From eafc667136c28fdde28d5dbc775ad978f888aa71 Mon Sep 17 00:00:00 2001
From: Giuseppe D'Angelo <dangelog@gmail.com>
Date: Wed, 29 Feb 2012 00:02:53 +0000
Subject: QRegExp: fix \i \I \c \C \p \P escape sequences

Those escape sequences have a special meaning in the XML Schema 1.1
regular expressions, but not in Perl-compatible ones.

An escape sequence that has no special meaning should match the
escaped character itself; this patch fixes QRegExp's behaviour in
that regard (previously, it added a character class matching
nothing).

Change-Id: I983f923baa7c2ec19938b96353f3a205e6c06d58
Reviewed-by: Andy Shaw <andy.shaw@digia.com>
Reviewed-by: Thiago Macieira <thiago.macieira@intel.com>
---
 src/corelib/tools/qregexp.cpp | 39 ++++++++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 13 deletions(-)

(limited to 'src/corelib/tools')

diff --git a/src/corelib/tools/qregexp.cpp b/src/corelib/tools/qregexp.cpp
index d7bcd0edbc..e55144ec4c 100644
--- a/src/corelib/tools/qregexp.cpp
+++ b/src/corelib/tools/qregexp.cpp
@@ -3015,6 +3015,8 @@ int QRegExpEngine::getEscape()
         if (xmlSchemaExtensions) {
             yyCharClass->setNegative(!yyCharClass->negative());
             // fall through
+        } else {
+            break;
         }
     case 'i':
         if (xmlSchemaExtensions) {
@@ -3045,12 +3047,16 @@ int QRegExpEngine::getEscape()
             yyCharClass->addRange(0xf900, 0xfdcf);
             yyCharClass->addRange(0xfdf0, 0xfffd);
             yyCharClass->addRange((ushort)0x10000, (ushort)0xeffff);
+            return Tok_CharClass;
+        } else {
+            break;
         }
-        return Tok_CharClass;
     case 'C':
         if (xmlSchemaExtensions) {
             yyCharClass->setNegative(!yyCharClass->negative());
             // fall through
+        } else {
+            break;
         }
     case 'c':
         if (xmlSchemaExtensions) {
@@ -3087,12 +3093,16 @@ int QRegExpEngine::getEscape()
             yyCharClass->addRange((ushort)0x10000, (ushort)0xeffff);
             yyCharClass->addRange(0x0300, 0x036f);
             yyCharClass->addRange(0x203f, 0x2040);
+            return Tok_CharClass;
+        } else {
+            break;
         }
-        return Tok_CharClass;
     case 'P':
         if (xmlSchemaExtensions) {
             yyCharClass->setNegative(!yyCharClass->negative());
             // fall through
+        } else {
+            break;
         }
     case 'p':
         if (xmlSchemaExtensions) {
@@ -3246,8 +3256,10 @@ int QRegExpEngine::getEscape()
             } else {
                 error(RXERR_CATEGORY);
             }
+            return Tok_CharClass;
+        } else {
+            break;
         }
-        return Tok_CharClass;
 #endif
 #ifndef QT_NO_REGEXP_ESCAPE
     case 'x':
@@ -3265,20 +3277,21 @@ int QRegExpEngine::getEscape()
         return Tok_Char | val;
 #endif
     default:
-        if (prevCh >= '1' && prevCh <= '9') {
+        break;
+    }
+    if (prevCh >= '1' && prevCh <= '9') {
 #ifndef QT_NO_REGEXP_BACKREF
-            val = prevCh - '0';
-            while (yyCh >= '0' && yyCh <= '9') {
-                val = (val * 10) + (yyCh - '0');
-                yyCh = getChar();
-            }
-            return Tok_BackRef | val;
+        val = prevCh - '0';
+        while (yyCh >= '0' && yyCh <= '9') {
+            val = (val * 10) + (yyCh - '0');
+            yyCh = getChar();
+        }
+        return Tok_BackRef | val;
 #else
-            error(RXERR_DISABLED);
+        error(RXERR_DISABLED);
 #endif
-        }
-        return Tok_Char | prevCh;
     }
+    return Tok_Char | prevCh;
 }
 
 #ifndef QT_NO_REGEXP_INTERVAL
-- 
cgit v1.2.3