + for (ix = 0; (c = utf[ix]);) { + if (c & 0x80) { + if ((utf[ix + 1] & 0xc0) != 0x80) + return(0); + if ((c & 0xe0) == 0xe0) { + if ((utf[ix + 2] & 0xc0) != 0x80) + return(0); + if ((c & 0xf0) == 0xf0) { + if ((c & 0xf8) != 0xf0 || (utf[ix + 3] & 0xc0) != 0x80) + return(0); + ix += 4; + /* 4-byte code */ + } else + /* 3-byte code */ + ix += 3; + } else + /* 2-byte code */ + ix += 2; + } else + /* 1-byte code */ + ix++; + } + return(1); +} + /** * isolat1ToUTF8: * @out: a pointer to an array of bytes to store the result @@ -66,27 +107,27 @@ * Returns the number of byte written, or -1 by lack of space. */ int -isolat1ToUTF8(unsigned char* out, int outlen, unsigned char* in, int inlen) -{ +isolat1ToUTF8(unsigned char* out, int outlen, + const unsigned char* in, int *inlen) { unsigned char* outstart= out; unsigned char* outend= out+outlen; - unsigned char* inend= in+inlen; + const unsigned char* inend= in+*inlen; unsigned char c; while (in < inend) { c= *in++; if (c < 0x80) { - if (out >= outend) return -1; + if (out >= outend) return(-1); *out++ = c; } else { - if (out >= outend) return -1; + if (out >= outend) return(-1); *out++ = 0xC0 | (c >> 6); - if (out >= outend) return -1; + if (out >= outend) return(-1); *out++ = 0x80 | (0x3F & c); } } - return out-outstart; + return(out-outstart); } /** @@ -101,138 +142,398 @@ isolat1ToUTF8(unsigned char* out, int outlen, unsigned char* in, int inlen) * TODO: UTF8Toisolat1 need a fallback mechanism ... * * Returns the number of byte written, or -1 by lack of space, or -2 - * if the transcoding failed. + * if the transcoding fails (for *in is not valid utf8 string or + * the result of transformation can't fit into the encoding we want) + * The value of @inlen after return is the number of octets consumed + * as the return value is positive, else unpredictiable. */ int -UTF8Toisolat1(unsigned char* out, int outlen, unsigned char* in, int inlen) -{ +UTF8Toisolat1(unsigned char* out, int outlen, + const unsigned char* in, int *inlen) { unsigned char* outstart= out; unsigned char* outend= out+outlen; - unsigned char* inend= in+inlen; + const unsigned char* inend= in+*inlen; unsigned char c; while (in < inend) { c= *in++; if (c < 0x80) { - if (out >= outend) return -1; + if (out >= outend) return(-1); *out++= c; } - else if (((c & 0xFE) == 0xC2) && in= outend) return -1; + else if (in == inend) { + *inlen -= 1; + break; + } + else if (((c & 0xFC) == 0xC0) && ((*in & 0xC0) == 0x80)) { + /* a two byte utf-8 and can be encoding as isolate1 */ *out++= ((c & 0x03) << 6) | (*in++ & 0x3F); - } - else return -2; + } + else + return(-2); + /* TODO : some should be represent as "&#x____;" */ } - return out-outstart; + return(out-outstart); } /** - * UTF16ToUTF8: + * UTF16LEToUTF8: * @out: a pointer to an array of bytes to store the result * @outlen: the length of @out - * @in: a pointer to an array of UTF-16 chars (array of unsigned shorts) - * @inlen: the length of @in + * @inb: a pointer to an array of UTF-16LE passwd as a byte array + * @inlenb: the length of @in in UTF-16LE chars * - * Take a block of UTF-16 ushorts in and try to convert it to an UTF-8 - * block of chars out. - * Returns the number of byte written, or -1 by lack of space. + * Take a block of UTF-16LE ushorts in and try to convert it to an UTF-8 + * block of chars out. This function assume the endian properity + * is the same between the native type of this machine and the + * inputed one. + * + * Returns the number of byte written, or -1 by lack of space, or -2 + * if the transcoding fails (for *in is not valid utf16 string) + * The value of *inlen after return is the number of octets consumed + * as the return value is positive, else unpredictiable. */ int -UTF16ToUTF8(unsigned char* out, int outlen, unsigned short* in, int inlen) +UTF16LEToUTF8(unsigned char* out, int outlen, + const unsigned char* inb, int *inlenb) { unsigned char* outstart= out; unsigned char* outend= out+outlen; - unsigned short* inend= in+inlen; - unsigned int c, d; + unsigned short* in = (unsigned short*) inb; + unsigned short* inend; + unsigned int c, d, inlen; + unsigned char *tmp; int bits; + if ((*inlenb % 2) == 1) + (*inlenb)--; + inlen = *inlenb / 2; + inend= in + inlen; while (in < inend) { +#ifdef BIG_ENDIAN + tmp = (unsigned char *) in; + c = *tmp++; + c = c | (((unsigned int)*tmp) << 8); + in++; +#else /* BIG_ENDIAN */ c= *in++; +#endif /* BIG_ENDIAN */ if ((c & 0xFC00) == 0xD800) { /* surrogates */ - if ((in= inend) { /* (in > inend) shouldn't happens */ + (*inlenb) -= 2; + break; + } +#ifdef BIG_ENDIAN + tmp = (unsigned char *) in; + d = *tmp++; + d = d | (((unsigned int)*tmp) << 8); + in++; +#else /* BIG_ENDIAN */ + d = *in++; +#endif /* BIG_ENDIAN */ + if ((d & 0xFC00) == 0xDC00) { c &= 0x03FF; c <<= 10; c |= d & 0x03FF; c += 0x10000; } - else return -1; + else + return(-2); } - /* assertion: c is a single UTF-4 value */ - - if (out >= outend) return -1; + /* assertion: c is a single UTF-4 value */ + if (out >= outend) + return(-1); if (c < 0x80) { *out++= c; bits= -6; } - else if (c < 0x800) { *out++= (c >> 6) | 0xC0; bits= 0; } - else if (c < 0x10000) { *out++= (c >> 12) | 0xE0; bits= 6; } - else { *out++= (c >> 18) | 0xF0; bits= 12; } + else if (c < 0x800) { *out++= ((c >> 6) & 0x1F) | 0xC0; bits= 0; } + else if (c < 0x10000) { *out++= ((c >> 12) & 0x0F) | 0xE0; bits= 6; } + else { *out++= ((c >> 18) & 0x07) | 0xF0; bits= 12; } - for ( ; bits > 0; bits-= 6) { - if (out >= outend) return -1; - *out++= (c >> bits) & 0x3F; + for ( ; bits >= 0; bits-= 6) { + if (out >= outend) + return(-1); + *out++= ((c >> bits) & 0x3F) | 0x80; } } - return out-outstart; + return(out-outstart); } /** - * UTF8ToUTF16: - * @out: a pointer to an array of shorts to store the result - * @outlen: the length of @out (number of shorts) + * UTF8ToUTF16LE: + * @outb: a pointer to an array of bytes to store the result + * @outlen: the length of @outb * @in: a pointer to an array of UTF-8 chars * @inlen: the length of @in * - * Take a block of UTF-8 chars in and try to convert it to an UTF-16 + * Take a block of UTF-8 chars in and try to convert it to an UTF-16LE * block of chars out. - * TODO: UTF8ToUTF16 need a fallback mechanism ... + * TODO: UTF8ToUTF16LE need a fallback mechanism ... * * Returns the number of byte written, or -1 by lack of space, or -2 - * if the transcoding failed. + * if the transcoding failed. */ int -UTF8ToUTF16(unsigned short* out, int outlen, unsigned char* in, int inlen) +UTF8ToUTF16LE(unsigned char* outb, int outlen, + const unsigned char* in, int *inlen) { + unsigned short* out = (unsigned short*) outb; unsigned short* outstart= out; - unsigned short* outend= out+outlen; - unsigned char* inend= in+inlen; + unsigned short* outend; + const unsigned char* inend= in+*inlen; unsigned int c, d, trailing; +#ifdef BIG_ENDIAN + unsigned char *tmp; + unsigned short tmp1, tmp2; +#endif /* BIG_ENDIAN */ + outlen /= 2; /* convert in short length */ + outend = out + outlen; while (in < inend) { d= *in++; if (d < 0x80) { c= d; trailing= 0; } - else if (d < 0xC0) return -2; /* trailing byte in leading position */ + else if (d < 0xC0) + return(-2); /* trailing byte in leading position */ else if (d < 0xE0) { c= d & 0x1F; trailing= 1; } else if (d < 0xF0) { c= d & 0x0F; trailing= 2; } else if (d < 0xF8) { c= d & 0x07; trailing= 3; } - else return -2; /* no chance for this in UTF-16 */ + else + return(-2); /* no chance for this in UTF-16 */ + + if (inend - in < trailing) { + *inlen -= (inend - in); + break; + } for ( ; trailing; trailing--) { - if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80)) return -1; + if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80)) + return(-1); c <<= 6; c |= d & 0x3F; } /* assertion: c is a single UTF-4 value */ if (c < 0x10000) { - if (out >= outend) return -1; + if (out >= outend) + return(-1); +#ifdef BIG_ENDIAN + tmp = (unsigned char *) out; + *tmp = c ; + *(tmp + 1) = c >> 8 ; + out++; +#else /* BIG_ENDIAN */ *out++ = c; +#endif /* BIG_ENDIAN */ } else if (c < 0x110000) { - if (out+1 >= outend) return -1; + if (out+1 >= outend) + return(-1); c -= 0x10000; +#ifdef BIG_ENDIAN + tmp1 = 0xD800 | (c >> 10); + tmp = (unsigned char *) out; + *tmp = tmp1; + *(tmp + 1) = tmp1 >> 8; + out++; + + tmp2 = 0xDC00 | (c & 0x03FF); + tmp = (unsigned char *) out; + *tmp = tmp2; + *(tmp + 1) = tmp2 >> 8; + out++; +#else /* BIG_ENDIAN */ *out++ = 0xD800 | (c >> 10); *out++ = 0xDC00 | (c & 0x03FF); +#endif /* BIG_ENDIAN */ } - else return -1; + else + return(-1); } - return out-outstart; + return(out-outstart); } -#endif /* ! HAVE_UNICODE_H */ +/** + * UTF16BEToUTF8: + * @out: a pointer to an array of bytes to store the result + * @outlen: the length of @out + * @inb: a pointer to an array of UTF-16 passwd as a byte array + * @inlenb: the length of @in in UTF-16 chars + * + * Take a block of UTF-16 ushorts in and try to convert it to an UTF-8 + * block of chars out. This function assume the endian properity + * is the same between the native type of this machine and the + * inputed one. + * + * Returns the number of byte written, or -1 by lack of space, or -2 + * if the transcoding fails (for *in is not valid utf16 string) + * The value of *inlen after return is the number of octets consumed + * as the return value is positive, else unpredictiable. + */ +int +UTF16BEToUTF8(unsigned char* out, int outlen, + const unsigned char* inb, int *inlenb) +{ + unsigned char* outstart= out; + unsigned char* outend= out+outlen; + unsigned short* in = (unsigned short*) inb; + unsigned short* inend; + unsigned int c, d, inlen; +#ifdef BIG_ENDIAN +#else /* BIG_ENDIAN */ + unsigned char *tmp; +#endif /* BIG_ENDIAN */ + int bits; + + if ((*inlenb % 2) == 1) + (*inlenb)--; + inlen = *inlenb / 2; + inend= in + inlen; + while (in < inend) { +#ifdef BIG_ENDIAN + c= *in++; +#else + tmp = (unsigned char *) in; + c = *tmp++; + c = c << 8; + c = c | (unsigned int) *tmp; + in++; +#endif + if ((c & 0xFC00) == 0xD800) { /* surrogates */ + if (in >= inend) { /* (in > inend) shouldn't happens */ + (*inlenb) -= 2; + break; + } + +#ifdef BIG_ENDIAN + d= *in++; +#else + tmp = (unsigned char *) in; + d = *tmp++; + d = d << 8; + d = d | (unsigned int) *tmp; + in++; +#endif + if ((d & 0xFC00) == 0xDC00) { + c &= 0x03FF; + c <<= 10; + c |= d & 0x03FF; + c += 0x10000; + } + else + return(-2); + } + + /* assertion: c is a single UTF-4 value */ + if (out >= outend) + return(-1); + if (c < 0x80) { *out++= c; bits= -6; } + else if (c < 0x800) { *out++= ((c >> 6) & 0x1F) | 0xC0; bits= 0; } + else if (c < 0x10000) { *out++= ((c >> 12) & 0x0F) | 0xE0; bits= 6; } + else { *out++= ((c >> 18) & 0x07) | 0xF0; bits= 12; } + + for ( ; bits >= 0; bits-= 6) { + if (out >= outend) + return(-1); + *out++= ((c >> bits) & 0x3F) | 0x80; + } + } + return(out-outstart); +} + +/** + * UTF8ToUTF16BE: + * @outb: a pointer to an array of bytes to store the result + * @outlen: the length of @outb + * @in: a pointer to an array of UTF-8 chars + * @inlen: the length of @in + * + * Take a block of UTF-8 chars in and try to convert it to an UTF-16BE + * block of chars out. + * TODO: UTF8ToUTF16BE need a fallback mechanism ... + * + * Returns the number of byte written, or -1 by lack of space, or -2 + * if the transcoding failed. + */ +int +UTF8ToUTF16BE(unsigned char* outb, int outlen, + const unsigned char* in, int *inlen) +{ + unsigned short* out = (unsigned short*) outb; + unsigned short* outstart= out; + unsigned short* outend; + const unsigned char* inend= in+*inlen; + unsigned int c, d, trailing; +#ifdef BIG_ENDIAN +#else + unsigned char *tmp; + unsigned short tmp1, tmp2; +#endif /* BIG_ENDIAN */ + + outlen /= 2; /* convert in short length */ + outend = out + outlen; + while (in < inend) { + d= *in++; + if (d < 0x80) { c= d; trailing= 0; } + else if (d < 0xC0) + return(-2); /* trailing byte in leading position */ + else if (d < 0xE0) { c= d & 0x1F; trailing= 1; } + else if (d < 0xF0) { c= d & 0x0F; trailing= 2; } + else if (d < 0xF8) { c= d & 0x07; trailing= 3; } + else + return(-2); /* no chance for this in UTF-16 */ + + if (inend - in < trailing) { + *inlen -= (inend - in); + break; + } + + for ( ; trailing; trailing--) { + if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80)) return(-1); + c <<= 6; + c |= d & 0x3F; + } + + /* assertion: c is a single UTF-4 value */ + if (c < 0x10000) { + if (out >= outend) return(-1); +#ifdef BIG_ENDIAN + *out++ = c; +#else + tmp = (unsigned char *) out; + *tmp = c >> 8; + *(tmp + 1) = c; + out++; +#endif /* BIG_ENDIAN */ + } + else if (c < 0x110000) { + if (out+1 >= outend) return(-1); + c -= 0x10000; +#ifdef BIG_ENDIAN + *out++ = 0xD800 | (c >> 10); + *out++ = 0xDC00 | (c & 0x03FF); +#else + tmp1 = 0xD800 | (c >> 10); + tmp = (unsigned char *) out; + *tmp = tmp1 >> 8; + *(tmp + 1) = tmp1; + out++; + + tmp2 = 0xDC00 | (c & 0x03FF); + tmp = (unsigned char *) out; + *tmp = tmp2 >> 8; + *(tmp + 1) = tmp2; + out++; +#endif + } + else return(-1); + } + return(out-outstart); +} /** * xmlDetectCharEncoding: * @in: a pointer to the first bytes of the XML entity, must be at least * 4 bytes long. + * @len: pointer to the length of the buffer * * Guess the encoding of the entity using the first bytes of the entity content * accordingly of the non-normative appendix F of the XML-1.0 recommendation. @@ -240,30 +541,34 @@ UTF8ToUTF16(unsigned short* out, int outlen, unsigned char* in, int inlen) * Returns one of the XML_CHAR_ENCODING_... values. */ xmlCharEncoding -xmlDetectCharEncoding(const unsigned char* in) +xmlDetectCharEncoding(const unsigned char* in, int len) { - if ((in[0] == 0x00) && (in[1] == 0x00) && - (in[2] == 0x00) && (in[3] == 0x3C)) - return(XML_CHAR_ENCODING_UCS4BE); - if ((in[0] == 0x3C) && (in[1] == 0x00) && - (in[2] == 0x00) && (in[3] == 0x00)) - return(XML_CHAR_ENCODING_UCS4LE); - if ((in[0] == 0x00) && (in[1] == 0x00) && - (in[2] == 0x3C) && (in[3] == 0x00)) - return(XML_CHAR_ENCODING_UCS4_2143); - if ((in[0] == 0x00) && (in[1] == 0x3C) && - (in[2] == 0x00) && (in[3] == 0x00)) - return(XML_CHAR_ENCODING_UCS4_3412); - if ((in[0] == 0xFE) && (in[1] == 0xFF)) - return(XML_CHAR_ENCODING_UTF16BE); - if ((in[0] == 0xFF) && (in[1] == 0xFE)) - return(XML_CHAR_ENCODING_UTF16LE); - if ((in[0] == 0x4C) && (in[1] == 0x6F) && - (in[2] == 0xA7) && (in[3] == 0x94)) - return(XML_CHAR_ENCODING_EBCDIC); - if ((in[0] == 0x3C) && (in[1] == 0x3F) && - (in[2] == 0x78) && (in[3] == 0x6D)) - return(XML_CHAR_ENCODING_UTF8); + if (len >= 4) { + if ((in[0] == 0x00) && (in[1] == 0x00) && + (in[2] == 0x00) && (in[3] == 0x3C)) + return(XML_CHAR_ENCODING_UCS4BE); + if ((in[0] == 0x3C) && (in[1] == 0x00) && + (in[2] == 0x00) && (in[3] == 0x00)) + return(XML_CHAR_ENCODING_UCS4LE); + if ((in[0] == 0x00) && (in[1] == 0x00) && + (in[2] == 0x3C) && (in[3] == 0x00)) + return(XML_CHAR_ENCODING_UCS4_2143); + if ((in[0] == 0x00) && (in[1] == 0x3C) && + (in[2] == 0x00) && (in[3] == 0x00)) + return(XML_CHAR_ENCODING_UCS4_3412); + if ((in[0] == 0x4C) && (in[1] == 0x6F) && + (in[2] == 0xA7) && (in[3] == 0x94)) + return(XML_CHAR_ENCODING_EBCDIC); + if ((in[0] == 0x3C) && (in[1] == 0x3F) && + (in[2] == 0x78) && (in[3] == 0x6D)) + return(XML_CHAR_ENCODING_UTF8); + } + if (len >= 2) { + if ((in[0] == 0xFE) && (in[1] == 0xFF)) + return(XML_CHAR_ENCODING_UTF16BE); + if ((in[0] == 0xFF) && (in[1] == 0xFE)) + return(XML_CHAR_ENCODING_UTF16LE); + } return(XML_CHAR_ENCODING_NONE); } @@ -364,7 +669,8 @@ static xmlCharEncodingHandlerPtr xmlDefaultCharEncodingHandler = NULL; * Returns the xmlCharEncodingHandlerPtr created (or NULL in case of error). */ xmlCharEncodingHandlerPtr -xmlNewCharEncodingHandler(const char *name, xmlCharEncodingInputFunc input, +xmlNewCharEncodingHandler(const char *name, + xmlCharEncodingInputFunc input, xmlCharEncodingOutputFunc output) { xmlCharEncodingHandlerPtr handler; char upper[500]; @@ -429,11 +735,11 @@ xmlInitCharEncodingHandlers(void) { return; } xmlNewCharEncodingHandler("UTF-8", NULL, NULL); -#ifdef HAVE_UNICODE_H -#else - /* xmlNewCharEncodingHandler("UTF-16", UTF16ToUTF8, UTF8ToUTF16); */ + xmlUTF16LEHandler = + xmlNewCharEncodingHandler("UTF-16LE", UTF16LEToUTF8, UTF8ToUTF16LE); + xmlUTF16BEHandler = + xmlNewCharEncodingHandler("UTF-16BE", UTF16BEToUTF8, UTF8ToUTF16BE); xmlNewCharEncodingHandler("ISO-8859-1", isolat1ToUTF8, UTF8Toisolat1); -#endif } /** @@ -493,7 +799,52 @@ xmlRegisterCharEncodingHandler(xmlCharEncodingHandlerPtr handler) { xmlCharEncodingHandlerPtr xmlGetCharEncodingHandler(xmlCharEncoding enc) { if (handlers == NULL) xmlInitCharEncodingHandlers(); - /* TODO xmlGetCharEncodingHandler !!!!!!! */ + switch (enc) { + case XML_CHAR_ENCODING_ERROR: + return(NULL); + case XML_CHAR_ENCODING_NONE: + return(NULL); + case XML_CHAR_ENCODING_UTF8: + return(NULL); + case XML_CHAR_ENCODING_UTF16LE: + return(xmlUTF16LEHandler); + case XML_CHAR_ENCODING_UTF16BE: + return(xmlUTF16BEHandler); + case XML_CHAR_ENCODING_EBCDIC: + return(NULL); + case XML_CHAR_ENCODING_UCS4LE: + return(NULL); + case XML_CHAR_ENCODING_UCS4BE: + return(NULL); + case XML_CHAR_ENCODING_UCS4_2143: + return(NULL); + case XML_CHAR_ENCODING_UCS4_3412: + return(NULL); + case XML_CHAR_ENCODING_UCS2: + return(NULL); + case XML_CHAR_ENCODING_8859_1: + return(NULL); + case XML_CHAR_ENCODING_8859_2: + return(NULL); + case XML_CHAR_ENCODING_8859_3: + return(NULL); + case XML_CHAR_ENCODING_8859_4: + return(NULL); + case XML_CHAR_ENCODING_8859_5: + return(NULL); + case XML_CHAR_ENCODING_8859_6: + return(NULL); + case XML_CHAR_ENCODING_8859_7: + return(NULL); + case XML_CHAR_ENCODING_8859_8: + return(NULL); + case XML_CHAR_ENCODING_8859_9: + return(NULL); + case XML_CHAR_ENCODING_2022_JP: + case XML_CHAR_ENCODING_SHIFT_JIS: + case XML_CHAR_ENCODING_EUC_JP: + return(NULL); + } return(NULL); } diff --git a/encoding.h b/encoding.h index 5eb1a52f..12a79108 100644 --- a/encoding.h +++ b/encoding.h @@ -67,11 +67,11 @@ typedef enum { * Returns the number of byte written, or -1 by lack of space. */ typedef int (* xmlCharEncodingInputFunc)(unsigned char* out, int outlen, - unsigned char* in, int inlen); + const unsigned char* in, int *inlen); /** - * xmlCharEncodingInputFunc: + * xmlCharEncodingOutputFunc: * @out: a pointer ot an array of bytes to store the result * @outlen: the lenght of @out * @in: a pointer ot an array of UTF-8 chars @@ -84,7 +84,7 @@ typedef int (* xmlCharEncodingInputFunc)(unsigned char* out, int outlen, * if the transcoding failed. */ typedef int (* xmlCharEncodingOutputFunc)(unsigned char* out, int outlen, - unsigned char* in, int inlen); + const unsigned char* in, int *inlen); /* * Block defining the handlers for non UTF-8 encodings. @@ -101,10 +101,12 @@ struct _xmlCharEncodingHandler { void xmlInitCharEncodingHandlers (void); void xmlCleanupCharEncodingHandlers (void); void xmlRegisterCharEncodingHandler (xmlCharEncodingHandlerPtr handler); -xmlCharEncoding xmlDetectCharEncoding (const unsigned char* in); +xmlCharEncoding xmlDetectCharEncoding (const unsigned char* in, + int len); xmlCharEncoding xmlParseCharEncoding (const char* name); xmlCharEncodingHandlerPtr xmlGetCharEncodingHandler(xmlCharEncoding enc); xmlCharEncodingHandlerPtr xmlFindCharEncodingHandler(const char *name); +int xmlCheckUTF8 (const unsigned char *utf); #ifdef __cplusplus diff --git a/entities.c b/entities.c index d6580cfe..d9cefed6 100644 --- a/entities.c +++ b/entities.c @@ -21,6 +21,8 @@ #include "entities.h" #include "parser.h" +#define DEBUG_ENT_REF /* debugging of cross entities dependancies */ + /* * The XML predefined entities. */ @@ -45,6 +47,8 @@ xmlEntitiesTablePtr xmlPredefinedEntities = NULL; void xmlFreeEntity(xmlEntityPtr entity) { if (entity == NULL) return; + if (entity->children) + xmlFreeNodeList(entity->children); if (entity->name != NULL) xmlFree((char *) entity->name); if (entity->ExternalID != NULL) @@ -55,22 +59,31 @@ void xmlFreeEntity(xmlEntityPtr entity) { xmlFree((char *) entity->content); if (entity->orig != NULL) xmlFree((char *) entity->orig); +#ifdef WITH_EXTRA_ENT_DETECT + if (entity->entTab != NULL) { + int i; + + for (i = 0; i < entity->entNr; i++) + xmlFree(entity->entTab[i]); + xmlFree(entity->entTab); + } +#endif memset(entity, -1, sizeof(xmlEntity)); + xmlFree(entity); } /* * xmlAddEntity : register a new entity for an entities table. */ -static void +static xmlEntityPtr xmlAddEntity(xmlEntitiesTablePtr table, const xmlChar *name, int type, const xmlChar *ExternalID, const xmlChar *SystemID, const xmlChar *content) { int i; - xmlEntityPtr cur; - int len; + xmlEntityPtr ret; for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; - if (!xmlStrcmp(cur->name, name)) { + ret = table->table[i]; + if (!xmlStrcmp(ret->name, name)) { /* * The entity is already defined in this Dtd, the spec says to NOT * override it ... Is it worth a Warning ??? !!! @@ -78,15 +91,15 @@ xmlAddEntity(xmlEntitiesTablePtr table, const xmlChar *name, int type, */ if (((type == XML_INTERNAL_PARAMETER_ENTITY) || (type == XML_EXTERNAL_PARAMETER_ENTITY)) && - ((cur->type == XML_INTERNAL_PARAMETER_ENTITY) || - (cur->type == XML_EXTERNAL_PARAMETER_ENTITY))) - return; + ((ret->etype == XML_INTERNAL_PARAMETER_ENTITY) || + (ret->etype == XML_EXTERNAL_PARAMETER_ENTITY))) + return(NULL); else if (((type != XML_INTERNAL_PARAMETER_ENTITY) && (type != XML_EXTERNAL_PARAMETER_ENTITY)) && - ((cur->type != XML_INTERNAL_PARAMETER_ENTITY) && - (cur->type != XML_EXTERNAL_PARAMETER_ENTITY))) - return; + ((ret->etype != XML_INTERNAL_PARAMETER_ENTITY) && + (ret->etype != XML_EXTERNAL_PARAMETER_ENTITY))) + return(NULL); } } if (table->nb_entities >= table->max_entities) { @@ -94,35 +107,43 @@ xmlAddEntity(xmlEntitiesTablePtr table, const xmlChar *name, int type, * need more elements. */ table->max_entities *= 2; - table->table = (xmlEntityPtr) - xmlRealloc(table->table, table->max_entities * sizeof(xmlEntity)); + table->table = (xmlEntityPtr *) + xmlRealloc(table->table, + table->max_entities * sizeof(xmlEntityPtr)); if (table->table == NULL) { perror("realloc failed"); - return; + return(NULL); } } - cur = &table->table[table->nb_entities]; - cur->name = xmlStrdup(name); - for (len = 0;name[0] != 0;name++)len++; - cur->len = len; - cur->type = type; - if (ExternalID != NULL) - cur->ExternalID = xmlStrdup(ExternalID); - else - cur->ExternalID = NULL; - if (SystemID != NULL) - cur->SystemID = xmlStrdup(SystemID); - else - cur->SystemID = NULL; - if (content != NULL) { - cur->length = xmlStrlen(content); - cur->content = xmlStrndup(content, cur->length); - } else { - cur->length = 0; - cur->content = NULL; + ret = (xmlEntityPtr) xmlMalloc(sizeof(xmlEntity)); + if (ret == NULL) { + fprintf(stderr, "xmlAddEntity: out of memory\n"); + return(NULL); } - cur->orig = NULL; + memset(ret, 0, sizeof(xmlEntity)); + ret->type = XML_ENTITY_DECL; + table->table[table->nb_entities] = ret; + + /* + * fill the structure. + */ + ret->name = xmlStrdup(name); + ret->etype = type; + if (ExternalID != NULL) + ret->ExternalID = xmlStrdup(ExternalID); + if (SystemID != NULL) + ret->SystemID = xmlStrdup(SystemID); + if (content != NULL) { + ret->length = xmlStrlen(content); + ret->content = xmlStrndup(content, ret->length); + } else { + ret->length = 0; + ret->content = NULL; + } + ret->orig = NULL; table->nb_entities++; + + return(ret); } /** @@ -182,7 +203,7 @@ xmlGetPredefinedEntity(const xmlChar *name) { if (xmlPredefinedEntities == NULL) xmlInitializePredefinedEntities(); for (i = 0;i < xmlPredefinedEntities->nb_entities;i++) { - cur = &xmlPredefinedEntities->table[i]; + cur = xmlPredefinedEntities->table[i]; if (!xmlStrcmp(cur->name, name)) return(cur); } return(NULL); @@ -197,24 +218,50 @@ xmlGetPredefinedEntity(const xmlChar *name) { * @SystemID: the entity system ID if available * @content: the entity content * - * Register a new entity for this document DTD. + * Register a new entity for this document DTD external subset. + * + * Returns a pointer to the entity or NULL in case of error */ -void +xmlEntityPtr xmlAddDtdEntity(xmlDocPtr doc, const xmlChar *name, int type, - const xmlChar *ExternalID, const xmlChar *SystemID, const xmlChar *content) { + const xmlChar *ExternalID, const xmlChar *SystemID, + const xmlChar *content) { xmlEntitiesTablePtr table; + xmlEntityPtr ret; + xmlDtdPtr dtd; + if (doc == NULL) { + fprintf(stderr, + "xmlAddDtdEntity: doc == NULL !\n"); + return(NULL); + } if (doc->extSubset == NULL) { fprintf(stderr, "xmlAddDtdEntity: document without external subset !\n"); - return; + return(NULL); } - table = (xmlEntitiesTablePtr) doc->extSubset->entities; + dtd = doc->extSubset; + table = (xmlEntitiesTablePtr) dtd->entities; if (table == NULL) { table = xmlCreateEntitiesTable(); - doc->extSubset->entities = table; + dtd->entities = table; } - xmlAddEntity(table, name, type, ExternalID, SystemID, content); + ret = xmlAddEntity(table, name, type, ExternalID, SystemID, content); + if (ret == NULL) return(NULL); + + /* + * Link it to the Dtd + */ + ret->parent = dtd; + ret->doc = dtd->doc; + if (dtd->last == NULL) { + dtd->children = dtd->last = (xmlNodePtr) ret; + } else { + dtd->last->next = (xmlNodePtr) ret; + ret->prev = dtd->last; + dtd->last = (xmlNodePtr) ret; + } + return(ret); } /** @@ -227,30 +274,187 @@ xmlAddDtdEntity(xmlDocPtr doc, const xmlChar *name, int type, * @content: the entity content * * Register a new entity for this document. + * + * Returns a pointer to the entity or NULL in case of error */ -void +xmlEntityPtr xmlAddDocEntity(xmlDocPtr doc, const xmlChar *name, int type, - const xmlChar *ExternalID, const xmlChar *SystemID, const xmlChar *content) { + const xmlChar *ExternalID, const xmlChar *SystemID, + const xmlChar *content) { xmlEntitiesTablePtr table; + xmlEntityPtr ret; + xmlDtdPtr dtd; if (doc == NULL) { fprintf(stderr, "xmlAddDocEntity: document is NULL !\n"); - return; + return(NULL); } if (doc->intSubset == NULL) { fprintf(stderr, "xmlAddDtdEntity: document without internal subset !\n"); - return; + return(NULL); } + dtd = doc->intSubset; table = (xmlEntitiesTablePtr) doc->intSubset->entities; if (table == NULL) { table = xmlCreateEntitiesTable(); doc->intSubset->entities = table; } - xmlAddEntity(table, name, type, ExternalID, SystemID, content); + ret = xmlAddEntity(table, name, type, ExternalID, SystemID, content); + if (ret == NULL) return(NULL); + + /* + * Link it to the Dtd + */ + ret->parent = dtd; + ret->doc = dtd->doc; + if (dtd->last == NULL) { + dtd->children = dtd->last = (xmlNodePtr) ret; + } else { + dtd->last->next = (xmlNodePtr) ret; + ret->prev = dtd->last; + dtd->last = (xmlNodePtr) ret; + } + return(ret); } +#ifdef WITH_EXTRA_ENT_DETECT +/** + * xmlEntityCheckReference: + * @ent: an existing entity + * @to: the entity name it's referencing + * + * Function to keep track of references and detect cycles (well formedness + * errors !). + * + * Returns: 0 if Okay, -1 in case of general error, 1 in case of loop + * detection. + */ +int +xmlEntityCheckReference(xmlEntityPtr ent, const xmlChar *to) { + int i; + xmlDocPtr doc; + + if (ent == NULL) return(-1); + if (to == NULL) return(-1); + + doc = ent->doc; + if (doc == NULL) return(-1); + +#ifdef DEBUG_ENT_REF + printf("xmlEntityCheckReference(%s to %s)\n", ent->name, to); +#endif + + + /* + * Do a recursive checking + */ + for (i = 0;i < ent->entNr;i++) { + xmlEntityPtr indir = NULL; + + if (!xmlStrcmp(to, ent->entTab[i])) + return(1); + + switch (ent->etype) { + case XML_INTERNAL_GENERAL_ENTITY: + case XML_EXTERNAL_GENERAL_PARSED_ENTITY: + indir = xmlGetDocEntity(doc, ent->entTab[i]); + break; + case XML_INTERNAL_PARAMETER_ENTITY: + case XML_EXTERNAL_PARAMETER_ENTITY: + indir = xmlGetDtdEntity(doc, ent->entTab[i]); + break; + case XML_INTERNAL_PREDEFINED_ENTITY: + case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: + break; + } + if (xmlEntityCheckReference(indir, to) == 1) + return(1); + } + return(0); +} + +/** + * xmlEntityAddReference: + * @ent: an existing entity + * @to: the entity name it's referencing + * + * Function to register reuse of an existing entity from a (new) one + * Used to keep track of references and detect cycles (well formedness + * errors !). + * + * Returns: 0 if Okay, -1 in case of general error, 1 in case of loop + * detection. + */ +int +xmlEntityAddReference(xmlEntityPtr ent, const xmlChar *to) { + int i; + xmlDocPtr doc; + xmlEntityPtr indir = NULL; + + if (ent == NULL) return(-1); + if (to == NULL) return(-1); + + doc = ent->doc; + if (doc == NULL) return(-1); + +#ifdef DEBUG_ENT_REF + printf("xmlEntityAddReference(%s to %s)\n", ent->name, to); +#endif + if (ent->entTab == NULL) { + ent->entNr = 0; + ent->entMax = 5; + ent->entTab = (xmlChar **) xmlMalloc(ent->entMax * sizeof(xmlChar *)); + if (ent->entTab == NULL) { + fprintf(stderr, "xmlEntityAddReference: out of memory !\n"); + return(-1); + } + } + + for (i = 0;i < ent->entNr;i++) { + if (!xmlStrcmp(to, ent->entTab[i])) + return(0); + } + + /* + * Do a recursive checking + */ + + switch (ent->etype) { + case XML_INTERNAL_GENERAL_ENTITY: + case XML_EXTERNAL_GENERAL_PARSED_ENTITY: + indir = xmlGetDocEntity(doc, to); + break; + case XML_INTERNAL_PARAMETER_ENTITY: + case XML_EXTERNAL_PARAMETER_ENTITY: + indir = xmlGetDtdEntity(doc, to); + break; + case XML_INTERNAL_PREDEFINED_ENTITY: + case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: + break; + } + if ((indir != NULL) && + (xmlEntityCheckReference(indir, ent->name) == 1)) + return(1); + + /* + * Add this to the list + */ + if (ent->entMax <= ent->entNr) { + ent->entMax *= 2; + ent->entTab = (xmlChar **) xmlRealloc(ent->entTab, + ent->entMax * sizeof(xmlChar *)); + if (ent->entTab == NULL) { + fprintf(stderr, "xmlEntityAddReference: out of memory !\n"); + return(-1); + } + } + ent->entTab[ent->entNr++] = xmlStrdup(to); + return(0); +} +#endif + /** * xmlGetParameterEntity: * @doc: the document referencing the entity @@ -270,27 +474,27 @@ xmlGetParameterEntity(xmlDocPtr doc, const xmlChar *name) { if ((doc->intSubset != NULL) && (doc->intSubset->entities != NULL)) { table = (xmlEntitiesTablePtr) doc->intSubset->entities; for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; - if (((cur->type == XML_INTERNAL_PARAMETER_ENTITY) || - (cur->type == XML_EXTERNAL_PARAMETER_ENTITY)) && + cur = table->table[i]; + if (((cur->etype == XML_INTERNAL_PARAMETER_ENTITY) || + (cur->etype == XML_EXTERNAL_PARAMETER_ENTITY)) && (!xmlStrcmp(cur->name, name))) return(cur); } } if ((doc->extSubset != NULL) && (doc->extSubset->entities != NULL)) { table = (xmlEntitiesTablePtr) doc->extSubset->entities; for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; - if (((cur->type == XML_INTERNAL_PARAMETER_ENTITY) || - (cur->type == XML_EXTERNAL_PARAMETER_ENTITY)) && + cur = table->table[i]; + if (((cur->etype == XML_INTERNAL_PARAMETER_ENTITY) || + (cur->etype == XML_EXTERNAL_PARAMETER_ENTITY)) && (!xmlStrcmp(cur->name, name))) return(cur); } } if ((doc->extSubset != NULL) && (doc->extSubset->entities != NULL)) { table = (xmlEntitiesTablePtr) doc->extSubset->entities; for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; - if (((cur->type == XML_INTERNAL_PARAMETER_ENTITY) || - (cur->type == XML_EXTERNAL_PARAMETER_ENTITY)) && + cur = table->table[i]; + if (((cur->etype == XML_INTERNAL_PARAMETER_ENTITY) || + (cur->etype == XML_EXTERNAL_PARAMETER_ENTITY)) && (!xmlStrcmp(cur->name, name))) return(cur); } } @@ -316,9 +520,9 @@ xmlGetDtdEntity(xmlDocPtr doc, const xmlChar *name) { if ((doc->extSubset != NULL) && (doc->extSubset->entities != NULL)) { table = (xmlEntitiesTablePtr) doc->extSubset->entities; for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; - if ((cur->type != XML_INTERNAL_PARAMETER_ENTITY) && - (cur->type != XML_EXTERNAL_PARAMETER_ENTITY) && + cur = table->table[i]; + if ((cur->etype != XML_INTERNAL_PARAMETER_ENTITY) && + (cur->etype != XML_EXTERNAL_PARAMETER_ENTITY) && (!xmlStrcmp(cur->name, name))) return(cur); } } @@ -345,18 +549,18 @@ xmlGetDocEntity(xmlDocPtr doc, const xmlChar *name) { if ((doc->intSubset != NULL) && (doc->intSubset->entities != NULL)) { table = (xmlEntitiesTablePtr) doc->intSubset->entities; for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; - if ((cur->type != XML_INTERNAL_PARAMETER_ENTITY) && - (cur->type != XML_EXTERNAL_PARAMETER_ENTITY) && + cur = table->table[i]; + if ((cur->etype != XML_INTERNAL_PARAMETER_ENTITY) && + (cur->etype != XML_EXTERNAL_PARAMETER_ENTITY) && (!xmlStrcmp(cur->name, name))) return(cur); } } if ((doc->extSubset != NULL) && (doc->extSubset->entities != NULL)) { table = (xmlEntitiesTablePtr) doc->extSubset->entities; for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; - if ((cur->type != XML_INTERNAL_PARAMETER_ENTITY) && - (cur->type != XML_EXTERNAL_PARAMETER_ENTITY) && + cur = table->table[i]; + if ((cur->etype != XML_INTERNAL_PARAMETER_ENTITY) && + (cur->etype != XML_EXTERNAL_PARAMETER_ENTITY) && (!xmlStrcmp(cur->name, name))) return(cur); } } @@ -364,9 +568,9 @@ xmlGetDocEntity(xmlDocPtr doc, const xmlChar *name) { xmlInitializePredefinedEntities(); table = xmlPredefinedEntities; for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; - if ((cur->type != XML_INTERNAL_PARAMETER_ENTITY) && - (cur->type != XML_EXTERNAL_PARAMETER_ENTITY) && + cur = table->table[i]; + if ((cur->etype != XML_INTERNAL_PARAMETER_ENTITY) && + (cur->etype != XML_EXTERNAL_PARAMETER_ENTITY) && (!xmlStrcmp(cur->name, name))) return(cur); } @@ -612,6 +816,7 @@ xmlEncodeEntitiesReentrant(xmlDocPtr doc, const xmlChar *input) { *out++ = 'o'; *out++ = 't'; *out++ = ';'; +#if 0 } else if ((*cur == '\'') && (!html)) { *out++ = '&'; *out++ = 'a'; @@ -619,23 +824,101 @@ xmlEncodeEntitiesReentrant(xmlDocPtr doc, const xmlChar *input) { *out++ = 'o'; *out++ = 's'; *out++ = ';'; +#endif } else if (((*cur >= 0x20) && (*cur < 0x80)) || (*cur == '\n') || (*cur == '\r') || (*cur == '\t')) { /* * default case, just copy ! */ *out++ = *cur; -#ifndef USE_UTF_8 - } else if ((sizeof(xmlChar) == 1) && (*cur >= 0x80)) { - char buf[10], *ptr; + } else if (*cur >= 0x80) { + if (html) { + char buf[15], *ptr; + + /* + * TODO: improve by searching in html40EntitiesTable + */ #ifdef HAVE_SNPRINTF - snprintf(buf, 9, "&#%d;", *cur); + snprintf(buf, 9, "&#%d;", *cur); #else - sprintf(buf, "&#%d;", *cur); + sprintf(buf, "&#%d;", *cur); #endif - ptr = buf; - while (*ptr != 0) *out++ = *ptr++; + ptr = buf; + while (*ptr != 0) *out++ = *ptr++; + } else if (doc->encoding != NULL) { + /* + * TODO !!! + */ + *out++ = *cur; + } else { + /* + * We assume we have UTF-8 input. + */ + char buf[10], *ptr; + int val = 0, l = 1; + + if (*cur < 0xC0) { + fprintf(stderr, + "xmlEncodeEntitiesReentrant : input not UTF-8\n"); + doc->encoding = xmlStrdup(BAD_CAST "ISO-8859-1"); +#ifdef HAVE_SNPRINTF + snprintf(buf, 9, "&#%d;", *cur); +#else + sprintf(buf, "&#%d;", *cur); #endif + ptr = buf; + while (*ptr != 0) *out++ = *ptr++; + continue; + } else if (*cur < 0xE0) { + val = (cur[0]) & 0x1F; + val <<= 6; + val |= (cur[1]) & 0x3F; + l = 2; + } else if (*cur < 0xF0) { + val = (cur[0]) & 0x0F; + val <<= 6; + val |= (cur[1]) & 0x3F; + val <<= 6; + val |= (cur[2]) & 0x3F; + l = 3; + } else if (*cur < 0xF8) { + val = (cur[0]) & 0x07; + val <<= 6; + val |= (cur[1]) & 0x3F; + val <<= 6; + val |= (cur[2]) & 0x3F; + val <<= 6; + val |= (cur[3]) & 0x3F; + l = 4; + } + if ((l == 1) || (!IS_CHAR(val))) { + fprintf(stderr, + "xmlEncodeEntitiesReentrant : char out of range\n"); + doc->encoding = xmlStrdup(BAD_CAST "ISO-8859-1"); +#ifdef HAVE_SNPRINTF + snprintf(buf, 9, "&#%d;", *cur); +#else + sprintf(buf, "&#%d;", *cur); +#endif + ptr = buf; + while (*ptr != 0) *out++ = *ptr++; + cur++; + continue; + } + /* + * We could do multiple things here. Just save as a char ref + */ +#ifdef HAVE_SNPRINTF + snprintf(buf, 14, "&#x%X;", val); +#else + sprintf(buf, "&#x%X;", val); +#endif + buf[14] = 0; + ptr = buf; + while (*ptr != 0) *out++ = *ptr++; + cur += l; + continue; + } } else if (IS_CHAR(*cur)) { char buf[10], *ptr; @@ -682,11 +965,11 @@ xmlCreateEntitiesTable(void) { } ret->max_entities = XML_MIN_ENTITIES_TABLE; ret->nb_entities = 0; - ret->table = (xmlEntityPtr ) - xmlMalloc(ret->max_entities * sizeof(xmlEntity)); + ret->table = (xmlEntityPtr *) + xmlMalloc(ret->max_entities * sizeof(xmlEntityPtr)); if (ret == NULL) { fprintf(stderr, "xmlCreateEntitiesTable : xmlMalloc(%ld) failed\n", - ret->max_entities * (long)sizeof(xmlEntity)); + ret->max_entities * (long)sizeof(xmlEntityPtr)); xmlFree(ret); return(NULL); } @@ -706,7 +989,7 @@ xmlFreeEntitiesTable(xmlEntitiesTablePtr table) { if (table == NULL) return; for (i = 0;i < table->nb_entities;i++) { - xmlFreeEntity(&table->table[i]); + xmlFreeEntity(table->table[i]); } xmlFree(table->table); xmlFree(table); @@ -731,8 +1014,8 @@ xmlCopyEntitiesTable(xmlEntitiesTablePtr table) { fprintf(stderr, "xmlCopyEntitiesTable: out of memory !\n"); return(NULL); } - ret->table = (xmlEntityPtr) xmlMalloc(table->max_entities * - sizeof(xmlEntity)); + ret->table = (xmlEntityPtr *) xmlMalloc(table->max_entities * + sizeof(xmlEntityPtr)); if (ret->table == NULL) { fprintf(stderr, "xmlCopyEntitiesTable: out of memory !\n"); xmlFree(ret); @@ -741,34 +1024,119 @@ xmlCopyEntitiesTable(xmlEntitiesTablePtr table) { ret->max_entities = table->max_entities; ret->nb_entities = table->nb_entities; for (i = 0;i < ret->nb_entities;i++) { - cur = &ret->table[i]; - ent = &table->table[i]; - cur->len = ent->len; - cur->type = ent->type; + cur = (xmlEntityPtr) xmlMalloc(sizeof(xmlEntity)); + if (cur == NULL) { + fprintf(stderr, "xmlCopyEntityTable: out of memory !\n"); + xmlFree(ret); + xmlFree(ret->table); + return(NULL); + } + memset(cur, 0, sizeof(xmlEntity)); + cur->type = XML_ELEMENT_DECL; + ret->table[i] = cur; + ent = table->table[i]; + + cur->etype = ent->etype; if (ent->name != NULL) cur->name = xmlStrdup(ent->name); - else - cur->name = NULL; if (ent->ExternalID != NULL) cur->ExternalID = xmlStrdup(ent->ExternalID); - else - cur->ExternalID = NULL; if (ent->SystemID != NULL) cur->SystemID = xmlStrdup(ent->SystemID); - else - cur->SystemID = NULL; if (ent->content != NULL) cur->content = xmlStrdup(ent->content); - else - cur->content = NULL; if (ent->orig != NULL) cur->orig = xmlStrdup(ent->orig); - else - cur->orig = NULL; } return(ret); } +/** + * xmlDumpEntityDecl: + * @buf: An XML buffer. + * @ent: An entity table + * + * This will dump the content of the entity table as an XML DTD definition + */ +void +xmlDumpEntityDecl(xmlBufferPtr buf, xmlEntityPtr ent) { + switch (ent->etype) { + case XML_INTERNAL_GENERAL_ENTITY: + xmlBufferWriteChar(buf, "name); + xmlBufferWriteChar(buf, " "); + if (ent->orig != NULL) + xmlBufferWriteQuotedString(buf, ent->orig); + else + xmlBufferWriteQuotedString(buf, ent->content); + xmlBufferWriteChar(buf, ">\n"); + break; + case XML_EXTERNAL_GENERAL_PARSED_ENTITY: + xmlBufferWriteChar(buf, "name); + if (ent->ExternalID != NULL) { + xmlBufferWriteChar(buf, " PUBLIC "); + xmlBufferWriteQuotedString(buf, ent->ExternalID); + xmlBufferWriteChar(buf, " "); + xmlBufferWriteQuotedString(buf, ent->SystemID); + } else { + xmlBufferWriteChar(buf, " SYSTEM "); + xmlBufferWriteQuotedString(buf, ent->SystemID); + } + xmlBufferWriteChar(buf, ">\n"); + break; + case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: + xmlBufferWriteChar(buf, "name); + if (ent->ExternalID != NULL) { + xmlBufferWriteChar(buf, " PUBLIC "); + xmlBufferWriteQuotedString(buf, ent->ExternalID); + xmlBufferWriteChar(buf, " "); + xmlBufferWriteQuotedString(buf, ent->SystemID); + } else { + xmlBufferWriteChar(buf, " SYSTEM "); + xmlBufferWriteQuotedString(buf, ent->SystemID); + } + if (ent->content != NULL) { /* Should be true ! */ + xmlBufferWriteChar(buf, " NDATA "); + if (ent->orig != NULL) + xmlBufferWriteCHAR(buf, ent->orig); + else + xmlBufferWriteCHAR(buf, ent->content); + } + xmlBufferWriteChar(buf, ">\n"); + break; + case XML_INTERNAL_PARAMETER_ENTITY: + xmlBufferWriteChar(buf, "name); + xmlBufferWriteChar(buf, " "); + if (ent->orig == NULL) + xmlBufferWriteQuotedString(buf, ent->content); + else + xmlBufferWriteQuotedString(buf, ent->orig); + xmlBufferWriteChar(buf, ">\n"); + break; + case XML_EXTERNAL_PARAMETER_ENTITY: + xmlBufferWriteChar(buf, "name); + if (ent->ExternalID != NULL) { + xmlBufferWriteChar(buf, " PUBLIC "); + xmlBufferWriteQuotedString(buf, ent->ExternalID); + xmlBufferWriteChar(buf, " "); + xmlBufferWriteQuotedString(buf, ent->SystemID); + } else { + xmlBufferWriteChar(buf, " SYSTEM "); + xmlBufferWriteQuotedString(buf, ent->SystemID); + } + xmlBufferWriteChar(buf, ">\n"); + break; + default: + fprintf(stderr, + "xmlDumpEntitiesTable: internal: unknown type %d\n", + ent->etype); + } +} + /** * xmlDumpEntitiesTable: * @buf: An XML buffer. @@ -784,81 +1152,7 @@ xmlDumpEntitiesTable(xmlBufferPtr buf, xmlEntitiesTablePtr table) { if (table == NULL) return; for (i = 0;i < table->nb_entities;i++) { - cur = &table->table[i]; - switch (cur->type) { - case XML_INTERNAL_GENERAL_ENTITY: - xmlBufferWriteChar(buf, "name); - xmlBufferWriteChar(buf, " "); - if (cur->orig != NULL) - xmlBufferWriteQuotedString(buf, cur->orig); - else - xmlBufferWriteQuotedString(buf, cur->content); - xmlBufferWriteChar(buf, ">\n"); - break; - case XML_EXTERNAL_GENERAL_PARSED_ENTITY: - xmlBufferWriteChar(buf, "name); - if (cur->ExternalID != NULL) { - xmlBufferWriteChar(buf, " PUBLIC "); - xmlBufferWriteQuotedString(buf, cur->ExternalID); - xmlBufferWriteChar(buf, " "); - xmlBufferWriteQuotedString(buf, cur->SystemID); - } else { - xmlBufferWriteChar(buf, " SYSTEM "); - xmlBufferWriteQuotedString(buf, cur->SystemID); - } - xmlBufferWriteChar(buf, ">\n"); - break; - case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: - xmlBufferWriteChar(buf, "name); - if (cur->ExternalID != NULL) { - xmlBufferWriteChar(buf, " PUBLIC "); - xmlBufferWriteQuotedString(buf, cur->ExternalID); - xmlBufferWriteChar(buf, " "); - xmlBufferWriteQuotedString(buf, cur->SystemID); - } else { - xmlBufferWriteChar(buf, " SYSTEM "); - xmlBufferWriteQuotedString(buf, cur->SystemID); - } - if (cur->content != NULL) { /* Should be true ! */ - xmlBufferWriteChar(buf, " NDATA "); - if (cur->orig != NULL) - xmlBufferWriteCHAR(buf, cur->orig); - else - xmlBufferWriteCHAR(buf, cur->content); - } - xmlBufferWriteChar(buf, ">\n"); - break; - case XML_INTERNAL_PARAMETER_ENTITY: - xmlBufferWriteChar(buf, "name); - xmlBufferWriteChar(buf, " "); - if (cur->orig == NULL) - xmlBufferWriteQuotedString(buf, cur->content); - else - xmlBufferWriteQuotedString(buf, cur->orig); - xmlBufferWriteChar(buf, ">\n"); - break; - case XML_EXTERNAL_PARAMETER_ENTITY: - xmlBufferWriteChar(buf, "name); - if (cur->ExternalID != NULL) { - xmlBufferWriteChar(buf, " PUBLIC "); - xmlBufferWriteQuotedString(buf, cur->ExternalID); - xmlBufferWriteChar(buf, " "); - xmlBufferWriteQuotedString(buf, cur->SystemID); - } else { - xmlBufferWriteChar(buf, " SYSTEM "); - xmlBufferWriteQuotedString(buf, cur->SystemID); - } - xmlBufferWriteChar(buf, ">\n"); - break; - default: - fprintf(stderr, - "xmlDumpEntitiesTable: internal: unknown type %d\n", - cur->type); - } + cur = table->table[i]; + xmlDumpEntityDecl(buf, cur); } } diff --git a/entities.h b/entities.h index 0347170e..50e1f51d 100644 --- a/entities.h +++ b/entities.h @@ -15,12 +15,17 @@ extern "C" { #endif -#define XML_INTERNAL_GENERAL_ENTITY 1 -#define XML_EXTERNAL_GENERAL_PARSED_ENTITY 2 -#define XML_EXTERNAL_GENERAL_UNPARSED_ENTITY 3 -#define XML_INTERNAL_PARAMETER_ENTITY 4 -#define XML_EXTERNAL_PARAMETER_ENTITY 5 -#define XML_INTERNAL_PREDEFINED_ENTITY 6 +/* + * The different valid entity types + */ +typedef enum { + XML_INTERNAL_GENERAL_ENTITY = 1, + XML_EXTERNAL_GENERAL_PARSED_ENTITY = 2, + XML_EXTERNAL_GENERAL_UNPARSED_ENTITY = 3, + XML_INTERNAL_PARAMETER_ENTITY = 4, + XML_EXTERNAL_PARAMETER_ENTITY = 5, + XML_INTERNAL_PREDEFINED_ENTITY = 6 +} xmlEntityType; /* * An unit of storage for an entity, contains the string, the value @@ -30,14 +35,32 @@ extern "C" { typedef struct _xmlEntity xmlEntity; typedef xmlEntity *xmlEntityPtr; struct _xmlEntity { - int type; /* The entity type */ - int len; /* The lenght of the name */ - const xmlChar *name; /* Name of the entity */ - const xmlChar *ExternalID; /* External identifier for PUBLIC Entity */ - const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC Entity */ - xmlChar *content; /* The entity content or ndata if unparsed */ - int length; /* the content length */ - xmlChar *orig; /* The entity cont without ref substitution */ +#ifndef XML_WITHOUT_CORBA + void *_private; /* for Corba, must be first ! */ +#endif + xmlElementType type; /* XML_ENTITY_DECL, must be second ! */ + const xmlChar *name; /* Attribute name */ + struct _xmlNode *children; /* NULL */ + struct _xmlNode *last; /* NULL */ + struct _xmlDtd *parent; /* -> DTD */ + struct _xmlNode *next; /* next sibling link */ + struct _xmlNode *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* the containing document */ + + xmlChar *orig; /* content without ref substitution */ + xmlChar *content; /* content or ndata if unparsed */ + int length; /* the content length */ + xmlEntityType etype; /* The entity type */ + const xmlChar *ExternalID; /* External identifier for PUBLIC */ + const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC Entity */ + +#ifdef WITH_EXTRA_ENT_DETECT + /* Referenced entities name stack */ + xmlChar *ent; /* Current parsed Node */ + int entNr; /* Depth of the parsing stack */ + int entMax; /* Max depth of the parsing stack */ + xmlChar * *entTab; /* array of nodes */ +#endif }; /* @@ -52,7 +75,7 @@ typedef xmlEntitiesTable *xmlEntitiesTablePtr; struct _xmlEntitiesTable { int nb_entities; /* number of elements stored */ int max_entities; /* maximum number of elements */ - xmlEntityPtr table; /* the table of entities */ + xmlEntityPtr *table; /* the table of entities */ }; @@ -60,13 +83,13 @@ struct _xmlEntitiesTable { * External functions : */ -void xmlAddDocEntity (xmlDocPtr doc, +xmlEntityPtr xmlAddDocEntity (xmlDocPtr doc, const xmlChar *name, int type, const xmlChar *ExternalID, const xmlChar *SystemID, const xmlChar *content); -void xmlAddDtdEntity (xmlDocPtr doc, +xmlEntityPtr xmlAddDtdEntity (xmlDocPtr doc, const xmlChar *name, int type, const xmlChar *ExternalID, @@ -88,9 +111,16 @@ xmlEntitiesTablePtr xmlCopyEntitiesTable (xmlEntitiesTablePtr table); void xmlFreeEntitiesTable (xmlEntitiesTablePtr table); void xmlDumpEntitiesTable (xmlBufferPtr buf, xmlEntitiesTablePtr table); +void xmlDumpEntityDecl (xmlBufferPtr buf, + xmlEntityPtr ent); xmlEntitiesTablePtr xmlCopyEntitiesTable (xmlEntitiesTablePtr table); void xmlCleanupPredefinedEntities(void); +#ifdef WITH_EXTRA_ENT_DETECT +int xmlEntityAddReference (xmlEntityPtr ent, + const xmlChar *to); +#endif + #ifdef __cplusplus } #endif diff --git a/include/libxml/encoding.h b/include/libxml/encoding.h index 5eb1a52f..12a79108 100644 --- a/include/libxml/encoding.h +++ b/include/libxml/encoding.h @@ -67,11 +67,11 @@ typedef enum { * Returns the number of byte written, or -1 by lack of space. */ typedef int (* xmlCharEncodingInputFunc)(unsigned char* out, int outlen, - unsigned char* in, int inlen); + const unsigned char* in, int *inlen); /** - * xmlCharEncodingInputFunc: + * xmlCharEncodingOutputFunc: * @out: a pointer ot an array of bytes to store the result * @outlen: the lenght of @out * @in: a pointer ot an array of UTF-8 chars @@ -84,7 +84,7 @@ typedef int (* xmlCharEncodingInputFunc)(unsigned char* out, int outlen, * if the transcoding failed. */ typedef int (* xmlCharEncodingOutputFunc)(unsigned char* out, int outlen, - unsigned char* in, int inlen); + const unsigned char* in, int *inlen); /* * Block defining the handlers for non UTF-8 encodings. @@ -101,10 +101,12 @@ struct _xmlCharEncodingHandler { void xmlInitCharEncodingHandlers (void); void xmlCleanupCharEncodingHandlers (void); void xmlRegisterCharEncodingHandler (xmlCharEncodingHandlerPtr handler); -xmlCharEncoding xmlDetectCharEncoding (const unsigned char* in); +xmlCharEncoding xmlDetectCharEncoding (const unsigned char* in, + int len); xmlCharEncoding xmlParseCharEncoding (const char* name); xmlCharEncodingHandlerPtr xmlGetCharEncodingHandler(xmlCharEncoding enc); xmlCharEncodingHandlerPtr xmlFindCharEncodingHandler(const char *name); +int xmlCheckUTF8 (const unsigned char *utf); #ifdef __cplusplus diff --git a/include/libxml/entities.h b/include/libxml/entities.h index 0347170e..50e1f51d 100644 --- a/include/libxml/entities.h +++ b/include/libxml/entities.h @@ -15,12 +15,17 @@ extern "C" { #endif -#define XML_INTERNAL_GENERAL_ENTITY 1 -#define XML_EXTERNAL_GENERAL_PARSED_ENTITY 2 -#define XML_EXTERNAL_GENERAL_UNPARSED_ENTITY 3 -#define XML_INTERNAL_PARAMETER_ENTITY 4 -#define XML_EXTERNAL_PARAMETER_ENTITY 5 -#define XML_INTERNAL_PREDEFINED_ENTITY 6 +/* + * The different valid entity types + */ +typedef enum { + XML_INTERNAL_GENERAL_ENTITY = 1, + XML_EXTERNAL_GENERAL_PARSED_ENTITY = 2, + XML_EXTERNAL_GENERAL_UNPARSED_ENTITY = 3, + XML_INTERNAL_PARAMETER_ENTITY = 4, + XML_EXTERNAL_PARAMETER_ENTITY = 5, + XML_INTERNAL_PREDEFINED_ENTITY = 6 +} xmlEntityType; /* * An unit of storage for an entity, contains the string, the value @@ -30,14 +35,32 @@ extern "C" { typedef struct _xmlEntity xmlEntity; typedef xmlEntity *xmlEntityPtr; struct _xmlEntity { - int type; /* The entity type */ - int len; /* The lenght of the name */ - const xmlChar *name; /* Name of the entity */ - const xmlChar *ExternalID; /* External identifier for PUBLIC Entity */ - const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC Entity */ - xmlChar *content; /* The entity content or ndata if unparsed */ - int length; /* the content length */ - xmlChar *orig; /* The entity cont without ref substitution */ +#ifndef XML_WITHOUT_CORBA + void *_private; /* for Corba, must be first ! */ +#endif + xmlElementType type; /* XML_ENTITY_DECL, must be second ! */ + const xmlChar *name; /* Attribute name */ + struct _xmlNode *children; /* NULL */ + struct _xmlNode *last; /* NULL */ + struct _xmlDtd *parent; /* -> DTD */ + struct _xmlNode *next; /* next sibling link */ + struct _xmlNode *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* the containing document */ + + xmlChar *orig; /* content without ref substitution */ + xmlChar *content; /* content or ndata if unparsed */ + int length; /* the content length */ + xmlEntityType etype; /* The entity type */ + const xmlChar *ExternalID; /* External identifier for PUBLIC */ + const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC Entity */ + +#ifdef WITH_EXTRA_ENT_DETECT + /* Referenced entities name stack */ + xmlChar *ent; /* Current parsed Node */ + int entNr; /* Depth of the parsing stack */ + int entMax; /* Max depth of the parsing stack */ + xmlChar * *entTab; /* array of nodes */ +#endif }; /* @@ -52,7 +75,7 @@ typedef xmlEntitiesTable *xmlEntitiesTablePtr; struct _xmlEntitiesTable { int nb_entities; /* number of elements stored */ int max_entities; /* maximum number of elements */ - xmlEntityPtr table; /* the table of entities */ + xmlEntityPtr *table; /* the table of entities */ }; @@ -60,13 +83,13 @@ struct _xmlEntitiesTable { * External functions : */ -void xmlAddDocEntity (xmlDocPtr doc, +xmlEntityPtr xmlAddDocEntity (xmlDocPtr doc, const xmlChar *name, int type, const xmlChar *ExternalID, const xmlChar *SystemID, const xmlChar *content); -void xmlAddDtdEntity (xmlDocPtr doc, +xmlEntityPtr xmlAddDtdEntity (xmlDocPtr doc, const xmlChar *name, int type, const xmlChar *ExternalID, @@ -88,9 +111,16 @@ xmlEntitiesTablePtr xmlCopyEntitiesTable (xmlEntitiesTablePtr table); void xmlFreeEntitiesTable (xmlEntitiesTablePtr table); void xmlDumpEntitiesTable (xmlBufferPtr buf, xmlEntitiesTablePtr table); +void xmlDumpEntityDecl (xmlBufferPtr buf, + xmlEntityPtr ent); xmlEntitiesTablePtr xmlCopyEntitiesTable (xmlEntitiesTablePtr table); void xmlCleanupPredefinedEntities(void); +#ifdef WITH_EXTRA_ENT_DETECT +int xmlEntityAddReference (xmlEntityPtr ent, + const xmlChar *to); +#endif + #ifdef __cplusplus } #endif diff --git a/include/libxml/parser.h b/include/libxml/parser.h index 9e232cac..54f00e65 100644 --- a/include/libxml/parser.h +++ b/include/libxml/parser.h @@ -49,6 +49,9 @@ struct _xmlParserInput { int col; /* Current column */ int consumed; /* How many xmlChars already consumed */ xmlParserInputDeallocate free; /* function to deallocate the base */ + const xmlChar *encoding; /* the encoding string for entity */ + const xmlChar *version; /* the version string for entity */ + int standalone; /* Was that entity marked standalone */ }; /** @@ -95,6 +98,7 @@ typedef enum { XML_PARSER_ENTITY_DECL, /* within an entity declaration */ XML_PARSER_ENTITY_VALUE, /* within an entity value in a decl */ XML_PARSER_ATTRIBUTE_VALUE, /* within an attribute value */ + XML_PARSER_SYSTEM_LITERAL, /* within a SYSTEM value */ XML_PARSER_EPILOG /* the Misc* after the last end tag */ } xmlParserInputState; @@ -151,7 +155,7 @@ struct _xmlParserCtxt { char *directory; /* the data directory */ - /* Node name stack only used for HTML parsing */ + /* Node name stack */ xmlChar *name; /* Current parsed Node */ int nameNr; /* Depth of the parsing stack */ int nameMax; /* Max depth of the parsing stack */ @@ -160,6 +164,20 @@ struct _xmlParserCtxt { long nbChars; /* number of xmlChar processed */ long checkIndex; /* used by progressive parsing lookup */ int keepBlanks; /* ugly but ... */ + int disableSAX; /* SAX callbacks are disabled */ + int inSubset; /* Parsing is in int 1/ext 2 subset */ + xmlChar * intSubName; /* name of subset */ + xmlChar * extSubURI; /* URI of external subset */ + xmlChar * extSubSystem; /* SYSTEM ID of external subset */ + + /* xml:space values */ + int * space; /* Should the parser preserve spaces */ + int spaceNr; /* Depth of the parsing stack */ + int spaceMax; /* Max depth of the parsing stack */ + int * spaceTab; /* array of space infos */ + + int depth; /* to prevent entity substitution loops */ + xmlParserInputPtr entity; /* used to check entities boundaries */ }; /** @@ -183,6 +201,8 @@ typedef xmlParserInputPtr (*resolveEntitySAXFunc) (void *ctx, const xmlChar *publicId, const xmlChar *systemId); typedef void (*internalSubsetSAXFunc) (void *ctx, const xmlChar *name, const xmlChar *ExternalID, const xmlChar *SystemID); +typedef void (*externalSubsetSAXFunc) (void *ctx, const xmlChar *name, + const xmlChar *ExternalID, const xmlChar *SystemID); typedef xmlEntityPtr (*getEntitySAXFunc) (void *ctx, const xmlChar *name); typedef xmlEntityPtr (*getParameterEntitySAXFunc) (void *ctx, @@ -254,6 +274,7 @@ struct _xmlSAXHandler { fatalErrorSAXFunc fatalError; getParameterEntitySAXFunc getParameterEntity; cdataBlockSAXFunc cdataBlock; + externalSubsetSAXFunc externalSubset; }; /** @@ -278,7 +299,7 @@ extern xmlSAXHandler htmlDefaultSAXHandler; */ extern int xmlSubstituteEntitiesDefaultValue; - +extern int xmlGetWarningsDefaultValue; /** @@ -363,6 +384,20 @@ xmlDtdPtr xmlParseDTD (const xmlChar *ExternalID, xmlDtdPtr xmlSAXParseDTD (xmlSAXHandlerPtr sax, const xmlChar *ExternalID, const xmlChar *SystemID); +int xmlParseBalancedChunkMemory(xmlDocPtr doc, + xmlSAXHandlerPtr sax, + void *user_data, + int depth, + const xmlChar *string, + xmlNodePtr *list); +int xmlParseExternalEntity (xmlDocPtr doc, + xmlSAXHandlerPtr sax, + void *user_data, + int depth, + const xmlChar *URL, + const xmlChar *ID, + xmlNodePtr *list); + /** * SAX initialization routines */ diff --git a/include/libxml/parserInternals.h b/include/libxml/parserInternals.h index 5a7b7ffe..db7965a6 100644 --- a/include/libxml/parserInternals.h +++ b/include/libxml/parserInternals.h @@ -17,31 +17,6 @@ extern "C" { #define XML_MAX_NAMELEN 1000 -/** - * A few macros needed to help building the parser. - */ -/* #define UNICODE */ - -#ifdef UNICODE -typedef unsigned long CHARVAL; - -#define NEXTCHARVAL(p) (unsigned long) \ - ((*(p) == 0) ? (unsigned long) 0 : \ - ((*(p) < 0x80) ? (unsigned long) (*(p)++) : \ - (*(p) < 0xC0) ? (unsigned long) 0 : \ - (*(p) < 0xE0) ? ((((unsigned long) *(p)++) << 6) + (*(p)++ & 0x3F)) : \ - (*(p) < 0xF0) ? (((((unsigned long) *(p)++) << 6) + (*(p)++ & 0x3F)) << 6 + \ - (*(p)++ & 0x3F)) : \ - (*(p) < 0xF8) ? ((((((unsigned long) *(p)++) << 6) + (*(p)++ & 0x3F)) << 6 + \ - (*(p)++ & 0x3F)) << 6 + (*(p)++ & 0x3F)) : 0)) -#else -typedef unsigned char CHARVAL; - -#define NEXTCHARVAL(p) (unsigned long) *(p); -#define SKIPCHARVAL(p) (p)++; -#endif - -#ifdef UNICODE /************************************************************************ * * * UNICODE version of the macros. * @@ -404,7 +379,7 @@ typedef unsigned char CHARVAL; #define IS_EXTENDER(c) \ (((c) == 0xb7) || ((c) == 0x2d0) || ((c) == 0x2d1) || \ ((c) == 0x387) || ((c) == 0x640) || ((c) == 0xe46) || \ - ((c) == 0xec6) || ((c) == 0x3005) \ + ((c) == 0xec6) || ((c) == 0x3005) || \ (((c) >= 0x3031) && ((c) <= 0x3035)) || \ (((c) >= 0x309b) && ((c) <= 0x309e)) || \ (((c) >= 0x30fc) && ((c) <= 0x30fe))) @@ -423,65 +398,6 @@ typedef unsigned char CHARVAL; */ #define IS_LETTER(c) (IS_BASECHAR(c) || IS_IDEOGRAPHIC(c)) -#else -/************************************************************************ - * * - * 8bits / ISO-Latin version of the macros. * - * * - ************************************************************************/ -/* - * [2] Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] - * | [#x10000-#x10FFFF] - * any Unicode character, excluding the surrogate blocks, FFFE, and FFFF. - */ -#define IS_CHAR(c) \ - ((((c) >= 0x20) && ((c) <= 0xD7FF)) || \ - ((c) == 0x09) || ((c) == 0x0a) || ((c) == 0x0d) || \ - (((c) >= 0xE000) && ((c) <= 0xFFFD)) || \ - (((c) >= 0x10000) && ((c) <= 0x10FFFF))) - -/* - * [85] BaseChar ::= ... long list see REC ... - */ -#define IS_BASECHAR(c) \ - ((((c) >= 0x0041) && ((c) <= 0x005A)) || \ - (((c) >= 0x0061) && ((c) <= 0x007A)) || \ - (((c) >= 0x00C0) && ((c) <= 0x00D6)) || \ - (((c) >= 0x00D8) && ((c) <= 0x00F6)) || \ - (((c) >= 0x00F8) && ((c) <= 0x00FF))) - -/* - * [88] Digit ::= ... long list see REC ... - */ -#define IS_DIGIT(c) (((c) >= 0x30) && ((c) <= 0x39)) - -/* - * [84] Letter ::= BaseChar | Ideographic - */ -#define IS_LETTER(c) IS_BASECHAR(c) - - -/* - * [87] CombiningChar ::= ... long list see REC ... - */ -#define IS_COMBINING(c) 0 - -/* - * [89] Extender ::= #x00B7 | #x02D0 | #x02D1 | #x0387 | #x0640 | - * #x0E46 | #x0EC6 | #x3005 | [#x3031-#x3035] | - * [#x309D-#x309E] | [#x30FC-#x30FE] - */ -#define IS_EXTENDER(c) ((c) == 0xb7) - -#endif /* !UNICODE */ - -/* - * Blank chars. - * - * [3] S ::= (#x20 | #x9 | #xD | #xA)+ - */ -#define IS_BLANK(c) (((c) == 0x20) || ((c) == 0x09) || ((c) == 0xa) || \ - ((c) == 0x0D)) /* * [13] PubidChar ::= #x20 | #xD | #xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%] @@ -502,10 +418,10 @@ typedef unsigned char CHARVAL; if (*(p) == 0x10) { p++ ; if (*(p) == 0x13) p++; } #define MOVETO_ENDTAG(p) \ - while (IS_CHAR(*p) && (*(p) != '>')) (p)++ + while ((*p) && (*(p) != '>')) (p)++ #define MOVETO_STARTTAG(p) \ - while (IS_CHAR(*p) && (*(p) != '<')) (p)++ + while ((*p) && (*(p) != '<')) (p)++ /** * Parser context @@ -514,10 +430,13 @@ xmlParserCtxtPtr xmlCreateDocParserCtxt (xmlChar *cur); xmlParserCtxtPtr xmlCreateFileParserCtxt (const char *filename); xmlParserCtxtPtr xmlCreateMemoryParserCtxt(char *buffer, int size); -void xmlFreeParserCtxt (xmlParserCtxtPtr ctxt); xmlParserCtxtPtr xmlNewParserCtxt (void); +xmlParserCtxtPtr xmlCreateEntityParserCtxt(const xmlChar *URL, + const xmlChar *ID, + const xmlChar *base); void xmlSwitchEncoding (xmlParserCtxtPtr ctxt, xmlCharEncoding enc); +void xmlFreeParserCtxt (xmlParserCtxtPtr ctxt); /** * Entities @@ -540,33 +459,34 @@ xmlParserInputPtr xmlNewInputFromFile (xmlParserCtxtPtr ctxt, /** * Namespaces. */ -xmlChar * xmlSplitQName (const xmlChar *name, +xmlChar * xmlSplitQName (xmlParserCtxtPtr ctxt, + const xmlChar *name, xmlChar **prefix); -xmlChar * xmlNamespaceParseNCName (xmlParserCtxtPtr ctxt); -xmlChar * xmlNamespaceParseQName (xmlParserCtxtPtr ctxt, +xmlChar * xmlNamespaceParseNCName (xmlParserCtxtPtr ctxt); +xmlChar * xmlNamespaceParseQName (xmlParserCtxtPtr ctxt, xmlChar **prefix); -xmlChar * xmlNamespaceParseNSDef (xmlParserCtxtPtr ctxt); -xmlChar * xmlParseQuotedString (xmlParserCtxtPtr ctxt); +xmlChar * xmlNamespaceParseNSDef (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseQuotedString (xmlParserCtxtPtr ctxt); void xmlParseNamespace (xmlParserCtxtPtr ctxt); /** * Generic production rules */ -xmlChar * xmlScanName (xmlParserCtxtPtr ctxt); -xmlChar * xmlParseName (xmlParserCtxtPtr ctxt); -xmlChar * xmlParseNmtoken (xmlParserCtxtPtr ctxt); -xmlChar * xmlParseEntityValue (xmlParserCtxtPtr ctxt, +xmlChar * xmlScanName (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseName (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseNmtoken (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseEntityValue (xmlParserCtxtPtr ctxt, xmlChar **orig); -xmlChar * xmlParseAttValue (xmlParserCtxtPtr ctxt); -xmlChar * xmlParseSystemLiteral (xmlParserCtxtPtr ctxt); -xmlChar * xmlParsePubidLiteral (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseAttValue (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseSystemLiteral (xmlParserCtxtPtr ctxt); +xmlChar * xmlParsePubidLiteral (xmlParserCtxtPtr ctxt); void xmlParseCharData (xmlParserCtxtPtr ctxt, int cdata); -xmlChar * xmlParseExternalID (xmlParserCtxtPtr ctxt, +xmlChar * xmlParseExternalID (xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict); void xmlParseComment (xmlParserCtxtPtr ctxt); -xmlChar * xmlParsePITarget (xmlParserCtxtPtr ctxt); +xmlChar * xmlParsePITarget (xmlParserCtxtPtr ctxt); void xmlParsePI (xmlParserCtxtPtr ctxt); void xmlParseNotationDecl (xmlParserCtxtPtr ctxt); void xmlParseEntityDecl (xmlParserCtxtPtr ctxt); @@ -593,19 +513,20 @@ xmlEntityPtr xmlParseEntityRef (xmlParserCtxtPtr ctxt); void xmlParseReference (xmlParserCtxtPtr ctxt); void xmlParsePEReference (xmlParserCtxtPtr ctxt); void xmlParseDocTypeDecl (xmlParserCtxtPtr ctxt); -xmlChar * xmlParseAttribute (xmlParserCtxtPtr ctxt, +xmlChar * xmlParseAttribute (xmlParserCtxtPtr ctxt, xmlChar **value); -xmlChar * xmlParseStartTag (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseStartTag (xmlParserCtxtPtr ctxt); void xmlParseEndTag (xmlParserCtxtPtr ctxt); void xmlParseCDSect (xmlParserCtxtPtr ctxt); void xmlParseContent (xmlParserCtxtPtr ctxt); void xmlParseElement (xmlParserCtxtPtr ctxt); -xmlChar * xmlParseVersionNum (xmlParserCtxtPtr ctxt); -xmlChar * xmlParseVersionInfo (xmlParserCtxtPtr ctxt); -xmlChar * xmlParseEncName (xmlParserCtxtPtr ctxt); -xmlChar * xmlParseEncodingDecl (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseVersionNum (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseVersionInfo (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseEncName (xmlParserCtxtPtr ctxt); +xmlChar * xmlParseEncodingDecl (xmlParserCtxtPtr ctxt); int xmlParseSDDecl (xmlParserCtxtPtr ctxt); void xmlParseXMLDecl (xmlParserCtxtPtr ctxt); +void xmlParseTextDecl (xmlParserCtxtPtr ctxt); void xmlParseMisc (xmlParserCtxtPtr ctxt); void xmlParseExternalSubset (xmlParserCtxtPtr ctxt, const xmlChar *ExternalID, @@ -618,12 +539,18 @@ void xmlParseExternalSubset (xmlParserCtxtPtr ctxt, #define XML_SUBSTITUTE_PEREF 2 #define XML_SUBSTITUTE_BOTH 3 -xmlChar * xmlDecodeEntities (xmlParserCtxtPtr ctxt, +xmlChar * xmlDecodeEntities (xmlParserCtxtPtr ctxt, int len, int what, xmlChar end, xmlChar end2, xmlChar end3); +xmlChar * xmlStringDecodeEntities (xmlParserCtxtPtr ctxt, + const xmlChar *str, + int what, + xmlChar end, + xmlChar end2, + xmlChar end3); /* * Generated by MACROS on top of parser.c c.f. PUSH_AND_POP diff --git a/include/libxml/tree.h b/include/libxml/tree.h index ee88d806..c881728b 100644 --- a/include/libxml/tree.h +++ b/include/libxml/tree.h @@ -36,24 +36,22 @@ typedef enum { XML_DOCUMENT_TYPE_NODE= 10, XML_DOCUMENT_FRAG_NODE= 11, XML_NOTATION_NODE= 12, - XML_HTML_DOCUMENT_NODE= 13 + XML_HTML_DOCUMENT_NODE= 13, + XML_DTD_NODE= 14, + XML_ELEMENT_DECL= 15, + XML_ATTRIBUTE_DECL= 16, + XML_ENTITY_DECL= 17 } xmlElementType; /* * Size of an internal character representation. * - * Currently we use 8bit chars internal representation for memory efficiency, - * but the parser is not tied to that, just define UNICODE to switch to - * a 16 bits internal representation. Note that with 8 bits wide - * xmlChars one can still use UTF-8 to handle correctly non ISO-Latin - * input. + * We use 8bit chars internal representation for memory efficiency, + * Note that with 8 bits wide xmlChars one can still use UTF-8 to handle + * correctly non ISO-Latin input. */ -#ifdef UNICODE -typedef unsigned short xmlChar; -#else typedef unsigned char xmlChar; -#endif #ifndef WIN32 #ifndef CHAR @@ -109,14 +107,25 @@ struct _xmlEnumeration { typedef struct _xmlAttribute xmlAttribute; typedef xmlAttribute *xmlAttributePtr; struct _xmlAttribute { - const xmlChar *elem; /* Element holding the attribute */ - const xmlChar *name; /* Attribute name */ - struct _xmlAttribute *next; /* list of attributes of an element */ - xmlAttributeType type; /* The type */ - xmlAttributeDefault def; /* the default */ - const xmlChar *defaultValue;/* or the default value */ - xmlEnumerationPtr tree; /* or the enumeration tree if any */ - const xmlChar *prefix; /* the namespace prefix if any */ +#ifndef XML_WITHOUT_CORBA + void *_private; /* for Corba, must be first ! */ +#endif + xmlElementType type; /* XML_ATTRIBUTE_DECL, must be second ! */ + const xmlChar *name; /* Attribute name */ + struct _xmlNode *children; /* NULL */ + struct _xmlNode *last; /* NULL */ + struct _xmlDtd *parent; /* -> DTD */ + struct _xmlNode *next; /* next sibling link */ + struct _xmlNode *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* the containing document */ + + struct _xmlAttribute *nexth; /* next in hash table */ + xmlAttributeType atype; /* The attribute type */ + xmlAttributeDefault def; /* the default */ + const xmlChar *defaultValue; /* or the default value */ + xmlEnumerationPtr tree; /* or the enumeration tree if any */ + const xmlChar *prefix; /* the namespace prefix if any */ + const xmlChar *elem; /* Element holding the attribute */ }; /* @@ -156,8 +165,19 @@ typedef enum { typedef struct _xmlElement xmlElement; typedef xmlElement *xmlElementPtr; struct _xmlElement { +#ifndef XML_WITHOUT_CORBA + void *_private; /* for Corba, must be first ! */ +#endif + xmlElementType type; /* XML_ELEMENT_DECL, must be second ! */ const xmlChar *name; /* Element name */ - xmlElementTypeVal type; /* The type */ + struct _xmlNode *children; /* NULL */ + struct _xmlNode *last; /* NULL */ + struct _xmlDtd *parent; /* -> DTD */ + struct _xmlNode *next; /* next sibling link */ + struct _xmlNode *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* the containing document */ + + xmlElementTypeVal etype; /* The type */ xmlElementContentPtr content; /* the allowed element content */ xmlAttributePtr attributes; /* List of the declared attributes */ }; @@ -188,14 +208,25 @@ struct _xmlNs { typedef struct _xmlDtd xmlDtd; typedef xmlDtd *xmlDtdPtr; struct _xmlDtd { +#ifndef XML_WITHOUT_CORBA + void *_private; /* for Corba, must be first ! */ +#endif + xmlElementType type; /* XML_DTD_NODE, must be second ! */ const xmlChar *name; /* Name of the DTD */ - const xmlChar *ExternalID; /* External identifier for PUBLIC DTD */ - const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC DTD */ + struct _xmlNode *children; /* the value of the property link */ + struct _xmlNode *last; /* last child link */ + struct _xmlDoc *parent; /* child->parent link */ + struct _xmlNode *next; /* next sibling link */ + struct _xmlNode *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* the containing document */ + + /* End of common part */ void *notations; /* Hash table for notations if any */ void *elements; /* Hash table for elements if any */ void *attributes; /* Hash table for attributes if any */ void *entities; /* Hash table for entities if any */ - /* struct xmlDtd *next; * next link for this document */ + const xmlChar *ExternalID; /* External identifier for PUBLIC DTD */ + const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC DTD */ }; /* @@ -206,14 +237,17 @@ typedef xmlAttr *xmlAttrPtr; struct _xmlAttr { #ifndef XML_WITHOUT_CORBA void *_private; /* for Corba, must be first ! */ - void *vepv; /* for Corba, must be next ! */ #endif - xmlElementType type; /* XML_ATTRIBUTE_NODE, must be third ! */ - struct _xmlNode *node; /* attr->node link */ - struct _xmlAttr *next; /* attribute list link */ + xmlElementType type; /* XML_ATTRIBUTE_NODE, must be second ! */ const xmlChar *name; /* the name of the property */ - struct _xmlNode *val; /* the value of the property */ + struct _xmlNode *children; /* the value of the property */ + struct _xmlNode *last; /* NULL */ + struct _xmlNode *parent; /* child->parent link */ + struct _xmlAttr *next; /* next sibling link */ + struct _xmlAttr *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* the containing document */ xmlNs *ns; /* pointer to the associated namespace */ + xmlAttributeType atype; /* the attribute type if validating */ }; /* @@ -266,24 +300,25 @@ typedef xmlNode *xmlNodePtr; struct _xmlNode { #ifndef XML_WITHOUT_CORBA void *_private; /* for Corba, must be first ! */ - void *vepv; /* for Corba, must be next ! */ #endif - xmlElementType type; /* type number in the DTD, must be third ! */ - struct _xmlDoc *doc; /* the containing document */ + xmlElementType type; /* type number, must be second ! */ + const xmlChar *name; /* the name of the node, or the entity */ + struct _xmlNode *children; /* parent->childs link */ + struct _xmlNode *last; /* last child link */ struct _xmlNode *parent; /* child->parent link */ struct _xmlNode *next; /* next sibling link */ struct _xmlNode *prev; /* previous sibling link */ - struct _xmlNode *childs; /* parent->childs link */ - struct _xmlNode *last; /* last child link */ - struct _xmlAttr *properties;/* properties list */ - const xmlChar *name; /* the name of the node, or the entity */ - xmlNs *ns; /* pointer to the associated namespace */ - xmlNs *nsDef; /* namespace definitions on this node */ + struct _xmlDoc *doc; /* the containing document */ + xmlNs *ns; /* pointer to the associated namespace */ #ifndef XML_USE_BUFFER_CONTENT - xmlChar *content; /* the content */ + xmlChar *content; /* the content */ #else - xmlBufferPtr content; /* the content in a buffer */ + xmlBufferPtr content; /* the content in a buffer */ #endif + + /* End of common part */ + struct _xmlAttr *properties;/* properties list */ + xmlNs *nsDef; /* namespace definitions on this node */ }; /* @@ -294,20 +329,27 @@ typedef xmlDoc *xmlDocPtr; struct _xmlDoc { #ifndef XML_WITHOUT_CORBA void *_private; /* for Corba, must be first ! */ - void *vepv; /* for Corba, must be next ! */ #endif xmlElementType type; /* XML_DOCUMENT_NODE, must be second ! */ char *name; /* name/filename/URI of the document */ - const xmlChar *version; /* the XML version string */ - const xmlChar *encoding; /* encoding, if any */ + struct _xmlNode *children; /* the document tree */ + struct _xmlNode *last; /* last child link */ + struct _xmlNode *parent; /* child->parent link */ + struct _xmlNode *next; /* next sibling link */ + struct _xmlNode *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* autoreference to itself */ + + /* End of common part */ int compression;/* level of zlib compression */ int standalone; /* standalone document (no external refs) */ struct _xmlDtd *intSubset; /* the document internal subset */ struct _xmlDtd *extSubset; /* the document external subset */ struct _xmlNs *oldNs; /* Global namespace, the old way */ - struct _xmlNode *root; /* the document tree */ + const xmlChar *version; /* the XML version string */ + const xmlChar *encoding; /* encoding, if any */ void *ids; /* Hash table for ID attributes if any */ void *refs; /* Hash table for IDREFs attributes if any */ + const xmlChar *URL; /* The URI for that document */ }; /* @@ -422,6 +464,8 @@ xmlNodePtr xmlNewComment (const xmlChar *content); xmlNodePtr xmlNewCDataBlock (xmlDocPtr doc, const xmlChar *content, int len); +xmlNodePtr xmlNewCharRef (xmlDocPtr doc, + const xmlChar *name); xmlNodePtr xmlNewReference (xmlDocPtr doc, const xmlChar *name); xmlNodePtr xmlCopyNode (xmlNodePtr node, @@ -513,13 +557,14 @@ xmlChar * xmlNodeGetContent (xmlNodePtr cur); xmlChar * xmlNodeGetLang (xmlNodePtr cur); void xmlNodeSetLang (xmlNodePtr cur, const xmlChar *lang); +int xmlNodeGetSpacePreserve (xmlNodePtr cur); xmlChar * xmlNodeGetBase (xmlDocPtr doc, xmlNodePtr cur); /* * Removing content. */ -int xmlRemoveProp (xmlAttrPtr attr); /* TODO */ +int xmlRemoveProp (xmlAttrPtr attr); int xmlRemoveNode (xmlNodePtr node); /* TODO */ /* @@ -532,6 +577,12 @@ void xmlBufferWriteChar (xmlBufferPtr buf, void xmlBufferWriteQuotedString(xmlBufferPtr buf, const xmlChar *string); +/* + * Namespace handling + */ +int xmlReconciliateNs (xmlDocPtr doc, + xmlNodePtr tree); + /* * Saving */ diff --git a/include/libxml/valid.h b/include/libxml/valid.h index 8c86b17b..d211207e 100644 --- a/include/libxml/valid.h +++ b/include/libxml/valid.h @@ -29,6 +29,14 @@ struct _xmlValidCtxt { void *userData; /* user specific data block */ xmlValidityErrorFunc error; /* the callback in case of errors */ xmlValidityWarningFunc warning; /* the callback in case of warning */ + + /* Node analysis stack used when validating within entities */ + xmlNodePtr node; /* Current parsed Node */ + int nodeNr; /* Depth of the parsing stack */ + int nodeMax; /* Max depth of the parsing stack */ + xmlNodePtr *nodeTab; /* array of nodes */ + + int finishDtd; /* finished validating the Dtd ? */ }; /* @@ -114,6 +122,8 @@ xmlNotationPtr xmlAddNotationDecl (xmlValidCtxtPtr ctxt, const xmlChar *SystemID); xmlNotationTablePtr xmlCopyNotationTable(xmlNotationTablePtr table); void xmlFreeNotationTable(xmlNotationTablePtr table); +void xmlDumpNotationDecl (xmlBufferPtr buf, + xmlNotationPtr nota); void xmlDumpNotationTable(xmlBufferPtr buf, xmlNotationTablePtr table); @@ -122,6 +132,9 @@ xmlElementContentPtr xmlNewElementContent (xmlChar *name, xmlElementContentType type); xmlElementContentPtr xmlCopyElementContent(xmlElementContentPtr content); void xmlFreeElementContent(xmlElementContentPtr cur); +void xmlSprintfElementContent(char *buf, + xmlElementContentPtr content, + int glob); /* Element */ xmlElementPtr xmlAddElementDecl (xmlValidCtxtPtr ctxt, @@ -133,6 +146,8 @@ xmlElementTablePtr xmlCopyElementTable (xmlElementTablePtr table); void xmlFreeElementTable (xmlElementTablePtr table); void xmlDumpElementTable (xmlBufferPtr buf, xmlElementTablePtr table); +void xmlDumpElementDecl (xmlBufferPtr buf, + xmlElementPtr elem); /* Enumeration */ xmlEnumerationPtr xmlCreateEnumeration (xmlChar *name); @@ -144,6 +159,7 @@ xmlAttributePtr xmlAddAttributeDecl (xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *elem, const xmlChar *name, + const xmlChar *prefix, xmlAttributeType type, xmlAttributeDefault def, const xmlChar *defaultValue, @@ -152,6 +168,8 @@ xmlAttributeTablePtr xmlCopyAttributeTable (xmlAttributeTablePtr table); void xmlFreeAttributeTable (xmlAttributeTablePtr table); void xmlDumpAttributeTable (xmlBufferPtr buf, xmlAttributeTablePtr table); +void xmlDumpAttributeDecl (xmlBufferPtr buf, + xmlAttributePtr attr); /* IDs */ xmlIDPtr xmlAddID (xmlValidCtxtPtr ctxt, @@ -188,6 +206,10 @@ int xmlValidateRoot (xmlValidCtxtPtr ctxt, int xmlValidateElementDecl (xmlValidCtxtPtr ctxt, xmlDocPtr doc, xmlElementPtr elem); +xmlChar * xmlValidNormalizeAttributeValue(xmlDocPtr doc, + xmlNodePtr elem, + const xmlChar *name, + const xmlChar *value); int xmlValidateAttributeDecl(xmlValidCtxtPtr ctxt, xmlDocPtr doc, xmlAttributePtr attr); @@ -199,6 +221,8 @@ int xmlValidateNotationDecl (xmlValidCtxtPtr ctxt, int xmlValidateDtd (xmlValidCtxtPtr ctxt, xmlDocPtr doc, xmlDtdPtr dtd); +int xmlValidateDtdFinal (xmlValidCtxtPtr ctxt, + xmlDocPtr doc); int xmlValidateDocument (xmlValidCtxtPtr ctxt, xmlDocPtr doc); int xmlValidateElement (xmlValidCtxtPtr ctxt, diff --git a/include/libxml/xmlmemory.h b/include/libxml/xmlmemory.h index 64477a1c..11121fb5 100644 --- a/include/libxml/xmlmemory.h +++ b/include/libxml/xmlmemory.h @@ -8,7 +8,7 @@ #ifndef _DEBUG_MEMORY_ALLOC_ #define _DEBUG_MEMORY_ALLOC_ -#define NO_DEBUG_MEMORY +/* #define NO_DEBUG_MEMORY */ #ifdef NO_DEBUG_MEMORY #ifdef HAVE_MALLOC_H diff --git a/libxml.spec.in b/libxml.spec.in index ec674567..33706b5f 100644 --- a/libxml.spec.in +++ b/libxml.spec.in @@ -3,14 +3,13 @@ %define prefix /usr Summary: libXML library -Name: libxml +Name: libxml2 Version: %ver Release: 1 Copyright: LGPL Group: X11/Libraries Source: ftp://ftp.gnome.org/pub/GNOME/sources/libxml/libxml-%{ver}.tar.gz BuildRoot: /var/tmp/libxml-%{PACKAGE_VERSION}-root -Provides: libxml.so.0 URL: http://rpmfind.net/veillard/XML/ Prereq: /sbin/install-info diff --git a/nanoftp.c b/nanoftp.c index 4fa38852..e4f42141 100644 --- a/nanoftp.c +++ b/nanoftp.c @@ -869,10 +869,11 @@ xmlNanoFTPConnect(void *ctx) { else #ifndef HAVE_SNPRINTF len = sprintf(buf, "PASS libxml@%s\r\n", + hostname); #else /* HAVE_SNPRINTF */ len = snprintf(buf, sizeof(buf), "PASS libxml@%s\r\n", -#endif /* HAVE_SNPRINTF */ hostname); +#endif /* HAVE_SNPRINTF */ #ifdef DEBUG_FTP printf(buf); #endif @@ -1226,11 +1227,13 @@ xmlNanoFTPGetConnection(void *ctx) { portp = (unsigned char *) &dataAddr.sin_port; #ifndef HAVE_SNPRINTF len = sprintf(buf, "PORT %d,%d,%d,%d,%d,%d\r\n", + adp[0] & 0xff, adp[1] & 0xff, adp[2] & 0xff, adp[3] & 0xff, + portp[0] & 0xff, portp[1] & 0xff); #else /* HAVE_SNPRINTF */ len = snprintf(buf, sizeof(buf), "PORT %d,%d,%d,%d,%d,%d\r\n", + adp[0] & 0xff, adp[1] & 0xff, adp[2] & 0xff, adp[3] & 0xff, + portp[0] & 0xff, portp[1] & 0xff); #endif /* HAVE_SNPRINTF */ - adp[0] & 0xff, adp[1] & 0xff, adp[2] & 0xff, adp[3] & 0xff, - portp[0] & 0xff, portp[1] & 0xff); buf[sizeof(buf) - 1] = 0; #ifdef DEBUG_FTP printf(buf); @@ -1264,13 +1267,34 @@ int xmlNanoFTPCloseConnection(void *ctx) { xmlNanoFTPCtxtPtr ctxt = (xmlNanoFTPCtxtPtr) ctx; int res; + fd_set rfd, efd; + struct timeval tv; close(ctxt->dataFd); ctxt->dataFd = -1; - res = xmlNanoFTPGetResponse(ctxt); - if (res != 2) { + tv.tv_sec = 15; + tv.tv_usec = 0; + FD_ZERO(&rfd); + FD_SET(ctxt->controlFd, &rfd); + FD_ZERO(&efd); + FD_SET(ctxt->controlFd, &efd); + res = select(ctxt->controlFd + 1, &rfd, NULL, &efd, &tv); + if (res < 0) { +#ifdef DEBUG_FTP + perror("select"); +#endif close(ctxt->controlFd); ctxt->controlFd = -1; return(-1); } + if (res == 0) { + fprintf(stderr, "xmlNanoFTPCloseConnection: timeout\n"); + close(ctxt->controlFd); ctxt->controlFd = -1; + } else { + res = xmlNanoFTPGetResponse(ctxt); + if (res != 2) { + close(ctxt->controlFd); ctxt->controlFd = -1; + return(-1); + } + } return(0); } diff --git a/nanohttp.c b/nanohttp.c index b8cb24ed..438257b2 100644 --- a/nanohttp.c +++ b/nanohttp.c @@ -753,7 +753,7 @@ retry: } ctxt->fd = ret; if (proxy) { -#ifdef have_snprintf +#ifdef HAVE_SNPRINTF if (ctxt->port != 80) snprintf(buf, sizeof(buf), "GET http://%s:%d%s HTTP/1.0\r\nHost: %s\r\n\r\n", diff --git a/parser.c b/parser.c index bd32ef4b..b43f5306 100644 --- a/parser.c +++ b/parser.c @@ -47,6 +47,7 @@ #define XML_PARSER_BUFFER_SIZE 100 const char *xmlParserVersion = LIBXML_VERSION; +int xmlGetWarningsDefaultValue = 1; /* * List of XML prefixed PI allowed by W3C specs @@ -57,6 +58,10 @@ const char *xmlW3CPIs[] = { NULL }; +void xmlParserHandleReference(xmlParserCtxtPtr ctxt); +void xmlParserHandlePEReference(xmlParserCtxtPtr ctxt); +xmlEntityPtr xmlParseStringPEReference(xmlParserCtxtPtr ctxt, + const xmlChar **str); /************************************************************************ * * * Input handling functions for progressive parsing * @@ -263,7 +268,7 @@ xmlParserInputShrink(xmlParserInputPtr in) { int xmlSubstituteEntitiesDefaultValue = 0; int xmlDoValidityCheckingDefaultValue = 0; -int xmlKeepBlanksDefaultValue = 0; +int xmlKeepBlanksDefaultValue = 1; xmlEntityPtr xmlParseStringEntityRef(xmlParserCtxtPtr ctxt, const xmlChar ** str); @@ -303,6 +308,34 @@ PUSH_AND_POP(extern, xmlParserInputPtr, input) PUSH_AND_POP(extern, xmlNodePtr, node) PUSH_AND_POP(extern, xmlChar*, name) +int spacePush(xmlParserCtxtPtr ctxt, int val) { + if (ctxt->spaceNr >= ctxt->spaceMax) { + ctxt->spaceMax *= 2; + ctxt->spaceTab = (void *) xmlRealloc(ctxt->spaceTab, + ctxt->spaceMax * sizeof(ctxt->spaceTab[0])); + if (ctxt->spaceTab == NULL) { + fprintf(stderr, "realloc failed !\n"); + return(0); + } + } + ctxt->spaceTab[ctxt->spaceNr] = val; + ctxt->space = &ctxt->spaceTab[ctxt->spaceNr]; + return(ctxt->spaceNr++); +} + +int spacePop(xmlParserCtxtPtr ctxt) { + int ret; + if (ctxt->spaceNr <= 0) return(0); + ctxt->spaceNr--; + if (ctxt->spaceNr > 0) + ctxt->space = &ctxt->spaceTab[ctxt->spaceNr - 1]; + else + ctxt->space = NULL; + ret = ctxt->spaceTab[ctxt->spaceNr]; + ctxt->spaceTab[ctxt->spaceNr] = -1; + return(ret); +} + /* * Macros for accessing the content. Those should be used only by the parser, * and not exported. @@ -310,9 +343,11 @@ PUSH_AND_POP(extern, xmlChar*, name) * Dirty macros, i.e. one need to make assumption on the context to use them * * CUR_PTR return the current pointer to the xmlChar to be parsed. + * To be used with extreme caution since operations consuming + * characters may move the input buffer to a different location ! * CUR returns the current xmlChar value, i.e. a 8 bit value if compiled - * in ISO-Latin or UTF-8, and the current 16 bit value if compiled - * in UNICODE mode. This should be used internally by the parser + * in ISO-Latin or UTF-8. + * This should be used internally by the parser * only to compare to ASCII values otherwise it would break when * running with UTF-8 encoding. * NXT(n) returns the n'th next xmlChar. Same as CUR is should be used only @@ -322,17 +357,24 @@ PUSH_AND_POP(extern, xmlChar*, name) * * Clean macros, not dependent of an ASCII context, expect UTF-8 encoding * - * CURRENT Returns the current char value, with the full decoding of - * UTF-8 if we are using this mode. It returns an int. * NEXT Skip to the next character, this does the proper decoding * in UTF-8 mode. It also pop-up unfinished entities on the fly. * COPY(to) copy one char to *to, increment CUR_PTR and to accordingly + * CUR_CHAR Return the current char as an int as well as its lenght. */ +#define RAW (ctxt->token ? -1 : (*ctxt->input->cur)) #define CUR (ctxt->token ? ctxt->token : (*ctxt->input->cur)) -#define SKIP(val) ctxt->nbChars += (val),ctxt->input->cur += (val) #define NXT(val) ctxt->input->cur[(val)] #define CUR_PTR ctxt->input->cur + +#define SKIP(val) ctxt->nbChars += (val),ctxt->input->cur += (val); \ + if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \ + if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt); \ + if ((*ctxt->input->cur == 0) && \ + (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) \ + xmlPopInput(ctxt) + #define SHRINK xmlParserInputShrink(ctxt->input); \ if ((*ctxt->input->cur == 0) && \ (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) \ @@ -343,35 +385,471 @@ PUSH_AND_POP(extern, xmlChar*, name) (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) \ xmlPopInput(ctxt) -#define SKIP_BLANKS \ - do { \ - while (IS_BLANK(CUR)) NEXT; \ - while ((CUR == 0) && (ctxt->inputNr > 1)) \ - xmlPopInput(ctxt); \ - if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \ - if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt); \ - } while (IS_BLANK(CUR)); +#define SKIP_BLANKS xmlSkipBlankChars(ctxt); -#define CURRENT (*ctxt->input->cur) -#define NEXT { \ - if (ctxt->token != 0) ctxt->token = 0; \ - else { \ - if ((*ctxt->input->cur == 0) && \ - (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) { \ - xmlPopInput(ctxt); \ - } else { \ - if (*(ctxt->input->cur) == '\n') { \ - ctxt->input->line++; ctxt->input->col = 1; \ - } else ctxt->input->col++; \ - ctxt->input->cur++; \ - ctxt->nbChars++; \ - if (*ctxt->input->cur == 0) \ - xmlParserInputGrow(ctxt->input, INPUT_CHUNK); \ - } \ +#define NEXT xmlNextChar(ctxt); + +#define NEXTL(l) \ + if (*(ctxt->input->cur) == '\n') { \ + ctxt->input->line++; ctxt->input->col = 1; \ + } else ctxt->input->col++; \ + ctxt->token = 0; ctxt->input->cur += l; \ if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \ - if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt); \ -}} + if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt); +#define CUR_CHAR(l) xmlCurrentChar(ctxt, &l); +#define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l); + +#define COPY_BUF(l,b,i,v) \ + if (l == 1) b[i++] = (xmlChar) v; \ + else i += xmlCopyChar(l,&b[i],v); + +/** + * xmlNextChar: + * @ctxt: the XML parser context + * + * Skip to the next char input char. + */ + +void +xmlNextChar(xmlParserCtxtPtr ctxt) { + /* + * TODO: 2.11 End-of-Line Handling + * the literal two-character sequence "#xD#xA" or a standalone + * literal #xD, an XML processor must pass to the application + * the single character #xA. + */ + if (ctxt->token != 0) ctxt->token = 0; + else { + if ((*ctxt->input->cur == 0) && + (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0) && + (ctxt->instate != XML_PARSER_COMMENT)) { + /* + * If we are at the end of the current entity and + * the context allows it, we pop consumed entities + * automatically. + * TODO: the auto closing should be blocked in other cases + */ + xmlPopInput(ctxt); + } else { + if (*(ctxt->input->cur) == '\n') { + ctxt->input->line++; ctxt->input->col = 1; + } else ctxt->input->col++; + if (ctxt->encoding == NULL) { + /* + * We are supposed to handle UTF8, check it's valid + * From rfc2044: encoding of the Unicode values on UTF-8: + * + * UCS-4 range (hex.) UTF-8 octet sequence (binary) + * 0000 0000-0000 007F 0xxxxxxx + * 0000 0080-0000 07FF 110xxxxx 10xxxxxx + * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx + * + * Check for the 0x110000 limit too + */ + const unsigned char *cur = ctxt->input->cur; + unsigned char c; + + c = *cur; + if (c & 0x80) { + if (cur[1] == 0) + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + if ((cur[1] & 0xc0) != 0x80) + goto encoding_error; + if ((c & 0xe0) == 0xe0) { + unsigned int val; + + if (cur[2] == 0) + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + if ((cur[2] & 0xc0) != 0x80) + goto encoding_error; + if ((c & 0xf0) == 0xf0) { + if (cur[3] == 0) + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + if (((c & 0xf8) != 0xf0) || + ((cur[3] & 0xc0) != 0x80)) + goto encoding_error; + /* 4-byte code */ + ctxt->input->cur += 4; + val = (cur[0] & 0x7) << 18; + val |= (cur[1] & 0x3f) << 12; + val |= (cur[2] & 0x3f) << 6; + val |= cur[3] & 0x3f; + } else { + /* 3-byte code */ + ctxt->input->cur += 3; + val = (cur[0] & 0xf) << 12; + val |= (cur[1] & 0x3f) << 6; + val |= cur[2] & 0x3f; + } + if (((val > 0xd7ff) && (val < 0xe000)) || + ((val > 0xfffd) && (val < 0x10000)) || + (val >= 0x110000)) { + if ((ctxt->sax != NULL) && + (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "Char out of allowed range\n"); + ctxt->errNo = XML_ERR_INVALID_ENCODING; + ctxt->wellFormed = 0; + ctxt->disableSAX = 1; + } + } else + /* 2-byte code */ + ctxt->input->cur += 2; + } else + /* 1-byte code */ + ctxt->input->cur++; + } else { + /* + * Assume it's a fixed lenght encoding (1) with + * a compatibke encoding for the ASCII set, since + * XML constructs only use < 128 chars + */ + ctxt->input->cur++; + } + ctxt->nbChars++; + if (*ctxt->input->cur == 0) + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + } + } + if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); + if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt); + if ((*ctxt->input->cur == 0) && + (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) + xmlPopInput(ctxt); + return; +encoding_error: + /* + * If we detect an UTF8 error that probably mean that the + * input encoding didn't get properly advertized in the + * declaration header. Report the error and switch the encoding + * to ISO-Latin-1 (if you don't like this policy, just declare the + * encoding !) + */ + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "Input is not proper UTF-8, indicate encoding !\n"); + ctxt->errNo = XML_ERR_INVALID_ENCODING; + + ctxt->encoding = xmlStrdup(BAD_CAST "ISO-8859-1"); + ctxt->input->cur++; + return; +} + +/** + * xmlCurrentChar: + * @ctxt: the XML parser context + * @len: pointer to the length of the char read + * + * The current char value, if using UTF-8 this may actaully span multiple + * bytes in the input buffer. Implement the end of line normalization: + * 2.11 End-of-Line Handling + * Wherever an external parsed entity or the literal entity value + * of an internal parsed entity contains either the literal two-character + * sequence "#xD#xA" or a standalone literal #xD, an XML processor + * must pass to the application the single character #xA. + * This behavior can conveniently be produced by normalizing all + * line breaks to #xA on input, before parsing.) + * + * Returns the current char value and its lenght + */ + +int +xmlCurrentChar(xmlParserCtxtPtr ctxt, int *len) { + if (ctxt->token != 0) { + *len = 0; + return(ctxt->token); + } + if (ctxt->encoding == NULL) { + /* + * We are supposed to handle UTF8, check it's valid + * From rfc2044: encoding of the Unicode values on UTF-8: + * + * UCS-4 range (hex.) UTF-8 octet sequence (binary) + * 0000 0000-0000 007F 0xxxxxxx + * 0000 0080-0000 07FF 110xxxxx 10xxxxxx + * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx + * + * Check for the 0x110000 limit too + */ + const unsigned char *cur = ctxt->input->cur; + unsigned char c; + unsigned int val; + + c = *cur; + if (c & 0x80) { + if (cur[1] == 0) + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + if ((cur[1] & 0xc0) != 0x80) + goto encoding_error; + if ((c & 0xe0) == 0xe0) { + + if (cur[2] == 0) + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + if ((cur[2] & 0xc0) != 0x80) + goto encoding_error; + if ((c & 0xf0) == 0xf0) { + if (cur[3] == 0) + xmlParserInputGrow(ctxt->input, INPUT_CHUNK); + if (((c & 0xf8) != 0xf0) || + ((cur[3] & 0xc0) != 0x80)) + goto encoding_error; + /* 4-byte code */ + *len = 4; + val = (cur[0] & 0x7) << 18; + val |= (cur[1] & 0x3f) << 12; + val |= (cur[2] & 0x3f) << 6; + val |= cur[3] & 0x3f; + } else { + /* 3-byte code */ + *len = 3; + val = (cur[0] & 0xf) << 12; + val |= (cur[1] & 0x3f) << 6; + val |= cur[2] & 0x3f; + } + } else { + /* 2-byte code */ + *len = 2; + val = (cur[0] & 0x1f) << 6; + val |= cur[1] & 0x3f; + } + if (!IS_CHAR(val)) { + if ((ctxt->sax != NULL) && + (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "Char out of allowed range\n"); + ctxt->errNo = XML_ERR_INVALID_ENCODING; + ctxt->wellFormed = 0; + ctxt->disableSAX = 1; + } + return(val); + } else { + /* 1-byte code */ + *len = 1; + if (*ctxt->input->cur == 0xD) { + if (ctxt->input->cur[1] == 0xA) { + ctxt->nbChars++; + ctxt->input->cur++; + } + return(0xA); + } + return((int) *ctxt->input->cur); + } + } + /* + * Assume it's a fixed lenght encoding (1) with + * a compatibke encoding for the ASCII set, since + * XML constructs only use < 128 chars + */ + *len = 1; + if (*ctxt->input->cur == 0xD) { + if (ctxt->input->cur[1] == 0xA) { + ctxt->nbChars++; + ctxt->input->cur++; + } + return(0xA); + } + return((int) *ctxt->input->cur); +encoding_error: + /* + * If we detect an UTF8 error that probably mean that the + * input encoding didn't get properly advertized in the + * declaration header. Report the error and switch the encoding + * to ISO-Latin-1 (if you don't like this policy, just declare the + * encoding !) + */ + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "Input is not proper UTF-8, indicate encoding !\n"); + ctxt->errNo = XML_ERR_INVALID_ENCODING; + + ctxt->encoding = xmlStrdup(BAD_CAST "ISO-8859-1"); + *len = 1; + return((int) *ctxt->input->cur); +} + +/** + * xmlStringCurrentChar: + * @ctxt: the XML parser context + * @cur: pointer to the beginning of the char + * @len: pointer to the length of the char read + * + * The current char value, if using UTF-8 this may actaully span multiple + * bytes in the input buffer. + * + * Returns the current char value and its lenght + */ + +int +xmlStringCurrentChar(xmlParserCtxtPtr ctxt, const xmlChar *cur, int *len) { + if (ctxt->encoding == NULL) { + /* + * We are supposed to handle UTF8, check it's valid + * From rfc2044: encoding of the Unicode values on UTF-8: + * + * UCS-4 range (hex.) UTF-8 octet sequence (binary) + * 0000 0000-0000 007F 0xxxxxxx + * 0000 0080-0000 07FF 110xxxxx 10xxxxxx + * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx + * + * Check for the 0x110000 limit too + */ + unsigned char c; + unsigned int val; + + c = *cur; + if (c & 0x80) { + if ((cur[1] & 0xc0) != 0x80) + goto encoding_error; + if ((c & 0xe0) == 0xe0) { + + if ((cur[2] & 0xc0) != 0x80) + goto encoding_error; + if ((c & 0xf0) == 0xf0) { + if (((c & 0xf8) != 0xf0) || + ((cur[3] & 0xc0) != 0x80)) + goto encoding_error; + /* 4-byte code */ + *len = 4; + val = (cur[0] & 0x7) << 18; + val |= (cur[1] & 0x3f) << 12; + val |= (cur[2] & 0x3f) << 6; + val |= cur[3] & 0x3f; + } else { + /* 3-byte code */ + *len = 3; + val = (cur[0] & 0xf) << 12; + val |= (cur[1] & 0x3f) << 6; + val |= cur[2] & 0x3f; + } + } else { + /* 2-byte code */ + *len = 2; + val = (cur[0] & 0x1f) << 6; + val |= cur[2] & 0x3f; + } + if (!IS_CHAR(val)) { + if ((ctxt->sax != NULL) && + (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "Char out of allowed range\n"); + ctxt->errNo = XML_ERR_INVALID_ENCODING; + ctxt->wellFormed = 0; + ctxt->disableSAX = 1; + } + return(val); + } else { + /* 1-byte code */ + *len = 1; + return((int) *cur); + } + } + /* + * Assume it's a fixed lenght encoding (1) with + * a compatibke encoding for the ASCII set, since + * XML constructs only use < 128 chars + */ + *len = 1; + return((int) *cur); +encoding_error: + /* + * If we detect an UTF8 error that probably mean that the + * input encoding didn't get properly advertized in the + * declaration header. Report the error and switch the encoding + * to ISO-Latin-1 (if you don't like this policy, just declare the + * encoding !) + */ + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "Input is not proper UTF-8, indicate encoding !\n"); + ctxt->errNo = XML_ERR_INVALID_ENCODING; + + *len = 1; + return((int) *cur); +} + +/** + * xmlCopyChar: + * @len: pointer to the length of the char read (or zero) + * @array: pointer to an arry of xmlChar + * @val: the char value + * + * append the char value in the array + * + * Returns the number of xmlChar written + */ + +int +xmlCopyChar(int len, xmlChar *out, int val) { + /* + * We are supposed to handle UTF8, check it's valid + * From rfc2044: encoding of the Unicode values on UTF-8: + * + * UCS-4 range (hex.) UTF-8 octet sequence (binary) + * 0000 0000-0000 007F 0xxxxxxx + * 0000 0080-0000 07FF 110xxxxx 10xxxxxx + * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx + */ + if (len == 0) { + if (val < 0) len = 0; + else if (val < 0x80) len = 1; + else if (val < 0x800) len = 2; + else if (val < 0x10000) len = 3; + else if (val < 0x110000) len = 4; + if (len == 0) { + fprintf(stderr, "Internal error, xmlCopyChar 0x%X out of bound\n", + val); + return(0); + } + } + if (len > 1) { + int bits; + + if (val < 0x80) { *out++= val; bits= -6; } + else if (val < 0x800) { *out++= (val >> 6) | 0xC0; bits= 0; } + else if (val < 0x10000) { *out++= (val >> 12) | 0xE0; bits= 6; } + else { *out++= (val >> 18) | 0xF0; bits= 12; } + + for ( ; bits >= 0; bits-= 6) + *out++= ((val >> bits) & 0x3F) | 0x80 ; + + return(len); + } + *out = (xmlChar) val; + return(1); +} + +/** + * xmlSkipBlankChars: + * @ctxt: the XML parser context + * + * skip all blanks character found at that point in the input streams. + * It pops up finished entities in the process if allowable at that point. + * + * Returns the number of space chars skipped + */ + +int +xmlSkipBlankChars(xmlParserCtxtPtr ctxt) { + int cur, res = 0; + + do { + cur = CUR; + while (IS_BLANK(cur)) { + NEXT; + cur = CUR; + res++; + } + while ((cur == 0) && (ctxt->inputNr > 1) && + (ctxt->instate != XML_PARSER_COMMENT)) { + xmlPopInput(ctxt); + cur = CUR; + } + if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); + if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt); + } while (IS_BLANK(cur)); + return(res); +} /************************************************************************ * * @@ -410,6 +888,7 @@ void xmlPushInput(xmlParserCtxtPtr ctxt, xmlParserInputPtr input) { if (input == NULL) return; inputPush(ctxt, input); + GROW; } /** @@ -424,6 +903,8 @@ xmlFreeInputStream(xmlParserInputPtr input) { if (input->filename != NULL) xmlFree((char *) input->filename); if (input->directory != NULL) xmlFree((char *) input->directory); + if (input->encoding != NULL) xmlFree((char *) input->encoding); + if (input->version != NULL) xmlFree((char *) input->version); if ((input->free != NULL) && (input->base != NULL)) input->free((xmlChar *) input->base); if (input->buf != NULL) @@ -452,17 +933,10 @@ xmlNewInputStream(xmlParserCtxtPtr ctxt) { ctxt->errNo = XML_ERR_NO_MEMORY; return(NULL); } - input->filename = NULL; - input->directory = NULL; - input->base = NULL; - input->cur = NULL; - input->buf = NULL; + memset(input, 0, sizeof(xmlParserInput)); input->line = 1; input->col = 1; - input->buf = NULL; - input->free = NULL; - input->consumed = 0; - input->length = 0; + input->standalone = -1; return(input); } @@ -488,7 +962,7 @@ xmlNewEntityInputStream(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) { return(NULL); } if (entity->content == NULL) { - switch (entity->type) { + switch (entity->etype) { case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: ctxt->errNo = XML_ERR_UNPARSED_ENTITY; if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) @@ -523,7 +997,7 @@ xmlNewEntityInputStream(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) { if (input == NULL) { return(NULL); } - input->filename = (char *) entity->SystemID; /* TODO !!! char <- xmlChar */ + input->filename = (char *) entity->SystemID; input->base = entity->content; input->cur = entity->content; input->length = entity->length; @@ -642,16 +1116,20 @@ xmlInitParserCtxt(xmlParserCtxtPtr ctxt) { xmlSAXHandler *sax; + xmlDefaultSAXHandlerInit(); + sax = (xmlSAXHandler *) xmlMalloc(sizeof(xmlSAXHandler)); if (sax == NULL) { fprintf(stderr, "xmlInitParserCtxt: out of memory\n"); } + memset(sax, 0, sizeof(xmlSAXHandler)); /* Allocate the Input stack */ ctxt->inputTab = (xmlParserInputPtr *) xmlMalloc(5 * sizeof(xmlParserInputPtr)); ctxt->inputNr = 0; ctxt->inputMax = 5; ctxt->input = NULL; + ctxt->version = NULL; ctxt->encoding = NULL; ctxt->standalone = -1; @@ -675,8 +1153,16 @@ xmlInitParserCtxt(xmlParserCtxtPtr ctxt) ctxt->nameMax = 10; ctxt->name = NULL; - if (sax == NULL) ctxt->sax = &xmlDefaultSAXHandler; - else { + /* Allocate the space stack */ + ctxt->spaceTab = (int *) xmlMalloc(10 * sizeof(int)); + ctxt->spaceNr = 1; + ctxt->spaceMax = 10; + ctxt->spaceTab[0] = -1; + ctxt->space = &ctxt->spaceTab[0]; + + if (sax == NULL) { + ctxt->sax = &xmlDefaultSAXHandler; + } else { ctxt->sax = sax; memcpy(sax, &xmlDefaultSAXHandler, sizeof(xmlSAXHandler)); } @@ -689,7 +1175,15 @@ xmlInitParserCtxt(xmlParserCtxtPtr ctxt) ctxt->vctxt.userData = ctxt; if (ctxt->validate) { ctxt->vctxt.error = xmlParserValidityError; - ctxt->vctxt.warning = xmlParserValidityWarning; + if (xmlGetWarningsDefaultValue == 0) + ctxt->vctxt.warning = NULL; + else + ctxt->vctxt.warning = xmlParserValidityWarning; + /* Allocate the Node stack */ + ctxt->vctxt.nodeTab = (xmlNodePtr *) xmlMalloc(4 * sizeof(xmlNodePtr)); + ctxt->vctxt.nodeNr = 0; + ctxt->vctxt.nodeMax = 4; + ctxt->vctxt.node = NULL; } else { ctxt->vctxt.error = NULL; ctxt->vctxt.warning = NULL; @@ -698,7 +1192,9 @@ xmlInitParserCtxt(xmlParserCtxtPtr ctxt) ctxt->record_info = 0; ctxt->nbChars = 0; ctxt->checkIndex = 0; + ctxt->inSubset = 0; ctxt->errNo = XML_ERR_OK; + ctxt->depth = 0; xmlInitNodeInfoSeq(&ctxt->node_seq); } @@ -724,11 +1220,16 @@ xmlFreeParserCtxt(xmlParserCtxtPtr ctxt) while ((oldname = namePop(ctxt)) != NULL) { xmlFree(oldname); } + if (ctxt->spaceTab != NULL) xmlFree(ctxt->spaceTab); if (ctxt->nameTab != NULL) xmlFree(ctxt->nameTab); if (ctxt->nodeTab != NULL) xmlFree(ctxt->nodeTab); if (ctxt->inputTab != NULL) xmlFree(ctxt->inputTab); if (ctxt->version != NULL) xmlFree((char *) ctxt->version); if (ctxt->encoding != NULL) xmlFree((char *) ctxt->encoding); + if (ctxt->intSubName != NULL) xmlFree((char *) ctxt->intSubName); + if (ctxt->extSubURI != NULL) xmlFree((char *) ctxt->extSubURI); + if (ctxt->extSubSystem != NULL) xmlFree((char *) ctxt->extSubSystem); + if (ctxt->vctxt.nodeTab != NULL) xmlFree(ctxt->vctxt.nodeTab); if ((ctxt->sax != NULL) && (ctxt->sax != &xmlDefaultSAXHandler)) xmlFree(ctxt->sax); if (ctxt->directory != NULL) xmlFree((char *) ctxt->directory); @@ -754,6 +1255,7 @@ xmlNewParserCtxt() perror("malloc"); return(NULL); } + memset(ctxt, 0, sizeof(xmlParserCtxt)); xmlInitParserCtxt(ctxt); return(ctxt); } @@ -778,10 +1280,18 @@ xmlClearParserCtxt(xmlParserCtxtPtr ctxt) * * ************************************************************************/ -void xmlParserHandleReference(xmlParserCtxtPtr ctxt); -void xmlParserHandlePEReference(xmlParserCtxtPtr ctxt); -xmlEntityPtr xmlParseStringPEReference(xmlParserCtxtPtr ctxt, - const xmlChar **str); +/** + * xmlCheckEntity: + * @ctxt: an XML parser context + * @content: the entity content string + * + * Parse an entity content and checks the WF constraints + * + */ + +void +xmlCheckEntity(xmlParserCtxtPtr ctxt, const xmlChar *content) { +} /** * xmlParseCharRef: @@ -807,15 +1317,15 @@ xmlParseCharRef(xmlParserCtxtPtr ctxt) { ctxt->token = 0; return(val); } - if ((CUR == '&') && (NXT(1) == '#') && + if ((RAW == '&') && (NXT(1) == '#') && (NXT(2) == 'x')) { SKIP(3); - while (CUR != ';') { - if ((CUR >= '0') && (CUR <= '9')) + while (RAW != ';') { + if ((RAW >= '0') && (RAW <= '9')) val = val * 16 + (CUR - '0'); - else if ((CUR >= 'a') && (CUR <= 'f')) + else if ((RAW >= 'a') && (RAW <= 'f')) val = val * 16 + (CUR - 'a') + 10; - else if ((CUR >= 'A') && (CUR <= 'F')) + else if ((RAW >= 'A') && (RAW <= 'F')) val = val * 16 + (CUR - 'A') + 10; else { ctxt->errNo = XML_ERR_INVALID_HEX_CHARREF; @@ -823,17 +1333,21 @@ xmlParseCharRef(xmlParserCtxtPtr ctxt) { ctxt->sax->error(ctxt->userData, "xmlParseCharRef: invalid hexadecimal value\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; val = 0; break; } NEXT; } - if (CUR == ';') - SKIP(1); /* on purpose to avoid reentrancy problems with NEXT */ - } else if ((CUR == '&') && (NXT(1) == '#')) { + if (RAW == ';') { + /* on purpose to avoid reentrancy problems with NEXT and SKIP */ + ctxt->nbChars ++; + ctxt->input->cur++; + } + } else if ((RAW == '&') && (NXT(1) == '#')) { SKIP(2); - while (CUR != ';') { - if ((CUR >= '0') && (CUR <= '9')) + while (RAW != ';') { + if ((RAW >= '0') && (RAW <= '9')) val = val * 10 + (CUR - '0'); else { ctxt->errNo = XML_ERR_INVALID_DEC_CHARREF; @@ -841,19 +1355,24 @@ xmlParseCharRef(xmlParserCtxtPtr ctxt) { ctxt->sax->error(ctxt->userData, "xmlParseCharRef: invalid decimal value\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; val = 0; break; } NEXT; } - if (CUR == ';') - SKIP(1); /* on purpose to avoid reentrancy problems with NEXT */ + if (RAW == ';') { + /* on purpose to avoid reentrancy problems with NEXT and SKIP */ + ctxt->nbChars ++; + ctxt->input->cur++; + } } else { ctxt->errNo = XML_ERR_INVALID_CHARREF; if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "xmlParseCharRef: invalid value\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } /* @@ -869,6 +1388,7 @@ xmlParseCharRef(xmlParserCtxtPtr ctxt) { ctxt->sax->error(ctxt->userData, "CharRef: invalid xmlChar value %d\n", val); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } return(0); } @@ -916,6 +1436,7 @@ xmlParseStringCharRef(xmlParserCtxtPtr ctxt, const xmlChar **str) { ctxt->sax->error(ctxt->userData, "xmlParseCharRef: invalid hexadecimal value\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; val = 0; break; } @@ -936,6 +1457,7 @@ xmlParseStringCharRef(xmlParserCtxtPtr ctxt, const xmlChar **str) { ctxt->sax->error(ctxt->userData, "xmlParseCharRef: invalid decimal value\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; val = 0; break; } @@ -950,6 +1472,7 @@ xmlParseStringCharRef(xmlParserCtxtPtr ctxt, const xmlChar **str) { ctxt->sax->error(ctxt->userData, "xmlParseCharRef: invalid value\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return(0); } *str = ptr; @@ -967,6 +1490,7 @@ xmlParseStringCharRef(xmlParserCtxtPtr ctxt, const xmlChar **str) { ctxt->sax->error(ctxt->userData, "CharRef: invalid xmlChar value %d\n", val); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } return(0); } @@ -1003,14 +1527,15 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { if (ctxt->token != 0) { return; } - if (CUR != '&') return; + if (RAW != '&') return; GROW; - if ((CUR == '&') && (NXT(1) == '#')) { + if ((RAW == '&') && (NXT(1) == '#')) { switch(ctxt->instate) { case XML_PARSER_ENTITY_DECL: case XML_PARSER_PI: case XML_PARSER_CDATA_SECTION: case XML_PARSER_COMMENT: + case XML_PARSER_SYSTEM_LITERAL: /* we just ignore it there */ return; case XML_PARSER_START_TAG: @@ -1022,6 +1547,7 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "CharRef at EOF\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; case XML_PARSER_PROLOG: case XML_PARSER_START: @@ -1030,12 +1556,14 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "CharRef in prolog!\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; case XML_PARSER_EPILOG: ctxt->errNo = XML_ERR_CHARREF_IN_EPILOG; if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "CharRef in epilog!\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; case XML_PARSER_DTD: ctxt->errNo = XML_ERR_CHARREF_IN_DTD; @@ -1043,6 +1571,7 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { ctxt->sax->error(ctxt->userData, "CharRef are forbiden in DTDs!\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; case XML_PARSER_ENTITY_VALUE: /* @@ -1055,7 +1584,6 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { return; case XML_PARSER_CONTENT: case XML_PARSER_ATTRIBUTE_VALUE: - /* !!! this may not be Ok for UTF-8, multibyte sequence */ ctxt->token = xmlParseCharRef(ctxt); return; } @@ -1067,6 +1595,8 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { return; case XML_PARSER_PI: case XML_PARSER_COMMENT: + case XML_PARSER_SYSTEM_LITERAL: + case XML_PARSER_CONTENT: return; case XML_PARSER_START_TAG: return; @@ -1077,6 +1607,7 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "Reference at EOF\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; case XML_PARSER_PROLOG: case XML_PARSER_START: @@ -1085,12 +1616,14 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "Reference in prolog!\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; case XML_PARSER_EPILOG: ctxt->errNo = XML_ERR_ENTITYREF_IN_EPILOG; if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "Reference in epilog!\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; case XML_PARSER_ENTITY_VALUE: /* @@ -1123,8 +1656,7 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { ctxt->sax->error(ctxt->userData, "Entity references are forbiden in DTDs!\n"); ctxt->wellFormed = 0; - return; - case XML_PARSER_CONTENT: + ctxt->disableSAX = 1; return; } @@ -1135,6 +1667,7 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "Entity reference: no name\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; ctxt->token = '&'; return; } @@ -1144,6 +1677,7 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { ctxt->sax->error(ctxt->userData, "Entity reference: ';' expected\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; ctxt->token = '&'; xmlFree(name); return; @@ -1169,6 +1703,7 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { "Entity reference: entity %s not declared\n", name); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; xmlFree(name); return; } @@ -1177,15 +1712,16 @@ xmlParserHandleReference(xmlParserCtxtPtr ctxt) { * [ WFC: Parsed Entity ] * An entity reference must not contain the name of an unparsed entity */ - if (ent->type == XML_EXTERNAL_GENERAL_UNPARSED_ENTITY) { + if (ent->etype == XML_EXTERNAL_GENERAL_UNPARSED_ENTITY) { ctxt->errNo = XML_ERR_UNPARSED_ENTITY; if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "Entity reference to unparsed entity %s\n", name); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } - if (ent->type == XML_INTERNAL_PREDEFINED_ENTITY) { + if (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY) { ctxt->token = ent->content[0]; xmlFree(name); return; @@ -1237,7 +1773,7 @@ xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) { if (ctxt->token != 0) { return; } - if (CUR != '%') return; + if (RAW != '%') return; switch(ctxt->instate) { case XML_PARSER_CDATA_SECTION: return; @@ -1252,6 +1788,7 @@ xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "PEReference at EOF\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; case XML_PARSER_PROLOG: case XML_PARSER_START: @@ -1260,11 +1797,13 @@ xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "PEReference in prolog!\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; case XML_PARSER_ENTITY_DECL: case XML_PARSER_CONTENT: case XML_PARSER_ATTRIBUTE_VALUE: case XML_PARSER_PI: + case XML_PARSER_SYSTEM_LITERAL: /* we just ignore it there */ return; case XML_PARSER_EPILOG: @@ -1272,6 +1811,7 @@ xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "PEReference in epilog!\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; case XML_PARSER_ENTITY_VALUE: /* @@ -1301,8 +1841,9 @@ xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "xmlHandlePEReference: no name\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } else { - if (CUR == ';') { + if (RAW == ';') { NEXT; if ((ctxt->sax != NULL) && (ctxt->sax->getParameterEntity != NULL)) entity = ctxt->sax->getParameterEntity(ctxt->userData, name); @@ -1323,6 +1864,7 @@ xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) { ctxt->sax->error(ctxt->userData, "PEReference: %%%s; not found\n", name); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } else { /* * [ VC: Entity Declared ] @@ -1337,22 +1879,29 @@ xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) { ctxt->valid = 0; } } else { - if ((entity->type == XML_INTERNAL_PARAMETER_ENTITY) || - (entity->type == XML_EXTERNAL_PARAMETER_ENTITY)) { + if ((entity->etype == XML_INTERNAL_PARAMETER_ENTITY) || + (entity->etype == XML_EXTERNAL_PARAMETER_ENTITY)) { /* - * TODO !!!! handle the extra spaces added before and after + * TODO !!! handle the extra spaces added before and after * c.f. http://www.w3.org/TR/REC-xml#as-PE - * TODO !!!! Avoid quote processing in parameters value - * c.f. http://www.w3.org/TR/REC-xml#inliteral */ input = xmlNewEntityInputStream(ctxt, entity); xmlPushInput(ctxt, input); + if ((entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) && + (RAW == '<') && (NXT(1) == '?') && + (NXT(2) == 'x') && (NXT(3) == 'm') && + (NXT(4) == 'l') && (IS_BLANK(NXT(5)))) { + xmlParseTextDecl(ctxt); + } + if (ctxt->token == 0) + ctxt->token = ' '; } else { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "xmlHandlePEReference: %s is not a parameter entity\n", name); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } } } else { @@ -1361,6 +1910,7 @@ xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) { ctxt->sax->error(ctxt->userData, "xmlHandlePEReference: expecting ';'\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } xmlFree(name); } @@ -1400,13 +1950,22 @@ xmlDecodeEntities(xmlParserCtxtPtr ctxt, int len, int what, xmlChar end, xmlChar end2, xmlChar end3) { xmlChar *buffer = NULL; int buffer_size = 0; - xmlChar *out = NULL; + int nbchars = 0; xmlChar *current = NULL; xmlEntityPtr ent; - int nbchars = 0; unsigned int max = (unsigned int) len; - xmlChar cur; + int c,l; + + if (ctxt->depth > 40) { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "Detected entity reference loop\n"); + ctxt->wellFormed = 0; + ctxt->disableSAX = 1; + ctxt->errNo = XML_ERR_ENTITY_LOOP; + return(NULL); + } /* * allocate a translation buffer. @@ -1417,52 +1976,44 @@ xmlDecodeEntities(xmlParserCtxtPtr ctxt, int len, int what, perror("xmlDecodeEntities: malloc failed"); return(NULL); } - out = buffer; /* * Ok loop until we reach one of the ending char or a size limit. */ - cur = CUR; - while ((nbchars < max) && (cur != end) && - (cur != end2) && (cur != end3)) { + c = CUR_CHAR(l); + while ((nbchars < max) && (c != end) && + (c != end2) && (c != end3)) { - if (cur == 0) break; - if ((cur == '&') && (NXT(1) == '#')) { + if (c == 0) break; + if (((c == '&') && (ctxt->token != '&')) && (NXT(1) == '#')) { int val = xmlParseCharRef(ctxt); - *out++ = val; - nbchars += 3; - } else if ((cur == '&') && (what & XML_SUBSTITUTE_REF)) { + COPY_BUF(0,buffer,nbchars,val); + NEXTL(l); + } else if ((c == '&') && (ctxt->token != '&') && + (what & XML_SUBSTITUTE_REF)) { ent = xmlParseEntityRef(ctxt); if ((ent != NULL) && (ctxt->replaceEntities != 0)) { current = ent->content; while (*current != 0) { - *out++ = *current++; - if (out - buffer > buffer_size - XML_PARSER_BUFFER_SIZE) { - int index = out - buffer; - + buffer[nbchars++] = *current++; + if (nbchars > buffer_size - XML_PARSER_BUFFER_SIZE) { growBuffer(buffer); - out = &buffer[index]; } } - nbchars += 3 + xmlStrlen(ent->name); } else if (ent != NULL) { - int i = xmlStrlen(ent->name); const xmlChar *cur = ent->name; - nbchars += i + 2; - *out++ = '&'; - if (out - buffer > buffer_size - i - XML_PARSER_BUFFER_SIZE) { - int index = out - buffer; - + buffer[nbchars++] = '&'; + if (nbchars > buffer_size - XML_PARSER_BUFFER_SIZE) { growBuffer(buffer); - out = &buffer[index]; } - for (;i > 0;i--) - *out++ = *cur++; - *out++ = ';'; + while (*cur != 0) { + buffer[nbchars++] = *cur++; + } + buffer[nbchars++] = ';'; } - } else if (cur == '%' && (what & XML_SUBSTITUTE_PEREF)) { + } else if (c == '%' && (what & XML_SUBSTITUTE_PEREF)) { /* * a PEReference induce to switch the entity flow, * we break here to flush the current set of chars @@ -1475,25 +2026,20 @@ xmlDecodeEntities(xmlParserCtxtPtr ctxt, int len, int what, /* * Pop-up of finished entities. */ - while ((CUR == 0) && (ctxt->inputNr > 1)) + while ((RAW == 0) && (ctxt->inputNr > 1)) xmlPopInput(ctxt); break; } else { - /* invalid for UTF-8 , use COPY(out); !!!!!! */ - *out++ = cur; - nbchars++; - if (out - buffer > buffer_size - XML_PARSER_BUFFER_SIZE) { - int index = out - buffer; - + COPY_BUF(l,buffer,nbchars,c); + NEXTL(l); + if (nbchars > buffer_size - XML_PARSER_BUFFER_SIZE) { growBuffer(buffer); - out = &buffer[index]; } - NEXT; } - cur = CUR; + c = CUR_CHAR(l); } - *out++ = 0; + buffer[nbchars++] = 0; return(buffer); } @@ -1518,11 +2064,21 @@ xmlStringDecodeEntities(xmlParserCtxtPtr ctxt, const xmlChar *str, int what, xmlChar end, xmlChar end2, xmlChar end3) { xmlChar *buffer = NULL; int buffer_size = 0; - xmlChar *out = NULL; xmlChar *current = NULL; xmlEntityPtr ent; - xmlChar cur; + int c,l; + int nbchars = 0; + + if (ctxt->depth > 40) { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "Detected entity reference loop\n"); + ctxt->wellFormed = 0; + ctxt->disableSAX = 1; + ctxt->errNo = XML_ERR_ENTITY_LOOP; + return(NULL); + } /* * allocate a translation buffer. @@ -1533,77 +2089,82 @@ xmlStringDecodeEntities(xmlParserCtxtPtr ctxt, const xmlChar *str, int what, perror("xmlDecodeEntities: malloc failed"); return(NULL); } - out = buffer; /* * Ok loop until we reach one of the ending char or a size limit. */ - cur = *str; - while ((cur != 0) && (cur != end) && - (cur != end2) && (cur != end3)) { + c = CUR_SCHAR(str, l); + while ((c != 0) && (c != end) && (c != end2) && (c != end3)) { - if (cur == 0) break; - if ((cur == '&') && (str[1] == '#')) { + if (c == 0) break; + if ((c == '&') && (str[1] == '#')) { int val = xmlParseStringCharRef(ctxt, &str); - if (val != 0) - *out++ = val; - } else if ((cur == '&') && (what & XML_SUBSTITUTE_REF)) { + if (val != 0) { + COPY_BUF(0,buffer,nbchars,val); + } + } else if ((c == '&') && (what & XML_SUBSTITUTE_REF)) { ent = xmlParseStringEntityRef(ctxt, &str); - if ((ent != NULL) && - (ctxt->replaceEntities != 0)) { - current = ent->content; - while (*current != 0) { - *out++ = *current++; - if (out - buffer > buffer_size - XML_PARSER_BUFFER_SIZE) { - int index = out - buffer; + if ((ent != NULL) && (ent->content != NULL)) { + xmlChar *rep; - growBuffer(buffer); - out = &buffer[index]; + ctxt->depth++; + rep = xmlStringDecodeEntities(ctxt, ent->content, what, + 0, 0, 0); + ctxt->depth--; + if (rep != NULL) { + current = rep; + while (*current != 0) { + buffer[nbchars++] = *current++; + if (nbchars > + buffer_size - XML_PARSER_BUFFER_SIZE) { + growBuffer(buffer); + } } + xmlFree(rep); } } else if (ent != NULL) { int i = xmlStrlen(ent->name); const xmlChar *cur = ent->name; - *out++ = '&'; - if (out - buffer > buffer_size - i - XML_PARSER_BUFFER_SIZE) { - int index = out - buffer; - + buffer[nbchars++] = '&'; + if (nbchars > buffer_size - i - XML_PARSER_BUFFER_SIZE) { growBuffer(buffer); - out = &buffer[index]; } for (;i > 0;i--) - *out++ = *cur++; - *out++ = ';'; + buffer[nbchars++] = *cur++; + buffer[nbchars++] = ';'; } - } else if (cur == '%' && (what & XML_SUBSTITUTE_PEREF)) { + } else if (c == '%' && (what & XML_SUBSTITUTE_PEREF)) { ent = xmlParseStringPEReference(ctxt, &str); if (ent != NULL) { - current = ent->content; - while (*current != 0) { - *out++ = *current++; - if (out - buffer > buffer_size - XML_PARSER_BUFFER_SIZE) { - int index = out - buffer; + xmlChar *rep; - growBuffer(buffer); - out = &buffer[index]; + ctxt->depth++; + rep = xmlStringDecodeEntities(ctxt, ent->content, what, + 0, 0, 0); + ctxt->depth--; + if (rep != NULL) { + current = rep; + while (*current != 0) { + buffer[nbchars++] = *current++; + if (nbchars > + buffer_size - XML_PARSER_BUFFER_SIZE) { + growBuffer(buffer); + } } + xmlFree(rep); } } } else { - /* invalid for UTF-8 , use COPY(out); !!!!!! */ - *out++ = cur; - if (out - buffer > buffer_size - XML_PARSER_BUFFER_SIZE) { - int index = out - buffer; - + COPY_BUF(l,buffer,nbchars,c); + str += l; + if (nbchars > buffer_size - XML_PARSER_BUFFER_SIZE) { growBuffer(buffer); - out = &buffer[index]; } - str++; } - cur = *str; + c = CUR_SCHAR(str, l); } - *out = 0; + buffer[nbchars++] = 0; return(buffer); } @@ -1614,6 +2175,74 @@ xmlStringDecodeEntities(xmlParserCtxtPtr ctxt, const xmlChar *str, int what, * * ************************************************************************/ +/* + * xmlCheckLanguageID + * @lang: pointer to the string value + * + * Checks that the value conforms to the LanguageID production: + * + * [33] LanguageID ::= Langcode ('-' Subcode)* + * [34] Langcode ::= ISO639Code | IanaCode | UserCode + * [35] ISO639Code ::= ([a-z] | [A-Z]) ([a-z] | [A-Z]) + * [36] IanaCode ::= ('i' | 'I') '-' ([a-z] | [A-Z])+ + * [37] UserCode ::= ('x' | 'X') '-' ([a-z] | [A-Z])+ + * [38] Subcode ::= ([a-z] | [A-Z])+ + * + * Returns 1 if correct 0 otherwise + **/ +int +xmlCheckLanguageID(const xmlChar *lang) { + const xmlChar *cur = lang; + + if (cur == NULL) + return(0); + if (((cur[0] == 'i') && (cur[1] == '-')) || + ((cur[0] == 'I') && (cur[1] == '-'))) { + /* + * IANA code + */ + cur += 2; + while (((cur[0] >= 'A') && (cur[0] <= 'Z')) || + ((cur[0] >= 'a') && (cur[0] <= 'z'))) + cur++; + } else if (((cur[0] == 'x') && (cur[1] == '-')) || + ((cur[0] == 'X') && (cur[1] == '-'))) { + /* + * User code + */ + cur += 2; + while (((cur[0] >= 'A') && (cur[0] <= 'Z')) || + ((cur[0] >= 'a') && (cur[0] <= 'z'))) + cur++; + } else if (((cur[0] >= 'A') && (cur[0] <= 'Z')) || + ((cur[0] >= 'a') && (cur[0] <= 'z'))) { + /* + * ISO639 + */ + cur++; + if (((cur[0] >= 'A') && (cur[0] <= 'Z')) || + ((cur[0] >= 'a') && (cur[0] <= 'z'))) + cur++; + else + return(0); + } else + return(0); + while (cur[0] != 0) { + if (cur[0] != '-') + return(0); + cur++; + if (((cur[0] >= 'A') && (cur[0] <= 'Z')) || + ((cur[0] >= 'a') && (cur[0] <= 'z'))) + cur++; + else + return(0); + while (((cur[0] >= 'A') && (cur[0] <= 'Z')) || + ((cur[0] >= 'a') && (cur[0] <= 'z'))) + cur++; + } + return(1); +} + /** * xmlSwitchEncoding: * @ctxt: the parser context @@ -1625,12 +2254,158 @@ xmlStringDecodeEntities(xmlParserCtxtPtr ctxt, const xmlChar *str, int what, void xmlSwitchEncoding(xmlParserCtxtPtr ctxt, xmlCharEncoding enc) { + xmlCharEncodingHandlerPtr handler; + + handler = xmlGetCharEncodingHandler(enc); + if (handler != NULL) { + if (ctxt->input != NULL) { + if (ctxt->input->buf != NULL) { + if (ctxt->input->buf->encoder != NULL) { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "xmlSwitchEncoding : encoder already regitered\n"); + return; + } + ctxt->input->buf->encoder = handler; + + /* + * Is there already some content down the pipe to convert + */ + if ((ctxt->input->buf->buffer != NULL) && + (ctxt->input->buf->buffer->use > 0)) { + xmlChar *buf; + int res, len, size; + int processed; + + /* + * Specific handling of the Byte Order Mark for + * UTF-16 + */ + if ((enc == XML_CHAR_ENCODING_UTF16LE) && + (ctxt->input->cur[0] == 0xFF) && + (ctxt->input->cur[1] == 0xFE)) { + SKIP(2); + } + if ((enc == XML_CHAR_ENCODING_UTF16BE) && + (ctxt->input->cur[0] == 0xFE) && + (ctxt->input->cur[1] == 0xFF)) { + SKIP(2); + } + + /* + * convert the non processed part + */ + processed = ctxt->input->cur - ctxt->input->base; + len = ctxt->input->buf->buffer->use - processed; + + if (len <= 0) { + return; + } + size = ctxt->input->buf->buffer->use * 4; + if (size < 4000) + size = 4000; +retry_larger: + buf = (xmlChar *) xmlMalloc(size + 1); + if (buf == NULL) { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "xmlSwitchEncoding : out of memory\n"); + return; + } + /* TODO !!! Handling of buf too small */ + res = handler->input(buf, size, ctxt->input->cur, &len); + if (res == -1) { + size *= 2; + xmlFree(buf); + goto retry_larger; + } + if ((res < 0) || + (len != ctxt->input->buf->buffer->use - processed)) { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "xmlSwitchEncoding : conversion failed\n"); + xmlFree(buf); + return; + } + + /* + * Conversion succeeded, get rid of the old buffer + */ + xmlFree(ctxt->input->buf->buffer->content); + ctxt->input->buf->buffer->content = buf; + ctxt->input->base = buf; + ctxt->input->cur = buf; + ctxt->input->buf->buffer->size = size; + ctxt->input->buf->buffer->use = res; + buf[res] = 0; + } + return; + } else { + if (ctxt->input->length == 0) { + /* + * When parsing a static memory array one must know the + * size to be able to convert the buffer. + */ + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "xmlSwitchEncoding : no input\n"); + return; + } else { + xmlChar *buf; + int res, len; + int processed = ctxt->input->cur - ctxt->input->base; + + /* + * convert the non processed part + */ + len = ctxt->input->length - processed; + if (len <= 0) { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "xmlSwitchEncoding : input fully consumed?\n"); + return; + } + buf = (xmlChar *) xmlMalloc(ctxt->input->length * 4); + if (buf == NULL) { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "xmlSwitchEncoding : out of memory\n"); + return; + } + res = handler->input(buf, ctxt->input->length * 4, + ctxt->input->cur, &len); + if ((res < 0) || + (len != ctxt->input->length - processed)) { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "xmlSwitchEncoding : conversion failed\n"); + xmlFree(buf); + return; + } + /* + * Conversion succeeded, get rid of the old buffer + */ + if ((ctxt->input->free != NULL) && + (ctxt->input->base != NULL)) + ctxt->input->free((xmlChar *) ctxt->input->base); + ctxt->input->base = ctxt->input->cur = buf; + ctxt->input->length = res; + } + } + } else { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "xmlSwitchEncoding : no input\n"); + } + } + switch (enc) { case XML_CHAR_ENCODING_ERROR: ctxt->errNo = XML_ERR_UNKNOWN_ENCODING; if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "encoding unknown\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; break; case XML_CHAR_ENCODING_NONE: /* let's assume it's UTF-8 without the XML decl */ @@ -1796,7 +2571,9 @@ xmlStrndup(const xmlChar *cur, int len) { * xmlStrdup: * @cur: the input xmlChar * * - * a strdup for array of xmlChar's + * a strdup for array of xmlChar's. Since they are supposed to be + * encoded in UTF-8 or an encoding with 8bit based chars, we assume + * a termination mark of '0'. * * Returns a new xmlChar * or NULL */ @@ -1805,7 +2582,7 @@ xmlStrdup(const xmlChar *cur) { const xmlChar *p = cur; if (cur == NULL) return(NULL); - while (IS_CHAR(*p)) p++; + while (*p != 0) p++; return(xmlStrndup(cur, p - cur)); } @@ -2042,7 +2819,9 @@ xmlStrncat(xmlChar *cur, const xmlChar *add, int len) { * @cur: the original xmlChar * array * @add: the xmlChar * array added * - * a strcat for array of xmlChar's + * a strcat for array of xmlChar's. Since they are supposed to be + * encoded in UTF-8 or an encoding with 8bit based chars, we assume + * a termination mark of '0'. * * Returns a new xmlChar * containing the concatenated string. */ @@ -2054,7 +2833,7 @@ xmlStrcat(xmlChar *cur, const xmlChar *add) { if (cur == NULL) return(xmlStrdup(add)); - while (IS_CHAR(*p)) p++; + while (*p != 0) p++; return(xmlStrncat(cur, add, p - add)); } @@ -2079,6 +2858,12 @@ static int areBlanks(xmlParserCtxtPtr ctxt, const xmlChar *str, int len) { int i, ret; xmlNodePtr lastChild; + /* + * Check for xml:space value. + */ + if (*(ctxt->space) == 1) + return(0); + /* * Check that the string is made of blanks */ @@ -2095,22 +2880,22 @@ static int areBlanks(xmlParserCtxtPtr ctxt, const xmlChar *str, int len) { } /* - * Do we allow an heuristic on white space + * Otherwise, heuristic :-\ */ if (ctxt->keepBlanks) return(0); - if (CUR != '<') return(0); + if (RAW != '<') return(0); if (ctxt->node == NULL) return(0); - if ((ctxt->node->childs == NULL) && - (CUR == '<') && (NXT(1) == '/')) return(0); + if ((ctxt->node->children == NULL) && + (RAW == '<') && (NXT(1) == '/')) return(0); lastChild = xmlGetLastChild(ctxt->node); if (lastChild == NULL) { if (ctxt->node->content != NULL) return(0); } else if (xmlNodeIsText(lastChild)) return(0); - else if ((ctxt->node->childs != NULL) && - (xmlNodeIsText(ctxt->node->childs))) + else if ((ctxt->node->children != NULL) && + (xmlNodeIsText(ctxt->node->children))) return(0); return(1); } @@ -2137,6 +2922,7 @@ xmlHandleEntity(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) { ctxt->sax->error(ctxt->userData, "xmlHandleEntity %s: content == NULL\n", entity->name); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return; } len = xmlStrlen(entity->content); @@ -2153,7 +2939,8 @@ handle_as_char: /* * Just handle the content as a set of chars. */ - if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL)) + if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && + (ctxt->sax->characters != NULL)) ctxt->sax->characters(ctxt->userData, entity->content, len); } @@ -2187,27 +2974,32 @@ void xmlParseReference(xmlParserCtxtPtr ctxt); xmlChar * xmlNamespaceParseNCName(xmlParserCtxtPtr ctxt) { - xmlChar buf[XML_MAX_NAMELEN]; - int len = 0; + xmlChar buf[XML_MAX_NAMELEN + 5]; + int len = 0, l; + int cur = CUR_CHAR(l); - if (!IS_LETTER(CUR) && (CUR != '_')) return(NULL); + /* load first the value of the char !!! */ + if (!IS_LETTER(cur) && (cur != '_')) return(NULL); - while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) || - (CUR == '.') || (CUR == '-') || - (CUR == '_') || - (IS_COMBINING(CUR)) || - (IS_EXTENDER(CUR))) { - buf[len++] = CUR; - NEXT; + while ((IS_LETTER(cur)) || (IS_DIGIT(cur)) || + (cur == '.') || (cur == '-') || + (cur == '_') || + (IS_COMBINING(cur)) || + (IS_EXTENDER(cur))) { + COPY_BUF(l,buf,len,cur); + NEXTL(l); + cur = CUR_CHAR(l); if (len >= XML_MAX_NAMELEN) { fprintf(stderr, "xmlNamespaceParseNCName: reached XML_MAX_NAMELEN limit\n"); - while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) || - (CUR == '.') || (CUR == '-') || - (CUR == '_') || - (IS_COMBINING(CUR)) || - (IS_EXTENDER(CUR))) - NEXT; + while ((IS_LETTER(cur)) || (IS_DIGIT(cur)) || + (cur == '.') || (cur == '-') || + (cur == '_') || + (IS_COMBINING(cur)) || + (IS_EXTENDER(cur))) { + NEXTL(l); + cur = CUR_CHAR(l); + } break; } } @@ -2237,7 +3029,7 @@ xmlNamespaceParseQName(xmlParserCtxtPtr ctxt, xmlChar **prefix) { *prefix = NULL; ret = xmlNamespaceParseNCName(ctxt); - if (CUR == ':') { + if (RAW == ':') { *prefix = ret; NEXT; ret = xmlNamespaceParseNCName(ctxt); @@ -2248,6 +3040,7 @@ xmlNamespaceParseQName(xmlParserCtxtPtr ctxt, xmlChar **prefix) { /** * xmlSplitQName: + * @ctxt: an XML parser context * @name: an XML parser context * @prefix: a xmlChar ** * @@ -2264,10 +3057,12 @@ xmlNamespaceParseQName(xmlParserCtxtPtr ctxt, xmlChar **prefix) { */ xmlChar * -xmlSplitQName(const xmlChar *name, xmlChar **prefix) { +xmlSplitQName(xmlParserCtxtPtr ctxt, const xmlChar *name, xmlChar **prefix) { + xmlChar buf[XML_MAX_NAMELEN + 5]; + int len = 0; xmlChar *ret = NULL; - const xmlChar *q; const xmlChar *cur = name; + int c,l; *prefix = NULL; @@ -2276,33 +3071,43 @@ xmlSplitQName(const xmlChar *name, xmlChar **prefix) { (cur[2] == 'l') && (cur[3] == ':')) return(xmlStrdup(name)); - if (!IS_LETTER(*cur) && (*cur != '_')) return(NULL); - q = cur++; + /* nasty but valid */ + if (cur[0] == ':') + return(xmlStrdup(name)); - while ((IS_LETTER(*cur)) || (IS_DIGIT(*cur)) || - (*cur == '.') || (*cur == '-') || - (*cur == '_') || - (IS_COMBINING(*cur)) || - (IS_EXTENDER(*cur))) - cur++; + c = CUR_SCHAR(cur, l); + if (!IS_LETTER(c) && (c != '_')) return(NULL); + + while ((IS_LETTER(c)) || (IS_DIGIT(c)) || + (c == '.') || (c == '-') || + (c == '_') || + (IS_COMBINING(c)) || + (IS_EXTENDER(c))) { + COPY_BUF(l,buf,len,c); + cur += l; + c = CUR_SCHAR(cur, l); + } - ret = xmlStrndup(q, cur - q); + ret = xmlStrndup(buf, len); - if (*cur == ':') { - cur++; - if (!IS_LETTER(*cur) && (*cur != '_')) return(ret); + if (c == ':') { + cur += l; + c = CUR_SCHAR(cur, l); + if (!IS_LETTER(c) && (c != '_')) return(ret); *prefix = ret; + len = 0; - q = cur++; - - while ((IS_LETTER(*cur)) || (IS_DIGIT(*cur)) || - (*cur == '.') || (*cur == '-') || - (*cur == '_') || - (IS_COMBINING(*cur)) || - (IS_EXTENDER(*cur))) - cur++; + while ((IS_LETTER(c)) || (IS_DIGIT(c)) || + (c == '.') || (c == '-') || + (c == '_') || + (IS_COMBINING(c)) || + (IS_EXTENDER(c))) { + COPY_BUF(l,buf,len,c); + cur += l; + c = CUR_SCHAR(cur, l); + } - ret = xmlStrndup(q, cur - q); + ret = xmlStrndup(buf, len); } return(ret); @@ -2324,11 +3129,11 @@ xmlChar * xmlNamespaceParseNSDef(xmlParserCtxtPtr ctxt) { xmlChar *name = NULL; - if ((CUR == 'x') && (NXT(1) == 'm') && + if ((RAW == 'x') && (NXT(1) == 'm') && (NXT(2) == 'l') && (NXT(3) == 'n') && (NXT(4) == 's')) { SKIP(5); - if (CUR == ':') { + if (RAW == ':') { NEXT; name = xmlNamespaceParseNCName(ctxt); } @@ -2348,20 +3153,20 @@ xmlNamespaceParseNSDef(xmlParserCtxtPtr ctxt) { xmlChar * xmlParseQuotedString(xmlParserCtxtPtr ctxt) { xmlChar *buf = NULL; - int len = 0; + int len = 0,l; int size = XML_PARSER_BUFFER_SIZE; - xmlChar c; + int c; buf = (xmlChar *) xmlMalloc(size * sizeof(xmlChar)); if (buf == NULL) { fprintf(stderr, "malloc of %d byte failed\n", size); return(NULL); } - if (CUR == '"') { + if (RAW == '"') { NEXT; - c = CUR; + c = CUR_CHAR(l); while (IS_CHAR(c) && (c != '"')) { - if (len + 1 >= size) { + if (len + 5 >= size) { size *= 2; buf = xmlRealloc(buf, size * sizeof(xmlChar)); if (buf == NULL) { @@ -2369,9 +3174,9 @@ xmlParseQuotedString(xmlParserCtxtPtr ctxt) { return(NULL); } } - buf[len++] = c; - NEXT; - c = CUR; + COPY_BUF(l,buf,len,c); + NEXTL(l); + c = CUR_CHAR(l); } if (c != '"') { ctxt->errNo = XML_ERR_STRING_NOT_CLOSED; @@ -2379,10 +3184,11 @@ xmlParseQuotedString(xmlParserCtxtPtr ctxt) { ctxt->sax->error(ctxt->userData, "String not closed \"%.50s\"\n", buf); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } else { NEXT; } - } else if (CUR == '\''){ + } else if (RAW == '\''){ NEXT; c = CUR; while (IS_CHAR(c) && (c != '\'')) { @@ -2398,12 +3204,13 @@ xmlParseQuotedString(xmlParserCtxtPtr ctxt) { NEXT; c = CUR; } - if (CUR != '\'') { + if (RAW != '\'') { ctxt->errNo = XML_ERR_STRING_NOT_CLOSED; if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "String not closed \"%.50s\"\n", buf); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } else { NEXT; } @@ -2435,59 +3242,59 @@ xmlParseNamespace(xmlParserCtxtPtr ctxt) { */ SKIP_BLANKS; - while (IS_CHAR(CUR) && (CUR != '>')) { + while (IS_CHAR(RAW) && (RAW != '>')) { /* * We can have "ns" or "prefix" attributes * Old encoding as 'href' or 'AS' attributes is still supported */ - if ((CUR == 'n') && (NXT(1) == 's')) { + if ((RAW == 'n') && (NXT(1) == 's')) { garbage = 0; SKIP(2); SKIP_BLANKS; - if (CUR != '=') continue; + if (RAW != '=') continue; NEXT; SKIP_BLANKS; href = xmlParseQuotedString(ctxt); SKIP_BLANKS; - } else if ((CUR == 'h') && (NXT(1) == 'r') && + } else if ((RAW == 'h') && (NXT(1) == 'r') && (NXT(2) == 'e') && (NXT(3) == 'f')) { garbage = 0; SKIP(4); SKIP_BLANKS; - if (CUR != '=') continue; + if (RAW != '=') continue; NEXT; SKIP_BLANKS; href = xmlParseQuotedString(ctxt); SKIP_BLANKS; - } else if ((CUR == 'p') && (NXT(1) == 'r') && + } else if ((RAW == 'p') && (NXT(1) == 'r') && (NXT(2) == 'e') && (NXT(3) == 'f') && (NXT(4) == 'i') && (NXT(5) == 'x')) { garbage = 0; SKIP(6); SKIP_BLANKS; - if (CUR != '=') continue; + if (RAW != '=') continue; NEXT; SKIP_BLANKS; prefix = xmlParseQuotedString(ctxt); SKIP_BLANKS; - } else if ((CUR == 'A') && (NXT(1) == 'S')) { + } else if ((RAW == 'A') && (NXT(1) == 'S')) { garbage = 0; SKIP(2); SKIP_BLANKS; - if (CUR != '=') continue; + if (RAW != '=') continue; NEXT; SKIP_BLANKS; prefix = xmlParseQuotedString(ctxt); SKIP_BLANKS; - } else if ((CUR == '?') && (NXT(1) == '>')) { + } else if ((RAW == '?') && (NXT(1) == '>')) { garbage = 0; NEXT; } else { @@ -2501,6 +3308,7 @@ xmlParseNamespace(xmlParserCtxtPtr ctxt) { } ctxt->errNo = XML_ERR_NS_DECL_ERROR; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; NEXT; } } @@ -2549,8 +3357,8 @@ xmlScanName(xmlParserCtxtPtr ctxt) { int len = 0; GROW; - if (!IS_LETTER(CUR) && (CUR != '_') && - (CUR != ':')) { + if (!IS_LETTER(RAW) && (RAW != '_') && + (RAW != ':')) { return(NULL); } @@ -2594,35 +3402,35 @@ xmlScanName(xmlParserCtxtPtr ctxt) { xmlChar * xmlParseName(xmlParserCtxtPtr ctxt) { - xmlChar buf[XML_MAX_NAMELEN]; - int len = 0; - xmlChar cur; + xmlChar buf[XML_MAX_NAMELEN + 5]; + int len = 0, l; + int c; GROW; - cur = CUR; - if (!IS_LETTER(cur) && (cur != '_') && - (cur != ':')) { + c = CUR_CHAR(l); + if (!IS_LETTER(c) && (c != '_') && + (c != ':')) { return(NULL); } - while ((IS_LETTER(cur)) || (IS_DIGIT(cur)) || - (cur == '.') || (cur == '-') || - (cur == '_') || (cur == ':') || - (IS_COMBINING(cur)) || - (IS_EXTENDER(cur))) { - buf[len++] = cur; - NEXT; - cur = CUR; + while ((IS_LETTER(c)) || (IS_DIGIT(c)) || + (c == '.') || (c == '-') || + (c == '_') || (c == ':') || + (IS_COMBINING(c)) || + (IS_EXTENDER(c))) { + COPY_BUF(l,buf,len,c); + NEXTL(l); + c = CUR_CHAR(l); if (len >= XML_MAX_NAMELEN) { fprintf(stderr, "xmlParseName: reached XML_MAX_NAMELEN limit\n"); - while ((IS_LETTER(cur)) || (IS_DIGIT(cur)) || - (cur == '.') || (cur == '-') || - (cur == '_') || (cur == ':') || - (IS_COMBINING(cur)) || - (IS_EXTENDER(cur))) { - NEXT; - cur = CUR; + while ((IS_LETTER(c)) || (IS_DIGIT(c)) || + (c == '.') || (c == '-') || + (c == '_') || (c == ':') || + (IS_COMBINING(c)) || + (IS_EXTENDER(c))) { + NEXTL(l); + c = CUR_CHAR(l); } break; } @@ -2650,29 +3458,41 @@ xmlParseName(xmlParserCtxtPtr ctxt) { xmlChar * xmlParseStringName(xmlParserCtxtPtr ctxt, const xmlChar** str) { - const xmlChar *ptr; - const xmlChar *start; - xmlChar cur; + xmlChar buf[XML_MAX_NAMELEN + 5]; + const xmlChar *cur = *str; + int len = 0, l; + int c; - if ((str == NULL) || (*str == NULL)) return(NULL); - - start = ptr = *str; - cur = *ptr; - if (!IS_LETTER(cur) && (cur != '_') && - (cur != ':')) { + c = CUR_SCHAR(cur, l); + if (!IS_LETTER(c) && (c != '_') && + (c != ':')) { return(NULL); } - while ((IS_LETTER(cur)) || (IS_DIGIT(cur)) || - (cur == '.') || (cur == '-') || - (cur == '_') || (cur == ':') || - (IS_COMBINING(cur)) || - (IS_EXTENDER(cur))) { - ptr++; - cur = *ptr; + while ((IS_LETTER(c)) || (IS_DIGIT(c)) || + (c == '.') || (c == '-') || + (c == '_') || (c == ':') || + (IS_COMBINING(c)) || + (IS_EXTENDER(c))) { + COPY_BUF(l,buf,len,c); + cur += l; + c = CUR_SCHAR(cur, l); + if (len >= XML_MAX_NAMELEN) { + fprintf(stderr, + "xmlParseName: reached XML_MAX_NAMELEN limit\n"); + while ((IS_LETTER(c)) || (IS_DIGIT(c)) || + (c == '.') || (c == '-') || + (c == '_') || (c == ':') || + (IS_COMBINING(c)) || + (IS_EXTENDER(c))) { + cur += l; + c = CUR_SCHAR(cur, l); + } + break; + } } - *str = ptr; - return(xmlStrndup(start, ptr - start )); + *str = cur; + return(xmlStrndup(buf, len)); } /** @@ -2692,27 +3512,34 @@ xmlChar * xmlParseNmtoken(xmlParserCtxtPtr ctxt) { xmlChar buf[XML_MAX_NAMELEN]; int len = 0; + int c,l; GROW; - while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) || - (CUR == '.') || (CUR == '-') || - (CUR == '_') || (CUR == ':') || - (IS_COMBINING(CUR)) || - (IS_EXTENDER(CUR))) { - buf[len++] = CUR; - NEXT; + c = CUR_CHAR(l); + while ((IS_LETTER(c)) || (IS_DIGIT(c)) || + (c == '.') || (c == '-') || + (c == '_') || (c == ':') || + (IS_COMBINING(c)) || + (IS_EXTENDER(c))) { + COPY_BUF(l,buf,len,c); + NEXTL(l); + c = CUR_CHAR(l); if (len >= XML_MAX_NAMELEN) { fprintf(stderr, "xmlParseNmtoken: reached XML_MAX_NAMELEN limit\n"); - while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) || - (CUR == '.') || (CUR == '-') || - (CUR == '_') || (CUR == ':') || - (IS_COMBINING(CUR)) || - (IS_EXTENDER(CUR))) - NEXT; + while ((IS_LETTER(c)) || (IS_DIGIT(c)) || + (c == '.') || (c == '-') || + (c == '_') || (c == ':') || + (IS_COMBINING(c)) || + (IS_EXTENDER(c))) { + NEXTL(l); + c = CUR_CHAR(l); + } break; } } + if (len == 0) + return(NULL); return(xmlStrndup(buf, len)); } @@ -2734,18 +3561,20 @@ xmlParseEntityValue(xmlParserCtxtPtr ctxt, xmlChar **orig) { xmlChar *buf = NULL; int len = 0; int size = XML_PARSER_BUFFER_SIZE; - xmlChar c; + int c, l; xmlChar stop; xmlChar *ret = NULL; + const xmlChar *cur = NULL; xmlParserInputPtr input; - if (CUR == '"') stop = '"'; - else if (CUR == '\'') stop = '\''; + if (RAW == '"') stop = '"'; + else if (RAW == '\'') stop = '\''; else { ctxt->errNo = XML_ERR_ENTITY_NOT_STARTED; if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "EntityValue: \" or ' expected\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return(NULL); } buf = (xmlChar *) xmlMalloc(size * sizeof(xmlChar)); @@ -2762,7 +3591,7 @@ xmlParseEntityValue(xmlParserCtxtPtr ctxt, xmlChar **orig) { input = ctxt->input; GROW; NEXT; - c = CUR; + c = CUR_CHAR(l); /* * NOTE: 4.4.5 Included in Literal * When a parameter entity reference appears in a literal entity @@ -2773,7 +3602,7 @@ xmlParseEntityValue(xmlParserCtxtPtr ctxt, xmlChar **orig) { * the initial entity and the quote is found */ while (IS_CHAR(c) && ((c != stop) || (ctxt->input != input))) { - if (len + 1 >= size) { + if (len + 5 >= size) { size *= 2; buf = xmlRealloc(buf, size * sizeof(xmlChar)); if (buf == NULL) { @@ -2781,21 +3610,59 @@ xmlParseEntityValue(xmlParserCtxtPtr ctxt, xmlChar **orig) { return(NULL); } } - buf[len++] = c; - NEXT; + COPY_BUF(l,buf,len,c); + NEXTL(l); /* * Pop-up of finished entities. */ - while ((CUR == 0) && (ctxt->inputNr > 1)) + while ((RAW == 0) && (ctxt->inputNr > 1)) xmlPopInput(ctxt); - c = CUR; + + c = CUR_CHAR(l); if (c == 0) { GROW; - c = CUR; + c = CUR_CHAR(l); } } buf[len] = 0; + /* + * Raise problem w.r.t. '&' and '%' being used in non-entities + * reference constructs. Note Charref will be handled in + * xmlStringDecodeEntities() + */ + cur = buf; + while (*cur != 0) { + if ((*cur == '%') || ((*cur == '&') && (cur[1] != '#'))) { + xmlChar *name; + xmlChar tmp = *cur; + + cur++; + name = xmlParseStringName(ctxt, &cur); + if ((name == NULL) || (*cur != ';')) { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "EntityValue: '%c' forbidden except for entities references\n", + tmp); + ctxt->wellFormed = 0; + ctxt->disableSAX = 1; + ctxt->errNo = XML_ERR_ENTITY_CHAR_ERROR; + } + if ((ctxt->inSubset == 1) && (tmp == '%')) { + if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) + ctxt->sax->error(ctxt->userData, + "EntityValue: PEReferences forbidden in internal subset\n", + tmp); + ctxt->wellFormed = 0; + ctxt->disableSAX = 1; + ctxt->errNo = XML_ERR_ENTITY_PE_INTERNAL; + } + if (name != NULL) + xmlFree(name); + } + cur++; + } + /* * Then PEReference entities are substituted. */ @@ -2804,13 +3671,15 @@ xmlParseEntityValue(xmlParserCtxtPtr ctxt, xmlChar **orig) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "EntityValue: \" expected\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; + xmlFree(buf); } else { NEXT; /* * NOTE: 4.4.7 Bypassed * When a general entity reference appears in the EntityValue in * an entity declaration, it is bypassed and left as is. - * so XML_SUBSTITUTE_REF is not set. + * so XML_SUBSTITUTE_REF is not set here. */ ret = xmlStringDecodeEntities(ctxt, buf, XML_SUBSTITUTE_PEREF, 0, 0, 0); @@ -2869,11 +3738,11 @@ xmlParseAttValue(xmlParserCtxtPtr ctxt) { SHRINK; - if (CUR == '"') { + if (NXT(0) == '"') { ctxt->instate = XML_PARSER_ATTRIBUTE_VALUE; limit = '"'; NEXT; - } else if (CUR == '\'') { + } else if (NXT(0) == '\'') { limit = '\''; ctxt->instate = XML_PARSER_ATTRIBUTE_VALUE; NEXT; @@ -2882,6 +3751,7 @@ xmlParseAttValue(xmlParserCtxtPtr ctxt) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "AttValue: \" or ' expected\n"); ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return(NULL); } @@ -2900,7 +3770,7 @@ xmlParseAttValue(xmlParserCtxtPtr ctxt) { * Ok loop until we reach one of the ending char or a size limit. */ cur = CUR; - while ((cur != limit) && (cur != '<')) { + while (((NXT(0) != limit) && (cur != '<')) || (ctxt->token != 0)) { if (cur == 0) break; if ((cur == '&') && (NXT(1) == '#')) { int val = xmlParseCharRef(ctxt); @@ -2909,20 +3779,47 @@ xmlParseAttValue(xmlParserCtxtPtr ctxt) { ent = xmlParseEntityRef(ctxt); if ((ent != NULL) && (ctxt->replaceEntities != 0)) { - current = ent->content; - while (*current != 0) { - *out++ = *current++; - if (out - buffer > buffer_size - 10) { - int index = out - buffer; + xmlChar *rep; - growBuffer(buffer); - out = &buffer[index]; + if (ent->etype != XML_INTERNAL_PREDEFINED_ENTITY) { + rep = xmlStringDecodeEntities(ctxt, ent->content, + XML_SUBSTITUTE_REF, 0, 0, 0); + if (rep != NULL) { + current = rep; + while (*current != 0) { + *out++ = *current++; + if (out - buffer > buffer_size - 10) { + int index = out - buffer; + + growBuffer(buffer); + out = &buffer[index]; + } + } + xmlFree(rep); } + } else { + if (ent->content != NULL) + *out++ = ent->content[0]; } } else if (ent != NULL) { int i = xmlStrlen(ent->name); const xmlChar *cur = ent->name; + /* + * This may look absurd but is needed to detect + * entities problems + */ + if (ent->etype != XML_INTERNAL_PREDEFINED_ENTITY) { + xmlChar *rep; + rep = xmlStringDecodeEntities(ctxt, ent->content, + XML_SUBSTITUTE_REF, 0, 0, 0); + if (rep != NULL) + xmlFree(rep); + } + + /* + * Just output the reference + */ *out++ = '&'; if (out - buffer > buffer_size - i - 10) { int index = out - buffer; @@ -2935,7 +3832,7 @@ xmlParseAttValue(xmlParserCtxtPtr ctxt) { *out++ = ';'; } } else { - /* invalid for UTF-8 , use COPY(out); !!!!!! */ + /* invalid for UTF-8 , use COPY(out); !!! */ if ((cur == 0x20) || (cur == 0xD) || (cur == 0xA) || (cur == 0x9)) { *out++ = 0x20; if (out - buffer > buffer_size - 10) { @@ -2958,17 +3855,19 @@ xmlParseAttValue(xmlParserCtxtPtr ctxt) { cur = CUR; } *out++ = 0; - if (CUR == '<') { + if (RAW == '<') { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "Unescaped '<' not allowed in attributes values\n"); ctxt->errNo = XML_ERR_LT_IN_ATTRIBUTE; ctxt->wellFormed = 0; - } else if (CUR != limit) { + ctxt->disableSAX = 1; + } else if (RAW != limit) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n"); ctxt->errNo = XML_ERR_ATTRIBUTE_NOT_FINISHED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } else NEXT; return(buffer); @@ -2990,14 +3889,15 @@ xmlParseSystemLiteral(xmlParserCtxtPtr ctxt) { xmlChar *buf = NULL; int len = 0; int size = XML_PARSER_BUFFER_SIZE; - xmlChar cur; + int cur, l; xmlChar stop; + int state = ctxt->instate; SHRINK; - if (CUR == '"') { + if (RAW == '"') { NEXT; stop = '"'; - } else if (CUR == '\'') { + } else if (RAW == '\'') { NEXT; stop = '\''; } else { @@ -3006,6 +3906,7 @@ xmlParseSystemLiteral(xmlParserCtxtPtr ctxt) { "SystemLiteral \" or ' expected\n"); ctxt->errNo = XML_ERR_LITERAL_NOT_STARTED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return(NULL); } @@ -3014,31 +3915,35 @@ xmlParseSystemLiteral(xmlParserCtxtPtr ctxt) { fprintf(stderr, "malloc of %d byte failed\n", size); return(NULL); } - cur = CUR; + ctxt->instate = XML_PARSER_SYSTEM_LITERAL; + cur = CUR_CHAR(l); while ((IS_CHAR(cur)) && (cur != stop)) { - if (len + 1 >= size) { + if (len + 5 >= size) { size *= 2; buf = xmlRealloc(buf, size * sizeof(xmlChar)); if (buf == NULL) { fprintf(stderr, "realloc of %d byte failed\n", size); + ctxt->instate = state; return(NULL); } } - buf[len++] = cur; - NEXT; - cur = CUR; + COPY_BUF(l,buf,len,cur); + NEXTL(l); + cur = CUR_CHAR(l); if (cur == 0) { GROW; SHRINK; - cur = CUR; + cur = CUR_CHAR(l); } } buf[len] = 0; + ctxt->instate = state; if (!IS_CHAR(cur)) { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n"); ctxt->errNo = XML_ERR_LITERAL_NOT_FINISHED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } else { NEXT; } @@ -3065,10 +3970,10 @@ xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) { xmlChar stop; SHRINK; - if (CUR == '"') { + if (RAW == '"') { NEXT; stop = '"'; - } else if (CUR == '\'') { + } else if (RAW == '\'') { NEXT; stop = '\''; } else { @@ -3077,6 +3982,7 @@ xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) { "SystemLiteral \" or ' expected\n"); ctxt->errNo = XML_ERR_LITERAL_NOT_STARTED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; return(NULL); } buf = (xmlChar *) xmlMalloc(size * sizeof(xmlChar)); @@ -3109,6 +4015,7 @@ xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) { ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n"); ctxt->errNo = XML_ERR_LITERAL_NOT_FINISHED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } else { NEXT; } @@ -3123,35 +4030,43 @@ xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) { * parse a CharData section. * if we are within a CDATA section ']]>' marks an end of section. * + * The right angle bracket (>) may be represented using the string ">", + * and must, for compatibility, be escaped using ">" or a character + * reference when it appears in the string "]]>" in content, when that + * string is not marking the end of a CDATA section. + * * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*) */ void xmlParseCharData(xmlParserCtxtPtr ctxt, int cdata) { - xmlChar buf[XML_PARSER_BIG_BUFFER_SIZE]; + xmlChar buf[XML_PARSER_BIG_BUFFER_SIZE + 5]; int nbchar = 0; - xmlChar cur; + int cur, l; SHRINK; - cur = CUR; - while ((IS_CHAR(cur)) && (cur != '<') && - (cur != '&')) { + cur = CUR_CHAR(l); + while ((IS_CHAR(cur)) && ((cur != '<') || (ctxt->token == '<')) && + ((cur != '&') || (ctxt->token == '&'))) { if ((cur == ']') && (NXT(1) == ']') && (NXT(2) == '>')) { if (cdata) break; else { if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) - ctxt->sax->warning(ctxt->userData, + ctxt->sax->error(ctxt->userData, "Sequence ']]>' not allowed in content\n"); ctxt->errNo = XML_ERR_MISPLACED_CDATA_END; + /* Should this be relaxed ??? I see a "must here */ + ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } } - buf[nbchar++] = CUR; - if (nbchar == XML_PARSER_BIG_BUFFER_SIZE) { + COPY_BUF(l,buf,nbchar,cur); + if (nbchar >= XML_PARSER_BIG_BUFFER_SIZE) { /* * Ok the segment is to be consumed as chars. */ - if (ctxt->sax != NULL) { + if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) { if (areBlanks(ctxt, buf, nbchar)) { if (ctxt->sax->ignorableWhitespace != NULL) ctxt->sax->ignorableWhitespace(ctxt->userData, @@ -3163,14 +4078,14 @@ xmlParseCharData(xmlParserCtxtPtr ctxt, int cdata) { } nbchar = 0; } - NEXT; - cur = CUR; + NEXTL(l); + cur = CUR_CHAR(l); } if (nbchar != 0) { /* * Ok the segment is to be consumed as chars. */ - if (ctxt->sax != NULL) { + if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) { if (areBlanks(ctxt, buf, nbchar)) { if (ctxt->sax->ignorableWhitespace != NULL) ctxt->sax->ignorableWhitespace(ctxt->userData, buf, nbchar); @@ -3209,7 +4124,7 @@ xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { xmlChar *URI = NULL; SHRINK; - if ((CUR == 'S') && (NXT(1) == 'Y') && + if ((RAW == 'S') && (NXT(1) == 'Y') && (NXT(2) == 'S') && (NXT(3) == 'T') && (NXT(4) == 'E') && (NXT(5) == 'M')) { SKIP(6); @@ -3219,6 +4134,7 @@ xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { "Space required after 'SYSTEM'\n"); ctxt->errNo = XML_ERR_SPACE_REQUIRED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } SKIP_BLANKS; URI = xmlParseSystemLiteral(ctxt); @@ -3228,8 +4144,9 @@ xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { "xmlParseExternalID: SYSTEM, no URI\n"); ctxt->errNo = XML_ERR_URI_REQUIRED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } - } else if ((CUR == 'P') && (NXT(1) == 'U') && + } else if ((RAW == 'P') && (NXT(1) == 'U') && (NXT(2) == 'B') && (NXT(3) == 'L') && (NXT(4) == 'I') && (NXT(5) == 'C')) { SKIP(6); @@ -3239,6 +4156,7 @@ xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { "Space required after 'PUBLIC'\n"); ctxt->errNo = XML_ERR_SPACE_REQUIRED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } SKIP_BLANKS; *publicID = xmlParsePubidLiteral(ctxt); @@ -3248,6 +4166,7 @@ xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { "xmlParseExternalID: PUBLIC, no Public Identifier\n"); ctxt->errNo = XML_ERR_PUBID_REQUIRED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } if (strict) { /* @@ -3259,6 +4178,7 @@ xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { "Space required after the Public Identifier\n"); ctxt->errNo = XML_ERR_SPACE_REQUIRED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } } else { /* @@ -3273,7 +4193,7 @@ xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { if (!IS_BLANK(*ptr)) return(NULL); while (IS_BLANK(*ptr)) ptr++; - if ((*ptr != '\'') || (*ptr != '"')) return(NULL); + if ((*ptr != '\'') && (*ptr != '"')) return(NULL); } SKIP_BLANKS; URI = xmlParseSystemLiteral(ctxt); @@ -3283,6 +4203,7 @@ xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { "xmlParseExternalID: PUBLIC, no URI\n"); ctxt->errNo = XML_ERR_URI_REQUIRED; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } } return(URI); @@ -3303,15 +4224,16 @@ xmlParseComment(xmlParserCtxtPtr ctxt) { xmlChar *buf = NULL; int len = 0; int size = XML_PARSER_BUFFER_SIZE; - xmlChar q; - xmlChar r; - xmlChar cur; + int q, ql; + int r, rl; + int cur, l; xmlParserInputState state; + xmlParserInputPtr input = ctxt->input; /* * Check that there is a comment right here. */ - if ((CUR != '<') || (NXT(1) != '!') || + if ((RAW != '<') || (NXT(1) != '!') || (NXT(2) != '-') || (NXT(3) != '-')) return; state = ctxt->instate; @@ -3324,11 +4246,11 @@ xmlParseComment(xmlParserCtxtPtr ctxt) { ctxt->instate = state; return; } - q = CUR; - NEXT; - r = CUR; - NEXT; - cur = CUR; + q = CUR_CHAR(ql); + NEXTL(ql); + r = CUR_CHAR(rl); + NEXTL(rl); + cur = CUR_CHAR(l); while (IS_CHAR(cur) && ((cur != '>') || (r != '-') || (q != '-'))) { @@ -3338,8 +4260,9 @@ xmlParseComment(xmlParserCtxtPtr ctxt) { "Comment must not contain '--' (double-hyphen)`\n"); ctxt->errNo = XML_ERR_HYPHEN_IN_COMMENT; ctxt->wellFormed = 0; + ctxt->disableSAX = 1; } - if (len + 1 >= size) { + if (len + 5 >= size) { size *= 2; buf = xmlRealloc(buf, size * sizeof(xmlChar)); if (buf == NULL) { @@ -3348,15 +4271,17 @@ xmlParseComment(xmlParserCtxtPtr ctxt) { return; } } - buf[len++] = q; + COPY_BUF(ql,buf,len,q); q = r; + ql = rl; r = cur; - NEXT; - cur = CUR; + rl = l; + NEXTL(l); + cur = CUR_CHAR(l); if (cur == 0) { SHRINK; GROW; - cur = CUR; + cur = CUR_CHAR(l); } } buf[len] = 0; @@ -3366,9 +4291,20 @@ xmlParseComment(xmlParserCtxtPtr ctxt) { "Comment not terminated \n Kona Lavadome mountain bike diff --git a/result/VC/OneID b/result/VC/OneID index 3ad97fad..c5dbd6c2 100644 --- a/result/VC/OneID +++ b/result/VC/OneID @@ -1,3 +1,6 @@ ./test/VC/OneID:4: validity error: Element doc has too may ID attributes defined : id ^ +./test/VC/OneID:4: validity error: Element doc has 2 ID attribute defined in the internal subset : id + + ^ diff --git a/result/VC/OneID2 b/result/VC/OneID2 index 738c42e1..b1e2ed5e 100644 --- a/result/VC/OneID2 +++ b/result/VC/OneID2 @@ -1,3 +1,6 @@ +./test/VC/OneID2:3: validity error: Element doc has 2 ID attribute defined in the internal subset : id + + ^ ./test/VC/OneID2:4: validity error: Element doc has too may ID attributes defined : val ^ diff --git a/result/VC/OneID3 b/result/VC/OneID3 index 03077571..3f08c9ef 100644 --- a/result/VC/OneID3 +++ b/result/VC/OneID3 @@ -1,3 +1,3 @@ -./test/VC/OneID3:2: validity error: Element doc has ID attribute defined in the external subset : id - - ^ +dtds/doc.dtd:2: validity error: Element doc has ID attributes defined in the internal and external subset : val + + ^ diff --git a/result/VC/UniqueElementTypeDeclaration b/result/VC/UniqueElementTypeDeclaration index c648610a..e24b8e7c 100644 --- a/result/VC/UniqueElementTypeDeclaration +++ b/result/VC/UniqueElementTypeDeclaration @@ -1,3 +1,3 @@ -./test/VC/UniqueElementTypeDeclaration:3: validity error: Redefinition of element a +dtds/a.dtd:1: validity error: Redefinition of element a ^ diff --git a/result/comment.xml b/result/comment.xml index 567160aa..98c5effd 100644 --- a/result/comment.xml +++ b/result/comment.xml @@ -1,6 +1,6 @@ - + diff --git a/result/comment2.xml b/result/comment2.xml index 26242381..9e122ecf 100644 --- a/result/comment2.xml +++ b/result/comment2.xml @@ -1,6 +1,6 @@ - + diff --git a/result/dtd1 b/result/dtd1 index 2cb4398e..fb11ffa8 100644 --- a/result/dtd1 +++ b/result/dtd1 @@ -1,3 +1,4 @@ - + + diff --git a/result/dtd10 b/result/dtd10 index 82ac138b..86bf28d4 100644 --- a/result/dtd10 +++ b/result/dtd10 @@ -7,7 +7,7 @@ ]> - This - is a - valid document +This + is a + valid document diff --git a/result/dtd12 b/result/dtd12 index c7bc1bcf..f0d12610 100644 --- a/result/dtd12 +++ b/result/dtd12 @@ -1,6 +1,6 @@ - + + ]> &WhatHeSaid; diff --git a/result/dtd13 b/result/dtd13 index e69de29b..28141464 100644 --- a/result/dtd13 +++ b/result/dtd13 @@ -0,0 +1,7 @@ + + + +]> + + diff --git a/result/dtd6 b/result/dtd6 index 8b3875e0..51ed4559 100644 --- a/result/dtd6 +++ b/result/dtd6 @@ -5,7 +5,7 @@ ]> - This - is a valid - document +This + is a valid + document diff --git a/result/dtd7 b/result/dtd7 index 4da0ce61..1dec0338 100644 --- a/result/dtd7 +++ b/result/dtd7 @@ -5,6 +5,6 @@ ]> - This - is a valid document +This + is a valid document diff --git a/result/dtd8 b/result/dtd8 index 77ab6426..b845a9e9 100644 --- a/result/dtd8 +++ b/result/dtd8 @@ -7,6 +7,6 @@ ]> - This - is a valid document +This + is a valid document diff --git a/result/dtd9 b/result/dtd9 index 020ab720..cded2117 100644 --- a/result/dtd9 +++ b/result/dtd9 @@ -7,6 +7,6 @@ ]> - This - is a valid document +This + is a valid document diff --git a/result/ent5 b/result/ent5 index d5b34e52..16e7e103 100644 --- a/result/ent5 +++ b/result/ent5 @@ -1,5 +1,5 @@ - This is an inverted exclamation sign ¡ + This is an inverted exclamation sign ¡ This is a space diff --git a/result/ent7 b/result/ent7 index e4e095ab..dcbc9cab 100644 --- a/result/ent7 +++ b/result/ent7 @@ -6,5 +6,5 @@ ]> - 'they called me &sampleEnt;' +'they called me &sampleEnt;' diff --git a/result/ent8 b/result/ent8 index 7b8f814c..86e6c302 100644 --- a/result/ent8 +++ b/result/ent8 @@ -4,7 +4,7 @@ ]> - Retenção - <> - &test1;&test2; + Retenção + <> + &test1;&test2; diff --git a/result/eve.xml b/result/eve.xml index 7156e2ec..dab72086 100644 --- a/result/eve.xml +++ b/result/eve.xml @@ -2,4 +2,5 @@ ]> - + + diff --git a/result/noent/comment.xml b/result/noent/comment.xml index 567160aa..98c5effd 100644 --- a/result/noent/comment.xml +++ b/result/noent/comment.xml @@ -1,6 +1,6 @@ - + diff --git a/result/noent/comment2.xml b/result/noent/comment2.xml index 26242381..9e122ecf 100644 --- a/result/noent/comment2.xml +++ b/result/noent/comment2.xml @@ -1,6 +1,6 @@ - + diff --git a/result/noent/dtd1 b/result/noent/dtd1 index 2cb4398e..fb11ffa8 100644 --- a/result/noent/dtd1 +++ b/result/noent/dtd1 @@ -1,3 +1,4 @@ - + + diff --git a/result/noent/dtd10 b/result/noent/dtd10 index 82ac138b..86bf28d4 100644 --- a/result/noent/dtd10 +++ b/result/noent/dtd10 @@ -7,7 +7,7 @@ ]> - This - is a - valid document +This + is a + valid document diff --git a/result/noent/dtd12 b/result/noent/dtd12 index 92c25609..8c4bf36d 100644 --- a/result/noent/dtd12 +++ b/result/noent/dtd12 @@ -1,6 +1,6 @@ - + + ]> -He said "Yes" +He said &YN; diff --git a/result/noent/dtd6 b/result/noent/dtd6 index 8b3875e0..51ed4559 100644 --- a/result/noent/dtd6 +++ b/result/noent/dtd6 @@ -5,7 +5,7 @@ ]> - This - is a valid - document +This + is a valid + document diff --git a/result/noent/dtd7 b/result/noent/dtd7 index 4da0ce61..1dec0338 100644 --- a/result/noent/dtd7 +++ b/result/noent/dtd7 @@ -5,6 +5,6 @@ ]> - This - is a valid document +This + is a valid document diff --git a/result/noent/dtd8 b/result/noent/dtd8 index 77ab6426..b845a9e9 100644 --- a/result/noent/dtd8 +++ b/result/noent/dtd8 @@ -7,6 +7,6 @@ ]> - This - is a valid document +This + is a valid document diff --git a/result/noent/dtd9 b/result/noent/dtd9 index 020ab720..cded2117 100644 --- a/result/noent/dtd9 +++ b/result/noent/dtd9 @@ -7,6 +7,6 @@ ]> - This - is a valid document +This + is a valid document diff --git a/result/noent/ent5 b/result/noent/ent5 index d5b34e52..16e7e103 100644 --- a/result/noent/ent5 +++ b/result/noent/ent5 @@ -1,5 +1,5 @@ - This is an inverted exclamation sign ¡ + This is an inverted exclamation sign ¡ This is a space diff --git a/result/noent/ent7 b/result/noent/ent7 index 45a1ceeb..1bf69cea 100644 --- a/result/noent/ent7 +++ b/result/noent/ent7 @@ -6,5 +6,5 @@ ]> - 'they called me the hyacinth girl' +'they called me the hyacinth girl' diff --git a/result/noent/ent8 b/result/noent/ent8 index 0ed738ae..676266c9 100644 --- a/result/noent/ent8 +++ b/result/noent/ent8 @@ -4,7 +4,7 @@ ]> - Retenção - <> - test 1test 2 + Retenção + <> + test 1test 2 diff --git a/result/noent/eve.xml b/result/noent/eve.xml index 7156e2ec..dab72086 100644 --- a/result/noent/eve.xml +++ b/result/noent/eve.xml @@ -2,4 +2,5 @@ ]> - + + diff --git a/result/noent/p3p b/result/noent/p3p index b2ba102f..5e366b56 100644 --- a/result/noent/p3p +++ b/result/noent/p3p @@ -1,22 +1,19 @@ - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + diff --git a/result/noent/pi.xml b/result/noent/pi.xml index 27bed5b9..48c7ff04 100644 --- a/result/noent/pi.xml +++ b/result/noent/pi.xml @@ -1,6 +1,6 @@ - + diff --git a/result/noent/pi2.xml b/result/noent/pi2.xml index acf76f95..710d51c9 100644 --- a/result/noent/pi2.xml +++ b/result/noent/pi2.xml @@ -1,6 +1,6 @@ - + diff --git a/result/noent/rdf2 b/result/noent/rdf2 index fe803995..284946bf 100644 --- a/result/noent/rdf2 +++ b/result/noent/rdf2 @@ -11,11 +11,11 @@ Till Bubeck <bubeck@delix.de>, Ngo Than <than@delix.de> Libraries Bibliothek zur Ansteuerung von Terminals - Diese Library stellt dem Programmierer vom Terminal unabhängige -Routinen zur Ansteuerung Ihres Bildschirms zur Verfügung, die + Diese Library stellt dem Programmierer vom Terminal unabhängige +Routinen zur Ansteuerung Ihres Bildschirms zur Verfügung, die speziell optimiert sind. -Diese Version ist die 'new curses' (ncurses) Variante und ist der -anerkannte Ersatz für die klassische Curses-Library, die nicht mehr +Diese Version ist die 'new curses' (ncurses) Variante und ist der +anerkannte Ersatz für die klassische Curses-Library, die nicht mehr weiterentwickelt wird. GPL ncurses4-4.2-3.src.rpm diff --git a/result/noent/slashdot.rdf b/result/noent/slashdot.rdf index 08d4922d..2fc1f07f 100644 --- a/result/noent/slashdot.rdf +++ b/result/noent/slashdot.rdf @@ -1,51 +1,63 @@ + Slashdot:News for Nerds. Stuff that Matters. http://slashdot.org/ News for Nerds. Stuff that Matters + Slashdot http://slashdot.org/images/slashdotlg.gif http://slashdot.org + 100 Mbit/s on Fibre to the home http://slashdot.org/articles/99/06/06/1440211.shtml + Gimp 1.2 Preview http://slashdot.org/articles/99/06/06/1438246.shtml + - Sony's AIBO robot Sold Out + Sony's AIBO robot Sold Out http://slashdot.org/articles/99/06/06/1432256.shtml + Ask Slashdot: Another Word for "Hacker"? http://slashdot.org/askslashdot/99/06/05/1815225.shtml + Corel Linux FAQ http://slashdot.org/articles/99/06/05/1842218.shtml + Upside downsides MP3.COM. http://slashdot.org/articles/99/06/05/1558210.shtml + 2 Terabits of Bandwidth http://slashdot.org/articles/99/06/05/1554258.shtml + Suppression of cold fusion research? http://slashdot.org/articles/99/06/04/2313200.shtml + California Gov. Halts Wage Info Sale http://slashdot.org/articles/99/06/04/235256.shtml + Red Hat Announces IPO http://slashdot.org/articles/99/06/04/0849207.shtml diff --git a/result/noent/slashdot.xml b/result/noent/slashdot.xml index f52ca805..5521254c 100644 --- a/result/noent/slashdot.xml +++ b/result/noent/slashdot.xml @@ -1,17 +1,17 @@ - + 100 Mbit/s on Fibre to the home http://slashdot.org/articles/99/06/06/1440211.shtml CmdrTaco - wouldn't-it-be-nice + wouldn't-it-be-nice internet 20
articles
topicinternet.jpg - + Gimp 1.2 Preview http://slashdot.org/articles/99/06/06/1438246.shtml @@ -22,8 +22,8 @@
articles
topicgimp.gif - - Sony's AIBO robot Sold Out + + Sony's AIBO robot Sold Out http://slashdot.org/articles/99/06/06/1432256.shtml CmdrTaco @@ -33,7 +33,7 @@
articles
topictech2.jpg - + Ask Slashdot: Another Word for "Hacker"? http://slashdot.org/askslashdot/99/06/05/1815225.shtml @@ -44,7 +44,7 @@
askslashdot
topicnews.gif - + Corel Linux FAQ http://slashdot.org/articles/99/06/05/1842218.shtml @@ -55,7 +55,7 @@
articles
topiccorel.gif - + Upside downsides MP3.COM. http://slashdot.org/articles/99/06/05/1558210.shtml @@ -66,7 +66,7 @@
articles
topicmusic.gif - + 2 Terabits of Bandwidth http://slashdot.org/articles/99/06/05/1554258.shtml @@ -77,7 +77,7 @@
articles
topicinternet.jpg - + Suppression of cold fusion research? http://slashdot.org/articles/99/06/04/2313200.shtml @@ -88,7 +88,7 @@
articles
topicscience.gif - + California Gov. Halts Wage Info Sale http://slashdot.org/articles/99/06/04/235256.shtml @@ -99,7 +99,7 @@
articles
topicus.gif - + Red Hat Announces IPO http://slashdot.org/articles/99/06/04/0849207.shtml diff --git a/result/noent/svg1 b/result/noent/svg1 index 6802e5cd..359bd455 100644 --- a/result/noent/svg1 +++ b/result/noent/svg1 @@ -1,161 +1,161 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/result/noent/svg2 b/result/noent/svg2 index 5e53829a..6c3990c8 100644 --- a/result/noent/svg2 +++ b/result/noent/svg2 @@ -1,54 +1,56 @@ - - - - - - - - - - - - - - - - - - Java Font definition:Dialog 0 - - - Java Font definition:Helvetica 0 - - - - this is text - - - - Java Font definition:Dialog 0 - - - Java Font definition:Helvetica 700 - - - - sadfsadfsad - - - - - - - - - Java Font definition:Dialog 700 - - - Java Font definition:Dialog 700 - - - + + + + + + + + + + + + + + + + + + + Java Font definition:Dialog 0 + + + Java Font definition:Helvetica 0 + + + + this is text + + + + Java Font definition:Dialog 0 + + + Java Font definition:Helvetica 700 + + + + sadfsadfsad + + + + + + + + + + + Java Font definition:Dialog 700 + + + Java Font definition:Dialog 700 + + diff --git a/result/noent/svg3 b/result/noent/svg3 index 35b9cd88..c4994b85 100644 --- a/result/noent/svg3 +++ b/result/noent/svg3 @@ -1,723 +1,723 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/result/noent/xml1 b/result/noent/xml1 index 51553fc7..a197468d 100644 --- a/result/noent/xml1 +++ b/result/noent/xml1 @@ -5,7 +5,7 @@ (&amp;).

"> ]> -

An ampersand (&) may be escaped +

An ampersand (&) may be escaped numerically (&#38;) or with a general entity (&amp;amp;).

 diff --git a/result/noent/xml2 b/result/noent/xml2 index f4865fcc..6c394543 100644 --- a/result/noent/xml2 +++ b/result/noent/xml2 @@ -1,8 +1,8 @@ '> - ]> This sample shows a error-prone method. diff --git a/result/p3p b/result/p3p index b2ba102f..5e366b56 100644 --- a/result/p3p +++ b/result/p3p @@ -1,22 +1,19 @@ - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + diff --git a/result/pi.xml b/result/pi.xml index 27bed5b9..48c7ff04 100644 --- a/result/pi.xml +++ b/result/pi.xml @@ -1,6 +1,6 @@ - + diff --git a/result/pi2.xml b/result/pi2.xml index acf76f95..710d51c9 100644 --- a/result/pi2.xml +++ b/result/pi2.xml @@ -1,6 +1,6 @@ - + diff --git a/result/rdf2 b/result/rdf2 index fe803995..284946bf 100644 --- a/result/rdf2 +++ b/result/rdf2 @@ -11,11 +11,11 @@ Till Bubeck <bubeck@delix.de>, Ngo Than <than@delix.de> Libraries Bibliothek zur Ansteuerung von Terminals - Diese Library stellt dem Programmierer vom Terminal unabhängige -Routinen zur Ansteuerung Ihres Bildschirms zur Verfügung, die + Diese Library stellt dem Programmierer vom Terminal unabhängige +Routinen zur Ansteuerung Ihres Bildschirms zur Verfügung, die speziell optimiert sind. -Diese Version ist die 'new curses' (ncurses) Variante und ist der -anerkannte Ersatz für die klassische Curses-Library, die nicht mehr +Diese Version ist die 'new curses' (ncurses) Variante und ist der +anerkannte Ersatz für die klassische Curses-Library, die nicht mehr weiterentwickelt wird. GPL ncurses4-4.2-3.src.rpm diff --git a/result/slashdot.rdf b/result/slashdot.rdf index 08d4922d..2fc1f07f 100644 --- a/result/slashdot.rdf +++ b/result/slashdot.rdf @@ -1,51 +1,63 @@ + Slashdot:News for Nerds. Stuff that Matters. http://slashdot.org/ News for Nerds. Stuff that Matters + Slashdot http://slashdot.org/images/slashdotlg.gif http://slashdot.org + 100 Mbit/s on Fibre to the home http://slashdot.org/articles/99/06/06/1440211.shtml + Gimp 1.2 Preview http://slashdot.org/articles/99/06/06/1438246.shtml + - Sony's AIBO robot Sold Out + Sony's AIBO robot Sold Out http://slashdot.org/articles/99/06/06/1432256.shtml + Ask Slashdot: Another Word for "Hacker"? http://slashdot.org/askslashdot/99/06/05/1815225.shtml + Corel Linux FAQ http://slashdot.org/articles/99/06/05/1842218.shtml + Upside downsides MP3.COM. http://slashdot.org/articles/99/06/05/1558210.shtml + 2 Terabits of Bandwidth http://slashdot.org/articles/99/06/05/1554258.shtml + Suppression of cold fusion research? http://slashdot.org/articles/99/06/04/2313200.shtml + California Gov. Halts Wage Info Sale http://slashdot.org/articles/99/06/04/235256.shtml + Red Hat Announces IPO http://slashdot.org/articles/99/06/04/0849207.shtml diff --git a/result/slashdot.xml b/result/slashdot.xml index f52ca805..5521254c 100644 --- a/result/slashdot.xml +++ b/result/slashdot.xml @@ -1,17 +1,17 @@ - + 100 Mbit/s on Fibre to the home http://slashdot.org/articles/99/06/06/1440211.shtml CmdrTaco - wouldn't-it-be-nice + wouldn't-it-be-nice internet 20
articles
topicinternet.jpg - + Gimp 1.2 Preview http://slashdot.org/articles/99/06/06/1438246.shtml @@ -22,8 +22,8 @@
articles
topicgimp.gif - - Sony's AIBO robot Sold Out + + Sony's AIBO robot Sold Out http://slashdot.org/articles/99/06/06/1432256.shtml CmdrTaco @@ -33,7 +33,7 @@
articles
topictech2.jpg - + Ask Slashdot: Another Word for "Hacker"? http://slashdot.org/askslashdot/99/06/05/1815225.shtml @@ -44,7 +44,7 @@
askslashdot
topicnews.gif - + Corel Linux FAQ http://slashdot.org/articles/99/06/05/1842218.shtml @@ -55,7 +55,7 @@
articles
topiccorel.gif - + Upside downsides MP3.COM. http://slashdot.org/articles/99/06/05/1558210.shtml @@ -66,7 +66,7 @@
articles
topicmusic.gif - + 2 Terabits of Bandwidth http://slashdot.org/articles/99/06/05/1554258.shtml @@ -77,7 +77,7 @@
articles
topicinternet.jpg - + Suppression of cold fusion research? http://slashdot.org/articles/99/06/04/2313200.shtml @@ -88,7 +88,7 @@
articles
topicscience.gif - + California Gov. Halts Wage Info Sale http://slashdot.org/articles/99/06/04/235256.shtml @@ -99,7 +99,7 @@
articles
topicus.gif - + Red Hat Announces IPO http://slashdot.org/articles/99/06/04/0849207.shtml diff --git a/result/svg1 b/result/svg1 index 6802e5cd..359bd455 100644 --- a/result/svg1 +++ b/result/svg1 @@ -1,161 +1,161 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/result/svg2 b/result/svg2 index 5e53829a..6c3990c8 100644 --- a/result/svg2 +++ b/result/svg2 @@ -1,54 +1,56 @@ - - - - - - - - - - - - - - - - - - Java Font definition:Dialog 0 - - - Java Font definition:Helvetica 0 - - - - this is text - - - - Java Font definition:Dialog 0 - - - Java Font definition:Helvetica 700 - - - - sadfsadfsad - - - - - - - - - Java Font definition:Dialog 700 - - - Java Font definition:Dialog 700 - - - + + + + + + + + + + + + + + + + + + + Java Font definition:Dialog 0 + + + Java Font definition:Helvetica 0 + + + + this is text + + + + Java Font definition:Dialog 0 + + + Java Font definition:Helvetica 700 + + + + sadfsadfsad + + + + + + + + + + + Java Font definition:Dialog 700 + + + Java Font definition:Dialog 700 + + diff --git a/result/svg3 b/result/svg3 index 35b9cd88..c4994b85 100644 --- a/result/svg3 +++ b/result/svg3 @@ -1,723 +1,723 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/result/valid/REC-xml-19980210.xml b/result/valid/REC-xml-19980210.xml index 7f70749f..a27855db 100644 --- a/result/valid/REC-xml-19980210.xml +++ b/result/valid/REC-xml-19980210.xml @@ -1,6 +1,8 @@ + @@ -15,58 +17,51 @@ - + - + amp, lt, gt, apos, quot"> - + ]> - - - - - -
- Extensible Markup Language (XML) 1.0 - - REC-xml-&iso6.doc.date; - W3C Recommendation - - &draft.day; - &draft.month; - &draft.year; - - - +
+Extensible Markup Language (XML) 1.0 + +REC-xml-&iso6.doc.date; +W3C Recommendation + +&draft.day; +&draft.month; +&draft.year; + + + http://www.w3.org/TR/1998/REC-xml-&iso6.doc.date; - + http://www.w3.org/TR/1998/REC-xml-&iso6.doc.date;.xml - + http://www.w3.org/TR/1998/REC-xml-&iso6.doc.date;.html - + http://www.w3.org/TR/1998/REC-xml-&iso6.doc.date;.pdf - + http://www.w3.org/TR/1998/REC-xml-&iso6.doc.date;.ps - - - + + + http://www.w3.org/TR/REC-xml - - - + + + http://www.w3.org/TR/PR-xml-971208 - - - - Tim Bray - Textuality and Netscape - tbray@textuality.com - - - Jean Paoli - Microsoft - jeanpa@microsoft.com - - - C. M. Sperberg-McQueen - University of Illinois at Chicago - cmsmcq@uic.edu - - - -

The Extensible Markup Language (XML) is a subset of + + + +Tim Bray +Textuality and Netscape +tbray@textuality.com + + +Jean Paoli +Microsoft +jeanpa@microsoft.com + + +C. M. Sperberg-McQueen +University of Illinois at Chicago +cmsmcq@uic.edu + + + +

The Extensible Markup Language (XML) is a subset of SGML that is completely described in this document. Its goal is to enable generic SGML to be served, received, and processed on the Web in the way that is now possible with HTML. XML has been designed for ease of implementation and for interoperability with both SGML and HTML.

- - -

This document has been reviewed by W3C Members and + + +

This document has been reviewed by W3C Members and other interested parties and has been endorsed by the Director as a W3C Recommendation. It is a stable document and may be used as reference material or cited -as a normative reference from another document. W3C's +as a normative reference from another document. W3C's role in making the Recommendation is to draw attention to the specification and to promote its widespread deployment. This enhances the functionality and interoperability of the Web.

-

+

This document specifies a syntax created by subsetting an existing, widely used international text processing standard (Standard Generalized Markup Language, ISO 8879:1986(E) as amended and @@ -124,55 +119,55 @@ XML Activity, details of which can be found at http://www.w3.org/TR.

-

This specification uses the term URI, which is defined by , a work in progress expected to update and . +

This specification uses the term URI, which is defined by , a work in progress expected to update and .

-

The list of known errors in this specification is +

The list of known errors in this specification is available at http://www.w3.org/XML/xml-19980210-errata.

-

Please report errors in this document to +

Please report errors in this document to xml-editor@w3.org.

- - -

Chicago, Vancouver, Mountain View, et al.: + + +

Chicago, Vancouver, Mountain View, et al.: World-Wide Web Consortium, XML Working Group, 1996, 1997.

- - -

Created in electronic form.

- - - English - Extended Backus-Naur Form (formal grammar) - - - - 1997-12-03 : CMSMcQ : yet further changes - 1997-12-02 : TB : further changes (see TB to XML WG, + + +

Created in electronic form.

+ + +English +Extended Backus-Naur Form (formal grammar) + + + +1997-12-03 : CMSMcQ : yet further changes +1997-12-02 : TB : further changes (see TB to XML WG, 2 December 1997) - 1997-12-02 : CMSMcQ : deal with as many corrections and +1997-12-02 : CMSMcQ : deal with as many corrections and comments from the proofreaders as possible: entify hard-coded document date in pubdate element, change expansion of entity WebSGML, update status description as per Dan Connolly (am not sure about refernece to Berners-Lee et al.), -add 'The' to abstract as per WG decision, +add 'The' to abstract as per WG decision, move Relationship to Existing Standards to back matter and combine with References, re-order back matter so normative appendices come first, re-tag back matter so informative appendices are tagged informdiv1, -remove XXX XXX from list of 'normative' specs in prose, +remove XXX XXX from list of 'normative' specs in prose, move some references from Other References to Normative References, add RFC 1738, 1808, and 2141 to Other References (they are not normative since we do not require the processor to enforce any rules based on them), -add reference to 'Fielding draft' (Berners-Lee et al.), +add reference to 'Fielding draft' (Berners-Lee et al.), move notation section to end of body, drop URIchar non-terminal and use SkipLit instead, -lose stray reference to defunct nonterminal 'markupdecls', -move reference to Aho et al. into appendix (Tim's right), +lose stray reference to defunct nonterminal 'markupdecls', +move reference to Aho et al. into appendix (Tim's right), add prose note saying that hash marks and fragment identifiers are NOT part of the URI formally speaking, and are NOT legal in -system identifiers (processor 'may' signal an error). +system identifiers (processor 'may' signal an error). Work through: Tim Bray reacting to James Clark, Tim Bray on his own, @@ -180,12 +175,12 @@ Eve Maler, NOT DONE YET: change binary / text to unparsed / parsed. -handle James's suggestion about < in attriubte values +handle James's suggestion about < in attriubte values uppercase hex characters, namechar list, - 1997-12-01 : JB : add some column-width parameters - 1997-12-01 : CMSMcQ : begin round of changes to incorporate +1997-12-01 : JB : add some column-width parameters +1997-12-01 : CMSMcQ : begin round of changes to incorporate recent WG decisions and other corrections: binding sources of character encoding info (27 Aug / 3 Sept), correct wording of Faust quotation (restore dropped line), @@ -193,7 +188,7 @@ drop SDD from EncodingDecl, change text at version number 1.0, drop misleading (wrong!) sentence about ignorables and extenders, modify definition of PCData to make bar on msc grammatical, -change grammar's handling of internal subset (drop non-terminal markupdecls), +change grammar's handling of internal subset (drop non-terminal markupdecls), change definition of includeSect to allow conditional sections, add integral-declaration constraint on internal subset, drop misleading / dangerous sentence about relationship of @@ -203,18 +198,18 @@ add rule about space normalization in public identifiers, add description of how to generate our name-space rules from Unicode character database (needs further work!). - 1997-10-08 : TB : Removed %-constructs again, new rules +1997-10-08 : TB : Removed %-constructs again, new rules for PE appearance. - 1997-10-01 : TB : Case-sensitive markup; cleaned up +1997-10-01 : TB : Case-sensitive markup; cleaned up element-type defs, lotsa little edits for style - 1997-09-25 : TB : Change to elm's new DTD, with +1997-09-25 : TB : Change to elm's new DTD, with substantial detail cleanup as a side-effect - 1997-07-24 : CMSMcQ : correct error (lost *) in definition +1997-07-24 : CMSMcQ : correct error (lost *) in definition of ignoreSectContents (thanks to Makoto Murata) - Allow all empty elements to have end-tags, consistent with +Allow all empty elements to have end-tags, consistent with SGML TC (as per JJC). - 1997-07-23 : CMSMcQ : pre-emptive strike on pending corrections: -introduce the term 'empty-element tag', note that all empty elements +1997-07-23 : CMSMcQ : pre-emptive strike on pending corrections: +introduce the term 'empty-element tag', note that all empty elements may use it, and elements declared EMPTY must use it. Add WFC requiring encoding decl to come first in an entity. Redefine notations to point to PIs as well as binary entities. @@ -223,21 +218,21 @@ examples with Byte Order Mark. Add content model as a term and clarify that it applies to both mixed and element content. - 1997-06-30 : CMSMcQ : change date, some cosmetic changes, +1997-06-30 : CMSMcQ : change date, some cosmetic changes, changes to productions for choice, seq, Mixed, NotationType, -Enumeration. Follow James Clark's suggestion and prohibit +Enumeration. Follow James Clark's suggestion and prohibit conditional sections in internal subset. TO DO: simplify -production for ignored sections as a result, since we don't -need to worry about parsers which don't expand PErefs finding +production for ignored sections as a result, since we don't +need to worry about parsers which don't expand PErefs finding a conditional section. - 1997-06-29 : TB : various edits - 1997-06-29 : CMSMcQ : further changes: +1997-06-29 : TB : various edits +1997-06-29 : CMSMcQ : further changes: Suppress old FINAL EDIT comments and some dead material. -Revise occurrences of % in grammar to exploit Henry Thompson's pun, +Revise occurrences of % in grammar to exploit Henry Thompson's pun, especially markupdecl and attdef. Remove RMD requirement relating to element content (?). - 1997-06-28 : CMSMcQ : Various changes for 1 July draft: +1997-06-28 : CMSMcQ : Various changes for 1 July draft: Add text for draconian error handling (introduce the term Fatal Error). RE deleta est (changing wording from @@ -248,44 +243,44 @@ Add colon as name character. Change def of %operator. Change standard definitions of lt, gt, amp. Strip leading zeros from #x00nn forms. - 1997-04-02 : CMSMcQ : final corrections of editorial errors -found in last night's proofreading. Reverse course once more on -well-formed: Webster's Second hyphenates it, and that's enough +1997-04-02 : CMSMcQ : final corrections of editorial errors +found in last night's proofreading. Reverse course once more on +well-formed: Webster's Second hyphenates it, and that's enough for me. - 1997-04-01 : CMSMcQ : corrections from JJC, EM, HT, and self - 1997-03-31 : Tim Bray : many changes - 1997-03-29 : CMSMcQ : some Henry Thompson (on entity handling), +1997-04-01 : CMSMcQ : corrections from JJC, EM, HT, and self +1997-03-31 : Tim Bray : many changes +1997-03-29 : CMSMcQ : some Henry Thompson (on entity handling), some Charles Goldfarb, some ERB decisions (PE handling in miscellaneous declarations. Changed Ident element to accept def attribute. Allow normalization of Unicode characters. move def of systemliteral into section on literals. - 1997-03-28 : CMSMcQ : make as many corrections as possible, from +1997-03-28 : CMSMcQ : make as many corrections as possible, from Terry Allen, Norbert Mikula, James Clark, Jon Bosak, Henry Thompson, Paul Grosso, and self. Among other things: give in on "well formed" (Terry is right), tentatively rename QuotedCData as AttValue and Literal as EntityValue to be more informative, since attribute values are the only place QuotedCData was used, and -vice versa for entity text and Literal. (I'd call it Entity Text, +vice versa for entity text and Literal. (I'd call it Entity Text, but 8879 uses that name for both internal and external entities.) - 1997-03-26 : CMSMcQ : resynch the two forks of this draft, reapply -my changes dated 03-20 and 03-21. Normalize old 'may not' to 'must not' -except in the one case where it meant 'may or may not'. - 1997-03-21 : TB : massive changes on plane flight from Chicago +1997-03-26 : CMSMcQ : resynch the two forks of this draft, reapply +my changes dated 03-20 and 03-21. Normalize old 'may not' to 'must not' +except in the one case where it meant 'may or may not'. +1997-03-21 : TB : massive changes on plane flight from Chicago to Vancouver - 1997-03-21 : CMSMcQ : correct as many reported errors as possible. +1997-03-21 : CMSMcQ : correct as many reported errors as possible. - 1997-03-20 : CMSMcQ : correct typos listed in CMSMcQ hand copy of spec. - 1997-03-20 : CMSMcQ : cosmetic changes preparatory to revision for +1997-03-20 : CMSMcQ : correct typos listed in CMSMcQ hand copy of spec. +1997-03-20 : CMSMcQ : cosmetic changes preparatory to revision for WWW conference April 1997: restore some of the internal entity references (e.g. to docdate, etc.), change character xA0 to &nbsp; and define nbsp as &#160;, and refill a lot of paragraphs for legibility. - 1996-11-12 : CMSMcQ : revise using Tim's edits: +1996-11-12 : CMSMcQ : revise using Tim's edits: Add list type of NUMBERED and change most lists either to BULLETS or to NUMBERED. Suppress QuotedNames, Names (not used). Correct trivial-grammar doc type decl. -Rename 'marked section' as 'CDATA section' passim. +Rename 'marked section' as 'CDATA section' passim. Also edits from James Clark: Define the set of characters from which [^abc] subtracts. Charref should use just [0-9] not Digit. @@ -293,9 +288,9 @@ Location info needs cleaner treatment: remove? (ERB question). One example of a PI has wrong pic. Clarify discussion of encoding names. -Encoding failure should lead to unspecified results; don't +Encoding failure should lead to unspecified results; don't prescribe error recovery. -Don't require exposure of entity boundaries. +Don't require exposure of entity boundaries. Ignore white space in element content. Reserve entity names of the form u-NNNN. Clarify relative URLs. @@ -303,33 +298,33 @@ And some of my own: Correct productions for content model: model cannot consist of a name, so "elements ::= cp" is no good. - 1996-11-11 : CMSMcQ : revise for style. +1996-11-11 : CMSMcQ : revise for style. Add new rhs to entity declaration, for parameter entities. - 1996-11-10 : CMSMcQ : revise for style. +1996-11-10 : CMSMcQ : revise for style. Fix / complete section on names, characters. Add sections on parameter entities, conditional sections. Still to do: Add compatibility note on deterministic content models. Finish stylistic revision. - 1996-10-31 : TB : Add Entity Handling section - 1996-10-30 : TB : Clean up term & termdef. Slip in +1996-10-31 : TB : Add Entity Handling section +1996-10-30 : TB : Clean up term & termdef. Slip in ERB decision re EMPTY. - 1996-10-28 : TB : Change DTD. Implement some of Michael's +1996-10-28 : TB : Change DTD. Implement some of Michael's suggestions. Change comments back to //. Introduce language for XML namespace reservation. Add section on white-space handling. Lots more cleanup. - 1996-10-24 : CMSMcQ : quick tweaks, implement some ERB +1996-10-24 : CMSMcQ : quick tweaks, implement some ERB decisions. Characters are not integers. Comments are /* */ not //. Add bibliographic refs to 10646, HyTime, Unicode. -Rename old Cdata as MsData since it's only seen +Rename old Cdata as MsData since it's only seen in marked sections. Call them attribute-value pairs not name-value pairs, except once. Internal subset is optional, needs -'?'. Implied attributes should be signaled to the app, not +'?'. Implied attributes should be signaled to the app, not have values supplied by processor. - 1996-10-16 : TB : track down & excise all DSD references; +1996-10-16 : TB : track down & excise all DSD references; introduce some EBNF for entity declarations. - 1996-10-?? : TB : consistency check, fix up scraps so +1996-10-?? : TB : consistency check, fix up scraps so they all parse, get formatter working, correct a few productions. - 1996-10-10/11 : CMSMcQ : various maintenance, stylistic, and +1996-10-10/11 : CMSMcQ : various maintenance, stylistic, and organizational changes: Replace a few literals with xmlpio and pic entities, to make them consistent and ensure we can change pic @@ -340,33 +335,33 @@ Move old 2.2 XML Processors and Apps into intro. Mention comments, PIs, and marked sections in discussion of delimiter escaping. Streamline discussion of doctype decl syntax. -Drop old section of 'PI syntax' for doctype decl, and add +Drop old section of 'PI syntax' for doctype decl, and add section on partial-DTD summary PIs to end of Logical Structures section. -Revise DSD syntax section to use Tim's subset-in-a-PI +Revise DSD syntax section to use Tim's subset-in-a-PI mechanism. - 1996-10-10 : TB : eliminate name recognizers (and more?) - 1996-10-09 : CMSMcQ : revise for style, consistency through 2.3 +1996-10-10 : TB : eliminate name recognizers (and more?) +1996-10-09 : CMSMcQ : revise for style, consistency through 2.3 (Characters) - 1996-10-09 : CMSMcQ : re-unite everything for convenience, +1996-10-09 : CMSMcQ : re-unite everything for convenience, at least temporarily, and revise quickly - 1996-10-08 : TB : first major homogenization pass - 1996-10-08 : TB : turn "current" attribute on div type into +1996-10-08 : TB : first major homogenization pass +1996-10-08 : TB : turn "current" attribute on div type into CDATA - 1996-10-02 : TB : remould into skeleton + entities - 1996-09-30 : CMSMcQ : add a few more sections prior to exchange +1996-10-02 : TB : remould into skeleton + entities +1996-09-30 : CMSMcQ : add a few more sections prior to exchange with Tim. - 1996-09-20 : CMSMcQ : finish transcribing notes. - 1996-09-19 : CMSMcQ : begin transcribing notes for draft. - 1996-09-13 : CMSMcQ : made outline from notes of 09-06, +1996-09-20 : CMSMcQ : finish transcribing notes. +1996-09-19 : CMSMcQ : begin transcribing notes for draft. +1996-09-13 : CMSMcQ : made outline from notes of 09-06, do some housekeeping - - -
- - - Introduction -

Extensible Markup Language, abbreviated XML, describes a class of + + +

+ + +Introduction +

Extensible Markup Language, abbreviated XML, describes a class of data objects called XML documents and partially describes the behavior of computer programs which process them. XML is an application profile or @@ -375,40 +370,40 @@ Language . By construction, XML documents are conforming SGML documents.

-

XML documents are made up of storage units called entities, which contain either parsed +

XML documents are made up of storage units called entities, which contain either parsed or unparsed data. Parsed data is made up of characters, some of which form character data, and some of which form markup. -Markup encodes a description of the document's storage layout and +Markup encodes a description of the document's storage layout and logical structure. XML provides a mechanism to impose constraints on the storage layout and logical structure.

-

A software module +

A software module called an XML processor is used to read XML documents and provide access to their content and structure. It is assumed that an XML processor is doing its work on behalf of another module, called the application. This specification describes the required behavior of an XML processor in terms of how it must read XML data and the information it must provide to the application.

- - Origin and Goals -

XML was developed by an XML Working Group (originally known as the + +Origin and Goals +

XML was developed by an XML Working Group (originally known as the SGML Editorial Review Board) formed under the auspices of the World Wide Web Consortium (W3C) in 1996. It was chaired by Jon Bosak of Sun Microsystems with the active participation of an XML Special Interest Group (previously known as the SGML Working Group) also organized by the W3C. The membership of the XML Working Group is given -in an appendix. Dan Connolly served as the WG's contact with the W3C. +in an appendix. Dan Connolly served as the WG's contact with the W3C.

-

The design goals for XML are:

XML shall be straightforwardly usable over the +

The design goals for XML are:

XML shall be straightforwardly usable over the Internet.

XML shall support a wide variety of applications.

XML shall be compatible with SGML.

It shall be easy to write programs which process XML documents.

The number of optional features in XML is to be kept to the absolute minimum, ideally zero.

XML documents should be human-legible and reasonably clear.

The XML design should be prepared quickly.

The design of XML shall be formal and concise.

XML documents shall be easy to create.

Terseness in XML markup is of minimal importance.

-

This specification, +

This specification, together with associated standards (Unicode and ISO/IEC 10646 for characters, Internet RFC 1766 for language identification tags, @@ -417,13 +412,13 @@ ISO 3166 for country name codes), provides all the information necessary to understand XML Version &XML.version; and construct computer programs to process it.

-

This version of the XML specification +

This version of the XML specification &doc.distribution;.

- - - Terminology -

The terminology used to describe XML documents is defined in the body of + + +Terminology +

The terminology used to describe XML documents is defined in the body of this specification. The terms defined in the following list are used in building those definitions and in describing the actions of an XML processor: @@ -447,7 +442,7 @@ the processor may make unprocessed data from the document (with intermingled character data and markup) available to the application. Once a fatal error is detected, however, the processor must not continue normal processing (i.e., it must not -continue to pass character data and information about the document's +continue to pass character data and information about the document's logical structure to the application in the normal way).

Conforming software may or must (depending on the modal verb in the sentence) behave as described; if it does, it must @@ -483,13 +478,13 @@ documents can be processed by the existing installed base of SGML processors which predate the &WebSGML;.

- - + + - - Documents -

- + +Documents +

+ A data object is an XML document if it is well-formed, as @@ -497,8 +492,8 @@ defined in this specification. A well-formed XML document may in addition be valid if it meets certain further constraints. -

-

Each XML document has both a logical and a physical structure. +

+

Each XML document has both a logical and a physical structure. Physically, the document is composed of units called entities. An entity may refer to other entities to cause their inclusion in the document. A document begins in a "root" or document entity. Logically, the document is composed of declarations, elements, @@ -510,9 +505,9 @@ markup. The logical and physical structures must nest properly, as described in .

- - Well-Formed XML Documents -

+ +Well-Formed XML Documents +

A textual object is a well-formed XML document if:

Taken as a whole, it @@ -520,12 +515,12 @@ matches the production labeled document.

Each of the parsed entities which is referenced directly or indirectly within the document is well-formed.

-

+

Documentdocumentprolog element Misc*

-

Matching the document production +

Matching the document production implies that:

It contains one or more elements.

- - - Common Syntactic Constructs -

This section defines some symbols used widely in the grammar.

-

S (white space) consists of one or more space (#x20) + + +Common Syntactic Constructs +

This section defines some symbols used widely in the grammar.

+

S (white space) consists of one or more space (#x20) characters, carriage returns, line feeds, or tabs. White SpaceS(#x20 | #x9 | #xD | #xA)+

-

Characters are classified for convenience as letters, digits, or other +

Characters are classified for convenience as letters, digits, or other characters. Letters consist of an alphabetic or syllabic base character possibly followed by one or more combining characters, or of an ideographic character. Full definitions of the specific characters in each class are given in .

-

A Name is a token +

A Name is a token beginning with a letter or one of a few punctuation characters, and continuing with letters, digits, hyphens, underscores, colons, or full stops, together known as name characters. Names beginning with the string "xml", or any string -which would match (('X'|'x') ('M'|'m') ('L'|'l')), are +which would match (('X'|'x') ('M'|'m') ('L'|'l')), are reserved for standardization in this or future versions of this specification.

- -

The colon character within XML names is reserved for experimentation with + +

The colon character within XML names is reserved for experimentation with name spaces. Its meaning is expected to be standardized at some future point, at which point those documents @@ -623,19 +618,19 @@ adopted for XML will in fact use the colon as a name-space delimiter.) In practice, this means that authors should not use the colon in XML names except as part of name-space experiments, but that XML processors should accept the colon as a name character.

- -

An + +

An Nmtoken (name token) is any mixture of name characters. Names and TokensNameCharLetter | Digit -| '.' | '-' | '_' | ':' +| '.' | '-' | '_' | ':' | CombiningChar -| ExtenderName(Letter | '_' | ':') +| ExtenderName(Letter | '_' | ':') (NameChar)*NamesName (S Name)*Nmtoken(NameChar)+NmtokensNmtoken (S Nmtoken)*

-

Literal data is any quoted string not containing +

Literal data is any quoted string not containing the quotation mark used as a delimiter for that string. Literals are used for specifying the content of internal entities @@ -645,35 +640,35 @@ and external identifiers (SystemLiteral). Note that a SystemLiteral can be parsed without scanning for markup. -LiteralsEntityValue'"' +LiteralsEntityValue'"' ([^%&"] | PEReference | Reference)* -'"' +'"' |  -"'" -([^%&'] +"'" +([^%&'] | PEReference | Reference)* -"'"AttValue'"' +"'"AttValue'"' ([^<&"] | Reference)* -'"' +'"' |  -"'" -([^<&'] +"'" +([^<&'] | Reference)* -"'"SystemLiteral('"' [^"]* '"') | ("'" [^']* "'") -PubidLiteral'"' PubidChar* -'"' -| "'" (PubidChar - "'")* "'"PubidChar#x20 | #xD | #xA +"'"SystemLiteral('"' [^"]* '"') | ("'" [^']* "'") +PubidLiteral'"' PubidChar* +'"' +| "'" (PubidChar - "'")* "'"PubidChar#x20 | #xD | #xA | [a-zA-Z0-9] -| [-'()+,./:=?;!*#@$_%] +| [-'()+,./:=?;!*#@$_%]

- - - Character Data and Markup -

Text consists of intermingled + + +Character Data and Markup +

Text consists of intermingled character data and markup. Markup takes the form of @@ -688,12 +683,12 @@ data and markup. processing instructions.

-

- All text that is not markup +

+All text that is not markup constitutes the character data of the document. -

-

The ampersand character (&) and the left angle bracket (<) +

+

The ampersand character (&) and the left angle bracket (<) may appear in their literal form only when used as markup delimiters, or within a comment, a processing instruction, @@ -720,59 +715,59 @@ in content, when that string is not marking the end of a CDATA section.

-

+

In the content of elements, character data is any string of characters which does not contain the start-delimiter of any markup. In a CDATA section, character data is any string of characters not including the CDATA-section-close delimiter, "]]>".

-

+

To allow attribute values to contain both single and double quotes, the -apostrophe or single-quote character (') may be represented as +apostrophe or single-quote character (') may be represented as "&apos;", and the double-quote character (") as "&quot;". -Character DataCharData[^<&]* - ([^<&]* ']]>' [^<&]*) +Character DataCharData[^<&]* - ([^<&]* ']]>' [^<&]*)

- - - Comments -

- Comments may + + +Comments +

+Comments may appear anywhere in a document outside other markup; in addition, they may appear within the document type declaration at places allowed by the grammar. -They are not part of the document's character +They are not part of the document's character data; an XML processor may, but need not, make it possible for an application to retrieve the text of comments. For compatibility, the string "--" (double-hyphen) must not occur within comments. -CommentsComment'<!--' -((Char - '-') -| ('-' (Char - '-')))* -'-->' +CommentsComment'<!--' +((Char - '-') +| ('-' (Char - '-')))* +'-->' -

-

An example of a comment: +

+

An example of a comment: <!&como; declarations for <head> & <body> &comc;>

- - - Processing Instructions -

Processing + + +Processing Instructions +

Processing instructions (PIs) allow documents to contain instructions for applications. -Processing InstructionsPI'<?' PITarget +Processing InstructionsPI'<?' PITarget (S (Char* - (Char* &pic; Char*)))? &pic;PITargetName - -(('X' | 'x') ('M' | 'm') ('L' | 'l')) -PIs are not part of the document's character +(('X' | 'x') ('M' | 'm') ('L' | 'l')) +PIs are not part of the document's character data, but must be passed through to the application. The PI begins with a target (PITarget) used to identify the application to which the instruction is directed. @@ -784,10 +779,10 @@ XML Notation mechanism may be used for formal declaration of PI targets.

- - - CDATA Sections -

CDATA sections + + +CDATA Sections +

CDATA sections may occur anywhere character data may occur; they are used to escape blocks of text containing characters which would @@ -796,9 +791,9 @@ string "<![CDATA[" and end with the string "]]>": CDATA SectionsCDSectCDStart CData -CDEndCDStart'<![CDATA['CData(Char* - -(Char* ']]>' Char*)) -CDEnd']]>' +CDEndCDStart'<![CDATA['CData(Char* - +(Char* ']]>' Char*)) +CDEnd']]>' Within a CDATA section, only the CDEnd string is recognized as markup, so that left angle brackets and ampersands may occur in @@ -806,16 +801,16 @@ their literal form; they need not (and cannot) be escaped using "&lt;" and "&amp;". CDATA sections cannot nest.

-

An example of a CDATA section, in which "<greeting>" and +

An example of a CDATA section, in which "<greeting>" and "</greeting>" are recognized as character data, not markup: <![CDATA[<greeting>Hello, world!</greeting>]]>

- - - Prolog and Document Type Declaration -

XML documents + + +Prolog and Document Type Declaration +

XML documents may, and should, begin with an XML declaration which specifies the version of @@ -829,7 +824,7 @@ and so is this: Hello, world! ]]>

-

The version number "1.0" should be used to indicate +

The version number "1.0" should be used to indicate conformance to this version of this specification; it is an error for a document to use the value "1.0" if it does not conform to this version of this specification. @@ -845,7 +840,7 @@ it become necessary. Processors may signal an error if they receive documents labeled with versions they do not support.

-

The function of the markup in an XML document is to describe its +

The function of the markup in an XML document is to describe its storage and logical structure and to associate attribute-value pairs with its logical structures. XML provides a mechanism, the document type declaration, to define constraints on the logical structure and to support the use of @@ -855,7 +850,7 @@ predefined storage units. valid if it has an associated document type declaration and if the document complies with the constraints expressed in it.

-

The document type declaration must appear before +

The document type declaration must appear before the first element in the document. PrologprologXMLDecl? Misc* @@ -865,11 +860,11 @@ the first element in the document. EncodingDecl? SDDecl? S? -&pic;VersionInfoS 'version' Eq -(' VersionNum ' -| " VersionNum ")EqS? '=' S?VersionNum([a-zA-Z0-9_.:] | '-')+MiscComment | PI | +&pic;VersionInfoS 'version' Eq +(' VersionNum ' +| " VersionNum ")EqS? '=' S?VersionNum([a-zA-Z0-9_.:] | '-')+MiscComment | PI | S

-

The XML +

The XML document type declaration contains or points to markup declarations @@ -886,7 +881,7 @@ both. The DTD for a document consists of both subsets taken together.

-

+

A markup declaration is an element type declaration, an attribute-list declaration, @@ -898,37 +893,37 @@ within parameter entities, as described in the well-formedness and validity constraints below. For fuller information, see .

- - Document Type Definition - - - doctypedecl - '<!DOCTYPE' S + +Document Type Definition + + +doctypedecl +'<!DOCTYPE' S Name (S ExternalID)? -S? ('[' +S? ('[' (markupdecl | PEReference | S)* -']' -S?)? '>' - - - - markupdecl - elementdecl +']' +S?)? '>' + + + +markupdecl +elementdecl | AttlistDecl | EntityDecl | NotationDecl | PI | Comment - - - - - -

The markup declarations may be made up in whole or in part of + + + + + +

The markup declarations may be made up in whole or in part of the replacement text of parameter entities. The productions later in this specification for @@ -936,16 +931,16 @@ individual nonterminals (elementdecl, AttlistDecl, and so on) describe the declarations after all the parameter entities have been included.

- - Root Element Type -

+ +Root Element Type +

The Name in the document type declaration must match the element type of the root element.

- - - Proper Declaration/PE Nesting -

Parameter-entity + + +Proper Declaration/PE Nesting +

Parameter-entity replacement text must be properly nested with markup declarations. That is to say, if either the first character @@ -954,18 +949,18 @@ declaration (markupdecl above) is contained in the replacement text for a parameter-entity reference, both must be contained in the same replacement text.

- - - PEs in Internal Subset -

In the internal DTD subset, + + +PEs in Internal Subset +

In the internal DTD subset, parameter-entity references can occur only where markup declarations can occur, not within markup declarations. (This does not apply to references that occur in external parameter entities or to the external subset.)

- -

+ +

Like the internal subset, the external subset and any external parameter entities referred to in the DTD must consist of a series of complete markup declarations of the types @@ -986,19 +981,19 @@ construct; this is not allowed in the internal subset. | PEReference | S )*

-

The external subset and external parameter entities also differ +

The external subset and external parameter entities also differ from the internal subset in that in them, parameter-entity references are permitted within markup declarations, not only between markup declarations.

-

An example of an XML document with a document type declaration: +

An example of an XML document with a document type declaration: Hello, world! ]]> The system identifier "hello.dtd" gives the URI of a DTD for the document.

-

The declarations can also be given locally, as in this +

The declarations can also be given locally, as in this example: - - - Standalone Document Declaration -

Markup declarations can affect the content of the document, + + +Standalone Document Declaration +

Markup declarations can affect the content of the document, as passed from an XML processor to an application; examples are attribute defaults and entity declarations. @@ -1025,10 +1020,10 @@ whether or not there are such declarations which appear external to the document entity. Standalone Document DeclarationSDDecl S -'standalone' Eq -(("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"')) +'standalone' Eq +(("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"'))

-

+

In a standalone document declaration, the value "yes" indicates that there are no markup declarations external to the document @@ -1044,49 +1039,49 @@ document, of references to external entities, when those entities are internally declared, does not change its standalone status.

-

If there are no external markup declarations, the standalone document +

If there are no external markup declarations, the standalone document declaration has no meaning. If there are external markup declarations but there is no standalone document declaration, the value "no" is assumed.

-

Any XML document for which standalone="no" holds can +

Any XML document for which standalone="no" holds can be converted algorithmically to a standalone document, which may be desirable for some network delivery applications.

- - Standalone Document Declaration -

The standalone document declaration must have + +Standalone Document Declaration +

The standalone document declaration must have the value "no" if any external markup declarations contain declarations of:

- - -

attributes with default values, if + + +

attributes with default values, if elements to which these attributes apply appear in the document without specifications of values for these attributes, or

- - -

entities (other than &magicents;), + + +

entities (other than &magicents;), if references to those entities appear in the document, or

- - -

attributes with values subject to + + +

attributes with values subject to normalization, where the attribute appears in the document with a value which will change as a result of normalization, or

- - -

element types with element content, + + +

element types with element content, if white space occurs directly within any instance of those types.

- - - -

An example XML declaration with a standalone document declaration:<?xml version="&XML.version;" standalone='yes'?>

- - - White Space Handling -

In editing XML documents, it is often convenient to use "white space" + + + +

An example XML declaration with a standalone document declaration:<?xml version="&XML.version;" standalone='yes'?>

+ + +White Space Handling +

In editing XML documents, it is often convenient to use "white space" (spaces, tabs, and blank lines, denoted by the nonterminal S in this specification) to set apart the markup for greater readability. Such white space is typically @@ -1094,14 +1089,14 @@ not intended for inclusion in the delivered version of the document. On the other hand, "significant" white space that should be preserved in the delivered version is common, for example in poetry and source code.

-

An XML processor +

An XML processor must always pass all characters in a document that are not markup through to the application. A validating XML processor must also inform the application which of these characters constitute white space appearing in element content.

-

A special attribute +

A special attribute named xml:space may be attached to an element to signal an intention that in that element, white space should be preserved by applications. @@ -1111,7 +1106,7 @@ When declared, it must be given as an enumerated type whose only possible values are "default" and "preserve". For example:]]>

-

The value "default" signals that applications' +

The value "default" signals that applications' default white-space processing modes are acceptable for this element; the value "preserve" indicates the intent that applications preserve all the white space. @@ -1119,19 +1114,19 @@ This declared intent is considered to apply to all elements within the content of the element where it is specified, unless overriden with another instance of the xml:space attribute.

-

The root element of any document +

The root element of any document is considered to have signaled no intentions as regards application space handling, unless it provides a value for this attribute or the attribute is declared with a default value.

- - - End-of-Line Handling -

XML parsed entities are often stored in + + +End-of-Line Handling +

XML parsed entities are often stored in computer files which, for editing convenience, are organized into lines. These lines are typically separated by some combination of the characters carriage-return (#xD) and line-feed (#xA).

-

To simplify the tasks of applications, +

To simplify the tasks of applications, wherever an external parsed entity or the literal entity value of an internal parsed entity contains either the literal two-character sequence "#xD#xA" or a standalone literal @@ -1141,10 +1136,10 @@ pass to the application the single character #xA. conveniently be produced by normalizing all line breaks to #xA on input, before parsing.)

- - - Language Identification -

In document processing, it is often useful to + + +Language Identification +

In document processing, it is often useful to identify the natural or formal language in which the content is written. @@ -1158,9 +1153,9 @@ In valid documents, this attribute, like any other, must be The values of the attribute are language identifiers as defined by , "Tags for the Identification of Languages": Language IdentificationLanguageIDLangcode -('-' Subcode)*LangcodeISO639Code | +('-' Subcode)*LangcodeISO639Code | IanaCode | -UserCodeISO639Code([a-z] | [A-Z]) ([a-z] | [A-Z])IanaCode('i' | 'I') '-' ([a-z] | [A-Z])+UserCode('x' | 'X') '-' ([a-z] | [A-Z])+Subcode([a-z] | [A-Z])+ +UserCodeISO639Code([a-z] | [A-Z]) ([a-z] | [A-Z])IanaCode('i' | 'I') '-' ([a-z] | [A-Z])+UserCode('x' | 'X') '-' ([a-z] | [A-Z])+Subcode([a-z] | [A-Z])+ The Langcode may be any of the following:

a two-letter language code as defined by , "Codes @@ -1170,7 +1165,7 @@ prefix "i-" (or "I-")

x-" or "X-" in order to ensure that they do not conflict with names later standardized or registered with IANA

-

There may be any number of Subcode segments; if +

There may be any number of Subcode segments; if the first subcode segment exists and the Subcode consists of two letters, then it must be a country code from @@ -1182,11 +1177,11 @@ a subcode for the language in question registered with IANA, unless the Langcode begins with the prefix "x-" or "X-".

-

It is customary to give the language code in lower case, and +

It is customary to give the language code in lower case, and the country code (if any) in upper case. Note that these values, unlike other names in XML documents, are case insensitive.

-

For example: +

For example: The quick brown fox jumps over the lazy dog.

What colour is it?

What color is it?

@@ -1200,7 +1195,7 @@ are case insensitive.

element and (unless otherwise via attribute default values) to the values of all of its attributes with free-text (CDATA) values. --> -

The intent declared with xml:lang is considered to apply to +

The intent declared with xml:lang is considered to apply to all attributes and content of the element where it is specified, unless overridden with an instance of xml:lang on another element within that content.

@@ -1219,7 +1214,7 @@ value for xml:lang: The application, not the XML processor, is responsible for this ' inheritance' of attribute values. --> -

A simple declaration for xml:lang might take +

A simple declaration for xml:lang might take the form xml:lang NMTOKEN #IMPLIED but specific default values may also be given, if appropriate. In a @@ -1229,12 +1224,12 @@ notes in English, the xml:lang attribute might be declared this way: ]]>

- - + + - - Logical Structures -

Each XML document contains one or more + +Logical Structures +

Each XML document contains one or more elements, the boundaries of which are either delimited by start-tags and end-tags, or, for empty elements, by an empty-element tag. Each element has a type, @@ -1243,79 +1238,79 @@ identifier" (GI), and may have a set of attribute specifications. Each attribute specification has a name and a value.

- - Element - - element - - EmptyElemTag - - | STag content + +Element + +element + +EmptyElemTag + +| STag content ETag - - - - -

This specification does not constrain the semantics, use, or (beyond + + + + +

This specification does not constrain the semantics, use, or (beyond syntax) names of the element types and attributes, except that names -beginning with a match to (('X'|'x')('M'|'m')('L'|'l')) +beginning with a match to (('X'|'x')('M'|'m')('L'|'l')) are reserved for standardization in this or future versions of this specification.

- - Element Type Match -

-The Name in an element's end-tag must match + +Element Type Match +

+The Name in an element's end-tag must match the element type in the start-tag.

- - - Element Valid -

An element is + + +Element Valid +

An element is valid if there is a declaration matching elementdecl where the Name matches the element type, and one of the following holds:

- - -

The declaration matches EMPTY and the element has no + + +

The declaration matches EMPTY and the element has no content.

- - -

The declaration matches children and + + +

The declaration matches children and the sequence of child elements belongs to the language generated by the regular expression in the content model, with optional white space (characters matching the nonterminal S) between each pair of child elements.

- - -

The declaration matches Mixed and + + +

The declaration matches Mixed and the content consists of character data and child elements whose types match names in the content model.

- - -

The declaration matches ANY, and the types + + +

The declaration matches ANY, and the types of any child elements have been declared.

- - - - - Start-Tags, End-Tags, and Empty-Element Tags -

The beginning of every + + + + +Start-Tags, End-Tags, and Empty-Element Tags +

The beginning of every non-empty XML element is marked by a start-tag. -Start-tagSTag'<' Name +Start-tagSTag'<' Name (S Attribute)* -S? '>'AttributeName Eq +S? '>'AttributeName Eq AttValue The Name in the start- and end-tags gives the -element's type. +element's type. The Name-AttValue pairs are referred to as @@ -1325,126 +1320,126 @@ the attribute specifications of the element, referred to as the attribute name and the content of the AttValue (the text between the -' or " delimiters) +' or " delimiters) as the attribute value.

- - Unique Att Spec -

+ +Unique Att Spec +

No attribute name may appear more than once in the same start-tag or empty-element tag.

- - - Attribute Value Type -

+ + +Attribute Value Type +

The attribute must have been declared; the value must be of the type declared for it. (For attribute types, see .)

- - - No External Entity References -

+ + +No External Entity References +

Attribute values cannot contain direct or indirect entity references to external entities.

- - - No < in Attribute Values -

The replacement text of any entity + + +No < in Attribute Values +

The replacement text of any entity referred to directly or indirectly in an attribute value (other than "&lt;") must not contain a <.

- -

An example of a start-tag: + +

An example of a start-tag: <termdef id="dt-dog" term="dog">

-

- The end of every element +

+The end of every element that begins with a start-tag must be marked by an end-tag -containing a name that echoes the element's type as given in the +containing a name that echoes the element's type as given in the start-tag: -End-tagETag'</' Name -S? '>' +End-tagETag'</' Name +S? '>' -

-

An example of an end-tag:</termdef>

-

- The +

+

An example of an end-tag:</termdef>

+

+The text between the start-tag and -end-tag is called the element's +end-tag is called the element's content: Content of Elementscontent(element | CharData | Reference | CDSect | PI | Comment)* -

-

If an element is empty, +

+

If an element is empty, it must be represented either by a start-tag immediately followed by an end-tag or by an empty-element tag. An empty-element tag takes a special form: -Tags for Empty ElementsEmptyElemTag'<' Name (S +Tags for Empty ElementsEmptyElemTag'<' Name (S Attribute)* S? -'/>' +'/>'

-

Empty-element tags may be used for any element which has no +

Empty-element tags may be used for any element which has no content, whether or not it is declared using the keyword EMPTY. For interoperability, the empty-element tag must be used, and can only be used, for elements which are declared EMPTY.

-

Examples of empty elements: +

Examples of empty elements: <IMG align="left" src="http://www.w3.org/Icons/WWW/w3c_home" /> <br></br> <br/>

- - - Element Type Declarations -

The element structure of an + + +Element Type Declarations +

The element structure of an XML document may, for validation purposes, be constrained using element type and attribute-list declarations. -An element type declaration constrains the element's +An element type declaration constrains the element's content.

-

Element type declarations often constrain which element types can +

Element type declarations often constrain which element types can appear as children of the element. At user option, an XML processor may issue a warning when a declaration mentions an element type for which no declaration is provided, but this is not an error.

-

An element +

An element type declaration takes the form: -Element Type Declarationelementdecl'<!ELEMENT' S +Element Type Declarationelementdecl'<!ELEMENT' S Name S contentspec -S? '>'contentspec'EMPTY' -| 'ANY' +S? '>'contentspec'EMPTY' +| 'ANY' | Mixed | children where the Name gives the element type being declared.

- - Unique Element Type Declaration -

+ +Unique Element Type Declaration +

No element type may be declared more than once.

- -

Examples of element type declarations: + +

Examples of element type declarations: <!ELEMENT br EMPTY> <!ELEMENT p (#PCDATA|emph)* > <!ELEMENT %name.para; %content.para; > <!ELEMENT container ANY>

- - Element Content -

An element type has + +Element Content +

An element type has element content when elements of that type must contain only child elements (no character data), optionally separated by @@ -1461,14 +1456,14 @@ choice lists of content particles, or sequence lists of content particles: Element-content Modelschildren(choice | seq) -('?' | '*' | '+')?cp(Name +('?' | '*' | '+')?cp(Name | choice | seq) -('?' | '*' | '+')?choice'(' S? cp -( S? '|' S? cp )* -S? ')'seq'(' S? cp -( S? ',' S? cp )* -S? ')' +('?' | '*' | '+')?choice'(' S? cp +( S? '|' S? cp )* +S? ')'seq'(' S? cp +( S? ',' S? cp )* +S? ')' where each Name is the type of an element which may appear as a child. Any content @@ -1486,7 +1481,7 @@ must appear exactly once. This syntax and meaning are identical to those used in the productions in this specification.

-

+

The content of an element matches a content model if and only if it is possible to trace out a path through the content model, obeying the sequence, choice, and repetition operators and matching each element in @@ -1497,9 +1492,9 @@ For more information, see .

- - Proper Group/PE Nesting -

Parameter-entity + +Proper Group/PE Nesting +

Parameter-entity replacement text must be properly nested with parenthetized groups. That is to say, if either of the opening or closing parentheses @@ -1508,7 +1503,7 @@ in a choice, seq, or is contained in the replacement text for a parameter entity, both must be contained in the same replacement text.

-

For interoperability, +

For interoperability, if a parameter-entity reference appears in a choice, seq, or Mixed construct, its replacement text @@ -1517,48 +1512,48 @@ neither the first nor last non-blank character of the replacement text should be a connector (| or ,).

- -

Examples of element-content models: + +

Examples of element-content models: <!ELEMENT spec (front, body, back?)> <!ELEMENT div1 (head, (p | list | note)*, div2*)> <!ELEMENT dictionary-body (%div.mix; | %dict.mix;)*>

- - - Mixed Content -

An element + + +Mixed Content +

An element type has mixed content when elements of that type may contain character data, optionally interspersed with child elements. In this case, the types of the child elements may be constrained, but not their order or their number of occurrences: -Mixed-content DeclarationMixed'(' S? -'#PCDATA' +Mixed-content DeclarationMixed'(' S? +'#PCDATA' (S? -'|' +'|' S? Name)* S? -')*' | '(' S? '#PCDATA' S? ')' +')*' | '(' S? '#PCDATA' S? ')' where the Names give the types of elements that may appear as children.

- - No Duplicate Types -

The same name must not appear more than once in a single mixed-content + +No Duplicate Types +

The same name must not appear more than once in a single mixed-content declaration.

- -

Examples of mixed content declarations: + +

Examples of mixed content declarations: <!ELEMENT p (#PCDATA|a|ul|b|i|em)*> <!ELEMENT p (#PCDATA | %font; | %phrase; | %special; | %form;)* > <!ELEMENT b (#PCDATA)>

- - - - Attribute-List Declarations -

Attributes are used to associate + + + +Attribute-List Declarations +

Attributes are used to associate name-value pairs with elements. Attribute specifications may appear only within start-tags and empty-element tags; @@ -1571,14 +1566,14 @@ element type.

To establish type constraints for these attributes.

To provide default values for attributes.

-

- +

+ Attribute-list declarations specify the name, data type, and default value (if any) of each attribute associated with a given element type: -Attribute-list DeclarationAttlistDecl'<!ATTLIST' S +Attribute-list DeclarationAttlistDecl'<!ATTLIST' S Name AttDef* -S? '>'AttDefS Name +S? '>'AttDefS Name S AttType S DefaultDecl The Name in the @@ -1588,8 +1583,8 @@ declared for an element type not itself declared, but this is not an error. The Name in the AttDef rule is the name of the attribute. -

-

+

+

When more than one AttlistDecl is provided for a given element type, the contents of all those provided are merged. When more than one definition is provided for the same attribute of a @@ -1606,39 +1601,39 @@ provided for a given element type, or more than one attribute definition is provided for a given attribute, but this is not an error.

- - Attribute Types -

XML attribute types are of three kinds: a string type, a + +Attribute Types +

XML attribute types are of three kinds: a string type, a set of tokenized types, and enumerated types. The string type may take any literal string as a value; the tokenized types have varying lexical and semantic constraints, as noted: Attribute TypesAttTypeStringType | TokenizedType | EnumeratedType -StringType'CDATA'TokenizedType'ID'| 'IDREF'| 'IDREFS'| 'ENTITY'| 'ENTITIES'| 'NMTOKEN'| 'NMTOKENS' +StringType'CDATA'TokenizedType'ID'| 'IDREF'| 'IDREFS'| 'ENTITY'| 'ENTITIES'| 'NMTOKEN'| 'NMTOKENS'

- - ID -

+ +ID +

Values of type ID must match the Name production. A name must not appear more than once in an XML document as a value of this type; i.e., ID values must uniquely identify the elements which bear them.

- - - One ID per Element Type -

No element type may have more than one ID attribute specified.

- - - ID Attribute Default -

An ID attribute must have a declared default of #IMPLIED or + + +One ID per Element Type +

No element type may have more than one ID attribute specified.

+ + +ID Attribute Default +

An ID attribute must have a declared default of #IMPLIED or #REQUIRED.

- - - IDREF -

+ + +IDREF +

Values of type IDREF must match the Name production, and values of type IDREFS must match @@ -1647,10 +1642,10 @@ each Name must match the value of an ID attribute on some element in the XML document; i.e. IDREF values must match the value of some ID attribute.

- - - Entity Name -

+ + +Entity Name +

Values of type ENTITY must match the Name production, values of type ENTITIES must match @@ -1660,79 +1655,79 @@ match the name of an unparsed entity declared in the DTD.

- - - Name Token -

+ + +Name Token +

Values of type NMTOKEN must match the Nmtoken production; values of type NMTOKENS must match Nmtokens.

- + -

Enumerated attributes can take one +

Enumerated attributes can take one of a list of values provided in the declaration. There are two kinds of enumerated types: Enumerated Attribute TypesEnumeratedTypeNotationType | Enumeration -NotationType'NOTATION' +NotationType'NOTATION' S -'(' +'(' S? Name -(S? '|' S? +(S? '|' S? Name)* -S? ')' -Enumeration'(' S? +S? ')' +Enumeration'(' S? Nmtoken -(S? '|' +(S? '|' S? Nmtoken)* S? -')' +')' A NOTATION attribute identifies a notation, declared in the DTD with associated system and/or public identifiers, to be used in interpreting the element to which the attribute is attached.

- - Notation Attributes -

+ +Notation Attributes +

Values of this type must match one of the notation names included in the declaration; all notation names in the declaration must be declared.

- - - Enumeration -

+ + +Enumeration +

Values of this type must match one of the Nmtoken tokens in the declaration.

- -

For interoperability, the same + +

For interoperability, the same Nmtoken should not occur more than once in the enumerated attribute types of a single element type.

- - - Attribute Defaults -

An attribute declaration provides + + +Attribute Defaults +

An attribute declaration provides information on whether -the attribute's presence is required, and if not, how an XML processor should +the attribute's presence is required, and if not, how an XML processor should react if a declared attribute is absent in a document. -Attribute DefaultsDefaultDecl'#REQUIRED' -| '#IMPLIED' | (('#FIXED' S)? AttValue) +Attribute DefaultsDefaultDecl'#REQUIRED' +| '#IMPLIED' | (('#FIXED' S)? AttValue)

-

In an attribute declaration, #REQUIRED means that the +

In an attribute declaration, #REQUIRED means that the attribute must always be provided, #IMPLIED that no default value is provided. - + - - Physical Structures -

An XML document may consist + +Physical Structures +

An XML document may consist of one or many storage units. These are called entities; they all have content and are all (except for the document entity, see below, and @@ -1902,13 +1897,13 @@ Each XML document has one entity called the document entity, which serves as the starting point for the XML processor and may contain the whole document.

-

Entities may be either parsed or unparsed. -A parsed entity's +

Entities may be either parsed or unparsed. +A parsed entity's contents are referred to as its replacement text; this text is considered an integral part of the document.

-

An +

An unparsed entity is a resource whose contents may or may not be text, and if text, may not be XML. @@ -1919,12 +1914,12 @@ that an XML processor make the identifiers for the entity and notation available to the application, XML places no constraints on the contents of unparsed entities.

-

+

Parsed entities are invoked by name using entity references; unparsed entities by name, given in the value of ENTITY or ENTITIES attributes.

-

General entities +

General entities are entities for use within the document content. In this specification, general entities are sometimes referred to with the unqualified term entity when this leads @@ -1936,25 +1931,25 @@ are recognized in different contexts. Furthermore, they occupy different namespaces; a parameter entity and a general entity with the same name are two distinct entities.

- - Character and Entity References -

+ +Character and Entity References +

A character reference refers to a specific character in the ISO/IEC 10646 character set, for example one not directly accessible from available input devices. -Character ReferenceCharRef'&#' [0-9]+ ';' | '&hcro;' [0-9a-fA-F]+ ';' +Character ReferenceCharRef'&#' [0-9]+ ';' | '&hcro;' [0-9a-fA-F]+ ';' Legal Character

Characters referred to using character references must match the production for Char.

If the character reference begins with "&#x", the digits and letters up to the terminating ; provide a hexadecimal -representation of the character's code point in ISO/IEC 10646. +representation of the character's code point in ISO/IEC 10646. If it begins just with "&#", the digits up to the terminating -; provide a decimal representation of the character's +; provide a decimal representation of the character's code point.

-

An entity +

An entity reference refers to the content of a named entity. References to parsed general entities @@ -1965,34 +1960,34 @@ delimiters. semicolon (;) as delimiters.

- - Entity Reference - - Reference - EntityRef + +Entity Reference + +Reference +EntityRef | CharRef - - - EntityRef - '&' Name ';' - - - - - - - PEReference - '%' Name ';' - - - - - - - Entity Declared -

In a document without any DTD, a document with only an internal + + +EntityRef +'&' Name ';' + + + + + + +PEReference +'%' Name ';' + + + + + + +Entity Declared +

In a document without any DTD, a document with only an internal DTD subset which contains no parameter entity references, or a document with -"standalone='yes'", +"standalone='yes'", the Name given in the entity reference must match that in an entity declaration, except that @@ -2002,17 +1997,17 @@ The declaration of a parameter entity must precede any reference to it. Similarly, the declaration of a general entity must precede any reference to it which appears in a default value in an attribute-list declaration.

-

Note that if entities are declared in the external subset or in +

Note that if entities are declared in the external subset or in external parameter entities, a non-validating processor is not obligated to read and process their declarations; for such documents, the rule that an entity must be declared is a well-formedness constraint only -if standalone='yes'.

- - - Entity Declared -

In a document with an external subset or external parameter -entities with "standalone='no'", +if standalone='yes'.

+ + +Entity Declared +

In a document with an external subset or external parameter +entities with "standalone='no'", the Name given in the entity reference must match that in an entity declaration. For interoperability, valid documents should declare the entities @@ -2022,51 +2017,51 @@ The declaration of a parameter entity must precede any reference to it. Similarly, the declaration of a general entity must precede any reference to it which appears in a default value in an attribute-list declaration.

- + - - Parsed Entity -

+ +Parsed Entity +

An entity reference must not contain the name of an unparsed entity. Unparsed entities may be referred to only in attribute values declared to be of type ENTITY or ENTITIES.

- - - No Recursion -

+ + +No Recursion +

A parsed entity must not contain a recursive reference to itself, either directly or indirectly.

- - - In DTD -

+ + +In DTD +

Parameter-entity references may only appear in the DTD.

- -

Examples of character and entity references: + +

Examples of character and entity references: Type <key>less-than</key> (&hcro;3C;) to save options. This document was prepared on &docdate; and is classified &security-level;.

-

Example of a parameter-entity reference: +

Example of a parameter-entity reference: %ISOLat2;]]>

- - - Entity Declarations -

+ + +Entity Declarations +

Entities are declared thus: Entity DeclarationEntityDeclGEDecl | PEDeclGEDecl'<!ENTITY' S Name +--> | PEDeclGEDecl'<!ENTITY' S Name S EntityDef -S? '>'PEDecl'<!ENTITY' S '%' S +S? '>'PEDecl'<!ENTITY' S '%' S Name S -PEDef S? '>'EntityDefEntityValue +PEDef S? '>'EntityDefEntityValue | (ExternalID NDataDecl?)PEDefEntityValue @@ -2079,9 +2074,9 @@ If the same entity is declared more than once, the first declaration encountered is binding; at user option, an XML processor may issue a warning if entities are declared multiple times.

- - Internal Entities -

If + +Internal Entities +

If the entity definition is an EntityValue, the defined entity is called an internal entity. @@ -2093,41 +2088,41 @@ Note that some processing of entity and character references in the produce the correct replacement text: see .

-

An internal entity is a parsed +

An internal entity is a parsed entity.

-

Example of an internal entity declaration: +

Example of an internal entity declaration: <!ENTITY Pub-Status "This is a pre-release of the specification.">

- - - External Entities -

- If the entity is not + + +External Entities +

+If the entity is not internal, it is an external entity, declared as follows: External Entity DeclarationExternalID'SYSTEM' S -SystemLiteral| 'PUBLIC' S + -->ExternalID'SYSTEM' S +SystemLiteral| 'PUBLIC' S PubidLiteral S SystemLiteral -NDataDeclS 'NDATA' S +NDataDeclS 'NDATA' S Name If the NDataDecl is present, this is a general unparsed entity; otherwise it is a parsed entity. -

- - Notation Declared -

+

+ +Notation Declared +

The Name must match the declared name of a notation.

- -

The + +

The SystemLiteral -is called the entity's system identifier. It is a URI, +is called the entity's system identifier. It is a URI, which may be used to retrieve the entity. Note that the hash mark (#) and fragment identifier frequently used with URIs are not, formally, part of the URI itself; @@ -2143,21 +2138,21 @@ A URI might thus be relative to the containing the external DTD subset, or to some other external parameter entity.

-

An XML processor should handle a non-ASCII character in a URI by +

An XML processor should handle a non-ASCII character in a URI by representing the character in UTF-8 as one or more bytes, and then escaping these bytes with the URI escaping mechanism (i.e., by converting each byte to %HH, where HH is the hexadecimal notation of the byte value).

-

+

In addition to a system identifier, an external identifier may include a public identifier. -An XML processor attempting to retrieve the entity's content may use the public +An XML processor attempting to retrieve the entity's content may use the public identifier to try to generate an alternative URI. If the processor is unable to do so, it must use the URI specified in the system literal. Before a match is attempted, all strings of white space in the public identifier must be normalized to single space characters (#x20), and leading and trailing white space must be removed.

-

Examples of external entity declarations: +

Examples of external entity declarations: <!ENTITY open-hatch SYSTEM "http://www.textuality.com/boilerplate/OpenHatch.xml"> <!ENTITY open-hatch @@ -2166,27 +2161,27 @@ and leading and trailing white space must be removed.

<!ENTITY hatch-pic SYSTEM "../grafix/OpenHatch.gif" NDATA gif >

- - - - Parsed Entities - - The Text Declaration -

External parsed entities may each begin with a text + + + +Parsed Entities + +The Text Declaration +

External parsed entities may each begin with a text declaration. Text DeclarationTextDecl&xmlpio; VersionInfo? EncodingDecl S? &pic;

-

The text declaration must be provided literally, not +

The text declaration must be provided literally, not by reference to a parsed entity. No text declaration may appear at any position other than the beginning of an external parsed entity.

- - - Well-Formed Parsed Entities -

The document entity is well-formed if it matches the production labeled + + +Well-Formed Parsed Entities +

The document entity is well-formed if it matches the production labeled document. An external general parsed entity is well-formed if it matches the production labeled @@ -2202,7 +2197,7 @@ matches the production labeled content. All internal parameter entities are well-formed by definition.

-

A consequence of well-formedness in entities is that the logical +

A consequence of well-formedness in entities is that the logical and physical structures in an XML document are properly nested; no start-tag, end-tag, @@ -2214,22 +2209,22 @@ and physical structures in an XML document are properly nested; no reference, or entity reference can begin in one entity and end in another.

- - - Character Encoding in Entities -

Each external parsed entity in an XML document may use a different + + +Character Encoding in Entities +

Each external parsed entity in an XML document may use a different encoding for its characters. All XML processors must be able to read entities in either UTF-8 or UTF-16.

-

Entities encoded in UTF-16 must +

Entities encoded in UTF-16 must begin with the Byte Order Mark described by ISO/IEC 10646 Annex E and Unicode Appendix B (the ZERO WIDTH NO-BREAK SPACE character, #xFEFF). This is an encoding signature, not part of either the markup or the character data of the XML document. XML processors must be able to use this character to differentiate between UTF-8 and UTF-16 encoded documents.

-

Although an XML processor is required to read only entities in +

Although an XML processor is required to read only entities in the UTF-8 and UTF-16 encodings, it is recognized that other encodings are used around the world, and it may be desired for XML processors to read entities that use them. @@ -2237,16 +2232,16 @@ Parsed entities which are stored in an encoding other than UTF-8 or UTF-16 must begin with a text declaration containing an encoding declaration: Encoding DeclarationEncodingDeclS -'encoding' Eq -('"' EncName '"' | -"'" EncName "'" ) -EncName[A-Za-z] ([A-Za-z0-9._] | '-')*Encoding name contains only Latin characters +'encoding' Eq +('"' EncName '"' | +"'" EncName "'" ) +EncName[A-Za-z] ([A-Za-z0-9._] | '-')*Encoding name contains only Latin characters In the document entity, the encoding declaration is part of the XML declaration. The EncName is the name of the encoding used.

-

In an encoding declaration, the values +

In an encoding declaration, the values "UTF-8", "UTF-16", "ISO-10646-UCS-2", and @@ -2271,7 +2266,7 @@ Note that these registered names are defined to be case-insensitive, so processors wishing to match against them should do so in a case-insensitive way.

-

In the absence of information provided by an external +

In the absence of information provided by an external transport protocol (e.g. HTTP or MIME), it is an error for an entity including an encoding declaration to be presented to the XML processor @@ -2283,16 +2278,16 @@ declaration to use an encoding other than UTF-8. Note that since ASCII is a subset of UTF-8, ordinary ASCII entities do not strictly need an encoding declaration.

-

It is a fatal error when an XML processor +

It is a fatal error when an XML processor encounters an entity with an encoding that it is unable to process.

-

Examples of encoding declarations: -<?xml encoding='UTF-8'?> -<?xml encoding='EUC-JP'?>

- - - - XML Processor Treatment of Entities and References -

The table below summarizes the contexts in which character references, +

Examples of encoding declarations: +<?xml encoding='UTF-8'?> +<?xml encoding='EUC-JP'?>

+ + + +XML Processor Treatment of Entities and References +

The table below summarizes the contexts in which character references, entity references, and invocations of unparsed entities might appear and the required behavior of an XML processor in each case. @@ -2309,138 +2304,138 @@ the value of an attribute which has been declared as type ENTITY, or as one of the space-separated tokens in the value of an attribute which has been declared as type ENTITIES.

as a reference -within a parameter or internal entity's +within a parameter or internal entity's literal entity value in -the entity's declaration; corresponds to the nonterminal +the entity's declaration; corresponds to the nonterminal EntityValue.

as a reference within either the internal or external subsets of the DTD, but outside of an EntityValue or AttValue.

- - - - - Entity Type - Character - - - Parameter - Internal + + + + +Entity Type +Character + + +Parameter +Internal General - External Parsed +External Parsed General - Unparsed - - - Reference +Unparsed + + +Reference in Content - - Not recognized - - - Included - - - Included if validating - - - Forbidden - - - Included - - - - Reference + +Not recognized + + +Included + + +Included if validating + + +Forbidden + + +Included + + + +Reference in Attribute Value - - Not recognized - - - Included in literal - - - Forbidden - - - Forbidden - - - Included - - - - Occurs as + +Not recognized + + +Included in literal + + +Forbidden + + +Forbidden + + +Included + + + +Occurs as Attribute Value - - Not recognized - - - Forbidden - - - Forbidden - - - Notify - - - Not recognized - - - - Reference + +Not recognized + + +Forbidden + + +Forbidden + + +Notify + + +Not recognized + + + +Reference in EntityValue - - Included in literal - - - Bypassed - - - Bypassed - - - Forbidden - - - Included - - - - Reference + +Included in literal + + +Bypassed + + +Bypassed + + +Forbidden + + +Included + + + +Reference in DTD - - Included as PE - - - Forbidden - - - Forbidden - - - Forbidden - - - Forbidden - - - - - - Not Recognized -

Outside the DTD, the % character has no + +Included as PE + + +Forbidden + + +Forbidden + + +Forbidden + + +Forbidden + + + + + +Not Recognized +

Outside the DTD, the % character has no special significance; thus, what would be parameter entity references in the DTD are not recognized as markup in content. Similarly, the names of unparsed entities are not recognized except when they appear in the value of an appropriately declared attribute.

- - - Included -

- An entity is + + +Included +

+An entity is included when its replacement text is retrieved and processed, in place of the reference itself, @@ -2458,11 +2453,11 @@ as an entity-reference delimiter.) A character reference is included when the indicated character is processed in place of the reference itself. -

- - - Included If Validating -

When an XML processor recognizes a reference to a parsed entity, in order +

+ + +Included If Validating +

When an XML processor recognizes a reference to a parsed entity, in order to validate the document, the processor must include its @@ -2470,22 +2465,22 @@ replacement text. If the entity is external, and the processor is not attempting to validate the XML document, the processor may, but need not, -include the entity's replacement text. +include the entity's replacement text. If a non-validating parser does not include the replacement text, it must inform the application that it recognized, but did not read, the entity.

-

This rule is based on the recognition that the automatic inclusion +

This rule is based on the recognition that the automatic inclusion provided by the SGML and XML entity mechanism, primarily designed to support modularity in authoring, is not necessarily appropriate for other applications, in particular document browsing. Browsers, for example, when encountering an external parsed entity reference, -might choose to provide a visual indication of the entity's +might choose to provide a visual indication of the entity's presence and retrieve it for display only on demand.

- - - Forbidden -

The following are forbidden, and constitute + + +Forbidden +

The following are forbidden, and constitute fatal errors:

the appearance of a reference to an unparsed entity. @@ -2493,10 +2488,10 @@ presence and retrieve it for display only on demand. DTD except within an EntityValue or AttValue.

a reference to an external entity in an attribute value.

- - - Included in Literal -

When an entity reference appears in an + + +Included in Literal +

When an entity reference appears in an attribute value, or a parameter entity reference appears in a literal entity value, its replacement text is processed in place of the reference itself as though it @@ -2508,13 +2503,13 @@ For example, this is well-formed: ]]> while this is not: -<!ENTITY EndAttr "27'" > -<element attribute='a-&EndAttr;> +<!ENTITY EndAttr "27'" > +<element attribute='a-&EndAttr;>

- - - Notify -

When the name of an unparsed + + +Notify +

When the name of an unparsed entity appears as a token in the value of an attribute of declared type ENTITY or ENTITIES, a validating processor must inform the @@ -2522,16 +2517,16 @@ application of the system and public (if any) identifiers for both the entity and its associated notation.

- - - Bypassed -

When a general entity reference appears in the + + +Bypassed +

When a general entity reference appears in the EntityValue in an entity declaration, it is bypassed and left as is.

- - - Included as PE -

Just as with external parsed entities, parameter entities + + +Included as PE +

Just as with external parsed entities, parameter entities need only be included if validating. When a parameter-entity reference is recognized in the DTD @@ -2542,13 +2537,13 @@ space (#x20) character; the intent is to constrain the replacement text of parameter entities to contain an integral number of grammatical tokens in the DTD.

- - - - Construction of Internal Entity Replacement Text -

In discussing the treatment + + + +Construction of Internal Entity Replacement Text +

In discussing the treatment of internal entities, it is -useful to distinguish two forms of the entity's value. +useful to distinguish two forms of the entity's value. The literal entity value is the quoted string actually present in the entity declaration, corresponding to the @@ -2558,7 +2553,7 @@ text is the content of the entity, after replacement of character references and parameter-entity references.

-

The literal entity value +

The literal entity value as given in an internal entity declaration (EntityValue) may contain character, parameter-entity, and general-entity references. @@ -2579,19 +2574,19 @@ For example, given the following declarations: © 1947 %pub;. &rights;" >]]> then the replacement text for the entity "book" is: La Peste: Albert Camus, -© 1947 Éditions Gallimard. &rights; +© 1947 Éditions Gallimard. &rights; The general-entity reference "&rights;" would be expanded -should the reference "&book;" appear in the document's +should the reference "&book;" appear in the document's content or an attribute value.

-

These simple rules may have complex interactions; for a detailed +

These simple rules may have complex interactions; for a detailed discussion of a difficult example, see .

- - - Predefined Entities -

- Entity and character + + +Predefined Entities +

+Entity and character references can both be used to escape the left angle bracket, ampersand, and other delimiters. A set of general entities (&magicents;) is specified for this purpose. @@ -2601,8 +2596,8 @@ character data, so the numeric character references "&#60;" and "&#38;" may be used to escape < and & when they occur in character data. -

-

All XML processors must recognize these entities whether they +

+

All XML processors must recognize these entities whether they are declared or not. For interoperability, valid XML documents should declare these @@ -2622,36 +2617,36 @@ in the declarations of "lt" and "amp&qu are doubly escaped to meet the requirement that entity replacement be well-formed.

- - - Notation Declarations -

- Notations identify by + + +Notation Declarations +

+Notations identify by name the format of unparsed entities, the format of elements which bear a notation attribute, or the application to which a processing instruction is addressed. -

-

- +

+

+ Notation declarations provide a name for the notation, for use in entity and attribute-list declarations and in attribute specifications, and an external identifier for the notation which may allow an XML processor or its client application to locate a helper application capable of processing data in the given notation. -Notation DeclarationsNotationDecl'<!NOTATION' S Name +Notation DeclarationsNotationDecl'<!NOTATION' S Name S (ExternalID | PublicID) -S? '>'PublicID'PUBLIC' S +S? '>'PublicID'PUBLIC' S PubidLiteral -

-

XML processors must provide applications with the name and external +

+

XML processors must provide applications with the name and external identifier(s) of any notation declared and referred to in an attribute value, attribute definition, or entity declaration. They may additionally resolve the external identifier into the @@ -2661,10 +2656,10 @@ application to call a processor for data in the notation described. (It is not an error, however, for XML documents to declare and refer to notations for which notation-specific applications are not available on the system where the XML processor or application is running.)

- - - Document Entity -

The document + + +Document Entity +

The document entity serves as the root of the entity tree and a starting-point for an XML processor. @@ -2673,22 +2668,22 @@ not specify how the document entity is to be located by an XML processor; unlike other entities, the document entity has no name and might well appear on a processor input stream without any identification at all.

- - + + - - Conformance - - Validating and Non-Validating Processors -

Conforming XML processors fall into two + +Conformance + +Validating and Non-Validating Processors +

Conforming XML processors fall into two classes: validating and non-validating.

-

Validating and non-validating processors alike must report -violations of this specification's well-formedness constraints +

Validating and non-validating processors alike must report +violations of this specification's well-formedness constraints in the content of the document entity and any other parsed entities that they read.

-

+

Validating processors must report violations of the constraints expressed by the declarations in the DTD, and @@ -2698,7 +2693,7 @@ in this specification. To accomplish this, validating XML processors must read and process the entire DTD and all external parsed entities referenced in the document.

-

Non-validating processors are required to check only the +

Non-validating processors are required to check only the document entity, including the entire internal DTD subset, for well-formedness. @@ -2721,10 +2716,10 @@ They must not process encountered after a reference to a parameter entity that is not read, since the entity may have contained overriding declarations.

- - - Using XML Processors -

The behavior of a validating XML processor is highly predictable; it + + +Using XML Processors +

The behavior of a validating XML processor is highly predictable; it must read every piece of a document and report all well-formedness and validity violations. Less is required of a non-validating processor; it need not read any @@ -2749,27 +2744,27 @@ internal entities, or supply where doing so depends on having read declarations in external or parameter entities.

-

For maximum reliability in interoperating between different XML +

For maximum reliability in interoperating between different XML processors, applications which use non-validating processors should not rely on any behaviors not required of such processors. Applications which require facilities such as the use of default attributes or internal entities which are declared in external entities should use validating XML processors.

- - - - Notation -

The formal grammar of XML is given in this specification using a simple + + + +Notation +

The formal grammar of XML is given in this specification using a simple Extended Backus-Naur Form (EBNF) notation. Each rule in the grammar defines one symbol, in the form symbol ::= expression

-

Symbols are written with an initial capital letter if they are +

Symbols are written with an initial capital letter if they are defined by a regular expression, or with an initial lower case letter otherwise. Literal strings are quoted.

-

Within the expression on the right-hand side of a rule, the following +

Within the expression on the right-hand side of a rule, the following expressions are used to match strings of one or more characters:

where N is a hexadecimal integer, the expression matches the character in ISO/IEC 10646 whose canonical @@ -2784,7 +2779,7 @@ with a value in the range(s) indicated (inclusive).

outside the range indicated.

matches any character with a value not among the characters given.

matches a literal string matching -that given inside the double quotes.

matches a literal string matching +that given inside the double quotes.

matches a literal string matching that given inside the single quotes.

 These symbols may be combined to match more complex patterns as follows, where A and B represent simple expressions: @@ -2800,42 +2795,42 @@ associated with a production.

- - - + + + - - References - - Normative References - - + +References + +Normative References + + (Internet Assigned Numbers Authority) Official Names for Character Sets, ed. Keld Simonsen et al. See ftp://ftp.isi.edu/in-notes/iana/assignments/character-sets. - + IETF (Internet Engineering Task Force). RFC 1766: Tags for the Identification of Languages, ed. H. Alvestrand. 1995. - + (International Organization for Standardization). ISO 639:1988 (E). Code for the representation of names of languages. [Geneva]: International Organization for Standardization, 1988. - + (International Organization for Standardization). ISO 3166-1:1997 (E). Codes for the representation of names of countries and their subdivisions — Part 1: Country codes [Geneva]: International Organization for Standardization, 1997. - ISO +ISO (International Organization for Standardization). ISO/IEC 10646-1993 (E). Information technology — Universal Multiple-Octet Coded Character Set (UCS) — Part 1: @@ -2843,67 +2838,67 @@ Architecture and Basic Multilingual Plane. [Geneva]: International Organization for Standardization, 1993 (plus amendments AM 1 through AM 7). - The Unicode Consortium. +The Unicode Consortium. The Unicode Standard, Version 2.0. Reading, Mass.: Addison-Wesley Developers Press, 1996. - - - - Other References - - Aho, Alfred V., + + + +Other References + +Aho, Alfred V., Ravi Sethi, and Jeffrey D. Ullman. Compilers: Principles, Techniques, and Tools. Reading: Addison-Wesley, 1986, rpt. corr. 1988. - + Berners-Lee, T., R. Fielding, and L. Masinter. Uniform Resource Identifiers (URI): Generic Syntax and Semantics. 1997. (Work in progress; see updates to RFC1738.) - Brüggemann-Klein, Anne. +Brüggemann-Klein, Anne. Regular Expressions into Finite Automata. Extended abstract in I. Simon, Hrsg., LATIN 1992, S. 97-98. Springer-Verlag, Berlin 1992. Full Version in Theoretical Computer Science 120: 197-213, 1993. - Brüggemann-Klein, Anne, +Brüggemann-Klein, Anne, and Derick Wood. Deterministic Regular Languages. -Universität Freiburg, Institut für Informatik, +Universität Freiburg, Institut für Informatik, Bericht 38, Oktober 1991. - James Clark. +James Clark. Comparison of SGML and XML. See http://www.w3.org/TR/NOTE-sgml-xml-971215. - + IETF (Internet Engineering Task Force). RFC 1738: Uniform Resource Locators (URL), ed. T. Berners-Lee, L. Masinter, M. McCahill. 1994. - + IETF (Internet Engineering Task Force). RFC 1808: Relative Uniform Resource Locators, ed. R. Fielding. 1995. - + IETF (Internet Engineering Task Force). RFC 2141: URN Syntax, ed. R. Moats. 1997. - ISO +ISO (International Organization for Standardization). ISO 8879:1986(E). Information processing — Text and Office Systems — Standard Generalized Markup Language (SGML). First edition — 1986-10-15. [Geneva]: International Organization for Standardization, 1986. - ISO +ISO (International Organization for Standardization). ISO/IEC 10744-1992 (E). Information technology — Hypermedia/Time-based Structuring Language (HyTime). @@ -2914,12 +2909,12 @@ Standardization, 1992. [Geneva]: International Organization for Standardization, 1996. - - - - - Character Classes -

Following the characteristics defined in the Unicode standard, + + + + +Character Classes +

Following the characteristics defined in the Unicode standard, characters are classed as base characters (among others, these contain the alphabetic characters of the Latin alphabet, without diacritics), ideographic characters, and combining characters (among @@ -3255,7 +3250,7 @@ also distinguished. | [#x30FC-#x30FE]

-

The character classes defined here can be derived from the +

The character classes defined here can be derived from the Unicode character database as follows:

Name start characters must have one of the categories Ll, Lu, Lo, Lt, Nl.

Name characters other than Name-start characters @@ -3268,24 +3263,24 @@ rather than name characters, because the property file classifies them as Alphabetic: [#x02BB-#x02C1], #x0559, #x06E5, #x06E6.

Characters #x20DD-#x20E0 are excluded (in accordance with Unicode, section 5.14).

Character #x00B7 is classified as an extender, because the property list so identifies it.

Character #x0387 is added as a name character, because #x00B7 -is its canonical equivalent.

Characters ':' and '_' are allowed as name-start characters.

Characters '-' and '.' are allowed as name characters.

 +is its canonical equivalent.

Characters ':' and '_' are allowed as name-start characters.

Characters '-' and '.' are allowed as name characters.

- - - XML and SGML -

XML is designed to be a subset of SGML, in that every + + +XML and SGML +

XML is designed to be a subset of SGML, in that every valid XML document should also be a conformant SGML document. For a detailed comparison of the additional restrictions that XML places on documents beyond those of SGML, see .

- - - Expansion of Entity and Character References -

This appendix contains some examples illustrating the + + +Expansion of Entity and Character References +

This appendix contains some examples illustrating the sequence of entity- and character-reference recognition and expansion, as specified in .

-

+

If the DTD contains the declaration An ampersand (&#38;) may be escaped numerically (&#38;#38;) or with a general entity @@ -3310,7 +3305,7 @@ numerically (&) or with a general entity (&). ]]>

-

A more complex example will illustrate the rules and their +

A more complex example will illustrate the rules and their effects fully. In the following example, the line numbers are solely for reference. @@ -3345,19 +3340,19 @@ recognized, and it is expanded, so the full content of the This sample shows a error-prone method.

- - - Deterministic Content Models -

For compatibility, it is + + +Deterministic Content Models +

For compatibility, it is required that content models in element type declarations be deterministic.

-

SGML +

SGML requires deterministic content models (it calls them "unambiguous"); XML processors built using SGML systems may flag non-deterministic content models as errors.

-

For example, the content model ((b, c) | (b, d)) is +

For example, the content model ((b, c) | (b, d)) is non-deterministic, because given an initial b the parser cannot know which b in the model is being matched without looking ahead to see which element follows the b. @@ -3365,10 +3360,10 @@ In this case, the two references to b can be collapsed into a single reference, making the model read (b, (c | d)). An initial b now clearly -matches only a single name in the content model. The parser doesn't +matches only a single name in the content model. The parser doesn't need to look ahead to see what follows; either c or d would be accepted.

-

More formally: a finite state automaton may be constructed from the +

More formally: a finite state automaton may be constructed from the content model using the standard algorithms, e.g. algorithm 3.5 in section 3.9 of Aho, Sethi, and Ullman . @@ -3382,13 +3377,13 @@ labeled with the same element type name, then the content model is in error and may be reported as an error.

-

Algorithms exist which allow many but not all non-deterministic +

Algorithms exist which allow many but not all non-deterministic content models to be reduced automatically to equivalent deterministic -models; see Brüggemann-Klein 1991 .

- - - Autodetection of Character Encodings -

The XML encoding declaration functions as an internal label on each +models; see Brüggemann-Klein 1991 .

+ + +Autodetection of Character Encodings +

The XML encoding declaration functions as an internal label on each entity, indicating which character encoding is in use. Before an XML processor can read the internal label, however, it apparently has to know what character encoding is in use—which is what the internal label @@ -3405,15 +3400,15 @@ depending on whether the XML entity is presented to the processor without, or with, any accompanying (external) information. We consider the first case first.

-

+

Because each XML entity not in UTF-8 or UTF-16 format must begin with an XML encoding declaration, in which the first characters -must be '<?xml', any conforming processor can detect, +must be '<?xml', any conforming processor can detect, after two to four octets of input, which of the following cases apply. -In reading this list, it may help to know that in UCS-4, '<' is -"#x0000003C" and '?' is "#x0000003F", and the Byte +In reading this list, it may help to know that in UCS-4, '<' is +"#x0000003C" and '?' is "#x0000003F", and the Byte Order Mark required of UTF-16 data streams is "#xFEFF".

-

+

00 00 00 3C: UCS-4, big-endian machine (1234 order)

3C 00 00 00: UCS-4, little-endian machine (4321 order)

00 00 3C 00: UCS-4, unusual octet order (2143)

00 3C 00 00: UCS-4, unusual octet order (3412)

FE FF: UTF-16, big-endian

FF FE: UTF-16, little-endian

00 3C 00 3F: UTF-16, big-endian, no Byte Order Mark (and thus, strictly speaking, in error)

3C 00 3F 00: UTF-16, little-endian, no Byte Order Mark (and thus, strictly speaking, in error)

3C 3F 78 6D: UTF-8, ISO 646, ASCII, some part of ISO 8859, @@ -3430,7 +3425,7 @@ use)

other: UTF-8 without an encoding declaration, or else the data stream is corrupt, fragmentary, or enclosed in a wrapper of some kind

-

+

This level of autodetection is enough to read the XML encoding declaration and parse the character-encoding identifier, which is still necessary to distinguish the individual members of each family @@ -3438,7 +3433,7 @@ of encodings (e.g. to tell UTF-8 from 8859, and the parts of 8859 from each other, or to distinguish the specific EBCDIC code page in use, and so on).

-

+

Because the contents of the encoding declaration are restricted to ASCII characters, a processor can reliably read the entire encoding declaration as soon as it has detected which family of encodings is in @@ -3448,20 +3443,20 @@ reasonably reliable in-band labeling of character encodings, even when external sources of information at the operating-system or transport-protocol level are unreliable.

-

+

Once the processor has detected the character encoding in use, it can act appropriately, whether by invoking a separate input routine for each case, or by calling the proper conversion function on each character of input.

-

+

Like any self-labeling system, the XML encoding declaration will not -work if any software changes the entity's character set or encoding +work if any software changes the entity's character set or encoding without updating the encoding declaration. Implementors of character-encoding routines should be careful to ensure the accuracy of the internal and external information used to label the entity.

-

The second possible case occurs when the XML entity is accompanied +

The second possible case occurs when the XML entity is accompanied by encoding information, as in some file systems and some network protocols. When multiple sources of information are available, @@ -3495,78 +3490,78 @@ in particular, when the MIME types text/xml and application/xml are defined, the recommendations of the relevant RFC will supersede these rules.

- - - W3C XML Working Group -

This specification was prepared and approved for publication by the + + +W3C XML Working Group +

This specification was prepared and approved for publication by the W3C XML Working Group (WG). WG approval of this specification does not necessarily imply that all WG members voted for its approval. The current and former members of the XML WG are:

- - - Jon Bosak, Sun - Chair - - - James Clark - Technical Lead - - - Tim Bray, Textuality and Netscape - XML Co-editor - - - Jean Paoli, Microsoft - XML Co-editor - - - C. M. Sperberg-McQueen, U. of Ill. - XML + + +Jon Bosak, Sun +Chair + + +James Clark +Technical Lead + + +Tim Bray, Textuality and Netscape +XML Co-editor + + +Jean Paoli, Microsoft +XML Co-editor + + +C. M. Sperberg-McQueen, U. of Ill. +XML Co-editor - - - Dan Connolly, W3C - W3C Liaison - - - Paula Angerstein, Texcel - - - Steve DeRose, INSO - - - Dave Hollander, HP - - - Eliot Kimber, ISOGEN - - - Eve Maler, ArborText - - - Tom Magliery, NCSA - - - Murray Maloney, Muzmo and Grif - - - Makoto Murata, Fuji Xerox Information Systems - - - Joel Nava, Adobe - - - Conleth O'Connell, Vignette - - - Peter Sharpe, SoftQuad - - - John Tigue, DataChannel - - - - + + +Dan Connolly, W3C +W3C Liaison + + +Paula Angerstein, Texcel + + +Steve DeRose, INSO + + +Dave Hollander, HP + + +Eliot Kimber, ISOGEN + + +Eve Maler, ArborText + + +Tom Magliery, NCSA + + +Murray Maloney, Muzmo and Grif + + +Makoto Murata, Fuji Xerox Information Systems + + +Joel Nava, Adobe + + +Conleth O'Connell, Vignette + + +Peter Sharpe, SoftQuad + + +John Tigue, DataChannel + + + + -
+
- XML Linking Language (XLink) - Version 1.0 - WD-xlink-19990527 - World Wide Web Consortium Working Draft - - 29 - May - 1999 - - -

This draft is for public discussion.

- - - http://www.w3.org/XML/Group/1999/05/WD-xlink-current - - +XML Linking Language (XLink) +Version 1.0 + WD-xlink-19990527 +World Wide Web Consortium Working Draft + +29 +May +1999 + + +

This draft is for public discussion.

+ + +http://www.w3.org/XML/Group/1999/05/WD-xlink-current + + - http://www.w3.org/XML/Group/1999/05/WD-xlink-19990527 - http://www.w3.org/XML/Group/1999/05/WD-xlink-19990505 - http://www.w3.org/TR/1998/WD-xlink-19980303 - http://www.w3.org/TR/WD-xml-link-970630 - - +http://www.w3.org/XML/Group/1999/05/WD-xlink-19990527 +http://www.w3.org/XML/Group/1999/05/WD-xlink-19990505 +http://www.w3.org/TR/1998/WD-xlink-19980303 +http://www.w3.org/TR/WD-xml-link-970630 + + - - Steve DeRose - Inso Corp. and Brown University - Steven_DeRose@Brown.edu - - - David Orchard - IBM Corp. - dorchard@ca.ibm.com - - - Ben Trafford - Invited Expert - bent@exemplary.net - + +Steve DeRose +Inso Corp. and Brown University +Steven_DeRose@Brown.edu + + +David Orchard +IBM Corp. +dorchard@ca.ibm.com + + +Ben Trafford +Invited Expert +bent@exemplary.net + - - -

This is a W3C Working Draft for review by W3C members and other interested parties. It is a draft document and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use W3C Working Drafts as reference material or to cite them as other than "work in progress". A list of current W3C working drafts can be found at http://www.w3.org/TR.

-

Note: Since working drafts are subject to frequent change, you are advised to reference the above URI, rather than the URIs for working drafts themselves. Some of the work remaining is described in .

-

This work is part of the W3C XML Activity (for current status, see http://www.w3.org/XML/Activity ). For information about the XPointer language which is expected to be used with XLink, see http://www.w3.org/TR/WD-xptr. + + +

This is a W3C Working Draft for review by W3C members and other interested parties. It is a draft document and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use W3C Working Drafts as reference material or to cite them as other than "work in progress". A list of current W3C working drafts can be found at http://www.w3.org/TR.

+

Note: Since working drafts are subject to frequent change, you are advised to reference the above URI, rather than the URIs for working drafts themselves. Some of the work remaining is described in .

+

This work is part of the W3C XML Activity (for current status, see http://www.w3.org/XML/Activity ). For information about the XPointer language which is expected to be used with XLink, see http://www.w3.org/TR/WD-xptr.

-

See http://www.w3.org/TR/NOTE-xlink-principles for additional background on the design principles informing XLink.

-

Also see http://www.w3.org/TR/NOTE-xlink-req/ for the XLink requirements that this document attempts to satisfy.

- - +

See http://www.w3.org/TR/NOTE-xlink-principles for additional background on the design principles informing XLink.

+

Also see http://www.w3.org/TR/NOTE-xlink-req/ for the XLink requirements that this document attempts to satisfy.

+ + -

This specification defines constructs that may be inserted into XML DTDs, schemas and document instances to describe links between objects. It uses XML syntax to create structures that can describe the simple unidirectional hyperlinks of today's HTML as well as more sophisticated links.

- - -

Burlington, Seekonk, et al.: World-Wide Web Consortium, XML Working Group, 1998.

- - -

Created in electronic form.

- - - English - Extended Backus-Naur Form (formal grammar) - - - - 1997-01-15 : Skeleton draft by TB - 1997-01-24 : Fleshed out by sjd - 1997-04-08 : Substantive draft - 1997-06-30 : Public draft - 1997-08-01 : Public draft - 1997-08-05 : Prose/organization work by sjd - 1997-10-14: Conformance and design principles; a bit of cleanup by elm - 1997-11-07: Update for editorial issues per issues doc, by sjd. - 1997-12-01: Update for editorial issues per issues doc in preparation for F2F meeting, by sjd. - 1998-01-13: Editorial cleanup, addition of new design principles, by elm. - 1998-02-27: Splitting out of XLink and XPointer, by elm. - 1998-03-03: Moved most of the XPointer locator stuff here. elm - 1999-04-24: Editorial rewrites to represent new ideas on XLink, especially the inclusion of arcs. bent - 1999-05-05: Prose/organization work by dorchard. Moved much of the semantics section around, from: locators, link semantics, remote resource semantics, local resource semantics; to: resource semantics, locators, behavior semantics, link semantics, arc semantics - 1999-05-12: Prose/organization work. Re-organized some of the sections, removed XML constructs from the document, added descriptive prose, edited document text for clarity. Rewrote the link recognition section. bent - 1999-05-17: Further prose work. Added non-normative examples. Clarified arcs. bent - 1999-05-23: Edited for grammar and clarity. bent - 1999-05-27: Final once-over before sending to group. Fixed sjd's email address. bent - - -
- - +

This specification defines constructs that may be inserted into XML DTDs, schemas and document instances to describe links between objects. It uses XML syntax to create structures that can describe the simple unidirectional hyperlinks of today's HTML as well as more sophisticated links.

+ + +

Burlington, Seekonk, et al.: World-Wide Web Consortium, XML Working Group, 1998.

+ + +

Created in electronic form.

+ + +English +Extended Backus-Naur Form (formal grammar) + + + +1997-01-15 : Skeleton draft by TB +1997-01-24 : Fleshed out by sjd +1997-04-08 : Substantive draft +1997-06-30 : Public draft +1997-08-01 : Public draft +1997-08-05 : Prose/organization work by sjd +1997-10-14: Conformance and design principles; a bit of cleanup by elm +1997-11-07: Update for editorial issues per issues doc, by sjd. +1997-12-01: Update for editorial issues per issues doc in preparation for F2F meeting, by sjd. +1998-01-13: Editorial cleanup, addition of new design principles, by elm. +1998-02-27: Splitting out of XLink and XPointer, by elm. +1998-03-03: Moved most of the XPointer locator stuff here. elm +1999-04-24: Editorial rewrites to represent new ideas on XLink, especially the inclusion of arcs. bent +1999-05-05: Prose/organization work by dorchard. Moved much of the semantics section around, from: locators, link semantics, remote resource semantics, local resource semantics; to: resource semantics, locators, behavior semantics, link semantics, arc semantics +1999-05-12: Prose/organization work. Re-organized some of the sections, removed XML constructs from the document, added descriptive prose, edited document text for clarity. Rewrote the link recognition section. bent +1999-05-17: Further prose work. Added non-normative examples. Clarified arcs. bent +1999-05-23: Edited for grammar and clarity. bent +1999-05-27: Final once-over before sending to group. Fixed sjd's email address. bent + + +
+ + - Introduction -

This specification defines constructs that may be inserted into XML DTDs, schemas, and document instances to describe links between objects. A link, as the term is used here, is an explicit relationship between two or more data objects or portions of data objects. This specification is concerned with the syntax used to assert link existence and describe link characteristics. Implicit (unasserted) relationships, for example that of one word to the next or that of a word in a text to its entry in an on-line dictionary are obviously important, but outside its scope.

-

Links are asserted by elements contained in XML document instances. The simplest case is very like an HTML A link, and has these characteristics: -

The link is expressed at one of its ends (similar to the A element in some document)

Users can only initiate travel from that end to the other

The link's effect on windows, frames, go-back lists, stylesheets in use, and so on is mainly determined by browsers, not by the link itself. For example, traveral of A links normally replaces the current view, perhaps with a user option to open a new window.

The link goes to only one destination (although a server may have great freedom in finding or dynamically creating that destination).

 +Introduction +

This specification defines constructs that may be inserted into XML DTDs, schemas, and document instances to describe links between objects. A link, as the term is used here, is an explicit relationship between two or more data objects or portions of data objects. This specification is concerned with the syntax used to assert link existence and describe link characteristics. Implicit (unasserted) relationships, for example that of one word to the next or that of a word in a text to its entry in an on-line dictionary are obviously important, but outside its scope.

+

Links are asserted by elements contained in XML document instances. The simplest case is very like an HTML A link, and has these characteristics: +

The link is expressed at one of its ends (similar to the A element in some document)

Users can only initiate travel from that end to the other

The link's effect on windows, frames, go-back lists, stylesheets in use, and so on is mainly determined by browsers, not by the link itself. For example, traveral of A links normally replaces the current view, perhaps with a user option to open a new window.

The link goes to only one destination (although a server may have great freedom in finding or dynamically creating that destination).

-

While this set of characteristics is already very powerful and obviously has proven itself highly useful and effective, each of these assumptions also limits the range of hypertext functionality. The linking model defined here provides ways to create links that go beyond each of these specific characteristics, thus providing features previously available mostly in dedicated hypermedia systems. +

While this set of characteristics is already very powerful and obviously has proven itself highly useful and effective, each of these assumptions also limits the range of hypertext functionality. The linking model defined here provides ways to create links that go beyond each of these specific characteristics, thus providing features previously available mostly in dedicated hypermedia systems.

- - Origin and Goals -

Following is a summary of the design principles governing XLink: + +Origin and Goals +

Following is a summary of the design principles governing XLink:

XLink must be straightforwardly usable over the Internet.

XLink must be usable by a wide variety of link usage domains and classes of linking application software.

XLink must support HTML 4.0 linking constructs.

The XLink expression language must be XML.

The XLink design must be formal, concise, and illustrative.

XLinks must be human-readable and human-writable.

XLinks may reside within or outside the documents in which the participating resources reside.

XLink must represent the abstract structure and significance of links.

XLink must be feasible to implement.

XLink must be informed by knowledge of established hypermedia systems and standards.

- + - - Relationship to Existing Standards -

Three standards have been especially influential: + +Relationship to Existing Standards +

Three standards have been especially influential:

HTML: Defines several SGML element types that represent links.

HyTime: Defines inline and out-of-line link structures and some semantic features, including traversal control and presentation of objects.

Text Encoding Initiative Guidelines (TEI P3): Provides structures for creating links, aggregate objects, and link collections out of them.

-

Many other linking systems have also informed this design, especially Dexter, FRESS, MicroCosm, and InterMedia.

- - - Terminology -

The following basic terms apply in this document.

A symbolic representation of traversal behavior in links, especially the direction, context and timing of traversal.

A representation of the relevant structure specified by the tags and attributes in an XML document, based on "groves" as defined in the ISO DSSSL standard.

Abstractly, a link which serves as one of its own resources. Concretely, a link where the content of the linking element serves as a participating resource. HTML A, HyTime clink, and TEI XREF are all inline links.

An explicit relationship between two or more data objects or portions of data objects.

An element that asserts the existence and describes the characteristics of a link.

The content of an inlinelinking element. Note that the content of the linking element could be explicitly pointed to by means of a regular locator in the same linking element, in which case the resource is considered remote, not local.

Data, provided as part of a link, which identifies a - resource.

A link whose traversal can be initiated from more than one of its participating resources. Note that being able to "go back" after following a one-directional link does not make the link multidirectional.

A link whose content does not serve as one of the link's participating resources . Such links presuppose a notion like extended link groups, which instruct application software where to look for links. Out-of-line links are generally required for supporting multidirectional traversal and for allowing read-only resources to have outgoing links.

In the context of link behavior, a parsed link is any link whose content is transcluded into the document where the link originated. The use of the term "parsed" directly refers to the concept in XML of a + resource.

A link whose traversal can be initiated from more than one of its participating resources. Note that being able to "go back" after following a one-directional link does not make the link multidirectional.

A link whose content does not serve as one of the link's participating resources . Such links presuppose a notion like extended link groups, which instruct application software where to look for links. Out-of-line links are generally required for supporting multidirectional traversal and for allowing read-only resources to have outgoing links.

In the context of link behavior, a parsed link is any link whose content is transcluded into the document where the link originated. The use of the term "parsed" directly refers to the concept in XML of a parsed entity.

A resource that belongs to a link. All resources are potential contributors to a link; participating resources are the actual contributors to a particular link.

Any participating resource of a link that is pointed to with a locator.

In the abstract sense, an addressable unit of information or service that is participating in a link. Examples include files, images, documents, programs, and query results. Concretely, anything reachable by the use of a locator in some linking element. Note that this term and its definition are taken from the basic specifications governing the World Wide Web.

A portion of a resource, pointed to as the precise destination of a link. As one example, a link might specify that an entire document be retrieved and displayed, but that some specific part(s) of it is the specific linked data, to be treated in an application-appropriate manner such as indication by highlighting, scrolling, etc.

The action of using a link; that is, of accessing a resource. Traversal may be initiated by a user action (for example, clicking on the displayed content of a linking element) or occur under program control.

- - - Notation -

The formal grammar for locators is given using a simple Extended Backus-Naur Form (EBNF) location, as described in the XML specification.

+ + +Notation +

The formal grammar for locators is given using a simple Extended Backus-Naur Form (EBNF) location, as described in the XML specification.

- - - + + + - Locator Syntax -

The locator for a resource is typically provided by means of a Uniform Resource Identifier, or URI. XPointers can be used in conjunction with the URI structure, as fragment identifiers, to specify a more precise sub-resource.

+Locator Syntax +

The locator for a resource is typically provided by means of a Uniform Resource Identifier, or URI. XPointers can be used in conjunction with the URI structure, as fragment identifiers, to specify a more precise sub-resource.

-

A locator generally contains a URI, as described in IETF RFCs and . As these RFCs state, the URI may include a trailing query (marked by a leading "?"), and be followed by a "#" and a fragment identifier, with the query interpreted by the host providing the indicated resource, and the interpretation of the fragment identifier dependent on the data type of the indicated resource.

+

A locator generally contains a URI, as described in IETF RFCs and . As these RFCs state, the URI may include a trailing query (marked by a leading "?"), and be followed by a "#" and a fragment identifier, with the query interpreted by the host providing the indicated resource, and the interpretation of the fragment identifier dependent on the data type of the indicated resource.

-

In order to locate XML documents and portions of documents, a locator value may contain either a URI or a fragment identifier, or both. Any fragment identifier for pointing into XML must be an XPointer.

-

Special syntax may be used to request the use of particular processing models in accessing the locator's resource. This is designed to reflect the realities of network operation, where it may or may not be desirable to exercise fine control over the distribution of work between local and remote processors. - LocatorLocatorURI| Connector (XPointer | Name)| URI Connector (XPointer | Name)Connector'#' | '|'URIURIchar* +

In order to locate XML documents and portions of documents, a locator value may contain either a URI or a fragment identifier, or both. Any fragment identifier for pointing into XML must be an XPointer.

+

Special syntax may be used to request the use of particular processing models in accessing the locator's resource. This is designed to reflect the realities of network operation, where it may or may not be desirable to exercise fine control over the distribution of work between local and remote processors. + LocatorLocatorURI| Connector (XPointer | Name)| URI Connector (XPointer | Name)Connector'#' | '|'URIURIchar*

-

In this discussion, the term designated resource refers to the resource which an entire locator serves to locate. The following rules apply: +

In this discussion, the term designated resource refers to the resource which an entire locator serves to locate. The following rules apply:

The URI, if provided, locates a resource called the containing resource.

If the URI is not provided, the containing resource is considered to be the document in which the linking element is contained.

If an XPointer is provided, the designated resource is a sub-resource of the containing resource; otherwise the designated resource is the @@ -167,59 +167,59 @@ document. bent--> Oy, yes, i think so. it will require some fun wording, though, so i haven't fixed it yet here -sjd-->

If the Connector is followed directly by a Name, the Name is shorthand for the XPointer"id(Name)"; that is, the sub-resource is the element in the containing resource that has an XML ID attribute whose value matches the Name. This shorthand is to encourage use of the robust id addressing mode.

If the connector is "#", this signals an intent that the containing resource is to be fetched as a whole from the host that provides it, and that the XPointer processing to extract the sub-resource is to be performed on the client, that is to say on the same system where the linking element is recognized and processed.

If the connector is "|", no intent is signaled as to what processing model is to be used to go about accessing the designated resource.

-

Note that the definition of a URI includes an optional query component.

-

In the case where the URI contains a query (to be interpreted by the server), information providers and authors of server software are urged to use queries as follows: - QueryQuery'XML-XPTR=' ( XPointer | Name) +

Note that the definition of a URI includes an optional query component.

+

In the case where the URI contains a query (to be interpreted by the server), information providers and authors of server software are urged to use queries as follows: + QueryQuery'XML-XPTR=' ( XPointer | Name)

- - + + - Link Recognition -

The existence of a link is asserted by a linking element. Linking elements must be recognized reliably by application software in order to provide appropriate display and behavior. There are several ways link recognition could be accomplished: for example, reserving element type names, reserving attributes names, leaving the matter of recognition entirely up to stylesheets and application software, or using the XLink namespace to specify element names and attribute names that would be recognized by namespace and XLink-aware processors. Using element and attribute names within the XLink namespace provides a balance between giving users control of their own markup language design and keeping the identification of linking elements simple and unambiguous.

-

The two approaches to identifying linking elements are relatively simple to implement. For example, here's how the HTML A element would be declared using attributes within the XLink namespace, and then how an element within the XLink namespace might do the same: +Link Recognition +

The existence of a link is asserted by a linking element. Linking elements must be recognized reliably by application software in order to provide appropriate display and behavior. There are several ways link recognition could be accomplished: for example, reserving element type names, reserving attributes names, leaving the matter of recognition entirely up to stylesheets and application software, or using the XLink namespace to specify element names and attribute names that would be recognized by namespace and XLink-aware processors. Using element and attribute names within the XLink namespace provides a balance between giving users control of their own markup language design and keeping the identification of linking elements simple and unambiguous.

+

The two approaches to identifying linking elements are relatively simple to implement. For example, here's how the HTML A element would be declared using attributes within the XLink namespace, and then how an element within the XLink namespace might do the same: <A xlink:type="simple" xlink:href="http://www.w3.org/TR/wd-xlink/" xlink:title="The Xlink Working Draft">The XLink Working Draft.</A> <xlink:simple href="http://www.w3.org/TR/wd-xlink/" title="The XLink Working Draft">The XLink Working Draft</xlink:simple> Any arbitrary element can be made into an XLink by using the xlink:type attribute. And, of course, the explicit XLink elements may be used, as well. This document will go on to describe the linking attributes that are associated with linking elements. It may be assumed by the reader that these attributes would require the xlink namespace prefix if they existed within an arbitrary element, or that they may be used directly if they exist within an explicit Xlink element.

- + - - Linking Attributes -

XLink has several attributes associated with the variety of links it may represent. These attributes define four main concepts: locators, arcs, behaviors, and semantics. Locators define where the actual resource is located. Arcs define the traversal of links. Where does the link come from? Where does it go to? All this information can be stored in the arc attributes. Behaviors define how the link is activated, and what the application should do with the resource being linked to. Semantics define useful information that the application may use, and enables the link for such specalized targets as constricted devices and accessibility software.

- - Locator Attributes -

The only locator attribute at this time is href. This attribute must contain either a string in the form of a URI that defines the remote resource being linked to, a string containing a fragment identifier that links to a local resource, or a string containing a URI with a fragment identifier concacenated onto it.

- - - Arc Attributes -

Arcs contain two attributes, from and to. The from attribute may contain a string containing the content of a role attribute from the resource being linked from. The purpose of the from attribute is to define where this link is being actuated from.

-

The to attribute may contain a string containing the content of a role attribute from the resource being linked to. The purpose of the to attribute is to define where this link traverses to.

-

The application may use this information in a number of ways, especially in a complex hypertext system, but it is mainly useful in providing context for application behavior.

+ +Linking Attributes +

XLink has several attributes associated with the variety of links it may represent. These attributes define four main concepts: locators, arcs, behaviors, and semantics. Locators define where the actual resource is located. Arcs define the traversal of links. Where does the link come from? Where does it go to? All this information can be stored in the arc attributes. Behaviors define how the link is activated, and what the application should do with the resource being linked to. Semantics define useful information that the application may use, and enables the link for such specalized targets as constricted devices and accessibility software.

+ +Locator Attributes +

The only locator attribute at this time is href. This attribute must contain either a string in the form of a URI that defines the remote resource being linked to, a string containing a fragment identifier that links to a local resource, or a string containing a URI with a fragment identifier concacenated onto it.

+ + +Arc Attributes +

Arcs contain two attributes, from and to. The from attribute may contain a string containing the content of a role attribute from the resource being linked from. The purpose of the from attribute is to define where this link is being actuated from.

+

The to attribute may contain a string containing the content of a role attribute from the resource being linked to. The purpose of the to attribute is to define where this link traverses to.

+

The application may use this information in a number of ways, especially in a complex hypertext system, but it is mainly useful in providing context for application behavior.

- - - Behavior Attributes -

There are two attributes associated with behavior: show and actuate. The show attribute defines how the remote resource is to be revealed to the user. It has three options: new, parsed, and replace. The new option indicates that the remote resource should be shown in a new window (or other device context) without replacing the previous content. The parsed option, relating directly to the XML concept of a parsed entity, indicates that the content should be integrated into the document from which the link was actuated. The replace option is the one most commonly seen on the World Wide Web, where the document being linked from is entirely replaced by the object being linked to.

-

The actuate attribute defines how the link is initiated. It has two options: user and auto. The user option indicates that the link must be initiated by some sort of human-initiated selection, such as clicking on an HTML anchor. The auto option indicates that the link is automatically initiated when the application deems that the user has reached the link. It then follows the behavior set out in the show option.

+ + +Behavior Attributes +

There are two attributes associated with behavior: show and actuate. The show attribute defines how the remote resource is to be revealed to the user. It has three options: new, parsed, and replace. The new option indicates that the remote resource should be shown in a new window (or other device context) without replacing the previous content. The parsed option, relating directly to the XML concept of a parsed entity, indicates that the content should be integrated into the document from which the link was actuated. The replace option is the one most commonly seen on the World Wide Web, where the document being linked from is entirely replaced by the object being linked to.

+

The actuate attribute defines how the link is initiated. It has two options: user and auto. The user option indicates that the link must be initiated by some sort of human-initiated selection, such as clicking on an HTML anchor. The auto option indicates that the link is automatically initiated when the application deems that the user has reached the link. It then follows the behavior set out in the show option.

- - - Semantic Attributes -

There are two attributes associated with semantics, role and title. The role attribute is a generic string used to describe the function of the link's content. For example, a poem might have a link with a role="stanza". The role is also used as an identifier for the from and to attributes of arcs.

-

The title attribute is designed to provide human-readable text describing the link. It is very useful for those who have text-based applications, whether that be due to a constricted device that cannot display the link's content, or if it's being read by an application to a visually-impaired user, or if it's being used to create a table of links. The title attribute contains a simple, descriptive string.

- - - - Linking Elements -

There are several kinds of linking elements in XLink: simple links, locators, arcs, and extended links. These elements may be instantiated via element declarations from the XLink namespace, or they may be instantiated via attribute declarations from the XLink namespace. Both kinds of instantiation are described in the definition of each linking element.

-

The simple link is used to declare a link that approximates the functionality of the HTML A element. It has, however, a few added features to increase its value, including the potential declaration of semantics and behavior. The locator elements are used to define the resource being linked to. Some links may contain multiple locators, representing a choice of potential links to be traversed. The arcs are used to define the traversal semantics of the link. Finally, an extended linking element differs from a simple link in that it can connect any number of resources, not just one local resource (optionally) and one remote resource, and in that extended links are more often out-of-line than simple links.

- - Simple Links - -

The following are two examples of linking elements, each showing all the possible attributes that can be associated with a simple link. Here is the explicit XLink simple linking element. + + +Semantic Attributes +

There are two attributes associated with semantics, role and title. The role attribute is a generic string used to describe the function of the link's content. For example, a poem might have a link with a role="stanza". The role is also used as an identifier for the from and to attributes of arcs.

+

The title attribute is designed to provide human-readable text describing the link. It is very useful for those who have text-based applications, whether that be due to a constricted device that cannot display the link's content, or if it's being read by an application to a visually-impaired user, or if it's being used to create a table of links. The title attribute contains a simple, descriptive string.

+ + + +Linking Elements +

There are several kinds of linking elements in XLink: simple links, locators, arcs, and extended links. These elements may be instantiated via element declarations from the XLink namespace, or they may be instantiated via attribute declarations from the XLink namespace. Both kinds of instantiation are described in the definition of each linking element.

+

The simple link is used to declare a link that approximates the functionality of the HTML A element. It has, however, a few added features to increase its value, including the potential declaration of semantics and behavior. The locator elements are used to define the resource being linked to. Some links may contain multiple locators, representing a choice of potential links to be traversed. The arcs are used to define the traversal semantics of the link. Finally, an extended linking element differs from a simple link in that it can connect any number of resources, not just one local resource (optionally) and one remote resource, and in that extended links are more often out-of-line than simple links.

+ +Simple Links + +

The following are two examples of linking elements, each showing all the possible attributes that can be associated with a simple link. Here is the explicit XLink simple linking element. <!ELEMENT xlink:simple ANY> <!ATTLIST xlink:slink href CDATA #REQUIRED @@ -248,33 +248,33 @@ The XLink Working Draft.</foo> Alternately, a simple link could be as terse as this: <foo xlink:href="#stanza1">The First Stanza.</foo>

-

+

There are no constraints on the contents of a simple linking element. In the sample declaration above, it is given a content model of ANY to illustrate that any content model or declared content is acceptable. In a valid document, every element that is significant to XLink must still conform to the constraints expressed in its governing DTD.

-

Note that it is meaningful to have an out-of-line simple link, although +

Note that it is meaningful to have an out-of-line simple link, although such links are uncommon. They are called "one-ended" and are typically used to associate discrete semantic properties with locations. The properties might - be expressed by attributes on the link, the link's element type name, or in + be expressed by attributes on the link, the link's element type name, or in some other way, and are not considered full-fledged resources of the link. Most out-of-line links are extended links, as these have a far wider range of uses.

- - - Extended Links -

- An extended link differs from a simple link in that it can connect any number of resources, not just one local resource (optionally) and one remote resource, and in that extended links are more often out-of-line than simple links. -

-

These additional capabilities of extended links are required for: + + +Extended Links +

+An extended link differs from a simple link in that it can connect any number of resources, not just one local resource (optionally) and one remote resource, and in that extended links are more often out-of-line than simple links. +

+

These additional capabilities of extended links are required for:

Enabling outgoing links in documents that cannot be modified to add an inline link

Creating links to and from resources in formats with no native support for embedded links (such as most multimedia formats)

Applying and filtering sets of relevant links on demand

Enabling other advanced hypermedia capabilities

-

Application software might be expected to provide traversal among all of a link's participating resources (subject to semantic constraints outside the scope of this specification) and to signal the fact that a given resource or sub-resource participates in one or more links when it is displayed (even though there is no markup at exactly that point to signal it).

-

A linking element for an extended link contains a series of child elements that serve as locators and arcs. Because an extended link can have more than one remote resource, it separates out linking itself from the mechanisms used to locate each resource (whereas a simple link combines the two).

-

The xlink:type attribute value for an extended link must be extended, if the link is being instantiated on an arbitrary element. Note that extended links introduce variants of the show and actuate behavior attributes. These attributes, the showdefault and actuatedefault define the same behavior as their counterparts. However, in this case, they are considered to define the default behavior for all the linking elements that they contain.

-

However, when a linking element within an extended link has a show or actuate attribute of its own, that attribute overrides the defaults set on the extended linking element.

-

The extended linking element itself retains those attributes relevant to the link as a whole, and to its local resource if any. Following are two sample declaration for an extended link. The first is an example of the explicit XLink extended link: +

Application software might be expected to provide traversal among all of a link's participating resources (subject to semantic constraints outside the scope of this specification) and to signal the fact that a given resource or sub-resource participates in one or more links when it is displayed (even though there is no markup at exactly that point to signal it).

+

A linking element for an extended link contains a series of child elements that serve as locators and arcs. Because an extended link can have more than one remote resource, it separates out linking itself from the mechanisms used to locate each resource (whereas a simple link combines the two).

+

The xlink:type attribute value for an extended link must be extended, if the link is being instantiated on an arbitrary element. Note that extended links introduce variants of the show and actuate behavior attributes. These attributes, the showdefault and actuatedefault define the same behavior as their counterparts. However, in this case, they are considered to define the default behavior for all the linking elements that they contain.

+

However, when a linking element within an extended link has a show or actuate attribute of its own, that attribute overrides the defaults set on the extended linking element.

+

The extended linking element itself retains those attributes relevant to the link as a whole, and to its local resource if any. Following are two sample declaration for an extended link. The first is an example of the explicit XLink extended link: <!ELEMENT xlink:extended ((xlink:arc | xlink:locator)*)> <!ATTLIST xlink:extended @@ -293,59 +293,59 @@ The XLink Working Draft.</foo> xlink:showdefault (new|parsed|replace) #IMPLIED xlink:actuatedefault (user|auto) #IMPLIED > - The following two examples demonstrate how each of the above might appear within a document instance. Note that the content of these examples would be other elements. For brevity's sake, they've been left blank. The first example shows how the link might appear, using an explicit XLink extended link: + The following two examples demonstrate how each of the above might appear within a document instance. Note that the content of these examples would be other elements. For brevity's sake, they've been left blank. The first example shows how the link might appear, using an explicit XLink extended link: -<xlink:extended role="address book" title="Ben's Address Book" showdefault="replace" actuatedefault="user"> ... </xlink:extended> +<xlink:extended role="address book" title="Ben's Address Book" showdefault="replace" actuatedefault="user"> ... </xlink:extended> And the second shows how the link might appear, using an arbitrary element: -<foo xlink:type="extended" xlink:role="address book" xlink:title="Ben's Address Book" xlink:showdefault="replace" xlink:actuatedefault="user"> ... </foo> +<foo xlink:type="extended" xlink:role="address book" xlink:title="Ben's Address Book" xlink:showdefault="replace" xlink:actuatedefault="user"> ... </foo>

- - - Arc Elements -

An arc is contained within an extended link for the purpose of defining traversal behavior. More than one arc may be associated with a link. Otherwise, arc elements function exactly as the arc attributes might lead on to expect.

+ + +Arc Elements +

An arc is contained within an extended link for the purpose of defining traversal behavior. More than one arc may be associated with a link. Otherwise, arc elements function exactly as the arc attributes might lead on to expect.

- - - - Conformance -

An element conforms to XLink if:

The element has an xml:link attribute whose value is + + + +Conformance +

An element conforms to XLink if:

The element has an xml:link attribute whose value is one of the attribute values prescribed by this specification, and

the element and all of its attributes and content adhere to the syntactic requirements imposed by the chosen xml:link attribute value, as prescribed in this specification.

-

Note that conformance is assessed at the level of individual elements, +

Note that conformance is assessed at the level of individual elements, rather than whole XML documents, because XLink and non-XLink linking mechanisms may be used side by side in any one document.

-

An application conforms to XLink if it interprets XLink-conforming elements +

An application conforms to XLink if it interprets XLink-conforming elements according to all required semantics prescribed by this specification and, for any optional semantics it chooses to support, supports them in the way prescribed.

- - - - - Unfinished Work - - Structured Titles -

The simple title mechanism described in this draft is insufficient to cope + + + + +Unfinished Work + +Structured Titles +

The simple title mechanism described in this draft is insufficient to cope with internationalization or the use of multimedia in link titles. A future version will provide a mechanism for the use of structured link titles.

- - - - References - - Eve Maler and Steve DeRose, editors. + + + +References + +Eve Maler and Steve DeRose, editors. XML Pointer Language (XPointer) V1.0. ArborText, Inso, and Brown University. Burlington, Seekonk, et al.: World Wide Web Consortium, 1998. (See http://www.w3.org/TR/WD-xptr .) - ISO (International Organization for +ISO (International Organization for Standardization). ISO/IEC 10744-1992 (E). Information technology - Hypermedia/Time-based Structuring Language (HyTime). [Geneva]: International Organization for Standardization, 1992. Extended @@ -354,29 +354,29 @@ Annex. [Geneva]: International Organization for Standardization, 1996. (See http://www.ornl.go v/sgml/wg8/hytime/html/is10744r.html ). - IETF (Internet Engineering Task +IETF (Internet Engineering Task Force). RFC 1738: Uniform Resource Locators. 1991. (See http://www.w3.org/Addressing/rfc1738.txt). - IETF (Internet Engineering Task +IETF (Internet Engineering Task Force). RFC 1808: Relative Uniform Resource Locators. 1995. (See http://www.w3.org/Addressing/rfc 1808.txt ). - C. M. Sperberg-McQueen and Lou Burnard, editors. +C. M. Sperberg-McQueen and Lou Burnard, editors. Guidelines for Electronic Text Encoding and Interchange. Association for Computers and the Humanities (ACH), Association for Computational Linguistics (ACL), and Association for Literary and Linguistic Computing (ALLC). Chicago, Oxford: Text Encoding Initiative, 1994. - ]Steven J. DeRose and David G. Durand. 1995. "The +]Steven J. DeRose and David G. Durand. 1995. "The TEI Hypertext Guidelines." In Computing and the Humanities 29(3). Reprinted in Text Encoding Initiative: Background and Context, ed. Nancy Ide and Jean ronis , ISBN 0-7923-3704-2. - - - + + + diff --git a/result/valid/xlink.xml.err b/result/valid/xlink.xml.err index 6e8beefd..48c3b0cb 100644 --- a/result/valid/xlink.xml.err +++ b/result/valid/xlink.xml.err @@ -1,6 +1,6 @@ ./test/valid/xlink.xml:450: validity error: ID dt-arc already defined

An arc is contained within an ^ -./test/valid/xlink.xml:530: validity error: IDREF attribute def reference an unknown ID 'dt-xlg' +./test/valid/xlink.xml:530: validity error: IDREF attribute def reference an unknown ID "dt-xlg" ^ diff --git a/result/xml2 b/result/xml2 index 89abac15..b26b3582 100644 --- a/result/xml2 +++ b/result/xml2 @@ -1,8 +1,8 @@ '> - ]> This sample shows a &tricky; method. diff --git a/test/dtd12 b/test/dtd12 index 033fecab..a0fbf229 100644 --- a/test/dtd12 +++ b/test/dtd12 @@ -1,5 +1,5 @@ - + + ]> &WhatHeSaid; diff --git a/testSAX.c b/testSAX.c index fd65092e..d7b0f12a 100644 --- a/testSAX.c +++ b/testSAX.c @@ -73,6 +73,7 @@ xmlSAXHandler emptySAXHandlerStruct = { NULL, /* xmlParserError */ NULL, /* xmlParserError */ NULL, /* getParameterEntity */ + NULL, /* cdataBlock; */ }; xmlSAXHandlerPtr emptySAXHandler = &emptySAXHandlerStruct; @@ -454,6 +455,21 @@ processingInstructionDebug(void *ctx, const xmlChar *target, (char *) target, (char *) data); } +/** + * cdataBlockDebug: + * @ctx: the user data (XML parser context) + * @value: The pcdata content + * @len: the block length + * + * called when a pcdata block has been parsed + */ +void +cdataBlockDebug(void *ctx, const xmlChar *value, int len) +{ + fprintf(stderr, "SAX.pcdata(%.20s, %d)\n", + (char *) value, len); +} + /** * commentDebug: * @ctxt: An XML parser context @@ -553,6 +569,7 @@ xmlSAXHandler debugSAXHandlerStruct = { errorDebug, fatalErrorDebug, getParameterEntityDebug, + cdataBlockDebug }; xmlSAXHandlerPtr debugSAXHandler = &debugSAXHandlerStruct; diff --git a/tester.c b/tester.c index 46817606..f7a4294c 100644 --- a/tester.c +++ b/tester.c @@ -14,6 +14,8 @@ #include #include +#include +#include #ifdef HAVE_SYS_TYPES_H #include @@ -39,6 +41,7 @@ #include "xmlmemory.h" #include "parser.h" +#include "parserInternals.h" #include "HTMLparser.h" #include "HTMLtree.h" #include "tree.h" @@ -51,18 +54,252 @@ static int copy = 0; static int recovery = 0; static int noent = 0; static int noout = 0; +static int nowrap = 0; static int valid = 0; static int postvalid = 0; static int repeat = 0; static int insert = 0; static int compress = 0; static int html = 0; +static int htmlout = 0; static int shell = 0; static int push = 0; -static int blanks = 0; +static int noblanks = 0; extern int xmlDoValidityCheckingDefaultValue; +extern int xmlGetWarningsDefaultValue; +/************************************************************************ + * * + * HTML ouput * + * * + ************************************************************************/ +char buffer[50000]; + +void +xmlHTMLEncodeSend(void) { + char *result; + + result = (char *) xmlEncodeEntitiesReentrant(NULL, BAD_CAST buffer); + if (result) { + fprintf(stderr, "%s", result); + xmlFree(result); + } + buffer[0] = 0; +} + +/** + * xmlHTMLPrintFileInfo: + * @input: an xmlParserInputPtr input + * + * Displays the associated file and line informations for the current input + */ + +void +xmlHTMLPrintFileInfo(xmlParserInputPtr input) { + fprintf(stderr, "

"); + if (input != NULL) { + if (input->filename) { + sprintf(&buffer[strlen(buffer)], "%s:%d: ", input->filename, + input->line); + } else { + sprintf(&buffer[strlen(buffer)], "Entity: line %d: ", input->line); + } + } + xmlHTMLEncodeSend(); +} + +/** + * xmlHTMLPrintFileContext: + * @input: an xmlParserInputPtr input + * + * Displays current context within the input content for error tracking + */ + +void +xmlHTMLPrintFileContext(xmlParserInputPtr input) { + const xmlChar *cur, *base; + int n; + + if (input == NULL) return; + fprintf(stderr, "

\n");
+    cur = input->cur;
+    base = input->base;
+    while ((cur > base) && ((*cur == '\n') || (*cur == '\r'))) {
+	cur--;
+    }
+    n = 0;
+    while ((n++ < 80) && (cur > base) && (*cur != '\n') && (*cur != '\r'))
+        cur--;
+    if ((*cur == '\n') || (*cur == '\r')) cur++;
+    base = cur;
+    n = 0;
+    while ((*cur != 0) && (*cur != '\n') && (*cur != '\r') && (n < 79)) {
+        sprintf(&buffer[strlen(buffer)], "%c", (unsigned char) *cur++);
+	n++;
+    }
+    sprintf(&buffer[strlen(buffer)], "\n");
+    cur = input->cur;
+    while ((*cur == '\n') || (*cur == '\r'))
+	cur--;
+    n = 0;
+    while ((cur != base) && (n++ < 80)) {
+        sprintf(&buffer[strlen(buffer)], " ");
+        base++;
+    }
+    sprintf(&buffer[strlen(buffer)],"^\n");
+    xmlHTMLEncodeSend();
+    fprintf(stderr, "
"); +} + +/** + * xmlHTMLError: + * @ctx: an XML parser context + * @msg: the message to display/transmit + * @...: extra parameters for the message display + * + * Display and format an error messages, gives file, line, position and + * extra parameters. + */ +void +xmlHTMLError(void *ctx, const char *msg, ...) +{ + xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) ctx; + xmlParserInputPtr input; + xmlParserInputPtr cur = NULL; + va_list args; + + buffer[0] = 0; + input = ctxt->input; + if ((input != NULL) && (input->filename == NULL) && (ctxt->inputNr > 1)) { + cur = input; + input = ctxt->inputTab[ctxt->inputNr - 2]; + } + + xmlHTMLPrintFileInfo(input); + + fprintf(stderr, "error: "); + va_start(args, msg); + vsprintf(&buffer[strlen(buffer)], msg, args); + va_end(args); + xmlHTMLEncodeSend(); + fprintf(stderr, "

\n"); + + xmlHTMLPrintFileContext(input); + xmlHTMLEncodeSend(); +} + +/** + * xmlHTMLWarning: + * @ctx: an XML parser context + * @msg: the message to display/transmit + * @...: extra parameters for the message display + * + * Display and format a warning messages, gives file, line, position and + * extra parameters. + */ +void +xmlHTMLWarning(void *ctx, const char *msg, ...) +{ + xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) ctx; + xmlParserInputPtr input; + xmlParserInputPtr cur = NULL; + va_list args; + + buffer[0] = 0; + input = ctxt->input; + if ((input != NULL) && (input->filename == NULL) && (ctxt->inputNr > 1)) { + cur = input; + input = ctxt->inputTab[ctxt->inputNr - 2]; + } + + + xmlHTMLPrintFileInfo(input); + + fprintf(stderr, "warning: "); + va_start(args, msg); + vsprintf(&buffer[strlen(buffer)], msg, args); + va_end(args); + xmlHTMLEncodeSend(); + fprintf(stderr, "

\n"); + + xmlHTMLPrintFileContext(input); + xmlHTMLEncodeSend(); +} + +/** + * xmlHTMLValidityError: + * @ctx: an XML parser context + * @msg: the message to display/transmit + * @...: extra parameters for the message display + * + * Display and format an validity error messages, gives file, + * line, position and extra parameters. + */ +void +xmlHTMLValidityError(void *ctx, const char *msg, ...) +{ + xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) ctx; + xmlParserInputPtr input; + va_list args; + + buffer[0] = 0; + input = ctxt->input; + if ((input->filename == NULL) && (ctxt->inputNr > 1)) + input = ctxt->inputTab[ctxt->inputNr - 2]; + + xmlHTMLPrintFileInfo(input); + + fprintf(stderr, "validity error: "); + va_start(args, msg); + vsprintf(&buffer[strlen(buffer)], msg, args); + va_end(args); + xmlHTMLEncodeSend(); + fprintf(stderr, "

\n"); + + xmlHTMLPrintFileContext(input); + xmlHTMLEncodeSend(); +} + +/** + * xmlHTMLValidityWarning: + * @ctx: an XML parser context + * @msg: the message to display/transmit + * @...: extra parameters for the message display + * + * Display and format a validity warning messages, gives file, line, + * position and extra parameters. + */ +void +xmlHTMLValidityWarning(void *ctx, const char *msg, ...) +{ + xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) ctx; + xmlParserInputPtr input; + va_list args; + + buffer[0] = 0; + input = ctxt->input; + if ((input->filename == NULL) && (ctxt->inputNr > 1)) + input = ctxt->inputTab[ctxt->inputNr - 2]; + + xmlHTMLPrintFileInfo(input); + + fprintf(stderr, "validity warning: "); + va_start(args, msg); + vsprintf(&buffer[strlen(buffer)], msg, args); + va_end(args); + xmlHTMLEncodeSend(); + fprintf(stderr, "

\n"); + + xmlHTMLPrintFileContext(input); + xmlHTMLEncodeSend(); +} + +/************************************************************************ + * * + * Shell Interface * + * * + ************************************************************************/ /** * xmlShellReadline: * @prompt: the prompt value @@ -97,6 +334,11 @@ xmlShellReadline(char *prompt) { #endif } +/************************************************************************ + * * + * Test processing * + * * + ************************************************************************/ void parseAndPrintFile(char *filename) { xmlDocPtr doc = NULL, tmp; @@ -129,9 +371,40 @@ void parseAndPrintFile(char *filename) { xmlFreeParserCtxt(ctxt); } } - } else if (recovery) + } else if (recovery) { doc = xmlRecoverFile(filename); - else + } else if (htmlout) { + int ret; + xmlParserCtxtPtr ctxt; + xmlSAXHandler silent, *old; + + ctxt = xmlCreateFileParserCtxt(filename); + memcpy(&silent, ctxt->sax, sizeof(silent)); + old = ctxt->sax; + silent.error = xmlHTMLError; + if (xmlGetWarningsDefaultValue) + silent.warning = xmlHTMLWarning; + else + silent.warning = NULL; + silent.fatalError = xmlHTMLError; + ctxt->sax = &silent; + ctxt->vctxt.error = xmlHTMLValidityError; + if (xmlGetWarningsDefaultValue) + ctxt->vctxt.warning = xmlHTMLValidityWarning; + else + ctxt->vctxt.warning = NULL; + + xmlParseDocument(ctxt); + + ret = ctxt->wellFormed; + doc = ctxt->myDoc; + ctxt->sax = old; + xmlFreeParserCtxt(ctxt); + if (!ret) { + xmlFreeDoc(doc); + doc = NULL; + } + } else doc = xmlParseFile(filename); } @@ -155,8 +428,8 @@ void parseAndPrintFile(char *filename) { int nb, i; xmlNodePtr node; - if (doc->root != NULL) { - node = doc->root; + if (doc->children != NULL) { + node = doc->children; while ((node != NULL) && (node->last == NULL)) node = node->next; if (node != NULL) { nb = xmlValidGetValidElements(node->last, NULL, list, 256); @@ -224,6 +497,12 @@ int main(int argc, char **argv) { else if ((!strcmp(argv[i], "-noout")) || (!strcmp(argv[i], "--noout"))) noout++; + else if ((!strcmp(argv[i], "-htmlout")) || + (!strcmp(argv[i], "--htmlout"))) + htmlout++; + else if ((!strcmp(argv[i], "-nowrap")) || + (!strcmp(argv[i], "--nowrap"))) + nowrap++; else if ((!strcmp(argv[i], "-valid")) || (!strcmp(argv[i], "--valid"))) valid++; @@ -244,15 +523,19 @@ int main(int argc, char **argv) { compress++; xmlSetCompressMode(9); } - else if ((!strcmp(argv[i], "-blanks")) || - (!strcmp(argv[i], "--blanks"))) { - blanks++; - xmlKeepBlanksDefault(1); - } else if ((!strcmp(argv[i], "-html")) || (!strcmp(argv[i], "--html"))) { html++; } + else if ((!strcmp(argv[i], "-nowarning")) || + (!strcmp(argv[i], "--nowarning"))) { + xmlGetWarningsDefaultValue = 0; + } + else if ((!strcmp(argv[i], "-noblanks")) || + (!strcmp(argv[i], "--noblanks"))) { + noblanks++; + xmlKeepBlanksDefault(0); + } else if ((!strcmp(argv[i], "-shell")) || (!strcmp(argv[i], "--shell"))) { shell++; @@ -261,6 +544,17 @@ int main(int argc, char **argv) { } if (noent != 0) xmlSubstituteEntitiesDefault(1); if (valid != 0) xmlDoValidityCheckingDefaultValue = 1; + if ((htmlout) && (!nowrap)) { + fprintf(stderr, + "\n"); + fprintf(stderr, + "%s output\n", + argv[0]); + fprintf(stderr, + "

%s output

\n", + argv[0]); + } for (i = 1; i < argc ; i++) { if (argv[i][0] != '-') { if (repeat) { @@ -271,8 +565,11 @@ int main(int argc, char **argv) { files ++; } } + if ((htmlout) && (!nowrap)) { + fprintf(stderr, "\n"); + } if (files == 0) { - printf("Usage : %s [--debug] [--shell] [--debugent] [--copy] [--recover] [--noent] [--noout] [--valid] [--repeat] XMLfiles ...\n", + printf("Usage : %s [--debug] [--debugent] [--copy] [--recover] [--noent] [--noout] [--valid] [--repeat] XMLfiles ...\n", argv[0]); printf("\tParse the XML files and output the result of the parsing\n"); printf("\t--debug : dump a debug tree of the in-memory document\n"); @@ -281,6 +578,8 @@ int main(int argc, char **argv) { printf("\t--recover : output what was parsable on broken XML documents\n"); printf("\t--noent : substitute entity references by their value\n"); printf("\t--noout : don't output the result tree\n"); + printf("\t--htmlout : output results as HTML\n"); + printf("\t--nowarp : do not put HTML doc wrapper\n"); printf("\t--valid : validate the document in addition to std well-formed check\n"); printf("\t--postvalid : do a posteriori validation, i.e after parsing\n"); printf("\t--repeat : repeat 100 times, for timing or profiling\n"); @@ -288,8 +587,9 @@ int main(int argc, char **argv) { printf("\t--compress : turn on gzip compression of output\n"); printf("\t--html : use the HTML parser\n"); printf("\t--shell : run a navigating shell\n"); - printf("\t--blanks : keep blank text node\n"); printf("\t--push : use the push mode of the parser\n"); + printf("\t--nowarning : do not emit warnings from parser/validator\n"); + printf("\t--noblanks : drop (ignorable?) blanks spaces\n"); } xmlCleanupParser(); xmlMemoryDump(); diff --git a/tree.c b/tree.c index 1142b9b8..0b98d2de 100644 --- a/tree.c +++ b/tree.c @@ -32,20 +32,20 @@ #include "valid.h" static xmlChar xmlStringText[] = { 't', 'e', 'x', 't', 0 }; +static xmlChar xmlStringComment[] = { 'c', 'o', 'm', 'm', 'e', 'n', 't', 0 }; int oldXMLWDcompatibility = 0; -int xmlIndentTreeOutput = 1; +int xmlIndentTreeOutput = 0; xmlBufferAllocationScheme xmlBufferAllocScheme = XML_BUFFER_ALLOC_EXACT; static int xmlCompressMode = 0; static int xmlCheckDTD = 1; int xmlSaveNoEmptyTags = 0; -extern int xmlKeepBlanksDefaultValue; #define IS_BLANK(c) \ (((c) == '\n') || ((c) == '\r') || ((c) == '\t') || ((c) == ' ')) #define UPDATE_LAST_CHILD(n) if ((n) != NULL) { \ - xmlNodePtr ulccur = (n)->childs; \ + xmlNodePtr ulccur = (n)->children; \ if (ulccur == NULL) { \ (n)->last = NULL; \ } else { \ @@ -102,7 +102,7 @@ xmlUpgradeOldNs(xmlDocPtr doc) { xmlNsPtr cur; if ((doc == NULL) || (doc->oldNs == NULL)) return; - if (doc->root == NULL) { + if (doc->children == NULL) { #ifdef DEBUG_TREE fprintf(stderr, "xmlUpgradeOldNs: failed no root !\n"); #endif @@ -115,8 +115,8 @@ xmlUpgradeOldNs(xmlDocPtr doc) { cur = cur->next; } cur->type = XML_LOCAL_NAMESPACE; - cur->next = doc->root->nsDef; - doc->root->nsDef = doc->oldNs; + cur->next = doc->children->nsDef; + doc->children->nsDef = doc->oldNs; doc->oldNs = NULL; } @@ -143,29 +143,25 @@ xmlNewNs(xmlNodePtr node, const xmlChar *href, const xmlChar *prefix) { } /* - * Allocate a new DTD and fill the fields. + * Allocate a new Namespace and fill the fields. */ cur = (xmlNsPtr) xmlMalloc(sizeof(xmlNs)); if (cur == NULL) { fprintf(stderr, "xmlNewNs : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlNs)); cur->type = XML_LOCAL_NAMESPACE; + if (href != NULL) cur->href = xmlStrdup(href); - else - cur->href = NULL; if (prefix != NULL) cur->prefix = xmlStrdup(prefix); - else - cur->prefix = NULL; /* * Add it at the end to preserve parsing order ... * and checks for existing use of the prefix */ - cur->next = NULL; if (node != NULL) { if (node->nsDef == NULL) { node->nsDef = cur; @@ -221,21 +217,17 @@ xmlNewGlobalNs(xmlDocPtr doc, const xmlChar *href, const xmlChar *prefix) { fprintf(stderr, "xmlNewGlobalNs : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlNs)); cur->type = XML_GLOBAL_NAMESPACE; + if (href != NULL) cur->href = xmlStrdup(href); - else - cur->href = NULL; if (prefix != NULL) cur->prefix = xmlStrdup(prefix); - else - cur->prefix = NULL; /* * Add it at the end to preserve parsing order ... */ - cur->next = NULL; if (doc != NULL) { if (doc->oldNs == NULL) { doc->oldNs = cur; @@ -262,7 +254,7 @@ xmlSetNs(xmlNodePtr node, xmlNsPtr ns) { if (node == NULL) { #ifdef DEBUG_TREE fprintf(stderr, "xmlSetNs: node == NULL\n"); -#else +#endif return; } node->ns = ns; @@ -317,7 +309,9 @@ xmlFreeNsList(xmlNsPtr cur) { * @ExternalID: the external ID * @SystemID: the system ID * - * Creation of a new DTD. + * Creation of a new DTD for the external subset. To create an + * internal subset, use xmlCreateIntSubset(). + * * Returns a pointer to the new DTD structure */ xmlDtdPtr @@ -342,29 +336,45 @@ xmlNewDtd(xmlDocPtr doc, const xmlChar *name, fprintf(stderr, "xmlNewDtd : malloc failed\n"); return(NULL); } + memset(cur, 0 , sizeof(xmlDtd)); + cur->type = XML_DTD_NODE; if (name != NULL) cur->name = xmlStrdup(name); - else - cur->name = NULL; if (ExternalID != NULL) cur->ExternalID = xmlStrdup(ExternalID); - else - cur->ExternalID = NULL; if (SystemID != NULL) cur->SystemID = xmlStrdup(SystemID); - else - cur->SystemID = NULL; - cur->notations = NULL; - cur->elements = NULL; - cur->attributes = NULL; - cur->entities = NULL; if (doc != NULL) doc->extSubset = cur; + cur->doc = doc; return(cur); } +/** + * xmlGetIntSubset: + * @doc: the document pointer + * + * Get the internal subset of a document + * Returns a pointer to the DTD structure or NULL if not found + */ + +xmlDtdPtr +xmlGetIntSubset(xmlDocPtr doc) { + xmlNodePtr cur; + + if (doc == NULL) + return(NULL); + cur = doc->children; + while (cur != NULL) { + if (cur->type == XML_DTD_NODE) + return((xmlDtdPtr) cur); + cur = cur->next; + } + return((xmlDtdPtr) doc->intSubset); +} + /** * xmlCreateIntSubset: * @doc: the document pointer @@ -380,7 +390,7 @@ xmlCreateIntSubset(xmlDocPtr doc, const xmlChar *name, const xmlChar *ExternalID, const xmlChar *SystemID) { xmlDtdPtr cur; - if ((doc != NULL) && (doc->intSubset != NULL)) { + if ((doc != NULL) && (xmlGetIntSubset(doc) != NULL)) { #ifdef DEBUG_TREE fprintf(stderr, "xmlCreateIntSubset(): document %s already have an internal subset\n", @@ -397,26 +407,31 @@ xmlCreateIntSubset(xmlDocPtr doc, const xmlChar *name, fprintf(stderr, "xmlNewDtd : malloc failed\n"); return(NULL); } + memset(cur, 0, sizeof(xmlDtd)); + cur->type = XML_DTD_NODE; if (name != NULL) cur->name = xmlStrdup(name); - else - cur->name = NULL; if (ExternalID != NULL) cur->ExternalID = xmlStrdup(ExternalID); - else - cur->ExternalID = NULL; if (SystemID != NULL) cur->SystemID = xmlStrdup(SystemID); - else - cur->SystemID = NULL; - cur->notations = NULL; - cur->elements = NULL; - cur->attributes = NULL; - cur->entities = NULL; - if (doc != NULL) + if (doc != NULL) { doc->intSubset = cur; + cur->parent = doc; + cur->doc = doc; + if (doc->children == NULL) { + doc->children = (xmlNodePtr) cur; + doc->last = (xmlNodePtr) cur; + } else { + xmlNodePtr prev; + prev = doc->last; + prev->next = (xmlNodePtr) cur; + cur->prev = prev; + doc->last = (xmlNodePtr) cur; + } + } return(cur); } @@ -434,17 +449,36 @@ xmlFreeDtd(xmlDtdPtr cur) { #endif return; } + if (cur->children != NULL) { + xmlNodePtr next, c = cur->children; + + /* + * Cleanup all the DTD comments they are not in the Dtd + * indexes. + */ + while (c != NULL) { + next = c->next; + if (c->type == XML_COMMENT_NODE) { + xmlUnlinkNode(c); + xmlFreeNode(c); + } + c = next; + } + } if (cur->name != NULL) xmlFree((char *) cur->name); if (cur->SystemID != NULL) xmlFree((char *) cur->SystemID); if (cur->ExternalID != NULL) xmlFree((char *) cur->ExternalID); + /* TODO !!! */ if (cur->notations != NULL) xmlFreeNotationTable((xmlNotationTablePtr) cur->notations); + if (cur->elements != NULL) xmlFreeElementTable((xmlElementTablePtr) cur->elements); if (cur->attributes != NULL) xmlFreeAttributeTable((xmlAttributeTablePtr) cur->attributes); if (cur->entities != NULL) xmlFreeEntitiesTable((xmlEntitiesTablePtr) cur->entities); + memset(cur, -1, sizeof(xmlDtd)); xmlFree(cur); } @@ -474,23 +508,13 @@ xmlNewDoc(const xmlChar *version) { fprintf(stderr, "xmlNewDoc : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlDoc)); cur->type = XML_DOCUMENT_NODE; + cur->version = xmlStrdup(version); - cur->name = NULL; - cur->root = NULL; - cur->intSubset = NULL; - cur->extSubset = NULL; - cur->oldNs = NULL; - cur->encoding = NULL; cur->standalone = -1; cur->compression = -1; /* not initialized */ - cur->ids = NULL; - cur->refs = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif + cur->doc = cur; return(cur); } @@ -512,12 +536,13 @@ xmlFreeDoc(xmlDocPtr cur) { if (cur->version != NULL) xmlFree((char *) cur->version); if (cur->name != NULL) xmlFree((char *) cur->name); if (cur->encoding != NULL) xmlFree((char *) cur->encoding); - if (cur->root != NULL) xmlFreeNodeList(cur->root); + if (cur->children != NULL) xmlFreeNodeList(cur->children); if (cur->intSubset != NULL) xmlFreeDtd(cur->intSubset); if (cur->extSubset != NULL) xmlFreeDtd(cur->extSubset); if (cur->oldNs != NULL) xmlFreeNsList(cur->oldNs); if (cur->ids != NULL) xmlFreeIDTable((xmlIDTablePtr) cur->ids); if (cur->refs != NULL) xmlFreeRefTable((xmlRefTablePtr) cur->refs); + if (cur->URL != NULL) xmlFree((char *) cur->URL); memset(cur, -1, sizeof(xmlDoc)); xmlFree(cur); } @@ -584,7 +609,7 @@ xmlStringLenGetNodeList(xmlDocPtr doc, const xmlChar *value, int len) { val = xmlStrndup(q, cur - q); ent = xmlGetDocEntity(doc, val); if ((ent != NULL) && - (ent->type == XML_INTERNAL_PREDEFINED_ENTITY)) { + (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) { if (last == NULL) { node = xmlNewDocText(doc, ent->content); last = ret = node; @@ -697,7 +722,7 @@ xmlStringGetNodeList(xmlDocPtr doc, const xmlChar *value) { val = xmlStrndup(q, cur - q); ent = xmlGetDocEntity(doc, val); if ((ent != NULL) && - (ent->type == XML_INTERNAL_PREDEFINED_ENTITY)) { + (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) { if (last == NULL) { node = xmlNewDocText(doc, ent->content); last = ret = node; @@ -849,28 +874,30 @@ xmlNewProp(xmlNodePtr node, const xmlChar *name, const xmlChar *value) { fprintf(stderr, "xmlNewProp : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlAttr)); cur->type = XML_ATTRIBUTE_NODE; - cur->node = node; - cur->ns = NULL; + + cur->parent = node; cur->name = xmlStrdup(name); if (value != NULL) { xmlChar *buffer; + xmlNodePtr tmp; + buffer = xmlEncodeEntitiesReentrant(node->doc, value); - cur->val = xmlStringGetNodeList(node->doc, buffer); + cur->children = xmlStringGetNodeList(node->doc, buffer); + tmp = cur->children; + while (tmp != NULL) { + tmp->parent = (xmlNodePtr) cur; + if (tmp->next == NULL) + cur->last = tmp; + tmp = tmp->next; + } xmlFree(buffer); } - else - cur->val = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif /* * Add it at the end to preserve parsing order ... */ - cur->next = NULL; if (node != NULL) { if (node->properties == NULL) { node->properties = cur; @@ -879,12 +906,9 @@ xmlNewProp(xmlNodePtr node, const xmlChar *name, const xmlChar *value) { while (prev->next != NULL) prev = prev->next; prev->next = cur; + cur->prev = prev; } } -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif return(cur); } @@ -918,24 +942,33 @@ xmlNewNsProp(xmlNodePtr node, xmlNsPtr ns, const xmlChar *name, fprintf(stderr, "xmlNewProp : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlAttr)); cur->type = XML_ATTRIBUTE_NODE; - cur->node = node; + + cur->parent = node; + if (node != NULL) + cur->doc = node->doc; cur->ns = ns; cur->name = xmlStrdup(name); - if (value != NULL) - cur->val = xmlStringGetNodeList(node->doc, value); - else - cur->val = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif + if (value != NULL) { + xmlChar *buffer; + xmlNodePtr tmp; + + buffer = xmlEncodeEntitiesReentrant(node->doc, value); + cur->children = xmlStringGetNodeList(node->doc, buffer); + tmp = cur->children; + while (tmp != NULL) { + tmp->parent = (xmlNodePtr) cur; + if (tmp->next == NULL) + cur->last = tmp; + tmp = tmp->next; + } + xmlFree(buffer); + } /* * Add it at the end to preserve parsing order ... */ - cur->next = NULL; if (node != NULL) { if (node->properties == NULL) { node->properties = cur; @@ -944,6 +977,7 @@ xmlNewNsProp(xmlNodePtr node, xmlNsPtr ns, const xmlChar *name, while (prev->next != NULL) prev = prev->next; prev->next = cur; + cur->prev = prev; } } return(cur); @@ -977,20 +1011,13 @@ xmlNewDocProp(xmlDocPtr doc, const xmlChar *name, const xmlChar *value) { fprintf(stderr, "xmlNewProp : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlAttr)); cur->type = XML_ATTRIBUTE_NODE; - cur->node = NULL; - cur->name = xmlStrdup(name); - if (value != NULL) - cur->val = xmlStringGetNodeList(doc, value); - else - cur->val = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif - cur->next = NULL; + cur->name = xmlStrdup(name); + cur->doc = doc; + if (value != NULL) + cur->children = xmlStringGetNodeList(doc, value); return(cur); } @@ -998,7 +1025,7 @@ xmlNewDocProp(xmlDocPtr doc, const xmlChar *name, const xmlChar *value) { * xmlFreePropList: * @cur: the first property in the list * - * Free a property and all its siblings, all the childs are freed too. + * Free a property and all its siblings, all the children are freed too. */ void xmlFreePropList(xmlAttrPtr cur) { @@ -1031,11 +1058,11 @@ xmlFreeProp(xmlAttrPtr cur) { return; } /* Check for ID removal -> leading to invalid references ! */ - if ((cur->node != NULL) && - (xmlIsID(cur->node->doc, cur->node, cur))) - xmlRemoveID(cur->node->doc, cur); + if ((cur->parent != NULL) && + (xmlIsID(cur->parent->doc, cur->parent, cur))) + xmlRemoveID(cur->parent->doc, cur); if (cur->name != NULL) xmlFree((char *) cur->name); - if (cur->val != NULL) xmlFreeNodeList(cur->val); + if (cur->children != NULL) xmlFreeNodeList(cur->children); memset(cur, -1, sizeof(xmlAttr)); xmlFree(cur); } @@ -1058,20 +1085,23 @@ xmlRemoveProp(xmlAttrPtr cur) { #endif return(-1); } - if (cur->node == NULL) { - fprintf(stderr, "xmlRemoveProp : cur->node == NULL\n"); + if (cur->parent == NULL) { +#ifdef DEBUG_TREE + fprintf(stderr, "xmlRemoveProp : cur->parent == NULL\n"); #endif return(-1); } - tmp = cur->node->properties; + tmp = cur->parent->properties; if (tmp == cur) { - cur->node->properties = cur->next; + cur->parent->properties = cur->next; xmlFreeProp(cur); return(0); } while (tmp != NULL) { if (tmp->next == cur) { tmp->next = cur->next; + if (tmp->next != NULL) + tmp->next->prev = tmp; xmlFreeProp(cur); return(0); } @@ -1110,18 +1140,10 @@ xmlNewPI(const xmlChar *name, const xmlChar *content) { fprintf(stderr, "xmlNewPI : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlNode)); cur->type = XML_PI_NODE; - cur->doc = NULL; - cur->parent = NULL; - cur->next = NULL; - cur->prev = NULL; - cur->childs = NULL; - cur->last = NULL; - cur->properties = NULL; + cur->name = xmlStrdup(name); - cur->ns = NULL; - cur->nsDef = NULL; if (content != NULL) { #ifndef XML_USE_BUFFER_CONTENT cur->content = xmlStrdup(content); @@ -1131,12 +1153,7 @@ xmlNewPI(const xmlChar *name, const xmlChar *content) { xmlGetBufferAllocationScheme()); xmlBufferAdd(cur->content, content, -1); #endif - } else - cur->content = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif + } return(cur); } @@ -1169,23 +1186,11 @@ xmlNewNode(xmlNsPtr ns, const xmlChar *name) { fprintf(stderr, "xmlNewNode : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlNode)); cur->type = XML_ELEMENT_NODE; - cur->doc = NULL; - cur->parent = NULL; - cur->next = NULL; - cur->prev = NULL; - cur->childs = NULL; - cur->last = NULL; - cur->properties = NULL; + cur->name = xmlStrdup(name); cur->ns = ns; - cur->nsDef = NULL; - cur->content = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif return(cur); } @@ -1214,7 +1219,7 @@ xmlNewDocNode(xmlDocPtr doc, xmlNsPtr ns, if (cur != NULL) { cur->doc = doc; if (content != NULL) { - cur->childs = xmlStringGetNodeList(doc, content); + cur->children = xmlStringGetNodeList(doc, content); UPDATE_LAST_CHILD(cur) } } @@ -1243,7 +1248,7 @@ xmlNewDocRawNode(xmlDocPtr doc, xmlNsPtr ns, if (cur != NULL) { cur->doc = doc; if (content != NULL) { - cur->childs = xmlNewDocText(doc, content); + cur->children = xmlNewDocText(doc, content); UPDATE_LAST_CHILD(cur) } } @@ -1269,23 +1274,10 @@ xmlNewDocFragment(xmlDocPtr doc) { fprintf(stderr, "xmlNewDocFragment : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlNode)); cur->type = XML_DOCUMENT_FRAG_NODE; + cur->doc = doc; - cur->parent = NULL; - cur->next = NULL; - cur->prev = NULL; - cur->childs = NULL; - cur->last = NULL; - cur->properties = NULL; - cur->name = NULL; - cur->ns = NULL; - cur->nsDef = NULL; - cur->content = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif return(cur); } @@ -1308,19 +1300,10 @@ xmlNewText(const xmlChar *content) { fprintf(stderr, "xmlNewText : malloc failed\n"); return(NULL); } + memset(cur, 0, sizeof(xmlNode)); + cur->type = XML_TEXT_NODE; - cur->type = XML_TEXT_NODE; - cur->doc = NULL; - cur->parent = NULL; - cur->next = NULL; - cur->prev = NULL; - cur->childs = NULL; - cur->last = NULL; - cur->properties = NULL; - cur->type = XML_TEXT_NODE; cur->name = xmlStrdup(xmlStringText); - cur->ns = NULL; - cur->nsDef = NULL; if (content != NULL) { #ifndef XML_USE_BUFFER_CONTENT cur->content = xmlStrdup(content); @@ -1330,12 +1313,7 @@ xmlNewText(const xmlChar *content) { xmlGetBufferAllocationScheme()); xmlBufferAdd(cur->content, content, -1); #endif - } else - cur->content = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif + } return(cur); } @@ -1346,7 +1324,7 @@ xmlNewText(const xmlChar *content) { * @name: the name of the child * @content: the text content of the child if any. * - * Creation of a new child element, added at the end of @parent childs list. + * Creation of a new child element, added at the end of @parent children list. * @ns and @content parameters are optionnal (NULL). If content is non NULL, * a child TEXT node will be created containing the string content. * @@ -1381,13 +1359,13 @@ xmlNewTextChild(xmlNodePtr parent, xmlNsPtr ns, if (cur == NULL) return(NULL); /* - * add the new element at the end of the childs list. + * add the new element at the end of the children list. */ cur->type = XML_ELEMENT_NODE; cur->parent = parent; cur->doc = parent->doc; - if (parent->childs == NULL) { - parent->childs = cur; + if (parent->children == NULL) { + parent->children = cur; parent->last = cur; } else { prev = parent->last; @@ -1399,6 +1377,43 @@ xmlNewTextChild(xmlNodePtr parent, xmlNsPtr ns, return(cur); } +/** + * xmlNewCharRef: + * @doc: the document + * @name: the char ref string, starting with # or "&# ... ;" + * + * Creation of a new character reference node. + * Returns a pointer to the new node object. + */ +xmlNodePtr +xmlNewCharRef(xmlDocPtr doc, const xmlChar *name) { + xmlNodePtr cur; + + /* + * Allocate a new node and fill the fields. + */ + cur = (xmlNodePtr) xmlMalloc(sizeof(xmlNode)); + if (cur == NULL) { + fprintf(stderr, "xmlNewText : malloc failed\n"); + return(NULL); + } + memset(cur, 0, sizeof(xmlNode)); + cur->type = XML_ENTITY_REF_NODE; + + cur->doc = doc; + if (name[0] == '&') { + int len; + name++; + len = xmlStrlen(name); + if (name[len - 1] == ';') + cur->name = xmlStrndup(name, len - 1); + else + cur->name = xmlStrndup(name, len); + } else + cur->name = xmlStrdup(name); + return(cur); +} + /** * xmlNewReference: * @doc: the document @@ -1420,15 +1435,10 @@ xmlNewReference(xmlDocPtr doc, const xmlChar *name) { fprintf(stderr, "xmlNewText : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlNode)); cur->type = XML_ENTITY_REF_NODE; + cur->doc = doc; - cur->parent = NULL; - cur->next = NULL; - cur->prev = NULL; - cur->childs = NULL; - cur->last = NULL; - cur->properties = NULL; if (name[0] == '&') { int len; name++; @@ -1439,8 +1449,6 @@ xmlNewReference(xmlDocPtr doc, const xmlChar *name) { cur->name = xmlStrndup(name, len); } else cur->name = xmlStrdup(name); - cur->ns = NULL; - cur->nsDef = NULL; ent = xmlGetDocEntity(doc, cur->name); if (ent != NULL) { @@ -1458,12 +1466,8 @@ xmlNewReference(xmlDocPtr doc, const xmlChar *name) { if (ent->content != NULL) xmlBufferAdd(cur->content, ent->content, -1); #endif - } else - cur->content = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif + cur->children = (xmlNodePtr) ent; + } return(cur); } @@ -1504,19 +1508,10 @@ xmlNewTextLen(const xmlChar *content, int len) { fprintf(stderr, "xmlNewText : malloc failed\n"); return(NULL); } + memset(cur, 0, sizeof(xmlNode)); + cur->type = XML_TEXT_NODE; - cur->type = XML_TEXT_NODE; - cur->doc = NULL; - cur->parent = NULL; - cur->prev = NULL; - cur->next = NULL; - cur->childs = NULL; - cur->last = NULL; - cur->properties = NULL; - cur->type = XML_TEXT_NODE; cur->name = xmlStrdup(xmlStringText); - cur->ns = NULL; - cur->nsDef = NULL; if (content != NULL) { #ifndef XML_USE_BUFFER_CONTENT cur->content = xmlStrndup(content, len); @@ -1526,12 +1521,7 @@ xmlNewTextLen(const xmlChar *content, int len) { xmlGetBufferAllocationScheme()); xmlBufferAdd(cur->content, content, len); #endif - } else - cur->content = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif + } return(cur); } @@ -1573,19 +1563,10 @@ xmlNewComment(const xmlChar *content) { fprintf(stderr, "xmlNewComment : malloc failed\n"); return(NULL); } + memset(cur, 0, sizeof(xmlNode)); + cur->type = XML_COMMENT_NODE; - cur->type = XML_COMMENT_NODE; - cur->doc = NULL; - cur->parent = NULL; - cur->prev = NULL; - cur->next = NULL; - cur->childs = NULL; - cur->last = NULL; - cur->properties = NULL; - cur->type = XML_COMMENT_NODE; - cur->name = xmlStrdup(xmlStringText); - cur->ns = NULL; - cur->nsDef = NULL; + cur->name = xmlStrdup(xmlStringComment); if (content != NULL) { #ifndef XML_USE_BUFFER_CONTENT cur->content = xmlStrdup(content); @@ -1595,12 +1576,7 @@ xmlNewComment(const xmlChar *content) { xmlGetBufferAllocationScheme()); xmlBufferAdd(cur->content, content, -1); #endif - } else - cur->content = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif + } return(cur); } @@ -1625,18 +1601,9 @@ xmlNewCDataBlock(xmlDocPtr doc, const xmlChar *content, int len) { fprintf(stderr, "xmlNewCDataBlock : malloc failed\n"); return(NULL); } - + memset(cur, 0, sizeof(xmlNode)); cur->type = XML_CDATA_SECTION_NODE; - cur->doc = NULL; - cur->parent = NULL; - cur->prev = NULL; - cur->next = NULL; - cur->childs = NULL; - cur->last = NULL; - cur->properties = NULL; - cur->name = xmlStrdup(xmlStringText); - cur->ns = NULL; - cur->nsDef = NULL; + if (content != NULL) { #ifndef XML_USE_BUFFER_CONTENT cur->content = xmlStrndup(content, len); @@ -1646,12 +1613,7 @@ xmlNewCDataBlock(xmlDocPtr doc, const xmlChar *content, int len) { xmlGetBufferAllocationScheme()); xmlBufferAdd(cur->content, content, len); #endif - } else - cur->content = NULL; -#ifndef XML_WITHOUT_CORBA - cur->_private = NULL; - cur->vepv = NULL; -#endif + } return(cur); } @@ -1680,7 +1642,7 @@ xmlNewDocComment(xmlDocPtr doc, const xmlChar *content) { * @name: the name of the child * @content: the XML content of the child if any. * - * Creation of a new child element, added at the end of @parent childs list. + * Creation of a new child element, added at the end of @parent children list. * @ns and @content parameters are optionnal (NULL). If content is non NULL, * a child list containing the TEXTs and ENTITY_REFs node will be created. * NOTE: @content is supposed to be a piece of XML CDATA, so it allow entities @@ -1719,13 +1681,13 @@ xmlNewChild(xmlNodePtr parent, xmlNsPtr ns, if (cur == NULL) return(NULL); /* - * add the new element at the end of the childs list. + * add the new element at the end of the children list. */ cur->type = XML_ELEMENT_NODE; cur->parent = parent; cur->doc = parent->doc; - if (parent->childs == NULL) { - parent->childs = cur; + if (parent->children == NULL) { + parent->children = cur; parent->last = cur; } else { prev = parent->last; @@ -1771,8 +1733,8 @@ xmlAddNextSibling(xmlNodePtr cur, xmlNodePtr elem) { cur->prev = elem; if (elem->prev != NULL) elem->prev->next = elem; - if ((elem->parent != NULL) && (elem->parent->childs == cur)) - elem->parent->childs = elem; + if ((elem->parent != NULL) && (elem->parent->children == cur)) + elem->parent->children = elem; return(elem); } @@ -1849,7 +1811,7 @@ xmlAddSibling(xmlNodePtr cur, xmlNodePtr elem) { * the last sibling. */ if ((cur->parent != NULL) && - (cur->parent->childs != NULL) && + (cur->parent->children != NULL) && (cur->parent->last != NULL) && (cur->parent->last->next == NULL)) { cur = cur->parent->last; @@ -1906,7 +1868,7 @@ xmlAddChild(xmlNodePtr parent, xmlNodePtr cur) { } /* - * add the new element at the end of the childs list. + * add the new element at the end of the children list. */ cur->parent = parent; cur->doc = parent->doc; /* the parent may not be linked to a doc ! */ @@ -1915,7 +1877,8 @@ xmlAddChild(xmlNodePtr parent, xmlNodePtr cur) { * Handle the case where parent->content != NULL, in that case it will * create a intermediate TEXT node. */ - if (parent->content != NULL) { + if (((parent->type == XML_ELEMENT_NODE) || (parent->type == XML_TEXT_NODE)) && + (parent->content != NULL)) { xmlNodePtr text; #ifndef XML_USE_BUFFER_CONTENT @@ -1924,10 +1887,10 @@ xmlAddChild(xmlNodePtr parent, xmlNodePtr cur) { text = xmlNewDocText(parent->doc, xmlBufferContent(parent->content)); #endif if (text != NULL) { - text->next = parent->childs; + text->next = parent->children; if (text->next != NULL) text->next->prev = text; - parent->childs = text; + parent->children = text; UPDATE_LAST_CHILD(parent) #ifndef XML_USE_BUFFER_CONTENT xmlFree(parent->content); @@ -1937,8 +1900,8 @@ xmlAddChild(xmlNodePtr parent, xmlNodePtr cur) { parent->content = NULL; } } - if (parent->childs == NULL) { - parent->childs = cur; + if (parent->children == NULL) { + parent->children = cur; parent->last = cur; } else { prev = parent->last; @@ -1973,7 +1936,7 @@ xmlGetLastChild(xmlNodePtr parent) { * @cur: the first node in the list * * Free a node and all its siblings, this is a recursive behaviour, all - * the childs are freed too. + * the children are freed too. */ void xmlFreeNodeList(xmlNodePtr cur) { @@ -1995,7 +1958,8 @@ xmlFreeNodeList(xmlNodePtr cur) { * xmlFreeNode: * @cur: the node * - * Free a node, this is a recursive behaviour, all the childs are freed too. + * Free a node, this is a recursive behaviour, all the children are freed too. + * This doesn't unlink the child from the list, use xmlUnlinkNode() first. */ void xmlFreeNode(xmlNodePtr cur) { @@ -2005,11 +1969,15 @@ xmlFreeNode(xmlNodePtr cur) { #endif return; } + if (cur->type == XML_DTD_NODE) + return; cur->doc = NULL; cur->parent = NULL; cur->next = NULL; cur->prev = NULL; - if (cur->childs != NULL) xmlFreeNodeList(cur->childs); + if ((cur->children != NULL) && + (cur->type != XML_ENTITY_REF_NODE)) + xmlFreeNodeList(cur->children); if (cur->properties != NULL) xmlFreePropList(cur->properties); if (cur->type != XML_ENTITY_REF_NODE) #ifndef XML_USE_BUFFER_CONTENT @@ -2037,8 +2005,8 @@ xmlUnlinkNode(xmlNodePtr cur) { #endif return; } - if ((cur->parent != NULL) && (cur->parent->childs == cur)) - cur->parent->childs = cur->next; + if ((cur->parent != NULL) && (cur->parent->children == cur)) + cur->parent->children = cur->next; if ((cur->parent != NULL) && (cur->parent->last == cur)) cur->parent->last = cur->prev; if (cur->next != NULL) @@ -2082,8 +2050,8 @@ xmlReplaceNode(xmlNodePtr old, xmlNodePtr cur) { if (cur->prev != NULL) cur->prev->next = cur; if (cur->parent != NULL) { - if (cur->parent->childs == old) - cur->parent->childs = cur; + if (cur->parent->children == old) + cur->parent->children = cur; if (cur->parent->last == old) cur->parent->last = cur; } @@ -2167,11 +2135,14 @@ xmlCopyProp(xmlNodePtr target, xmlAttrPtr cur) { xmlAttrPtr ret; if (cur == NULL) return(NULL); - if (cur->val != NULL) - ret = xmlNewDocProp(cur->val->doc, cur->name, NULL); + if (cur->parent != NULL) + ret = xmlNewDocProp(cur->parent->doc, cur->name, NULL); + else if (cur->children != NULL) + ret = xmlNewDocProp(cur->children->doc, cur->name, NULL); else ret = xmlNewDocProp(NULL, cur->name, NULL); if (ret == NULL) return(NULL); + ret->parent = target; if ((cur->ns != NULL) && (target != NULL)) { xmlNsPtr ns; @@ -2181,8 +2152,8 @@ xmlCopyProp(xmlNodePtr target, xmlAttrPtr cur) { } else ret->ns = NULL; - if (cur->val != NULL) - ret->val = xmlCopyNodeList(cur->val); + if (cur->children != NULL) + ret->children = xmlCopyNodeList(cur->children); return(ret); } @@ -2206,6 +2177,7 @@ xmlCopyPropList(xmlNodePtr target, xmlAttrPtr cur) { ret = p = q; } else { p->next = q; + q->prev = p; p = q; } cur = cur->next; @@ -2245,21 +2217,13 @@ xmlStaticCopyNode(xmlNodePtr node, xmlDocPtr doc, xmlNodePtr parent, fprintf(stderr, "xmlStaticCopyNode : malloc failed\n"); return(NULL); } - + memset(ret, 0, sizeof(xmlNode)); ret->type = node->type; + ret->doc = doc; ret->parent = parent; - ret->next = NULL; - ret->prev = NULL; - ret->childs = NULL; - ret->last = NULL; - ret->properties = NULL; if (node->name != NULL) ret->name = xmlStrdup(node->name); - else - ret->name = NULL; - ret->ns = NULL; - ret->nsDef = NULL; if ((node->content != NULL) && (node->type != XML_ENTITY_REF_NODE)) { #ifndef XML_USE_BUFFER_CONTENT ret->content = xmlStrdup(node->content); @@ -2271,12 +2235,7 @@ xmlStaticCopyNode(xmlNodePtr node, xmlDocPtr doc, xmlNodePtr parent, xmlBufferContent(node->content), xmlBufferLength(node->content)); #endif - } else - ret->content = NULL; -#ifndef XML_WITHOUT_CORBA - ret->_private = NULL; - ret->vepv = NULL; -#endif + } if (parent != NULL) xmlAddChild(parent, ret); @@ -2310,8 +2269,8 @@ xmlStaticCopyNode(xmlNodePtr node, xmlDocPtr doc, xmlNodePtr parent, } if (node->properties != NULL) ret->properties = xmlCopyPropList(ret, node->properties); - if (node->childs != NULL) - ret->childs = xmlStaticCopyNodeList(node->childs, doc, ret); + if (node->children != NULL) + ret->children = xmlStaticCopyNodeList(node->children, doc, ret); UPDATE_LAST_CHILD(ret) return(ret); } @@ -2390,8 +2349,8 @@ xmlCopyElement(xmlElementPtr elem) { if (elem->nsDef != NULL) ret->nsDef = xmlCopyNamespaceList(elem->nsDef); - if (elem->childs != NULL) - ret->childs = xmlCopyElementList(elem->childs); + if (elem->children != NULL) + ret->children = xmlCopyElementList(elem->children); return(ret); } */ @@ -2455,8 +2414,8 @@ xmlCopyDoc(xmlDocPtr doc, int recursive) { ret->intSubset = xmlCopyDtd(doc->intSubset); if (doc->oldNs != NULL) ret->oldNs = xmlCopyNamespaceList(doc->oldNs); - if (doc->root != NULL) - ret->root = xmlStaticCopyNodeList(doc->root, ret, NULL); + if (doc->children != NULL) + ret->children = xmlStaticCopyNodeList(doc->children, ret, NULL); return(ret); } @@ -2470,7 +2429,7 @@ xmlCopyDoc(xmlDocPtr doc, int recursive) { * xmlDocGetRootElement: * @doc: the document * - * Get the root element of the document (doc->root is a list + * Get the root element of the document (doc->children is a list * containing possibly comments, PIs, etc ...). * * Returns the xmlNodePtr for the root or NULL @@ -2480,7 +2439,7 @@ xmlDocGetRootElement(xmlDocPtr doc) { xmlNodePtr ret; if (doc == NULL) return(NULL); - ret = doc->root; + ret = doc->children; while (ret != NULL) { if (ret->type == XML_ELEMENT_NODE) return(ret); @@ -2494,7 +2453,7 @@ xmlDocGetRootElement(xmlDocPtr doc) { * @doc: the document * @root: the new document root element * - * Set the root element of the document (doc->root is a list + * Set the root element of the document (doc->children is a list * containing possibly comments, PIs, etc ...). * * Returns the old root element if any was found @@ -2504,17 +2463,17 @@ xmlDocSetRootElement(xmlDocPtr doc, xmlNodePtr root) { xmlNodePtr old = NULL; if (doc == NULL) return(NULL); - old = doc->root; + old = doc->children; while (old != NULL) { if (old->type == XML_ELEMENT_NODE) break; old = old->next; } if (old == NULL) { - if (doc->root == NULL) { - doc->root = root; + if (doc->children == NULL) { + doc->children = root; } else { - xmlAddSibling(doc->root, root); + xmlAddSibling(doc->children, root); } } else { xmlReplaceNode(old, root); @@ -2542,6 +2501,10 @@ xmlNodeSetLang(xmlNodePtr cur, const xmlChar *lang) { case XML_DOCUMENT_FRAG_NODE: case XML_NOTATION_NODE: case XML_HTML_DOCUMENT_NODE: + case XML_DTD_NODE: + case XML_ELEMENT_DECL: + case XML_ATTRIBUTE_DECL: + case XML_ENTITY_DECL: return; case XML_ELEMENT_NODE: case XML_ATTRIBUTE_NODE: @@ -2576,6 +2539,37 @@ xmlNodeGetLang(xmlNodePtr cur) { return(NULL); } +/** + * xmlNodeGetSpacePreserve: + * @cur: the node being checked + * + * Searches the language of a node, i.e. the values of the xml:space + * attribute or the one carried by the nearest ancestor. + * + * Returns -1 if xml:space is not inheried, 0 if "default", 1 if "preserve" + */ +int +xmlNodeGetSpacePreserve(xmlNodePtr cur) { + xmlChar *space; + + while (cur != NULL) { + space = xmlGetProp(cur, BAD_CAST "xml:space"); + if (space != NULL) { + if (!xmlStrcmp(space, BAD_CAST "preserve")) { + xmlFree(space); + return(1); + } + if (!xmlStrcmp(space, BAD_CAST "default")) { + xmlFree(space); + return(0); + } + xmlFree(space); + } + cur = cur->parent; + } + return(-1); +} + /** * xmlNodeSetName: * @cur: the node being changed @@ -2592,7 +2586,6 @@ xmlNodeSetName(xmlNodePtr cur, const xmlChar *name) { case XML_TEXT_NODE: case XML_CDATA_SECTION_NODE: case XML_COMMENT_NODE: - case XML_DOCUMENT_NODE: case XML_DOCUMENT_TYPE_NODE: case XML_DOCUMENT_FRAG_NODE: case XML_NOTATION_NODE: @@ -2603,6 +2596,11 @@ xmlNodeSetName(xmlNodePtr cur, const xmlChar *name) { case XML_PI_NODE: case XML_ENTITY_REF_NODE: case XML_ENTITY_NODE: + case XML_DTD_NODE: + case XML_DOCUMENT_NODE: + case XML_ELEMENT_DECL: + case XML_ATTRIBUTE_DECL: + case XML_ENTITY_DECL: break; } if (cur->name != NULL) xmlFree((xmlChar *) cur->name); @@ -2628,7 +2626,7 @@ xmlNodeGetBase(xmlDocPtr doc, xmlNodePtr cur) { return(NULL); if (doc == NULL) doc = cur->doc; if ((doc != NULL) && (doc->type == XML_HTML_DOCUMENT_NODE)) { - cur = doc->root; + cur = doc->children; while ((cur != NULL) && (cur->name != NULL)) { if (cur->type != XML_ELEMENT_NODE) { cur = cur->next; @@ -2636,12 +2634,12 @@ xmlNodeGetBase(xmlDocPtr doc, xmlNodePtr cur) { } if ((!xmlStrcmp(cur->name, BAD_CAST "html")) || (!xmlStrcmp(cur->name, BAD_CAST "HTML"))) { - cur = cur->childs; + cur = cur->children; continue; } if ((!xmlStrcmp(cur->name, BAD_CAST "head")) || (!xmlStrcmp(cur->name, BAD_CAST "HEAD"))) { - cur = cur->childs; + cur = cur->children; continue; } if ((!xmlStrcmp(cur->name, BAD_CAST "base")) || @@ -2650,7 +2648,10 @@ xmlNodeGetBase(xmlDocPtr doc, xmlNodePtr cur) { if (base != NULL) return(base); return(xmlGetProp(cur, BAD_CAST "HREF")); } + cur = cur->next; } + if ((doc != NULL) && (doc->URL != NULL)) + return(xmlStrdup(doc->URL)); return(NULL); } while (cur != NULL) { @@ -2659,6 +2660,8 @@ xmlNodeGetBase(xmlDocPtr doc, xmlNodePtr cur) { return(base); cur = cur->parent; } + if ((doc != NULL) && (doc->URL != NULL)) + return(xmlStrdup(doc->URL)); return(NULL); } @@ -2679,14 +2682,14 @@ xmlNodeGetContent(xmlNodePtr cur) { switch (cur->type) { case XML_DOCUMENT_FRAG_NODE: case XML_ELEMENT_NODE: - return(xmlNodeListGetString(cur->doc, cur->childs, 1)); + return(xmlNodeListGetString(cur->doc, cur->children, 1)); break; case XML_ATTRIBUTE_NODE: { xmlAttrPtr attr = (xmlAttrPtr) cur; - if (attr->node != NULL) - return(xmlNodeListGetString(attr->node->doc, attr->val, 1)); + if (attr->parent != NULL) + return(xmlNodeListGetString(attr->parent->doc, attr->children, 1)); else - return(xmlNodeListGetString(NULL, attr->val, 1)); + return(xmlNodeListGetString(NULL, attr->children, 1)); break; } case XML_COMMENT_NODE: @@ -2709,6 +2712,16 @@ xmlNodeGetContent(xmlNodePtr cur) { case XML_HTML_DOCUMENT_NODE: case XML_DOCUMENT_TYPE_NODE: case XML_NOTATION_NODE: + case XML_DTD_NODE: + return(NULL); + case XML_ELEMENT_DECL: + /* TODO !!! */ + return(NULL); + case XML_ATTRIBUTE_DECL: + /* TODO !!! */ + return(NULL); + case XML_ENTITY_DECL: + /* TODO !!! */ return(NULL); case XML_CDATA_SECTION_NODE: case XML_TEXT_NODE: @@ -2749,8 +2762,8 @@ xmlNodeSetContent(xmlNodePtr cur, const xmlChar *content) { #endif cur->content = NULL; } - if (cur->childs != NULL) xmlFreeNodeList(cur->childs); - cur->childs = xmlStringGetNodeList(cur->doc, content); + if (cur->children != NULL) xmlFreeNodeList(cur->children); + cur->children = xmlStringGetNodeList(cur->doc, content); UPDATE_LAST_CHILD(cur) break; case XML_ATTRIBUTE_NODE: @@ -2768,8 +2781,8 @@ xmlNodeSetContent(xmlNodePtr cur, const xmlChar *content) { xmlBufferFree(cur->content); #endif } - if (cur->childs != NULL) xmlFreeNodeList(cur->childs); - cur->last = cur->childs = NULL; + if (cur->children != NULL) xmlFreeNodeList(cur->children); + cur->last = cur->children = NULL; if (content != NULL) { #ifndef XML_USE_BUFFER_CONTENT cur->content = xmlStrdup(content); @@ -2788,6 +2801,17 @@ xmlNodeSetContent(xmlNodePtr cur, const xmlChar *content) { break; case XML_NOTATION_NODE: break; + case XML_DTD_NODE: + break; + case XML_ELEMENT_DECL: + /* TODO !!! */ + break; + case XML_ATTRIBUTE_DECL: + /* TODO !!! */ + break; + case XML_ENTITY_DECL: + /* TODO !!! */ + break; } } @@ -2818,8 +2842,8 @@ xmlNodeSetContentLen(xmlNodePtr cur, const xmlChar *content, int len) { #endif cur->content = NULL; } - if (cur->childs != NULL) xmlFreeNodeList(cur->childs); - cur->childs = xmlStringLenGetNodeList(cur->doc, content, len); + if (cur->children != NULL) xmlFreeNodeList(cur->children); + cur->children = xmlStringLenGetNodeList(cur->doc, content, len); UPDATE_LAST_CHILD(cur) break; case XML_ATTRIBUTE_NODE: @@ -2838,8 +2862,8 @@ xmlNodeSetContentLen(xmlNodePtr cur, const xmlChar *content, int len) { xmlBufferFree(cur->content); #endif } - if (cur->childs != NULL) xmlFreeNodeList(cur->childs); - cur->childs = cur->last = NULL; + if (cur->children != NULL) xmlFreeNodeList(cur->children); + cur->children = cur->last = NULL; if (content != NULL) { #ifndef XML_USE_BUFFER_CONTENT cur->content = xmlStrndup(content, len); @@ -2853,9 +2877,19 @@ xmlNodeSetContentLen(xmlNodePtr cur, const xmlChar *content, int len) { cur->content = NULL; break; case XML_DOCUMENT_NODE: + case XML_DTD_NODE: case XML_HTML_DOCUMENT_NODE: case XML_DOCUMENT_TYPE_NODE: break; + case XML_ELEMENT_DECL: + /* TODO !!! */ + break; + case XML_ATTRIBUTE_DECL: + /* TODO !!! */ + break; + case XML_ENTITY_DECL: + /* TODO !!! */ + break; } } @@ -2881,14 +2915,14 @@ xmlNodeAddContentLen(xmlNodePtr cur, const xmlChar *content, int len) { case XML_ELEMENT_NODE: { xmlNodePtr last = NULL, new; - if (cur->childs != NULL) { + if (cur->children != NULL) { last = cur->last; } else { if (cur->content != NULL) { #ifndef XML_USE_BUFFER_CONTENT - cur->childs = xmlStringGetNodeList(cur->doc, cur->content); + cur->children = xmlStringGetNodeList(cur->doc, cur->content); #else - cur->childs = xmlStringGetNodeList(cur->doc, + cur->children = xmlStringGetNodeList(cur->doc, xmlBufferContent(cur->content)); #endif UPDATE_LAST_CHILD(cur) @@ -2927,9 +2961,14 @@ xmlNodeAddContentLen(xmlNodePtr cur, const xmlChar *content, int len) { #endif } case XML_DOCUMENT_NODE: + case XML_DTD_NODE: case XML_HTML_DOCUMENT_NODE: case XML_DOCUMENT_TYPE_NODE: break; + case XML_ELEMENT_DECL: + case XML_ATTRIBUTE_DECL: + case XML_ENTITY_DECL: + break; } } @@ -3051,14 +3090,16 @@ xmlSearchNs(xmlDocPtr doc, xmlNodePtr node, const xmlChar *nameSpace) { if (node == NULL) return(NULL); while (node != NULL) { - cur = node->nsDef; - while (cur != NULL) { - if ((cur->prefix == NULL) && (nameSpace == NULL)) - return(cur); - if ((cur->prefix != NULL) && (nameSpace != NULL) && - (!xmlStrcmp(cur->prefix, nameSpace))) - return(cur); - cur = cur->next; + if (node->type == XML_ELEMENT_NODE) { + cur = node->nsDef; + while (cur != NULL) { + if ((cur->prefix == NULL) && (nameSpace == NULL)) + return(cur); + if ((cur->prefix != NULL) && (nameSpace != NULL) && + (!xmlStrcmp(cur->prefix, nameSpace))) + return(cur); + cur = cur->next; + } } node = node->parent; } @@ -3329,9 +3370,9 @@ xmlReconciliateNs(xmlDocPtr doc, xmlNodePtr tree) { /* * Browse the full subtree, deep first */ - if (node->childs != NULL) { + if (node->children != NULL) { /* deep first */ - node = node->childs; + node = node->children; } else if ((node != tree) && (node->next != NULL)) { /* then siblings */ node = node->next; @@ -3384,7 +3425,7 @@ xmlGetProp(xmlNodePtr node, const xmlChar *name) { if (!xmlStrcmp(prop->name, name)) { xmlChar *ret; - ret = xmlNodeListGetString(node->doc, prop->val, 1); + ret = xmlNodeListGetString(node->doc, prop->children, 1); if (ret == NULL) return(xmlStrdup((xmlChar *)"")); return(ret); } @@ -3447,7 +3488,7 @@ xmlGetNsProp(xmlNodePtr node, const xmlChar *name, const xmlChar *namespace) { ((prop->ns != NULL) && (!xmlStrcmp(prop->ns->href, namespace))))) { xmlChar *ret; - ret = xmlNodeListGetString(node->doc, prop->val, 1); + ret = xmlNodeListGetString(node->doc, prop->children, 1); if (ret == NULL) return(xmlStrdup((xmlChar *)"")); return(ret); } @@ -3495,13 +3536,22 @@ xmlSetProp(xmlNodePtr node, const xmlChar *name, const xmlChar *value) { while (prop != NULL) { if (!xmlStrcmp(prop->name, name)) { - if (prop->val != NULL) - xmlFreeNodeList(prop->val); - prop->val = NULL; + if (prop->children != NULL) + xmlFreeNodeList(prop->children); + prop->children = NULL; if (value != NULL) { xmlChar *buffer; + xmlNodePtr tmp; + buffer = xmlEncodeEntitiesReentrant(node->doc, value); - prop->val = xmlStringGetNodeList(node->doc, buffer); + prop->children = xmlStringGetNodeList(node->doc, buffer); + tmp = prop->children; + while (tmp != NULL) { + tmp->parent = (xmlNodePtr) prop; + if (tmp->next == NULL) + prop->last = tmp; + tmp = tmp->next; + } xmlFree(buffer); } return(prop); @@ -3842,7 +3892,7 @@ xmlBufferResize(xmlBufferPtr buf, int size) */ void xmlBufferAdd(xmlBufferPtr buf, const xmlChar *str, int len) { - int l, needSize; + int needSize; if (str == NULL) { #ifdef DEBUG_BUFFER @@ -3858,22 +3908,8 @@ xmlBufferAdd(xmlBufferPtr buf, const xmlChar *str, int len) { } if (len == 0) return; - /* CJN What's this for??? */ if (len < 0) - l = xmlStrlen(str); - else - for (l = 0;l < len;l++) - if (str[l] == 0) break; - if (l < len){ - len = l; -#ifdef DEBUG_BUFFER - printf("xmlBufferAdd bad length\n"); -#endif - } - - /* CJN 11.18.99 okay, now I'm using the length */ - if(len == -1) len = l; - + len = xmlStrlen(str); if (len <= 0) return; @@ -3987,6 +4023,15 @@ xmlBufferWriteQuotedString(xmlBufferPtr buf, const xmlChar *string) { } +static void +xmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, int level, + int format); +static void +xmlNodeListDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, int level, + int format); +void +htmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur); + /** * xmlGlobalNsDump: * @buf: the XML buffer output @@ -4083,43 +4128,42 @@ xmlNsListDump(xmlBufferPtr buf, xmlNsPtr cur) { * Dump the XML document DTD, if any. */ static void -xmlDtdDump(xmlBufferPtr buf, xmlDocPtr doc) { - xmlDtdPtr cur = doc->intSubset; - - if (cur == NULL) { +xmlDtdDump(xmlBufferPtr buf, xmlDtdPtr dtd) { + if (dtd == NULL) { #ifdef DEBUG_TREE fprintf(stderr, "xmlDtdDump : no internal subset\n"); #endif return; } xmlBufferWriteChar(buf, "name); - if (cur->ExternalID != NULL) { + xmlBufferWriteCHAR(buf, dtd->name); + if (dtd->ExternalID != NULL) { xmlBufferWriteChar(buf, " PUBLIC "); - xmlBufferWriteQuotedString(buf, cur->ExternalID); + xmlBufferWriteQuotedString(buf, dtd->ExternalID); xmlBufferWriteChar(buf, " "); - xmlBufferWriteQuotedString(buf, cur->SystemID); - } else if (cur->SystemID != NULL) { + xmlBufferWriteQuotedString(buf, dtd->SystemID); + } else if (dtd->SystemID != NULL) { xmlBufferWriteChar(buf, " SYSTEM "); - xmlBufferWriteQuotedString(buf, cur->SystemID); + xmlBufferWriteQuotedString(buf, dtd->SystemID); } - if ((cur->entities == NULL) && (cur->elements == NULL) && - (cur->attributes == NULL) && (cur->notations == NULL)) { - xmlBufferWriteChar(buf, ">\n"); + if ((dtd->entities == NULL) && (dtd->elements == NULL) && + (dtd->attributes == NULL) && (dtd->notations == NULL)) { + xmlBufferWriteChar(buf, ">"); return; } xmlBufferWriteChar(buf, " [\n"); - if (cur->entities != NULL) - xmlDumpEntitiesTable(buf, (xmlEntitiesTablePtr) cur->entities); - if (cur->notations != NULL) - xmlDumpNotationTable(buf, (xmlNotationTablePtr) cur->notations); - if (cur->elements != NULL) - xmlDumpElementTable(buf, (xmlElementTablePtr) cur->elements); - if (cur->attributes != NULL) - xmlDumpAttributeTable(buf, (xmlAttributeTablePtr) cur->attributes); - xmlBufferWriteChar(buf, "]"); - - xmlBufferWriteChar(buf, ">\n"); + xmlNodeListDump(buf, dtd->doc, dtd->children, -1, 0); +#if 0 + if (dtd->entities != NULL) + xmlDumpEntitiesTable(buf, (xmlEntitiesTablePtr) dtd->entities); + if (dtd->notations != NULL) + xmlDumpNotationTable(buf, (xmlNotationTablePtr) dtd->notations); + if (dtd->elements != NULL) + xmlDumpElementTable(buf, (xmlElementTablePtr) dtd->elements); + if (dtd->attributes != NULL) + xmlDumpAttributeTable(buf, (xmlAttributeTablePtr) dtd->attributes); +#endif + xmlBufferWriteChar(buf, "]>"); } /** @@ -4146,7 +4190,7 @@ xmlAttrDump(xmlBufferPtr buf, xmlDocPtr doc, xmlAttrPtr cur) { xmlBufferWriteChar(buf, ":"); } xmlBufferWriteCHAR(buf, cur->name); - value = xmlNodeListGetString(doc, cur->val, 0); + value = xmlNodeListGetString(doc, cur->children, 0); if (value) { xmlBufferWriteChar(buf, "="); xmlBufferWriteQuotedString(buf, value); @@ -4179,18 +4223,13 @@ xmlAttrListDump(xmlBufferPtr buf, xmlDocPtr doc, xmlAttrPtr cur) { } -static void -xmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, int level, - int format); -void -htmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur); /** * xmlNodeListDump: * @buf: the XML buffer output * @doc: the document * @cur: the first node - * @level: the imbrication level for indenting, -1 to disable it + * @level: the imbrication level for indenting * @format: is formatting allowed * * Dump an XML node list, recursive behaviour,children are printed too. @@ -4224,7 +4263,7 @@ xmlNodeListDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, int level, * @buf: the XML buffer output * @doc: the document * @cur: the current node - * @level: the imbrication level for indenting, -1 to disable it + * @level: the imbrication level for indenting * @format: is formatting allowed * * Dump an XML node, recursive behaviour,children are printed too. @@ -4241,6 +4280,22 @@ xmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, int level, #endif return; } + if (cur->type == XML_DTD_NODE) { + xmlDtdDump(buf, (xmlDtdPtr) cur); + return; + } + if (cur->type == XML_ELEMENT_DECL) { + xmlDumpElementDecl(buf, (xmlElementPtr) cur); + return; + } + if (cur->type == XML_ATTRIBUTE_DECL) { + xmlDumpAttributeDecl(buf, (xmlAttributePtr) cur); + return; + } + if (cur->type == XML_ENTITY_DECL) { + xmlDumpEntityDecl(buf, (xmlEntityPtr) cur); + return; + } if (cur->type == XML_TEXT_NODE) { if (cur->content != NULL) { xmlChar *buffer; @@ -4271,6 +4326,10 @@ xmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, int level, #endif } xmlBufferWriteChar(buf, "?>"); + } else { + xmlBufferWriteChar(buf, "name); + xmlBufferWriteChar(buf, "?>"); } return; } @@ -4305,7 +4364,7 @@ xmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, int level, } if (format == 1) { - tmp = cur->childs; + tmp = cur->children; while (tmp != NULL) { if ((tmp->type == XML_TEXT_NODE) || (tmp->type == XML_ENTITY_REF_NODE)) { @@ -4327,7 +4386,7 @@ xmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, int level, if (cur->properties != NULL) xmlAttrListDump(buf, doc, cur->properties); - if ((cur->content == NULL) && (cur->childs == NULL) && + if ((cur->content == NULL) && (cur->children == NULL) && (!xmlSaveNoEmptyTags)) { xmlBufferWriteChar(buf, "/>"); return; @@ -4347,9 +4406,9 @@ xmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, int level, xmlFree(buffer); } } - if (cur->childs != NULL) { + if (cur->children != NULL) { if (format) xmlBufferWriteChar(buf, "\n"); - xmlNodeListDump(buf, doc, cur->childs, + xmlNodeListDump(buf, doc, cur->children, (level >= 0?level+1:-1), format); if ((xmlIndentTreeOutput) && (format)) for (i = 0;i < level;i++) @@ -4426,10 +4485,8 @@ xmlDocContentDump(xmlBufferPtr buf, xmlDocPtr cur) { break; } xmlBufferWriteChar(buf, "?>\n"); - if (cur->intSubset != NULL) - xmlDtdDump(buf, cur); - if (cur->root != NULL) { - xmlNodePtr child = cur->root; + if (cur->children != NULL) { + xmlNodePtr child = cur->children; /* global namespace definitions, the old way */ if (oldXMLWDcompatibility) diff --git a/tree.h b/tree.h index ee88d806..c881728b 100644 --- a/tree.h +++ b/tree.h @@ -36,24 +36,22 @@ typedef enum { XML_DOCUMENT_TYPE_NODE= 10, XML_DOCUMENT_FRAG_NODE= 11, XML_NOTATION_NODE= 12, - XML_HTML_DOCUMENT_NODE= 13 + XML_HTML_DOCUMENT_NODE= 13, + XML_DTD_NODE= 14, + XML_ELEMENT_DECL= 15, + XML_ATTRIBUTE_DECL= 16, + XML_ENTITY_DECL= 17 } xmlElementType; /* * Size of an internal character representation. * - * Currently we use 8bit chars internal representation for memory efficiency, - * but the parser is not tied to that, just define UNICODE to switch to - * a 16 bits internal representation. Note that with 8 bits wide - * xmlChars one can still use UTF-8 to handle correctly non ISO-Latin - * input. + * We use 8bit chars internal representation for memory efficiency, + * Note that with 8 bits wide xmlChars one can still use UTF-8 to handle + * correctly non ISO-Latin input. */ -#ifdef UNICODE -typedef unsigned short xmlChar; -#else typedef unsigned char xmlChar; -#endif #ifndef WIN32 #ifndef CHAR @@ -109,14 +107,25 @@ struct _xmlEnumeration { typedef struct _xmlAttribute xmlAttribute; typedef xmlAttribute *xmlAttributePtr; struct _xmlAttribute { - const xmlChar *elem; /* Element holding the attribute */ - const xmlChar *name; /* Attribute name */ - struct _xmlAttribute *next; /* list of attributes of an element */ - xmlAttributeType type; /* The type */ - xmlAttributeDefault def; /* the default */ - const xmlChar *defaultValue;/* or the default value */ - xmlEnumerationPtr tree; /* or the enumeration tree if any */ - const xmlChar *prefix; /* the namespace prefix if any */ +#ifndef XML_WITHOUT_CORBA + void *_private; /* for Corba, must be first ! */ +#endif + xmlElementType type; /* XML_ATTRIBUTE_DECL, must be second ! */ + const xmlChar *name; /* Attribute name */ + struct _xmlNode *children; /* NULL */ + struct _xmlNode *last; /* NULL */ + struct _xmlDtd *parent; /* -> DTD */ + struct _xmlNode *next; /* next sibling link */ + struct _xmlNode *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* the containing document */ + + struct _xmlAttribute *nexth; /* next in hash table */ + xmlAttributeType atype; /* The attribute type */ + xmlAttributeDefault def; /* the default */ + const xmlChar *defaultValue; /* or the default value */ + xmlEnumerationPtr tree; /* or the enumeration tree if any */ + const xmlChar *prefix; /* the namespace prefix if any */ + const xmlChar *elem; /* Element holding the attribute */ }; /* @@ -156,8 +165,19 @@ typedef enum { typedef struct _xmlElement xmlElement; typedef xmlElement *xmlElementPtr; struct _xmlElement { +#ifndef XML_WITHOUT_CORBA + void *_private; /* for Corba, must be first ! */ +#endif + xmlElementType type; /* XML_ELEMENT_DECL, must be second ! */ const xmlChar *name; /* Element name */ - xmlElementTypeVal type; /* The type */ + struct _xmlNode *children; /* NULL */ + struct _xmlNode *last; /* NULL */ + struct _xmlDtd *parent; /* -> DTD */ + struct _xmlNode *next; /* next sibling link */ + struct _xmlNode *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* the containing document */ + + xmlElementTypeVal etype; /* The type */ xmlElementContentPtr content; /* the allowed element content */ xmlAttributePtr attributes; /* List of the declared attributes */ }; @@ -188,14 +208,25 @@ struct _xmlNs { typedef struct _xmlDtd xmlDtd; typedef xmlDtd *xmlDtdPtr; struct _xmlDtd { +#ifndef XML_WITHOUT_CORBA + void *_private; /* for Corba, must be first ! */ +#endif + xmlElementType type; /* XML_DTD_NODE, must be second ! */ const xmlChar *name; /* Name of the DTD */ - const xmlChar *ExternalID; /* External identifier for PUBLIC DTD */ - const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC DTD */ + struct _xmlNode *children; /* the value of the property link */ + struct _xmlNode *last; /* last child link */ + struct _xmlDoc *parent; /* child->parent link */ + struct _xmlNode *next; /* next sibling link */ + struct _xmlNode *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* the containing document */ + + /* End of common part */ void *notations; /* Hash table for notations if any */ void *elements; /* Hash table for elements if any */ void *attributes; /* Hash table for attributes if any */ void *entities; /* Hash table for entities if any */ - /* struct xmlDtd *next; * next link for this document */ + const xmlChar *ExternalID; /* External identifier for PUBLIC DTD */ + const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC DTD */ }; /* @@ -206,14 +237,17 @@ typedef xmlAttr *xmlAttrPtr; struct _xmlAttr { #ifndef XML_WITHOUT_CORBA void *_private; /* for Corba, must be first ! */ - void *vepv; /* for Corba, must be next ! */ #endif - xmlElementType type; /* XML_ATTRIBUTE_NODE, must be third ! */ - struct _xmlNode *node; /* attr->node link */ - struct _xmlAttr *next; /* attribute list link */ + xmlElementType type; /* XML_ATTRIBUTE_NODE, must be second ! */ const xmlChar *name; /* the name of the property */ - struct _xmlNode *val; /* the value of the property */ + struct _xmlNode *children; /* the value of the property */ + struct _xmlNode *last; /* NULL */ + struct _xmlNode *parent; /* child->parent link */ + struct _xmlAttr *next; /* next sibling link */ + struct _xmlAttr *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* the containing document */ xmlNs *ns; /* pointer to the associated namespace */ + xmlAttributeType atype; /* the attribute type if validating */ }; /* @@ -266,24 +300,25 @@ typedef xmlNode *xmlNodePtr; struct _xmlNode { #ifndef XML_WITHOUT_CORBA void *_private; /* for Corba, must be first ! */ - void *vepv; /* for Corba, must be next ! */ #endif - xmlElementType type; /* type number in the DTD, must be third ! */ - struct _xmlDoc *doc; /* the containing document */ + xmlElementType type; /* type number, must be second ! */ + const xmlChar *name; /* the name of the node, or the entity */ + struct _xmlNode *children; /* parent->childs link */ + struct _xmlNode *last; /* last child link */ struct _xmlNode *parent; /* child->parent link */ struct _xmlNode *next; /* next sibling link */ struct _xmlNode *prev; /* previous sibling link */ - struct _xmlNode *childs; /* parent->childs link */ - struct _xmlNode *last; /* last child link */ - struct _xmlAttr *properties;/* properties list */ - const xmlChar *name; /* the name of the node, or the entity */ - xmlNs *ns; /* pointer to the associated namespace */ - xmlNs *nsDef; /* namespace definitions on this node */ + struct _xmlDoc *doc; /* the containing document */ + xmlNs *ns; /* pointer to the associated namespace */ #ifndef XML_USE_BUFFER_CONTENT - xmlChar *content; /* the content */ + xmlChar *content; /* the content */ #else - xmlBufferPtr content; /* the content in a buffer */ + xmlBufferPtr content; /* the content in a buffer */ #endif + + /* End of common part */ + struct _xmlAttr *properties;/* properties list */ + xmlNs *nsDef; /* namespace definitions on this node */ }; /* @@ -294,20 +329,27 @@ typedef xmlDoc *xmlDocPtr; struct _xmlDoc { #ifndef XML_WITHOUT_CORBA void *_private; /* for Corba, must be first ! */ - void *vepv; /* for Corba, must be next ! */ #endif xmlElementType type; /* XML_DOCUMENT_NODE, must be second ! */ char *name; /* name/filename/URI of the document */ - const xmlChar *version; /* the XML version string */ - const xmlChar *encoding; /* encoding, if any */ + struct _xmlNode *children; /* the document tree */ + struct _xmlNode *last; /* last child link */ + struct _xmlNode *parent; /* child->parent link */ + struct _xmlNode *next; /* next sibling link */ + struct _xmlNode *prev; /* previous sibling link */ + struct _xmlDoc *doc; /* autoreference to itself */ + + /* End of common part */ int compression;/* level of zlib compression */ int standalone; /* standalone document (no external refs) */ struct _xmlDtd *intSubset; /* the document internal subset */ struct _xmlDtd *extSubset; /* the document external subset */ struct _xmlNs *oldNs; /* Global namespace, the old way */ - struct _xmlNode *root; /* the document tree */ + const xmlChar *version; /* the XML version string */ + const xmlChar *encoding; /* encoding, if any */ void *ids; /* Hash table for ID attributes if any */ void *refs; /* Hash table for IDREFs attributes if any */ + const xmlChar *URL; /* The URI for that document */ }; /* @@ -422,6 +464,8 @@ xmlNodePtr xmlNewComment (const xmlChar *content); xmlNodePtr xmlNewCDataBlock (xmlDocPtr doc, const xmlChar *content, int len); +xmlNodePtr xmlNewCharRef (xmlDocPtr doc, + const xmlChar *name); xmlNodePtr xmlNewReference (xmlDocPtr doc, const xmlChar *name); xmlNodePtr xmlCopyNode (xmlNodePtr node, @@ -513,13 +557,14 @@ xmlChar * xmlNodeGetContent (xmlNodePtr cur); xmlChar * xmlNodeGetLang (xmlNodePtr cur); void xmlNodeSetLang (xmlNodePtr cur, const xmlChar *lang); +int xmlNodeGetSpacePreserve (xmlNodePtr cur); xmlChar * xmlNodeGetBase (xmlDocPtr doc, xmlNodePtr cur); /* * Removing content. */ -int xmlRemoveProp (xmlAttrPtr attr); /* TODO */ +int xmlRemoveProp (xmlAttrPtr attr); int xmlRemoveNode (xmlNodePtr node); /* TODO */ /* @@ -532,6 +577,12 @@ void xmlBufferWriteChar (xmlBufferPtr buf, void xmlBufferWriteQuotedString(xmlBufferPtr buf, const xmlChar *string); +/* + * Namespace handling + */ +int xmlReconciliateNs (xmlDocPtr doc, + xmlNodePtr tree); + /* * Saving */ diff --git a/valid.c b/valid.c index ee4ae226..398fee12 100644 --- a/valid.c +++ b/valid.c @@ -25,6 +25,120 @@ #include "parser.h" #include "parserInternals.h" +/* + * Generic function for accessing stacks in the Validity Context + */ + +#define PUSH_AND_POP(scope, type, name) \ +scope int name##VPush(xmlValidCtxtPtr ctxt, type value) { \ + if (ctxt->name##Nr >= ctxt->name##Max) { \ + ctxt->name##Max *= 2; \ + ctxt->name##Tab = (void *) xmlRealloc(ctxt->name##Tab, \ + ctxt->name##Max * sizeof(ctxt->name##Tab[0])); \ + if (ctxt->name##Tab == NULL) { \ + fprintf(stderr, "realloc failed !\n"); \ + return(0); \ + } \ + } \ + ctxt->name##Tab[ctxt->name##Nr] = value; \ + ctxt->name = value; \ + return(ctxt->name##Nr++); \ +} \ +scope type name##VPop(xmlValidCtxtPtr ctxt) { \ + type ret; \ + if (ctxt->name##Nr <= 0) return(0); \ + ctxt->name##Nr--; \ + if (ctxt->name##Nr > 0) \ + ctxt->name = ctxt->name##Tab[ctxt->name##Nr - 1]; \ + else \ + ctxt->name = NULL; \ + ret = ctxt->name##Tab[ctxt->name##Nr]; \ + ctxt->name##Tab[ctxt->name##Nr] = 0; \ + return(ret); \ +} \ + +PUSH_AND_POP(static, xmlNodePtr, node) + +/* #define DEBUG_VALID_ALGO */ + +#ifdef DEBUG_VALID_ALGO +void xmlValidPrintNodeList(xmlNodePtr cur) { + if (cur == NULL) + fprintf(stderr, "null "); + while (cur != NULL) { + switch (cur->type) { + case XML_ELEMENT_NODE: + fprintf(stderr, "%s ", cur->name); + break; + case XML_TEXT_NODE: + fprintf(stderr, "text "); + break; + case XML_CDATA_SECTION_NODE: + fprintf(stderr, "cdata "); + break; + case XML_ENTITY_REF_NODE: + fprintf(stderr, "&%s; ", cur->name); + break; + case XML_PI_NODE: + fprintf(stderr, "pi(%s) ", cur->name); + break; + case XML_COMMENT_NODE: + fprintf(stderr, "comment "); + break; + case XML_ATTRIBUTE_NODE: + fprintf(stderr, "?attr? "); + break; + case XML_ENTITY_NODE: + fprintf(stderr, "?ent? "); + break; + case XML_DOCUMENT_NODE: + fprintf(stderr, "?doc? "); + break; + case XML_DOCUMENT_TYPE_NODE: + fprintf(stderr, "?doctype? "); + break; + case XML_DOCUMENT_FRAG_NODE: + fprintf(stderr, "?frag? "); + break; + case XML_NOTATION_NODE: + fprintf(stderr, "?nota? "); + break; + case XML_HTML_DOCUMENT_NODE: + fprintf(stderr, "?html? "); + break; + case XML_DTD_NODE: + fprintf(stderr, "?dtd? "); + break; + case XML_ELEMENT_DECL: + fprintf(stderr, "?edecl? "); + break; + case XML_ATTRIBUTE_DECL: + fprintf(stderr, "?adecl? "); + break; + case XML_ENTITY_DECL: + fprintf(stderr, "?entdecl? "); + break; + } + cur = cur->next; + } +} + +void xmlValidDebug(xmlNodePtr cur, xmlElementContentPtr cont) { + char expr[1000]; + + expr[0] = 0; + fprintf(stderr, "valid: "); + xmlValidPrintNodeList(cur); + fprintf(stderr, "against "); + xmlSprintfElementContent(expr, cont, 0); + fprintf(stderr, "%s\n", expr); +} + +#define DEBUG_VALID_STATE(n,c) xmlValidDebug(n,c); +#else +#define DEBUG_VALID_STATE(n,c) +#endif + /* TODO: use hash table for accesses to elem and attribute dedinitions */ #define VERROR \ @@ -310,7 +424,8 @@ xmlCreateElementTable(void) { */ xmlElementPtr xmlAddElementDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *name, - xmlElementTypeVal type, xmlElementContentPtr content) { + xmlElementTypeVal type, + xmlElementContentPtr content) { xmlElementPtr ret, cur; xmlElementTablePtr table; int i; @@ -403,17 +518,31 @@ xmlAddElementDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *name, fprintf(stderr, "xmlAddElementDecl: out of memory\n"); return(NULL); } + memset(ret, 0, sizeof(xmlElement)); + ret->type = XML_ELEMENT_DECL; table->table[table->nb_elements] = ret; /* * fill the structure. */ - ret->type = type; + ret->etype = type; ret->name = xmlStrdup(name); ret->content = xmlCopyElementContent(content); ret->attributes = xmlScanAttributeDecl(dtd, name); table->nb_elements++; + /* + * Link it to the Dtd + */ + ret->parent = dtd; + ret->doc = dtd->doc; + if (dtd->last == NULL) { + dtd->children = dtd->last = (xmlNodePtr) ret; + } else { + dtd->last->next = (xmlNodePtr) ret; + ret->prev = dtd->last; + dtd->last = (xmlNodePtr) ret; + } return(ret); } @@ -426,6 +555,7 @@ xmlAddElementDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *name, void xmlFreeElement(xmlElementPtr elem) { if (elem == NULL) return; + xmlUnlinkNode((xmlNodePtr) elem); xmlFreeElementContent(elem->content); if (elem->name != NULL) xmlFree((xmlChar *) elem->name); @@ -488,9 +618,11 @@ xmlCopyElementTable(xmlElementTablePtr table) { xmlFree(ret->table); return(NULL); } + memset(cur, 0, sizeof(xmlElement)); + cur->type = XML_ELEMENT_DECL; ret->table[i] = cur; ent = table->table[i]; - cur->type = ent->type; + cur->etype = ent->etype; if (ent->name != NULL) cur->name = xmlStrdup(ent->name); else @@ -502,6 +634,48 @@ xmlCopyElementTable(xmlElementTablePtr table) { return(ret); } +/** + * xmlDumpElementDecl: + * @buf: the XML buffer output + * @elem: An element table + * + * This will dump the content of the element declaration as an XML + * DTD definition + */ +void +xmlDumpElementDecl(xmlBufferPtr buf, xmlElementPtr elem) { + switch (elem->etype) { + case XML_ELEMENT_TYPE_EMPTY: + xmlBufferWriteChar(buf, "name); + xmlBufferWriteChar(buf, " EMPTY>\n"); + break; + case XML_ELEMENT_TYPE_ANY: + xmlBufferWriteChar(buf, "name); + xmlBufferWriteChar(buf, " ANY>\n"); + break; + case XML_ELEMENT_TYPE_MIXED: + xmlBufferWriteChar(buf, "name); + xmlBufferWriteChar(buf, " "); + xmlDumpElementContent(buf, elem->content, 1); + xmlBufferWriteChar(buf, ">\n"); + break; + case XML_ELEMENT_TYPE_ELEMENT: + xmlBufferWriteChar(buf, "name); + xmlBufferWriteChar(buf, " "); + xmlDumpElementContent(buf, elem->content, 1); + xmlBufferWriteChar(buf, ">\n"); + break; + default: + fprintf(stderr, + "xmlDumpElementDecl: internal: unknown type %d\n", + elem->etype); + } +} + /** * xmlDumpElementTable: * @buf: the XML buffer output @@ -518,36 +692,7 @@ xmlDumpElementTable(xmlBufferPtr buf, xmlElementTablePtr table) { for (i = 0;i < table->nb_elements;i++) { cur = table->table[i]; - switch (cur->type) { - case XML_ELEMENT_TYPE_EMPTY: - xmlBufferWriteChar(buf, "name); - xmlBufferWriteChar(buf, " EMPTY>\n"); - break; - case XML_ELEMENT_TYPE_ANY: - xmlBufferWriteChar(buf, "name); - xmlBufferWriteChar(buf, " ANY>\n"); - break; - case XML_ELEMENT_TYPE_MIXED: - xmlBufferWriteChar(buf, "name); - xmlBufferWriteChar(buf, " "); - xmlDumpElementContent(buf, cur->content, 1); - xmlBufferWriteChar(buf, ">\n"); - break; - case XML_ELEMENT_TYPE_ELEMENT: - xmlBufferWriteChar(buf, "name); - xmlBufferWriteChar(buf, " "); - xmlDumpElementContent(buf, cur->content, 1); - xmlBufferWriteChar(buf, ">\n"); - break; - default: - fprintf(stderr, - "xmlDumpElementTable: internal: unknown type %d\n", - cur->type); - } + xmlDumpElementDecl(buf, cur); } } @@ -570,12 +715,10 @@ xmlCreateEnumeration(xmlChar *name) { (long)sizeof(xmlEnumeration)); return(NULL); } + memset(ret, 0, sizeof(xmlEnumeration)); if (name != NULL) ret->name = xmlStrdup(name); - else - ret->name = NULL; - ret->next = NULL; return(ret); } @@ -701,7 +844,7 @@ xmlScanAttributeDecl(xmlDtdPtr dtd, const xmlChar *elem) { for (i = 0;i < table->nb_attributes;i++) { if (!xmlStrcmp(table->table[i]->elem, elem)) { - table->table[i]->next = ret; + table->table[i]->nexth = ret; ret = table->table[i]; } } @@ -726,14 +869,14 @@ xmlScanIDAttributeDecl(xmlValidCtxtPtr ctxt, xmlElementPtr elem) { if (elem == NULL) return(0); cur = elem->attributes; while (cur != NULL) { - if (cur->type == XML_ATTRIBUTE_ID) { + if (cur->atype == XML_ATTRIBUTE_ID) { ret ++; if (ret > 1) VERROR(ctxt->userData, "Element %s has too may ID attributes defined : %s\n", elem->name, cur->name); } - cur = cur->next; + cur = cur->nexth; } return(ret); } @@ -745,6 +888,7 @@ xmlScanIDAttributeDecl(xmlValidCtxtPtr ctxt, xmlElementPtr elem) { * @dtd: pointer to the DTD * @elem: the element name * @name: the attribute name + * @ns: the attribute namespace prefix * @type: the attribute type * @def: the attribute default type * @defaultValue: the attribute default value @@ -756,14 +900,12 @@ xmlScanIDAttributeDecl(xmlValidCtxtPtr ctxt, xmlElementPtr elem) { */ xmlAttributePtr xmlAddAttributeDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *elem, - const xmlChar *name, xmlAttributeType type, - xmlAttributeDefault def, const xmlChar *defaultValue, - xmlEnumerationPtr tree) { + const xmlChar *name, const xmlChar *ns, + xmlAttributeType type, xmlAttributeDefault def, + const xmlChar *defaultValue, xmlEnumerationPtr tree) { xmlAttributePtr ret, cur; xmlAttributeTablePtr table; xmlElementPtr elemDef; - xmlChar *rname; - xmlChar *ns; int i; if (dtd == NULL) { @@ -824,11 +966,6 @@ xmlAddAttributeDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *elem, return(NULL); } - /* - * Split the full name into a namespace prefix and the tag name - */ - rname = xmlSplitQName(name, &ns); - /* * Validity Check: * Search the DTD for previous declarations of the ATTLIST @@ -837,12 +974,12 @@ xmlAddAttributeDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *elem, cur = table->table[i]; if ((ns != NULL) && (cur->prefix == NULL)) continue; if ((ns == NULL) && (cur->prefix != NULL)) continue; - if ((!xmlStrcmp(cur->name, rname)) && (!xmlStrcmp(cur->elem, elem)) && + if ((!xmlStrcmp(cur->name, name)) && (!xmlStrcmp(cur->elem, elem)) && ((ns == NULL) || (!xmlStrcmp(cur->prefix, ns)))) { /* * The attribute is already defined in this Dtd. */ - VERROR(ctxt->userData, "Attribute %s on %s: already defined\n", + VWARNING(ctxt->userData, "Attribute %s on %s: already defined\n", elem, name); } } @@ -868,21 +1005,21 @@ xmlAddAttributeDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *elem, fprintf(stderr, "xmlAddAttributeDecl: out of memory\n"); return(NULL); } + memset(ret, 0, sizeof(xmlAttribute)); + ret->type = XML_ATTRIBUTE_DECL; table->table[table->nb_attributes] = ret; /* * fill the structure. */ - ret->type = type; - ret->name = rname; - ret->prefix = ns; + ret->atype = type; + ret->name = xmlStrdup(name); + ret->prefix = xmlStrdup(ns); ret->elem = xmlStrdup(elem); ret->def = def; ret->tree = tree; if (defaultValue != NULL) ret->defaultValue = xmlStrdup(defaultValue); - else - ret->defaultValue = NULL; elemDef = xmlGetDtdElementDesc(dtd, elem); if (elemDef != NULL) { if ((type == XML_ATTRIBUTE_ID) && @@ -890,11 +1027,23 @@ xmlAddAttributeDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *elem, VERROR(ctxt->userData, "Element %s has too may ID attributes defined : %s\n", elem, name); - ret->next = elemDef->attributes; + ret->nexth = elemDef->attributes; elemDef->attributes = ret; } table->nb_attributes++; + /* + * Link it to the Dtd + */ + ret->parent = dtd; + ret->doc = dtd->doc; + if (dtd->last == NULL) { + dtd->children = dtd->last = (xmlNodePtr) ret; + } else { + dtd->last->next = (xmlNodePtr) ret; + ret->prev = dtd->last; + dtd->last = (xmlNodePtr) ret; + } return(ret); } @@ -907,6 +1056,7 @@ xmlAddAttributeDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *elem, void xmlFreeAttribute(xmlAttributePtr attr) { if (attr == NULL) return; + xmlUnlinkNode((xmlNodePtr) attr); if (attr->tree != NULL) xmlFreeEnumeration(attr->tree); if (attr->elem != NULL) @@ -977,27 +1127,99 @@ xmlCopyAttributeTable(xmlAttributeTablePtr table) { xmlFree(ret->table); return(NULL); } + memset(cur, 0, sizeof(xmlAttribute)); + /* !!! cur->type = XML_ATTRIBUTE_DECL; */ ret->table[i] = cur; - cur->type = attr->type; + cur->atype = attr->atype; cur->def = attr->def; cur->tree = xmlCopyEnumeration(attr->tree); if (attr->elem != NULL) cur->elem = xmlStrdup(attr->elem); - else - cur->elem = NULL; if (attr->name != NULL) cur->name = xmlStrdup(attr->name); - else - cur->name = NULL; if (attr->defaultValue != NULL) cur->defaultValue = xmlStrdup(attr->defaultValue); - else - cur->defaultValue = NULL; /* NEED to rebuild the next chain !!!!!! */ } return(ret); } +/** + * xmlDumpAttributeDecl: + * @buf: the XML buffer output + * @attr: An attribute declaration + * + * This will dump the content of the attribute declaration as an XML + * DTD definition + */ +void +xmlDumpAttributeDecl(xmlBufferPtr buf, xmlAttributePtr attr) { + xmlBufferWriteChar(buf, "elem); + xmlBufferWriteChar(buf, " "); + xmlBufferWriteCHAR(buf, attr->name); + switch (attr->atype) { + case XML_ATTRIBUTE_CDATA: + xmlBufferWriteChar(buf, " CDATA"); + break; + case XML_ATTRIBUTE_ID: + xmlBufferWriteChar(buf, " ID"); + break; + case XML_ATTRIBUTE_IDREF: + xmlBufferWriteChar(buf, " IDREF"); + break; + case XML_ATTRIBUTE_IDREFS: + xmlBufferWriteChar(buf, " IDREFS"); + break; + case XML_ATTRIBUTE_ENTITY: + xmlBufferWriteChar(buf, " ENTITY"); + break; + case XML_ATTRIBUTE_ENTITIES: + xmlBufferWriteChar(buf, " ENTITIES"); + break; + case XML_ATTRIBUTE_NMTOKEN: + xmlBufferWriteChar(buf, " NMTOKEN"); + break; + case XML_ATTRIBUTE_NMTOKENS: + xmlBufferWriteChar(buf, " NMTOKENS"); + break; + case XML_ATTRIBUTE_ENUMERATION: + xmlBufferWriteChar(buf, " ("); + xmlDumpEnumeration(buf, attr->tree); + break; + case XML_ATTRIBUTE_NOTATION: + xmlBufferWriteChar(buf, " NOTATION ("); + xmlDumpEnumeration(buf, attr->tree); + break; + default: + fprintf(stderr, + "xmlDumpAttributeTable: internal: unknown type %d\n", + attr->atype); + } + switch (attr->def) { + case XML_ATTRIBUTE_NONE: + break; + case XML_ATTRIBUTE_REQUIRED: + xmlBufferWriteChar(buf, " #REQUIRED"); + break; + case XML_ATTRIBUTE_IMPLIED: + xmlBufferWriteChar(buf, " #IMPLIED"); + break; + case XML_ATTRIBUTE_FIXED: + xmlBufferWriteChar(buf, " #FIXED"); + break; + default: + fprintf(stderr, + "xmlDumpAttributeTable: internal: unknown default %d\n", + attr->def); + } + if (attr->defaultValue != NULL) { + xmlBufferWriteChar(buf, " "); + xmlBufferWriteQuotedString(buf, attr->defaultValue); + } + xmlBufferWriteChar(buf, ">\n"); +} + /** * xmlDumpAttributeTable: * @buf: the XML buffer output @@ -1014,70 +1236,7 @@ xmlDumpAttributeTable(xmlBufferPtr buf, xmlAttributeTablePtr table) { for (i = 0;i < table->nb_attributes;i++) { cur = table->table[i]; - xmlBufferWriteChar(buf, "elem); - xmlBufferWriteChar(buf, " "); - xmlBufferWriteCHAR(buf, cur->name); - switch (cur->type) { - case XML_ATTRIBUTE_CDATA: - xmlBufferWriteChar(buf, " CDATA"); - break; - case XML_ATTRIBUTE_ID: - xmlBufferWriteChar(buf, " ID"); - break; - case XML_ATTRIBUTE_IDREF: - xmlBufferWriteChar(buf, " IDREF"); - break; - case XML_ATTRIBUTE_IDREFS: - xmlBufferWriteChar(buf, " IDREFS"); - break; - case XML_ATTRIBUTE_ENTITY: - xmlBufferWriteChar(buf, " ENTITY"); - break; - case XML_ATTRIBUTE_ENTITIES: - xmlBufferWriteChar(buf, " ENTITIES"); - break; - case XML_ATTRIBUTE_NMTOKEN: - xmlBufferWriteChar(buf, " NMTOKEN"); - break; - case XML_ATTRIBUTE_NMTOKENS: - xmlBufferWriteChar(buf, " NMTOKENS"); - break; - case XML_ATTRIBUTE_ENUMERATION: - xmlBufferWriteChar(buf, " ("); - xmlDumpEnumeration(buf, cur->tree); - break; - case XML_ATTRIBUTE_NOTATION: - xmlBufferWriteChar(buf, " NOTATION ("); - xmlDumpEnumeration(buf, cur->tree); - break; - default: - fprintf(stderr, - "xmlDumpAttributeTable: internal: unknown type %d\n", - cur->type); - } - switch (cur->def) { - case XML_ATTRIBUTE_NONE: - break; - case XML_ATTRIBUTE_REQUIRED: - xmlBufferWriteChar(buf, " #REQUIRED"); - break; - case XML_ATTRIBUTE_IMPLIED: - xmlBufferWriteChar(buf, " #IMPLIED"); - break; - case XML_ATTRIBUTE_FIXED: - xmlBufferWriteChar(buf, " #FIXED"); - break; - default: - fprintf(stderr, - "xmlDumpAttributeTable: internal: unknown default %d\n", - cur->def); - } - if (cur->defaultValue != NULL) { - xmlBufferWriteChar(buf, " "); - xmlBufferWriteQuotedString(buf, cur->defaultValue); - } - xmlBufferWriteChar(buf, ">\n"); + xmlDumpAttributeDecl(buf, cur); } } @@ -1197,6 +1356,7 @@ xmlAddNotationDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *name, fprintf(stderr, "xmlAddNotationDecl: out of memory\n"); return(NULL); } + memset(ret, 0, sizeof(xmlNotation)); table->table[table->nb_notations] = ret; /* @@ -1205,12 +1365,8 @@ xmlAddNotationDecl(xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *name, ret->name = xmlStrdup(name); if (SystemID != NULL) ret->SystemID = xmlStrdup(SystemID); - else - ret->SystemID = NULL; if (PublicID != NULL) ret->PublicID = xmlStrdup(PublicID); - else - ret->PublicID = NULL; table->nb_notations++; return(ret); @@ -1308,6 +1464,31 @@ xmlCopyNotationTable(xmlNotationTablePtr table) { return(ret); } +/** + * xmlDumpNotationDecl: + * @buf: the XML buffer output + * @nota: A notation declaration + * + * This will dump the content the notation declaration as an XML DTD definition + */ +void +xmlDumpNotationDecl(xmlBufferPtr buf, xmlNotationPtr nota) { + xmlBufferWriteChar(buf, "name); + if (nota->PublicID != NULL) { + xmlBufferWriteChar(buf, " PUBLIC "); + xmlBufferWriteQuotedString(buf, nota->PublicID); + if (nota->SystemID != NULL) { + xmlBufferWriteChar(buf, " "); + xmlBufferWriteCHAR(buf, nota->SystemID); + } + } else { + xmlBufferWriteChar(buf, " SYSTEM "); + xmlBufferWriteCHAR(buf, nota->SystemID); + } + xmlBufferWriteChar(buf, " >\n"); +} + /** * xmlDumpNotationTable: * @buf: the XML buffer output @@ -1324,20 +1505,7 @@ xmlDumpNotationTable(xmlBufferPtr buf, xmlNotationTablePtr table) { for (i = 0;i < table->nb_notations;i++) { cur = table->table[i]; - xmlBufferWriteChar(buf, "name); - if (cur->PublicID != NULL) { - xmlBufferWriteChar(buf, " PUBLIC "); - xmlBufferWriteQuotedString(buf, cur->PublicID); - if (cur->SystemID != NULL) { - xmlBufferWriteChar(buf, " "); - xmlBufferWriteCHAR(buf, cur->SystemID); - } - } else { - xmlBufferWriteChar(buf, " SYSTEM "); - xmlBufferWriteCHAR(buf, cur->SystemID); - } - xmlBufferWriteChar(buf, " >\n"); + xmlDumpNotationDecl(buf, cur); } } @@ -1537,7 +1705,7 @@ xmlIsID(xmlDocPtr doc, xmlNodePtr elem, xmlAttrPtr attr) { attrDecl = xmlGetDtdAttrDesc(doc->extSubset, elem->name, attr->name); - if ((attrDecl != NULL) && (attrDecl->type == XML_ATTRIBUTE_ID)) + if ((attrDecl != NULL) && (attrDecl->atype == XML_ATTRIBUTE_ID)) return(1); } return(0); @@ -1795,7 +1963,7 @@ xmlIsRef(xmlDocPtr doc, xmlNodePtr elem, xmlAttrPtr attr) { attrDecl = xmlGetDtdAttrDesc(doc->extSubset, elem->name, attr->name); - if ((attrDecl != NULL) && (attrDecl->type == XML_ATTRIBUTE_IDREF)) + if ((attrDecl != NULL) && (attrDecl->atype == XML_ATTRIBUTE_IDREF)) return(1); } return(0); @@ -2022,7 +2190,7 @@ xmlIsMixedElement(xmlDocPtr doc, const xmlChar *name) { if ((elemDecl == NULL) && (doc->extSubset != NULL)) elemDecl = xmlGetDtdElementDesc(doc->extSubset, name); if (elemDecl == NULL) return(-1); - switch (elemDecl->type) { + switch (elemDecl->etype) { case XML_ELEMENT_TYPE_ELEMENT: return(0); case XML_ELEMENT_TYPE_EMPTY: @@ -2174,6 +2342,7 @@ xmlValidateNmtokensValue(const xmlChar *value) { if (value == NULL) return(0); cur = value; + while (IS_BLANK(*cur)) cur++; if (!IS_LETTER(*cur) && !IS_DIGIT(*cur) && (*cur != '.') && (*cur != '-') && (*cur != '_') && (*cur != ':') && @@ -2190,6 +2359,7 @@ xmlValidateNmtokensValue(const xmlChar *value) { while (IS_BLANK(*cur)) { while (IS_BLANK(*cur)) cur++; + if (*cur == 0) return(1); if (!IS_LETTER(*cur) && !IS_DIGIT(*cur) && (*cur != '.') && (*cur != '-') && @@ -2281,6 +2451,176 @@ xmlValidateAttributeValue(xmlAttributeType type, const xmlChar *value) { return(1); } +/** + * xmlValidateAttributeValue2: + * @ctxt: the validation context + * @doc: the document + * @name: the attribute name (used for error reporting only) + * @type: the attribute type + * @value: the attribute value + * + * Validate that the given attribute value match a given type. + * This typically cannot be done before having finished parsing + * the subsets. + * + * [ VC: IDREF ] + * Values of type IDREF must match one of the declared IDs + * Values of type IDREFS must match a sequence of the declared IDs + * each Name must match the value of an ID attribute on some element + * in the XML document; i.e. IDREF values must match the value of + * some ID attribute + * + * [ VC: Entity Name ] + * Values of type ENTITY must match one declared entity + * Values of type ENTITIES must match a sequence of declared entities + * + * [ VC: Notation Attributes ] + * all notation names in the declaration must be declared. + * + * returns 1 if valid or 0 otherwise + */ + +int +xmlValidateAttributeValue2(xmlValidCtxtPtr ctxt, xmlDocPtr doc, + const xmlChar *name, xmlAttributeType type, const xmlChar *value) { + int ret = 1; + switch (type) { + case XML_ATTRIBUTE_IDREFS: + case XML_ATTRIBUTE_IDREF: + case XML_ATTRIBUTE_ID: + case XML_ATTRIBUTE_NMTOKENS: + case XML_ATTRIBUTE_ENUMERATION: + case XML_ATTRIBUTE_NMTOKEN: + case XML_ATTRIBUTE_CDATA: + break; + case XML_ATTRIBUTE_ENTITY: { + xmlEntityPtr ent; + + ent = xmlGetDocEntity(doc, value); + if (ent == NULL) { + VERROR(ctxt->userData, + "ENTITY attribute %s reference an unknown entity \"%s\"\n", + name, value); + ret = 0; + } else if (ent->etype != XML_EXTERNAL_GENERAL_UNPARSED_ENTITY) { + VERROR(ctxt->userData, + "ENTITY attribute %s reference an entity \"%s\" of wrong type\n", + name, value); + ret = 0; + } + break; + } + case XML_ATTRIBUTE_ENTITIES: { + xmlChar *dup, *nam = NULL, *cur, save; + xmlEntityPtr ent; + + dup = xmlStrdup(value); + if (dup == NULL) + return(0); + cur = dup; + while (*cur != 0) { + nam = cur; + while ((*cur != 0) && (!IS_BLANK(*cur))) cur++; + save = *cur; + *cur = 0; + ent = xmlGetDocEntity(doc, nam); + if (ent == NULL) { + VERROR(ctxt->userData, + "ENTITIES attribute %s reference an unknown entity \"%s\"\n", + name, nam); + ret = 0; + } else if (ent->etype != XML_EXTERNAL_GENERAL_UNPARSED_ENTITY) { + VERROR(ctxt->userData, + "ENTITIES attribute %s reference an entity \"%s\" of wrong type\n", + name, nam); + ret = 0; + } + if (save == 0) + break; + *cur = save; + while (IS_BLANK(*cur)) cur++; + } + xmlFree(dup); + break; + } + case XML_ATTRIBUTE_NOTATION: { + xmlNotationPtr nota; + + nota = xmlGetDtdNotationDesc(doc->intSubset, value); + if ((nota == NULL) && (doc->extSubset != NULL)) + nota = xmlGetDtdNotationDesc(doc->extSubset, value); + + if (nota == NULL) { + VERROR(ctxt->userData, + "NOTATION attribute %s reference an unknown notation \"%s\"\n", + name, value); + ret = 0; + } + break; + } + } + return(ret); +} + +/** + * xmlValidNormalizeAttributeValue: + * @doc: the document + * @elem: the parent + * @name: the attribute name + * @value: the attribute value + * + * Does the validation related extra step of the normalization of attribute + * values: + * + * If the declared value is not CDATA, then the XML processor must further + * process the normalized attribute value by discarding any leading and + * trailing space (#x20) characters, and by replacing sequences of space + * (#x20) characters by single space (#x20) character. + * + * returns a new normalized string if normalization is needed, NULL otherwise + * the caller must free the returned value. + */ + +xmlChar * +xmlValidNormalizeAttributeValue(xmlDocPtr doc, xmlNodePtr elem, + const xmlChar *name, const xmlChar *value) { + xmlChar *ret, *dst; + const xmlChar *src; + xmlAttributePtr attrDecl; + + if (doc == NULL) return(NULL); + if (elem == NULL) return(NULL); + if (name == NULL) return(NULL); + if (value == NULL) return(NULL); + + attrDecl = xmlGetDtdAttrDesc(doc->intSubset, elem->name, name); + if ((attrDecl == NULL) && (doc->extSubset != NULL)) + attrDecl = xmlGetDtdAttrDesc(doc->extSubset, elem->name, name); + + if (attrDecl == NULL) + return(NULL); + if (attrDecl->atype == XML_ATTRIBUTE_CDATA) + return(NULL); + + ret = xmlStrdup(value); + if (ret == NULL) + return(NULL); + src = value; + dst = ret; + while (*src == 0x20) src++; + while (*src != 0) { + if (*src == 0x20) { + while (*src == 0x20) src++; + if (*src != 0) + *dst++ = 0x20; + } else { + *dst++ = *src++; + } + } + *dst = 0; + return(ret); +} + /** * xmlValidateAttributeDecl: * @ctxt: the validation context @@ -2310,7 +2650,7 @@ xmlValidateAttributeDecl(xmlValidCtxtPtr ctxt, xmlDocPtr doc, /* Attribute Default Legal */ /* Enumeration */ if (attr->defaultValue != NULL) { - val = xmlValidateAttributeValue(attr->type, attr->defaultValue); + val = xmlValidateAttributeValue(attr->atype, attr->defaultValue); if (val == 0) { VERROR(ctxt->userData, "Syntax of default value for attribute %s on %s is not valid\n", @@ -2320,7 +2660,7 @@ xmlValidateAttributeDecl(xmlValidCtxtPtr ctxt, xmlDocPtr doc, } /* ID Attribute Default */ - if ((attr->type == XML_ATTRIBUTE_ID)&& + if ((attr->atype == XML_ATTRIBUTE_ID)&& (attr->def != XML_ATTRIBUTE_IMPLIED) && (attr->def != XML_ATTRIBUTE_REQUIRED)) { VERROR(ctxt->userData, @@ -2330,19 +2670,68 @@ xmlValidateAttributeDecl(xmlValidCtxtPtr ctxt, xmlDocPtr doc, } /* One ID per Element Type */ - if ((attr->type == XML_ATTRIBUTE_ID) && (doc->extSubset != NULL)) { - int nbId = 0; + if (attr->atype == XML_ATTRIBUTE_ID) { + int nbId; /* the trick is taht we parse DtD as their own internal subset */ - xmlElementPtr elem = xmlGetDtdElementDesc(doc->extSubset, + xmlElementPtr elem = xmlGetDtdElementDesc(doc->intSubset, attr->elem); if (elem != NULL) { nbId = xmlScanIDAttributeDecl(NULL, elem); + } else { + xmlAttributeTablePtr table; + int i; + + /* + * The attribute may be declared in the internal subset and the + * element in the external subset. + */ + nbId = 0; + table = doc->intSubset->attributes; + if (table != NULL) { + for (i = 0;i < table->nb_attributes;i++) { + if ((table->table[i]->atype == XML_ATTRIBUTE_ID) && + (!xmlStrcmp(table->table[i]->elem, attr->elem))) { + nbId++; + } + } + } } - if (nbId >= 1) + if (nbId > 1) { VERROR(ctxt->userData, - "Element %s has ID attribute defined in the external subset : %s\n", - attr->elem, attr->name); + "Element %s has %d ID attribute defined in the internal subset : %s\n", + attr->elem, nbId, attr->name); + } else if (doc->extSubset != NULL) { + int extId = 0; + elem = xmlGetDtdElementDesc(doc->extSubset, attr->elem); + if (elem != NULL) { + extId = xmlScanIDAttributeDecl(NULL, elem); + } + if (extId > 1) { + VERROR(ctxt->userData, + "Element %s has %d ID attribute defined in the external subset : %s\n", + attr->elem, extId, attr->name); + } else if (extId + nbId > 1) { + VERROR(ctxt->userData, +"Element %s has ID attributes defined in the internal and external subset : %s\n", + attr->elem, attr->name); + } + } + } + + /* Validity Constraint: Enumeration */ + if ((attr->defaultValue != NULL) && (attr->tree != NULL)) { + xmlEnumerationPtr tree = attr->tree; + while (tree != NULL) { + if (!xmlStrcmp(tree->name, attr->defaultValue)) break; + tree = tree->next; + } + if (tree == NULL) { + VERROR(ctxt->userData, +"Default value \"%s\" for attribute %s on %s is not among the enumerated set\n", + attr->defaultValue, attr->name, attr->elem); + ret = 0; + } } return(ret); @@ -2375,7 +2764,7 @@ xmlValidateElementDecl(xmlValidCtxtPtr ctxt, xmlDocPtr doc, if (elem == NULL) return(1); /* No Duplicate Types */ - if (elem->type == XML_ELEMENT_TYPE_MIXED) { + if (elem->etype == XML_ELEMENT_TYPE_MIXED) { xmlElementContentPtr cur, next; const xmlChar *name; @@ -2441,7 +2830,7 @@ xmlValidateElementDecl(xmlValidCtxtPtr ctxt, xmlDocPtr doc, * @value: the attribute value (without entities processing) * * Try to validate a single attribute for an element - * basically it * does the following checks as described by the + * basically it does the following checks as described by the * XML-1.0 recommendation: * - [ VC: Attribute Value Type ] * - [ VC: Fixed Attribute Default ] @@ -2481,7 +2870,9 @@ xmlValidateOneAttribute(xmlValidCtxtPtr ctxt, xmlDocPtr doc, attr->name, elem->name); return(0); } - val = xmlValidateAttributeValue(attrDecl->type, value); + attr->atype = attrDecl->atype; + + val = xmlValidateAttributeValue(attrDecl->atype, value); if (val == 0) { VERROR(ctxt->userData, "Syntax of value for attribute %s on %s is not valid\n", @@ -2489,17 +2880,28 @@ xmlValidateOneAttribute(xmlValidCtxtPtr ctxt, xmlDocPtr doc, ret = 0; } + /* Validity constraint: Fixed Attribute Default */ + if (attrDecl->def == XML_ATTRIBUTE_FIXED) { + if (xmlStrcmp(value, attrDecl->defaultValue)) { + VERROR(ctxt->userData, + "Value for attribute %s on %s is differnt from default \"%s\"\n", + attr->name, elem->name, attrDecl->defaultValue); + ret = 0; + } + } + /* Validity Constraint: ID uniqueness */ - if (attrDecl->type == XML_ATTRIBUTE_ID) { + if (attrDecl->atype == XML_ATTRIBUTE_ID) { xmlAddID(ctxt, doc, value, attr); } - if (attrDecl->type == XML_ATTRIBUTE_IDREF) { + if ((attrDecl->atype == XML_ATTRIBUTE_IDREF) || + (attrDecl->atype == XML_ATTRIBUTE_IDREFS)) { xmlAddRef(ctxt, doc, value, attr); } /* Validity Constraint: Notation Attributes */ - if (attrDecl->type == XML_ATTRIBUTE_NOTATION) { + if (attrDecl->atype == XML_ATTRIBUTE_NOTATION) { xmlEnumerationPtr tree = attrDecl->tree; xmlNotationPtr nota; @@ -2522,14 +2924,14 @@ xmlValidateOneAttribute(xmlValidCtxtPtr ctxt, xmlDocPtr doc, } if (tree == NULL) { VERROR(ctxt->userData, - "Value \"%s\" for attribute %s on %s is among the enumerated notations\n", +"Value \"%s\" for attribute %s on %s is not among the enumerated notations\n", value, attr->name, elem->name); ret = 0; } } /* Validity Constraint: Enumeration */ - if (attrDecl->type == XML_ATTRIBUTE_ENUMERATION) { + if (attrDecl->atype == XML_ATTRIBUTE_ENUMERATION) { xmlEnumerationPtr tree = attrDecl->tree; while (tree != NULL) { if (!xmlStrcmp(tree->name, value)) break; @@ -2552,14 +2954,10 @@ xmlValidateOneAttribute(xmlValidCtxtPtr ctxt, xmlDocPtr doc, ret = 0; } - /******** - elemDecl = xmlGetDtdElementDesc(doc->intSubset, elem->name); - if ((elemDecl == NULL) && (doc->extSubset != NULL)) - elemDecl = xmlGetDtdElementDesc(doc->extSubset, elem->name); - if (elemDecl == NULL) { - return(0); - } - ********/ + /* Extra check for the attribute value */ + ret &= xmlValidateAttributeValue2(ctxt, doc, attr->name, + attrDecl->atype, value); + return(ret); } @@ -2586,7 +2984,22 @@ xmlValidateElementTypeExpr(xmlValidCtxtPtr ctxt, xmlNodePtr *child, int ret = 1; if (cont == NULL) return(-1); + DEBUG_VALID_STATE(*child, cont) while (*child != NULL) { + if ((*child)->type == XML_ENTITY_REF_NODE) { + /* + * If there is an entity declared an it's not empty + * Push the current node on the stack and process with the + * entity content. + */ + if (((*child)->children != NULL) && + ((*child)->children->children != NULL)) { + nodeVPush(ctxt, *child); + *child = (*child)->children->children; + } else + *child = (*child)->next; + continue; + } if ((*child)->type == XML_PI_NODE) { *child = (*child)->next; continue; @@ -2600,6 +3013,7 @@ xmlValidateElementTypeExpr(xmlValidCtxtPtr ctxt, xmlNodePtr *child, } break; } + DEBUG_VALID_STATE(*child, cont) switch (cont->type) { case XML_ELEMENT_CONTENT_PCDATA: if (*child == NULL) return(0); @@ -2608,8 +3022,16 @@ xmlValidateElementTypeExpr(xmlValidCtxtPtr ctxt, xmlNodePtr *child, case XML_ELEMENT_CONTENT_ELEMENT: if (*child == NULL) return(0); ret = (!xmlStrcmp((*child)->name, cont->name)); - if (ret == 1) + if (ret == 1) { + while ((*child)->next == NULL) { + if (((*child)->parent != NULL) && + ((*child)->parent->type == XML_ENTITY_DECL)) { + *child = nodeVPop(ctxt); + } else + break; + } *child = (*child)->next; + } return(ret); case XML_ELEMENT_CONTENT_OR: cur = *child; @@ -2666,7 +3088,23 @@ xmlValidateElementTypeElement(xmlValidCtxtPtr ctxt, xmlNodePtr *child, int ret = 1; if (cont == NULL) return(-1); + + DEBUG_VALID_STATE(*child, cont) while (*child != NULL) { + if ((*child)->type == XML_ENTITY_REF_NODE) { + /* + * If there is an entity declared an it's not empty + * Push the current node on the stack and process with the + * entity content. + */ + if (((*child)->children != NULL) && + ((*child)->children->children != NULL)) { + nodeVPush(ctxt, *child); + *child = (*child)->children->children; + } else + *child = (*child)->next; + continue; + } if ((*child)->type == XML_PI_NODE) { *child = (*child)->next; continue; @@ -2680,6 +3118,7 @@ xmlValidateElementTypeElement(xmlValidCtxtPtr ctxt, xmlNodePtr *child, } break; } + DEBUG_VALID_STATE(*child, cont) cur = *child; ret = xmlValidateElementTypeExpr(ctxt, child, cont); if (ret == -1) return(-1); @@ -2690,7 +3129,14 @@ xmlValidateElementTypeElement(xmlValidCtxtPtr ctxt, xmlNodePtr *child, while ((*child != NULL) && (((*child)->type == XML_PI_NODE) || ((*child)->type == XML_COMMENT_NODE))) { - *child = (*child)->next; + while ((*child)->next == NULL) { + if (((*child)->parent != NULL) && + ((*child)->parent->type == XML_ENTITY_REF_NODE)) { + *child = (*child)->parent; + } else + break; + } + *child = (*child)->next; } return(1); } @@ -2722,6 +3168,20 @@ xmlValidateElementTypeElement(xmlValidCtxtPtr ctxt, xmlNodePtr *child, break; } while (*child != NULL) { + if ((*child)->type == XML_ENTITY_REF_NODE) { + /* + * If there is an entity declared an it's not empty + * Push the current node on the stack and process with the + * entity content. + */ + if (((*child)->children != NULL) && + ((*child)->children->children != NULL)) { + nodeVPush(ctxt, *child); + *child = (*child)->children->children; + } else + *child = (*child)->next; + continue; + } if ((*child)->type == XML_PI_NODE) { *child = (*child)->next; continue; @@ -2753,7 +3213,7 @@ xmlSprintfElementChilds(char *buf, xmlNodePtr node, int glob) { if (node == NULL) return; if (glob) strcat(buf, "("); - cur = node->childs; + cur = node->children; while (cur != NULL) { switch (cur->type) { case XML_ELEMENT_NODE: @@ -2780,7 +3240,11 @@ xmlSprintfElementChilds(char *buf, xmlNodePtr node, int glob) { break; case XML_ENTITY_NODE: case XML_PI_NODE: + case XML_DTD_NODE: case XML_COMMENT_NODE: + case XML_ELEMENT_DECL: + case XML_ATTRIBUTE_DECL: + case XML_ENTITY_DECL: break; } cur = cur->next; @@ -2828,7 +3292,7 @@ xmlValidateOneElement(xmlValidCtxtPtr ctxt, xmlDocPtr doc, "Attribute element not expected here\n"); return(0); case XML_TEXT_NODE: - if (elem->childs != NULL) { + if (elem->children != NULL) { VERROR(ctxt->userData, "Text element has childs !\n"); return(0); } @@ -2893,9 +3357,9 @@ xmlValidateOneElement(xmlValidCtxtPtr ctxt, xmlDocPtr doc, } /* Check taht the element content matches the definition */ - switch (elemDecl->type) { + switch (elemDecl->etype) { case XML_ELEMENT_TYPE_EMPTY: - if (elem->childs != NULL) { + if (elem->children != NULL) { VERROR(ctxt->userData, "Element %s was declared EMPTY this one has content\n", elem->name); @@ -2907,7 +3371,7 @@ xmlValidateOneElement(xmlValidCtxtPtr ctxt, xmlDocPtr doc, break; case XML_ELEMENT_TYPE_MIXED: /* Hum, this start to get messy */ - child = elem->childs; + child = elem->children; while (child != NULL) { if (child->type == XML_ELEMENT_NODE) { name = child->name; @@ -2939,7 +3403,7 @@ xmlValidateOneElement(xmlValidCtxtPtr ctxt, xmlDocPtr doc, } break; case XML_ELEMENT_TYPE_ELEMENT: - child = elem->childs; + child = elem->children; cont = elemDecl->content; ret = xmlValidateElementTypeElement(ctxt, &child, cont); if ((ret == 0) || (child != NULL)) { @@ -3020,7 +3484,7 @@ xmlValidateOneElement(xmlValidCtxtPtr ctxt, xmlDocPtr doc, } } found: - attr = attr->next; + attr = attr->nexth; } return(ret); } @@ -3091,13 +3555,13 @@ xmlValidateElement(xmlValidCtxtPtr ctxt, xmlDocPtr doc, xmlNodePtr elem) { ret &= xmlValidateOneElement(ctxt, doc, elem); attr = elem->properties; while(attr != NULL) { - value = xmlNodeListGetString(doc, attr->val, 0); + value = xmlNodeListGetString(doc, attr->children, 0); ret &= xmlValidateOneAttribute(ctxt, doc, elem, attr, value); if (value != NULL) xmlFree(value); attr= attr->next; } - child = elem->childs; + child = elem->children; while (child != NULL) { ret &= xmlValidateElement(ctxt, doc, child); child = child->next; @@ -3132,17 +3596,50 @@ xmlValidateDocumentFinal(xmlValidCtxtPtr ctxt, xmlDocPtr doc) { } /* - * Get the refs table + * Check all the NOTATION/NOTATIONS attributes + */ + /* + * Check all the ENTITY/ENTITIES attributes definition for validity + */ + /* + * Check all the IDREF/IDREFS attributes definition for validity */ table = doc->refs; if (table != NULL) { for (i = 0; i < table->nb_refs; i++) { - id = xmlGetID(doc, table->table[i]->value); - if (id == NULL) { - VERROR(ctxt->userData, - "IDREF attribute %s reference an unknown ID '%s'\n", - table->table[i]->attr->name, table->table[i]->value); - ret = 0; + if (table->table[i]->attr->atype == XML_ATTRIBUTE_IDREF) { + id = xmlGetID(doc, table->table[i]->value); + if (id == NULL) { + VERROR(ctxt->userData, + "IDREF attribute %s reference an unknown ID \"%s\"\n", + table->table[i]->attr->name, table->table[i]->value); + ret = 0; + } + } else if (table->table[i]->attr->atype == XML_ATTRIBUTE_IDREFS) { + xmlChar *dup, *name = NULL, *cur, save; + + dup = xmlStrdup(table->table[i]->value); + if (dup == NULL) + return(0); + cur = dup; + while (*cur != 0) { + name = cur; + while ((*cur != 0) && (!IS_BLANK(*cur))) cur++; + save = *cur; + *cur = 0; + id = xmlGetID(doc, name); + if (id == NULL) { + VERROR(ctxt->userData, + "IDREFS attribute %s reference an unknown ID \"%s\"\n", + table->table[i]->attr->name, name); + ret = 0; + } + if (save == 0) + break; + *cur = save; + while (IS_BLANK(*cur)) cur++; + } + xmlFree(dup); } } } @@ -3184,6 +3681,102 @@ xmlValidateDtd(xmlValidCtxtPtr ctxt, xmlDocPtr doc, xmlDtdPtr dtd) { return(ret); } +/** + * xmlValidateDtdFinal: + * @ctxt: the validation context + * @doc: a document instance + * + * Does the final step for the dtds validation once all the + * subsets have been parsed + * + * basically it does the following checks described by the XML Rec + * - check that ENTITY and ENTITIES type attributes default or + * possible values matches one of the defined entities. + * - check that NOTATION type attributes default or + * possible values matches one of the defined notations. + * + * returns 1 if valid or 0 otherwise + */ + +int +xmlValidateDtdFinal(xmlValidCtxtPtr ctxt, xmlDocPtr doc) { + int ret = 1, i; + xmlDtdPtr dtd; + xmlAttributeTablePtr table; + xmlAttributePtr cur; + + if (doc == NULL) return(0); + if ((doc->intSubset == NULL) && (doc->extSubset == NULL)) + return(0); + dtd = doc->intSubset; + if ((dtd != NULL) && (dtd->attributes != NULL)) { + table = dtd->attributes; + + for (i = 0;i < table->nb_attributes;i++) { + cur = table->table[i]; + switch (cur->atype) { + case XML_ATTRIBUTE_CDATA: + case XML_ATTRIBUTE_ID: + case XML_ATTRIBUTE_IDREF : + case XML_ATTRIBUTE_IDREFS: + case XML_ATTRIBUTE_NMTOKEN: + case XML_ATTRIBUTE_NMTOKENS: + case XML_ATTRIBUTE_ENUMERATION: + break; + case XML_ATTRIBUTE_ENTITY: + case XML_ATTRIBUTE_ENTITIES: + case XML_ATTRIBUTE_NOTATION: + if (cur->defaultValue != NULL) { + ret &= xmlValidateAttributeValue2(ctxt, doc, cur->name, + cur->atype, cur->defaultValue); + } + if (cur->tree != NULL) { + xmlEnumerationPtr tree = cur->tree; + while (tree != NULL) { + ret &= xmlValidateAttributeValue2(ctxt, doc, + cur->name, cur->atype, tree->name); + tree = tree->next; + } + } + } + } + } + dtd = doc->extSubset; + if ((dtd != NULL) && (dtd->attributes != NULL)) { + table = dtd->attributes; + + for (i = 0;i < table->nb_attributes;i++) { + cur = table->table[i]; + switch (cur->atype) { + case XML_ATTRIBUTE_CDATA: + case XML_ATTRIBUTE_ID: + case XML_ATTRIBUTE_IDREF : + case XML_ATTRIBUTE_IDREFS: + case XML_ATTRIBUTE_NMTOKEN: + case XML_ATTRIBUTE_NMTOKENS: + case XML_ATTRIBUTE_ENUMERATION: + break; + case XML_ATTRIBUTE_ENTITY: + case XML_ATTRIBUTE_ENTITIES: + case XML_ATTRIBUTE_NOTATION: + if (cur->defaultValue != NULL) { + ret &= xmlValidateAttributeValue2(ctxt, doc, cur->name, + cur->atype, cur->defaultValue); + } + if (cur->tree != NULL) { + xmlEnumerationPtr tree = cur->tree; + while (tree != NULL) { + ret &= xmlValidateAttributeValue2(ctxt, doc, + cur->name, cur->atype, tree->name); + tree = tree->next; + } + } + } + } + } + return(ret); +} + /** * xmlValidateDocument: * @ctxt: the validation context @@ -3212,21 +3805,22 @@ xmlValidateDocument(xmlValidCtxtPtr ctxt, xmlDocPtr doc) { if (doc->extSubset == NULL) { if (doc->intSubset->SystemID != NULL) { VERROR(ctxt->userData, - "Could not load the external subset '%s'\n", + "Could not load the external subset \"%s\"\n", doc->intSubset->SystemID); } else { VERROR(ctxt->userData, - "Could not load the external subset '%s'\n", + "Could not load the external subset \"%s\"\n", doc->intSubset->ExternalID); } return(0); } } + ret = xmlValidateDtdFinal(ctxt, doc); if (!xmlValidateRoot(ctxt, doc)) return(0); root = xmlDocGetRootElement(doc); - ret = xmlValidateElement(ctxt, doc, root); + ret &= xmlValidateElement(ctxt, doc, root); ret &= xmlValidateDocumentFinal(ctxt, doc); return(ret); } @@ -3351,7 +3945,7 @@ xmlValidGetValidElements(xmlNode *prev, xmlNode *next, const xmlChar **list, */ prev_next = prev ? prev->next : NULL; next_prev = next ? next->prev : NULL; - parent_childs = parent->childs; + parent_childs = parent->children; parent_last = parent->last; /* @@ -3364,7 +3958,7 @@ xmlValidGetValidElements(xmlNode *prev, xmlNode *next, const xmlChar **list, test_node->next = next; if (prev) prev->next = test_node; - else parent->childs = test_node; + else parent->children = test_node; if (next) next->prev = test_node; else parent->last = test_node; @@ -3393,7 +3987,7 @@ xmlValidGetValidElements(xmlNode *prev, xmlNode *next, const xmlChar **list, */ if (prev) prev->next = prev_next; if (next) next->prev = next_prev; - parent->childs = parent_childs; + parent->children = parent_childs; parent->last = parent_last; return(nb_valid_elements); diff --git a/valid.h b/valid.h index 8c86b17b..d211207e 100644 --- a/valid.h +++ b/valid.h @@ -29,6 +29,14 @@ struct _xmlValidCtxt { void *userData; /* user specific data block */ xmlValidityErrorFunc error; /* the callback in case of errors */ xmlValidityWarningFunc warning; /* the callback in case of warning */ + + /* Node analysis stack used when validating within entities */ + xmlNodePtr node; /* Current parsed Node */ + int nodeNr; /* Depth of the parsing stack */ + int nodeMax; /* Max depth of the parsing stack */ + xmlNodePtr *nodeTab; /* array of nodes */ + + int finishDtd; /* finished validating the Dtd ? */ }; /* @@ -114,6 +122,8 @@ xmlNotationPtr xmlAddNotationDecl (xmlValidCtxtPtr ctxt, const xmlChar *SystemID); xmlNotationTablePtr xmlCopyNotationTable(xmlNotationTablePtr table); void xmlFreeNotationTable(xmlNotationTablePtr table); +void xmlDumpNotationDecl (xmlBufferPtr buf, + xmlNotationPtr nota); void xmlDumpNotationTable(xmlBufferPtr buf, xmlNotationTablePtr table); @@ -122,6 +132,9 @@ xmlElementContentPtr xmlNewElementContent (xmlChar *name, xmlElementContentType type); xmlElementContentPtr xmlCopyElementContent(xmlElementContentPtr content); void xmlFreeElementContent(xmlElementContentPtr cur); +void xmlSprintfElementContent(char *buf, + xmlElementContentPtr content, + int glob); /* Element */ xmlElementPtr xmlAddElementDecl (xmlValidCtxtPtr ctxt, @@ -133,6 +146,8 @@ xmlElementTablePtr xmlCopyElementTable (xmlElementTablePtr table); void xmlFreeElementTable (xmlElementTablePtr table); void xmlDumpElementTable (xmlBufferPtr buf, xmlElementTablePtr table); +void xmlDumpElementDecl (xmlBufferPtr buf, + xmlElementPtr elem); /* Enumeration */ xmlEnumerationPtr xmlCreateEnumeration (xmlChar *name); @@ -144,6 +159,7 @@ xmlAttributePtr xmlAddAttributeDecl (xmlValidCtxtPtr ctxt, xmlDtdPtr dtd, const xmlChar *elem, const xmlChar *name, + const xmlChar *prefix, xmlAttributeType type, xmlAttributeDefault def, const xmlChar *defaultValue, @@ -152,6 +168,8 @@ xmlAttributeTablePtr xmlCopyAttributeTable (xmlAttributeTablePtr table); void xmlFreeAttributeTable (xmlAttributeTablePtr table); void xmlDumpAttributeTable (xmlBufferPtr buf, xmlAttributeTablePtr table); +void xmlDumpAttributeDecl (xmlBufferPtr buf, + xmlAttributePtr attr); /* IDs */ xmlIDPtr xmlAddID (xmlValidCtxtPtr ctxt, @@ -188,6 +206,10 @@ int xmlValidateRoot (xmlValidCtxtPtr ctxt, int xmlValidateElementDecl (xmlValidCtxtPtr ctxt, xmlDocPtr doc, xmlElementPtr elem); +xmlChar * xmlValidNormalizeAttributeValue(xmlDocPtr doc, + xmlNodePtr elem, + const xmlChar *name, + const xmlChar *value); int xmlValidateAttributeDecl(xmlValidCtxtPtr ctxt, xmlDocPtr doc, xmlAttributePtr attr); @@ -199,6 +221,8 @@ int xmlValidateNotationDecl (xmlValidCtxtPtr ctxt, int xmlValidateDtd (xmlValidCtxtPtr ctxt, xmlDocPtr doc, xmlDtdPtr dtd); +int xmlValidateDtdFinal (xmlValidCtxtPtr ctxt, + xmlDocPtr doc); int xmlValidateDocument (xmlValidCtxtPtr ctxt, xmlDocPtr doc); int xmlValidateElement (xmlValidCtxtPtr ctxt, diff --git a/xml-error.h b/xml-error.h index d7e09f47..709dfa20 100644 --- a/xml-error.h +++ b/xml-error.h @@ -115,8 +115,22 @@ typedef enum { XML_ERR_ENCODING_NAME, /* 80 */ - XML_ERR_HYPHEN_IN_COMMENT /* 81 */ + XML_ERR_HYPHEN_IN_COMMENT, /* 81 */ + XML_ERR_INVALID_ENCODING, /* 82 */ + + XML_ERR_EXT_ENTITY_STANDALONE, /* 83 */ + + XML_ERR_CONDSEC_INVALID, /* 84 */ + + XML_ERR_VALUE_REQUIRED, /* 85 */ + + XML_ERR_NOT_WELL_BALANCED, /* 86 */ + XML_ERR_EXTRA_CONTENT, /* 87 */ + XML_ERR_ENTITY_CHAR_ERROR, /* 88 */ + XML_ERR_ENTITY_PE_INTERNAL, /* 88 */ + XML_ERR_ENTITY_LOOP, /* 89 */ + XML_ERR_ENTITY_BOUNDARY /* 90 */ }xmlParserErrors; void xmlParserError (void *ctx, diff --git a/xmlIO.c b/xmlIO.c index aeee1abc..65db3fe4 100644 --- a/xmlIO.c +++ b/xmlIO.c @@ -118,6 +118,7 @@ xmlFreeParserInputBuffer(xmlParserInputBufferPtr in) { * If filename is "-' then we use stdin as the input. * Automatic support for ZLIB/Compress compressed document is provided * by default if found at compile-time. + * Do an encoding check if enc == XML_CHAR_ENCODING_NONE * * Returns the new parser input or NULL */ @@ -201,13 +202,10 @@ xmlParserInputBufferCreateFilename(const char *filename, xmlCharEncoding enc) { } #endif } - /* - * TODO : get the 4 first bytes and decode the charset - * if enc == XML_CHAR_ENCODING_NONE - * plug some encoding conversion routines here. !!! - * enc = xmlDetectCharEncoding(buffer); - */ + /* + * Allocate the Input buffer front-end. + */ ret = xmlAllocParserInputBuffer(enc); if (ret != NULL) { #ifdef HAVE_ZLIB_H @@ -218,7 +216,6 @@ xmlParserInputBufferCreateFilename(const char *filename, xmlCharEncoding enc) { ret->httpIO = httpIO; ret->ftpIO = ftpIO; } - xmlParserInputBufferRead(ret, 4); return(ret); } @@ -289,19 +286,30 @@ xmlParserInputBufferPush(xmlParserInputBufferPtr in, int len, const char *buf) { if (len < 0) return(0); if (in->encoder != NULL) { xmlChar *buffer; + int processed = len; buffer = (xmlChar *) xmlMalloc((len + 1) * 2 * sizeof(xmlChar)); if (buffer == NULL) { fprintf(stderr, "xmlParserInputBufferGrow : out of memory !\n"); - xmlFree(buffer); return(-1); } nbchars = in->encoder->input(buffer, (len + 1) * 2 * sizeof(xmlChar), - (xmlChar *) buf, len); + (xmlChar *) buf, &processed); /* * TODO : we really need to have something atomic or the * encoder must report the number of bytes read */ + if (nbchars < 0) { + fprintf(stderr, "xmlParserInputBufferPush: encoder error\n"); + xmlFree(buffer); + return(-1); + } + if (processed != len) { + fprintf(stderr, + "TODO xmlParserInputBufferPush: processed != len\n"); + xmlFree(buffer); + return(-1); + } buffer[nbchars] = 0; xmlBufferAdd(in->buffer, (xmlChar *) buffer, nbchars); xmlFree(buffer); @@ -382,6 +390,7 @@ xmlParserInputBufferGrow(xmlParserInputBufferPtr in, int len) { } if (in->encoder != NULL) { xmlChar *buf; + int wrote = res; buf = (xmlChar *) xmlMalloc((res + 1) * 2 * sizeof(xmlChar)); if (buf == NULL) { @@ -390,10 +399,24 @@ xmlParserInputBufferGrow(xmlParserInputBufferPtr in, int len) { return(-1); } nbchars = in->encoder->input(buf, (res + 1) * 2 * sizeof(xmlChar), - BAD_CAST buffer, res); + BAD_CAST buffer, &wrote); buf[nbchars] = 0; xmlBufferAdd(in->buffer, (xmlChar *) buf, nbchars); xmlFree(buf); + + /* + * Check that the encoder was able to process the full input + */ + if (wrote != res) { + fprintf(stderr, + "TODO : xmlParserInputBufferGrow wrote %d != res %d\n", + wrote, res); + /* + * TODO !!! + * Need to keep the unprocessed input in a buffer in->unprocessed + */ + } + } else { nbchars = res; buffer[nbchars] = 0; diff --git a/xmlmemory.h b/xmlmemory.h index 64477a1c..11121fb5 100644 --- a/xmlmemory.h +++ b/xmlmemory.h @@ -8,7 +8,7 @@ #ifndef _DEBUG_MEMORY_ALLOC_ #define _DEBUG_MEMORY_ALLOC_ -#define NO_DEBUG_MEMORY +/* #define NO_DEBUG_MEMORY */ #ifdef NO_DEBUG_MEMORY #ifdef HAVE_MALLOC_H diff --git a/xpath.c b/xpath.c index b2b3c893..398972f7 100644 --- a/xpath.c +++ b/xpath.c @@ -213,9 +213,9 @@ PUSH_AND_POP(xmlXPathObjectPtr, value) * Dirty macros, i.e. one need to make assumption on the context to use them * * CUR_PTR return the current pointer to the xmlChar to be parsed. - * CUR returns the current xmlChar value, i.e. a 8 bit value if compiled - * in ISO-Latin or UTF-8, and the current 16 bit value if compiled - * in UNICODE mode. This should be used internally by the parser + * CUR returns the current xmlChar value, i.e. a 8 bit value + * in ISO-Latin or UTF-8. + * This should be used internally by the parser * only to compare to ASCII values otherwise it would break when * running with UTF-8 encoding. * NXT(n) returns the n'th next xmlChar. Same as CUR is should be used only @@ -237,11 +237,8 @@ PUSH_AND_POP(xmlXPathObjectPtr, value) #define SKIP_BLANKS \ while (IS_BLANK(*(ctxt->cur))) NEXT -#ifndef USE_UTF_8 #define CURRENT (*ctxt->cur) #define NEXT ((*ctxt->cur) ? ctxt->cur++: ctxt->cur) -#else -#endif /************************************************************************ * * @@ -877,7 +874,7 @@ xmlXPathFreeContext(xmlXPathContextPtr ctxt) { fprintf(xmlXPathDebug, "%s:%d Internal error: no document\n", \ __FILE__, __LINE__); \ } \ - if (ctxt->doc->root == NULL) { \ + if (ctxt->doc->children == NULL) { \ fprintf(xmlXPathDebug, \ "%s:%d Internal error: document without root\n", \ __FILE__, __LINE__); \ @@ -1496,14 +1493,18 @@ xmlXPathNextChild(xmlXPathParserContextPtr ctxt, xmlNodePtr cur) { case XML_PI_NODE: case XML_COMMENT_NODE: case XML_NOTATION_NODE: - return(ctxt->context->node->childs); - case XML_ATTRIBUTE_NODE: - return(NULL); + case XML_DTD_NODE: + return(ctxt->context->node->children); case XML_DOCUMENT_NODE: case XML_DOCUMENT_TYPE_NODE: case XML_DOCUMENT_FRAG_NODE: case XML_HTML_DOCUMENT_NODE: - return(((xmlDocPtr) ctxt->context->node)->root); + return(((xmlDocPtr) ctxt->context->node)->children); + case XML_ELEMENT_DECL: + case XML_ATTRIBUTE_DECL: + case XML_ENTITY_DECL: + case XML_ATTRIBUTE_NODE: + return(NULL); } return(NULL); } @@ -1533,11 +1534,11 @@ xmlXPathNextDescendant(xmlXPathParserContextPtr ctxt, xmlNodePtr cur) { return(NULL); if (ctxt->context->node == (xmlNodePtr) ctxt->context->doc) - return(ctxt->context->doc->root); - return(ctxt->context->node->childs); + return(ctxt->context->doc->children); + return(ctxt->context->node->children); } - if (cur->childs != NULL) return(cur->childs); + if (cur->children != NULL) return(cur->children); if (cur->next != NULL) return(cur->next); do { @@ -1606,13 +1607,17 @@ xmlXPathNextParent(xmlXPathParserContextPtr ctxt, xmlNodePtr cur) { case XML_PI_NODE: case XML_COMMENT_NODE: case XML_NOTATION_NODE: + case XML_DTD_NODE: + case XML_ELEMENT_DECL: + case XML_ATTRIBUTE_DECL: + case XML_ENTITY_DECL: if (ctxt->context->node->parent == NULL) return((xmlNodePtr) ctxt->context->doc); return(ctxt->context->node->parent); case XML_ATTRIBUTE_NODE: { xmlAttrPtr att = (xmlAttrPtr) ctxt->context->node; - return(att->node); + return(att->parent); } case XML_DOCUMENT_NODE: case XML_DOCUMENT_TYPE_NODE: @@ -1655,6 +1660,10 @@ xmlXPathNextAncestor(xmlXPathParserContextPtr ctxt, xmlNodePtr cur) { case XML_ENTITY_NODE: case XML_PI_NODE: case XML_COMMENT_NODE: + case XML_DTD_NODE: + case XML_ELEMENT_DECL: + case XML_ATTRIBUTE_DECL: + case XML_ENTITY_DECL: case XML_NOTATION_NODE: if (ctxt->context->node->parent == NULL) return((xmlNodePtr) ctxt->context->doc); @@ -1662,7 +1671,7 @@ xmlXPathNextAncestor(xmlXPathParserContextPtr ctxt, xmlNodePtr cur) { case XML_ATTRIBUTE_NODE: { xmlAttrPtr cur = (xmlAttrPtr) ctxt->context->node; - return(cur->node); + return(cur->parent); } case XML_DOCUMENT_NODE: case XML_DOCUMENT_TYPE_NODE: @@ -1672,7 +1681,7 @@ xmlXPathNextAncestor(xmlXPathParserContextPtr ctxt, xmlNodePtr cur) { } return(NULL); } - if (cur == ctxt->context->doc->root) + if (cur == ctxt->context->doc->children) return((xmlNodePtr) ctxt->context->doc); if (cur == (xmlNodePtr) ctxt->context->doc) return(NULL); @@ -1685,11 +1694,15 @@ xmlXPathNextAncestor(xmlXPathParserContextPtr ctxt, xmlNodePtr cur) { case XML_PI_NODE: case XML_COMMENT_NODE: case XML_NOTATION_NODE: + case XML_DTD_NODE: + case XML_ELEMENT_DECL: + case XML_ATTRIBUTE_DECL: + case XML_ENTITY_DECL: return(cur->parent); case XML_ATTRIBUTE_NODE: { xmlAttrPtr att = (xmlAttrPtr) ctxt->context->node; - return(att->node); + return(att->parent); } case XML_DOCUMENT_NODE: case XML_DOCUMENT_TYPE_NODE: @@ -1780,13 +1793,13 @@ xmlXPathNextFollowing(xmlXPathParserContextPtr ctxt, xmlNodePtr cur) { return(NULL); if (cur == NULL) return(ctxt->context->node->next);; /* !!!!!!!!! */ - if (cur->childs != NULL) return(cur->childs); + if (cur->children != NULL) return(cur->children); if (cur->next != NULL) return(cur->next); do { cur = cur->parent; if (cur == NULL) return(NULL); - if (cur == ctxt->context->doc->root) return(NULL); + if (cur == ctxt->context->doc->children) return(NULL); if (cur->next != NULL) { cur = cur->next; return(cur); @@ -1820,7 +1833,7 @@ xmlXPathNextPreceding(xmlXPathParserContextPtr ctxt, xmlNodePtr cur) { do { cur = cur->parent; if (cur == NULL) return(NULL); - if (cur == ctxt->context->doc->root) return(NULL); + if (cur == ctxt->context->doc->children) return(NULL); if (cur->prev != NULL) { cur = cur->prev; return(cur); @@ -2278,7 +2291,7 @@ xmlXPathIdFunction(xmlXPathParserContextPtr ctxt, int nargs) { ID = xmlStrndup(tokens, cur - tokens); attr = xmlGetID(ctxt->context->doc, ID); if (attr != NULL) { - elem = attr->node; + elem = attr->parent; xmlXPathNodeSetAdd(ret->nodesetval, elem); } if (ID != NULL) @@ -3677,6 +3690,8 @@ xmlXPathEvalPathExpr(xmlXPathParserContextPtr ctxt) { if (name != NULL) xmlFree(name); } + if (ctxt->context->nodelist != NULL) + valuePush(ctxt, xmlXPathNewNodeSetList(ctxt->context->nodelist)); } /**