2015-09-08 09:10:03 +02:00
|
|
|
#ifndef REGENC_H
|
|
|
|
#define REGENC_H
|
|
|
|
/**********************************************************************
|
|
|
|
regenc.h - Oniguruma (regular expression library)
|
|
|
|
**********************************************************************/
|
|
|
|
/*-
|
2019-08-08 13:53:03 +02:00
|
|
|
* Copyright (c) 2002-2019 K.Kosako <sndgk393 AT ybb DOT ne DOT jp>
|
2015-09-08 09:10:03 +02:00
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
#ifndef ONIGURUMA_EXPORT
|
|
|
|
#define ONIGURUMA_EXPORT
|
2015-09-08 09:10:03 +02:00
|
|
|
#endif
|
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
//#include "config.h"
|
|
|
|
//#include <stddef.h>
|
|
|
|
|
2015-09-08 09:10:03 +02:00
|
|
|
#ifdef ONIG_ESCAPE_UCHAR_COLLISION
|
|
|
|
#undef ONIG_ESCAPE_UCHAR_COLLISION
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#include "oniguruma.h"
|
|
|
|
|
|
|
|
typedef struct {
|
|
|
|
OnigCodePoint from;
|
|
|
|
OnigCodePoint to;
|
|
|
|
} OnigPairCaseFoldCodes;
|
|
|
|
|
|
|
|
|
|
|
|
#ifndef NULL
|
|
|
|
#define NULL ((void* )0)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef TRUE
|
|
|
|
#define TRUE 1
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef FALSE
|
|
|
|
#define FALSE 0
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef ARG_UNUSED
|
|
|
|
#if defined(__GNUC__)
|
|
|
|
# define ARG_UNUSED __attribute__ ((unused))
|
|
|
|
#else
|
|
|
|
# define ARG_UNUSED
|
|
|
|
#endif
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#define ONIG_IS_NULL(p) (((void*)(p)) == (void*)0)
|
|
|
|
#define ONIG_IS_NOT_NULL(p) (((void*)(p)) != (void*)0)
|
|
|
|
#define ONIG_CHECK_NULL_RETURN(p) if (ONIG_IS_NULL(p)) return NULL
|
|
|
|
#define ONIG_CHECK_NULL_RETURN_VAL(p,val) if (ONIG_IS_NULL(p)) return (val)
|
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
#define MAX_CODE_POINT (~((OnigCodePoint )0))
|
|
|
|
|
|
|
|
#define enclen(enc,p) ONIGENC_MBC_ENC_LEN(enc,p)
|
2015-09-08 09:10:03 +02:00
|
|
|
|
|
|
|
/* character types bit flag */
|
|
|
|
#define BIT_CTYPE_NEWLINE (1<< ONIGENC_CTYPE_NEWLINE)
|
|
|
|
#define BIT_CTYPE_ALPHA (1<< ONIGENC_CTYPE_ALPHA)
|
|
|
|
#define BIT_CTYPE_BLANK (1<< ONIGENC_CTYPE_BLANK)
|
|
|
|
#define BIT_CTYPE_CNTRL (1<< ONIGENC_CTYPE_CNTRL)
|
|
|
|
#define BIT_CTYPE_DIGIT (1<< ONIGENC_CTYPE_DIGIT)
|
|
|
|
#define BIT_CTYPE_GRAPH (1<< ONIGENC_CTYPE_GRAPH)
|
|
|
|
#define BIT_CTYPE_LOWER (1<< ONIGENC_CTYPE_LOWER)
|
|
|
|
#define BIT_CTYPE_PRINT (1<< ONIGENC_CTYPE_PRINT)
|
|
|
|
#define BIT_CTYPE_PUNCT (1<< ONIGENC_CTYPE_PUNCT)
|
|
|
|
#define BIT_CTYPE_SPACE (1<< ONIGENC_CTYPE_SPACE)
|
|
|
|
#define BIT_CTYPE_UPPER (1<< ONIGENC_CTYPE_UPPER)
|
|
|
|
#define BIT_CTYPE_XDIGIT (1<< ONIGENC_CTYPE_XDIGIT)
|
|
|
|
#define BIT_CTYPE_WORD (1<< ONIGENC_CTYPE_WORD)
|
|
|
|
#define BIT_CTYPE_ALNUM (1<< ONIGENC_CTYPE_ALNUM)
|
|
|
|
#define BIT_CTYPE_ASCII (1<< ONIGENC_CTYPE_ASCII)
|
|
|
|
|
|
|
|
#define CTYPE_TO_BIT(ctype) (1<<(ctype))
|
|
|
|
#define CTYPE_IS_WORD_GRAPH_PRINT(ctype) \
|
|
|
|
((ctype) == ONIGENC_CTYPE_WORD || (ctype) == ONIGENC_CTYPE_GRAPH ||\
|
|
|
|
(ctype) == ONIGENC_CTYPE_PRINT)
|
|
|
|
|
|
|
|
|
|
|
|
typedef struct {
|
|
|
|
UChar *name;
|
|
|
|
int ctype;
|
|
|
|
short int len;
|
|
|
|
} PosixBracketEntryType;
|
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
struct PropertyNameCtype {
|
|
|
|
char *name;
|
|
|
|
int ctype;
|
|
|
|
};
|
2015-09-08 09:10:03 +02:00
|
|
|
|
|
|
|
/* #define USE_CRNL_AS_LINE_TERMINATOR */
|
|
|
|
#define USE_UNICODE_PROPERTIES
|
2018-09-06 10:04:58 +02:00
|
|
|
#define USE_UNICODE_EXTENDED_GRAPHEME_CLUSTER
|
2019-08-08 13:53:03 +02:00
|
|
|
#define USE_UNICODE_WORD_BREAK
|
2015-09-08 09:10:03 +02:00
|
|
|
/* #define USE_UNICODE_CASE_FOLD_TURKISH_AZERI */
|
2018-09-06 10:04:58 +02:00
|
|
|
/* #define USE_UNICODE_ALL_LINE_TERMINATORS */ /* see Unicode.org UTS #18 */
|
2015-09-08 09:10:03 +02:00
|
|
|
|
|
|
|
|
|
|
|
#define ONIG_ENCODING_INIT_DEFAULT ONIG_ENCODING_ASCII
|
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
|
2019-08-08 13:53:03 +02:00
|
|
|
#define ENC_SKIP_OFFSET_1_OR_0 7
|
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
#define ENC_FLAG_ASCII_COMPATIBLE (1<<0)
|
|
|
|
#define ENC_FLAG_UNICODE (1<<1)
|
2019-08-08 13:53:03 +02:00
|
|
|
#define ENC_FLAG_SKIP_OFFSET_MASK (7<<2)
|
|
|
|
#define ENC_FLAG_SKIP_OFFSET_0 0
|
|
|
|
#define ENC_FLAG_SKIP_OFFSET_1 (1<<2)
|
|
|
|
#define ENC_FLAG_SKIP_OFFSET_2 (2<<2)
|
|
|
|
#define ENC_FLAG_SKIP_OFFSET_3 (3<<2)
|
|
|
|
#define ENC_FLAG_SKIP_OFFSET_4 (4<<2)
|
|
|
|
#define ENC_FLAG_SKIP_OFFSET_1_OR_0 (ENC_SKIP_OFFSET_1_OR_0<<2)
|
|
|
|
|
|
|
|
#define ENC_GET_SKIP_OFFSET(enc) \
|
|
|
|
(((enc)->flag & ENC_FLAG_SKIP_OFFSET_MASK)>>2)
|
2018-09-06 10:04:58 +02:00
|
|
|
|
|
|
|
|
2015-09-08 09:10:03 +02:00
|
|
|
/* for encoding system implementation (internal) */
|
2018-09-06 10:04:58 +02:00
|
|
|
extern int onigenc_end(void);
|
|
|
|
extern int onigenc_ascii_apply_all_case_fold P_((OnigCaseFoldType flag, OnigApplyAllCaseFoldFunc f, void* arg));
|
|
|
|
extern int onigenc_ascii_get_case_fold_codes_by_str P_((OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[]));
|
|
|
|
extern int onigenc_apply_all_case_fold_with_map P_((int map_size, const OnigPairCaseFoldCodes map[], int ess_tsett_flag, OnigCaseFoldType flag, OnigApplyAllCaseFoldFunc f, void* arg));
|
|
|
|
extern int onigenc_get_case_fold_codes_by_str_with_map P_((int map_size, const OnigPairCaseFoldCodes map[], int ess_tsett_flag, OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[]));
|
|
|
|
extern int onigenc_not_support_get_ctype_code_range P_((OnigCtype ctype, OnigCodePoint* sb_out, const OnigCodePoint* ranges[]));
|
|
|
|
extern int onigenc_is_mbc_newline_0x0a P_((const UChar* p, const UChar* end));
|
2015-09-08 09:10:03 +02:00
|
|
|
|
|
|
|
|
|
|
|
/* methods for single byte encoding */
|
2018-09-06 10:04:58 +02:00
|
|
|
extern int onigenc_ascii_mbc_case_fold P_((OnigCaseFoldType flag, const UChar** p, const UChar* end, UChar* lower));
|
|
|
|
extern int onigenc_single_byte_mbc_enc_len P_((const UChar* p));
|
|
|
|
extern OnigCodePoint onigenc_single_byte_mbc_to_code P_((const UChar* p, const UChar* end));
|
|
|
|
extern int onigenc_single_byte_code_to_mbclen P_((OnigCodePoint code));
|
|
|
|
extern int onigenc_single_byte_code_to_mbc P_((OnigCodePoint code, UChar *buf));
|
|
|
|
extern UChar* onigenc_single_byte_left_adjust_char_head P_((const UChar* start, const UChar* s));
|
|
|
|
extern int onigenc_always_true_is_allowed_reverse_match P_((const UChar* s, const UChar* end));
|
|
|
|
extern int onigenc_always_false_is_allowed_reverse_match P_((const UChar* s, const UChar* end));
|
|
|
|
extern int onigenc_always_true_is_valid_mbc_string P_((const UChar* s, const UChar* end));
|
|
|
|
extern int onigenc_length_check_is_valid_mbc_string P_((OnigEncoding enc, const UChar* s, const UChar* end));
|
2015-09-08 09:10:03 +02:00
|
|
|
|
|
|
|
/* methods for multi byte encoding */
|
2018-09-06 10:04:58 +02:00
|
|
|
extern OnigCodePoint onigenc_mbn_mbc_to_code P_((OnigEncoding enc, const UChar* p, const UChar* end));
|
|
|
|
extern int onigenc_mbn_mbc_case_fold P_((OnigEncoding enc, OnigCaseFoldType flag, const UChar** p, const UChar* end, UChar* lower));
|
|
|
|
extern int onigenc_mb2_code_to_mbclen P_((OnigCodePoint code));
|
|
|
|
extern int onigenc_mb2_code_to_mbc P_((OnigEncoding enc, OnigCodePoint code, UChar *buf));
|
|
|
|
extern int onigenc_minimum_property_name_to_ctype P_((OnigEncoding enc, UChar* p, UChar* end));
|
|
|
|
extern int onigenc_unicode_property_name_to_ctype P_((OnigEncoding enc, UChar* p, UChar* end));
|
|
|
|
extern int onigenc_is_mbc_word_ascii P_((OnigEncoding enc, UChar* s, const UChar* end));
|
|
|
|
extern int onigenc_mb2_is_code_ctype P_((OnigEncoding enc, OnigCodePoint code, unsigned int ctype));
|
|
|
|
extern int onigenc_mb4_code_to_mbclen P_((OnigCodePoint code));
|
|
|
|
extern int onigenc_mb4_code_to_mbc P_((OnigEncoding enc, OnigCodePoint code, UChar *buf));
|
|
|
|
extern int onigenc_mb4_is_code_ctype P_((OnigEncoding enc, OnigCodePoint code, unsigned int ctype));
|
|
|
|
extern struct PropertyNameCtype* onigenc_euc_jp_lookup_property_name P_((register const char *str, register size_t len));
|
|
|
|
extern struct PropertyNameCtype* onigenc_sjis_lookup_property_name P_((register const char *str, register size_t len));
|
2015-09-08 09:10:03 +02:00
|
|
|
|
2019-08-08 13:53:03 +02:00
|
|
|
/* in unicode.c */
|
2018-09-06 10:04:58 +02:00
|
|
|
extern int onigenc_unicode_is_code_ctype P_((OnigCodePoint code, unsigned int ctype));
|
|
|
|
extern int onigenc_utf16_32_get_ctype_code_range P_((OnigCtype ctype, OnigCodePoint *sb_out, const OnigCodePoint* ranges[]));
|
|
|
|
extern int onigenc_unicode_ctype_code_range P_((OnigCtype ctype, const OnigCodePoint* ranges[]));
|
|
|
|
extern int onigenc_unicode_get_case_fold_codes_by_str P_((OnigEncoding enc, OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[]));
|
|
|
|
extern int onigenc_unicode_mbc_case_fold P_((OnigEncoding enc, OnigCaseFoldType flag, const UChar** pp, const UChar* end, UChar* fold));
|
|
|
|
extern int onigenc_unicode_apply_all_case_fold P_((OnigCaseFoldType flag, OnigApplyAllCaseFoldFunc f, void* arg));
|
2019-08-08 13:53:03 +02:00
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
extern int onigenc_egcb_is_break_position P_((OnigEncoding enc, UChar* p, UChar* prev, const UChar* start, const UChar* end));
|
2015-09-08 09:10:03 +02:00
|
|
|
|
2019-08-08 13:53:03 +02:00
|
|
|
#ifdef USE_UNICODE_WORD_BREAK
|
|
|
|
extern int onigenc_wb_is_break_position P_((OnigEncoding enc, UChar* p, UChar* prev, const UChar* start, const UChar* end));
|
|
|
|
#endif
|
2015-09-08 09:10:03 +02:00
|
|
|
|
|
|
|
#define UTF16_IS_SURROGATE_FIRST(c) (((c) & 0xfc) == 0xd8)
|
|
|
|
#define UTF16_IS_SURROGATE_SECOND(c) (((c) & 0xfc) == 0xdc)
|
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
/* from unicode generated codes */
|
|
|
|
#define FOLDS1_FOLD(i) (OnigUnicodeFolds1 + (i))
|
|
|
|
#define FOLDS2_FOLD(i) (OnigUnicodeFolds2 + (i))
|
|
|
|
#define FOLDS3_FOLD(i) (OnigUnicodeFolds3 + (i))
|
|
|
|
#define FOLDS1_UNFOLDS_NUM(i) (OnigUnicodeFolds1[(i)+1])
|
|
|
|
#define FOLDS2_UNFOLDS_NUM(i) (OnigUnicodeFolds2[(i)+2])
|
|
|
|
#define FOLDS3_UNFOLDS_NUM(i) (OnigUnicodeFolds3[(i)+3])
|
|
|
|
#define FOLDS1_UNFOLDS(i) (OnigUnicodeFolds1 + (i) + 2)
|
|
|
|
#define FOLDS2_UNFOLDS(i) (OnigUnicodeFolds2 + (i) + 3)
|
|
|
|
#define FOLDS3_UNFOLDS(i) (OnigUnicodeFolds3 + (i) + 4)
|
|
|
|
#define FOLDS1_NEXT_INDEX(i) ((i) + 2 + OnigUnicodeFolds1[(i)+1])
|
|
|
|
#define FOLDS2_NEXT_INDEX(i) ((i) + 3 + OnigUnicodeFolds2[(i)+2])
|
|
|
|
#define FOLDS3_NEXT_INDEX(i) ((i) + 4 + OnigUnicodeFolds3[(i)+3])
|
|
|
|
|
|
|
|
#define FOLDS_FOLD_ADDR_BUK(buk, addr) do {\
|
|
|
|
if ((buk)->fold_len == 1)\
|
|
|
|
addr = OnigUnicodeFolds1 + (buk)->index;\
|
|
|
|
else if ((buk)->fold_len == 2)\
|
|
|
|
addr = OnigUnicodeFolds2 + (buk)->index;\
|
|
|
|
else if ((buk)->fold_len == 3)\
|
|
|
|
addr = OnigUnicodeFolds3 + (buk)->index;\
|
|
|
|
else\
|
2018-10-11 08:57:01 +02:00
|
|
|
return ONIGERR_INVALID_CODE_POINT_VALUE;\
|
2018-09-06 10:04:58 +02:00
|
|
|
} while (0)
|
|
|
|
|
|
|
|
extern OnigCodePoint OnigUnicodeFolds1[];
|
|
|
|
extern OnigCodePoint OnigUnicodeFolds2[];
|
|
|
|
extern OnigCodePoint OnigUnicodeFolds3[];
|
|
|
|
|
|
|
|
struct ByUnfoldKey {
|
|
|
|
OnigCodePoint code;
|
|
|
|
short int index;
|
|
|
|
short int fold_len;
|
|
|
|
};
|
|
|
|
|
|
|
|
extern const struct ByUnfoldKey* onigenc_unicode_unfold_key(OnigCodePoint code);
|
|
|
|
extern int onigenc_unicode_fold1_key(OnigCodePoint code[]);
|
|
|
|
extern int onigenc_unicode_fold2_key(OnigCodePoint code[]);
|
|
|
|
extern int onigenc_unicode_fold3_key(OnigCodePoint code[]);
|
|
|
|
|
|
|
|
extern int onig_codes_cmp(OnigCodePoint a[], OnigCodePoint b[], int n);
|
|
|
|
extern int onig_codes_byte_at(OnigCodePoint code[], int at);
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-08 09:10:03 +02:00
|
|
|
#define ONIGENC_ISO_8859_1_TO_LOWER_CASE(c) \
|
|
|
|
OnigEncISO_8859_1_ToLowerCaseTable[c]
|
|
|
|
#define ONIGENC_ISO_8859_1_TO_UPPER_CASE(c) \
|
|
|
|
OnigEncISO_8859_1_ToUpperCaseTable[c]
|
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
extern const UChar OnigEncISO_8859_1_ToLowerCaseTable[];
|
|
|
|
extern const UChar OnigEncISO_8859_1_ToUpperCaseTable[];
|
2015-09-08 09:10:03 +02:00
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
extern int
|
2015-09-08 09:10:03 +02:00
|
|
|
onigenc_with_ascii_strncmp P_((OnigEncoding enc, const UChar* p, const UChar* end, const UChar* sascii /* ascii */, int n));
|
2018-09-06 10:04:58 +02:00
|
|
|
extern UChar*
|
2015-09-08 09:10:03 +02:00
|
|
|
onigenc_step P_((OnigEncoding enc, const UChar* p, const UChar* end, int n));
|
|
|
|
|
|
|
|
/* defined in regexec.c, but used in enc/xxx.c */
|
|
|
|
extern int onig_is_in_code_range P_((const UChar* p, OnigCodePoint code));
|
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
extern OnigEncoding OnigEncDefaultCharEncoding;
|
|
|
|
extern const UChar OnigEncAsciiToLowerCaseTable[];
|
|
|
|
extern const UChar OnigEncAsciiToUpperCaseTable[];
|
|
|
|
extern const unsigned short OnigEncAsciiCtypeTable[];
|
|
|
|
|
2015-09-08 09:10:03 +02:00
|
|
|
|
|
|
|
#define ONIGENC_IS_ASCII_CODE(code) ((code) < 0x80)
|
|
|
|
#define ONIGENC_ASCII_CODE_TO_LOWER_CASE(c) OnigEncAsciiToLowerCaseTable[c]
|
|
|
|
#define ONIGENC_ASCII_CODE_TO_UPPER_CASE(c) OnigEncAsciiToUpperCaseTable[c]
|
|
|
|
#define ONIGENC_IS_ASCII_CODE_CTYPE(code,ctype) \
|
|
|
|
((OnigEncAsciiCtypeTable[code] & CTYPE_TO_BIT(ctype)) != 0)
|
2018-09-06 10:04:58 +02:00
|
|
|
#define ONIGENC_IS_ASCII_CODE_WORD(code) \
|
|
|
|
((OnigEncAsciiCtypeTable[code] & CTYPE_TO_BIT(ONIGENC_CTYPE_WORD)) != 0)
|
2015-09-08 09:10:03 +02:00
|
|
|
#define ONIGENC_IS_ASCII_CODE_CASE_AMBIG(code) \
|
|
|
|
(ONIGENC_IS_ASCII_CODE_CTYPE(code, ONIGENC_CTYPE_UPPER) ||\
|
|
|
|
ONIGENC_IS_ASCII_CODE_CTYPE(code, ONIGENC_CTYPE_LOWER))
|
2019-08-08 13:53:03 +02:00
|
|
|
|
2018-09-06 10:04:58 +02:00
|
|
|
#define ONIGENC_IS_UNICODE_ENCODING(enc) \
|
|
|
|
(((enc)->flag & ENC_FLAG_UNICODE) != 0)
|
|
|
|
|
|
|
|
#define ONIGENC_IS_ASCII_COMPATIBLE_ENCODING(enc) \
|
|
|
|
(((enc)->flag & ENC_FLAG_ASCII_COMPATIBLE) != 0)
|
2015-09-08 09:10:03 +02:00
|
|
|
|
|
|
|
#endif /* REGENC_H */
|