mirror of
https://gitlab.gnome.org/GNOME/libxml2
synced 2025-03-28 21:33:13 +00:00
Rework control flow in htmlCurrentChar
Don't call xmlCurrentChar after switching encodings. Rearrange code blocks and fall through to normal UTF-8 handling.
This commit is contained in:
Nick Wellnhofer
parent
922bebccdd
commit
dfd4e33048
197
HTMLparser.c
197
HTMLparser.c
@ -414,6 +414,10 @@ htmlFindEncoding(xmlParserCtxtPtr ctxt) {
|
||||
|
||||
static int
|
||||
htmlCurrentChar(xmlParserCtxtPtr ctxt, int *len) {
|
||||
const unsigned char *cur;
|
||||
unsigned char c;
|
||||
unsigned int val;
|
||||
|
||||
if (ctxt->instate == XML_PARSER_EOF)
|
||||
return(0);
|
||||
|
||||
@ -421,107 +425,23 @@ htmlCurrentChar(xmlParserCtxtPtr ctxt, int *len) {
|
||||
*len = 0;
|
||||
return(ctxt->token);
|
||||
}
|
||||
if (ctxt->charset == XML_CHAR_ENCODING_UTF8) {
|
||||
/*
|
||||
* We are supposed to handle UTF8, check it's valid
|
||||
* From rfc2044: encoding of the Unicode values on UTF-8:
|
||||
*
|
||||
* UCS-4 range (hex.) UTF-8 octet sequence (binary)
|
||||
* 0000 0000-0000 007F 0xxxxxxx
|
||||
* 0000 0080-0000 07FF 110xxxxx 10xxxxxx
|
||||
* 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx
|
||||
*
|
||||
* Check for the 0x110000 limit too
|
||||
*/
|
||||
const unsigned char *cur = ctxt->input->cur;
|
||||
unsigned char c;
|
||||
unsigned int val;
|
||||
|
||||
c = *cur;
|
||||
if (c & 0x80) {
|
||||
if ((c & 0x40) == 0)
|
||||
goto encoding_error;
|
||||
if (cur[1] == 0) {
|
||||
xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
|
||||
cur = ctxt->input->cur;
|
||||
}
|
||||
if ((cur[1] & 0xc0) != 0x80)
|
||||
goto encoding_error;
|
||||
if ((c & 0xe0) == 0xe0) {
|
||||
|
||||
if (cur[2] == 0) {
|
||||
xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
|
||||
cur = ctxt->input->cur;
|
||||
}
|
||||
if ((cur[2] & 0xc0) != 0x80)
|
||||
goto encoding_error;
|
||||
if ((c & 0xf0) == 0xf0) {
|
||||
if (cur[3] == 0) {
|
||||
xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
|
||||
cur = ctxt->input->cur;
|
||||
}
|
||||
if (((c & 0xf8) != 0xf0) ||
|
||||
((cur[3] & 0xc0) != 0x80))
|
||||
goto encoding_error;
|
||||
/* 4-byte code */
|
||||
*len = 4;
|
||||
val = (cur[0] & 0x7) << 18;
|
||||
val |= (cur[1] & 0x3f) << 12;
|
||||
val |= (cur[2] & 0x3f) << 6;
|
||||
val |= cur[3] & 0x3f;
|
||||
if (val < 0x10000)
|
||||
goto encoding_error;
|
||||
} else {
|
||||
/* 3-byte code */
|
||||
*len = 3;
|
||||
val = (cur[0] & 0xf) << 12;
|
||||
val |= (cur[1] & 0x3f) << 6;
|
||||
val |= cur[2] & 0x3f;
|
||||
if (val < 0x800)
|
||||
goto encoding_error;
|
||||
}
|
||||
} else {
|
||||
/* 2-byte code */
|
||||
*len = 2;
|
||||
val = (cur[0] & 0x1f) << 6;
|
||||
val |= cur[1] & 0x3f;
|
||||
if (val < 0x80)
|
||||
goto encoding_error;
|
||||
}
|
||||
if (!IS_CHAR(val)) {
|
||||
htmlParseErrInt(ctxt, XML_ERR_INVALID_CHAR,
|
||||
"Char 0x%X out of allowed range\n", val);
|
||||
}
|
||||
return(val);
|
||||
} else {
|
||||
if ((*ctxt->input->cur == 0) &&
|
||||
(ctxt->input->cur < ctxt->input->end)) {
|
||||
htmlParseErrInt(ctxt, XML_ERR_INVALID_CHAR,
|
||||
"Char 0x%X out of allowed range\n", 0);
|
||||
*len = 1;
|
||||
return(' ');
|
||||
}
|
||||
/* 1-byte code */
|
||||
*len = 1;
|
||||
return((int) *ctxt->input->cur);
|
||||
}
|
||||
}
|
||||
/*
|
||||
* Assume it's a fixed length encoding (1) with
|
||||
* a compatible encoding for the ASCII set, since
|
||||
* XML constructs only use < 128 chars
|
||||
*/
|
||||
*len = 1;
|
||||
if ((int) *ctxt->input->cur < 0x80)
|
||||
return((int) *ctxt->input->cur);
|
||||
|
||||
/*
|
||||
* Humm this is bad, do an automatic flow conversion
|
||||
*/
|
||||
{
|
||||
if (ctxt->charset != XML_CHAR_ENCODING_UTF8) {
|
||||
xmlChar * guess;
|
||||
xmlCharEncodingHandlerPtr handler;
|
||||
|
||||
/*
|
||||
* Assume it's a fixed length encoding (1) with
|
||||
* a compatible encoding for the ASCII set, since
|
||||
* HTML constructs only use < 128 chars
|
||||
*/
|
||||
if ((int) *ctxt->input->cur < 0x80) {
|
||||
*len = 1;
|
||||
return((int) *ctxt->input->cur);
|
||||
}
|
||||
|
||||
/*
|
||||
* Humm this is bad, do an automatic flow conversion
|
||||
*/
|
||||
guess = htmlFindEncoding(ctxt);
|
||||
if (guess == NULL) {
|
||||
xmlSwitchEncoding(ctxt, XML_CHAR_ENCODING_8859_1);
|
||||
@ -540,7 +460,86 @@ htmlCurrentChar(xmlParserCtxtPtr ctxt, int *len) {
|
||||
ctxt->charset = XML_CHAR_ENCODING_UTF8;
|
||||
}
|
||||
|
||||
return(xmlCurrentChar(ctxt, len));
|
||||
/*
|
||||
* We are supposed to handle UTF8, check it's valid
|
||||
* From rfc2044: encoding of the Unicode values on UTF-8:
|
||||
*
|
||||
* UCS-4 range (hex.) UTF-8 octet sequence (binary)
|
||||
* 0000 0000-0000 007F 0xxxxxxx
|
||||
* 0000 0080-0000 07FF 110xxxxx 10xxxxxx
|
||||
* 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx
|
||||
*
|
||||
* Check for the 0x110000 limit too
|
||||
*/
|
||||
cur = ctxt->input->cur;
|
||||
c = *cur;
|
||||
if (c & 0x80) {
|
||||
if ((c & 0x40) == 0)
|
||||
goto encoding_error;
|
||||
if (cur[1] == 0) {
|
||||
xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
|
||||
cur = ctxt->input->cur;
|
||||
}
|
||||
if ((cur[1] & 0xc0) != 0x80)
|
||||
goto encoding_error;
|
||||
if ((c & 0xe0) == 0xe0) {
|
||||
|
||||
if (cur[2] == 0) {
|
||||
xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
|
||||
cur = ctxt->input->cur;
|
||||
}
|
||||
if ((cur[2] & 0xc0) != 0x80)
|
||||
goto encoding_error;
|
||||
if ((c & 0xf0) == 0xf0) {
|
||||
if (cur[3] == 0) {
|
||||
xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
|
||||
cur = ctxt->input->cur;
|
||||
}
|
||||
if (((c & 0xf8) != 0xf0) ||
|
||||
((cur[3] & 0xc0) != 0x80))
|
||||
goto encoding_error;
|
||||
/* 4-byte code */
|
||||
*len = 4;
|
||||
val = (cur[0] & 0x7) << 18;
|
||||
val |= (cur[1] & 0x3f) << 12;
|
||||
val |= (cur[2] & 0x3f) << 6;
|
||||
val |= cur[3] & 0x3f;
|
||||
if (val < 0x10000)
|
||||
goto encoding_error;
|
||||
} else {
|
||||
/* 3-byte code */
|
||||
*len = 3;
|
||||
val = (cur[0] & 0xf) << 12;
|
||||
val |= (cur[1] & 0x3f) << 6;
|
||||
val |= cur[2] & 0x3f;
|
||||
if (val < 0x800)
|
||||
goto encoding_error;
|
||||
}
|
||||
} else {
|
||||
/* 2-byte code */
|
||||
*len = 2;
|
||||
val = (cur[0] & 0x1f) << 6;
|
||||
val |= cur[1] & 0x3f;
|
||||
if (val < 0x80)
|
||||
goto encoding_error;
|
||||
}
|
||||
if (!IS_CHAR(val)) {
|
||||
htmlParseErrInt(ctxt, XML_ERR_INVALID_CHAR,
|
||||
"Char 0x%X out of allowed range\n", val);
|
||||
}
|
||||
return(val);
|
||||
} else {
|
||||
if ((*ctxt->input->cur == 0) &&
|
||||
(ctxt->input->cur < ctxt->input->end)) {
|
||||
htmlParseErrInt(ctxt, XML_ERR_INVALID_CHAR,
|
||||
"Char 0x%X out of allowed range\n", 0);
|
||||
*len = 1;
|
||||
return(' ');
|
||||
}
|
||||
/* 1-byte code */
|
||||
*len = 1;
|
||||
return((int) *ctxt->input->cur);
|
||||
}
|
||||
|
||||
encoding_error:
|
||||
/*
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user