Improve error messages for NO_BS0 and PYTHON_OCTAL errors

src/pcre2.h.in

@@ -321,10 +321,11 @@ pcre2_pattern_convert(). */
 #define PCRE2_ERROR_ALPHA_ASSERTION_UNKNOWN        195
 #define PCRE2_ERROR_SCRIPT_RUN_NOT_AVAILABLE       196
 #define PCRE2_ERROR_TOO_MANY_CAPTURES              197
-#define PCRE2_ERROR_CONDITION_ATOMIC_ASSERTION_EXPECTED  198
+#define PCRE2_ERROR_MISSING_OCTAL_DIGIT            198
 #define PCRE2_ERROR_BACKSLASH_K_IN_LOOKAROUND      199
 #define PCRE2_ERROR_MAX_VAR_LOOKBEHIND_EXCEEDED    200
 #define PCRE2_ERROR_PATTERN_COMPILED_SIZE_TOO_BIG  201
+#define PCRE2_ERROR_OVERSIZE_PYTHON_OCTAL          202
 
 
 /* "Expected" matching error codes: no match and partial match. */

src/pcre2_compile.c

@@ -1890,16 +1890,19 @@ else
     c -= CHAR_0;
     while(i++ < 2 && ptr < ptrend && *ptr >= CHAR_0 && *ptr <= CHAR_7)
         c = c * 8 + *ptr++ - CHAR_0;
+    if (c > 0xff)
+      {
+      if ((xoptions & PCRE2_EXTRA_PYTHON_OCTAL) != 0) *errorcodeptr = ERR102;
 #if PCRE2_CODE_UNIT_WIDTH == 8
-    if (!utf && c > 0xff) *errorcodeptr = ERR51;
+      else if (!utf) *errorcodeptr = ERR51;
 #endif
-    if ((xoptions & PCRE2_EXTRA_PYTHON_OCTAL) != 0 && c > 0xff)
-        *errorcodeptr = ERR51;
+      }
 
     /* PCRE2_EXTRA_NO_BS0 disables the NUL escape '\0' but doesn't affect
     two- or three-character octal escapes \00 and \000, nor \x00. */
+
     if ((xoptions & PCRE2_EXTRA_NO_BS0) != 0 && c == 0 && i == 1)
-        *errorcodeptr = ERR3;
+        *errorcodeptr = ERR98;
     break;
 
     /* \o is a relatively new Perl feature, supporting a more general way of

src/pcre2_compile.h

@@ -61,7 +61,7 @@ enum { ERR0 = COMPILE_ERROR_BASE,
        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 };
+       ERR101,ERR102 };
 
 /* 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

@@ -185,11 +185,12 @@ static const unsigned char compile_error_texts[] =
   "(*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"
-  "UNUSED ERROR\0"
+  "octal digit missing after \\0 (PCRE2_EXTRA_NO_BS0 is set)\0"
   "\\K is not allowed in lookarounds (but see PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK)\0"
   /* 100 */
   "branch too long in variable-length lookbehind assertion\0"
   "compiled pattern would be longer than the limit set by the application\0"
+  "octal value given by \\ddd is greater than \\377 (forbidden by PCRE2_EXTRA_PYTHON_OCTAL)\0"
   ;
 
 /* Match-time and UTF error texts are in the same format. */

src/pcre2posix.c

@@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
      Original API code Copyright (c) 1997-2012 University of Cambridge
-          New API code Copyright (c) 2016-2022 University of Cambridge
+          New API code Copyright (c) 2016-2024 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -98,7 +98,8 @@ changed. This #define is a copy of the one in pcre2_internal.h. */
 /* Table to translate PCRE2 compile time error codes into POSIX error codes.
 Only a few PCRE2 errors with a value greater than 23 turn into special POSIX
 codes: most go to REG_BADPAT. The second table lists, in pairs, those that
-don't. */
+don't, even though some of them cannot currently be provoked from within the
+POSIX wrapper. */
 
 static const int eint1[] = {
   0,           /* No error */
@@ -137,7 +138,9 @@ static const int eint2[] = {
   37, REG_EESCAPE, /* PCRE2 does not support \L, \l, \N{name}, \U, or \u */
   56, REG_INVARG,  /* internal error: unknown newline setting */
   92, REG_INVARG,  /* invalid option bits with PCRE2_LITERAL */
-  99, REG_EESCAPE  /* \K in lookaround */
+  98, REG_EESCAPE, /* missing digit after \0 in NO_BS0 mode */
+  99, REG_EESCAPE, /* \K in lookaround */
+ 102, REG_EESCAPE  /* \ddd octal > \377 in PYTHON_OCTAL mode */  
 };
 
 /* Table of texts corresponding to POSIX error codes */

testdata/testoutput10

@@ -1965,7 +1965,7 @@ Failed: error 151 at offset 4: octal value is greater than \377 in 8-bit non-UTF
 Failed: error -57 at offset 4 in replacement: bad escape sequence in replacement string
 
 /\400/python_octal
-Failed: error 151 at offset 4: octal value is greater than \377 in 8-bit non-UTF-8 mode
+Failed: error 202 at offset 4: octal value given by \ddd is greater than \377 (forbidden by PCRE2_EXTRA_PYTHON_OCTAL)
 
 /abc/substitute_extended,python_octal
     abc\=replace=\400
@@ -1978,7 +1978,7 @@ Failed: error -57 at offset 4 in replacement: bad escape sequence in replacement
  1: \x{100}
 
 /\400/utf,python_octal
-Failed: error 151 at offset 4: octal value is greater than \377 in 8-bit non-UTF-8 mode
+Failed: error 202 at offset 4: octal value given by \ddd is greater than \377 (forbidden by PCRE2_EXTRA_PYTHON_OCTAL)
 
 /abc/utf,substitute_extended,python_octal
     abc\=replace=\400

testdata/testoutput2

@@ -19477,7 +19477,7 @@ Failed: error 161 at offset 12: subpattern number is too big
  0: a\x00b\x00c\x00d
 
 /a\0b/no_bs0
-Failed: error 103 at offset 3: unrecognized character follows \
+Failed: error 198 at offset 3: octal digit missing after \0 (PCRE2_EXTRA_NO_BS0 is set)
 
 /b\x00c\00d/no_bs0
     b\x{00}c\x{00}d

testdata/testoutput5

@@ -5530,7 +5530,7 @@ Failed: error 147 at offset 10: unknown property after \P or \p
  0: \x{100}
 
 /\400/utf,python_octal
-Failed: error 151 at offset 4: octal value is greater than \377 in 8-bit non-UTF-8 mode
+Failed: error 202 at offset 4: octal value given by \ddd is greater than \377 (forbidden by PCRE2_EXTRA_PYTHON_OCTAL)
 
 /abc/utf,substitute_extended
     abc\=replace=\400