diff --git a/ChangeLog b/ChangeLog index 878b306..9d0bb57 100644 --- a/ChangeLog +++ b/ChangeLog @@ -37,6 +37,11 @@ use. 8. Minor tidies to the pcre2demo.c sample program, including more comments about its 8-bit-ness. +9. Detect unmatched closing parentheses and give the error in the pre-scan +instead of later. Previously the pre-scan carried on and could give a +misleading incorrect error message. For example, /(?J)(?'a'))(?'a')/ gave a +message about invalid duplicate group names. + Version 10.21 12-January-2016 ----------------------------- diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c index d852837..e33d620 100644 --- a/src/pcre2_compile.c +++ b/src/pcre2_compile.c @@ -3377,27 +3377,24 @@ for (; ptr < cb->end_pattern; ptr++) if ((options & PCRE2_NO_AUTO_CAPTURE) == 0) cb->bracount++; } - /* (*something) - just skip to closing ket unless PCRE2_ALT_VERBNAMES is - set, in which case we have to process escapes in the string after the - name. */ + /* (*something) - skip over a name, and then just skip to closing ket + unless PCRE2_ALT_VERBNAMES is set, in which case we have to process + escapes in the string after a verb name terminated by a colon. */ else { ptr += 2; while (MAX_255(*ptr) && (cb->ctypes[*ptr] & ctype_word) != 0) ptr++; - if (*ptr == CHAR_COLON) + if (*ptr == CHAR_COLON && (options & PCRE2_ALT_VERBNAMES) != 0) { ptr++; - if ((options & PCRE2_ALT_VERBNAMES) != 0) - { - if (process_verb_name(&ptr, NULL, &errorcode, options, utf, cb) < 0) - goto FAILED; - } - else - { - while (ptr < cb->end_pattern && *ptr != CHAR_RIGHT_PARENTHESIS) - ptr++; - } + if (process_verb_name(&ptr, NULL, &errorcode, options, utf, cb) < 0) + goto FAILED; + } + else + { + while (ptr < cb->end_pattern && *ptr != CHAR_RIGHT_PARENTHESIS) + ptr++; } nest_depth--; } @@ -3748,7 +3745,12 @@ for (; ptr < cb->end_pattern; ptr++) if (top_nest == (nest_save *)(cb->start_workspace)) top_nest = NULL; else top_nest--; } - if (nest_depth > 0) nest_depth--; /* Can be 0 for unmatched ) */ + if (nest_depth == 0) /* Unmatched closing parenthesis */ + { + errorcode = ERR22; + goto FAILED; + } + nest_depth--; break; } } @@ -8704,14 +8706,11 @@ if (cb.had_accept) reqcuflags = REQ_NONE; } -/* If we have not reached end of pattern after a successful compile, there's an -excess bracket. Fill in the final opcode and check for disastrous overflow. -If no overflow, but the estimated length exceeds the really used length, adjust -the value of re->blocksize, and if valgrind support is configured, mark the -extra allocated memory as unaddressable, so that any out-of-bound reads can be -detected. */ +/* Fill in the final opcode and check for disastrous overflow. If no overflow, +but the estimated length exceeds the really used length, adjust the value of +re->blocksize, and if valgrind support is configured, mark the extra allocated +memory as unaddressable, so that any out-of-bound reads can be detected. */ -if (errorcode == 0 && ptr < cb.end_pattern) errorcode = ERR22; *code++ = OP_END; usedlength = code - codestart; if (usedlength > length) errorcode = ERR23; else diff --git a/testdata/testinput2 b/testdata/testinput2 index 40f22c4..51a1bfa 100644 --- a/testdata/testinput2 +++ b/testdata/testinput2 @@ -4804,4 +4804,6 @@ a)"xI /effg/hex +/(?J)(?'a'))(?'a')/ + # End of testinput2 diff --git a/testdata/testoutput2 b/testdata/testoutput2 index 13b7f7c..ce116fc 100644 --- a/testdata/testoutput2 +++ b/testdata/testoutput2 @@ -15165,4 +15165,7 @@ MK: A\x00b /effg/hex ** Unexpected non-hex-digit 'g' in hex pattern: quote missing? +/(?J)(?'a'))(?'a')/ +Failed: error 122 at offset 10: unmatched closing parenthesis + # End of testinput2