diff options
| -rw-r--r-- | ChangeLog | 6 | ||||
| -rw-r--r-- | enc/gb18030.c | 2 | ||||
| -rw-r--r-- | enc/koi8_u.c | 221 | ||||
| -rw-r--r-- | enc/unicode.c | 4 | ||||
| -rw-r--r-- | enc/utf_8.c | 10 | ||||
| -rw-r--r-- | regenc.c | 48 |
6 files changed, 260 insertions, 31 deletions
@@ -1,3 +1,9 @@ +Sun Jan 20 00:33:59 2008 NARUSE, Yui <naruse@ruby-lang.org> + + * enc/koi8_u.c: added. + + * regenc.c, enc/utf_8.c, enc/unicode.c, enc/gb18030.c: add ARG_UNUSED. + Sat Jan 19 22:41:39 2008 Tanaka Akira <akr@fsij.org> * string.c (coderange_scan): don't call mbclen functions for ASCII diff --git a/enc/gb18030.c b/enc/gb18030.c index b2adb785f8..1d48ef23d6 100644 --- a/enc/gb18030.c +++ b/enc/gb18030.c @@ -494,5 +494,5 @@ OnigEncodingDefine(gb18030, GB18030) = { gb18030_is_allowed_reverse_match }; ENC_REPLICATE("GBK", "GB18030"); -ENC_ALIAS("CP936", "GBK"); +ENC_REPLICATE("CP936", "GB18030"); ENC_ALIAS("Windows-936", "GBK"); diff --git a/enc/koi8_u.c b/enc/koi8_u.c new file mode 100644 index 0000000000..9bd363df12 --- /dev/null +++ b/enc/koi8_u.c @@ -0,0 +1,221 @@ +/********************************************************************** + koi8_u.c - Oniguruma (regular expression library) +**********************************************************************/ +/*- + * Copyright (c) 2002-2007 K.Kosako <sndgk393 AT ybb DOT ne DOT jp> + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#include "regenc.h" + +#define ENC_KOI8_U_TO_LOWER_CASE(c) EncKOI8_U_ToLowerCaseTable[c] +#define ENC_IS_KOI8_U_CTYPE(code,ctype) \ + ((EncKOI8_U_CtypeTable[code] & CTYPE_TO_BIT(ctype)) != 0) + +static const UChar EncKOI8_U_ToLowerCaseTable[256] = { + '\000', '\001', '\002', '\003', '\004', '\005', '\006', '\007', + '\010', '\011', '\012', '\013', '\014', '\015', '\016', '\017', + '\020', '\021', '\022', '\023', '\024', '\025', '\026', '\027', + '\030', '\031', '\032', '\033', '\034', '\035', '\036', '\037', + '\040', '\041', '\042', '\043', '\044', '\045', '\046', '\047', + '\050', '\051', '\052', '\053', '\054', '\055', '\056', '\057', + '\060', '\061', '\062', '\063', '\064', '\065', '\066', '\067', + '\070', '\071', '\072', '\073', '\074', '\075', '\076', '\077', + '\100', '\141', '\142', '\143', '\144', '\145', '\146', '\147', + '\150', '\151', '\152', '\153', '\154', '\155', '\156', '\157', + '\160', '\161', '\162', '\163', '\164', '\165', '\166', '\167', + '\170', '\171', '\172', '\133', '\134', '\135', '\136', '\137', + '\140', '\141', '\142', '\143', '\144', '\145', '\146', '\147', + '\150', '\151', '\152', '\153', '\154', '\155', '\156', '\157', + '\160', '\161', '\162', '\163', '\164', '\165', '\166', '\167', + '\170', '\171', '\172', '\173', '\174', '\175', '\176', '\177', + '\200', '\201', '\202', '\203', '\204', '\205', '\206', '\207', + '\210', '\211', '\212', '\213', '\214', '\215', '\216', '\217', + '\220', '\221', '\222', '\223', '\224', '\225', '\226', '\227', + '\230', '\231', '\232', '\233', '\234', '\235', '\236', '\237', + '\240', '\241', '\242', '\243', '\244', '\245', '\246', '\247', + '\250', '\251', '\252', '\253', '\254', '\255', '\256', '\257', + '\260', '\261', '\262', '\243', '\244', '\265', '\246', '\247', + '\270', '\271', '\272', '\273', '\274', '\255', '\276', '\277', + '\300', '\301', '\302', '\303', '\304', '\305', '\306', '\307', + '\310', '\311', '\312', '\313', '\314', '\315', '\316', '\317', + '\320', '\321', '\322', '\323', '\324', '\325', '\326', '\327', + '\330', '\331', '\332', '\333', '\334', '\335', '\336', '\337', + '\300', '\301', '\302', '\303', '\304', '\305', '\306', '\307', + '\310', '\311', '\312', '\313', '\314', '\315', '\316', '\317', + '\320', '\321', '\322', '\323', '\324', '\325', '\326', '\327', + '\330', '\331', '\332', '\333', '\334', '\335', '\336', '\337' +}; + +static const unsigned short EncKOI8_U_CtypeTable[256] = { + 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, + 0x4008, 0x420c, 0x4209, 0x4208, 0x4208, 0x4208, 0x4008, 0x4008, + 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, + 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, 0x4008, + 0x4284, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, + 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, + 0x78b0, 0x78b0, 0x78b0, 0x78b0, 0x78b0, 0x78b0, 0x78b0, 0x78b0, + 0x78b0, 0x78b0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x41a0, + 0x41a0, 0x7ca2, 0x7ca2, 0x7ca2, 0x7ca2, 0x7ca2, 0x7ca2, 0x74a2, + 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, + 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, 0x74a2, + 0x74a2, 0x74a2, 0x74a2, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x51a0, + 0x41a0, 0x78e2, 0x78e2, 0x78e2, 0x78e2, 0x78e2, 0x78e2, 0x70e2, + 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, + 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, 0x70e2, + 0x70e2, 0x70e2, 0x70e2, 0x41a0, 0x41a0, 0x41a0, 0x41a0, 0x4008, + 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, + 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, + 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, + 0x00a0, 0x00a0, 0x0284, 0x00a0, 0x00a0, 0x10a0, 0x01a0, 0x00a0, + 0x00a0, 0x00a0, 0x00a0, 0x30e2, 0x30e2, 0x00a0, 0x30e2, 0x30e2, + 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x30e2, 0x00a0, 0x00a0, + 0x00a0, 0x00a0, 0x00a0, 0x34a2, 0x34a2, 0x00a0, 0x34a2, 0x34a2, + 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x00a0, 0x34a2, 0x00a0, 0x00a0, + 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, + 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, + 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, + 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, 0x30e2, + 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, + 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, + 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, + 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2, 0x34a2 +}; + +static int +koi8_u_mbc_case_fold(OnigCaseFoldType flag ARG_UNUSED, + const UChar** pp, const UChar* end ARG_UNUSED, + UChar* lower, OnigEncoding enc ARG_UNUSED) +{ + const UChar* p = *pp; + + *lower = ENC_KOI8_U_TO_LOWER_CASE(*p); + (*pp)++; + return 1; +} + +#if 0 +static int +koi8_u_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, + const UChar* end, OnigEncoding enc ARG_UNUSED) +{ + int v; + const UChar* p = *pp; + + (*pp)++; + v = (EncKOI8_U_CtypeTable[*p] & (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER)); + return (v != 0 ? TRUE : FALSE); +} +#endif + +static int +koi8_u_is_code_ctype(OnigCodePoint code, unsigned int ctype, + OnigEncoding enc ARG_UNUSED) +{ + if (code < 256) + return ENC_IS_KOI8_U_CTYPE(code, ctype); + else + return FALSE; +} + +static const OnigPairCaseFoldCodes CaseFoldMap[] = { + { 0xa3, 0xb3 }, + { 0xa4, 0xb4 }, + { 0xa6, 0xb6 }, + { 0xa7, 0xb7 }, + { 0xad, 0xbd }, + + { 0xc0, 0xe0 }, + { 0xc1, 0xe1 }, + { 0xc2, 0xe2 }, + { 0xc3, 0xe3 }, + { 0xc4, 0xe4 }, + { 0xc5, 0xe5 }, + { 0xc6, 0xe6 }, + { 0xc7, 0xe7 }, + { 0xc8, 0xe8 }, + { 0xc9, 0xe9 }, + { 0xca, 0xea }, + { 0xcb, 0xeb }, + { 0xcc, 0xec }, + { 0xcd, 0xed }, + { 0xce, 0xee }, + { 0xcf, 0xef }, + + { 0xd0, 0xf0 }, + { 0xd1, 0xf1 }, + { 0xd2, 0xf2 }, + { 0xd3, 0xf3 }, + { 0xd4, 0xf4 }, + { 0xd5, 0xf5 }, + { 0xd6, 0xf6 }, + { 0xd7, 0xf7 }, + { 0xd8, 0xf8 }, + { 0xd9, 0xf9 }, + { 0xda, 0xfa }, + { 0xdb, 0xfb }, + { 0xdc, 0xfc }, + { 0xdd, 0xfd }, + { 0xde, 0xfe }, + { 0xdf, 0xff } +}; + +static int +koi8_u_apply_all_case_fold(OnigCaseFoldType flag, + OnigApplyAllCaseFoldFunc f, + void* arg, OnigEncoding enc ARG_UNUSED) +{ + return onigenc_apply_all_case_fold_with_map( + sizeof(CaseFoldMap)/sizeof(OnigPairCaseFoldCodes), CaseFoldMap, 0, + flag, f, arg); +} + +static int +koi8_u_get_case_fold_codes_by_str(OnigCaseFoldType flag, + const OnigUChar* p, const OnigUChar* end, + OnigCaseFoldCodeItem items[], OnigEncoding enc ARG_UNUSED) +{ + return onigenc_get_case_fold_codes_by_str_with_map( + sizeof(CaseFoldMap)/sizeof(OnigPairCaseFoldCodes), CaseFoldMap, 0, + flag, p, end, items); +} + +OnigEncodingDefine(koi8_u, KOI8_U) = { + onigenc_single_byte_mbc_enc_len, + "KOI8-U", /* name */ + 1, /* max enc length */ + 1, /* min enc length */ + onigenc_is_mbc_newline_0x0a, + onigenc_single_byte_mbc_to_code, + onigenc_single_byte_code_to_mbclen, + onigenc_single_byte_code_to_mbc, + koi8_u_mbc_case_fold, + koi8_u_apply_all_case_fold, + koi8_u_get_case_fold_codes_by_str, + onigenc_minimum_property_name_to_ctype, + koi8_u_is_code_ctype, + onigenc_not_support_get_ctype_code_range, + onigenc_single_byte_left_adjust_char_head, + onigenc_always_true_is_allowed_reverse_match +}; diff --git a/enc/unicode.c b/enc/unicode.c index 126588f3fb..bcd82e54fa 100644 --- a/enc/unicode.c +++ b/enc/unicode.c @@ -10745,7 +10745,7 @@ static void init_code_range_array(void) { } extern int -onigenc_unicode_is_code_ctype(OnigCodePoint code, unsigned int ctype, OnigEncoding enc) +onigenc_unicode_is_code_ctype(OnigCodePoint code, unsigned int ctype, OnigEncoding enc ARG_UNUSED) { if ( #ifdef USE_UNICODE_PROPERTIES @@ -11014,7 +11014,7 @@ onigenc_unicode_mbc_case_fold(OnigEncoding enc, extern int onigenc_unicode_apply_all_case_fold(OnigCaseFoldType flag, OnigApplyAllCaseFoldFunc f, void* arg, - OnigEncoding enc) + OnigEncoding enc ARG_UNUSED) { const CaseUnfold_11_Type* p11; OnigCodePoint code; diff --git a/enc/utf_8.c b/enc/utf_8.c index ebc53f24b8..b9dfe71f8d 100644 --- a/enc/utf_8.c +++ b/enc/utf_8.c @@ -217,7 +217,7 @@ static const signed char trans[][0x100] = { #undef F static int -mbc_enc_len(const UChar* p, const UChar* e, OnigEncoding enc) +mbc_enc_len(const UChar* p, const UChar* e, OnigEncoding enc ARG_UNUSED) { int firstbyte = *p++; state_t s; @@ -294,7 +294,7 @@ mbc_to_code(const UChar* p, const UChar* end, OnigEncoding enc) } static int -code_to_mbclen(OnigCodePoint code, OnigEncoding enc) +code_to_mbclen(OnigCodePoint code, OnigEncoding enc ARG_UNUSED) { if ((code & 0xffffff80) == 0) return 1; else if ((code & 0xfffff800) == 0) return 2; @@ -311,7 +311,7 @@ code_to_mbclen(OnigCodePoint code, OnigEncoding enc) } static int -code_to_mbc(OnigCodePoint code, UChar *buf, OnigEncoding enc) +code_to_mbc(OnigCodePoint code, UChar *buf, OnigEncoding enc ARG_UNUSED) { #define UTF8_TRAILS(code, shift) (UChar )((((code) >> (shift)) & 0x3f) | 0x80) #define UTF8_TRAIL0(code) (UChar )(((code) & 0x3f) | 0x80) @@ -397,7 +397,7 @@ mbc_case_fold(OnigCaseFoldType flag, const UChar** pp, static int get_ctype_code_range(OnigCtype ctype, OnigCodePoint *sb_out, - const OnigCodePoint* ranges[], OnigEncoding enc) + const OnigCodePoint* ranges[], OnigEncoding enc ARG_UNUSED) { *sb_out = 0x80; return onigenc_unicode_ctype_code_range(ctype, ranges); @@ -405,7 +405,7 @@ get_ctype_code_range(OnigCtype ctype, OnigCodePoint *sb_out, static UChar* -left_adjust_char_head(const UChar* start, const UChar* s, OnigEncoding enc) +left_adjust_char_head(const UChar* start, const UChar* s, OnigEncoding enc ARG_UNUSED) { const UChar *p; @@ -395,7 +395,7 @@ const OnigPairCaseFoldCodes OnigAsciiLowerMap[] = { extern int onigenc_ascii_apply_all_case_fold(OnigCaseFoldType flag ARG_UNUSED, OnigApplyAllCaseFoldFunc f, void* arg, - OnigEncoding enc) + OnigEncoding enc ARG_UNUSED) { OnigCodePoint code; int i, r; @@ -416,9 +416,9 @@ onigenc_ascii_apply_all_case_fold(OnigCaseFoldType flag ARG_UNUSED, } extern int -onigenc_ascii_get_case_fold_codes_by_str(OnigCaseFoldType flag, - const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[], - OnigEncoding enc) +onigenc_ascii_get_case_fold_codes_by_str(OnigCaseFoldType flag ARG_UNUSED, + const OnigUChar* p, const OnigUChar* end ARG_UNUSED, OnigCaseFoldCodeItem items[], + OnigEncoding enc ARG_UNUSED) { if (0x41 <= *p && *p <= 0x5a) { items[0].byte_len = 1; @@ -564,7 +564,7 @@ onigenc_not_support_get_ctype_code_range(OnigCtype ctype, } extern int -onigenc_is_mbc_newline_0x0a(const UChar* p, const UChar* end, OnigEncoding enc) +onigenc_is_mbc_newline_0x0a(const UChar* p, const UChar* end, OnigEncoding enc ARG_UNUSED) { if (p < end) { if (*p == 0x0a) return 1; @@ -574,8 +574,8 @@ onigenc_is_mbc_newline_0x0a(const UChar* p, const UChar* end, OnigEncoding enc) /* for single byte encodings */ extern int -onigenc_ascii_mbc_case_fold(OnigCaseFoldType flag, const UChar** p, - const UChar*end, UChar* lower, OnigEncoding enc) +onigenc_ascii_mbc_case_fold(OnigCaseFoldType flag ARG_UNUSED, const UChar** p, + const UChar*end, UChar* lower, OnigEncoding enc ARG_UNUSED) { *lower = ONIGENC_ASCII_CODE_TO_LOWER_CASE(**p); @@ -585,8 +585,8 @@ onigenc_ascii_mbc_case_fold(OnigCaseFoldType flag, const UChar** p, #if 0 extern int -onigenc_ascii_is_mbc_ambiguous(OnigCaseFoldType flag, - const UChar** pp, const UChar* end) +onigenc_ascii_is_mbc_ambiguous(OnigCaseFoldType flag ARG_UNUSED, + const UChar** pp, const UChar* end ARG_UNUSED) { const UChar* p = *pp; @@ -596,54 +596,56 @@ onigenc_ascii_is_mbc_ambiguous(OnigCaseFoldType flag, #endif extern int -onigenc_single_byte_mbc_enc_len(const UChar* p, const UChar* e, OnigEncoding enc) +onigenc_single_byte_mbc_enc_len(const UChar* p ARG_UNUSED, const UChar* e ARG_UNUSED, + OnigEncoding enc ARG_UNUSED) { return 1; } extern OnigCodePoint -onigenc_single_byte_mbc_to_code(const UChar* p, const UChar* end, OnigEncoding enc) +onigenc_single_byte_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED, + OnigEncoding enc ARG_UNUSED) { return (OnigCodePoint )(*p); } extern int -onigenc_single_byte_code_to_mbclen(OnigCodePoint code, OnigEncoding enc) +onigenc_single_byte_code_to_mbclen(OnigCodePoint code ARG_UNUSED, OnigEncoding enc ARG_UNUSED) { return 1; } extern int -onigenc_single_byte_code_to_mbc(OnigCodePoint code, UChar *buf, OnigEncoding enc) +onigenc_single_byte_code_to_mbc(OnigCodePoint code, UChar *buf, OnigEncoding enc ARG_UNUSED) { *buf = (UChar )(code & 0xff); return 1; } extern UChar* -onigenc_single_byte_left_adjust_char_head(const UChar* start, const UChar* s, - OnigEncoding enc) +onigenc_single_byte_left_adjust_char_head(const UChar* start ARG_UNUSED, const UChar* s, + OnigEncoding enc ARG_UNUSED) { return (UChar* )s; } extern int -onigenc_always_true_is_allowed_reverse_match(const UChar* s, const UChar* end, - OnigEncoding enc) +onigenc_always_true_is_allowed_reverse_match(const UChar* s ARG_UNUSED, const UChar* end ARG_UNUSED, + OnigEncoding enc ARG_UNUSED) { return TRUE; } extern int -onigenc_always_false_is_allowed_reverse_match(const UChar* s, const UChar* end, - OnigEncoding enc) +onigenc_always_false_is_allowed_reverse_match(const UChar* s ARG_UNUSED, const UChar* end ARG_UNUSED, + OnigEncoding enc ARG_UNUSED) { return FALSE; } extern int onigenc_ascii_is_code_ctype(OnigCodePoint code, unsigned int ctype, - OnigEncoding enc) + OnigEncoding enc ARG_UNUSED) { if (code < 128) return ONIGENC_IS_ASCII_CODE_CTYPE(code, ctype); @@ -697,7 +699,7 @@ onigenc_mbn_mbc_case_fold(OnigEncoding enc, OnigCaseFoldType flag ARG_UNUSED, #if 0 extern int onigenc_mbn_is_mbc_ambiguous(OnigEncoding enc, OnigCaseFoldType flag, - const UChar** pp, const UChar* end) + const UChar** pp ARG_UNUSED, const UChar* end ARG_UNUSED) { const UChar* p = *pp; @@ -712,14 +714,14 @@ onigenc_mbn_is_mbc_ambiguous(OnigEncoding enc, OnigCaseFoldType flag, #endif extern int -onigenc_mb2_code_to_mbclen(OnigCodePoint code, OnigEncoding enc) +onigenc_mb2_code_to_mbclen(OnigCodePoint code, OnigEncoding enc ARG_UNUSED) { if ((code & 0xff00) != 0) return 2; else return 1; } extern int -onigenc_mb4_code_to_mbclen(OnigCodePoint code, OnigEncoding enc) +onigenc_mb4_code_to_mbclen(OnigCodePoint code, OnigEncoding enc ARG_UNUSED) { if ((code & 0xff000000) != 0) return 4; else if ((code & 0xff0000) != 0) return 3; |