Fix auto-possessify bugs for \s*\R and \S*R.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@961 2f5784b3-3f2a-0410-8824-cb99058d5e15

4 files changed, 90 insertions, 3 deletions

diff --git a/ChangeLog b/ChangeLog
index 3540768..cc900d9 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -86,6 +86,10 @@ Version 8.31
     matches in certain environments (the workspace was not being correctly
     retained). Also added to pcre_dfa_exec() a simple plausibility check on
     some of the workspace data at the beginning of a restart.
+    
+25. \s*\R was auto-possessifying the \s* when it should not, whereas \S*\R
+    was not doing so when it should - probably a typo introduced by SVN 528
+    (change 8.10/14). 
 
 
 Version 8.30 04-February-2012
diff --git a/pcre_compile.c b/pcre_compile.c
index d4aa7c9..b267f31 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -3349,10 +3349,10 @@ switch(op_code)
   return next == -ESC_d;
 
   case OP_WHITESPACE:
-  return next == -ESC_S || next == -ESC_d || next == -ESC_w || next == -ESC_R;
+  return next == -ESC_S || next == -ESC_d || next == -ESC_w;
 
   case OP_NOT_WHITESPACE:
-  return next == -ESC_s || next == -ESC_h || next == -ESC_v;
+  return next == -ESC_s || next == -ESC_h || next == -ESC_v || next == -ESC_R;
 
   case OP_HSPACE:
   return next == -ESC_S || next == -ESC_H || next == -ESC_d ||
diff --git a/testdata/testinput2 b/testdata/testinput2
index 484ba8d..7a2182d 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -3102,6 +3102,24 @@ with \Y. ---/
 /\d*\R/BZ
 
 /\s*\R/BZ
+    \x20\x0a
+    \x20\x0d
+    \x20\x0d\x0a
+
+/\S*\R/BZ
+    a\x0a
+
+/X\h*\R/BZ
+    X\x20\x0a
+
+/X\H*\R/BZ
+    X\x0d\x0a
+
+/X\H+\R/BZ
+    X\x0d\x0a
+
+/X\H++\R/BZ
+    X\x0d\x0a
 
 /-- Perl treats this one differently, not failing the second string. I believe
     that is a bug in Perl. --/
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 4acc35d..a595d6f 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -10755,11 +10755,76 @@ No match
 /\s*\R/BZ
 ------------------------------------------------------------------
         Bra
-        \s*+
+        \s*
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    \x20\x0a
+ 0:  \x0a
+    \x20\x0d
+ 0:  \x0d
+    \x20\x0d\x0a
+ 0:  \x0d\x0a
+
+/\S*\R/BZ
+------------------------------------------------------------------
+        Bra
+        \S*+
         \R
         Ket
         End
 ------------------------------------------------------------------
+    a\x0a
+ 0: a\x0a
+
+/X\h*\R/BZ
+------------------------------------------------------------------
+        Bra
+        X
+        \h*+
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    X\x20\x0a
+ 0: X \x0a
+
+/X\H*\R/BZ
+------------------------------------------------------------------
+        Bra
+        X
+        \H*
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    X\x0d\x0a
+ 0: X\x0d\x0a
+
+/X\H+\R/BZ
+------------------------------------------------------------------
+        Bra
+        X
+        \H+
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    X\x0d\x0a
+ 0: X\x0d\x0a
+
+/X\H++\R/BZ
+------------------------------------------------------------------
+        Bra
+        X
+        \H++
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    X\x0d\x0a
+No match
 
 /-- Perl treats this one differently, not failing the second string. I believe
     that is a bug in Perl. --/