c/libxml2
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/libxml2 synced 2025-03-28 21:33:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

parser: Make xmlSwitchEncoding always skip the BOM

Browse Source 
Chromium calls xmlSwitchEncoding from the start document handler and
relies on this function to skip the BOM. Commit 98840d40 changed the
behavior when switching to UTF-16 since inspecting the input buffer at
this point is fragile.

Revert part of the commit to also skip a potential (decoded UTF-8) BOM
when switching to UTF-16. Make sure that we do this only at the start of
an input stream to avoid U-FEFF characters being lost.

BOM handling should ultimately be moved to the parsing code to avoid
such bugs.

See https://bugs.chromium.org/p/chromium/issues/detail?id=1451026
This commit is contained in:
Nick Wellnhofer 2023-06-22 18:06:53 +02:00
parent c376ddd1bc
commit 044eebfede
1 changed files with 33 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
parserInternals.c
View File

@ -1085,6 +1085,33 @@ xmlSwitchEncoding(xmlParserCtxtPtr ctxt, xmlCharEncoding enc)
int ret;
if (ctxt == NULL) return(-1);
/*
* FIXME: The BOM shouldn't be skipped here, but in the parsing code.
*
* Note that we look for a decoded UTF-8 BOM when switching to UTF-16.
* This is mostly useless but Webkit/Chromium relies on this behavior.
* See https://bugs.chromium.org/p/chromium/issues/detail?id=1451026
*/
if ((ctxt->input != NULL) &&
(ctxt->input->consumed == 0) &&
(ctxt->input->cur != NULL) &&
(ctxt->input->cur == ctxt->input->base) &&
((enc == XML_CHAR_ENCODING_UTF8) ||
(enc == XML_CHAR_ENCODING_UTF16LE) ||
(enc == XML_CHAR_ENCODING_UTF16BE))) {
/*
* Errata on XML-1.0 June 20 2001
* Specific handling of the Byte Order Mark for
* UTF-8
*/
if ((ctxt->input->cur[0] == 0xEF) &&
(ctxt->input->cur[1] == 0xBB) &&
(ctxt->input->cur[2] == 0xBF)) {
ctxt->input->cur += 3;
}
}
switch (enc) {
case XML_CHAR_ENCODING_ERROR:
__xmlErrEncoding(ctxt, XML_ERR_UNKNOWN_ENCODING,
@ -1097,18 +1124,6 @@ xmlSwitchEncoding(xmlParserCtxtPtr ctxt, xmlCharEncoding enc)
case XML_CHAR_ENCODING_UTF8:
/* default encoding, no conversion should be needed */
ctxt->charset = XML_CHAR_ENCODING_UTF8;
/*
* Errata on XML-1.0 June 20 2001
* Specific handling of the Byte Order Mark for
* UTF-8
*/
if ((ctxt->input != NULL) &&
(ctxt->input->cur[0] == 0xEF) &&
(ctxt->input->cur[1] == 0xBB) &&
(ctxt->input->cur[2] == 0xBF)) {
ctxt->input->cur += 3;
}
return(0);
case XML_CHAR_ENCODING_EBCDIC:
handler = xmlDetectEBCDIC(ctxt->input);
@ -1200,8 +1215,8 @@ xmlSwitchInputEncoding(xmlParserCtxtPtr ctxt, xmlParserInputPtr input,
/*
* Switching encodings during parsing is a really bad idea,
* but WebKit/Chromium switches from ISO-8859-1 to UTF-16 as soon as
* it finds Unicode characters with code points larger than 255.
* but Chromium can switch between ISO-8859-1 and UTF-16 before
* separate calls to xmlParseChunk.
*
* TODO: We should check whether the "raw" input buffer is empty and
* convert the old content using the old encoder.
@ -1221,6 +1236,10 @@ xmlSwitchInputEncoding(xmlParserCtxtPtr ctxt, xmlParserInputPtr input,
if (xmlBufIsEmpty(in->buffer) == 0) {
size_t processed, use, consumed;
/*
* FIXME: The BOM shouldn't be skipped here, but in the parsing code.
*/
/*
* Specific handling of the Byte Order Mark for
* UTF-16