a30e3ddd6c
handle utf8 encoding better.
62 lines
1.9 KiB
Plaintext
62 lines
1.9 KiB
Plaintext
$OpenBSD: patch-src_codecs_qutfcodec_cpp,v 1.1 2007/03/31 22:49:46 espie Exp $
|
|
--- src/codecs/qutfcodec.cpp.orig Thu Oct 19 16:25:07 2006
|
|
+++ src/codecs/qutfcodec.cpp Sat Mar 31 14:51:50 2007
|
|
@@ -154,6 +154,7 @@ int QUtf8Codec::heuristicContentMatch(const char* char
|
|
|
|
class QUtf8Decoder : public QTextDecoder {
|
|
uint uc;
|
|
+ uint min_uc;
|
|
int need;
|
|
bool headerDone;
|
|
public:
|
|
@@ -167,8 +168,9 @@ class QUtf8Decoder : public QTextDecoder { (public)
|
|
result.setLength( len ); // worst case
|
|
QChar *qch = (QChar *)result.unicode();
|
|
uchar ch;
|
|
+ int error = -1;
|
|
for (int i=0; i<len; i++) {
|
|
- ch = *chars++;
|
|
+ ch = chars[i];
|
|
if (need) {
|
|
if ( (ch&0xc0) == 0x80 ) {
|
|
uc = (uc << 6) | (ch & 0x3f);
|
|
@@ -182,6 +184,8 @@ class QUtf8Decoder : public QTextDecoder { (public)
|
|
*qch++ = QChar(high);
|
|
*qch++ = QChar(low);
|
|
headerDone = TRUE;
|
|
+ } else if ((uc < min_uc) || (uc >= 0xd800 && uc <= 0xdfff) || (uc >= 0xfffe)) {
|
|
+ *qch++ = QChar::replacement;
|
|
} else {
|
|
if (headerDone || QChar(uc) != QChar::byteOrderMark)
|
|
*qch++ = uc;
|
|
@@ -190,6 +194,7 @@ class QUtf8Decoder : public QTextDecoder { (public)
|
|
}
|
|
} else {
|
|
// error
|
|
+ i = error;
|
|
*qch++ = QChar::replacement;
|
|
need = 0;
|
|
}
|
|
@@ -200,12 +205,21 @@ class QUtf8Decoder : public QTextDecoder { (public)
|
|
} else if ((ch & 0xe0) == 0xc0) {
|
|
uc = ch & 0x1f;
|
|
need = 1;
|
|
+ error = i;
|
|
+ min_uc = 0x80;
|
|
} else if ((ch & 0xf0) == 0xe0) {
|
|
uc = ch & 0x0f;
|
|
need = 2;
|
|
+ error = i;
|
|
+ min_uc = 0x800;
|
|
} else if ((ch&0xf8) == 0xf0) {
|
|
uc = ch & 0x07;
|
|
need = 3;
|
|
+ error = i;
|
|
+ min_uc = 0x10000;
|
|
+ } else {
|
|
+ // error
|
|
+ *qch++ = QChar::replacement;
|
|
}
|
|
}
|
|
}
|