diff options
| author | Daniel Veillard <veillard@src.gnome.org> | 2001-11-10 11:43:05 +0000 |
|---|---|---|
| committer | Daniel Veillard <veillard@src.gnome.org> | 2001-11-10 11:43:05 +0000 |
| commit | c1f78343b6b1e566147d90f43d13fe514fb2f214 (patch) | |
| tree | e1b188695ada3f086a6ff55ff5829e6a72d346ce /HTMLparser.c | |
| parent | c6e013ab52d1f6634088d468b967c33350f37858 (diff) | |
| download | android_external_libxml2-c1f78343b6b1e566147d90f43d13fe514fb2f214.tar.gz android_external_libxml2-c1f78343b6b1e566147d90f43d13fe514fb2f214.tar.bz2 android_external_libxml2-c1f78343b6b1e566147d90f43d13fe514fb2f214.zip | |
fix comment in scripts element parsing. updated the results. Daniel
* HTMLparser.c: fix comment in scripts element parsing.
* result/HTML/doc3*: updated the results.
Daniel
Diffstat (limited to 'HTMLparser.c')
| -rw-r--r-- | HTMLparser.c | 35 |
1 files changed, 34 insertions, 1 deletions
diff --git a/HTMLparser.c b/HTMLparser.c index af941a0e..8ff74e47 100644 --- a/HTMLparser.c +++ b/HTMLparser.c @@ -53,6 +53,7 @@ static int htmlOmittedDefaultValue = 1; xmlChar * htmlDecodeEntities(htmlParserCtxtPtr ctxt, int len, xmlChar end, xmlChar end2, xmlChar end3); +static void htmlParseComment(htmlParserCtxtPtr ctxt); /************************************************************************ * * @@ -2299,7 +2300,21 @@ htmlParseScript(htmlParserCtxtPtr ctxt) { SHRINK; cur = CUR; while (IS_CHAR(cur)) { - if ((cur == '<') && (NXT(1) == '/')) { + if ((cur == '<') && (NXT(1) == '!') && (NXT(2) == '-') && + (NXT(3) == '-')) { + if ((nbchar != 0) && (ctxt->sax != NULL) && (!ctxt->disableSAX)) { + if (ctxt->sax->cdataBlock!= NULL) { + /* + * Insert as CDATA, which is the same as HTML_PRESERVE_NODE + */ + ctxt->sax->cdataBlock(ctxt->userData, buf, nbchar); + } + } + nbchar = 0; + htmlParseComment(ctxt); + cur = CUR; + continue; + } else if ((cur == '<') && (NXT(1) == '/')) { /* * One should break here, the specification is clear: * Authors should therefore escape "</" within the content. @@ -3841,6 +3856,7 @@ htmlParseLookupSequence(htmlParserCtxtPtr ctxt, xmlChar first, int base, len; htmlParserInputPtr in; const xmlChar *buf; + int incomment = 0; in = ctxt->input; if (in == NULL) return(-1); @@ -3859,6 +3875,23 @@ htmlParseLookupSequence(htmlParserCtxtPtr ctxt, xmlChar first, if (third) len -= 2; else if (next) len --; for (;base < len;base++) { + if (!incomment && (base + 4 < len)) { + if ((buf[base] == '<') && (buf[base + 1] == '!') && + (buf[base + 2] == '-') && (buf[base + 3] == '-')) { + incomment = 1; + } + /* do not increment base, some people use <!--> */ + } + if (incomment) { + if (base + 3 < len) + return(-1); + if ((buf[base] == '-') && (buf[base + 1] == '-') && + (buf[base + 2] == '>')) { + incomment = 0; + base += 2; + } + continue; + } if (buf[base] == first) { if (third != 0) { if ((buf[base + 1] != next) || |