diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 000000000..3f90bdf54 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,2 @@ +*.sh text eol=lf +*.bat text eol=crlf diff --git a/Versions/build.txt b/Versions/build.txt index 8caa513e2..7e73f8fff 100644 --- a/Versions/build.txt +++ b/Versions/build.txt @@ -1 +1 @@ -1608 +1611 diff --git a/minipath/src/Dlapi.c b/minipath/src/Dlapi.c index 8524b04f5..27aa9c2fa 100644 --- a/minipath/src/Dlapi.c +++ b/minipath/src/Dlapi.c @@ -1346,7 +1346,7 @@ BOOL DriveBox_SelectDrive(HWND hwnd,LPCWSTR lpszPath) } // Don't select anything - SendMessage(hwnd,CB_SETCURSEL,(WPARAM)-1,0); + SendMessage(hwnd,CB_SETCURSEL,(WPARAM)1,0); return FALSE; } diff --git a/onigmo/.gitignore b/onigmo/.gitignore index 085b4a143..43dbb4835 100644 --- a/onigmo/.gitignore +++ b/onigmo/.gitignore @@ -38,16 +38,30 @@ /build*/ # autotools generated files +/aclocal.m4 /autom4te.cache +/compile +/config.guess /config.h +/config.h.in /config.log /config.status +/config.sub +/configure +/depcomp +/install-sh /libtool +/ltmain.sh +/m4/*.m4 +/missing /onigmo-config /onigmo.pc /Makefile +/Makefile.in /sample/Makefile +/sample/Makefile.in /stamp-h1 +/test-driver # generated executable files /enc/mktable diff --git a/onigmo/HISTORY b/onigmo/HISTORY index 43a14e5d3..9858cc638 100644 --- a/onigmo/HISTORY +++ b/onigmo/HISTORY @@ -1,5 +1,43 @@ History of Onigmo (Oniguruma-mod) +2019/01/30: Version 6.2.0 + +2019/01/30: [dist] Update LTVERSION to "6:5:0". +2019/01/30: [dist] Delete all autotools generated files from the repository. + (PR #115) +2019/01/30: [test] Update tests. (PR #127) +2019/01/30: [impl] Add USE_CASE_MAP_API configuration. (PR #125) +2019/01/29: [test] Add some tests. (PR #124) +2019/01/29: [impl] Revise the code for searching. (PR #123) +2019/01/28: [bug] Fix initialization of the table for quick search. + This was caused by PR #113. + (Issue #120) (PR #121) +2019/01/26: [spec] (thanks omochimetaru) + Make it possible to extend UTF-8 to 31 bits. (PR #111) +2019/01/25: [dist] Remove minor version from the py command. (PR #119) +2019/01/25: [impl] Avoid negative character. (PR #118) +2019/01/25: [impl] Fix lgtm.com warnings. (PR #117) +2019/01/25: [bug] Fix that "ss" in look-behind causes syntax error. + (Issue #92) (PR #116) +2019/01/24: [bug] Fix performance regression if quantifier lower bound is 1. + (Issue #100) (PR #114) +2019/01/24: [bug] Fix performance problem with /k/i and /s/i. + (Issue #97) (PR #113) +2019/01/24: [new] Update Unicode data: Unicode 11.0.0, Emoji 11.0 (PR #112) +2019/01/24: [bug] Import the latest code from Ruby (PR #112) +2019/01/24: [impl] (thanks aycabta) + Support gperf 3.1 with backward compatibility. (PR #101) +2018/12/10: [dist] (thanks Xavier RENE-CORAIL) + Add LGTM.com code quality badges. (PR #108) +2018/11/10: [impl] (thanks Urabe, Shyouhei) + Avoid negative character. (PR #107) +2018/01/19: [impl] (thanks Tom Lord) + Remove unused variable. (PR #99) +2017/09/27: [spec] Import Ruby r58965 + Change max byte length of UTF-8 to 4 bytes. +2017/09/26: [new] Update Unicode data: Unicode 10.0.0, Emoji 5.0 (PR #93) + + 2017/09/26: Version 6.1.3 2017/09/26: [dist] Update LTVERSION to "6:4:0". diff --git a/onigmo/README b/onigmo/README index 87a48fa25..8f468bb4a 100644 --- a/onigmo/README +++ b/onigmo/README @@ -92,9 +92,10 @@ Install Case 1: Unix and Cygwin platform - 1. ./configure - 2. make - 3. make install + 1. ./autogen.sh (If `configure` doesn't exist.) + 2. ./configure + 3. make + 4. make install * uninstall diff --git a/onigmo/README.md b/onigmo/README.md index 144640491..ca29c0b7e 100644 --- a/onigmo/README.md +++ b/onigmo/README.md @@ -32,9 +32,10 @@ Install ### Case 1: Unix and Cygwin platform - 1. `./configure` - 2. `make` - 3. `make install` + 1. `./autogen.sh` (If `configure` doesn't exist.) + 2. `./configure` + 3. `make` + 4. `make install` * test diff --git a/onigmo/enc/ascii.c b/onigmo/enc/ascii.c index 8b32c414f..233971e2b 100644 --- a/onigmo/enc/ascii.c +++ b/onigmo/enc/ascii.c @@ -54,7 +54,11 @@ OnigEncodingDefine(ascii, ASCII) = { onigenc_not_support_get_ctype_code_range, onigenc_single_byte_left_adjust_char_head, onigenc_always_true_is_allowed_reverse_match, +#ifdef USE_CASE_MAP_API onigenc_single_byte_ascii_only_case_map, +#else + NULL, +#endif ENCINDEX_ASCII, ONIGENC_FLAG_NONE, }; diff --git a/onigmo/enc/unicode.c b/onigmo/enc/unicode.c index c41fe8fbd..71c1bf16c 100644 --- a/onigmo/enc/unicode.c +++ b/onigmo/enc/unicode.c @@ -651,6 +651,7 @@ onigenc_unicode_get_case_fold_codes_by_str(OnigEncoding enc, return n; } +#ifdef USE_CASE_MAP_API /* length in bytes for three characters in UTF-32; e.g. needed for ffi (U+FB03) */ #define CASE_MAPPING_SLACK 12 #define MODIFIED (flags |= ONIGENC_CASE_MODIFIED) @@ -678,15 +679,13 @@ onigenc_unicode_case_map(OnigCaseFoldType* flagP, *pp += codepoint_length; if (code <= 'z') { /* ASCII comes first */ - if (code >= 'a' && code <= 'z') { + if (code >= 'a' /*&& code <= 'z'*/) { if (flags & ONIGENC_CASE_UPCASE) { MODIFIED; if (flags & ONIGENC_CASE_FOLD_TURKISH_AZERI && code == 'i') code = I_WITH_DOT_ABOVE; - else { - code -= 'a'; - code += 'A'; - } + else + code -= 'a' - 'A'; } } else if (code >= 'A' && code <= 'Z') { @@ -796,6 +795,7 @@ SpecialsCopy: *flagP = flags; return (int )(to - to_start); } +#endif #if 0 const char onigenc_unicode_version_string[] = diff --git a/onigmo/enc/unicode/name2ctype.h b/onigmo/enc/unicode/name2ctype.h index 7cfa702f0..d1c7d8e3d 100644 --- a/onigmo/enc/unicode/name2ctype.h +++ b/onigmo/enc/unicode/name2ctype.h @@ -1,4 +1,4 @@ -/* ANSI-C code produced by gperf version 3.1 */ +/* ANSI-C code produced by gperf version 3.1 */ /* Command-line: gperf -7 -c -j1 -i1 -t -C -P -T -H uniname2ctype_hash -Q uniname2ctype_pool -N uniname2ctype_p */ #ifndef USE_UNICODE_PROPERTIES /* Computed positions: -k'1,3' */ @@ -36382,7 +36382,7 @@ uniname2ctype_hash (register const char *str, register size_t len) #ifndef USE_UNICODE_PROPERTIES return len + asso_values[(unsigned char)str[2]] + asso_values[(unsigned char)str[0]]; #else /* USE_UNICODE_PROPERTIES */ - register unsigned int hval = len; + register unsigned int hval = (unsigned int)len; switch (hval) { diff --git a/onigmo/enc/us_ascii.c b/onigmo/enc/us_ascii.c index 08f9072c4..253ee6957 100644 --- a/onigmo/enc/us_ascii.c +++ b/onigmo/enc/us_ascii.c @@ -32,7 +32,11 @@ OnigEncodingDefine(us_ascii, US_ASCII) = { onigenc_not_support_get_ctype_code_range, onigenc_single_byte_left_adjust_char_head, onigenc_always_true_is_allowed_reverse_match, +#ifdef USE_CASE_MAP_API onigenc_single_byte_ascii_only_case_map, +#else + NULL, +#endif ENCINDEX_US_ASCII, ONIGENC_FLAG_NONE, }; diff --git a/onigmo/enc/utf_8.c b/onigmo/enc/utf_8.c index f5ec6b9ea..212aa37ad 100644 --- a/onigmo/enc/utf_8.c +++ b/onigmo/enc/utf_8.c @@ -37,13 +37,19 @@ #endif #define USE_INVALID_CODE_SCHEME +/* #define USE_UTF8_31BITS */ #ifdef USE_INVALID_CODE_SCHEME /* virtual codepoint values for invalid encoding byte 0xfe and 0xff */ # define INVALID_CODE_FE 0xfffffffe # define INVALID_CODE_FF 0xffffffff #endif + +#ifndef USE_UTF8_31BITS #define VALID_CODE_LIMIT 0x0010ffff +#else +#define VALID_CODE_LIMIT 0x7fffffff +#endif #define utf8_islead(c) ((UChar )((c) & 0xc0) != 0x80) @@ -63,14 +69,19 @@ static const int EncLen_UTF8[] = { 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, +#ifndef USE_UTF8_31BITS 4, 4, 4, 4, 4, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 +#else + 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 6, 6, 1, 1 +#endif }; typedef enum { FAILURE = -2, ACCEPT, S0, S1, S2, S3, - S4, S5, S6, S7 + S4, S5, S6, S7, + S8, S9,S10,S11, } state_t; #define A ACCEPT #define F FAILURE @@ -91,7 +102,11 @@ static const signed char trans[][0x100] = { /* c */ F, F, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* d */ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* e */ 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 3, 3, +#ifndef USE_UTF8_31BITS /* f */ 5, 6, 6, 6, 7, F, F, F, F, F, F, F, F, F, F, F +#else + /* f */ 5, 6, 6, 6, 6, 6, 6, 6, 8, 9, 9, 9,10,11, F, F +#endif }, { /* S1 0 1 2 3 4 5 6 7 8 9 a b c d e f */ /* 0 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, @@ -219,6 +234,80 @@ static const signed char trans[][0x100] = { /* e */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, /* f */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F }, +#ifdef USE_UTF8_31BITS + { /* S8 0 1 2 3 4 5 6 7 8 9 a b c d e f */ + /* 0 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 1 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 2 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 3 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 4 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 5 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 6 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 7 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 8 */ F, F, F, F, F, F, F, F, 6, 6, 6, 6, 6, 6, 6, 6, + /* 9 */ 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + /* a */ 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + /* b */ 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + /* c */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* d */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* e */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* f */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F + }, + { /* S9 0 1 2 3 4 5 6 7 8 9 a b c d e f */ + /* 0 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 1 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 2 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 3 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 4 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 5 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 6 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 7 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 8 */ 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + /* 9 */ 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + /* a */ 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + /* b */ 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + /* c */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* d */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* e */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* f */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F + }, + { /* S10 0 1 2 3 4 5 6 7 8 9 a b c d e f */ + /* 0 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 1 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 2 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 3 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 4 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 5 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 6 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 7 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 8 */ F, F, F, F, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + /* 9 */ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + /* a */ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + /* b */ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + /* c */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* d */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* e */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* f */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F + }, + { /* S11 0 1 2 3 4 5 6 7 8 9 a b c d e f */ + /* 0 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 1 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 2 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 3 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 4 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 5 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 6 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 7 */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* 8 */ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + /* 9 */ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + /* a */ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + /* b */ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, + /* c */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* d */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* e */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, + /* f */ F, F, F, F, F, F, F, F, F, F, F, F, F, F, F, F + }, +#endif // USE_UTF8_31BITS }; #undef A #undef F @@ -244,8 +333,24 @@ mbc_enc_len(const UChar* p, const UChar* e, OnigEncoding enc ARG_UNUSED) if (p == e) return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(EncLen_UTF8[firstbyte]-3); s = trans[s][*p++]; + +#ifndef USE_UTF8_31BITS return s == ACCEPT ? ONIGENC_CONSTRUCT_MBCLEN_CHARFOUND(4) : ONIGENC_CONSTRUCT_MBCLEN_INVALID(); +#else + if (s < 0) return s == ACCEPT ? ONIGENC_CONSTRUCT_MBCLEN_CHARFOUND(4) : + ONIGENC_CONSTRUCT_MBCLEN_INVALID(); + + if (p == e) return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(EncLen_UTF8[firstbyte]-4); + s = trans[s][*p++]; + if (s < 0) return s == ACCEPT ? ONIGENC_CONSTRUCT_MBCLEN_CHARFOUND(5) : + ONIGENC_CONSTRUCT_MBCLEN_INVALID(); + + if (p == e) return ONIGENC_CONSTRUCT_MBCLEN_NEEDMORE(EncLen_UTF8[firstbyte]-5); + s = trans[s][*p++]; + return s == ACCEPT ? ONIGENC_CONSTRUCT_MBCLEN_CHARFOUND(6) : + ONIGENC_CONSTRUCT_MBCLEN_INVALID(); +#endif } static int @@ -308,7 +413,13 @@ code_to_mbclen(OnigCodePoint code, OnigEncoding enc ARG_UNUSED) if ((code & 0xffffff80) == 0) return 1; else if ((code & 0xfffff800) == 0) return 2; else if ((code & 0xffff0000) == 0) return 3; +#ifndef USE_UTF8_31BITS else if (code <= VALID_CODE_LIMIT) return 4; +#else + else if ((code & 0xffe00000) == 0) return 4; + else if ((code & 0xfc000000) == 0) return 5; + else if (code <= VALID_CODE_LIMIT) return 6; +#endif #ifdef USE_INVALID_CODE_SCHEME else if (code == INVALID_CODE_FE) return 1; else if (code == INVALID_CODE_FF) return 1; @@ -337,11 +448,33 @@ code_to_mbc(OnigCodePoint code, UChar *buf, OnigEncoding enc ARG_UNUSED) *p++ = (UChar )(((code>>12) & 0x0f) | 0xe0); *p++ = UTF8_TRAILS(code, 6); } +#ifndef USE_UTF8_31BITS else if (code <= VALID_CODE_LIMIT) { *p++ = (UChar )(((code>>18) & 0x07) | 0xf0); *p++ = UTF8_TRAILS(code, 12); *p++ = UTF8_TRAILS(code, 6); } +#else + else if ((code & 0xffe00000) == 0) { + *p++ = (UChar )(((code>>18) & 0x07) | 0xf0); + *p++ = UTF8_TRAILS(code, 12); + *p++ = UTF8_TRAILS(code, 6); + } + else if ((code & 0xfc000000) == 0) { + *p++ = (UChar )(((code>>24) & 0x03) | 0xf8); + *p++ = UTF8_TRAILS(code, 18); + *p++ = UTF8_TRAILS(code, 12); + *p++ = UTF8_TRAILS(code, 6); + } + else if (code <= VALID_CODE_LIMIT) { + *p++ = (UChar )(((code>>30) & 0x01) | 0xfc); + *p++ = UTF8_TRAILS(code, 24); + *p++ = UTF8_TRAILS(code, 18); + *p++ = UTF8_TRAILS(code, 12); + *p++ = UTF8_TRAILS(code, 6); + } +#endif + #ifdef USE_INVALID_CODE_SCHEME else if (code == INVALID_CODE_FE) { *p = 0xfe; @@ -421,7 +554,11 @@ get_case_fold_codes_by_str(OnigCaseFoldType flag, OnigEncodingDefine(utf_8, UTF_8) = { mbc_enc_len, "UTF-8", /* name */ +#ifndef USE_UTF8_31BITS 4, /* max byte length */ +#else + 6, /* max byte length */ +#endif 1, /* min byte length */ is_mbc_newline, mbc_to_code, @@ -435,7 +572,11 @@ OnigEncodingDefine(utf_8, UTF_8) = { get_ctype_code_range, left_adjust_char_head, onigenc_always_true_is_allowed_reverse_match, +#ifdef USE_CASE_MAP_API onigenc_unicode_case_map, +#else + NULL, +#endif ENCINDEX_UTF_8, ONIGENC_FLAG_UNICODE, }; diff --git a/onigmo/onigmo.h b/onigmo/onigmo.h index 385f2d6a8..fbbf6c9b0 100644 --- a/onigmo/onigmo.h +++ b/onigmo/onigmo.h @@ -4,8 +4,8 @@ onigmo.h - Onigmo (Oniguruma-mod) (regular expression library) **********************************************************************/ /*- - * Copyright (c) 2002-2009 K.Kosako - * Copyright (c) 2011-2017 K.Takata + * Copyright (c) 2002-2016 K.Kosako + * Copyright (c) 2011-2019 K.Takata * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -38,8 +38,8 @@ extern "C" { #endif #define ONIGMO_VERSION_MAJOR 6 -#define ONIGMO_VERSION_MINOR 1 -#define ONIGMO_VERSION_TEENY 3 +#define ONIGMO_VERSION_MINOR 2 +#define ONIGMO_VERSION_TEENY 0 #ifndef ONIG_EXTERN # ifdef RUBY_EXTERN @@ -784,8 +784,8 @@ typedef struct re_pattern_buffer { unsigned char *exact; unsigned char *exact_end; unsigned char map[ONIG_CHAR_TABLE_SIZE]; /* used as BM skip or char-map */ - int *int_map; /* BM skip for exact_len > 255 */ - int *int_map_backward; /* BM skip for backward search */ + int *reserved1; + int *reserved2; OnigDistance dmin; /* min-distance of exact or map */ OnigDistance dmax; /* max-distance of exact or map */ diff --git a/onigmo/regcomp.c b/onigmo/regcomp.c index c843b1dea..8d8631dc0 100644 --- a/onigmo/regcomp.c +++ b/onigmo/regcomp.c @@ -1,9 +1,9 @@ -/********************************************************************** +/********************************************************************** regcomp.c - Onigmo (Oniguruma-mod) (regular expression library) **********************************************************************/ /*- - * Copyright (c) 2002-2013 K.Kosako - * Copyright (c) 2011-2016 K.Takata + * Copyright (c) 2002-2018 K.Kosako + * Copyright (c) 2011-2019 K.Takata * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -2770,10 +2770,8 @@ get_head_value_node(Node* node, int exact, regex_t* reg) if (sn->end <= sn->s) break; - if (exact != 0 && - !NSTRING_IS_RAW(node) && IS_IGNORECASE(reg->options)) { - } - else { + if (exact == 0 || + NSTRING_IS_RAW(node) || !IS_IGNORECASE(reg->options)) { n = node; } } @@ -3264,6 +3262,14 @@ setup_subexp_call(Node* node, ScanEnv* env) } #endif +#define IN_ALT (1<<0) +#define IN_NOT (1<<1) +#define IN_REPEAT (1<<2) +#define IN_VAR_REPEAT (1<<3) +#define IN_CALL (1<<4) +#define IN_RECCALL (1<<5) +#define IN_LOOK_BEHIND (1<<6) + /* divide different length alternatives in look-behind. (?<=A|B) ==> (?<=A)|(?<=B) (? (?s; end = sn->end; if (start >= end) return 0; + is_in_look_behind = (state & IN_LOOK_BEHIND) != 0; + r = 0; top_root = root = prev_node = snode = NULL_NODE; alt_num = 1; @@ -3593,7 +3604,7 @@ expand_case_fold_string(Node* node, regex_t* reg) len = enclen(reg->enc, p, end); varlen = is_case_fold_variable_len(n, items, len); - if (n == 0 || varlen == 0) { + if (n == 0 || varlen == 0 || is_in_look_behind) { if (IS_NULL(snode)) { if (IS_NULL(root) && IS_NOT_NULL(prev_node)) { onig_node_free(top_root); @@ -3854,13 +3865,6 @@ setup_comb_exp_check(Node* node, int state, ScanEnv* env) } #endif -#define IN_ALT (1<<0) -#define IN_NOT (1<<1) -#define IN_REPEAT (1<<2) -#define IN_VAR_REPEAT (1<<3) -#define IN_CALL (1<<4) -#define IN_RECCALL (1<<5) - /* setup_tree does the following work. 1. check empty loop. (set qn->target_empty_info) 2. expand ignore-case in char class. @@ -3902,7 +3906,7 @@ restart: case NT_STR: if (IS_IGNORECASE(reg->options) && !NSTRING_IS_RAW(node)) { - r = expand_case_fold_string(node, reg); + r = expand_case_fold_string(node, reg, state); } break; @@ -4145,7 +4149,7 @@ restart: if (r < 0) return r; if (r > 0) return ONIGERR_INVALID_LOOK_BEHIND_PATTERN; if (NTYPE(node) != NT_ANCHOR) goto restart; - r = setup_tree(an->target, reg, state, env); + r = setup_tree(an->target, reg, (state | IN_LOOK_BEHIND), env); if (r != 0) return r; r = setup_look_behind(node, reg, env); } @@ -4158,7 +4162,8 @@ restart: if (r < 0) return r; if (r > 0) return ONIGERR_INVALID_LOOK_BEHIND_PATTERN; if (NTYPE(node) != NT_ANCHOR) goto restart; - r = setup_tree(an->target, reg, (state | IN_NOT), env); + r = setup_tree(an->target, reg, (state | IN_NOT | IN_LOOK_BEHIND), + env); if (r != 0) return r; r = setup_look_behind(node, reg, env); } @@ -4174,93 +4179,10 @@ restart: return r; } -#ifndef USE_SUNDAY_QUICK_SEARCH -/* set skip map for Boyer-Moore search */ -static int -set_bm_skip(UChar* s, UChar* end, regex_t* reg, - UChar skip[], int** int_skip, int ignore_case) -{ - OnigDistance i, len; - int clen, flen, n, j, k; - UChar *p, buf[ONIGENC_GET_CASE_FOLD_CODES_MAX_NUM][ONIGENC_MBC_CASE_FOLD_MAXLEN]; - OnigCaseFoldCodeItem items[ONIGENC_GET_CASE_FOLD_CODES_MAX_NUM]; - OnigEncoding enc = reg->enc; - - len = end - s; - if (len < ONIG_CHAR_TABLE_SIZE) { - for (i = 0; i < ONIG_CHAR_TABLE_SIZE; i++) skip[i] = (UChar )len; - - n = 0; - for (i = 0; i < len - 1; i += clen) { - p = s + i; - if (ignore_case) - n = ONIGENC_GET_CASE_FOLD_CODES_BY_STR(enc, reg->case_fold_flag, - p, end, items); - clen = enclen(enc, p, end); - if (p + clen > end) - clen = (int )(end - p); - - for (j = 0; j < n; j++) { - if ((items[j].code_len != 1) || (items[j].byte_len != clen)) - return 1; /* different length isn't supported. */ - flen = ONIGENC_CODE_TO_MBC(enc, items[j].code[0], buf[j]); - if (flen != clen) - return 1; /* different length isn't supported. */ - } - for (j = 0; j < clen; j++) { - skip[s[i + j]] = (UChar )(len - 1 - i - j); - for (k = 0; k < n; k++) { - skip[buf[k][j]] = (UChar )(len - 1 - i - j); - } - } - } - } - else { -# if OPT_EXACT_MAXLEN < ONIG_CHAR_TABLE_SIZE - /* This should not happen. */ - return ONIGERR_TYPE_BUG; -# else - if (IS_NULL(*int_skip)) { - *int_skip = (int* )xmalloc(sizeof(int) * ONIG_CHAR_TABLE_SIZE); - if (IS_NULL(*int_skip)) return ONIGERR_MEMORY; - } - for (i = 0; i < ONIG_CHAR_TABLE_SIZE; i++) (*int_skip)[i] = (int )len; - - n = 0; - for (i = 0; i < len - 1; i += clen) { - p = s + i; - if (ignore_case) - n = ONIGENC_GET_CASE_FOLD_CODES_BY_STR(enc, reg->case_fold_flag, - p, end, items); - clen = enclen(enc, p, end); - if (p + clen > end) - clen = (int )(end - p); - - for (j = 0; j < n; j++) { - if ((items[j].code_len != 1) || (items[j].byte_len != clen)) - return 1; /* different length isn't supported. */ - flen = ONIGENC_CODE_TO_MBC(enc, items[j].code[0], buf[j]); - if (flen != clen) - return 1; /* different length isn't supported. */ - } - for (j = 0; j < clen; j++) { - (*int_skip)[s[i + j]] = (int )(len - 1 - i - j); - for (k = 0; k < n; k++) { - (*int_skip)[buf[k][j]] = (int )(len - 1 - i - j); - } - } - } -# endif - } - return 0; -} - -#else /* USE_SUNDAY_QUICK_SEARCH */ - /* set skip map for Sunday's quick search */ static int set_bm_skip(UChar* s, UChar* end, regex_t* reg, - UChar skip[], int** int_skip, int ignore_case) + UChar skip[], int ignore_case) { OnigDistance i, len; int clen, flen, n, j, k; @@ -4269,96 +4191,61 @@ set_bm_skip(UChar* s, UChar* end, regex_t* reg, OnigEncoding enc = reg->enc; len = end - s; - if (len < ONIG_CHAR_TABLE_SIZE) { - for (i = 0; i < ONIG_CHAR_TABLE_SIZE; i++) skip[i] = (UChar )(len + 1); - - if (ignore_case) { - for (i = 0; i < len; i += clen) { - p = s + i; - n = ONIGENC_GET_CASE_FOLD_CODES_BY_STR(enc, reg->case_fold_flag, - p, end, items); - clen = enclen(enc, p, end); - if (p + clen > end) - clen = (int )(end - p); - - for (j = 0; j < n; j++) { - if ((items[j].code_len != 1) || (items[j].byte_len != clen)) { - /* Different length isn't supported. Stop optimization at here. */ - end = p; - goto endcheck; - } - flen = ONIGENC_CODE_TO_MBC(enc, items[j].code[0], buf); - if (flen != clen) { - /* Different length isn't supported. Stop optimization at here. */ - end = p; - goto endcheck; - } - } - } -endcheck: - ; - } - - len = end - s; - n = 0; - for (i = 0; i < len; i += clen) { - p = s + i; - if (ignore_case) - n = ONIGENC_GET_CASE_FOLD_CODES_BY_STR(enc, reg->case_fold_flag, - p, end, items); - clen = enclen(enc, p, end); - if (p + clen > end) - clen = (int )(end - p); - - for (j = 0; j < clen; j++) { - skip[s[i + j]] = (UChar )(len - i - j); - for (k = 0; k < n; k++) { - ONIGENC_CODE_TO_MBC(enc, items[k].code[0], buf); - skip[buf[j]] = (UChar )(len - i - j); - } - } - } - } - else { -# if OPT_EXACT_MAXLEN < ONIG_CHAR_TABLE_SIZE + if (len >= ONIG_CHAR_TABLE_SIZE) { /* This should not happen. */ return ONIGERR_TYPE_BUG; -# else - if (IS_NULL(*int_skip)) { - *int_skip = (int* )xmalloc(sizeof(int) * ONIG_CHAR_TABLE_SIZE); - if (IS_NULL(*int_skip)) return ONIGERR_MEMORY; - } - for (i = 0; i < ONIG_CHAR_TABLE_SIZE; i++) (*int_skip)[i] = (int )(len + 1); + } - n = 0; + if (ignore_case) { for (i = 0; i < len; i += clen) { p = s + i; - if (ignore_case) - n = ONIGENC_GET_CASE_FOLD_CODES_BY_STR(enc, reg->case_fold_flag, - p, end, items); + n = ONIGENC_GET_CASE_FOLD_CODES_BY_STR(enc, reg->case_fold_flag, + p, end, items); clen = enclen(enc, p, end); if (p + clen > end) clen = (int )(end - p); for (j = 0; j < n; j++) { - if ((items[j].code_len != 1) || (items[j].byte_len != clen)) - return 1; /* different length isn't supported. */ - flen = ONIGENC_CODE_TO_MBC(enc, items[j].code[0], buf[j]); - if (flen != clen) - return 1; /* different length isn't supported. */ - } - for (j = 0; j < clen; j++) { - (*int_skip)[s[i + j]] = (int )(len - i - j); - for (k = 0; k < n; k++) { - (*int_skip)[buf[k][j]] = (int )(len - i - j); + if ((items[j].code_len != 1) || (items[j].byte_len != clen)) { + /* Different length isn't supported. Stop optimization at here. */ + end = p; + goto endcheck; + } + flen = ONIGENC_CODE_TO_MBC(enc, items[j].code[0], buf); + if (flen != clen) { + /* Different length isn't supported. Stop optimization at here. */ + end = p; + goto endcheck; } } } -# endif +endcheck: + len = end - s; } - return len; + + for (i = 0; i < ONIG_CHAR_TABLE_SIZE; i++) + skip[i] = (UChar )(len + 1); + n = 0; + for (i = 0; i < len; i += clen) { + p = s + i; + if (ignore_case) + n = ONIGENC_GET_CASE_FOLD_CODES_BY_STR(enc, reg->case_fold_flag, + p, end, items); + clen = enclen(enc, p, end); + if (p + clen > end) + clen = (int )(end - p); + + for (j = 0; j < clen; j++) { + skip[s[i + j]] = (UChar )(len - i - j); + for (k = 0; k < n; k++) { + ONIGENC_CODE_TO_MBC(enc, items[k].code[0], buf); + skip[buf[j]] = (UChar )(len - i - j); + } + } + } + + return (int)len; } -#endif /* USE_SUNDAY_QUICK_SEARCH */ typedef struct { OnigDistance min; /* min byte length */ @@ -5036,7 +4923,7 @@ optimize_node_left(Node* node, NodeOptInfo* opt, OptEnv* env) if (NSTRING_IS_DONT_GET_OPT_INFO(node)) { int n = onigenc_strlen(env->enc, sn->s, sn->end); - max = ONIGENC_MBC_MAXLEN_DIST(env->enc) * n; + max = (OnigDistance )ONIGENC_MBC_MAXLEN_DIST(env->enc) * n; } else { concat_opt_exact_info_str(&opt->exb, sn->s, sn->end, @@ -5344,7 +5231,7 @@ set_optimize_exact_info(regex_t* reg, OptExactInfo* e) if (e->ignore_case > 0) { if (e->len >= 3 || (e->len >= 2 && allow_reverse)) { e->len = set_bm_skip(reg->exact, reg->exact_end, reg, - reg->map, &(reg->int_map), 1); + reg->map, 1); reg->exact_end = reg->exact + e->len; if (e->len >= 3) { reg->optimize = (allow_reverse != 0 @@ -5363,7 +5250,7 @@ set_optimize_exact_info(regex_t* reg, OptExactInfo* e) else { if (e->len >= 3 || (e->len >= 2 && allow_reverse)) { set_bm_skip(reg->exact, reg->exact_end, reg, - reg->map, &(reg->int_map), 0); + reg->map, 0); reg->optimize = (allow_reverse != 0 ? ONIG_OPTIMIZE_EXACT_BM : ONIG_OPTIMIZE_EXACT_BM_NOT_REV); } @@ -5648,8 +5535,6 @@ onig_free_body(regex_t* reg) if (IS_NOT_NULL(reg)) { if (IS_NOT_NULL(reg->p)) xfree(reg->p); if (IS_NOT_NULL(reg->exact)) xfree(reg->exact); - if (IS_NOT_NULL(reg->int_map)) xfree(reg->int_map); - if (IS_NOT_NULL(reg->int_map_backward)) xfree(reg->int_map_backward); if (IS_NOT_NULL(reg->repeat_range)) xfree(reg->repeat_range); if (IS_NOT_NULL(reg->chain)) onig_free(reg->chain); @@ -5676,8 +5561,6 @@ onig_memsize(const regex_t *reg) if (IS_NULL(reg)) return 0; if (IS_NOT_NULL(reg->p)) size += reg->alloc; if (IS_NOT_NULL(reg->exact)) size += reg->exact_end - reg->exact; - if (IS_NOT_NULL(reg->int_map)) size += sizeof(int) * ONIG_CHAR_TABLE_SIZE; - if (IS_NOT_NULL(reg->int_map_backward)) size += sizeof(int) * ONIG_CHAR_TABLE_SIZE; if (IS_NOT_NULL(reg->repeat_range)) size += reg->repeat_range_alloc * sizeof(OnigRepeatRange); if (IS_NOT_NULL(reg->chain)) size += onig_memsize(reg->chain); @@ -5961,8 +5844,6 @@ onig_reg_init(regex_t* reg, OnigOptionType option, (reg)->syntax = syntax; (reg)->optimize = 0; (reg)->exact = (UChar* )NULL; - (reg)->int_map = (int* )NULL; - (reg)->int_map_backward = (int* )NULL; (reg)->chain = (regex_t* )NULL; (reg)->p = (UChar* )NULL; diff --git a/onigmo/regenc.c b/onigmo/regenc.c index 7be3166ff..64374d7bd 100644 --- a/onigmo/regenc.c +++ b/onigmo/regenc.c @@ -3,7 +3,7 @@ **********************************************************************/ /*- * Copyright (c) 2002-2007 K.Kosako - * Copyright (c) 2011-2016 K.Takata + * Copyright (c) 2011-2019 K.Takata * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -951,6 +951,7 @@ onigenc_property_list_add_property(UChar* name, const OnigCodePoint* prop, } #endif +#ifdef USE_CASE_MAP_API extern int onigenc_ascii_only_case_map(OnigCaseFoldType* flagP, const OnigUChar** pp, const OnigUChar* end, OnigUChar* to, OnigUChar* to_end, const struct OnigEncodingTypeST* enc) @@ -969,7 +970,7 @@ onigenc_ascii_only_case_map(OnigCaseFoldType* flagP, const OnigUChar** pp, const if (code >= 'a' && code <= 'z' && (flags & ONIGENC_CASE_UPCASE)) { flags |= ONIGENC_CASE_MODIFIED; - code += 'A' - 'a'; + code -= 'a' - 'A'; } else if (code >= 'A' && code <= 'Z' && (flags & (ONIGENC_CASE_DOWNCASE | ONIGENC_CASE_FOLD))) { flags |= ONIGENC_CASE_MODIFIED; @@ -997,8 +998,7 @@ onigenc_single_byte_ascii_only_case_map(OnigCaseFoldType* flagP, const OnigUChar if (code >= 'a' && code <= 'z' && (flags & ONIGENC_CASE_UPCASE)) { flags |= ONIGENC_CASE_MODIFIED; - code -= 'a'; - code += 'A'; + code -= 'a' - 'A'; } else if (code >= 'A' && code <= 'Z' && (flags & (ONIGENC_CASE_DOWNCASE | ONIGENC_CASE_FOLD))) { flags |= ONIGENC_CASE_MODIFIED; @@ -1011,3 +1011,4 @@ onigenc_single_byte_ascii_only_case_map(OnigCaseFoldType* flagP, const OnigUChar *flagP = flags; return (int )(to - to_start); } +#endif diff --git a/onigmo/regenc.h b/onigmo/regenc.h index d21b5afc1..08f19c978 100644 --- a/onigmo/regenc.h +++ b/onigmo/regenc.h @@ -5,7 +5,7 @@ **********************************************************************/ /*- * Copyright (c) 2002-2008 K.Kosako - * Copyright (c) 2011-2016 K.Takata + * Copyright (c) 2011-2019 K.Takata * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -129,12 +129,14 @@ typedef struct { #endif +/* config */ #define USE_CRNL_AS_LINE_TERMINATOR #define USE_UNICODE_PROPERTIES #define USE_UNICODE_AGE_PROPERTIES /* #define USE_UNICODE_CASE_FOLD_TURKISH_AZERI */ #define USE_ASCII_ALL_LINE_BREAKS // LF, VT, FF, CR /* #define USE_UNICODE_ALL_LINE_TERMINATORS */ /* see Unicode.org UTS #18 */ +/* #define USE_CASE_MAP_API */ #define ONIG_ENCODING_INIT_DEFAULT ONIG_ENCODING_ASCII diff --git a/onigmo/regerror.c b/onigmo/regerror.c index 59cf53068..63b67fce1 100644 --- a/onigmo/regerror.c +++ b/onigmo/regerror.c @@ -3,7 +3,7 @@ **********************************************************************/ /*- * Copyright (c) 2002-2007 K.Kosako - * Copyright (c) 2011-2016 K.Takata + * Copyright (c) 2011-2019 K.Takata * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -63,14 +63,18 @@ onig_error_code_to_format(OnigPosition code) p = "parse depth limit over"; break; case ONIGERR_DEFAULT_ENCODING_IS_NOT_SET: p = "default multibyte-encoding is not set"; break; +#if 0 case ONIGERR_SPECIFIED_ENCODING_CANT_CONVERT_TO_WIDE_CHAR: p = "can't convert to wide-char on specified multibyte-encoding"; break; +#endif case ONIGERR_INVALID_ARGUMENT: p = "invalid argument"; break; case ONIGERR_END_PATTERN_AT_LEFT_BRACE: p = "end pattern at left brace"; break; +#if 0 case ONIGERR_END_PATTERN_AT_LEFT_BRACKET: p = "end pattern at left bracket"; break; +#endif case ONIGERR_EMPTY_CHAR_CLASS: p = "empty char-class"; break; case ONIGERR_PREMATURE_END_OF_CHAR_CLASS: @@ -87,16 +91,20 @@ onig_error_code_to_format(OnigPosition code) p = "invalid control-code syntax"; break; case ONIGERR_CHAR_CLASS_VALUE_AT_END_OF_RANGE: p = "char-class value at end of range"; break; +#if 0 case ONIGERR_CHAR_CLASS_VALUE_AT_START_OF_RANGE: p = "char-class value at start of range"; break; +#endif case ONIGERR_UNMATCHED_RANGE_SPECIFIER_IN_CHAR_CLASS: p = "unmatched range specifier in char-class"; break; case ONIGERR_TARGET_OF_REPEAT_OPERATOR_NOT_SPECIFIED: p = "target of repeat operator is not specified"; break; case ONIGERR_TARGET_OF_REPEAT_OPERATOR_INVALID: p = "target of repeat operator is invalid"; break; +#if 0 case ONIGERR_NESTED_REPEAT_OPERATOR: p = "nested repeat operator"; break; +#endif case ONIGERR_UNMATCHED_CLOSE_PARENTHESIS: p = "unmatched close parenthesis"; break; case ONIGERR_END_PATTERN_WITH_UNMATCHED_PARENTHESIS: @@ -121,14 +129,18 @@ onig_error_code_to_format(OnigPosition code) p = "upper is smaller than lower in repeat range"; break; case ONIGERR_EMPTY_RANGE_IN_CHAR_CLASS: p = "empty range in char class"; break; +#if 0 case ONIGERR_MISMATCH_CODE_LENGTH_IN_CLASS_RANGE: p = "mismatch multibyte code length in char-class range"; break; +#endif case ONIGERR_TOO_MANY_MULTI_BYTE_RANGES: p = "too many multibyte code ranges are specified"; break; case ONIGERR_TOO_SHORT_MULTI_BYTE_STRING: p = "too short multibyte code string"; break; +#if 0 case ONIGERR_TOO_BIG_BACKREF_NUMBER: p = "too big backref number"; break; +#endif case ONIGERR_INVALID_BACKREF: #ifdef USE_NAMED_GROUP p = "invalid backref number/name"; break; diff --git a/onigmo/regexec.c b/onigmo/regexec.c index 9b6232e30..fdd67184d 100644 --- a/onigmo/regexec.c +++ b/onigmo/regexec.c @@ -2,8 +2,8 @@ regexec.c - Onigmo (Oniguruma-mod) (regular expression library) **********************************************************************/ /*- - * Copyright (c) 2002-2008 K.Kosako - * Copyright (c) 2011-2016 K.Takata + * Copyright (c) 2002-2018 K.Kosako + * Copyright (c) 2011-2019 K.Takata * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -1808,7 +1808,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, /* default behavior: return first-matching result. */ goto finish; - NEXT; CASE(OP_EXACT1) MOP_IN(OP_EXACT1); DATA_ENSURE(1); @@ -2369,7 +2368,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, } } goto fail; - NEXT; CASE(OP_ASCII_WORD_BEGIN) MOP_IN(OP_ASCII_WORD_BEGIN); if (DATA_ENSURE_CHECK1 && ONIGENC_IS_MBC_ASCII_WORD(encode, s, end)) { @@ -2379,7 +2377,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, } } goto fail; - NEXT; CASE(OP_WORD_END) MOP_IN(OP_WORD_END); if (!ON_STR_BEGIN(s) && ONIGENC_IS_MBC_WORD(encode, sprev, end)) { @@ -2389,7 +2386,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, } } goto fail; - NEXT; CASE(OP_ASCII_WORD_END) MOP_IN(OP_ASCII_WORD_END); if (!ON_STR_BEGIN(s) && ONIGENC_IS_MBC_ASCII_WORD(encode, sprev, end)) { @@ -2399,7 +2395,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, } } goto fail; - NEXT; #endif CASE(OP_BEGIN_BUF) MOP_IN(OP_BEGIN_BUF); @@ -2432,7 +2427,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, JUMP; } goto fail; - NEXT; CASE(OP_END_LINE) MOP_IN(OP_END_LINE); if (ON_STR_END(s)) { @@ -2451,7 +2445,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, JUMP; } goto fail; - NEXT; CASE(OP_SEMI_END_BUF) MOP_IN(OP_SEMI_END_BUF); if (ON_STR_END(s)) { @@ -2483,7 +2476,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, #endif } goto fail; - NEXT; CASE(OP_BEGIN_POSITION) MOP_IN(OP_BEGIN_POSITION); if (s != msa->gpos) @@ -2549,12 +2541,10 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, CASE(OP_BACKREF1) MOP_IN(OP_BACKREF1); mem = 1; goto backref; - NEXT; CASE(OP_BACKREF2) MOP_IN(OP_BACKREF2); mem = 2; goto backref; - NEXT; CASE(OP_BACKREFN) MOP_IN(OP_BACKREFN); GET_MEMNUM_INC(mem, p); @@ -2964,7 +2954,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, STACK_GET_REPEAT(mem, stkp); si = GET_STACK_INDEX(stkp); goto repeat_inc; - NEXT; CASE(OP_REPEAT_INC_NG) MOP_IN(OP_REPEAT_INC_NG); GET_MEMNUM_INC(mem, p); /* mem: OP_REPEAT ID */ @@ -2997,7 +2986,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, STACK_GET_REPEAT(mem, stkp); si = GET_STACK_INDEX(stkp); goto repeat_inc_ng; - NEXT; CASE(OP_PUSH_POS) MOP_IN(OP_PUSH_POS); STACK_PUSH_POS(s, sprev, pkeep); @@ -3022,7 +3010,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, CASE(OP_FAIL_POS) MOP_IN(OP_FAIL_POS); STACK_POP_TIL_POS_NOT; goto fail; - NEXT; CASE(OP_PUSH_STOP_BT) MOP_IN(OP_PUSH_STOP_BT); STACK_PUSH_STOP_BT; @@ -3063,7 +3050,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, CASE(OP_FAIL_LOOK_BEHIND_NOT) MOP_IN(OP_FAIL_LOOK_BEHIND_NOT); STACK_POP_TIL_LOOK_BEHIND_NOT; goto fail; - NEXT; CASE(OP_PUSH_ABSENT_POS) MOP_IN(OP_PUSH_ABSENT_POS); /* Save the absent-start-pos and the original end-pos. */ @@ -3120,7 +3106,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, #endif STACK_POP_TIL_ABSENT; goto fail; - NEXT; #ifdef USE_SUBEXP_CALL CASE(OP_CALL) MOP_IN(OP_CALL); @@ -3150,7 +3135,6 @@ match_at(regex_t* reg, const UChar* str, const UChar* end, CASE(OP_FINISH) goto finish; - NEXT; CASE(OP_FAIL) if (0) { @@ -3346,219 +3330,6 @@ slow_search_backward_ic(OnigEncoding enc, int case_fold_flag, return (UChar* )NULL; } -#ifndef USE_SUNDAY_QUICK_SEARCH -/* Boyer-Moore-Horspool search applied to a multibyte string */ -static UChar* -bm_search_notrev(regex_t* reg, const UChar* target, const UChar* target_end, - const UChar* text, const UChar* text_end, - const UChar* text_range) -{ - const UChar *s, *se, *t, *p, *end; - const UChar *tail; - ptrdiff_t skip, tlen1; - -# ifdef ONIG_DEBUG_SEARCH - fprintf(stderr, "bm_search_notrev: text: %"PRIuPTR" (%p), text_end: %"PRIuPTR" (%p), text_range: %"PRIuPTR" (%p)\n", - (uintptr_t )text, text, (uintptr_t )text_end, text_end, (uintptr_t )text_range, text_range); -# endif - - tail = target_end - 1; - tlen1 = tail - target; - end = text_range; - if (end + tlen1 > text_end) - end = text_end - tlen1; - - s = text; - - if (IS_NULL(reg->int_map)) { - while (s < end) { - p = se = s + tlen1; - t = tail; - while (*p == *t) { - if (t == target) return (UChar* )s; - p--; t--; - } - skip = reg->map[*se]; - t = s; - do { - s += enclen(reg->enc, s, end); - } while ((s - t) < skip && s < end); - } - } - else { -# if OPT_EXACT_MAXLEN >= ONIG_CHAR_TABLE_SIZE - while (s < end) { - p = se = s + tlen1; - t = tail; - while (*p == *t) { - if (t == target) return (UChar* )s; - p--; t--; - } - skip = reg->int_map[*se]; - t = s; - do { - s += enclen(reg->enc, s, end); - } while ((s - t) < skip && s < end); - } -# endif - } - - return (UChar* )NULL; -} - -/* Boyer-Moore-Horspool search */ -static UChar* -bm_search(regex_t* reg, const UChar* target, const UChar* target_end, - const UChar* text, const UChar* text_end, const UChar* text_range) -{ - const UChar *s, *t, *p, *end; - const UChar *tail; - -# ifdef ONIG_DEBUG_SEARCH - fprintf(stderr, "bm_search: text: %"PRIuPTR" (%p), text_end: %"PRIuPTR" (%p), text_range: %"PRIuPTR" (%p)\n", - (uintptr_t )text, text, (uintptr_t )text_end, text_end, (uintptr_t )text_range, text_range); -# endif - - end = text_range + (target_end - target) - 1; - if (end > text_end) - end = text_end; - - tail = target_end - 1; - s = text + (target_end - target) - 1; - if (IS_NULL(reg->int_map)) { - while (s < end) { - p = s; - t = tail; -# ifdef ONIG_DEBUG_SEARCH - fprintf(stderr, "bm_search_loop: pos: %"PRIdPTR" %s\n", - (intptr_t )(s - text), s); -# endif - while (*p == *t) { - if (t == target) return (UChar* )p; - p--; t--; - } - s += reg->map[*s]; - } - } - else { /* see int_map[] */ -# if OPT_EXACT_MAXLEN >= ONIG_CHAR_TABLE_SIZE - while (s < end) { - p = s; - t = tail; - while (*p == *t) { - if (t == target) return (UChar* )p; - p--; t--; - } - s += reg->int_map[*s]; - } -# endif - } - return (UChar* )NULL; -} - -/* Boyer-Moore-Horspool search applied to a multibyte string (ignore case) */ -static UChar* -bm_search_notrev_ic(regex_t* reg, const UChar* target, const UChar* target_end, - const UChar* text, const UChar* text_end, - const UChar* text_range) -{ - const UChar *s, *se, *t, *end; - const UChar *tail; - ptrdiff_t skip, tlen1; - OnigEncoding enc = reg->enc; - int case_fold_flag = reg->case_fold_flag; - -# ifdef ONIG_DEBUG_SEARCH - fprintf(stderr, "bm_search_notrev_ic: text: %d (%p), text_end: %d (%p), text_range: %d (%p)\n", - (int )text, text, (int )text_end, text_end, (int )text_range, text_range); -# endif - - tail = target_end - 1; - tlen1 = tail - target; - end = text_range; - if (end + tlen1 > text_end) - end = text_end - tlen1; - - s = text; - - if (IS_NULL(reg->int_map)) { - while (s < end) { - se = s + tlen1; - if (str_lower_case_match(enc, case_fold_flag, target, target_end, - s, se + 1)) - return (UChar* )s; - skip = reg->map[*se]; - t = s; - do { - s += enclen(reg->enc, s, end); - } while ((s - t) < skip && s < end); - } - } - else { -# if OPT_EXACT_MAXLEN >= ONIG_CHAR_TABLE_SIZE - while (s < end) { - se = s + tlen1; - if (str_lower_case_match(enc, case_fold_flag, target, target_end, - s, se + 1)) - return (UChar* )s; - skip = reg->int_map[*se]; - t = s; - do { - s += enclen(reg->enc, s, end); - } while ((s - t) < skip && s < end); - } -# endif - } - - return (UChar* )NULL; -} - -/* Boyer-Moore-Horspool search (ignore case) */ -static UChar* -bm_search_ic(regex_t* reg, const UChar* target, const UChar* target_end, - const UChar* text, const UChar* text_end, const UChar* text_range) -{ - const UChar *s, *p, *end; - const UChar *tail; - OnigEncoding enc = reg->enc; - int case_fold_flag = reg->case_fold_flag; - -# ifdef ONIG_DEBUG_SEARCH - fprintf(stderr, "bm_search_ic: text: %d (%p), text_end: %d (%p), text_range: %d (%p)\n", - (int )text, text, (int )text_end, text_end, (int )text_range, text_range); -# endif - - end = text_range + (target_end - target) - 1; - if (end > text_end) - end = text_end; - - tail = target_end - 1; - s = text + (target_end - target) - 1; - if (IS_NULL(reg->int_map)) { - while (s < end) { - p = s - (target_end - target) + 1; - if (str_lower_case_match(enc, case_fold_flag, target, target_end, - p, s + 1)) - return (UChar* )p; - s += reg->map[*s]; - } - } - else { /* see int_map[] */ -# if OPT_EXACT_MAXLEN >= ONIG_CHAR_TABLE_SIZE - while (s < end) { - p = s - (target_end - target) + 1; - if (str_lower_case_match(enc, case_fold_flag, target, target_end, - p, s + 1)) - return (UChar* )p; - s += reg->int_map[*s]; - } -# endif - } - return (UChar* )NULL; -} - -#else /* USE_SUNDAY_QUICK_SEARCH */ - /* Sunday's quick search applied to a multibyte string */ static UChar* bm_search_notrev(regex_t* reg, const UChar* target, const UChar* target_end, @@ -3583,39 +3354,19 @@ bm_search_notrev(regex_t* reg, const UChar* target, const UChar* target_end, s = text; - if (IS_NULL(reg->int_map)) { - while (s < end) { - p = se = s + tlen1; - t = tail; - while (*p == *t) { - if (t == target) return (UChar* )s; - p--; t--; - } - if (s + 1 >= end) break; - skip = reg->map[se[1]]; - t = s; - do { - s += enclen(enc, s, end); - } while ((s - t) < skip && s < end); + while (s < end) { + p = se = s + tlen1; + t = tail; + while (*p == *t) { + if (t == target) return (UChar* )s; + p--; t--; } - } - else { -# if OPT_EXACT_MAXLEN >= ONIG_CHAR_TABLE_SIZE - while (s < end) { - p = se = s + tlen1; - t = tail; - while (*p == *t) { - if (t == target) return (UChar* )s; - p--; t--; - } - if (s + 1 >= end) break; - skip = reg->int_map[se[1]]; - t = s; - do { - s += enclen(enc, s, end); - } while ((s - t) < skip && s < end); - } -# endif + if (s + 1 >= end) break; + skip = reg->map[se[1]]; + t = s; + do { + s += enclen(enc, s, end); + } while ((s - t) < skip && s < end); } return (UChar* )NULL; @@ -3642,32 +3393,17 @@ bm_search(regex_t* reg, const UChar* target, const UChar* target_end, end = text_end; s = text + tlen1; - if (IS_NULL(reg->int_map)) { - while (s < end) { - p = s; - t = tail; - while (*p == *t) { - if (t == target) return (UChar* )p; - p--; t--; - } - if (s + 1 >= end) break; - s += reg->map[s[1]]; + while (s < end) { + p = s; + t = tail; + while (*p == *t) { + if (t == target) return (UChar* )p; + p--; t--; } + if (s + 1 >= end) break; + s += reg->map[s[1]]; } - else { /* see int_map[] */ -# if OPT_EXACT_MAXLEN >= ONIG_CHAR_TABLE_SIZE - while (s < end) { - p = s; - t = tail; - while (*p == *t) { - if (t == target) return (UChar* )p; - p--; t--; - } - if (s + 1 >= end) break; - s += reg->int_map[s[1]]; - } -# endif - } + return (UChar* )NULL; } @@ -3696,35 +3432,17 @@ bm_search_notrev_ic(regex_t* reg, const UChar* target, const UChar* target_end, s = text; - if (IS_NULL(reg->int_map)) { - while (s < end) { - se = s + tlen1; - if (str_lower_case_match(enc, case_fold_flag, target, target_end, - s, se + 1)) - return (UChar* )s; - if (s + 1 >= end) break; - skip = reg->map[se[1]]; - t = s; - do { - s += enclen(enc, s, end); - } while ((s - t) < skip && s < end); - } - } - else { -# if OPT_EXACT_MAXLEN >= ONIG_CHAR_TABLE_SIZE - while (s < end) { - se = s + tlen1; - if (str_lower_case_match(enc, case_fold_flag, target, target_end, - s, se + 1)) - return (UChar* )s; - if (s + 1 >= end) break; - skip = reg->int_map[se[1]]; - t = s; - do { - s += enclen(enc, s, end); - } while ((s - t) < skip && s < end); - } -# endif + while (s < end) { + se = s + tlen1; + if (str_lower_case_match(enc, case_fold_flag, target, target_end, + s, se + 1)) + return (UChar* )s; + if (s + 1 >= end) break; + skip = reg->map[se[1]]; + t = s; + do { + s += enclen(enc, s, end); + } while ((s - t) < skip && s < end); } return (UChar* )NULL; @@ -3753,83 +3471,17 @@ bm_search_ic(regex_t* reg, const UChar* target, const UChar* target_end, end = text_end; s = text + tlen1; - if (IS_NULL(reg->int_map)) { - while (s < end) { - p = s - tlen1; - if (str_lower_case_match(enc, case_fold_flag, target, target_end, - p, s + 1)) - return (UChar* )p; - if (s + 1 >= end) break; - s += reg->map[s[1]]; - } - } - else { /* see int_map[] */ -# if OPT_EXACT_MAXLEN >= ONIG_CHAR_TABLE_SIZE - while (s < end) { - p = s - tlen1; - if (str_lower_case_match(enc, case_fold_flag, target, target_end, - p, s + 1)) - return (UChar* )p; - if (s + 1 >= end) break; - s += reg->int_map[s[1]]; - } -# endif - } - return (UChar* )NULL; -} -#endif /* USE_SUNDAY_QUICK_SEARCH */ - -#ifdef USE_INT_MAP_BACKWARD -static int -set_bm_backward_skip(UChar* s, UChar* end, OnigEncoding enc ARG_UNUSED, - int** skip) -{ - int i, len; - - if (IS_NULL(*skip)) { - *skip = (int* )xmalloc(sizeof(int) * ONIG_CHAR_TABLE_SIZE); - if (IS_NULL(*skip)) return ONIGERR_MEMORY; - } - - len = (int )(end - s); - for (i = 0; i < ONIG_CHAR_TABLE_SIZE; i++) - (*skip)[i] = len; - - for (i = len - 1; i > 0; i--) - (*skip)[s[i]] = i; - - return 0; -} - -static UChar* -bm_search_backward(regex_t* reg, const UChar* target, const UChar* target_end, - const UChar* text, const UChar* adjust_text, - const UChar* text_end, const UChar* text_start) -{ - const UChar *s, *t, *p; - - s = text_end - (target_end - target); - if (text_start < s) - s = text_start; - else - s = ONIGENC_LEFT_ADJUST_CHAR_HEAD(reg->enc, adjust_text, s, text_end); - - while (s >= text) { - p = s; - t = target; - while (t < target_end && *p == *t) { - p++; t++; - } - if (t == target_end) - return (UChar* )s; - - s -= reg->int_map_backward[*s]; - s = ONIGENC_LEFT_ADJUST_CHAR_HEAD(reg->enc, adjust_text, s, text_end); + while (s < end) { + p = s - tlen1; + if (str_lower_case_match(enc, case_fold_flag, target, target_end, + p, s + 1)) + return (UChar* )p; + if (s + 1 >= end) break; + s += reg->map[s[1]]; } return (UChar* )NULL; } -#endif static UChar* map_search(OnigEncoding enc, UChar map[], @@ -4064,21 +3716,7 @@ backward_search_range(regex_t* reg, const UChar* str, const UChar* end, case ONIG_OPTIMIZE_EXACT_BM: case ONIG_OPTIMIZE_EXACT_BM_NOT_REV: -#ifdef USE_INT_MAP_BACKWARD - if (IS_NULL(reg->int_map_backward)) { - int r; - if (s - range < BM_BACKWARD_SEARCH_LENGTH_THRESHOLD) - goto exact_method; - - r = set_bm_backward_skip(reg->exact, reg->exact_end, reg->enc, - &(reg->int_map_backward)); - if (r) return r; - } - p = bm_search_backward(reg, reg->exact, reg->exact_end, range, adjrange, - end, p); -#else goto exact_method; -#endif break; case ONIG_OPTIMIZE_MAP: diff --git a/onigmo/regint.h b/onigmo/regint.h index 8dc8bf6a9..48f13fd8e 100644 --- a/onigmo/regint.h +++ b/onigmo/regint.h @@ -5,7 +5,7 @@ **********************************************************************/ /*- * Copyright (c) 2002-2013 K.Kosako - * Copyright (c) 2011-2016 K.Takata + * Copyright (c) 2011-2019 K.Takata * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -81,13 +81,12 @@ /* #define USE_OP_PUSH_OR_JUMP_EXACT */ #define USE_QTFR_PEEK_NEXT #define USE_ST_LIBRARY -#define USE_SUNDAY_QUICK_SEARCH #define INIT_MATCH_STACK_SIZE 160 #define DEFAULT_MATCH_STACK_LIMIT_SIZE 0 /* unlimited */ #define DEFAULT_PARSE_DEPTH_LIMIT 4096 -#define OPT_EXACT_MAXLEN 24 +#define OPT_EXACT_MAXLEN 24 /* This must be smaller than ONIG_CHAR_TABLE_SIZE. */ /* check config */ #if defined(USE_PERL_SUBEXP_CALL) || defined(USE_CAPITAL_P_NAMED_GROUP) @@ -128,14 +127,14 @@ # undef ONIG_ESCAPE_UCHAR_COLLISION #endif -#define USE_WORD_BEGIN_END /* "\<": word-begin, "\>": word-end */ +/* #define USE_WORD_BEGIN_END */ /* "\<": word-begin, "\>": word-end */ #ifdef RUBY # undef USE_CAPTURE_HISTORY #else -# define USE_CAPTURE_HISTORY +/* # define USE_CAPTURE_HISTORY */ #endif -#define USE_VARIABLE_META_CHARS -#define USE_FIND_LONGEST_SEARCH_ALL_OF_RANGE +/* #define USE_VARIABLE_META_CHARS */ +/* #define USE_FIND_LONGEST_SEARCH_ALL_OF_RANGE */ /* #define USE_COMBINATION_EXPLOSION_CHECK */ /* (X*)* */ diff --git a/onigmo/regparse.c b/onigmo/regparse.c index 5e51e3950..b54a98914 100644 --- a/onigmo/regparse.c +++ b/onigmo/regparse.c @@ -3,7 +3,7 @@ **********************************************************************/ /*- * Copyright (c) 2002-2008 K.Kosako - * Copyright (c) 2011-2016 K.Takata + * Copyright (c) 2011-2019 K.Takata * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/onigmo/regparse.h b/onigmo/regparse.h index acdd3e2f5..5e8b1f6d0 100644 --- a/onigmo/regparse.h +++ b/onigmo/regparse.h @@ -5,7 +5,7 @@ **********************************************************************/ /*- * Copyright (c) 2002-2007 K.Kosako - * Copyright (c) 2011-2016 K.Takata + * Copyright (c) 2011-2019 K.Takata * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/onigmo/regversion.c b/onigmo/regversion.c index d80e8d280..9e9e3875b 100644 --- a/onigmo/regversion.c +++ b/onigmo/regversion.c @@ -2,8 +2,8 @@ regversion.c - Onigmo (Oniguruma-mod) (regular expression library) **********************************************************************/ /*- - * Copyright (c) 2002-2016 K.Kosako - * Copyright (c) 2011-2017 K.Takata + * Copyright (c) 2002-2018 K.Kosako + * Copyright (c) 2011-2019 K.Takata * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -48,8 +48,8 @@ extern const char* onig_copyright(void) { const char *s = - "Onigmo " ONIG_VERSION_STRING " : Copyright (C) 2002-2016 K.Kosako, " - "2011-2017 K.Takata"; + "Onigmo " ONIG_VERSION_STRING " : Copyright (C) 2002-2018 K.Kosako, " + "2011-2019 K.Takata"; return s; } diff --git a/onigmo/version.txt b/onigmo/version.txt index 88d06f108..6abaeb2f9 100644 --- a/onigmo/version.txt +++ b/onigmo/version.txt @@ -1 +1 @@ -6.1.3 +6.2.0 diff --git a/res/Notepad3.exe.manifest.conf b/res/Notepad3.exe.manifest.conf index 29533d7bb..4ae33eccc 100644 --- a/res/Notepad3.exe.manifest.conf +++ b/res/Notepad3.exe.manifest.conf @@ -3,7 +3,7 @@ Notepad3 develop diff --git a/scintilla/doc/ScintillaDoc.html b/scintilla/doc/ScintillaDoc.html index 709b0e7ad..a3d2d27c6 100644 --- a/scintilla/doc/ScintillaDoc.html +++ b/scintilla/doc/ScintillaDoc.html @@ -5003,8 +5003,6 @@ struct Sci_TextToFind { There is some interaction between call tips and autocompletion lists in that showing a call tip cancels any active autocompletion list, and vice versa.

-

Call tips are not implemented on Qt.

-

Call tips can highlight part of the text within them. You could use this to highlight the current argument to a function by counting the number of commas (or whatever separator your language uses). See SciTEBase::CharAdded() in SciTEBase.cxx for an diff --git a/scintilla/doc/ScintillaHistory.html b/scintilla/doc/ScintillaHistory.html index 6a90f17e0..11b388ce6 100644 --- a/scintilla/doc/ScintillaHistory.html +++ b/scintilla/doc/ScintillaHistory.html @@ -540,6 +540,7 @@ jj5 Jad Altahan + Andrea Ricchi

@@ -558,6 +559,10 @@

  • Released 10 January 2019.
    • +
  • + Calltips implemented on Qt. + Bug #1548. +
  • The C++ lexer, with styling.within.preprocessor on, now interprets "(" in preprocessor "#if(" as an operator instead of part of the directive. This improves folding as well which could become @@ -568,9 +573,21 @@ Feature #1253.
  • + Fix inconsistency with dot styling in Nim. + Feature #1260. +
    • +
  • + Enhance the styling of backticks in Nim. + Feature #1261. +
    • +
  • Fix fold behaviour with comments in nim. Feature #1254.
    • +
  • + Fix TCL lexer recognizing '"' after "," inside a bracketed substitution. + Bug #1947. +

    • Release 4.1.3 diff --git a/scintilla/lexers/LexNim.cxx b/scintilla/lexers/LexNim.cxx index 109b3547b..fec9159ef 100644 --- a/scintilla/lexers/LexNim.cxx +++ b/scintilla/lexers/LexNim.cxx @@ -424,13 +424,17 @@ void SCI_METHOD LexerNim::Lex(Sci_PositionU startPos, Sci_Position length, sc.SetState(SCE_NIM_DEFAULT); break; case SCE_NIM_IDENTIFIER: - if (!IsAWordChar(sc.ch)) { + if (sc.ch == '.' || !IsAWordChar(sc.ch)) { char s[100]; sc.GetCurrent(s, sizeof(s)); int style = SCE_NIM_IDENTIFIER; if (keywords.InList(s) && !funcNameExists) { - style = SCE_NIM_WORD; + // Prevent styling keywords if they are sub-identifiers + Sci_Position segStart = styler.GetStartSegment() - 1; + if (segStart < 0 || styler.SafeGetCharAt(segStart, '\0') != '.') { + style = SCE_NIM_WORD; + } } else if (funcNameExists) { style = SCE_NIM_FUNCNAME; } @@ -450,6 +454,18 @@ void SCI_METHOD LexerNim::Lex(Sci_PositionU startPos, Sci_Position length, sc.ForwardSetState(SCE_NIM_DEFAULT); } break; + case SCE_NIM_FUNCNAME: + if (sc.ch == '`') { + funcNameExists = false; + sc.ForwardSetState(SCE_NIM_DEFAULT); + } else if (sc.atLineEnd) { + // Prevent leaking the style to the next line if not closed + funcNameExists = false; + + sc.ChangeState(SCE_NIM_STRINGEOL); + sc.ForwardSetState(SCE_NIM_DEFAULT); + } + break; case SCE_NIM_COMMENT: if (sc.Match(']', '#')) { if (commentNestLevel > 0) { @@ -523,7 +539,10 @@ void SCI_METHOD LexerNim::Lex(Sci_PositionU startPos, Sci_Position length, } break; case SCE_NIM_BACKTICKS: - if (sc.ch == '`' || sc.atLineEnd) { + if (sc.ch == '`' ) { + sc.ForwardSetState(SCE_NIM_DEFAULT); + } else if (sc.atLineEnd) { + sc.ChangeState(SCE_NIM_STRINGEOL); sc.ForwardSetState(SCE_NIM_DEFAULT); } break; @@ -627,10 +646,10 @@ void SCI_METHOD LexerNim::Lex(Sci_PositionU startPos, Sci_Position length, } // Operator definition else if (sc.ch == '`') { - sc.SetState(SCE_NIM_BACKTICKS); - if (funcNameExists) { - funcNameExists = false; + sc.SetState(SCE_NIM_FUNCNAME); + } else { + sc.SetState(SCE_NIM_BACKTICKS); } } // Keyword diff --git a/scintilla/lexers/LexTCL.cxx b/scintilla/lexers/LexTCL.cxx index 0948f4880..1ea6ecf6e 100644 --- a/scintilla/lexers/LexTCL.cxx +++ b/scintilla/lexers/LexTCL.cxx @@ -128,8 +128,10 @@ next: continue; case ',': sc.SetState(SCE_TCL_OPERATOR); - if (subParen) + if (subParen) { sc.ForwardSetState(SCE_TCL_SUBSTITUTION); + goto next; // Already forwarded so avoid loop's Forward() + } continue; default : // maybe spaces should be allowed ??? diff --git a/scionigmo/OnigmoRegExEngine.cxx b/scionigmo/OnigmoRegExEngine.cxx index fbc543e8a..0eb925b60 100644 --- a/scionigmo/OnigmoRegExEngine.cxx +++ b/scionigmo/OnigmoRegExEngine.cxx @@ -251,7 +251,7 @@ Sci::Position OnigmoRegExEngine::FindText(Document* doc, Sci::Position minPos, S ONIG_OPTION_ON(onigmoOptions, (rangeEnd != docLen) ? ONIG_OPTION_NOTEOL : ONIG_OPTION_NONE); std::string sPattern(pattern); - std::string const sRegExprStrg = translateRegExpr(sPattern, word, wordStart, doc->eolMode, onigmoOptions); + std::string const & sRegExprStrg = translateRegExpr(sPattern, word, wordStart, doc->eolMode, onigmoOptions); bool const bReCompile = (m_RegExpr == nullptr) || (m_CmplOptions != onigmoOptions) || (m_RegExprStrg.compare(sRegExprStrg) != 0); @@ -360,7 +360,7 @@ const char* OnigmoRegExEngine::SubstituteByPosition(Document* doc, const char* t return nullptr; } std::string sText(text, *length); - std::string const rawReplStrg = convertReplExpr(sText); + std::string const & rawReplStrg = convertReplExpr(sText); m_SubstBuffer.clear(); diff --git a/src/Dialogs.c b/src/Dialogs.c index 1ab60140a..900f85920 100644 --- a/src/Dialogs.c +++ b/src/Dialogs.c @@ -508,28 +508,26 @@ INT_PTR CALLBACK AboutDlgProc(HWND hwnd, UINT umsg, WPARAM wParam, LPARAM lParam { case WM_INITDIALOG: { - { - if (Globals.hDlgIcon) { SendMessage(hwnd, WM_SETICON, ICON_SMALL, (LPARAM)Globals.hDlgIcon); } + if (Globals.hDlgIcon) { SendMessage(hwnd, WM_SETICON, ICON_SMALL, (LPARAM)Globals.hDlgIcon); } - SetDlgItemText(hwnd, IDC_VERSION, MKWCS(VERSION_FILEVERSION_LONG)); + SetDlgItemText(hwnd, IDC_VERSION, MKWCS(VERSION_FILEVERSION_LONG)); - if (hFontTitle) { DeleteObject(hFontTitle); } + if (hFontTitle) { DeleteObject(hFontTitle); } - if (NULL == (hFontTitle = (HFONT)SendDlgItemMessage(hwnd, IDC_VERSION, WM_GETFONT, 0, 0))) { - hFontTitle = GetStockObject(DEFAULT_GUI_FONT); - } - - LOGFONT lf; - GetObject(hFontTitle, sizeof(LOGFONT), &lf); - lf.lfWeight = FW_BOLD; - lf.lfWidth = ScaleIntFontSize(8); - lf.lfHeight = ScaleIntFontSize(22); - // lf.lfQuality = ANTIALIASED_QUALITY; - hFontTitle = CreateFontIndirect(&lf); - - SendDlgItemMessage(hwnd, IDC_VERSION, WM_SETFONT, (WPARAM)hFontTitle, true); + if (NULL == (hFontTitle = (HFONT)SendDlgItemMessage(hwnd, IDC_VERSION, WM_GETFONT, 0, 0))) { + hFontTitle = GetStockObject(DEFAULT_GUI_FONT); } + LOGFONT lf; + GetObject(hFontTitle, sizeof(LOGFONT), &lf); + lf.lfWeight = FW_BOLD; + lf.lfWidth = ScaleIntFontSize(8); + lf.lfHeight = ScaleIntFontSize(22); + // lf.lfQuality = ANTIALIASED_QUALITY; + hFontTitle = CreateFontIndirect(&lf); + + SendDlgItemMessage(hwnd, IDC_VERSION, WM_SETFONT, (WPARAM)hFontTitle, true); + SetDlgItemText(hwnd, IDC_SCI_VERSION, VERSION_SCIVERSION); SetDlgItemText(hwnd, IDC_COPYRIGHT, VERSION_LEGALCOPYRIGHT); SetDlgItemText(hwnd, IDC_AUTHORNAME, VERSION_AUTHORNAME); diff --git a/src/Dlapi.c b/src/Dlapi.c index 2f8e4794d..909c7211c 100644 --- a/src/Dlapi.c +++ b/src/Dlapi.c @@ -1266,7 +1266,7 @@ bool DriveBox_SelectDrive(HWND hwnd,LPCWSTR lpszPath) } // Don't select anything - SendMessage(hwnd,CB_SETCURSEL,(WPARAM)-1,0); + SendMessage(hwnd,CB_SETCURSEL,(WPARAM)1,0); return false; } diff --git a/src/Edit.c b/src/Edit.c index 0ea9d2f7b..60d0c71cc 100644 --- a/src/Edit.c +++ b/src/Edit.c @@ -3479,7 +3479,7 @@ void EditStripLastCharacter(HWND hwnd, bool bIgnoreSelection, bool bTrailingBlan if (bTrailingBlanksOnly) { DocPos i = iEndPos; - char ch = '\0'; + char ch; do { ch = SciCall_GetCharAt(--i); } while ((i >= iStartPos) && IsBlankChar(ch)); diff --git a/src/Encoding.c b/src/Encoding.c index 7f403b8de..bb00fb5f1 100644 --- a/src/Encoding.c +++ b/src/Encoding.c @@ -343,7 +343,7 @@ typedef struct _ee { } ENCODINGENTRY, *PENCODINGENTRY; int CmpEncoding(const void *s1, const void *s2) { - return StrCmp(((PENCODINGENTRY)s1)->wch, ((PENCODINGENTRY)s2)->wch); + return StrCmp(((const PENCODINGENTRY)s1)->wch, ((const PENCODINGENTRY)s2)->wch); } // ============================================================================ diff --git a/src/Notepad3.c b/src/Notepad3.c index bdf92934d..4e9c8f417 100644 --- a/src/Notepad3.c +++ b/src/Notepad3.c @@ -2937,7 +2937,7 @@ LRESULT MsgInitMenu(HWND hwnd, WPARAM wParam, LPARAM lParam) EnableCmd(hmenu,IDM_VIEW_CUSTOMIZETB, Settings.ShowToolbar); CheckCmd(hmenu,IDM_VIEW_STATUSBAR,Settings.ShowStatusbar); - i = SciCall_GetLexer(); + //i = SciCall_GetLexer(); //EnableCmd(hmenu,IDM_VIEW_AUTOCLOSETAGS,(i == SCLEX_HTML || i == SCLEX_XML)); CheckCmd(hmenu, IDM_VIEW_AUTOCLOSETAGS, Settings.AutoCloseTags /*&& (i == SCLEX_HTML || i == SCLEX_XML)*/); diff --git a/src/Notepad3.cppcheck b/src/Notepad3.cppcheck new file mode 100644 index 000000000..ee5822030 --- /dev/null +++ b/src/Notepad3.cppcheck @@ -0,0 +1,14 @@ + + + win64 + true + + windows + + + cert + + + clang-tidy + + diff --git a/src/Styles.c b/src/Styles.c index 0b6bd76dc..85fc209c8 100644 --- a/src/Styles.c +++ b/src/Styles.c @@ -338,14 +338,13 @@ void Style_Load() // void Style_Save() { - WCHAR tch[32] = { L'\0' };; - WCHAR szTmpStyle[BUFSIZE_STYLE_VALUE] = { L'\0' }; size_t const len = NUMLEXERS * AVG_NUM_OF_STYLES_PER_LEXER * 100; WCHAR *pIniSection = AllocMem(len * sizeof(WCHAR), HEAP_ZERO_MEMORY); if (pIniSection) { // Custom colors for (int i = 0; i < 16; i++) { if (s_colorCustom[i] != s_colorDefault[i]) { + WCHAR tch[32] = { L'\0' }; WCHAR wch[32] = { L'\0' }; StringCchPrintf(tch, COUNTOF(tch), L"%02i", i + 1); StringCchPrintf(wch, COUNTOF(wch), L"#%02X%02X%02X", @@ -393,6 +392,7 @@ void Style_Save() while (g_pLexArray[iLexer]->Styles[i].iStyle != -1) { if (((*pLexFunction)(FCT_SETTING_CHANGE, 0) & (((__int64)1) << (i+2))) != 0LL) { // normalize + WCHAR szTmpStyle[BUFSIZE_STYLE_VALUE]; szTmpStyle[0] = L'\0'; // clear Style_CopyStyles_IfNotDefined(g_pLexArray[iLexer]->Styles[i].szValue, szTmpStyle, COUNTOF(szTmpStyle), true, true); IniSectionSetString(pIniSection, g_pLexArray[iLexer]->Styles[i].pszName, szTmpStyle); @@ -468,7 +468,6 @@ bool Style_Export(HWND hwnd) WCHAR szFile[MAX_PATH * 2] = { L'\0' }; WCHAR szFilter[256] = { L'\0' }; OPENFILENAME ofn; - DWORD dwError = ERROR_SUCCESS; ZeroMemory(&ofn,sizeof(OPENFILENAME)); GetLngString(IDS_MUI_FILTER_INI,szFilter,COUNTOF(szFilter)); @@ -485,6 +484,7 @@ bool Style_Export(HWND hwnd) if (GetSaveFileName(&ofn)) { + DWORD dwError = ERROR_SUCCESS; size_t const len = NUMLEXERS * AVG_NUM_OF_STYLES_PER_LEXER * 100; WCHAR *pIniSection = AllocMem(len * sizeof(WCHAR), HEAP_ZERO_MEMORY); if (pIniSection) { @@ -843,10 +843,10 @@ void Style_SetLexer(HWND hwnd, PEDITLEXER pLexNew) else { SendMessage(hwnd, SCI_SETCARETSTYLE, CARETSTYLE_LINE, 0); - WCHAR wch[32] = { L'\0' }; iValue = 1; fValue = 1.0f; // default caret width if (Style_StrGetSize(pCurrentStandard->Styles[STY_CARET].szValue, &fValue)) { + WCHAR wch[32] = { L'\0' }; iValue = clampi(float2int(fValue), 1, 3); // don't allow invisible 0 StringCchPrintf(wch,COUNTOF(wch),L"size:%i",iValue); StringCchCat(wchSpecificStyle,COUNTOF(wchSpecificStyle),wch); @@ -1822,10 +1822,10 @@ bool Style_StrGetFont(LPCWSTR lpszStyle, LPWSTR lpszFont, int cchFont) // bool Style_StrGetFontQuality(LPCWSTR lpszStyle,LPWSTR lpszQuality,int cchQuality) { - WCHAR tch[BUFSIZE_STYLE_VALUE] = { L'\0' }; WCHAR *p = StrStrI(lpszStyle, L"smoothing:"); if (p) { + WCHAR tch[BUFSIZE_STYLE_VALUE] = { L'\0' }; StringCchCopy(tch,COUNTOF(tch),p + CSTRLEN(L"smoothing:")); p = StrChr(tch, L';'); if (p) @@ -1929,12 +1929,10 @@ bool Style_StrGetSize(LPCWSTR lpszStyle, float* f) // bool Style_StrGetSizeStr(LPCWSTR lpszStyle,LPWSTR lpszSize,int cchSize) { - WCHAR tch[BUFSIZE_STYLE_VALUE] = { L'\0' }; - WCHAR wchFloatVal[64]; - WCHAR *p = StrStrI(lpszStyle, L"size:"); if (p) { + WCHAR tch[BUFSIZE_STYLE_VALUE] = { L'\0' }; StringCchCopy(tch, COUNTOF(tch), (p + CSTRLEN(L"size:"))); p = StrChr(tch, L';'); if (p) { *p = L'\0'; } @@ -1942,6 +1940,7 @@ bool Style_StrGetSizeStr(LPCWSTR lpszStyle,LPWSTR lpszSize,int cchSize) float fValue = 0.0f; if (Char2FloatW(tch, &fValue)) { + WCHAR wchFloatVal[64]; fValue = (float)fabs(fValue); Float2String(fValue, wchFloatVal, COUNTOF(wchFloatVal)); @@ -2034,12 +2033,12 @@ void Style_AppendWeightStr(LPWSTR lpszWeight, int cchSize, int fontWeight) // bool Style_StrGetColor(bool bFore, LPCWSTR lpszStyle, COLORREF* rgb) { - WCHAR tch[BUFSIZE_STYLE_VALUE] = { L'\0' }; WCHAR *pItem = (bFore) ? L"fore:" : L"back:"; WCHAR *p = StrStrI(lpszStyle, pItem); if (p) { + WCHAR tch[BUFSIZE_STYLE_VALUE] = { L'\0' }; StringCchCopy(tch, COUNTOF(tch), p + StringCchLenW(pItem,0)); if (tch[0] == L'#') tch[0] = L' '; @@ -2586,11 +2585,11 @@ bool Style_SelectFont(HWND hwnd,LPWSTR lpszStyle,int cchStyle, LPCWSTR sLexerNam StringCchCat(szNewStyle, COUNTOF(szNewStyle), newSize); - WCHAR chset[32] = { L'\0' }; if (bGlobalDefaultStyle && (lf.lfCharSet != DEFAULT_CHARSET) && (lf.lfCharSet != ANSI_CHARSET) && (lf.lfCharSet != Globals.iDefaultCharSet)) { + WCHAR chset[32] = { L'\0' }; if (lf.lfCharSet == iCharSet) { if (StrStrI(lpszStyle, L"charset:")) { @@ -3129,7 +3128,6 @@ INT_PTR CALLBACK Style_CustomizeSchemesDlgProc(HWND hwnd,UINT umsg,WPARAM wParam static PEDITLEXER pCurrentLexer = NULL; static PEDITSTYLE pCurrentStyle = NULL; static int iCurStyleIdx = -1; - static HFONT hFontTitle; static HBRUSH hbrFore; static HBRUSH hbrBack; static bool bIsStyleSelected = false; @@ -3137,13 +3135,11 @@ INT_PTR CALLBACK Style_CustomizeSchemesDlgProc(HWND hwnd,UINT umsg,WPARAM wParam static WCHAR* Style_StylesBackup[NUMLEXERS * AVG_NUM_OF_STYLES_PER_LEXER]; static __int64 Style_ChangedBackup[NUMLEXERS]; - WCHAR tchBuf[128] = { L'\0' }; - WCHAR wchText[512] = { L'\0' }; - switch(umsg) { case WM_INITDIALOG: { + WCHAR wchText[512] = { L'\0' }; if (Globals.hDlgIcon) { SendMessage(hwnd, WM_SETICON, ICON_SMALL, (LPARAM)Globals.hDlgIcon); } GetLngString(IDS_MUI_STYLEEDIT_HELP, wchText, COUNTOF(wchText)); SetDlgItemText(hwnd, IDC_STYLEEDIT_HELP, wchText); @@ -3207,6 +3203,7 @@ INT_PTR CALLBACK Style_CustomizeSchemesDlgProc(HWND hwnd,UINT umsg,WPARAM wParam MakeBitmapButton(hwnd,IDC_NEXTSTYLE,Globals.hInstance,IDB_NEXT); // Setup title font + static HFONT hFontTitle = NULL; if (hFontTitle) { DeleteObject(hFontTitle); } @@ -3225,6 +3222,7 @@ INT_PTR CALLBACK Style_CustomizeSchemesDlgProc(HWND hwnd,UINT umsg,WPARAM wParam else SetDlgPos(hwnd, Settings.CustomSchemesDlgPosX, Settings.CustomSchemesDlgPosY); + WCHAR tchBuf[128] = { L'\0' }; HMENU hmenu = GetSystemMenu(hwnd, false); GetLngString(IDS_MUI_PREVIEW, tchBuf, COUNTOF(tchBuf)); InsertMenu(hmenu, 0, MF_BYPOSITION | MF_STRING | MF_ENABLED, IDS_MUI_PREVIEW, tchBuf); diff --git a/src/Version.h b/src/Version.h index 4fe3effde..2c8463108 100644 --- a/src/Version.h +++ b/src/Version.h @@ -71,7 +71,7 @@ #endif #elif (_MSC_VER >= 1916) #if(_MSC_FULL_VER >= 191627026) - #define VER_CPL MS Visual C++ 2017 v15.9.5 + #define VER_CPL MS Visual C++ 2017 v15.9.(5-6) #elif(_MSC_FULL_VER >= 191627025) #define VER_CPL MS Visual C++ 2017 v15.9.4 #elif(_MSC_FULL_VER >= 191627024) diff --git a/src/VersionEx.h b/src/VersionEx.h index 057886679..a702587da 100644 --- a/src/VersionEx.h +++ b/src/VersionEx.h @@ -6,8 +6,8 @@ #define APPNAME "Notepad3" #define VERSION_MAJOR 5 #define VERSION_MINOR 19 -#define VERSION_REV 125 -#define VERSION_BUILD 1608 +#define VERSION_REV 130 +#define VERSION_BUILD 1611 #define SCINTILLA_VER 413 -#define ONIGMO_REGEX_VER 6.1.3 +#define ONIGMO_REGEX_VER 6.2.0 #define VERSION_PATCH "develop"