Improve error descriptions for capture lists (#709)

Author: zherczeg

src/pcre2_compile.c

@@ -2707,7 +2707,7 @@ int i;
 
 if (ptr >= ptrend || *ptr != CHAR_LEFT_PARENTHESIS)
   {
-  *errorcodeptr = ERR15;
+  *errorcodeptr = ERR118;
   goto FAILED;
   }
 
@@ -2716,6 +2716,12 @@ for (;;)
   ptr++;
   next_offset = (PCRE2_SIZE)(ptr - cb->start_pattern);
 
+  if (ptr >= ptrend)
+    {
+    *errorcodeptr = ERR117;
+    goto FAILED;
+    }
+
   /* Handle [+-]number cases */
   if (read_number(&ptr, ptrend, cb->bracount, MAX_GROUP_NUMBER, ERR61,
       &i, errorcodeptr))
@@ -2732,16 +2738,14 @@ for (;;)
   else if (*errorcodeptr != 0) goto FAILED; /* Number too big */
   else
     {
-    if (ptr >= ptrend) goto UNCLOSED_PARENTHESIS;
-
     /* Handle 'name' or <name> cases. */
     if (*ptr == CHAR_LESS_THAN_SIGN)
       terminator = CHAR_GREATER_THAN_SIGN;
     else if (*ptr == CHAR_APOSTROPHE)
       terminator = CHAR_APOSTROPHE;
     else
       {
-      *errorcodeptr = ERR15;
+      *errorcodeptr = ERR117;
       goto FAILED;
       }
 
@@ -4767,8 +4771,7 @@ while (ptr < ptrend)
           goto NEGATIVE_LOOK_AHEAD;
 
           case META_SCS:
-          if (++ptr >= ptrend) goto UNCLOSED_PARENTHESIS;
-
+          ptr++;
           *parsed_pattern++ = META_SCS;
 
           parsed_pattern = parse_capture_list(&ptr, ptrend, utf, parsed_pattern,

src/pcre2_compile.h

@@ -51,18 +51,18 @@ pcre2.h.in must be updated - their values are exactly 100 greater than these
 values. */
 
 enum { ERR0 = COMPILE_ERROR_BASE,
-       ERR1,  ERR2,  ERR3,  ERR4,  ERR5,  ERR6,  ERR7,  ERR8,  ERR9,  ERR10,
-       ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19, ERR20,
-       ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, ERR30,
-       ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, ERR40,
-       ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, ERR50,
-       ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59, ERR60,
-       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, ERR97, ERR98, ERR99, ERR100,
-       ERR101,ERR102,ERR103,ERR104,ERR105,ERR106,ERR107,ERR108,ERR109,ERR110,
-       ERR111,ERR112,ERR113,ERR114,ERR115,ERR116 };
+       ERR1,   ERR2,   ERR3,   ERR4,   ERR5,   ERR6,   ERR7,   ERR8,   ERR9,   ERR10,
+       ERR11,  ERR12,  ERR13,  ERR14,  ERR15,  ERR16,  ERR17,  ERR18,  ERR19,  ERR20,
+       ERR21,  ERR22,  ERR23,  ERR24,  ERR25,  ERR26,  ERR27,  ERR28,  ERR29,  ERR30,
+       ERR31,  ERR32,  ERR33,  ERR34,  ERR35,  ERR36,  ERR37,  ERR38,  ERR39,  ERR40,
+       ERR41,  ERR42,  ERR43,  ERR44,  ERR45,  ERR46,  ERR47,  ERR48,  ERR49,  ERR50,
+       ERR51,  ERR52,  ERR53,  ERR54,  ERR55,  ERR56,  ERR57,  ERR58,  ERR59,  ERR60,
+       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,  ERR97,  ERR98,  ERR99,  ERR100,
+       ERR101, ERR102, ERR103, ERR104, ERR105, ERR106, ERR107, ERR108, ERR109, ERR110,
+       ERR111, ERR112, ERR113, ERR114, ERR115, ERR116, ERR117, ERR118 };
 
 /* Code values for parsed patterns, which are stored in a vector of 32-bit
 unsigned ints. Values less than META_END are literal data values. The coding

src/pcre2_error.c

@@ -206,6 +206,8 @@ static const unsigned char compile_error_texts[] =
   /* 115 */
   "terminating ] with no following closing parenthesis in (?[...]\0"
   "unexpected character in (?[...]) extended character class\0"
+  "expected capture group number or name\0"
+  "missing opening parenthesis\0"
   ;
 
 /* Match-time and UTF error texts are in the same format. */

testdata/testinput2

@@ -7838,6 +7838,8 @@ a)"xI
 
 /(?1:1/
 
+/(?R:(1/
+
 /(?R:(1,/
 
 /(?R0:(1,2!/

testdata/testoutput2

@@ -18812,10 +18812,10 @@ No match
 # Parse errors first
 
 /(*scs:/
-Failed: error 114 at offset 6: missing closing parenthesis
+Failed: error 218 at offset 6: missing opening parenthesis
 
 /(*scan_substring:(/
-Failed: error 114 at offset 18: missing closing parenthesis
+Failed: error 217 at offset 18: expected capture group number or name
 
 /(*scs:('name'/
 Failed: error 114 at offset 13: missing closing parenthesis
@@ -21885,13 +21885,16 @@ Failed: error -69: error performing replacement case transformation
 # Parse error tests
 
 /(?1:/
-Failed: error 115 at offset 4: reference to non-existent subpattern
+Failed: error 218 at offset 4: missing opening parenthesis
 
 /(?1:1/
-Failed: error 115 at offset 4: reference to non-existent subpattern
+Failed: error 218 at offset 4: missing opening parenthesis
+
+/(?R:(1/
+Failed: error 114 at offset 6: missing closing parenthesis
 
 /(?R:(1,/
-Failed: error 114 at offset 7: missing closing parenthesis
+Failed: error 217 at offset 7: expected capture group number or name
 
 /(?R0:(1,2!/
 Failed: error 158 at offset 3: (?R (recursive pattern call) must be followed by a closing parenthesis