shaba/libxml2
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/libxml2.git synced 2025-01-12 09:17:37 +03:00
Code

encoding: Restore old lookup order in xmlOpenCharEncodingHandler

Browse Source 
When looking up encodings with xmlLookupCharEncodingHandler, the
returned handler can have a different name than requested
(capitalization, internal aliases). This should eventually be fixed.
For now we revert part of commit 5b893fa9, start the lookup with
xmlFindHandler and add an explicit check for UTF-8.

Should fix the encoding name issue mentioned in #749.
This commit is contained in:
Nick Wellnhofer 2024-06-27 12:00:45 +02:00
parent e6f25fdc7c
commit b1a416bf52
2 changed files with 22 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
encoding.c
View File

@ -1161,7 +1161,7 @@ xmlParseCharEncoding(const char* name)
if (!strcmp(upper, "SHIFT_JIS")) return(XML_CHAR_ENCODING_SHIFT_JIS);
if (!strcmp(upper, "EUC-JP")) return(XML_CHAR_ENCODING_EUC_JP);
return(XML_CHAR_ENCODING_NONE);
return(XML_CHAR_ENCODING_ERROR);
}
/**
@ -1936,7 +1936,9 @@ int
xmlOpenCharEncodingHandler(const char *name, int output,
xmlCharEncodingHandler **out) {
const char *nalias;
const char *norig;
xmlCharEncoding enc;
int ret;
if (out == NULL)
return(XML_ERR_ARGUMENT);
@ -1945,30 +1947,32 @@ xmlOpenCharEncodingHandler(const char *name, int output,
if (name == NULL)
return(XML_ERR_ARGUMENT);
if ((xmlStrcasecmp(BAD_CAST name, BAD_CAST "UTF-8") == 0) ||
(xmlStrcasecmp(BAD_CAST name, BAD_CAST "UTF8") == 0))
return(XML_ERR_OK);
/*
* Do the alias resolution
*/
norig = name;
nalias = xmlGetEncodingAlias(name);
if (nalias != NULL)
name = nalias;
ret = xmlFindHandler(name, output, out);
if (*out != NULL)
return(0);
if (ret != XML_ERR_UNSUPPORTED_ENCODING)
return(ret);
/*
* UTF-16 needs the built-in handler which is only available via
* xmlFindHandler.
* Fallback using the canonical names
*
* TODO: We should make sure that the name of the returned
* handler equals norig.
*/
if (xmlStrcasecmp(BAD_CAST name, BAD_CAST "UTF16") == 0) {
name = "UTF-16";
} else if (xmlStrcasecmp(BAD_CAST name, BAD_CAST "UTF-16") != 0) {
enc = xmlParseCharEncoding(name);
if (enc != XML_CHAR_ENCODING_NONE) {
int res = xmlLookupCharEncodingHandler(enc, out);
if (res != XML_ERR_UNSUPPORTED_ENCODING)
return(res);
}
}
return(xmlFindHandler(name, output, out));
enc = xmlParseCharEncoding(norig);
return(xmlLookupCharEncodingHandler(enc, out));
}
/**

3
testparser.c
View File

@ -50,7 +50,8 @@ testUnsupportedEncoding(void) {
xmlFreeDoc(doc);
error = xmlGetLastError();
if (error->code != XML_ERR_UNSUPPORTED_ENCODING ||
if (error == NULL ||
error->code != XML_ERR_UNSUPPORTED_ENCODING ||
error->level != XML_ERR_WARNING ||
strcmp(error->message, "Unsupported encoding: #unsupported\n") != 0)
{