Magic-Mirror/gecko-dev
1
0
Fork 0
mirror of https://github.com/mozilla/gecko-dev.git synced 2024-12-02 10:00:54 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix bug 39197. r=erik. Detect UTF8 BOM since Win2K notepad generate them

Browse Source
This commit is contained in:
ftang%netscape.com 2000-05-16 21:35:40 +00:00
parent 824cb7fac1
commit ca40fc6994
2 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
htmlparser/src/nsParser.cpp
View File

@ -1670,12 +1670,16 @@ nsresult nsParser::OnStartRequest(nsIChannel* channel, nsISupports* aContext)
#define UCS4_LE "UTF-32LE"
#define UCS4_2143 "X-ISO-10646-UCS-4-2143"
#define UCS4_3412 "X-ISO-10646-UCS-4-3412"
#define UTF8 "UTF-8"
static PRBool detectByteOrderMark(const unsigned char* aBytes, PRInt32 aLen, nsString& oCharset, nsCharsetSource& oCharsetSource) {
oCharsetSource= kCharsetFromAutoDetection;
oCharset.SetLength(0);
// see http://www.w3.org/TR/1998/REC-xml-19980210#sec-oCharseting
// for details
// Also, MS Win2K notepad now generate 3 bytes BOM in UTF8 as UTF8 signature
// We need to check that
// UCS2 BOM FEFF = UTF8 EF BB BF
switch(aBytes[0])
{
case 0x00:
@ -1741,6 +1745,14 @@ static PRBool detectByteOrderMark(const unsigned char* aBytes, PRInt32 aLen, nsS
}
}
break;
case 0xEF:
if((0xBB==aBytes[1]) && (0xBF==aBytes[2])) {
// EF BB BF
// Win2K UTF-8 BOM
oCharset.AssignWithConversion(UTF8);
oCharsetSource= kCharsetFromByteOrderMark;
}
break;
case 0xFE:
if(0xFF==aBytes[1]) {
// FE FF

12
parser/htmlparser/src/nsParser.cpp
View File

@ -1670,12 +1670,16 @@ nsresult nsParser::OnStartRequest(nsIChannel* channel, nsISupports* aContext)
#define UCS4_LE "UTF-32LE"
#define UCS4_2143 "X-ISO-10646-UCS-4-2143"
#define UCS4_3412 "X-ISO-10646-UCS-4-3412"
#define UTF8 "UTF-8"
static PRBool detectByteOrderMark(const unsigned char* aBytes, PRInt32 aLen, nsString& oCharset, nsCharsetSource& oCharsetSource) {
oCharsetSource= kCharsetFromAutoDetection;
oCharset.SetLength(0);
// see http://www.w3.org/TR/1998/REC-xml-19980210#sec-oCharseting
// for details
// Also, MS Win2K notepad now generate 3 bytes BOM in UTF8 as UTF8 signature
// We need to check that
// UCS2 BOM FEFF = UTF8 EF BB BF
switch(aBytes[0])
{
case 0x00:
@ -1741,6 +1745,14 @@ static PRBool detectByteOrderMark(const unsigned char* aBytes, PRInt32 aLen, nsS
}
}
break;
case 0xEF:
if((0xBB==aBytes[1]) && (0xBF==aBytes[2])) {
// EF BB BF
// Win2K UTF-8 BOM
oCharset.AssignWithConversion(UTF8);
oCharsetSource= kCharsetFromByteOrderMark;
}
break;
case 0xFE:
if(0xFF==aBytes[1]) {
// FE FF