Implement a check on the number of capturing parentheses, which for some reason

has never existed. This fixes ClusterFuzz issue 14376. 


git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@1088 6239d852-aaf2-0410-a92c-79f79f948069

12 files changed, 46 insertions, 4 deletions

diff --git a/ChangeLog b/ChangeLog
index 66c6d0b..da4ffb6 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -2,6 +2,14 @@ Change Log for PCRE2
 --------------------
 
 
+Version 10.34 22-April-2019
+---------------------------
+
+1. The maximum number of capturing subpatterns is 65535 (documented), but no 
+check on this was ever implemented. This omission has been rectified; it fixes
+ClusterFuzz 14376.
+
+
 Version 10.33 16-April-2019
 ---------------------------
 
diff --git a/configure.ac b/configure.ac
index 93c2b53..35b947b 100644
--- a/configure.ac
+++ b/configure.ac
@@ -9,9 +9,9 @@ dnl The PCRE2_PRERELEASE feature is for identifying release candidates. It might
 dnl be defined as -RC2, for example. For real releases, it should be empty.
 
 m4_define(pcre2_major, [10])
-m4_define(pcre2_minor, [33])
-m4_define(pcre2_prerelease, [])
-m4_define(pcre2_date, [2019-04-16])
+m4_define(pcre2_minor, [34])
+m4_define(pcre2_prerelease, [-RC1])
+m4_define(pcre2_date, [2019-04-22])
 
 # NOTE: The CMakeLists.txt file searches for the above variables in the first
 # 50 lines of this file. Please update that if the variables above are moved.
diff --git a/src/pcre2.h.in b/src/pcre2.h.in
index 9415d70..29f3688 100644
--- a/src/pcre2.h.in
+++ b/src/pcre2.h.in
@@ -305,6 +305,7 @@ pcre2_pattern_convert(). */
 #define PCRE2_ERROR_INVALID_HYPHEN_IN_OPTIONS      194
 #define PCRE2_ERROR_ALPHA_ASSERTION_UNKNOWN        195
 #define PCRE2_ERROR_SCRIPT_RUN_NOT_AVAILABLE       196
+#define PCRE2_ERROR_TOO_MANY_CAPTURES              197
 
 
 /* "Expected" matching error codes: no match and partial match. */
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index 068735a..cd6fbea 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -781,7 +781,7 @@ enum { ERR0 = COMPILE_ERROR_BASE,
        ERR61, ERR62, ERR63, ERR64, ERR65, ERR66, ERR67, ERR68, ERR69, ERR70,
        ERR71, ERR72, ERR73, ERR74, ERR75, ERR76, ERR77, ERR78, ERR79, ERR80,
        ERR81, ERR82, ERR83, ERR84, ERR85, ERR86, ERR87, ERR88, ERR89, ERR90,
-       ERR91, ERR92, ERR93, ERR94, ERR95, ERR96 };
+       ERR91, ERR92, ERR93, ERR94, ERR95, ERR96, ERR97 };
 
 /* This is a table of start-of-pattern options such as (*UTF) and settings such
 as (*LIMIT_MATCH=nnnn) and (*CRLF). For completeness and backward
@@ -3611,6 +3611,11 @@ while (ptr < ptrend)
         nest_depth++;
         if ((options & PCRE2_NO_AUTO_CAPTURE) == 0)
           {
+          if (cb->bracount >= MAX_GROUP_NUMBER)
+            {
+            errorcode = ERR97;
+            goto FAILED;
+            }    
           cb->bracount++;
           *parsed_pattern++ = META_CAPTURE | cb->bracount;
           }
@@ -4435,6 +4440,11 @@ while (ptr < ptrend)
       /* We have a name for this capturing group. It is also assigned a number,
       which is its primary means of identification. */
 
+      if (cb->bracount >= MAX_GROUP_NUMBER)
+        {
+        errorcode = ERR97;
+        goto FAILED;
+        }    
       cb->bracount++;
       *parsed_pattern++ = META_CAPTURE | cb->bracount;
       nest_depth++;
diff --git a/src/pcre2_error.c b/src/pcre2_error.c
index 1d02cf1..5517e74 100644
--- a/src/pcre2_error.c
+++ b/src/pcre2_error.c
@@ -184,6 +184,7 @@ static const unsigned char compile_error_texts[] =
   /* 95 */
   "(*alpha_assertion) not recognized\0"
   "script runs require Unicode support, which this version of PCRE2 does not have\0"
+  "too many capturing groups (maximum 65535)\0"
   ;
 
 /* Match-time and UTF error texts are in the same format. */
diff --git a/testdata/testinput11 b/testdata/testinput11
index 2d267d6..fca6042 100644
--- a/testdata/testinput11
+++ b/testdata/testinput11
@@ -368,4 +368,6 @@
     abÿAz
     ab\x{80000041}z 
 
+/\[()]{65535}/expand
+
 # End of testinput11
diff --git a/testdata/testinput2 b/testdata/testinput2
index 9e59b62..8a98f94 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -5587,4 +5587,8 @@ a)"xI
 \= Expect error message
     abc\=null_context
 
+/\[()]{65535}()/expand
+
+/\[()]{65535}(?<A>)/expand
+
 # End of testinput2
diff --git a/testdata/testinput9 b/testdata/testinput9
index 7be4b15..792d610 100644
--- a/testdata/testinput9
+++ b/testdata/testinput9
@@ -260,4 +260,6 @@
 
 /(*:*++++++++++++''''''''''''''''''''+''+++'+++x+++++++++++++++++++++++++++++++++++(++++++++++++++++++++:++++++%++:''''''''''''''''''''''''+++++++++++++++++++++++++++++++++++++++++++++++++++++-++++++++k+++++++''''+++'+++++++++++++++++++++++''''++++++++++++':Æ¿)/
 
+/\[()]{65535}/expand
+
 # End of testinput9
diff --git a/testdata/testoutput11-16 b/testdata/testoutput11-16
index 78bf7fb..f2b9637 100644
--- a/testdata/testoutput11-16
+++ b/testdata/testoutput11-16
@@ -661,4 +661,7 @@ Subject length lower bound = 1
     abÿAz
     ab\x{80000041}z 
 
+/\[()]{65535}/expand
+Failed: error 120 at offset 131070: regular expression is too large
+
 # End of testinput11
diff --git a/testdata/testoutput11-32 b/testdata/testoutput11-32
index 4b00384..1908ab7 100644
--- a/testdata/testoutput11-32
+++ b/testdata/testoutput11-32
@@ -667,4 +667,6 @@ Subject length lower bound = 1
     ab\x{80000041}z 
  0: ab\x{80000041}z
 
+/\[()]{65535}/expand
+
 # End of testinput11
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 2f91c38..158fbad 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -16934,6 +16934,12 @@ Subject length lower bound = 0
     abc\=null_context
 ** Replacement callouts are not supported with null_context.
 
+/\[()]{65535}()/expand
+Failed: error 197 at offset 131071: too many capturing groups (maximum 65535)
+
+/\[()]{65535}(?<A>)/expand
+Failed: error 197 at offset 131075: too many capturing groups (maximum 65535)
+
 # End of testinput2
 Error -70: PCRE2_ERROR_BADDATA (unknown error number)
 Error -62: bad serialized data
diff --git a/testdata/testoutput9 b/testdata/testoutput9
index f98f276..f66ca3d 100644
--- a/testdata/testoutput9
+++ b/testdata/testoutput9
@@ -367,4 +367,7 @@ Failed: error 134 at offset 14: character code point value in \x{} or \o{} is to
 /(*:*++++++++++++''''''''''''''''''''+''+++'+++x+++++++++++++++++++++++++++++++++++(++++++++++++++++++++:++++++%++:''''''''''''''''''''''''+++++++++++++++++++++++++++++++++++++++++++++++++++++-++++++++k+++++++''''+++'+++++++++++++++++++++++''''++++++++++++':Æ¿)/
 Failed: error 176 at offset 259: name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
 
+/\[()]{65535}/expand
+Failed: error 120 at offset 131070: regular expression is too large
+
 # End of testinput9