From d2e62311cd15651e68f921167c7fcf05b19378f9 Mon Sep 17 00:00:00 2001 From: Adam Spragg Date: Wed, 3 Nov 2010 15:33:40 +0100 Subject: [PATCH] Add xmlSaveOption XML_SAVE_WSNONSIG non destructive indentation option using spaces within markup constructs and hence not modifying content * include/libxml/xmlsave.h: new option * xmlsave.c: some refactoring and new code for the new option * xmllint.c: adds --pretty option where option 2 uses the new formatting --- include/libxml/xmlsave.h | 3 +- xmllint.c | 22 ++++++++++ xmlsave.c | 92 ++++++++++++++++++++++++++++++++++++---- 3 files changed, 107 insertions(+), 10 deletions(-) diff --git a/include/libxml/xmlsave.h b/include/libxml/xmlsave.h index 4201b4d1..fb329b22 100644 --- a/include/libxml/xmlsave.h +++ b/include/libxml/xmlsave.h @@ -33,7 +33,8 @@ typedef enum { XML_SAVE_NO_XHTML = 1<<3, /* disable XHTML1 specific rules */ XML_SAVE_XHTML = 1<<4, /* force XHTML1 specific rules */ XML_SAVE_AS_XML = 1<<5, /* force XML serialization on HTML doc */ - XML_SAVE_AS_HTML = 1<<6 /* force HTML serialization on XML doc */ + XML_SAVE_AS_HTML = 1<<6, /* force HTML serialization on XML doc */ + XML_SAVE_WSNONSIG = 1<<7 /* format with non-significant whitespace */ } xmlSaveOption; diff --git a/xmllint.c b/xmllint.c index aca0a7da..b7af32f0 100644 --- a/xmllint.c +++ b/xmllint.c @@ -2658,6 +2658,8 @@ static void parseAndPrintFile(char *filename, xmlParserCtxtPtr rectxt) { if (format == 1) saveOpts |= XML_SAVE_FORMAT; + else if (format == 2) + saveOpts |= XML_SAVE_WSNONSIG; #if defined(LIBXML_HTML_ENABLED) || defined(LIBXML_VALID_ENABLED) if (xmlout) @@ -3014,6 +3016,10 @@ static void usage(const char *name) { printf("\t--format : reformat/reindent the input\n"); printf("\t--encode encoding : output in the given encoding\n"); printf("\t--dropdtd : remove the DOCTYPE of the input docs\n"); + printf("\t--pretty STYLE : pretty-print in a particular style\n"); + printf("\t 0 Do not pretty print\n"); + printf("\t 1 Format the XML content, as --format\n"); + printf("\t 2 Add whitespace inside tags, preserving content\n"); #endif /* LIBXML_OUTPUT_ENABLED */ printf("\t--c14n : save in W3C canonical format v1.0 (with comments)\n"); printf("\t--c14n11 : save in W3C canonical format v1.1 (with comments)\n"); @@ -3338,6 +3344,17 @@ main(int argc, char **argv) { #endif /* LIBXML_OUTPUT_ENABLED */ xmlKeepBlanksDefault(0); } + else if ((!strcmp(argv[i], "-pretty")) || + (!strcmp(argv[i], "--pretty"))) { + i++; +#ifdef LIBXML_OUTPUT_ENABLED + format = atoi(argv[i]); +#endif /* LIBXML_OUTPUT_ENABLED */ + if (format == 1) { + noblanks++; + xmlKeepBlanksDefault(0); + } + } #ifdef LIBXML_READER_ENABLED else if ((!strcmp(argv[i], "-stream")) || (!strcmp(argv[i], "--stream"))) { @@ -3624,6 +3641,11 @@ main(int argc, char **argv) { i++; continue; } + if ((!strcmp(argv[i], "-pretty")) || + (!strcmp(argv[i], "--pretty"))) { + i++; + continue; + } if ((!strcmp(argv[i], "-schema")) || (!strcmp(argv[i], "--schema"))) { i++; diff --git a/xmlsave.c b/xmlsave.c index 745b98da..ddf7143c 100644 --- a/xmlsave.c +++ b/xmlsave.c @@ -408,6 +408,8 @@ xmlNewSaveCtxt(const char *encoding, int options) ret->options = options; if (options & XML_SAVE_FORMAT) ret->format = 1; + else if (options & XML_SAVE_WSNONSIG) + ret->format = 2; return(ret); } @@ -500,32 +502,90 @@ static void xmlNodeDumpOutputInternal(xmlSaveCtxtPtr ctxt, xmlNodePtr cur); void xmlNsListDumpOutput(xmlOutputBufferPtr buf, xmlNsPtr cur); static int xmlDocContentDumpOutput(xmlSaveCtxtPtr ctxt, xmlDocPtr cur); +/** + * xmlOutputBufferWriteWSNonSig: + * @ctxt: The save context + * @extra: Number of extra indents to apply to ctxt->level + * + * Write out formatting for non-significant whitespace output. + */ +static void +xmlOutputBufferWriteWSNonSig(xmlSaveCtxtPtr ctxt, int extra) +{ + int i; + if ((ctxt == NULL) || (ctxt->buf == NULL)) + return; + xmlOutputBufferWrite(ctxt->buf, 1, "\n"); + for (i = 0; i < (ctxt->level + extra); i += ctxt->indent_nr) { + xmlOutputBufferWrite(ctxt->buf, ctxt->indent_size * + ((ctxt->level + extra - i) > ctxt->indent_nr ? + ctxt->indent_nr : (ctxt->level + extra - i)), + ctxt->indent); + } +} + /** * xmlNsDumpOutput: * @buf: the XML buffer output * @cur: a namespace + * @ctxt: the output save context. Optional. * * Dump a local Namespace definition. * Should be called in the context of attributes dumps. + * If @ctxt is supplied, @buf should be its buffer. */ static void -xmlNsDumpOutput(xmlOutputBufferPtr buf, xmlNsPtr cur) { +xmlNsDumpOutput(xmlOutputBufferPtr buf, xmlNsPtr cur, xmlSaveCtxtPtr ctxt) { if ((cur == NULL) || (buf == NULL)) return; if ((cur->type == XML_LOCAL_NAMESPACE) && (cur->href != NULL)) { if (xmlStrEqual(cur->prefix, BAD_CAST "xml")) return; + if (ctxt != NULL && ctxt->format == 2) + xmlOutputBufferWriteWSNonSig(ctxt, 2); + else + xmlOutputBufferWrite(buf, 1, " "); + /* Within the context of an element attributes */ if (cur->prefix != NULL) { - xmlOutputBufferWrite(buf, 7, " xmlns:"); + xmlOutputBufferWrite(buf, 6, "xmlns:"); xmlOutputBufferWriteString(buf, (const char *)cur->prefix); } else - xmlOutputBufferWrite(buf, 6, " xmlns"); + xmlOutputBufferWrite(buf, 5, "xmlns"); xmlOutputBufferWrite(buf, 1, "="); xmlBufferWriteQuotedString(buf->buffer, cur->href); } } +/** + * xmlNsDumpOutputCtxt + * @ctxt: the save context + * @cur: a namespace + * + * Dump a local Namespace definition to a save context. + * Should be called in the context of attribute dumps. + */ +static void +xmlNsDumpOutputCtxt(xmlSaveCtxtPtr ctxt, xmlNsPtr cur) { + xmlNsDumpOutput(ctxt->buf, cur, ctxt); +} + +/** + * xmlNsListDumpOutputCtxt + * @ctxt: the save context + * @cur: the first namespace + * + * Dump a list of local namespace definitions to a save context. + * Should be called in the context of attribute dumps. + */ +static void +xmlNsListDumpOutputCtxt(xmlSaveCtxtPtr ctxt, xmlNsPtr cur) { + while (cur != NULL) { + xmlNsDumpOutput(ctxt->buf, cur, ctxt); + cur = cur->next; + } +} + /** * xmlNsListDumpOutput: * @buf: the XML buffer output @@ -537,7 +597,7 @@ xmlNsDumpOutput(xmlOutputBufferPtr buf, xmlNsPtr cur) { void xmlNsListDumpOutput(xmlOutputBufferPtr buf, xmlNsPtr cur) { while (cur != NULL) { - xmlNsDumpOutput(buf, cur); + xmlNsDumpOutput(buf, cur, NULL); cur = cur->next; } } @@ -612,7 +672,10 @@ xmlAttrDumpOutput(xmlSaveCtxtPtr ctxt, xmlAttrPtr cur) { if (cur == NULL) return; buf = ctxt->buf; if (buf == NULL) return; - xmlOutputBufferWrite(buf, 1, " "); + if (ctxt->format == 2) + xmlOutputBufferWriteWSNonSig(ctxt, 2); + else + xmlOutputBufferWrite(buf, 1, " "); if ((cur->ns != NULL) && (cur->ns->prefix != NULL)) { xmlOutputBufferWriteString(buf, (const char *)cur->ns->prefix); xmlOutputBufferWrite(buf, 1, ":"); @@ -808,13 +871,18 @@ xmlNodeDumpOutputInternal(xmlSaveCtxtPtr ctxt, xmlNodePtr cur) { xmlOutputBufferWrite(buf, 2, "name); if (cur->content != NULL) { - xmlOutputBufferWrite(buf, 1, " "); + if (ctxt->format == 2) + xmlOutputBufferWriteWSNonSig(ctxt, 0); + else + xmlOutputBufferWrite(buf, 1, " "); xmlOutputBufferWriteString(buf, (const char *)cur->content); } xmlOutputBufferWrite(buf, 2, "?>"); } else { xmlOutputBufferWrite(buf, 2, "name); + if (ctxt->format == 2) + xmlOutputBufferWriteWSNonSig(ctxt, 0); xmlOutputBufferWrite(buf, 2, "?>"); } return; @@ -862,7 +930,7 @@ xmlNodeDumpOutputInternal(xmlSaveCtxtPtr ctxt, xmlNodePtr cur) { return; } if (cur->type == XML_NAMESPACE_DECL) { - xmlNsDumpOutput(buf, (xmlNsPtr) cur); + xmlNsDumpOutputCtxt(ctxt, (xmlNsPtr) cur); return; } @@ -887,16 +955,20 @@ xmlNodeDumpOutputInternal(xmlSaveCtxtPtr ctxt, xmlNodePtr cur) { xmlOutputBufferWriteString(buf, (const char *)cur->name); if (cur->nsDef) - xmlNsListDumpOutput(buf, cur->nsDef); + xmlNsListDumpOutputCtxt(ctxt, cur->nsDef); if (cur->properties != NULL) xmlAttrListDumpOutput(ctxt, cur->properties); if (((cur->type == XML_ELEMENT_NODE) || (cur->content == NULL)) && (cur->children == NULL) && ((ctxt->options & XML_SAVE_NO_EMPTY) == 0)) { + if (ctxt->format == 2) + xmlOutputBufferWriteWSNonSig(ctxt, 0); xmlOutputBufferWrite(buf, 2, "/>"); ctxt->format = format; return; } + if (ctxt->format == 2) + xmlOutputBufferWriteWSNonSig(ctxt, 1); xmlOutputBufferWrite(buf, 1, ">"); if ((cur->type != XML_ELEMENT_NODE) && (cur->content != NULL)) { xmlOutputBufferWriteEscape(buf, cur->content, ctxt->escape); @@ -919,6 +991,8 @@ xmlNodeDumpOutputInternal(xmlSaveCtxtPtr ctxt, xmlNodePtr cur) { } xmlOutputBufferWriteString(buf, (const char *)cur->name); + if (ctxt->format == 2) + xmlOutputBufferWriteWSNonSig(ctxt, 0); xmlOutputBufferWrite(buf, 1, ">"); ctxt->format = format; } @@ -1410,7 +1484,7 @@ xhtmlNodeDumpOutput(xmlSaveCtxtPtr ctxt, xmlNodePtr cur) { xmlOutputBufferWriteString(buf, (const char *)cur->name); if (cur->nsDef) - xmlNsListDumpOutput(buf, cur->nsDef); + xmlNsListDumpOutputCtxt(ctxt, cur->nsDef); if ((xmlStrEqual(cur->name, BAD_CAST "html") && (cur->ns == NULL) && (cur->nsDef == NULL))) { /*