* 2022-01-18 [ci skip]
[ruby-80x24.org.git] / regenc.h
blob16ed6c39da0144e3f72a25f3064dedca5c39448e
1 #ifndef ONIGMO_REGENC_H
2 #define ONIGMO_REGENC_H
3 /**********************************************************************
4 regenc.h - Onigmo (Oniguruma-mod) (regular expression library)
5 **********************************************************************/
6 /*-
7 * Copyright (c) 2002-2008 K.Kosako <sndgk393 AT ybb DOT ne DOT jp>
8 * Copyright (c) 2011-2016 K.Takata <kentkt AT csc DOT jp>
9 * All rights reserved.
11 * Redistribution and use in source and binary forms, with or without
12 * modification, are permitted provided that the following conditions
13 * are met:
14 * 1. Redistributions of source code must retain the above copyright
15 * notice, this list of conditions and the following disclaimer.
16 * 2. Redistributions in binary form must reproduce the above copyright
17 * notice, this list of conditions and the following disclaimer in the
18 * documentation and/or other materials provided with the distribution.
20 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
21 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
22 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
23 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
24 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
25 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
26 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
27 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
28 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
29 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
30 * SUCH DAMAGE.
33 #if !defined(RUBY) && (defined(RUBY_EXPORT) || defined(ONIG_ENC_REGISTER))
34 # define RUBY
35 #endif
36 #ifdef RUBY
37 # ifndef ONIGMO_REGINT_H
38 # ifndef RUBY_EXTERN
39 # include "ruby/config.h"
40 # include "ruby/defines.h"
41 # endif
42 # endif
43 #else /* RUBY */
44 # ifndef PACKAGE
45 /* PACKAGE is defined in config.h */
46 # include "config.h"
47 # endif
48 #endif /* RUBY */
50 #ifdef ONIG_ESCAPE_UCHAR_COLLISION
51 # undef ONIG_ESCAPE_UCHAR_COLLISION
52 #endif
54 #ifdef RUBY
55 # include "ruby/onigmo.h"
56 #else
57 # include "onigmo.h"
58 #endif
60 RUBY_SYMBOL_EXPORT_BEGIN
62 typedef struct {
63 OnigCodePoint from;
64 OnigCodePoint to;
65 } OnigPairCaseFoldCodes;
68 #ifndef NULL
69 # define NULL ((void* )0)
70 #endif
72 #ifndef TRUE
73 # define TRUE 1
74 #endif
76 #ifndef FALSE
77 # define FALSE 0
78 #endif
80 #ifndef ARG_UNUSED
81 # if defined(__GNUC__)
82 # define ARG_UNUSED __attribute__ ((unused))
83 # else
84 # define ARG_UNUSED
85 # endif
86 #endif
88 #define ONIG_IS_NULL(p) (((void*)(p)) == (void*)0)
89 #define ONIG_IS_NOT_NULL(p) (((void*)(p)) != (void*)0)
90 #define ONIG_CHECK_NULL_RETURN(p) if (ONIG_IS_NULL(p)) return NULL
91 #define ONIG_CHECK_NULL_RETURN_VAL(p,val) if (ONIG_IS_NULL(p)) return (val)
93 #define enclen(enc,p,e) ((enc->max_enc_len == enc->min_enc_len) ? enc->min_enc_len : ONIGENC_MBC_ENC_LEN(enc,p,e))
95 /* character types bit flag */
96 #define BIT_CTYPE_NEWLINE (1<< ONIGENC_CTYPE_NEWLINE)
97 #define BIT_CTYPE_ALPHA (1<< ONIGENC_CTYPE_ALPHA)
98 #define BIT_CTYPE_BLANK (1<< ONIGENC_CTYPE_BLANK)
99 #define BIT_CTYPE_CNTRL (1<< ONIGENC_CTYPE_CNTRL)
100 #define BIT_CTYPE_DIGIT (1<< ONIGENC_CTYPE_DIGIT)
101 #define BIT_CTYPE_GRAPH (1<< ONIGENC_CTYPE_GRAPH)
102 #define BIT_CTYPE_LOWER (1<< ONIGENC_CTYPE_LOWER)
103 #define BIT_CTYPE_PRINT (1<< ONIGENC_CTYPE_PRINT)
104 #define BIT_CTYPE_PUNCT (1<< ONIGENC_CTYPE_PUNCT)
105 #define BIT_CTYPE_SPACE (1<< ONIGENC_CTYPE_SPACE)
106 #define BIT_CTYPE_UPPER (1<< ONIGENC_CTYPE_UPPER)
107 #define BIT_CTYPE_XDIGIT (1<< ONIGENC_CTYPE_XDIGIT)
108 #define BIT_CTYPE_WORD (1<< ONIGENC_CTYPE_WORD)
109 #define BIT_CTYPE_ALNUM (1<< ONIGENC_CTYPE_ALNUM)
110 #define BIT_CTYPE_ASCII (1<< ONIGENC_CTYPE_ASCII)
112 #define CTYPE_TO_BIT(ctype) (1<<(ctype))
113 #define CTYPE_IS_WORD_GRAPH_PRINT(ctype) \
114 ((ctype) == ONIGENC_CTYPE_WORD || (ctype) == ONIGENC_CTYPE_GRAPH ||\
115 (ctype) == ONIGENC_CTYPE_PRINT)
118 typedef struct {
119 short int len;
120 const UChar name[6];
121 int ctype;
122 } PosixBracketEntryType;
124 #define POSIX_BRACKET_ENTRY_INIT(name, ctype) \
125 {(short int )(sizeof(name) - 1), name, (ctype)}
127 #ifndef numberof
128 # define numberof(array) (int )(sizeof(array) / sizeof((array)[0]))
129 #endif
132 #define USE_CRNL_AS_LINE_TERMINATOR
133 #define USE_UNICODE_PROPERTIES
134 #define USE_UNICODE_AGE_PROPERTIES
135 /* #define USE_UNICODE_CASE_FOLD_TURKISH_AZERI */
136 /* #define USE_UNICODE_ALL_LINE_TERMINATORS */ /* see Unicode.org UTS #18 */
139 #define ONIG_ENCODING_INIT_DEFAULT ONIG_ENCODING_ASCII
141 /* for encoding system implementation (internal) */
142 ONIG_EXTERN int onigenc_ascii_apply_all_case_fold(OnigCaseFoldType flag, OnigApplyAllCaseFoldFunc f, void* arg, OnigEncoding enc);
143 ONIG_EXTERN int onigenc_ascii_get_case_fold_codes_by_str(OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[], OnigEncoding enc);
144 ONIG_EXTERN int onigenc_apply_all_case_fold_with_map(int map_size, const OnigPairCaseFoldCodes map[], int ess_tsett_flag, OnigCaseFoldType flag, OnigApplyAllCaseFoldFunc f, void* arg);
145 ONIG_EXTERN int onigenc_get_case_fold_codes_by_str_with_map(int map_size, const OnigPairCaseFoldCodes map[], int ess_tsett_flag, OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[]);
146 ONIG_EXTERN int onigenc_not_support_get_ctype_code_range(OnigCtype ctype, OnigCodePoint* sb_out, const OnigCodePoint* ranges[], OnigEncoding enc);
147 ONIG_EXTERN int onigenc_is_mbc_newline_0x0a(const UChar* p, const UChar* end, OnigEncoding enc);
148 ONIG_EXTERN int onigenc_single_byte_ascii_only_case_map(OnigCaseFoldType* flagP, const OnigUChar** pp, const OnigUChar* end, OnigUChar* to, OnigUChar* to_end, const struct OnigEncodingTypeST* enc);
151 /* methods for single byte encoding */
152 ONIG_EXTERN int onigenc_ascii_mbc_case_fold(OnigCaseFoldType flag, const UChar** p, const UChar* end, UChar* lower, OnigEncoding enc);
153 ONIG_EXTERN int onigenc_single_byte_mbc_enc_len(const UChar* p, const UChar* e, OnigEncoding enc);
154 ONIG_EXTERN OnigCodePoint onigenc_single_byte_mbc_to_code(const UChar* p, const UChar* end, OnigEncoding enc);
155 ONIG_EXTERN int onigenc_single_byte_code_to_mbclen(OnigCodePoint code, OnigEncoding enc);
156 ONIG_EXTERN int onigenc_single_byte_code_to_mbc(OnigCodePoint code, UChar *buf, OnigEncoding enc);
157 ONIG_EXTERN UChar* onigenc_single_byte_left_adjust_char_head(const UChar* start, const UChar* s, const OnigUChar* end, OnigEncoding enc);
158 ONIG_EXTERN int onigenc_always_true_is_allowed_reverse_match(const UChar* s, const UChar* end, OnigEncoding enc);
159 ONIG_EXTERN int onigenc_always_false_is_allowed_reverse_match(const UChar* s, const UChar* end, OnigEncoding enc);
160 ONIG_EXTERN int onigenc_ascii_is_code_ctype(OnigCodePoint code, unsigned int ctype, OnigEncoding enc);
162 /* methods for multi byte encoding */
163 ONIG_EXTERN OnigCodePoint onigenc_mbn_mbc_to_code(OnigEncoding enc, const UChar* p, const UChar* end);
164 ONIG_EXTERN int onigenc_mbn_mbc_case_fold(OnigEncoding enc, OnigCaseFoldType flag, const UChar** p, const UChar* end, UChar* lower);
165 ONIG_EXTERN int onigenc_mb2_code_to_mbclen(OnigCodePoint code, OnigEncoding enc);
166 ONIG_EXTERN int onigenc_mb2_code_to_mbc(OnigEncoding enc, OnigCodePoint code, UChar *buf);
167 ONIG_EXTERN int onigenc_minimum_property_name_to_ctype(OnigEncoding enc, const UChar* p, const UChar* end);
168 ONIG_EXTERN int onigenc_unicode_property_name_to_ctype(OnigEncoding enc, const UChar* p, const UChar* end);
169 ONIG_EXTERN int onigenc_mb2_is_code_ctype(OnigEncoding enc, OnigCodePoint code, unsigned int ctype);
170 ONIG_EXTERN int onigenc_mb4_code_to_mbclen(OnigCodePoint code, OnigEncoding enc);
171 ONIG_EXTERN int onigenc_mb4_code_to_mbc(OnigEncoding enc, OnigCodePoint code, UChar *buf);
172 ONIG_EXTERN int onigenc_mb4_is_code_ctype(OnigEncoding enc, OnigCodePoint code, unsigned int ctype);
174 ONIG_EXTERN int onigenc_unicode_case_map(OnigCaseFoldType* flagP, const OnigUChar** pp, const OnigUChar* end, OnigUChar* to, OnigUChar* to_end, const struct OnigEncodingTypeST* enc);
177 /* in enc/unicode.c */
178 ONIG_EXTERN int onigenc_unicode_is_code_ctype(OnigCodePoint code, unsigned int ctype, OnigEncoding enc);
179 ONIG_EXTERN int onigenc_utf16_32_get_ctype_code_range(OnigCtype ctype, OnigCodePoint *sb_out, const OnigCodePoint* ranges[], OnigEncoding enc);
180 ONIG_EXTERN int onigenc_unicode_ctype_code_range(int ctype, const OnigCodePoint* ranges[]);
181 ONIG_EXTERN int onigenc_unicode_get_case_fold_codes_by_str(OnigEncoding enc, OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[]);
182 ONIG_EXTERN int onigenc_unicode_mbc_case_fold(OnigEncoding enc, OnigCaseFoldType flag, const UChar** pp, const UChar* end, UChar* fold);
183 ONIG_EXTERN int onigenc_unicode_apply_all_case_fold(OnigCaseFoldType flag, OnigApplyAllCaseFoldFunc f, void* arg, OnigEncoding enc);
186 #define UTF16_IS_SURROGATE_FIRST(c) (((c) & 0xfc) == 0xd8)
187 #define UTF16_IS_SURROGATE_SECOND(c) (((c) & 0xfc) == 0xdc)
188 #define UTF16_IS_SURROGATE(c) (((c) & 0xf8) == 0xd8)
189 #define UNICODE_VALID_CODEPOINT_P(c) ( \
190 ((c) <= 0x10ffff) && \
191 !((c) < 0x10000 && UTF16_IS_SURROGATE((c) >> 8)))
193 #define ONIGENC_ISO_8859_1_TO_LOWER_CASE(c) \
194 OnigEncISO_8859_1_ToLowerCaseTable[c]
195 #define ONIGENC_ISO_8859_1_TO_UPPER_CASE(c) \
196 OnigEncISO_8859_1_ToUpperCaseTable[c]
198 ONIG_EXTERN const UChar OnigEncISO_8859_1_ToLowerCaseTable[];
199 ONIG_EXTERN const UChar OnigEncISO_8859_1_ToUpperCaseTable[];
201 ONIG_EXTERN int
202 onigenc_with_ascii_strncmp(OnigEncoding enc, const UChar* p, const UChar* end, const UChar* sascii /* ascii */, int n);
203 ONIG_EXTERN int
204 onigenc_with_ascii_strnicmp(OnigEncoding enc, const UChar* p, const UChar* end, const UChar* sascii /* ascii */, int n);
205 ONIG_EXTERN UChar*
206 onigenc_step(OnigEncoding enc, const UChar* p, const UChar* end, int n);
208 /* defined in regexec.c, but used in enc/xxx.c */
209 extern int onig_is_in_code_range(const UChar* p, OnigCodePoint code);
211 ONIG_EXTERN OnigEncoding OnigEncDefaultCharEncoding;
212 ONIG_EXTERN const UChar OnigEncAsciiToLowerCaseTable[];
213 ONIG_EXTERN const UChar OnigEncAsciiToUpperCaseTable[];
214 ONIG_EXTERN const unsigned short OnigEncAsciiCtypeTable[];
216 #define ONIGENC_IS_ASCII_CODE(code) ((code) < 0x80)
217 #define ONIGENC_ASCII_CODE_TO_LOWER_CASE(c) OnigEncAsciiToLowerCaseTable[c]
218 #define ONIGENC_ASCII_CODE_TO_UPPER_CASE(c) OnigEncAsciiToUpperCaseTable[c]
219 #define ONIGENC_IS_ASCII_CODE_CTYPE(code,ctype) \
220 ((OnigEncAsciiCtypeTable[code] & CTYPE_TO_BIT(ctype)) != 0)
221 #define ONIGENC_IS_ASCII_CODE_CASE_AMBIG(code) \
222 (ONIGENC_IS_ASCII_CODE_CTYPE(code, ONIGENC_CTYPE_UPPER) ||\
223 ONIGENC_IS_ASCII_CODE_CTYPE(code, ONIGENC_CTYPE_LOWER))
225 /* Check if the code is in the range. (from <= code && code <= to) */
226 #define ONIGENC_IS_IN_RANGE(code, from, to) \
227 ((OnigCodePoint )((code) - (from)) <= (OnigCodePoint )((to) - (from)))
230 #ifdef ONIG_ENC_REGISTER
231 extern int ONIG_ENC_REGISTER(const char *, OnigEncoding);
232 # define OnigEncodingName(n) encoding_##n
233 # define OnigEncodingDeclare(n) static const OnigEncodingType OnigEncodingName(n)
234 # define OnigEncodingDefine(f,n) \
235 OnigEncodingDeclare(n); \
236 void Init_##f(void) { \
237 ONIG_ENC_REGISTER(OnigEncodingName(n).name, \
238 &OnigEncodingName(n)); \
240 OnigEncodingDeclare(n)
241 #else
242 # define OnigEncodingName(n) OnigEncoding##n
243 # define OnigEncodingDeclare(n) const OnigEncodingType OnigEncodingName(n)
244 # define OnigEncodingDefine(f,n) OnigEncodingDeclare(n)
245 #endif
247 /* macros for define replica encoding and encoding alias */
248 #define ENC_REPLICATE(name, orig)
249 #define ENC_ALIAS(name, orig)
250 #define ENC_DUMMY(name)
252 RUBY_SYMBOL_EXPORT_END
254 #endif /* ONIGMO_REGENC_H */