MdeModulePkg RegularExpressionDxe: Update Oniguruma from v6.9.0 to v6.9.3

[mirror_edk2.git] / MdeModulePkg / Universal / RegularExpressionDxe / Oniguruma / regenc.h

#ifndef REGENC_H\r
#define REGENC_H\r
/**********************************************************************\r
  regenc.h -  Oniguruma (regular expression library)\r
**********************************************************************/\r
/*-\r
 * Copyright (c) 2002-2019  K.Kosako  <sndgk393 AT ybb DOT ne DOT jp>\r
 * All rights reserved.\r
 *\r
 * Redistribution and use in source and binary forms, with or without\r
 * modification, are permitted provided that the following conditions\r
 * are met:\r
 * 1. Redistributions of source code must retain the above copyright\r
 *    notice, this list of conditions and the following disclaimer.\r
 * 2. Redistributions in binary form must reproduce the above copyright\r
 *    notice, this list of conditions and the following disclaimer in the\r
 *    documentation and/or other materials provided with the distribution.\r
 *\r
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND\r
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE\r
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE\r
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE\r
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL\r
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS\r
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)\r
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT\r
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY\r
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF\r
 * SUCH DAMAGE.\r
 */\r
\r
#ifndef ONIGURUMA_EXPORT\r
#define ONIGURUMA_EXPORT\r
#endif\r
\r
//#include "config.h"\r
//#include <stddef.h>\r
\r
#ifdef ONIG_ESCAPE_UCHAR_COLLISION\r
#undef ONIG_ESCAPE_UCHAR_COLLISION\r
#endif\r
\r
#include "oniguruma.h"\r
\r
typedef struct {\r
  OnigCodePoint from;\r
  OnigCodePoint to;\r
} OnigPairCaseFoldCodes;\r
\r
\r
#ifndef NULL\r
#define NULL   ((void* )0)\r
#endif\r
\r
#ifndef TRUE\r
#define TRUE    1\r
#endif\r
\r
#ifndef FALSE\r
#define FALSE   0\r
#endif\r
\r
#ifndef ARG_UNUSED\r
#if defined(__GNUC__)\r
#  define ARG_UNUSED  __attribute__ ((unused))\r
#else\r
#  define ARG_UNUSED\r
#endif\r
#endif\r
\r
#define ONIG_IS_NULL(p)                    (((void*)(p)) == (void*)0)\r
#define ONIG_IS_NOT_NULL(p)                (((void*)(p)) != (void*)0)\r
#define ONIG_CHECK_NULL_RETURN(p)          if (ONIG_IS_NULL(p)) return NULL\r
#define ONIG_CHECK_NULL_RETURN_VAL(p,val)  if (ONIG_IS_NULL(p)) return (val)\r
\r
#define MAX_CODE_POINT         (~((OnigCodePoint )0))\r
\r
#define enclen(enc,p)          ONIGENC_MBC_ENC_LEN(enc,p)\r
\r
/* character types bit flag */\r
#define BIT_CTYPE_NEWLINE  (1<< ONIGENC_CTYPE_NEWLINE)\r
#define BIT_CTYPE_ALPHA    (1<< ONIGENC_CTYPE_ALPHA)\r
#define BIT_CTYPE_BLANK    (1<< ONIGENC_CTYPE_BLANK)\r
#define BIT_CTYPE_CNTRL    (1<< ONIGENC_CTYPE_CNTRL)\r
#define BIT_CTYPE_DIGIT    (1<< ONIGENC_CTYPE_DIGIT)\r
#define BIT_CTYPE_GRAPH    (1<< ONIGENC_CTYPE_GRAPH)\r
#define BIT_CTYPE_LOWER    (1<< ONIGENC_CTYPE_LOWER)\r
#define BIT_CTYPE_PRINT    (1<< ONIGENC_CTYPE_PRINT)\r
#define BIT_CTYPE_PUNCT    (1<< ONIGENC_CTYPE_PUNCT)\r
#define BIT_CTYPE_SPACE    (1<< ONIGENC_CTYPE_SPACE)\r
#define BIT_CTYPE_UPPER    (1<< ONIGENC_CTYPE_UPPER)\r
#define BIT_CTYPE_XDIGIT   (1<< ONIGENC_CTYPE_XDIGIT)\r
#define BIT_CTYPE_WORD     (1<< ONIGENC_CTYPE_WORD)\r
#define BIT_CTYPE_ALNUM    (1<< ONIGENC_CTYPE_ALNUM)\r
#define BIT_CTYPE_ASCII    (1<< ONIGENC_CTYPE_ASCII)\r
\r
#define CTYPE_TO_BIT(ctype)  (1<<(ctype))\r
#define CTYPE_IS_WORD_GRAPH_PRINT(ctype) \\r
  ((ctype) == ONIGENC_CTYPE_WORD || (ctype) == ONIGENC_CTYPE_GRAPH ||\\r
   (ctype) == ONIGENC_CTYPE_PRINT)\r
\r
\r
typedef struct {\r
  UChar    *name;\r
  int       ctype;\r
  short int len;\r
} PosixBracketEntryType;\r
\r
struct PropertyNameCtype {\r
  char *name;\r
  int ctype;\r
};\r
\r
/* #define USE_CRNL_AS_LINE_TERMINATOR */\r
#define USE_UNICODE_PROPERTIES\r
#define USE_UNICODE_EXTENDED_GRAPHEME_CLUSTER\r
#define USE_UNICODE_WORD_BREAK\r
/* #define USE_UNICODE_CASE_FOLD_TURKISH_AZERI */\r
/* #define USE_UNICODE_ALL_LINE_TERMINATORS */  /* see Unicode.org UTS #18 */\r
\r
\r
#define ONIG_ENCODING_INIT_DEFAULT           ONIG_ENCODING_ASCII\r
\r
\r
#define ENC_SKIP_OFFSET_1_OR_0             7\r
\r
#define ENC_FLAG_ASCII_COMPATIBLE      (1<<0)\r
#define ENC_FLAG_UNICODE               (1<<1)\r
#define ENC_FLAG_SKIP_OFFSET_MASK      (7<<2)\r
#define ENC_FLAG_SKIP_OFFSET_0             0\r
#define ENC_FLAG_SKIP_OFFSET_1         (1<<2)\r
#define ENC_FLAG_SKIP_OFFSET_2         (2<<2)\r
#define ENC_FLAG_SKIP_OFFSET_3         (3<<2)\r
#define ENC_FLAG_SKIP_OFFSET_4         (4<<2)\r
#define ENC_FLAG_SKIP_OFFSET_1_OR_0    (ENC_SKIP_OFFSET_1_OR_0<<2)\r
\r
#define ENC_GET_SKIP_OFFSET(enc) \\r
  (((enc)->flag & ENC_FLAG_SKIP_OFFSET_MASK)>>2)\r
\r
\r
/* for encoding system implementation (internal) */\r
extern int onigenc_end(void);\r
extern int onigenc_ascii_apply_all_case_fold P_((OnigCaseFoldType flag, OnigApplyAllCaseFoldFunc f, void* arg));\r
extern int onigenc_ascii_get_case_fold_codes_by_str P_((OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[]));\r
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));\r
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[]));\r
extern int onigenc_not_support_get_ctype_code_range P_((OnigCtype ctype, OnigCodePoint* sb_out, const OnigCodePoint* ranges[]));\r
extern int onigenc_is_mbc_newline_0x0a P_((const UChar* p, const UChar* end));\r
\r
\r
/* methods for single byte encoding */\r
extern int onigenc_ascii_mbc_case_fold P_((OnigCaseFoldType flag, const UChar** p, const UChar* end, UChar* lower));\r
extern int onigenc_single_byte_mbc_enc_len P_((const UChar* p));\r
extern OnigCodePoint onigenc_single_byte_mbc_to_code P_((const UChar* p, const UChar* end));\r
extern int onigenc_single_byte_code_to_mbclen P_((OnigCodePoint code));\r
extern int onigenc_single_byte_code_to_mbc P_((OnigCodePoint code, UChar *buf));\r
extern UChar* onigenc_single_byte_left_adjust_char_head P_((const UChar* start, const UChar* s));\r
extern int onigenc_always_true_is_allowed_reverse_match P_((const UChar* s, const UChar* end));\r
extern int onigenc_always_false_is_allowed_reverse_match P_((const UChar* s, const UChar* end));\r
extern int onigenc_always_true_is_valid_mbc_string P_((const UChar* s, const UChar* end));\r
extern int onigenc_length_check_is_valid_mbc_string P_((OnigEncoding enc, const UChar* s, const UChar* end));\r
\r
/* methods for multi byte encoding */\r
extern OnigCodePoint onigenc_mbn_mbc_to_code P_((OnigEncoding enc, const UChar* p, const UChar* end));\r
extern int onigenc_mbn_mbc_case_fold P_((OnigEncoding enc, OnigCaseFoldType flag, const UChar** p, const UChar* end, UChar* lower));\r
extern int onigenc_mb2_code_to_mbclen P_((OnigCodePoint code));\r
extern int onigenc_mb2_code_to_mbc P_((OnigEncoding enc, OnigCodePoint code, UChar *buf));\r
extern int onigenc_minimum_property_name_to_ctype P_((OnigEncoding enc, UChar* p, UChar* end));\r
extern int onigenc_unicode_property_name_to_ctype P_((OnigEncoding enc, UChar* p, UChar* end));\r
extern int onigenc_is_mbc_word_ascii P_((OnigEncoding enc, UChar* s, const UChar* end));\r
extern int onigenc_mb2_is_code_ctype P_((OnigEncoding enc, OnigCodePoint code, unsigned int ctype));\r
extern int onigenc_mb4_code_to_mbclen P_((OnigCodePoint code));\r
extern int onigenc_mb4_code_to_mbc P_((OnigEncoding enc, OnigCodePoint code, UChar *buf));\r
extern int onigenc_mb4_is_code_ctype P_((OnigEncoding enc, OnigCodePoint code, unsigned int ctype));\r
extern struct PropertyNameCtype* onigenc_euc_jp_lookup_property_name P_((register const char *str, register size_t len));\r
extern struct PropertyNameCtype* onigenc_sjis_lookup_property_name P_((register const char *str, register size_t len));\r
\r
/* in unicode.c */\r
extern int onigenc_unicode_is_code_ctype P_((OnigCodePoint code, unsigned int ctype));\r
extern int onigenc_utf16_32_get_ctype_code_range P_((OnigCtype ctype, OnigCodePoint *sb_out, const OnigCodePoint* ranges[]));\r
extern int onigenc_unicode_ctype_code_range P_((OnigCtype ctype, const OnigCodePoint* ranges[]));\r
extern int onigenc_unicode_get_case_fold_codes_by_str P_((OnigEncoding enc, OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[]));\r
extern int onigenc_unicode_mbc_case_fold P_((OnigEncoding enc, OnigCaseFoldType flag, const UChar** pp, const UChar* end, UChar* fold));\r
extern int onigenc_unicode_apply_all_case_fold P_((OnigCaseFoldType flag, OnigApplyAllCaseFoldFunc f, void* arg));\r
\r
extern int onigenc_egcb_is_break_position P_((OnigEncoding enc, UChar* p, UChar* prev, const UChar* start, const UChar* end));\r
\r
#ifdef USE_UNICODE_WORD_BREAK\r
extern int onigenc_wb_is_break_position P_((OnigEncoding enc, UChar* p, UChar* prev, const UChar* start, const UChar* end));\r
#endif\r
\r
#define UTF16_IS_SURROGATE_FIRST(c)    (((c) & 0xfc) == 0xd8)\r
#define UTF16_IS_SURROGATE_SECOND(c)   (((c) & 0xfc) == 0xdc)\r
\r
/* from unicode generated codes */\r
#define FOLDS1_FOLD(i)         (OnigUnicodeFolds1 + (i))\r
#define FOLDS2_FOLD(i)         (OnigUnicodeFolds2 + (i))\r
#define FOLDS3_FOLD(i)         (OnigUnicodeFolds3 + (i))\r
#define FOLDS1_UNFOLDS_NUM(i)  (OnigUnicodeFolds1[(i)+1])\r
#define FOLDS2_UNFOLDS_NUM(i)  (OnigUnicodeFolds2[(i)+2])\r
#define FOLDS3_UNFOLDS_NUM(i)  (OnigUnicodeFolds3[(i)+3])\r
#define FOLDS1_UNFOLDS(i)      (OnigUnicodeFolds1 + (i) + 2)\r
#define FOLDS2_UNFOLDS(i)      (OnigUnicodeFolds2 + (i) + 3)\r
#define FOLDS3_UNFOLDS(i)      (OnigUnicodeFolds3 + (i) + 4)\r
#define FOLDS1_NEXT_INDEX(i)   ((i) + 2 + OnigUnicodeFolds1[(i)+1])\r
#define FOLDS2_NEXT_INDEX(i)   ((i) + 3 + OnigUnicodeFolds2[(i)+2])\r
#define FOLDS3_NEXT_INDEX(i)   ((i) + 4 + OnigUnicodeFolds3[(i)+3])\r
\r
#define FOLDS_FOLD_ADDR_BUK(buk, addr) do {\\r
  if ((buk)->fold_len == 1)\\r
    addr = OnigUnicodeFolds1 + (buk)->index;\\r
  else if ((buk)->fold_len == 2)\\r
    addr = OnigUnicodeFolds2 + (buk)->index;\\r
  else if ((buk)->fold_len == 3)\\r
    addr = OnigUnicodeFolds3 + (buk)->index;\\r
  else\\r
    return ONIGERR_INVALID_CODE_POINT_VALUE;\\r
} while (0)\r
\r
extern OnigCodePoint OnigUnicodeFolds1[];\r
extern OnigCodePoint OnigUnicodeFolds2[];\r
extern OnigCodePoint OnigUnicodeFolds3[];\r
\r
struct ByUnfoldKey {\r
  OnigCodePoint code;\r
  short int     index;\r
  short int     fold_len;\r
};\r
\r
extern const struct ByUnfoldKey* onigenc_unicode_unfold_key(OnigCodePoint code);\r
extern int onigenc_unicode_fold1_key(OnigCodePoint code[]);\r
extern int onigenc_unicode_fold2_key(OnigCodePoint code[]);\r
extern int onigenc_unicode_fold3_key(OnigCodePoint code[]);\r
\r
extern int onig_codes_cmp(OnigCodePoint a[], OnigCodePoint b[], int n);\r
extern int onig_codes_byte_at(OnigCodePoint code[], int at);\r
\r
\r
\r
#define ONIGENC_ISO_8859_1_TO_LOWER_CASE(c) \\r
  OnigEncISO_8859_1_ToLowerCaseTable[c]\r
#define ONIGENC_ISO_8859_1_TO_UPPER_CASE(c) \\r
  OnigEncISO_8859_1_ToUpperCaseTable[c]\r
\r
extern const UChar OnigEncISO_8859_1_ToLowerCaseTable[];\r
extern const UChar OnigEncISO_8859_1_ToUpperCaseTable[];\r
\r
extern int\r
onigenc_with_ascii_strncmp P_((OnigEncoding enc, const UChar* p, const UChar* end, const UChar* sascii /* ascii */, int n));\r
extern UChar*\r
onigenc_step P_((OnigEncoding enc, const UChar* p, const UChar* end, int n));\r
\r
/* defined in regexec.c, but used in enc/xxx.c */\r
extern int  onig_is_in_code_range P_((const UChar* p, OnigCodePoint code));\r
\r
extern OnigEncoding  OnigEncDefaultCharEncoding;\r
extern const UChar  OnigEncAsciiToLowerCaseTable[];\r
extern const UChar  OnigEncAsciiToUpperCaseTable[];\r
extern const unsigned short OnigEncAsciiCtypeTable[];\r
\r
\r
#define ONIGENC_IS_ASCII_CODE(code)  ((code) < 0x80)\r
#define ONIGENC_ASCII_CODE_TO_LOWER_CASE(c) OnigEncAsciiToLowerCaseTable[c]\r
#define ONIGENC_ASCII_CODE_TO_UPPER_CASE(c) OnigEncAsciiToUpperCaseTable[c]\r
#define ONIGENC_IS_ASCII_CODE_CTYPE(code,ctype) \\r
  ((OnigEncAsciiCtypeTable[code] & CTYPE_TO_BIT(ctype)) != 0)\r
#define ONIGENC_IS_ASCII_CODE_WORD(code) \\r
  ((OnigEncAsciiCtypeTable[code] & CTYPE_TO_BIT(ONIGENC_CTYPE_WORD)) != 0)\r
#define ONIGENC_IS_ASCII_CODE_CASE_AMBIG(code) \\r
 (ONIGENC_IS_ASCII_CODE_CTYPE(code, ONIGENC_CTYPE_UPPER) ||\\r
  ONIGENC_IS_ASCII_CODE_CTYPE(code, ONIGENC_CTYPE_LOWER))\r
\r
#define ONIGENC_IS_UNICODE_ENCODING(enc) \\r
  (((enc)->flag & ENC_FLAG_UNICODE) != 0)\r
\r
#define ONIGENC_IS_ASCII_COMPATIBLE_ENCODING(enc)  \\r
  (((enc)->flag & ENC_FLAG_ASCII_COMPATIBLE) != 0)\r
\r
#endif /* REGENC_H */\r