Fix some numerical checking bugs, Bugzilla 2690.

ChangeLog

@@ -16,6 +16,15 @@ but I have put in a check in order to get rid of the compiler error.
 3. An alternative patch for CMakeLists.txt because 10.36 # 4 breaks CMake on
 Windows. Patch from email@cs-ware.de fixes bugzilla #2688.
 
+4. Two bugs related to over-large numbers have been fixed so the behaviour is 
+now the same as Perl.
+  
+  (a) A pattern such as /\214748364/ gave an overflow error instead of being 
+  treated as the octal number \214 followed by literal digits.
+  
+  (b) A sequence such as {65536 that has no terminating } so is not a 
+  quantifier was nevertheless complaining that a quantifier number was too big.
+
 
 Version 10.36 04-December-2020
 ------------------------------

src/pcre2_compile.c

@@ -1398,32 +1398,47 @@ static BOOL
 read_repeat_counts(PCRE2_SPTR *ptrptr, PCRE2_SPTR ptrend, uint32_t *minp,
   uint32_t *maxp, int *errorcodeptr)
 {
-PCRE2_SPTR p = *ptrptr;
+PCRE2_SPTR p;
 BOOL yield = FALSE;
+BOOL had_comma = FALSE;
 int32_t min = 0;
 int32_t max = REPEAT_UNLIMITED; /* This value is larger than MAX_REPEAT_COUNT */
 
-/* NB read_number() initializes the error code to zero. The only error is for a
+/* Check the syntax */
-number that is too big. */
 
+*errorcodeptr = 0;
+for (p = *ptrptr;; p++)
+  {
+  uint32_t c;
+  if (p >= ptrend) return FALSE;
+  c = *p;
+  if (IS_DIGIT(c)) continue;
+  if (c == CHAR_RIGHT_CURLY_BRACKET) break;
+  if (c == CHAR_COMMA)
+    {
+    if (had_comma) return FALSE;
+    had_comma = TRUE;
+    }
+  else return FALSE;   
+  }
+
+/* The only error from read_number() is for a number that is too big. */
+
+p = *ptrptr;
 if (!read_number(&p, ptrend, -1, MAX_REPEAT_COUNT, ERR5, &min, errorcodeptr))
   goto EXIT;
 
-if (p >= ptrend) goto EXIT;
-
 if (*p == CHAR_RIGHT_CURLY_BRACKET)
   {
   p++;
   max = min;
   }
-
 else
   {
-  if (*p++ != CHAR_COMMA || p >= ptrend) goto EXIT;
+  if (*(++p) != CHAR_RIGHT_CURLY_BRACKET)
-  if (*p != CHAR_RIGHT_CURLY_BRACKET)
     {
     if (!read_number(&p, ptrend, -1, MAX_REPEAT_COUNT, ERR5, &max,
-        errorcodeptr) || p >= ptrend ||  *p != CHAR_RIGHT_CURLY_BRACKET)
+        errorcodeptr))
       goto EXIT;
     if (max < min)
       {
@@ -1438,11 +1453,10 @@ yield = TRUE;
 if (minp != NULL) *minp = (uint32_t)min;
 if (maxp != NULL) *maxp = (uint32_t)max;
 
-/* Update the pattern pointer on success, or after an error, but not when
+/* Update the pattern pointer */
-the result is "not a repeat quantifier". */
 
 EXIT:
-if (yield || *errorcodeptr != 0) *ptrptr = p;
+*ptrptr = p;
 return yield;
 }
 
@@ -1776,19 +1790,23 @@ else
       {
       oldptr = ptr;
       ptr--;   /* Back to the digit */
-      if (!read_number(&ptr, ptrend, -1, INT_MAX/10 - 1, ERR61, &s,
-          errorcodeptr))
-        break;
 
-      /* \1 to \9 are always back references. \8x and \9x are too; \1x to \7x
+      /* As we know we are at a digit, the only possible error from
+      read_number() is a number that is too large to be a group number. In this
+      case we fall through handle this as not a group reference. If we have
+      read a small enough number, check for a back reference.
+
+      \1 to \9 are always back references. \8x and \9x are too; \1x to \7x
       are octal escapes if there are not that many previous captures. */
 
-      if (s < 10 || oldptr[-1] >= CHAR_8 || s <= (int)cb->bracount)
+      if (read_number(&ptr, ptrend, -1, INT_MAX/10 - 1, 0, &s, errorcodeptr) &&
+          (s < 10 || oldptr[-1] >= CHAR_8 || s <= (int)cb->bracount))
         {
         if (s > (int)MAX_GROUP_NUMBER) *errorcodeptr = ERR61;
           else escape = -s;     /* Indicates a back reference */
         break;
         }
+
       ptr = oldptr;      /* Put the pointer back and fall through */
       }
 

testdata/testinput1

@@ -6420,4 +6420,13 @@ ef) x/x,mark
 /(?(DEFINE)(?<foo>bar))(?<![-a-z0-9])word/
     word
 
+/a{1,2,3}b/
+    a{1,2,3}b
+
+/\214748364/
+    >\x{8c}748364<
+    
+/a{65536/
+    >a{65536<
+
 # End of testinput1 

testdata/testinput11

@@ -368,4 +368,7 @@
     ab˙Az
     ab\x{80000041}z 
 
+/(?i:A{1,}\6666666666)/
+    A\x{1b6}6666666
+
 # End of testinput11

testdata/testinput2

@@ -2189,8 +2189,6 @@
 
 /a(*MARK)b/
 
-/(?i:A{1,}\6666666666)/
-
 /\g6666666666/
 
 /[\g6666666666]/B

testdata/testinput9

@@ -260,4 +260,7 @@
 
 /(*:*++++++++++++''''''''''''''''''''+''+++'+++x+++++++++++++++++++++++++++++++++++(++++++++++++++++++++:++++++%++:''''''''''''''''''''''''+++++++++++++++++++++++++++++++++++++++++++++++++++++-++++++++k+++++++''''+++'+++++++++++++++++++++++''''++++++++++++':ƿ)/
 
+/(?i:A{1,}\6666666666)/
+    A\x{1b6}6666666
+
 # End of testinput9

testdata/testoutput1

@@ -10176,4 +10176,16 @@ No match
     word
  0: word
 
+/a{1,2,3}b/
+    a{1,2,3}b
+ 0: a{1,2,3}b
+
+/\214748364/
+    >\x{8c}748364<
+ 0: \x8c748364
+    
+/a{65536/
+    >a{65536<
+ 0: a{65536
+
 # End of testinput1 

testdata/testoutput11-16

@@ -661,4 +661,8 @@ Subject length lower bound = 1
     ab˙Az
     ab\x{80000041}z 
 
+/(?i:A{1,}\6666666666)/
+    A\x{1b6}6666666
+ 0: A\x{1b6}6666666
+
 # End of testinput11

testdata/testoutput11-32

@@ -667,4 +667,8 @@ Subject length lower bound = 1
     ab\x{80000041}z 
  0: ab\x{80000041}z
 
+/(?i:A{1,}\6666666666)/
+    A\x{1b6}6666666
+ 0: A\x{1b6}6666666
+
 # End of testinput11

testdata/testoutput2

@@ -8374,9 +8374,6 @@ No match
 /a(*MARK)b/
 Failed: error 166 at offset 7: (*MARK) must have an argument
 
-/(?i:A{1,}\6666666666)/
-Failed: error 161 at offset 19: subpattern number is too big
-
 /\g6666666666/
 Failed: error 161 at offset 7: subpattern number is too big
 

testdata/testoutput9

@@ -367,4 +367,8 @@ Failed: error 134 at offset 14: character code point value in \x{} or \o{} is to
 /(*:*++++++++++++''''''''''''''''''''+''+++'+++x+++++++++++++++++++++++++++++++++++(++++++++++++++++++++:++++++%++:''''''''''''''''''''''''+++++++++++++++++++++++++++++++++++++++++++++++++++++-++++++++k+++++++''''+++'+++++++++++++++++++++++''''++++++++++++':ƿ)/
 Failed: error 176 at offset 259: name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
 
+/(?i:A{1,}\6666666666)/
+Failed: error 151 at offset 13: octal value is greater than \377 in 8-bit non-UTF-8 mode
+    A\x{1b6}6666666
+
 # End of testinput9