diff options
Diffstat (limited to 'src/3rdparty/pcre2/src/pcre2_internal.h')
| -rw-r--r-- | src/3rdparty/pcre2/src/pcre2_internal.h | 158 |
1 files changed, 86 insertions, 72 deletions
diff --git a/src/3rdparty/pcre2/src/pcre2_internal.h b/src/3rdparty/pcre2/src/pcre2_internal.h index 56908708aa..9ccce25d47 100644 --- a/src/3rdparty/pcre2/src/pcre2_internal.h +++ b/src/3rdparty/pcre2/src/pcre2_internal.h @@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel Original API code Copyright (c) 1997-2012 University of Cambridge - New API code Copyright (c) 2016 University of Cambridge + New API code Copyright (c) 2016-2017 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -142,20 +142,6 @@ pcre2_match() because of the way it backtracks. */ #define PCRE2_SPTR CUSTOM_SUBJECT_PTR #endif -/* When compiling with the MSVC compiler, it is sometimes necessary to include -a "calling convention" before exported function names. (This is secondhand -information; I know nothing about MSVC myself). For example, something like - - void __cdecl function(....) - -might be needed. In order so make this easy, all the exported functions have -PCRE2_CALL_CONVENTION just before their names. It is rarely needed; if not -set, we ensure here that it has no effect. */ - -#ifndef PCRE2_CALL_CONVENTION -#define PCRE2_CALL_CONVENTION -#endif - /* When checking for integer overflow in pcre2_compile(), we need to handle large integers. If a 64-bit integer type is available, we can use that. Otherwise we have to cast to double, which of course requires floating point @@ -254,6 +240,16 @@ not rely on this. */ #define COMPILE_ERROR_BASE 100 +/* The initial frames vector for remembering backtracking points in +pcre2_match() is allocated on the system stack, of this size (bytes). The size +must be a multiple of sizeof(PCRE2_SPTR) in all environments, so making it a +multiple of 8 is best. Typical frame sizes are a few hundred bytes (it depends +on the number of capturing parentheses) so 20K handles quite a few frames. A +larger vector on the heap is obtained for patterns that need more frames. The +maximum size of this can be limited. */ + +#define START_FRAMES_SIZE 20480 + /* Define the default BSR convention. */ #ifdef BSR_ANYCRLF @@ -561,9 +557,14 @@ enum { PCRE2_MATCHEDBY_INTERPRETER, /* pcre2_match() */ #define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */ /* The maximum remaining length of subject we are prepared to search for a -req_unit match. */ +req_unit match. In 8-bit mode, memchr() is used and is much faster than the +search loop that has to be used in 16-bit and 32-bit modes. */ +#if PCRE2_CODE_UNIT_WIDTH == 8 +#define REQ_CU_MAX 2000 +#else #define REQ_CU_MAX 1000 +#endif /* Offsets for the bitmap tables in the cbits set of tables. Each table contains a set of bits for a class map. Some classes are built by combining @@ -682,7 +683,7 @@ a positive value. */ /* The remaining definitions work in both environments. */ -#define CHAR_NULL '\0' +#define CHAR_NUL '\0' #define CHAR_HT '\t' #define CHAR_VT '\v' #define CHAR_FF '\f' @@ -923,6 +924,7 @@ a positive value. */ #define STRING_CRLF_RIGHTPAR "CRLF)" #define STRING_ANY_RIGHTPAR "ANY)" #define STRING_ANYCRLF_RIGHTPAR "ANYCRLF)" +#define STRING_NUL_RIGHTPAR "NUL)" #define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)" #define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)" #define STRING_UTF8_RIGHTPAR "UTF8)" @@ -936,7 +938,9 @@ a positive value. */ #define STRING_NO_START_OPT_RIGHTPAR "NO_START_OPT)" #define STRING_NOTEMPTY_RIGHTPAR "NOTEMPTY)" #define STRING_NOTEMPTY_ATSTART_RIGHTPAR "NOTEMPTY_ATSTART)" +#define STRING_LIMIT_HEAP_EQ "LIMIT_HEAP=" #define STRING_LIMIT_MATCH_EQ "LIMIT_MATCH=" +#define STRING_LIMIT_DEPTH_EQ "LIMIT_DEPTH=" #define STRING_LIMIT_RECURSION_EQ "LIMIT_RECURSION=" #define STRING_MARK "MARK" @@ -958,7 +962,7 @@ only. */ #define CHAR_ESC '\033' #define CHAR_DEL '\177' -#define CHAR_NULL '\0' +#define CHAR_NUL '\0' #define CHAR_SPACE '\040' #define CHAR_EXCLAMATION_MARK '\041' #define CHAR_QUOTATION_MARK '\042' @@ -1196,6 +1200,7 @@ only. */ #define STRING_CRLF_RIGHTPAR STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS #define STRING_ANY_RIGHTPAR STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS #define STRING_ANYCRLF_RIGHTPAR STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS +#define STRING_NUL_RIGHTPAR STR_N STR_U STR_L STR_RIGHT_PARENTHESIS #define STRING_BSR_ANYCRLF_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS #define STRING_BSR_UNICODE_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS #define STRING_UTF8_RIGHTPAR STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS @@ -1209,7 +1214,9 @@ only. */ #define STRING_NO_START_OPT_RIGHTPAR STR_N STR_O STR_UNDERSCORE STR_S STR_T STR_A STR_R STR_T STR_UNDERSCORE STR_O STR_P STR_T STR_RIGHT_PARENTHESIS #define STRING_NOTEMPTY_RIGHTPAR STR_N STR_O STR_T STR_E STR_M STR_P STR_T STR_Y STR_RIGHT_PARENTHESIS #define STRING_NOTEMPTY_ATSTART_RIGHTPAR STR_N STR_O STR_T STR_E STR_M STR_P STR_T STR_Y STR_UNDERSCORE STR_A STR_T STR_S STR_T STR_A STR_R STR_T STR_RIGHT_PARENTHESIS +#define STRING_LIMIT_HEAP_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_H STR_E STR_A STR_P STR_EQUALS_SIGN #define STRING_LIMIT_MATCH_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_M STR_A STR_T STR_C STR_H STR_EQUALS_SIGN +#define STRING_LIMIT_DEPTH_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_D STR_E STR_P STR_T STR_H STR_EQUALS_SIGN #define STRING_LIMIT_RECURSION_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_R STR_E STR_C STR_U STR_R STR_S STR_I STR_O STR_N STR_EQUALS_SIGN #define STRING_MARK STR_M STR_A STR_R STR_K @@ -1298,23 +1305,16 @@ mode rather than an escape sequence. It is also used for [^] in JavaScript compatibility mode, and for \C in non-utf mode. In non-DOTALL mode, "." behaves like \N. -The special values ESC_DU, ESC_du, etc. are used instead of ESC_D, ESC_d, etc. -when PCRE2_UCP is set and replacement of \d etc by \p sequences is required. -They must be contiguous, and remain in order so that the replacements can be -looked up from a table. - Negative numbers are used to encode a backreference (\1, \2, \3, etc.) in -check_escape(). There are two tests in the code for an escape -greater than ESC_b and less than ESC_Z to detect the types that may be -repeated. These are the types that consume characters. If any new escapes are -put in between that don't consume a character, that code will have to change. -*/ +check_escape(). There are tests in the code for an escape greater than ESC_b +and less than ESC_Z to detect the types that may be repeated. These are the +types that consume characters. If any new escapes are put in between that don't +consume a character, that code will have to change. */ enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W, ESC_w, ESC_N, ESC_dum, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H, ESC_h, ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, - ESC_E, ESC_Q, ESC_g, ESC_k, - ESC_DU, ESC_du, ESC_SU, ESC_su, ESC_WU, ESC_wu }; + ESC_E, ESC_Q, ESC_g, ESC_k }; /********************** Opcode definitions ******************/ @@ -1380,7 +1380,8 @@ enum { OP_CIRC, /* 27 Start of line - not multiline */ OP_CIRCM, /* 28 Start of line - multiline */ - /* Single characters; caseful must precede the caseless ones */ + /* Single characters; caseful must precede the caseless ones, and these + must remain in this order, and adjacent. */ OP_CHAR, /* 29 Match one character, casefully */ OP_CHARI, /* 30 Match one character, caselessly */ @@ -1530,68 +1531,67 @@ enum { OP_ASSERTBACK, /* 128 Positive lookbehind */ OP_ASSERTBACK_NOT, /* 129 Negative lookbehind */ - /* ONCE, ONCE_NC, BRA, BRAPOS, CBRA, CBRAPOS, and COND must come immediately - after the assertions, with ONCE first, as there's a test for >= ONCE for a - subpattern that isn't an assertion. The POS versions must immediately follow - the non-POS versions in each case. */ + /* ONCE, BRA, BRAPOS, CBRA, CBRAPOS, and COND must come immediately after the + assertions, with ONCE first, as there's a test for >= ONCE for a subpattern + that isn't an assertion. The POS versions must immediately follow the non-POS + versions in each case. */ OP_ONCE, /* 130 Atomic group, contains captures */ - OP_ONCE_NC, /* 131 Atomic group containing no captures */ - OP_BRA, /* 132 Start of non-capturing bracket */ - OP_BRAPOS, /* 133 Ditto, with unlimited, possessive repeat */ - OP_CBRA, /* 134 Start of capturing bracket */ - OP_CBRAPOS, /* 135 Ditto, with unlimited, possessive repeat */ - OP_COND, /* 136 Conditional group */ + OP_BRA, /* 131 Start of non-capturing bracket */ + OP_BRAPOS, /* 132 Ditto, with unlimited, possessive repeat */ + OP_CBRA, /* 133 Start of capturing bracket */ + OP_CBRAPOS, /* 134 Ditto, with unlimited, possessive repeat */ + OP_COND, /* 135 Conditional group */ /* These five must follow the previous five, in the same order. There's a check for >= SBRA to distinguish the two sets. */ - OP_SBRA, /* 137 Start of non-capturing bracket, check empty */ - OP_SBRAPOS, /* 138 Ditto, with unlimited, possessive repeat */ - OP_SCBRA, /* 139 Start of capturing bracket, check empty */ - OP_SCBRAPOS, /* 140 Ditto, with unlimited, possessive repeat */ - OP_SCOND, /* 141 Conditional group, check empty */ + OP_SBRA, /* 136 Start of non-capturing bracket, check empty */ + OP_SBRAPOS, /* 137 Ditto, with unlimited, possessive repeat */ + OP_SCBRA, /* 138 Start of capturing bracket, check empty */ + OP_SCBRAPOS, /* 139 Ditto, with unlimited, possessive repeat */ + OP_SCOND, /* 140 Conditional group, check empty */ /* The next two pairs must (respectively) be kept together. */ - OP_CREF, /* 142 Used to hold a capture number as condition */ - OP_DNCREF, /* 143 Used to point to duplicate names as a condition */ - OP_RREF, /* 144 Used to hold a recursion number as condition */ - OP_DNRREF, /* 145 Used to point to duplicate names as a condition */ - OP_FALSE, /* 146 Always false (used by DEFINE and VERSION) */ - OP_TRUE, /* 147 Always true (used by VERSION) */ + OP_CREF, /* 141 Used to hold a capture number as condition */ + OP_DNCREF, /* 142 Used to point to duplicate names as a condition */ + OP_RREF, /* 143 Used to hold a recursion number as condition */ + OP_DNRREF, /* 144 Used to point to duplicate names as a condition */ + OP_FALSE, /* 145 Always false (used by DEFINE and VERSION) */ + OP_TRUE, /* 146 Always true (used by VERSION) */ - OP_BRAZERO, /* 148 These two must remain together and in this */ - OP_BRAMINZERO, /* 149 order. */ - OP_BRAPOSZERO, /* 150 */ + OP_BRAZERO, /* 147 These two must remain together and in this */ + OP_BRAMINZERO, /* 148 order. */ + OP_BRAPOSZERO, /* 149 */ /* These are backtracking control verbs */ - OP_MARK, /* 151 always has an argument */ - OP_PRUNE, /* 152 */ - OP_PRUNE_ARG, /* 153 same, but with argument */ - OP_SKIP, /* 154 */ - OP_SKIP_ARG, /* 155 same, but with argument */ - OP_THEN, /* 156 */ - OP_THEN_ARG, /* 157 same, but with argument */ - OP_COMMIT, /* 158 */ + OP_MARK, /* 150 always has an argument */ + OP_PRUNE, /* 151 */ + OP_PRUNE_ARG, /* 152 same, but with argument */ + OP_SKIP, /* 153 */ + OP_SKIP_ARG, /* 154 same, but with argument */ + OP_THEN, /* 155 */ + OP_THEN_ARG, /* 156 same, but with argument */ + OP_COMMIT, /* 157 */ /* These are forced failure and success verbs */ - OP_FAIL, /* 159 */ - OP_ACCEPT, /* 160 */ - OP_ASSERT_ACCEPT, /* 161 Used inside assertions */ - OP_CLOSE, /* 162 Used before OP_ACCEPT to close open captures */ + OP_FAIL, /* 158 */ + OP_ACCEPT, /* 159 */ + OP_ASSERT_ACCEPT, /* 160 Used inside assertions */ + OP_CLOSE, /* 161 Used before OP_ACCEPT to close open captures */ /* This is used to skip a subpattern with a {0} quantifier */ - OP_SKIPZERO, /* 163 */ + OP_SKIPZERO, /* 162 */ /* This is used to identify a DEFINE group during compilation so that it can be checked for having only one branch. It is changed to OP_FALSE before compilation finishes. */ - OP_DEFINE, /* 164 */ + OP_DEFINE, /* 163 */ /* This is not an opcode, but is used to check that tables indexed by opcode are the correct length, in order to catch updating errors - there have been @@ -1638,7 +1638,7 @@ some cases doesn't actually use these names at all). */ "Recurse", "Callout", "CalloutStr", \ "Alt", "Ket", "KetRmax", "KetRmin", "KetRpos", \ "Reverse", "Assert", "Assert not", "AssertB", "AssertB not", \ - "Once", "Once_NC", \ + "Once", \ "Bra", "BraPos", "CBra", "CBraPos", \ "Cond", \ "SBra", "SBraPos", "SCBra", "SCBraPos", \ @@ -1722,7 +1722,6 @@ in UTF-8 mode. The code that uses this table must know about such things. */ 1+LINK_SIZE, /* Assert behind */ \ 1+LINK_SIZE, /* Assert behind not */ \ 1+LINK_SIZE, /* ONCE */ \ - 1+LINK_SIZE, /* ONCE_NC */ \ 1+LINK_SIZE, /* BRA */ \ 1+LINK_SIZE, /* BRAPOS */ \ 1+LINK_SIZE+IMM2_SIZE, /* CBRA */ \ @@ -1794,10 +1793,17 @@ typedef struct { /* UCD access macros */ #define UCD_BLOCK_SIZE 128 -#define GET_UCD(ch) (PRIV(ucd_records) + \ +#define REAL_GET_UCD(ch) (PRIV(ucd_records) + \ PRIV(ucd_stage2)[PRIV(ucd_stage1)[(int)(ch) / UCD_BLOCK_SIZE] * \ UCD_BLOCK_SIZE + (int)(ch) % UCD_BLOCK_SIZE]) +#if PCRE2_CODE_UNIT_WIDTH == 32 +#define GET_UCD(ch) ((ch > MAX_UTF_CODE_POINT)? \ + PRIV(dummy_ucd_record) : REAL_GET_UCD(ch)) +#else +#define GET_UCD(ch) REAL_GET_UCD(ch) +#endif + #define UCD_CHARTYPE(ch) GET_UCD(ch)->chartype #define UCD_SCRIPT(ch) GET_UCD(ch)->script #define UCD_CATEGORY(ch) PRIV(ucp_gentype)[UCD_CHARTYPE(ch)] @@ -1852,8 +1858,12 @@ extern const uint8_t PRIV(utf8_table4)[]; #define _pcre2_callout_end_delims PCRE2_SUFFIX(_pcre2_callout_end_delims_) #define _pcre2_callout_start_delims PCRE2_SUFFIX(_pcre2_callout_start_delims_) #define _pcre2_default_compile_context PCRE2_SUFFIX(_pcre2_default_compile_context_) +#define _pcre2_default_convert_context PCRE2_SUFFIX(_pcre2_default_convert_context_) #define _pcre2_default_match_context PCRE2_SUFFIX(_pcre2_default_match_context_) #define _pcre2_default_tables PCRE2_SUFFIX(_pcre2_default_tables_) +#if PCRE2_CODE_UNIT_WIDTH == 32 +#define _pcre2_dummy_ucd_record PCRE2_SUFFIX(_pcre2_dummy_ucd_record_) +#endif #define _pcre2_hspace_list PCRE2_SUFFIX(_pcre2_hspace_list_) #define _pcre2_vspace_list PCRE2_SUFFIX(_pcre2_vspace_list_) #define _pcre2_ucd_caseless_sets PCRE2_SUFFIX(_pcre2_ucd_caseless_sets_) @@ -1872,12 +1882,16 @@ extern const uint8_t PRIV(OP_lengths)[]; extern const uint32_t PRIV(callout_end_delims)[]; extern const uint32_t PRIV(callout_start_delims)[]; extern const pcre2_compile_context PRIV(default_compile_context); +extern const pcre2_convert_context PRIV(default_convert_context); extern const pcre2_match_context PRIV(default_match_context); extern const uint8_t PRIV(default_tables)[]; extern const uint32_t PRIV(hspace_list)[]; extern const uint32_t PRIV(vspace_list)[]; extern const uint32_t PRIV(ucd_caseless_sets)[]; extern const ucd_record PRIV(ucd_records)[]; +#if PCRE2_CODE_UNIT_WIDTH == 32 +extern const ucd_record PRIV(dummy_ucd_record)[]; +#endif extern const uint8_t PRIV(ucd_stage1)[]; extern const uint16_t PRIV(ucd_stage2)[]; extern const uint32_t PRIV(ucp_gbtable)[]; |