diff --git a/ChangeLog b/ChangeLog index 2af9bb9a..aa04c548 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,17 @@ +Thu Jan 13 11:49:11 CET 2000 Daniel Veillard + + * tree.c : restored xmlNewGlobalNs since this seems used by + a lot of existing code :-(, fixed a bug in xmlNewNs + * nanohttp.c: fixed a problem with INCLUDE_WINSOCK + * HTMLparser.c, parser.c, entities.c, valid.c : removed all calls + to exit() from the library code. + * xpath.c, parser.c: removed bugs or unused code detected by + Windows compilers + * parser.c: started adding interfaces for parsing well balanced + XML fragments + * configure.in: releasing 1.8.4 + * doc/* : rebuilt the docs + Sun Jan 9 23:03:20 CET 2000 Daniel Veillard * tree.[ch] : added xmlNewDocFragment() for DOM diff --git a/HTMLparser.c b/HTMLparser.c index a5b16575..a1fdac5c 100644 --- a/HTMLparser.c +++ b/HTMLparser.c @@ -69,7 +69,7 @@ scope int html##name##Push(htmlParserCtxtPtr ctxt, type value) { \ ctxt->name##Max * sizeof(ctxt->name##Tab[0])); \ if (ctxt->name##Tab == NULL) { \ fprintf(stderr, "realloc failed !\n"); \ - exit(1); \ + return(0); \ } \ } \ ctxt->name##Tab[ctxt->name##Nr] = value; \ @@ -854,7 +854,7 @@ htmlEntityDesc html40EntitiesTable[] = { buffer = (xmlChar *) xmlRealloc(buffer, buffer##_size * sizeof(xmlChar)); \ if (buffer == NULL) { \ perror("realloc failed"); \ - exit(1); \ + return(NULL); \ } \ } diff --git a/SAXresult/ns4 b/SAXresult/ns4 index 47b58d89..674b9a38 100644 --- a/SAXresult/ns4 +++ b/SAXresult/ns4 @@ -1,60 +1,5 @@ SAX.setDocumentLocator() SAX.startDocument() -SAX.processingInstruction(xml-stylesheet, type="text/xml" -href="#style1") -SAX.internalSubset(doc, (null), doc.dtd) -SAX.startElement(doc) -SAX.characters( -, 1) -SAX.startElement(head) -SAX.characters( -, 1) -SAX.startElement(xsl:stylesheet, id='style1', version='1.0', xmlns:xsl='http://www.w3.org/1999/XSL/Transform', xmlns:fo='http://www.w3.org/1999/XSL/Format') -SAX.characters( -, 1) -SAX.startElement(xsl:import, href='doc.xsl') -SAX.endElement(xsl:import) -SAX.characters( -, 1) -SAX.startElement(xsl:template, match='id('foo')') -SAX.characters( -, 1) -SAX.startElement(fo:block, font-weight='bold') -SAX.startElement(xsl:apply-templates) -SAX.endElement(xsl:apply-templates) -SAX.endElement(fo:block) -SAX.characters( -, 1) -SAX.endElement(xsl:template) -SAX.characters( -, 1) -SAX.startElement(xsl:template, match='xsl:stylesheet') -SAX.characters( -, 1) -SAX.comment( ignore ) -SAX.characters( -, 1) -SAX.endElement(xsl:template) -SAX.characters( -, 1) -SAX.endElement(xsl:stylesheet) -SAX.characters( -, 1) -SAX.endElement(head) -SAX.characters( -, 1) -SAX.startElement(body) -SAX.characters( -, 1) -SAX.startElement(para, id='foo') -SAX.characters( -... -, 5) -SAX.endElement(para) -SAX.characters( -, 1) -SAX.endElement(body) -SAX.characters( -, 1) -SAX.endElement(doc) +SAX.startElement(diagram, testattr='test', xml:lang='en', xml:link='simple', xml:space='preserve') +SAX.endElement(diagram) SAX.endDocument() diff --git a/configure.in b/configure.in index 79dfd5dd..2f4d9ce3 100644 --- a/configure.in +++ b/configure.in @@ -5,7 +5,7 @@ AM_CONFIG_HEADER(config.h) LIBXML_MAJOR_VERSION=1 LIBXML_MINOR_VERSION=8 -LIBXML_MICRO_VERSION=3 +LIBXML_MICRO_VERSION=4 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 diff --git a/doc/html/gnome-xml-entities.html b/doc/html/gnome-xml-entities.html index 4b8005cb..bfb94475 100644 --- a/doc/html/gnome-xml-entities.html +++ b/doc/html/gnome-xml-entities.html @@ -115,7 +115,7 @@ SIZE="3" >

Name

Synopsis

Description

Details

Name

Synopsis

Description

Details

Name

Synopsis

Description

Details

Name

Synopsis

Description

Details

Name

Synopsis

Description

Details

xmlNodePtr xmlNewDocFragment (xmlDocPtr doc); +xmlNodePtr xmlDocGetRootElement (

Description

Details

Creation of a Namespace, the old way using PI and without scoping DEPRECATED !!! -Will be removed at next major release !

xmlNewDocFragment ()

xmlNodePtr  xmlNewDocFragment               (xmlDocPtr doc);

Creation of a new Fragment node.

doc : the document owning the fragment
Returns :a pointer to the new node object.

Name

Synopsis

Description

Details

Name

Synopsis

Description

Details

Name

Synopsis

xmlMalloc (size_t size); +> (int size); void* xmlRealloc (void *ptr, - size_t size); + int size); char* xmlMemStrdup

Description

Details

  the memory block pointer

void*       xmlMalloc                       (size_t size);
void* xmlMalloc (int size);  an int specifying the size in byte to allocate.

void*       xmlRealloc                      (void *ptr,
-                                             size_t size);
  the initial memory block pointer  an int specifying the size in byte to allocate.

Name

Synopsis

Description

Details

+ diff --git a/doc/xml.html b/doc/xml.html index 0bc1cbcb..a9d91da6 100644 --- a/doc/xml.html +++ b/doc/xml.html @@ -23,7 +23,9 @@
  • The SAX interface
  • The XML library interfaces

    • working on HTML and XML links recognition layers, get in touch with me if you want to test those.
      • +
    • adding APIs to parse a well balanced chunk of XML (production [43] content of the XML + spec)
      • +
    + +

    1.8.4: Jan 13 2000

    +
      +
    • bug fixes, reintroduced xmlNewGlobalNs(), fixed xmlNewNs()
      • +
    • all exit() call should have been removed from libxml
      • +
    • fixed a problem with INCLUDE_WINSOCK on WIN32 platform
      • +
    • added newDocFragment()

    1.8.3: Jan 5 2000

    @@ -283,8 +312,7 @@ standalone=true ATTRIBUTE prop2 ENTITY_REF TEXT - content= too - ELEMENT head + content= linux too ELEMENT title TEXT content=Welcome to Gnome @@ -374,7 +402,11 @@ required, but as a separated set of documents. The interfaces of the XML library are by principle low level, there is nearly zero abstration. Those interested in a higher level API should look at DOM.

    -

    Invoking the parser

    +

    The parser interfaces for XML are +separated from the HTML parser ones, +let's have a look at how it can be called:

    + +

    Invoking the parser : the pull way

    Usually, the first thing to do is to read an XML input, the parser accepts to parse both memory mapped documents or direct files. The functions are @@ -393,10 +425,56 @@ defined in "parser.h":

    This returns a pointer to the document structure (or NULL in case of failure).

    +

    Invoking the parser: the push way

    + +

    In order for the application to keep the control when the document is been +fetched (common for GUI based programs) the libxml, as of version 1.8.3 +provides a push interface too, here are the interfaces:

    +
    xmlParserCtxtPtr xmlCreatePushParserCtxt(xmlSAXHandlerPtr sax,
+                                         void *user_data,
+                                         const char *chunk,
+                                         int size,
+                                         const char *filename);
+int              xmlParseChunk          (xmlParserCtxtPtr ctxt,
+                                         const char *chunk,
+                                         int size,
+                                         int terminate);
    + +

    and here is a simple use example:

    +
                FILE *f;
+
+            f = fopen(filename, "r");
+            if (f != NULL) {
+                int res, size = 1024;
+                char chars[1024];
+                xmlParserCtxtPtr ctxt;
+
+                res = fread(chars, 1, 4, f);
+                if (res > 0) {
+                    ctxt = xmlCreatePushParserCtxt(NULL, NULL,
+                                chars, res, filename);
+                    while ((res = fread(chars, 1, size, f)) > 0) {
+                        xmlParseChunk(ctxt, chars, res, 0);
+                    }
+                    xmlParseChunk(ctxt, chars, 0, 1);
+                    doc = ctxt->myDoc;
+                    xmlFreeParserCtxt(ctxt);
+                }
+            }
    + +

    Also note that the HTML parser embedded into libxml also have a push +interface they are just prefixed by "html" instead of "xml"

    + +

    Invoking the parser: the SAX interface

    +

    A couple of comments can be made, first this mean that the parser is memory-hungry, first to load the document in memory, second to build the tree. -Reading a document without building the tree will be possible in the future by -pluggin the code to the SAX interface (see SAX.c).

    +Reading a document without building the tree is possible using the SAX +interfaces (see SAX.h and James +Henstridge documentation), not also that the push interface can be limited +to SAX, just use the two first arguments of +xmlCreatePushParserCtxt().

    Building a tree from scratch

    @@ -410,7 +488,7 @@ example used before:

    doc = xmlNewDoc("1.0"); doc->root = xmlNewDocNode(doc, NULL, "EXAMPLE", NULL); xmlSetProp(doc->root, "prop1", "gnome is great"); - xmlSetProp(doc->root, "prop2", "&linux; too"); + xmlSetProp(doc->root, "prop2", "& linux too"); tree = xmlNewChild(doc->root, NULL, "head", NULL); subtree = xmlNewChild(tree, NULL, "title", "Welcome to Gnome"); tree = xmlNewChild(doc->root, NULL, "chapter", NULL); @@ -423,11 +501,12 @@ example used before:

    Traversing the tree

    -

    Basically by including "tree.h" your code has access to the internal -structure of all the element of the tree. The names should be somewhat simple -like parent, childs, next, -prev, properties, etc... For example still -with the previous example:

    +

    Basically by including "tree.h" your code +has access to the internal structure of all the element of the tree. The names +should be somewhat simple like parent, +childs, next, prev, +properties, etc... For example still with the previous +example:

    doc->root->childs->childs

    points to the title element,

    @@ -435,10 +514,6 @@ with the previous example:

    points to the text node containing the chapter titlle "The Linux adventure" and

    -
    doc->root->properties->next->val
    - -

    points to the entity reference containing the value of "&linux" at the -beginning of the second attribute of the root element "EXAMPLE".

    NOTE: XML allows PIs and comments to be present before the document root, so doc->root may point to an element which @@ -447,7 +522,8 @@ is not the document Root Element, a function

    Modifying the tree

    -

    functions are provided to read and write the document content:

    +

    functions are provided to read and write the document content, here is an +excerpt from the tree API:

    xmlAttrPtr xmlSetProp(xmlNodePtr node, const xmlChar *name, const xmlChar *value);
    @@ -915,6 +991,6 @@ base under gnome-xml/example

    Daniel Veillard

    -

    $Id: xml.html,v 1.19 2000/01/03 17:30:45 veillard Exp $

    +

    $Id: xml.html,v 1.20 2000/01/05 19:54:23 veillard Exp $

    diff --git a/entities.c b/entities.c index 027acd05..d6580cfe 100644 --- a/entities.c +++ b/entities.c @@ -388,13 +388,14 @@ xmlGetDocEntity(xmlDocPtr doc, const xmlChar *name) { static int buffer_size = 0; static xmlChar *buffer = NULL; -void growBuffer(void) { +int growBuffer(void) { buffer_size *= 2; buffer = (xmlChar *) xmlRealloc(buffer, buffer_size * sizeof(xmlChar)); if (buffer == NULL) { perror("realloc failed"); - exit(1); + return(-1); } + return(0); } @@ -437,7 +438,7 @@ xmlEncodeEntities(xmlDocPtr doc, const xmlChar *input) { buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar)); if (buffer == NULL) { perror("malloc failed"); - exit(1); + return(NULL); } out = buffer; } @@ -530,10 +531,11 @@ xmlEncodeEntities(xmlDocPtr doc, const xmlChar *input) { */ #define growBufferReentrant() { \ buffer_size *= 2; \ - buffer = (xmlChar *) xmlRealloc(buffer, buffer_size * sizeof(xmlChar)); \ + buffer = (xmlChar *) \ + xmlRealloc(buffer, buffer_size * sizeof(xmlChar)); \ if (buffer == NULL) { \ perror("realloc failed"); \ - exit(1); \ + return(NULL); \ } \ } @@ -572,7 +574,7 @@ xmlEncodeEntitiesReentrant(xmlDocPtr doc, const xmlChar *input) { buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar)); if (buffer == NULL) { perror("malloc failed"); - exit(1); + return(NULL); } out = buffer; diff --git a/nanohttp.c b/nanohttp.c index 6a921e11..4b27225a 100644 --- a/nanohttp.c +++ b/nanohttp.c @@ -15,7 +15,7 @@ fly with ZLIB if found at compile-time */ #ifdef WIN32 -#define INCLUDE_WINSOCKS +#define INCLUDE_WINSOCK #include "win32config.h" #else #include "config.h" diff --git a/parser.c b/parser.c index a861deb2..eb9a578f 100644 --- a/parser.c +++ b/parser.c @@ -277,7 +277,7 @@ scope int name##Push(xmlParserCtxtPtr ctxt, type value) { \ ctxt->name##Max * sizeof(ctxt->name##Tab[0])); \ if (ctxt->name##Tab == NULL) { \ fprintf(stderr, "realloc failed !\n"); \ - exit(1); \ + return(0); \ } \ } \ ctxt->name##Tab[ctxt->name##Nr] = value; \ @@ -917,7 +917,7 @@ xmlParseStringCharRef(xmlParserCtxtPtr ctxt, const xmlChar **str) { } if (cur == ';') ptr++; - } else if ((cur = '&') && (ptr[1] == '#')){ + } else if ((cur == '&') && (ptr[1] == '#')){ ptr += 2; cur = *ptr; while (cur != ';') { @@ -1366,10 +1366,11 @@ fprintf(stderr, "xmlParserHandlePEReference : ctxt->token != 0\n"); */ #define growBuffer(buffer) { \ buffer##_size *= 2; \ - buffer = (xmlChar *) xmlRealloc(buffer, buffer##_size * sizeof(xmlChar)); \ + buffer = (xmlChar *) \ + xmlRealloc(buffer, buffer##_size * sizeof(xmlChar)); \ if (buffer == NULL) { \ perror("realloc failed"); \ - exit(1); \ + return(NULL); \ } \ } @@ -8044,6 +8045,107 @@ xmlParseDTD(const xmlChar *ExternalID, const xmlChar *SystemID) { return(xmlSAXParseDTD(NULL, ExternalID, SystemID)); } +/** + * xmlSAXParseBalancedChunk : + * @ctx: an XML parser context (possibly NULL) + * @sax: the SAX handler bloc (possibly NULL) + * @user_data: The user data returned on SAX callbacks (possibly NULL) + * @input: a parser input stream + * @enc: the encoding + * + * Parse a well-balanced chunk of an XML document + * The user has to provide SAX callback block whose routines will be + * called by the parser + * The allowed sequence for the Well Balanced Chunk is the one defined by + * the content production in the XML grammar: + * + * [43] content ::= (element | CharData | Reference | CDSect | PI | Comment)* + * + * Returns 0 id the chunk is well balanced, -1 in case of args problem and + * the error code otherwise + */ + +int +xmlSAXParseBalancedChunk(xmlParserCtxtPtr ctx, xmlSAXHandlerPtr sax, + void *user_data, xmlParserInputPtr input, + xmlCharEncoding enc) { + xmlParserCtxtPtr ctxt; + int ret; + + if (input == NULL) return(-1); + + if (ctx != NULL) + ctxt = ctx; + else { + ctxt = xmlNewParserCtxt(); + if (ctxt == NULL) + return(-1); + if (sax == NULL) + ctxt->myDoc = xmlNewDoc(BAD_CAST "1.0"); + } + + /* + * Set-up the SAX context + */ + if (sax != NULL) { + if (ctxt->sax != NULL) + xmlFree(ctxt->sax); + ctxt->sax = sax; + ctxt->userData = user_data; + } + + /* + * plug some encoding conversion routines here. + */ + xmlPushInput(ctxt, input); + if (enc != XML_CHAR_ENCODING_NONE) + xmlSwitchEncoding(ctxt, enc); + + /* + * let's parse that entity knowing it's an external subset. + */ + xmlParseContent(ctxt); + ret = ctxt->errNo; + + if (ctx == NULL) { + if (sax != NULL) + ctxt->sax = NULL; + else + xmlFreeDoc(ctxt->myDoc); + xmlFreeParserCtxt(ctxt); + } + return(ret); +} + +/** + * xmlParseBalancedChunk : + * @doc: the document the chunk pertains to + * @node: the node defining the context in which informations will be added + * + * Parse a well-balanced chunk of an XML document present in memory + * + * Returns the resulting list of nodes resulting from the parsing, + * they are not added to @node + */ + +xmlNodePtr +xmlParseBalancedChunkMemory(xmlDocPtr doc, xmlNodePtr node) { +} + +/** + * xmlParseBalancedChunkFile : + * @doc: the document the chunk pertains to + * + * Parse a well-balanced chunk of an XML document contained in a file + * + * Returns the resulting list of nodes resulting from the parsing, + * they are not added to @node + */ + +xmlNodePtr +xmlParseBalancedChunkFile(xmlDocPtr doc, xmlNodePtr node) { +} + /** * xmlRecoverDoc : * @cur: a pointer to an array of xmlChar @@ -8326,7 +8428,7 @@ xmlSetupParserForBuffer(xmlParserCtxtPtr ctxt, const xmlChar* buffer, if (input == NULL) { perror("malloc"); xmlFree(ctxt); - exit(1); + return; } xmlClearParserCtxt(ctxt); diff --git a/result/noent/ns4 b/result/noent/ns4 index fb372432..fb7bc3e7 100644 --- a/result/noent/ns4 +++ b/result/noent/ns4 @@ -1,24 +1,2 @@ - - - - - - - - - - - - - - - - - - -... - - - + diff --git a/result/ns4 b/result/ns4 index fb372432..fb7bc3e7 100644 --- a/result/ns4 +++ b/result/ns4 @@ -1,24 +1,2 @@ - - - - - - - - - - - - - - - - - - -... - - - + diff --git a/test/ns4 b/test/ns4 index a0f15e03..136bf923 100644 --- a/test/ns4 +++ b/test/ns4 @@ -1,24 +1,2 @@ - - - - - - - - - - - - - - - - -... - - - + + diff --git a/tree.c b/tree.c index 3c145784..425b4543 100644 --- a/tree.c +++ b/tree.c @@ -160,13 +160,18 @@ xmlNewNs(xmlNodePtr node, const xmlChar *href, const xmlChar *prefix) { } else { xmlNsPtr prev = node->nsDef; + if (((prev->prefix == NULL) && (cur->prefix == NULL)) || + (!xmlStrcmp(prev->prefix, cur->prefix))) { + xmlFreeNs(cur); + return(NULL); + } while (prev->next != NULL) { + prev = prev->next; if (((prev->prefix == NULL) && (cur->prefix == NULL)) || (!xmlStrcmp(prev->prefix, cur->prefix))) { xmlFreeNs(cur); return(NULL); } - prev = prev->next; } prev->next = cur; } @@ -182,12 +187,55 @@ xmlNewNs(xmlNodePtr node, const xmlChar *href, const xmlChar *prefix) { * * Creation of a Namespace, the old way using PI and without scoping * DEPRECATED !!! - * Will be removed at next major release ! + * It now create a namespace on the root element of the document if found. * Returns NULL this functionnality had been removed */ xmlNsPtr xmlNewGlobalNs(xmlDocPtr doc, const xmlChar *href, const xmlChar *prefix) { - return(NULL); + xmlNodePtr root; + + xmlNsPtr cur; + + root = xmlDocGetRootElement(doc); + if (root != NULL) + return(xmlNewNs(root, href, prefix)); + + /* + * if there is no root element yet, create an old Namespace type + * and it will be moved to the root at save time. + */ + cur = (xmlNsPtr) xmlMalloc(sizeof(xmlNs)); + if (cur == NULL) { + fprintf(stderr, "xmlNewGlobalNs : malloc failed\n"); + return(NULL); + } + + 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; + } else { + xmlNsPtr prev = doc->oldNs; + + while (prev->next != NULL) prev = prev->next; + prev->next = cur; + } + } + + return(NULL); } /** diff --git a/valid.c b/valid.c index 0efa3c6b..7ee20a02 100644 --- a/valid.c +++ b/valid.c @@ -74,7 +74,7 @@ xmlNewElementContent(xmlChar *name, xmlElementContentType type) { break; default: fprintf(stderr, "xmlNewElementContent: unknown type %d\n", type); - exit(1); + return(NULL); } ret = (xmlElementContentPtr) xmlMalloc(sizeof(xmlElementContent)); if (ret == NULL) { diff --git a/xpath.c b/xpath.c index 4882b04f..7f2a5894 100644 --- a/xpath.c +++ b/xpath.c @@ -186,7 +186,7 @@ extern int name##Push(xmlXPathParserContextPtr ctxt, type value) { \ ctxt->name##Max * sizeof(ctxt->name##Tab[0])); \ if (ctxt->name##Tab == NULL) { \ fprintf(xmlXPathDebug, "realloc failed !\n"); \ - exit(1); \ + return(0); \ } \ } \ ctxt->name##Tab[ctxt->name##Nr] = value; \ @@ -1218,11 +1218,6 @@ xmlXPathEqualValues(xmlXPathParserContextPtr ctxt) { break; } break; -#ifdef DEBUG_EXPR - fprintf(xmlXPathDebug, "Equal: %s string %s \n", - arg1->stringval, arg2->stringval); -#endif - ret = !xmlStrcmp(arg1->stringval, arg2->stringval); } xmlXPathFreeObject(arg1); xmlXPathFreeObject(arg2);