Bart/bullet3
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updated to more recent libxml2 version (work in progress)

Browse Source
This commit is contained in:
ejcoumans
2006-06-18 23:22:39 +00:00
parent c91d74bfa3
commit f2636f8d4b
70 changed files with 12357 additions and 3518 deletions
Download Patch File Download Diff File Expand all files Collapse all files

181
Extras/LibXML/HTMLparser.c
View File

@@ -192,16 +192,16 @@ htmlnamePop(htmlParserCtxtPtr ctxt)
const xmlChar *ret;
if (ctxt->nameNr <= 0)
return (0);
return (NULL);
ctxt->nameNr--;
if (ctxt->nameNr < 0)
return (0);
return (NULL);
if (ctxt->nameNr > 0)
ctxt->name = ctxt->nameTab[ctxt->nameNr - 1];
else
ctxt->name = NULL;
ret = ctxt->nameTab[ctxt->nameNr];
ctxt->nameTab[ctxt->nameNr] = 0;
ctxt->nameTab[ctxt->nameNr] = NULL;
return (ret);
}
@@ -230,7 +230,7 @@ htmlnamePop(htmlParserCtxtPtr ctxt)
* 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.
* NEXTL(l) Skip the current Unicode character of l xmlChars long.
* NEXTL(l) Skip the current unicode character of l xmlChars long.
* COPY(to) copy one char to *to, increment CUR_PTR and to accordingly
*/
@@ -964,7 +964,6 @@ NULL
static const char *htmlNoContentElements[] = {
"html",
"head",
"body",
NULL
};
@@ -1745,7 +1744,7 @@ htmlEntityLookup(const xmlChar *name) {
/**
* htmlEntityValueLookup:
* @value: the entity's Unicode value
* @value: the entity's unicode value
*
* Lookup the given entity in EntitiesTable
*
@@ -2042,6 +2041,7 @@ static int areBlanks(htmlParserCtxtPtr ctxt, const xmlChar *str, int len) {
unsigned int i;
int j;
xmlNodePtr lastChild;
xmlDtdPtr dtd;
for (j = 0;j < len;j++)
if (!(IS_BLANK_CH(str[j]))) return(0);
@@ -2054,8 +2054,17 @@ static int areBlanks(htmlParserCtxtPtr ctxt, const xmlChar *str, int len) {
return(1);
if (xmlStrEqual(ctxt->name, BAD_CAST"head"))
return(1);
if (xmlStrEqual(ctxt->name, BAD_CAST"body"))
return(1);
/* Only strip CDATA children of the body tag for strict HTML DTDs */
if (xmlStrEqual(ctxt->name, BAD_CAST "body") && ctxt->myDoc != NULL) {
dtd = xmlGetIntSubset(ctxt->myDoc);
if (dtd != NULL && dtd->ExternalID != NULL) {
if (!xmlStrcasecmp(dtd->ExternalID, BAD_CAST "-//W3C//DTD HTML 4.01//EN") ||
!xmlStrcasecmp(dtd->ExternalID, BAD_CAST "-//W3C//DTD HTML 4//EN"))
return(1);
}
}
if (ctxt->node == NULL) return(0);
lastChild = xmlGetLastChild(ctxt->node);
while ((lastChild) && (lastChild->type == XML_COMMENT_NODE))
@@ -2627,12 +2636,12 @@ htmlParsePubidLiteral(htmlParserCtxtPtr ctxt) {
*/
static void
htmlParseScript(htmlParserCtxtPtr ctxt) {
xmlChar buf[HTML_PARSER_BIG_BUFFER_SIZE + 1];
xmlChar buf[HTML_PARSER_BIG_BUFFER_SIZE + 5];
int nbchar = 0;
xmlChar cur;
int cur,l;
SHRINK;
cur = CUR;
cur = CUR_CHAR(l);
while (IS_CHAR_CH(cur)) {
if ((cur == '<') && (NXT(1) == '!') && (NXT(2) == '-') &&
(NXT(3) == '-')) {
@@ -2648,20 +2657,39 @@ htmlParseScript(htmlParserCtxtPtr ctxt) {
}
nbchar = 0;
htmlParseComment(ctxt);
cur = CUR;
cur = CUR_CHAR(l);
continue;
} else if ((cur == '<') && (NXT(1) == '/')) {
/*
* One should break here, the specification is clear:
* Authors should therefore escape "</" within the content.
* Escape mechanisms are specific to each scripting or
* style sheet language.
*/
if (((NXT(2) >= 'A') && (NXT(2) <= 'Z')) ||
((NXT(2) >= 'a') && (NXT(2) <= 'z')))
break; /* while */
/*
* One should break here, the specification is clear:
* Authors should therefore escape "</" within the content.
* Escape mechanisms are specific to each scripting or
* style sheet language.
*
* In recovery mode, only break if end tag match the
* current tag, effectively ignoring all tags inside the
* script/style block and treating the entire block as
* CDATA.
*/
if (ctxt->recovery) {
if (xmlStrncasecmp(ctxt->name, ctxt->input->cur+2,
xmlStrlen(ctxt->name)) == 0)
{
break; /* while */
} else {
htmlParseErr(ctxt, XML_ERR_TAG_NAME_MISMATCH,
"Element %s embeds close tag\n",
ctxt->name, NULL);
}
} else {
if (((NXT(2) >= 'A') && (NXT(2) <= 'Z')) ||
((NXT(2) >= 'a') && (NXT(2) <= 'z')))
{
break; /* while */
}
}
}
buf[nbchar++] = cur;
COPY_BUF(l,buf,nbchar,cur);
if (nbchar >= HTML_PARSER_BIG_BUFFER_SIZE) {
if (ctxt->sax->cdataBlock!= NULL) {
/*
@@ -2673,9 +2701,11 @@ htmlParseScript(htmlParserCtxtPtr ctxt) {
}
nbchar = 0;
}
NEXT;
cur = CUR;
GROW;
NEXTL(l);
cur = CUR_CHAR(l);
}
if (!(IS_CHAR_CH(cur))) {
htmlParseErrInt(ctxt, XML_ERR_INVALID_CHAR,
"Invalid char in CDATA 0x%X\n", cur);
@@ -2743,6 +2773,8 @@ htmlParseCharData(htmlParserCtxtPtr ctxt) {
}
}
if (nbchar != 0) {
buf[nbchar] = 0;
/*
* Ok the segment is to be consumed as chars.
*/
@@ -3349,27 +3381,31 @@ htmlCheckMeta(htmlParserCtxtPtr ctxt, const xmlChar **atts) {
*
* [NS 10] EmptyElement ::= '<' QName (S Attribute)* S? '/>'
*
* Returns 0 in case of success and -1 in case of error.
*/
static void
static int
htmlParseStartTag(htmlParserCtxtPtr ctxt) {
const xmlChar *name;
const xmlChar *attname;
xmlChar *attvalue;
const xmlChar **atts = ctxt->atts;
const xmlChar **atts;
int nbatts = 0;
int maxatts = ctxt->maxatts;
int maxatts;
int meta = 0;
int i;
if ((ctxt == NULL) || (ctxt->input == NULL)) {
htmlParseErr(ctxt, XML_ERR_INTERNAL_ERROR,
"htmlParseStartTag: context error\n", NULL, NULL);
return;
return -1;
}
if (CUR != '<') return;
if (CUR != '<') return -1;
NEXT;
atts = ctxt->atts;
maxatts = ctxt->maxatts;
GROW;
name = htmlParseHTMLName(ctxt);
if (name == NULL) {
@@ -3379,7 +3415,7 @@ htmlParseStartTag(htmlParserCtxtPtr ctxt) {
/* Dump the bogus tag like browsers do */
while ((IS_CHAR_CH(CUR)) && (CUR != '>'))
NEXT;
return;
return -1;
}
if (xmlStrEqual(name, BAD_CAST"meta"))
meta = 1;
@@ -3402,14 +3438,14 @@ htmlParseStartTag(htmlParserCtxtPtr ctxt) {
htmlParseErr(ctxt, XML_HTML_STRUCURE_ERROR,
"htmlParseStartTag: misplaced <html> tag\n",
name, NULL);
return;
return 0;
}
if ((ctxt->nameNr != 1) &&
(xmlStrEqual(name, BAD_CAST"head"))) {
htmlParseErr(ctxt, XML_HTML_STRUCURE_ERROR,
"htmlParseStartTag: misplaced <head> tag\n",
name, NULL);
return;
return 0;
}
if (xmlStrEqual(name, BAD_CAST"body")) {
int indx;
@@ -3420,7 +3456,7 @@ htmlParseStartTag(htmlParserCtxtPtr ctxt) {
name, NULL);
while ((IS_CHAR_CH(CUR)) && (CUR != '>'))
NEXT;
return;
return 0;
}
}
}
@@ -3533,6 +3569,8 @@ failed:
xmlFree((xmlChar *) atts[i]);
}
}
return 0;
}
/**
@@ -3575,6 +3613,15 @@ htmlParseEndTag(htmlParserCtxtPtr ctxt)
if ((!IS_CHAR_CH(CUR)) || (CUR != '>')) {
htmlParseErr(ctxt, XML_ERR_GT_REQUIRED,
"End tag : expected '>'\n", NULL, NULL);
if (ctxt->recovery) {
/*
* We're not at the ending > !!
* Error, unless in recover mode where we search forwards
* until we find a >
*/
while (CUR != '\0' && CUR != '>') NEXT;
NEXT;
}
} else
NEXT;
@@ -3709,10 +3756,8 @@ htmlParseReference(htmlParserCtxtPtr ctxt) {
/**
* htmlParseContent:
* @ctxt: an HTML parser context
* @name: the node name
*
* Parse a content: comment, sub-element, reference or text.
*
*/
static void
@@ -3830,6 +3875,19 @@ htmlParseContent(htmlParserCtxtPtr ctxt) {
if (currentNode != NULL) xmlFree(currentNode);
}
/**
* htmlParseContent:
* @ctxt: an HTML parser context
*
* Parse a content: comment, sub-element, reference or text.
*/
void
__htmlParseContent(void *ctxt) {
if (ctxt != NULL)
htmlParseContent((htmlParserCtxtPtr) ctxt);
}
/**
* htmlParseElement:
* @ctxt: an HTML parser context
@@ -3847,16 +3905,15 @@ htmlParseElement(htmlParserCtxtPtr ctxt) {
xmlChar *currentNode = NULL;
const htmlElemDesc * info;
htmlParserNodeInfo node_info;
const xmlChar *oldname;
int failed;
int depth;
const xmlChar *oldptr;
if ((ctxt == NULL) || (ctxt->input == NULL)) {
htmlParseErr(ctxt, XML_ERR_INTERNAL_ERROR,
"htmlParseStartTag: context error\n", NULL, NULL);
"htmlParseElement: context error\n", NULL, NULL);
return;
}
depth = ctxt->nameNr;
/* Capture start position */
if (ctxt->record_info) {
node_info.begin_pos = ctxt->input->consumed +
@@ -3864,11 +3921,9 @@ htmlParseElement(htmlParserCtxtPtr ctxt) {
node_info.begin_line = ctxt->input->line;
}
oldname = ctxt->name;
htmlParseStartTag(ctxt);
failed = htmlParseStartTag(ctxt);
name = ctxt->name;
if (((depth == ctxt->nameNr) && (xmlStrEqual(oldname, ctxt->name))) ||
(name == NULL)) {
if (failed || (name == NULL)) {
if (CUR == '>')
NEXT;
return;
@@ -3911,7 +3966,7 @@ htmlParseElement(htmlParserCtxtPtr ctxt) {
/*
* Capture end position and add node
*/
if ( currentNode != NULL && ctxt->record_info ) {
if (ctxt->record_info) {
node_info.end_pos = ctxt->input->consumed +
(CUR_PTR - ctxt->input->base);
node_info.end_line = ctxt->input->line;
@@ -4577,11 +4632,11 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
#endif
} else {
ctxt->instate = XML_PARSER_MISC;
}
#ifdef DEBUG_PUSH
xmlGenericError(xmlGenericErrorContext,
"HPP: entering MISC\n");
xmlGenericError(xmlGenericErrorContext,
"HPP: entering MISC\n");
#endif
}
break;
case XML_PARSER_MISC:
SKIP_BLANKS;
@@ -4738,8 +4793,8 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
}
break;
case XML_PARSER_START_TAG: {
const xmlChar *name, *oldname;
int depth = ctxt->nameNr;
const xmlChar *name;
int failed;
const htmlElemDesc * info;
if (avail < 2)
@@ -4766,11 +4821,9 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
(htmlParseLookupSequence(ctxt, '>', 0, 0, 0) < 0))
goto done;
oldname = ctxt->name;
htmlParseStartTag(ctxt);
failed = htmlParseStartTag(ctxt);
name = ctxt->name;
if (((depth == ctxt->nameNr) &&
(xmlStrEqual(oldname, ctxt->name))) ||
if (failed ||
(name == NULL)) {
if (CUR == '>')
NEXT;
@@ -4793,7 +4846,7 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
SKIP(2);
if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
ctxt->sax->endElement(ctxt->userData, name);
oldname = htmlnamePop(ctxt);
htmlnamePop(ctxt);
ctxt->instate = XML_PARSER_CONTENT;
#ifdef DEBUG_PUSH
xmlGenericError(xmlGenericErrorContext,
@@ -4814,7 +4867,7 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
*/
if (xmlStrEqual(name, ctxt->name)) {
nodePop(ctxt);
oldname = htmlnamePop(ctxt);
htmlnamePop(ctxt);
}
ctxt->instate = XML_PARSER_CONTENT;
@@ -4831,7 +4884,7 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
if ((info != NULL) && (info->empty)) {
if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
ctxt->sax->endElement(ctxt->userData, name);
oldname = htmlnamePop(ctxt);
htmlnamePop(ctxt);
}
ctxt->instate = XML_PARSER_CONTENT;
#ifdef DEBUG_PUSH
@@ -5178,10 +5231,18 @@ htmlParseChunk(htmlParserCtxtPtr ctxt, const char *chunk, int size,
(ctxt->input->buf != NULL) && (ctxt->instate != XML_PARSER_EOF)) {
int base = ctxt->input->base - ctxt->input->buf->buffer->content;
int cur = ctxt->input->cur - ctxt->input->base;
int res;
xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
res = xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
if (res < 0) {
ctxt->errNo = XML_PARSER_EOF;
ctxt->disableSAX = 1;
return (XML_PARSER_EOF);
}
ctxt->input->base = ctxt->input->buf->buffer->content + base;
ctxt->input->cur = ctxt->input->base + cur;
ctxt->input->end =
&ctxt->input->buf->buffer->content[ctxt->input->buf->buffer->use];
#ifdef DEBUG_PUSH
xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size);
#endif
@@ -5779,6 +5840,14 @@ htmlCtxtUseOptions(htmlParserCtxtPtr ctxt, int options)
ctxt->options |= XML_PARSE_NOBLANKS;
} else
ctxt->keepBlanks = 1;
if (options & HTML_PARSE_RECOVER) {
ctxt->recovery = 1;
} else
ctxt->recovery = 0;
if (options & HTML_PARSE_COMPACT) {
ctxt->options |= HTML_PARSE_COMPACT;
options -= HTML_PARSE_COMPACT;
}
ctxt->dictNames = 0;
return (options);
}