aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDaniel Veillard <veillard@redhat.com>2011-05-16 16:03:50 +0800
committerDaniel Veillard <veillard@redhat.com>2011-05-26 11:47:37 +0800
commitc62efc847c836d4c4f1aea08c68cd93bd342b9f4 (patch)
tree9841d1b5335cc3ff729fa8a38eee1474bbcad0e6
parent0329a1471ee1c2ab4f4b46a2adae37dc52739257 (diff)
downloadandroid_external_libxml2-c62efc847c836d4c4f1aea08c68cd93bd342b9f4.tar.gz
android_external_libxml2-c62efc847c836d4c4f1aea08c68cd93bd342b9f4.tar.bz2
android_external_libxml2-c62efc847c836d4c4f1aea08c68cd93bd342b9f4.zip
Add options to ignore the internal encoding
For both XML and HTML, the document can provide an encoding either in XMLDecl in XML, or as a meta element in HTML head. This adds options to ignore those encodings if the encoding is known in advace for example if the content had been converted before being passed to the parser. * parser.c include/libxml/parser.h: add XML_PARSE_IGNORE_ENC option for XML parsing * include/libxml/HTMLparser.h HTMLparser.c: adds the HTML_PARSE_IGNORE_ENC for HTML parsing * HTMLtree.c: fix the handling of saving when an unknown encoding is defined in meta document header * xmllint.c: add a --noenc option to activate the new parser options
-rw-r--r--HTMLparser.c11
-rw-r--r--HTMLtree.c18
-rw-r--r--include/libxml/HTMLparser.h3
-rw-r--r--include/libxml/parser.h5
-rw-r--r--parser.c11
-rw-r--r--xmllint.c6
6 files changed, 39 insertions, 15 deletions
diff --git a/HTMLparser.c b/HTMLparser.c
index 4d43b93d..1a4d80d3 100644
--- a/HTMLparser.c
+++ b/HTMLparser.c
@@ -3448,7 +3448,8 @@ static void
htmlCheckEncoding(htmlParserCtxtPtr ctxt, const xmlChar *attvalue) {
const xmlChar *encoding;
- if ((ctxt == NULL) || (attvalue == NULL))
+ if ((ctxt == NULL) || (attvalue == NULL) ||
+ (ctxt->options & HTML_PARSE_IGNORE_ENC))
return;
/* do not change encoding */
@@ -3500,7 +3501,9 @@ htmlCheckEncoding(htmlParserCtxtPtr ctxt, const xmlChar *attvalue) {
xmlSwitchToEncoding(ctxt, handler);
ctxt->charset = XML_CHAR_ENCODING_UTF8;
} else {
- ctxt->errNo = XML_ERR_UNSUPPORTED_ENCODING;
+ htmlParseErr(ctxt, XML_ERR_UNSUPPORTED_ENCODING,
+ "htmlCheckEncoding: unknown encoding %s\n",
+ encoding, NULL);
}
}
@@ -6537,6 +6540,10 @@ htmlCtxtUseOptions(htmlParserCtxtPtr ctxt, int options)
ctxt->options |= HTML_PARSE_NODEFDTD;
options -= HTML_PARSE_NODEFDTD;
}
+ if (options & HTML_PARSE_IGNORE_ENC) {
+ ctxt->options |= HTML_PARSE_IGNORE_ENC;
+ options -= HTML_PARSE_IGNORE_ENC;
+ }
ctxt->dictNames = 0;
return (options);
}
diff --git a/HTMLtree.c b/HTMLtree.c
index b5085836..f23ae023 100644
--- a/HTMLtree.c
+++ b/HTMLtree.c
@@ -481,7 +481,7 @@ htmlNodeDumpFileFormat(FILE *out, xmlDocPtr doc,
if (enc != XML_CHAR_ENCODING_UTF8) {
handler = xmlFindCharEncodingHandler(encoding);
if (handler == NULL)
- return(-1);
+ htmlSaveErr(XML_SAVE_UNKNOWN_ENCODING, NULL, encoding);
}
}
@@ -562,11 +562,9 @@ htmlDocDumpMemoryFormat(xmlDocPtr cur, xmlChar**mem, int *size, int format) {
}
handler = xmlFindCharEncodingHandler(encoding);
- if (handler == NULL) {
- *mem = NULL;
- *size = 0;
- return;
- }
+ if (handler == NULL)
+ htmlSaveErr(XML_SAVE_UNKNOWN_ENCODING, NULL, encoding);
+
} else {
handler = xmlFindCharEncodingHandler(encoding);
}
@@ -587,7 +585,7 @@ htmlDocDumpMemoryFormat(xmlDocPtr cur, xmlChar**mem, int *size, int format) {
return;
}
- htmlDocContentDumpFormatOutput(buf, cur, NULL, format);
+ htmlDocContentDumpFormatOutput(buf, cur, NULL, format);
xmlOutputBufferFlush(buf);
if (buf->conv != NULL) {
@@ -1061,7 +1059,7 @@ htmlDocDump(FILE *f, xmlDocPtr cur) {
handler = xmlFindCharEncodingHandler(encoding);
if (handler == NULL)
- return(-1);
+ htmlSaveErr(XML_SAVE_UNKNOWN_ENCODING, NULL, encoding);
} else {
handler = xmlFindCharEncodingHandler(encoding);
}
@@ -1120,7 +1118,7 @@ htmlSaveFile(const char *filename, xmlDocPtr cur) {
handler = xmlFindCharEncodingHandler(encoding);
if (handler == NULL)
- return(-1);
+ htmlSaveErr(XML_SAVE_UNKNOWN_ENCODING, NULL, encoding);
}
}
@@ -1181,7 +1179,7 @@ htmlSaveFileFormat(const char *filename, xmlDocPtr cur,
handler = xmlFindCharEncodingHandler(encoding);
if (handler == NULL)
- return(-1);
+ htmlSaveErr(XML_SAVE_UNKNOWN_ENCODING, NULL, encoding);
}
htmlSetMetaEncoding(cur, (const xmlChar *) encoding);
} else {
diff --git a/include/libxml/HTMLparser.h b/include/libxml/HTMLparser.h
index fbcc811e..10a3d654 100644
--- a/include/libxml/HTMLparser.h
+++ b/include/libxml/HTMLparser.h
@@ -184,7 +184,8 @@ typedef enum {
HTML_PARSE_NOBLANKS = 1<<8, /* remove blank nodes */
HTML_PARSE_NONET = 1<<11,/* Forbid network access */
HTML_PARSE_NOIMPLIED= 1<<13,/* Do not add implied html/body... elements */
- HTML_PARSE_COMPACT = 1<<16 /* compact small text nodes */
+ HTML_PARSE_COMPACT = 1<<16,/* compact small text nodes */
+ HTML_PARSE_IGNORE_ENC=1<<21 /* ignore internal document encoding hint */
} htmlParserOption;
XMLPUBFUN void XMLCALL
diff --git a/include/libxml/parser.h b/include/libxml/parser.h
index 47b3df15..aabb96cf 100644
--- a/include/libxml/parser.h
+++ b/include/libxml/parser.h
@@ -1105,8 +1105,9 @@ typedef enum {
crash if you try to modify the tree) */
XML_PARSE_OLD10 = 1<<17,/* parse using XML-1.0 before update 5 */
XML_PARSE_NOBASEFIX = 1<<18,/* do not fixup XINCLUDE xml:base uris */
- XML_PARSE_HUGE = 1<<19, /* relax any hardcoded limit from the parser */
- XML_PARSE_OLDSAX = 1<<20 /* parse using SAX2 interface from before 2.7.0 */
+ XML_PARSE_HUGE = 1<<19,/* relax any hardcoded limit from the parser */
+ XML_PARSE_OLDSAX = 1<<20,/* parse using SAX2 interface before 2.7.0 */
+ XML_PARSE_IGNORE_ENC= 1<<21 /* ignore internal document encoding hint */
} xmlParserOption;
XMLPUBFUN void XMLCALL
diff --git a/parser.c b/parser.c
index 9ab86412..02a18771 100644
--- a/parser.c
+++ b/parser.c
@@ -9922,6 +9922,13 @@ xmlParseEncodingDecl(xmlParserCtxtPtr ctxt) {
} else {
xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL);
}
+
+ /*
+ * Non standard parsing, allowing the user to ignore encoding
+ */
+ if (ctxt->options & XML_PARSE_IGNORE_ENC)
+ return(encoding);
+
/*
* UTF-16 encoding stwich has already taken place at this stage,
* more over the little-endian/big-endian selection is already done
@@ -14561,6 +14568,10 @@ xmlCtxtUseOptionsInternal(xmlParserCtxtPtr ctxt, int options, const char *encodi
ctxt->options |= XML_PARSE_OLDSAX;
options -= XML_PARSE_OLDSAX;
}
+ if (options & XML_PARSE_IGNORE_ENC) {
+ ctxt->options |= XML_PARSE_IGNORE_ENC;
+ options -= XML_PARSE_IGNORE_ENC;
+ }
ctxt->linenumbers = 1;
return (options);
}
diff --git a/xmllint.c b/xmllint.c
index 8af56cd4..14c64bec 100644
--- a/xmllint.c
+++ b/xmllint.c
@@ -130,6 +130,7 @@ static int copy = 0;
#endif /* LIBXML_TREE_ENABLED */
static int recovery = 0;
static int noent = 0;
+static int noenc = 0;
static int noblanks = 0;
static int noout = 0;
static int nowrap = 0;
@@ -2983,6 +2984,7 @@ static void usage(const char *name) {
printf("\t--recover : output what was parsable on broken XML documents\n");
printf("\t--huge : remove any internal arbitrary parser limits\n");
printf("\t--noent : substitute entity references by their value\n");
+ printf("\t--noenc : ignore any encoding specified inside the document\n");
printf("\t--noout : don't output the result tree\n");
printf("\t--path 'paths': provide a set of paths for resources\n");
printf("\t--load-trace : print trace of all external entites loaded\n");
@@ -3137,6 +3139,10 @@ main(int argc, char **argv) {
(!strcmp(argv[i], "--noent"))) {
noent++;
options |= XML_PARSE_NOENT;
+ } else if ((!strcmp(argv[i], "-noenc")) ||
+ (!strcmp(argv[i], "--noenc"))) {
+ noenc++;
+ options |= XML_PARSE_IGNORE_ENC;
} else if ((!strcmp(argv[i], "-nsclean")) ||
(!strcmp(argv[i], "--nsclean"))) {
options |= XML_PARSE_NSCLEAN;