qt-bugs@ issue : N154454
bugs.kde.org number : none
applied: no
author: Dirk Mueller <mueller@kde.org>

This patch makes the utf8 decoders in Qt reject overlong
sequences, like required.

--- src/codecs/qutfcodec.cpp
+++ src/codecs/qutfcodec.cpp
@@ -154,6 +154,7 @@
 
 class QUtf8Decoder : public QTextDecoder {
     uint uc;
+    uint min_uc;
     int need;
     bool headerDone;
 public:
@@ -167,8 +168,9 @@
 	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 @@
 			    *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 @@
 		    }
 		} else {
 		    // error
+                    i = error;
 		    *qch++ = QChar::replacement;
 		    need = 0;
 		}
@@ -200,12 +205,21 @@
 		} 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;
 		}
 	    }
 	}
--- src/tools/qstring.cpp
+++ src/tools/qstring.cpp
@@ -5805,6 +5805,7 @@
     result.setLength( len ); // worst case
     QChar *qch = (QChar *)result.unicode();
     uint uc = 0;
+    uint min_uc = 0;
     int need = 0;
     int error = -1;
     uchar ch;
@@ -5822,6 +5823,12 @@
 			unsigned short low = uc%0x400 + 0xdc00;
 			*qch++ = QChar(high);
 			*qch++ = QChar(low);
+		    } else if (uc < min_uc || (uc >= 0xd800 && uc <= 0xdfff) || (uc >= 0xfffe)) {
+			// overlong seqence, UTF16 surrogate or BOM
+                        i = error;
+                        qch = addOne(qch, result);
+                        *qch++ = QChar(0xdbff);
+                        *qch++ = QChar(0xde00+((uchar)utf8[i]));
 		    } else {
 			*qch++ = uc;
 		    }
@@ -5844,14 +5851,17 @@
 		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 = addOne(qch, result);