/[pcre]/code/trunk/pcre_internal.h

Diff of /code/trunk/pcre_internal.h

Parent Directory | Revision Log | View Patch Patch

-revision 351 by ph10,
Fri Jul  4 18:27:16 2008 UTC
+revision 488 by ph10,
Mon Jan 11 15:29:42 2010 UTC
 Line 7
  and semantics are as close as possible to those of the Perl 5 language.
                         Written by Philip Hazel
-            Copyright (c) 1997-2008 University of Cambridge
+            Copyright (c) 1997-2010 University of Cambridge
  -----------------------------------------------------------------------------
  Redistribution and use in source and binary forms, with or without
 Line 45 
 functions whose names all begin with "_p
  #ifndef PCRE_INTERNAL_H
  #define PCRE_INTERNAL_H
- /* Define DEBUG to get debugging output on stdout. */
+ /* Define PCRE_DEBUG to get debugging output on stdout. */
  #if 0
- #define DEBUG
+ #define PCRE_DEBUG
+ #endif
+ /* We do not support both EBCDIC and UTF-8 at the same time. The "configure"
+ script prevents both being selected, but not everybody uses "configure". */
+ #if defined EBCDIC && defined SUPPORT_UTF8
+ #error The use of both EBCDIC and SUPPORT_UTF8 is not supported.
+ #endif
+ /* If SUPPORT_UCP is defined, SUPPORT_UTF8 must also be defined. The
+ "configure" script ensures this, but not everybody uses "configure". */
+ #if defined SUPPORT_UCP && !defined SUPPORT_UTF8
+ #define SUPPORT_UTF8 1
  #endif
  /* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef
-Line 60 
 It turns out that the Mac Debugging.h he
+Line 74 
 It turns out that the Mac Debugging.h he
  be absolutely sure we get our version. */
  #undef DPRINTF
- #ifdef DEBUG
+ #ifdef PCRE_DEBUG
  #define DPRINTF(p) printf p
  #else
  #define DPRINTF(p) /* Nothing */
-Line 72 
 setjmp and stdarg are used is when NO_RE
+Line 86 
 setjmp and stdarg are used is when NO_RE
  #include <ctype.h>
  #include <limits.h>
- #include <setjmp.h>
- #include <stdarg.h>
  #include <stddef.h>
  #include <stdio.h>
  #include <stdlib.h>
-Line 132 
 PCRE_EXP_DATA_DEFN only if they are not
+Line 144 
 PCRE_EXP_DATA_DEFN only if they are not
  #  endif
  #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
+ PCRE_CALL_CONVENTION just before their names. It is rarely needed; if not
+ set, we ensure here that it has no effect. */
+ #ifndef PCRE_CALL_CONVENTION
+ #define PCRE_CALL_CONVENTION
+ #endif
  /* We need to have types that specify unsigned 16-bit and 32-bit integers. We
  cannot determine these outside the compilation (e.g. by running a program as
  part of "configure") because PCRE is often cross-compiled for use on other
-Line 158 
 preprocessor time in standard C environm
+Line 184 
 preprocessor time in standard C environm
    #error Cannot determine a type for 32-bit unsigned integers
  #endif
+ /* When checking for integer overflow in pcre_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
+ arithmetic. Handle this by defining a macro for the appropriate type. If
+ stdint.h is available, include it; it may define INT64_MAX. The macro int64_t
+ may be set by "configure". */
+ #if HAVE_STDINT_H
+ #include <stdint.h>
+ #endif
+ #if defined INT64_MAX || defined int64_t
+ #define INT64_OR_DOUBLE int64_t
+ #else
+ #define INT64_OR_DOUBLE double
+ #endif
  /* All character handling must be done as unsigned characters. Otherwise there
  are problems with top-bit-set characters and functions such as isspace().
  However, we leave the interface to the outside world as char *, because that
-Line 367 
 never be called in byte mode. To make su
+Line 410 
 never be called in byte mode. To make su
  support is omitted, we don't even define it. */
  #ifndef SUPPORT_UTF8
- #define NEXTCHAR(p) p++;
  #define GETCHAR(c, eptr) c = *eptr;
  #define GETCHARTEST(c, eptr) c = *eptr;
  #define GETCHARINC(c, eptr) c = *eptr++;
-Line 377 
 support is omitted, we don't even define
+Line 419 
 support is omitted, we don't even define
  #else   /* SUPPORT_UTF8 */
- /* Advance a character pointer one byte in non-UTF-8 mode and by one character
- in UTF-8 mode. */
- #define NEXTCHAR(p) \
-   p++; \
-   if (utf8) { while((*p & 0xc0) == 0x80) p++; }
  /* Get the next UTF-8 character, not advancing the pointer. This is called when
  we know we are in UTF-8 mode. */
-Line 472 
 if there are extra bytes. This is called
+Line 507 
 if there are extra bytes. This is called
      len += gcaa; \
      }
+ /* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the
+ pointer, incrementing length if there are extra bytes. This is called when we
+ know we are in UTF-8 mode. */
+ #define GETCHARLENTEST(c, eptr, len) \
+   c = *eptr; \
+   if (utf8 && c >= 0xc0) \
+     { \
+     int gcii; \
+     int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \
+     int gcss = 6*gcaa; \
+     c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
+     for (gcii = 1; gcii <= gcaa; gcii++) \
+       { \
+       gcss -= 6; \
+       c |= (eptr[gcii] & 0x3f) << gcss; \
+       } \
+     len += gcaa; \
+     }
  /* If the pointer is not at the start of a character, move it back until
  it is. This is called only in UTF-8 mode - we don't put a test within the macro
  because almost all calls are already within a block of UTF-8 only code. */
-Line 495 
 Standard C system should have one. */
+Line 550 
 Standard C system should have one. */
  /* Private flags containing information about the compiled regex. They used to
  live at the top end of the options word, but that got almost full, so now they
- are in a 16-bit flags word. */
+ are in a 16-bit flags word. From release 8.00, PCRE_NOPARTIAL is unused, as
+ the restrictions on partial matching have been lifted. It remains for backwards
+ compatibility. */
  #define PCRE_NOPARTIAL     0x0001  /* can't use partial with this regex */
  #define PCRE_FIRSTSET      0x0002  /* first_byte is set */
-Line 507 
 are in a 16-bit flags word. */
+Line 564 
 are in a 16-bit flags word. */
  /* Options for the "extra" block produced by pcre_study(). */
  #define PCRE_STUDY_MAPPED   0x01     /* a map of starting chars exists */
+ #define PCRE_STUDY_MINLEN   0x02     /* a minimum length field exists */
  /* Masks for identifying the public options that are permitted at compile
  time, run time, or study time, respectively. */
-Line 514 
 time, run time, or study time, respectiv
+Line 572 
 time, run time, or study time, respectiv
  #define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \
                             PCRE_NEWLINE_ANYCRLF)
- #define PUBLIC_OPTIONS \
+ #define PUBLIC_COMPILE_OPTIONS \
    (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \
     PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \
     PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \
-Line 522 
 time, run time, or study time, respectiv
+Line 580 
 time, run time, or study time, respectiv
     PCRE_JAVASCRIPT_COMPAT)
  #define PUBLIC_EXEC_OPTIONS \
-   (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
+   (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \
-    PCRE_PARTIAL|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)
+    PCRE_NO_UTF8_CHECK|PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT|PCRE_NEWLINE_BITS| \
+    PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE|PCRE_NO_START_OPTIMIZE)
  #define PUBLIC_DFA_EXEC_OPTIONS \
-   (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
+   (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \
-    PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS| \
+    PCRE_NO_UTF8_CHECK|PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT|PCRE_DFA_SHORTEST| \
-    PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)
+    PCRE_DFA_RESTART|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \
+    PCRE_NO_START_OPTIMIZE)
  #define PUBLIC_STUDY_OPTIONS 0   /* None defined */
-Line 553 
 variable-length repeat, or a anything ot
+Line 613 
 variable-length repeat, or a anything ot
  #define REQ_CASELESS 0x0100    /* indicates caselessness */
  #define REQ_VARY     0x0200    /* reqbyte followed non-literal item */
- /* Miscellaneous definitions */
+ /* Miscellaneous definitions. The #ifndef is to pacify compiler warnings in
+ environments where these macros are defined elsewhere. Unfortunately, there
+ is no way to do the same for the typedef. */
  typedef int BOOL;
+ #ifndef FALSE
  #define FALSE   0
  #define TRUE    1
+ #endif
+ /* If PCRE is to support UTF-8 on EBCDIC platforms, we cannot use normal
+ character constants like '*' because the compiler would emit their EBCDIC code,
+ which is different from their ASCII/UTF-8 code. Instead we define macros for
+ the characters so that they always use the ASCII/UTF-8 code when UTF-8 support
+ is enabled. When UTF-8 support is not enabled, the definitions use character
+ literals. Both character and string versions of each character are needed, and
+ there are some longer strings as well.
+ This means that, on EBCDIC platforms, the PCRE library can handle either
+ EBCDIC, or UTF-8, but not both. To support both in the same compiled library
+ would need different lookups depending on whether PCRE_UTF8 was set or not.
+ This would make it impossible to use characters in switch/case statements,
+ which would reduce performance. For a theoretical use (which nobody has asked
+ for) in a minority area (EBCDIC platforms), this is not sensible. Any
+ application that did need both could compile two versions of the library, using
+ macros to give the functions distinct names. */
+ #ifndef SUPPORT_UTF8
+ /* UTF-8 support is not enabled; use the platform-dependent character literals
+ so that PCRE works on both ASCII and EBCDIC platforms, in non-UTF-mode only. */
+ #define CHAR_HT                     '\t'
+ #define CHAR_VT                     '\v'
+ #define CHAR_FF                     '\f'
+ #define CHAR_CR                     '\r'
+ #define CHAR_NL                     '\n'
+ #define CHAR_BS                     '\b'
+ #define CHAR_BEL                    '\a'
+ #ifdef EBCDIC
+ #define CHAR_ESC                    '\047'
+ #define CHAR_DEL                    '\007'
+ #else
+ #define CHAR_ESC                    '\033'
+ #define CHAR_DEL                    '\177'
+ #endif
+ #define CHAR_SPACE                  ' '
+ #define CHAR_EXCLAMATION_MARK       '!'
+ #define CHAR_QUOTATION_MARK         '"'
+ #define CHAR_NUMBER_SIGN            '#'
+ #define CHAR_DOLLAR_SIGN            '$'
+ #define CHAR_PERCENT_SIGN           '%'
+ #define CHAR_AMPERSAND              '&'
+ #define CHAR_APOSTROPHE             '\''
+ #define CHAR_LEFT_PARENTHESIS       '('
+ #define CHAR_RIGHT_PARENTHESIS      ')'
+ #define CHAR_ASTERISK               '*'
+ #define CHAR_PLUS                   '+'
+ #define CHAR_COMMA                  ','
+ #define CHAR_MINUS                  '-'
+ #define CHAR_DOT                    '.'
+ #define CHAR_SLASH                  '/'
+ #define CHAR_0                      '0'
+ #define CHAR_1                      '1'
+ #define CHAR_2                      '2'
+ #define CHAR_3                      '3'
+ #define CHAR_4                      '4'
+ #define CHAR_5                      '5'
+ #define CHAR_6                      '6'
+ #define CHAR_7                      '7'
+ #define CHAR_8                      '8'
+ #define CHAR_9                      '9'
+ #define CHAR_COLON                  ':'
+ #define CHAR_SEMICOLON              ';'
+ #define CHAR_LESS_THAN_SIGN         '<'
+ #define CHAR_EQUALS_SIGN            '='
+ #define CHAR_GREATER_THAN_SIGN      '>'
+ #define CHAR_QUESTION_MARK          '?'
+ #define CHAR_COMMERCIAL_AT          '@'
+ #define CHAR_A                      'A'
+ #define CHAR_B                      'B'
+ #define CHAR_C                      'C'
+ #define CHAR_D                      'D'
+ #define CHAR_E                      'E'
+ #define CHAR_F                      'F'
+ #define CHAR_G                      'G'
+ #define CHAR_H                      'H'
+ #define CHAR_I                      'I'
+ #define CHAR_J                      'J'
+ #define CHAR_K                      'K'
+ #define CHAR_L                      'L'
+ #define CHAR_M                      'M'
+ #define CHAR_N                      'N'
+ #define CHAR_O                      'O'
+ #define CHAR_P                      'P'
+ #define CHAR_Q                      'Q'
+ #define CHAR_R                      'R'
+ #define CHAR_S                      'S'
+ #define CHAR_T                      'T'
+ #define CHAR_U                      'U'
+ #define CHAR_V                      'V'
+ #define CHAR_W                      'W'
+ #define CHAR_X                      'X'
+ #define CHAR_Y                      'Y'
+ #define CHAR_Z                      'Z'
+ #define CHAR_LEFT_SQUARE_BRACKET    '['
+ #define CHAR_BACKSLASH              '\\'
+ #define CHAR_RIGHT_SQUARE_BRACKET   ']'
+ #define CHAR_CIRCUMFLEX_ACCENT      '^'
+ #define CHAR_UNDERSCORE             '_'
+ #define CHAR_GRAVE_ACCENT           '`'
+ #define CHAR_a                      'a'
+ #define CHAR_b                      'b'
+ #define CHAR_c                      'c'
+ #define CHAR_d                      'd'
+ #define CHAR_e                      'e'
+ #define CHAR_f                      'f'
+ #define CHAR_g                      'g'
+ #define CHAR_h                      'h'
+ #define CHAR_i                      'i'
+ #define CHAR_j                      'j'
+ #define CHAR_k                      'k'
+ #define CHAR_l                      'l'
+ #define CHAR_m                      'm'
+ #define CHAR_n                      'n'
+ #define CHAR_o                      'o'
+ #define CHAR_p                      'p'
+ #define CHAR_q                      'q'
+ #define CHAR_r                      'r'
+ #define CHAR_s                      's'
+ #define CHAR_t                      't'
+ #define CHAR_u                      'u'
+ #define CHAR_v                      'v'
+ #define CHAR_w                      'w'
+ #define CHAR_x                      'x'
+ #define CHAR_y                      'y'
+ #define CHAR_z                      'z'
+ #define CHAR_LEFT_CURLY_BRACKET     '{'
+ #define CHAR_VERTICAL_LINE          '|'
+ #define CHAR_RIGHT_CURLY_BRACKET    '}'
+ #define CHAR_TILDE                  '~'
+ #define STR_HT                      "\t"
+ #define STR_VT                      "\v"
+ #define STR_FF                      "\f"
+ #define STR_CR                      "\r"
+ #define STR_NL                      "\n"
+ #define STR_BS                      "\b"
+ #define STR_BEL                     "\a"
+ #ifdef EBCDIC
+ #define STR_ESC                     "\047"
+ #define STR_DEL                     "\007"
+ #else
+ #define STR_ESC                     "\033"
+ #define STR_DEL                     "\177"
+ #endif
+ #define STR_SPACE                   " "
+ #define STR_EXCLAMATION_MARK        "!"
+ #define STR_QUOTATION_MARK          "\""
+ #define STR_NUMBER_SIGN             "#"
+ #define STR_DOLLAR_SIGN             "$"
+ #define STR_PERCENT_SIGN            "%"
+ #define STR_AMPERSAND               "&"
+ #define STR_APOSTROPHE              "'"
+ #define STR_LEFT_PARENTHESIS        "("
+ #define STR_RIGHT_PARENTHESIS       ")"
+ #define STR_ASTERISK                "*"
+ #define STR_PLUS                    "+"
+ #define STR_COMMA                   ","
+ #define STR_MINUS                   "-"
+ #define STR_DOT                     "."
+ #define STR_SLASH                   "/"
+ #define STR_0                       "0"
+ #define STR_1                       "1"
+ #define STR_2                       "2"
+ #define STR_3                       "3"
+ #define STR_4                       "4"
+ #define STR_5                       "5"
+ #define STR_6                       "6"
+ #define STR_7                       "7"
+ #define STR_8                       "8"
+ #define STR_9                       "9"
+ #define STR_COLON                   ":"
+ #define STR_SEMICOLON               ";"
+ #define STR_LESS_THAN_SIGN          "<"
+ #define STR_EQUALS_SIGN             "="
+ #define STR_GREATER_THAN_SIGN       ">"
+ #define STR_QUESTION_MARK           "?"
+ #define STR_COMMERCIAL_AT           "@"
+ #define STR_A                       "A"
+ #define STR_B                       "B"
+ #define STR_C                       "C"
+ #define STR_D                       "D"
+ #define STR_E                       "E"
+ #define STR_F                       "F"
+ #define STR_G                       "G"
+ #define STR_H                       "H"
+ #define STR_I                       "I"
+ #define STR_J                       "J"
+ #define STR_K                       "K"
+ #define STR_L                       "L"
+ #define STR_M                       "M"
+ #define STR_N                       "N"
+ #define STR_O                       "O"
+ #define STR_P                       "P"
+ #define STR_Q                       "Q"
+ #define STR_R                       "R"
+ #define STR_S                       "S"
+ #define STR_T                       "T"
+ #define STR_U                       "U"
+ #define STR_V                       "V"
+ #define STR_W                       "W"
+ #define STR_X                       "X"
+ #define STR_Y                       "Y"
+ #define STR_Z                       "Z"
+ #define STR_LEFT_SQUARE_BRACKET     "["
+ #define STR_BACKSLASH               "\\"
+ #define STR_RIGHT_SQUARE_BRACKET    "]"
+ #define STR_CIRCUMFLEX_ACCENT       "^"
+ #define STR_UNDERSCORE              "_"
+ #define STR_GRAVE_ACCENT            "`"
+ #define STR_a                       "a"
+ #define STR_b                       "b"
+ #define STR_c                       "c"
+ #define STR_d                       "d"
+ #define STR_e                       "e"
+ #define STR_f                       "f"
+ #define STR_g                       "g"
+ #define STR_h                       "h"
+ #define STR_i                       "i"
+ #define STR_j                       "j"
+ #define STR_k                       "k"
+ #define STR_l                       "l"
+ #define STR_m                       "m"
+ #define STR_n                       "n"
+ #define STR_o                       "o"
+ #define STR_p                       "p"
+ #define STR_q                       "q"
+ #define STR_r                       "r"
+ #define STR_s                       "s"
+ #define STR_t                       "t"
+ #define STR_u                       "u"
+ #define STR_v                       "v"
+ #define STR_w                       "w"
+ #define STR_x                       "x"
+ #define STR_y                       "y"
+ #define STR_z                       "z"
+ #define STR_LEFT_CURLY_BRACKET      "{"
+ #define STR_VERTICAL_LINE           "|"
+ #define STR_RIGHT_CURLY_BRACKET     "}"
+ #define STR_TILDE                   "~"
+ #define STRING_ACCEPT0              "ACCEPT\0"
+ #define STRING_COMMIT0              "COMMIT\0"
+ #define STRING_F0                   "F\0"
+ #define STRING_FAIL0                "FAIL\0"
+ #define STRING_PRUNE0               "PRUNE\0"
+ #define STRING_SKIP0                "SKIP\0"
+ #define STRING_THEN                 "THEN"
+ #define STRING_alpha0               "alpha\0"
+ #define STRING_lower0               "lower\0"
+ #define STRING_upper0               "upper\0"
+ #define STRING_alnum0               "alnum\0"
+ #define STRING_ascii0               "ascii\0"
+ #define STRING_blank0               "blank\0"
+ #define STRING_cntrl0               "cntrl\0"
+ #define STRING_digit0               "digit\0"
+ #define STRING_graph0               "graph\0"
+ #define STRING_print0               "print\0"
+ #define STRING_punct0               "punct\0"
+ #define STRING_space0               "space\0"
+ #define STRING_word0                "word\0"
+ #define STRING_xdigit               "xdigit"
+ #define STRING_DEFINE               "DEFINE"
+ #define STRING_CR_RIGHTPAR          "CR)"
+ #define STRING_LF_RIGHTPAR          "LF)"
+ #define STRING_CRLF_RIGHTPAR        "CRLF)"
+ #define STRING_ANY_RIGHTPAR         "ANY)"
+ #define STRING_ANYCRLF_RIGHTPAR     "ANYCRLF)"
+ #define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)"
+ #define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)"
+ #define STRING_UTF8_RIGHTPAR        "UTF8)"
+ #else  /* SUPPORT_UTF8 */
+ /* UTF-8 support is enabled; always use UTF-8 (=ASCII) character codes. This
+ works in both modes non-EBCDIC platforms, and on EBCDIC platforms in UTF-8 mode
+ only. */
+ #define CHAR_HT                     '\011'
+ #define CHAR_VT                     '\013'
+ #define CHAR_FF                     '\014'
+ #define CHAR_CR                     '\015'
+ #define CHAR_NL                     '\012'
+ #define CHAR_BS                     '\010'
+ #define CHAR_BEL                    '\007'
+ #define CHAR_ESC                    '\033'
+ #define CHAR_DEL                    '\177'
+ #define CHAR_SPACE                  '\040'
+ #define CHAR_EXCLAMATION_MARK       '\041'
+ #define CHAR_QUOTATION_MARK         '\042'
+ #define CHAR_NUMBER_SIGN            '\043'
+ #define CHAR_DOLLAR_SIGN            '\044'
+ #define CHAR_PERCENT_SIGN           '\045'
+ #define CHAR_AMPERSAND              '\046'
+ #define CHAR_APOSTROPHE             '\047'
+ #define CHAR_LEFT_PARENTHESIS       '\050'
+ #define CHAR_RIGHT_PARENTHESIS      '\051'
+ #define CHAR_ASTERISK               '\052'
+ #define CHAR_PLUS                   '\053'
+ #define CHAR_COMMA                  '\054'
+ #define CHAR_MINUS                  '\055'
+ #define CHAR_DOT                    '\056'
+ #define CHAR_SLASH                  '\057'
+ #define CHAR_0                      '\060'
+ #define CHAR_1                      '\061'
+ #define CHAR_2                      '\062'
+ #define CHAR_3                      '\063'
+ #define CHAR_4                      '\064'
+ #define CHAR_5                      '\065'
+ #define CHAR_6                      '\066'
+ #define CHAR_7                      '\067'
+ #define CHAR_8                      '\070'
+ #define CHAR_9                      '\071'
+ #define CHAR_COLON                  '\072'
+ #define CHAR_SEMICOLON              '\073'
+ #define CHAR_LESS_THAN_SIGN         '\074'
+ #define CHAR_EQUALS_SIGN            '\075'
+ #define CHAR_GREATER_THAN_SIGN      '\076'
+ #define CHAR_QUESTION_MARK          '\077'
+ #define CHAR_COMMERCIAL_AT          '\100'
+ #define CHAR_A                      '\101'
+ #define CHAR_B                      '\102'
+ #define CHAR_C                      '\103'
+ #define CHAR_D                      '\104'
+ #define CHAR_E                      '\105'
+ #define CHAR_F                      '\106'
+ #define CHAR_G                      '\107'
+ #define CHAR_H                      '\110'
+ #define CHAR_I                      '\111'
+ #define CHAR_J                      '\112'
+ #define CHAR_K                      '\113'
+ #define CHAR_L                      '\114'
+ #define CHAR_M                      '\115'
+ #define CHAR_N                      '\116'
+ #define CHAR_O                      '\117'
+ #define CHAR_P                      '\120'
+ #define CHAR_Q                      '\121'
+ #define CHAR_R                      '\122'
+ #define CHAR_S                      '\123'
+ #define CHAR_T                      '\124'
+ #define CHAR_U                      '\125'
+ #define CHAR_V                      '\126'
+ #define CHAR_W                      '\127'
+ #define CHAR_X                      '\130'
+ #define CHAR_Y                      '\131'
+ #define CHAR_Z                      '\132'
+ #define CHAR_LEFT_SQUARE_BRACKET    '\133'
+ #define CHAR_BACKSLASH              '\134'
+ #define CHAR_RIGHT_SQUARE_BRACKET   '\135'
+ #define CHAR_CIRCUMFLEX_ACCENT      '\136'
+ #define CHAR_UNDERSCORE             '\137'
+ #define CHAR_GRAVE_ACCENT           '\140'
+ #define CHAR_a                      '\141'
+ #define CHAR_b                      '\142'
+ #define CHAR_c                      '\143'
+ #define CHAR_d                      '\144'
+ #define CHAR_e                      '\145'
+ #define CHAR_f                      '\146'
+ #define CHAR_g                      '\147'
+ #define CHAR_h                      '\150'
+ #define CHAR_i                      '\151'
+ #define CHAR_j                      '\152'
+ #define CHAR_k                      '\153'
+ #define CHAR_l                      '\154'
+ #define CHAR_m                      '\155'
+ #define CHAR_n                      '\156'
+ #define CHAR_o                      '\157'
+ #define CHAR_p                      '\160'
+ #define CHAR_q                      '\161'
+ #define CHAR_r                      '\162'
+ #define CHAR_s                      '\163'
+ #define CHAR_t                      '\164'
+ #define CHAR_u                      '\165'
+ #define CHAR_v                      '\166'
+ #define CHAR_w                      '\167'
+ #define CHAR_x                      '\170'
+ #define CHAR_y                      '\171'
+ #define CHAR_z                      '\172'
+ #define CHAR_LEFT_CURLY_BRACKET     '\173'
+ #define CHAR_VERTICAL_LINE          '\174'
+ #define CHAR_RIGHT_CURLY_BRACKET    '\175'
+ #define CHAR_TILDE                  '\176'
+ #define STR_HT                      "\011"
+ #define STR_VT                      "\013"
+ #define STR_FF                      "\014"
+ #define STR_CR                      "\015"
+ #define STR_NL                      "\012"
+ #define STR_BS                      "\010"
+ #define STR_BEL                     "\007"
+ #define STR_ESC                     "\033"
+ #define STR_DEL                     "\177"
+ #define STR_SPACE                   "\040"
+ #define STR_EXCLAMATION_MARK        "\041"
+ #define STR_QUOTATION_MARK          "\042"
+ #define STR_NUMBER_SIGN             "\043"
+ #define STR_DOLLAR_SIGN             "\044"
+ #define STR_PERCENT_SIGN            "\045"
+ #define STR_AMPERSAND               "\046"
+ #define STR_APOSTROPHE              "\047"
+ #define STR_LEFT_PARENTHESIS        "\050"
+ #define STR_RIGHT_PARENTHESIS       "\051"
+ #define STR_ASTERISK                "\052"
+ #define STR_PLUS                    "\053"
+ #define STR_COMMA                   "\054"
+ #define STR_MINUS                   "\055"
+ #define STR_DOT                     "\056"
+ #define STR_SLASH                   "\057"
+ #define STR_0                       "\060"
+ #define STR_1                       "\061"
+ #define STR_2                       "\062"
+ #define STR_3                       "\063"
+ #define STR_4                       "\064"
+ #define STR_5                       "\065"
+ #define STR_6                       "\066"
+ #define STR_7                       "\067"
+ #define STR_8                       "\070"
+ #define STR_9                       "\071"
+ #define STR_COLON                   "\072"
+ #define STR_SEMICOLON               "\073"
+ #define STR_LESS_THAN_SIGN          "\074"
+ #define STR_EQUALS_SIGN             "\075"
+ #define STR_GREATER_THAN_SIGN       "\076"
+ #define STR_QUESTION_MARK           "\077"
+ #define STR_COMMERCIAL_AT           "\100"
+ #define STR_A                       "\101"
+ #define STR_B                       "\102"
+ #define STR_C                       "\103"
+ #define STR_D                       "\104"
+ #define STR_E                       "\105"
+ #define STR_F                       "\106"
+ #define STR_G                       "\107"
+ #define STR_H                       "\110"
+ #define STR_I                       "\111"
+ #define STR_J                       "\112"
+ #define STR_K                       "\113"
+ #define STR_L                       "\114"
+ #define STR_M                       "\115"
+ #define STR_N                       "\116"
+ #define STR_O                       "\117"
+ #define STR_P                       "\120"
+ #define STR_Q                       "\121"
+ #define STR_R                       "\122"
+ #define STR_S                       "\123"
+ #define STR_T                       "\124"
+ #define STR_U                       "\125"
+ #define STR_V                       "\126"
+ #define STR_W                       "\127"
+ #define STR_X                       "\130"
+ #define STR_Y                       "\131"
+ #define STR_Z                       "\132"
+ #define STR_LEFT_SQUARE_BRACKET     "\133"
+ #define STR_BACKSLASH               "\134"
+ #define STR_RIGHT_SQUARE_BRACKET    "\135"
+ #define STR_CIRCUMFLEX_ACCENT       "\136"
+ #define STR_UNDERSCORE              "\137"
+ #define STR_GRAVE_ACCENT            "\140"
+ #define STR_a                       "\141"
+ #define STR_b                       "\142"
+ #define STR_c                       "\143"
+ #define STR_d                       "\144"
+ #define STR_e                       "\145"
+ #define STR_f                       "\146"
+ #define STR_g                       "\147"
+ #define STR_h                       "\150"
+ #define STR_i                       "\151"
+ #define STR_j                       "\152"
+ #define STR_k                       "\153"
+ #define STR_l                       "\154"
+ #define STR_m                       "\155"
+ #define STR_n                       "\156"
+ #define STR_o                       "\157"
+ #define STR_p                       "\160"
+ #define STR_q                       "\161"
+ #define STR_r                       "\162"
+ #define STR_s                       "\163"
+ #define STR_t                       "\164"
+ #define STR_u                       "\165"
+ #define STR_v                       "\166"
+ #define STR_w                       "\167"
+ #define STR_x                       "\170"
+ #define STR_y                       "\171"
+ #define STR_z                       "\172"
+ #define STR_LEFT_CURLY_BRACKET      "\173"
+ #define STR_VERTICAL_LINE           "\174"
+ #define STR_RIGHT_CURLY_BRACKET     "\175"
+ #define STR_TILDE                   "\176"
+ #define STRING_ACCEPT0              STR_A STR_C STR_C STR_E STR_P STR_T "\0"
+ #define STRING_COMMIT0              STR_C STR_O STR_M STR_M STR_I STR_T "\0"
+ #define STRING_F0                   STR_F "\0"
+ #define STRING_FAIL0                STR_F STR_A STR_I STR_L "\0"
+ #define STRING_PRUNE0               STR_P STR_R STR_U STR_N STR_E "\0"
+ #define STRING_SKIP0                STR_S STR_K STR_I STR_P "\0"
+ #define STRING_THEN                 STR_T STR_H STR_E STR_N
+ #define STRING_alpha0               STR_a STR_l STR_p STR_h STR_a "\0"
+ #define STRING_lower0               STR_l STR_o STR_w STR_e STR_r "\0"
+ #define STRING_upper0               STR_u STR_p STR_p STR_e STR_r "\0"
+ #define STRING_alnum0               STR_a STR_l STR_n STR_u STR_m "\0"
+ #define STRING_ascii0               STR_a STR_s STR_c STR_i STR_i "\0"
+ #define STRING_blank0               STR_b STR_l STR_a STR_n STR_k "\0"
+ #define STRING_cntrl0               STR_c STR_n STR_t STR_r STR_l "\0"
+ #define STRING_digit0               STR_d STR_i STR_g STR_i STR_t "\0"
+ #define STRING_graph0               STR_g STR_r STR_a STR_p STR_h "\0"
+ #define STRING_print0               STR_p STR_r STR_i STR_n STR_t "\0"
+ #define STRING_punct0               STR_p STR_u STR_n STR_c STR_t "\0"
+ #define STRING_space0               STR_s STR_p STR_a STR_c STR_e "\0"
+ #define STRING_word0                STR_w STR_o STR_r STR_d       "\0"
+ #define STRING_xdigit               STR_x STR_d STR_i STR_g STR_i STR_t
+ #define STRING_DEFINE               STR_D STR_E STR_F STR_I STR_N STR_E
+ #define STRING_CR_RIGHTPAR          STR_C STR_R STR_RIGHT_PARENTHESIS
+ #define STRING_LF_RIGHTPAR          STR_L STR_F STR_RIGHT_PARENTHESIS
+ #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_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
+ #endif  /* SUPPORT_UTF8 */
  /* Escape items that are just an encoding of a particular data value. */
  #ifndef ESC_e
- #define ESC_e 27
+ #define ESC_e CHAR_ESC
  #endif
  #ifndef ESC_f
- #define ESC_f '\f'
+ #define ESC_f CHAR_FF
  #endif
  #ifndef ESC_n
- #define ESC_n '\n'
+ #define ESC_n CHAR_NL
  #endif
  #ifndef ESC_r
- #define ESC_r '\r'
+ #define ESC_r CHAR_CR
  #endif
  /* We can't officially use ESC_t because it is a POSIX reserved identifier
  (presumably because of all the others like size_t). */
  #ifndef ESC_tee
- #define ESC_tee '\t'
+ #define ESC_tee CHAR_HT
  #endif
  /* Codes for different types of Unicode property */
-Line 629 
 enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, E
+Line 1225 
 enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, E
  OP_EOD must correspond in order to the list of escapes immediately above.
  *** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions
- that follow must also be updated to match. There is also a table called
+ that follow must also be updated to match. There are also tables called
- "coptable" in pcre_dfa_exec.c that must be updated. */
+ "coptable" and "poptable" in pcre_dfa_exec.c that must be updated. */
  enum {
    OP_END,            /* 0 End of pattern */
-Line 766 
 enum {
+Line 1362 
 enum {
    OP_SCBRA,          /* 98 Start of capturing bracket, check empty */
    OP_SCOND,          /* 99 Conditional group, check empty */
+   /* The next two pairs must (respectively) be kept together. */
    OP_CREF,           /* 100 Used to hold a capture number as condition */
-   OP_RREF,           /* 101 Used to hold a recursion number as condition */
+   OP_NCREF,          /* 101 Same, but generaged by a name reference*/
-   OP_DEF,            /* 102 The DEFINE condition */
+   OP_RREF,           /* 102 Used to hold a recursion number as condition */
+   OP_NRREF,          /* 103 Same, but generaged by a name reference*/
+   OP_DEF,            /* 104 The DEFINE condition */
-   OP_BRAZERO,        /* 103 These two must remain together and in this */
+   OP_BRAZERO,        /* 105 These two must remain together and in this */
-   OP_BRAMINZERO,     /* 104 order. */
+   OP_BRAMINZERO,     /* 106 order. */
    /* These are backtracking control verbs */
-   OP_PRUNE,          /* 105 */
+   OP_PRUNE,          /* 107 */
-   OP_SKIP,           /* 106 */
+   OP_SKIP,           /* 108 */
-   OP_THEN,           /* 107 */
+   OP_THEN,           /* 109 */
-   OP_COMMIT,         /* 108 */
+   OP_COMMIT,         /* 110 */
    /* These are forced failure and success verbs */
-   OP_FAIL,           /* 109 */
+   OP_FAIL,           /* 111 */
-   OP_ACCEPT,         /* 110 */
+   OP_ACCEPT,         /* 112 */
+   OP_CLOSE,          /* 113 Used before OP_ACCEPT to close open captures */
    /* This is used to skip a subpattern with a {0} quantifier */
-   OP_SKIPZERO        /* 111 */
+   OP_SKIPZERO        /* 114 */
  };
+ /* *** NOTE NOTE NOTE *** Whenever the list above is updated, the two macro
+ definitions that follow must also be updated to match. There are also tables
+ called "coptable" cna "poptable" in pcre_dfa_exec.c that must be updated. */
  /* This macro defines textual names for all the opcodes. These are used only
  for debugging. The macro is referenced only in pcre_printint.c. */
-Line 811 
 for debugging. The macro is referenced o
+Line 1416 
 for debugging. The macro is referenced o
    "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not",     \
    "AssertB", "AssertB not", "Reverse",                            \
    "Once", "Bra", "CBra", "Cond", "SBra", "SCBra", "SCond",        \
-   "Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero",    \
+   "Cond ref", "Cond nref", "Cond rec", "Cond nrec", "Cond def",   \
+   "Brazero", "Braminzero",                                        \
    "*PRUNE", "*SKIP", "*THEN", "*COMMIT", "*FAIL", "*ACCEPT",      \
-   "Skip zero"
+   "Close", "Skip zero"
  /* This macro defines the length of fixed length operations in the compiled
-Line 873 
 in UTF-8 mode. The code that uses this t
+Line 1479 
 in UTF-8 mode. The code that uses this t
 +LINK_SIZE,                   /* SBRA                                   */ \
 +LINK_SIZE,                   /* SCBRA                                  */ \
 +LINK_SIZE,                   /* SCOND                                  */ \
-,                             /* CREF                                   */ \
+, 3,                          /* CREF, NCREF                            */ \
-,                             /* RREF                                   */ \
+, 3,                          /* RREF, NRREF                            */ \
 ,                             /* DEF                                    */ \
 , 1,                          /* BRAZERO, BRAMINZERO                    */ \
 , 1, 1, 1,                    /* PRUNE, SKIP, THEN, COMMIT,             */ \
-, 1, 1                        /* FAIL, ACCEPT, SKIPZERO                 */
+, 1, 3, 1                     /* FAIL, ACCEPT, CLOSE, SKIPZERO          */
- /* A magic value for OP_RREF to indicate the "any recursion" condition. */
+ /* A magic value for OP_RREF and OP_NRREF to indicate the "any recursion"
+ condition. */
  #define RREF_ANY  0xffff
-Line 894 
 enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,
+Line 1501 
 enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,
         ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39,
         ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49,
         ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59,
-        ERR60, ERR61, ERR62, ERR63, ERR64 };
+        ERR60, ERR61, ERR62, ERR63, ERR64, ERR65 };
  /* The real format of the start of the pcre block; the index of names and the
  code vector run on as long as necessary after the end. We store an explicit
-Line 910 
 Because people can now save and re-use c
+Line 1517 
 Because people can now save and re-use c
  structure should be made at the end, and something earlier (e.g. a new
  flag in the options or one of the dummy fields) should indicate that the new
  fields are present. Currently PCRE always sets the dummy fields to zero.
- NOTE NOTE NOTE:
+ NOTE NOTE NOTE
  */
  typedef struct real_pcre {
-Line 937 
 remark (see NOTE above) about extending
+Line 1544 
 remark (see NOTE above) about extending
  typedef struct pcre_study_data {
    pcre_uint32 size;               /* Total that was malloced */
-   pcre_uint32 options;
+   pcre_uint32 flags;              /* Private flags */
-   uschar start_bits[32];
+   uschar start_bits[32];          /* Starting char bits */
+   pcre_uint32 minlength;          /* Minimum subject length */
  } pcre_study_data;
+ /* Structure for building a chain of open capturing subpatterns during
+ compiling, so that instructions to close them can be compiled when (*ACCEPT) is
+ encountered. This is also used to identify subpatterns that contain recursive
+ back references to themselves, so that they can be made atomic. */
+ typedef struct open_capitem {
+   struct open_capitem *next;    /* Chain link */
+   pcre_uint16 number;           /* Capture number */
+   pcre_uint16 flag;             /* Set TRUE if recursive back ref */
+ } open_capitem;
  /* Structure for passing "static" information around between the functions
  doing the compiling, so that they are thread-safe. */
-Line 953 
 typedef struct compile_data {
+Line 1572 
 typedef struct compile_data {
    const uschar *start_code;     /* The start of the compiled code */
    const uschar *start_pattern;  /* The start of the pattern */
    const uschar *end_pattern;    /* The end of the pattern */
+   open_capitem *open_caps;      /* Chain of open capture items */
    uschar *hwm;                  /* High watermark of workspace */
    uschar *name_table;           /* The name/number table */
    int  names_found;             /* Number of entries so far */
-Line 965 
 typedef struct compile_data {
+Line 1585 
 typedef struct compile_data {
    int  external_flags;          /* External flag bits to be set */
    int  req_varyopt;             /* "After variable item" flag for reqbyte */
    BOOL had_accept;              /* (*ACCEPT) encountered */
+   BOOL check_lookbehind;        /* Lookbehinds need later checking */
    int  nltype;                  /* Newline type */
    int  nllen;                   /* Newline string length */
    uschar nl[4];                 /* Newline string when fixed length */
-Line 975 
 branches, for testing for left recursion
+Line 1596 
 branches, for testing for left recursion
  typedef struct branch_chain {
    struct branch_chain *outer;
-   uschar *current;
+   uschar *current_branch;
  } branch_chain;
  /* Structure for items in a linked list that represents an explicit recursive
-Line 988 
 typedef struct recursion_info {
+Line 1609 
 typedef struct recursion_info {
    USPTR save_start;             /* Old value of mstart */
    int *offset_save;             /* Pointer to start of saved offsets */
    int saved_max;                /* Number of saved offsets */
+   int save_offset_top;          /* Current value of offset_top */
  } recursion_info;
  /* Structure for building a chain of data for holding the values of the subject
-Line 1012 
 typedef struct match_data {
+Line 1634 
 typedef struct match_data {
    int    offset_max;            /* The maximum usable for return data */
    int    nltype;                /* Newline type */
    int    nllen;                 /* Newline string length */
+   int    name_count;            /* Number of names in name table */
+   int    name_entry_size;       /* Size of entry in names table */
+   uschar *name_table;           /* Table of names */
    uschar nl[4];                 /* Newline string when fixed */
    const uschar *lcc;            /* Points to lower casing table */
    const uschar *ctypes;         /* Points to table of type maps */
-Line 1022 
 typedef struct match_data {
+Line 1647 
 typedef struct match_data {
    BOOL   jscript_compat;        /* JAVASCRIPT_COMPAT flag */
    BOOL   endonly;               /* Dollar not before final \n */
    BOOL   notempty;              /* Empty string match not wanted */
-   BOOL   partial;               /* PARTIAL flag */
+   BOOL   notempty_atstart;      /* Empty string match at start not wanted */
    BOOL   hitend;                /* Hit the end of the subject at some point */
    BOOL   bsr_anycrlf;           /* \R is just any CRLF, not full Unicode */
    const uschar *start_code;     /* For use when recursing */
-Line 1030 
 typedef struct match_data {
+Line 1655 
 typedef struct match_data {
    USPTR  end_subject;           /* End of the subject string */
    USPTR  start_match_ptr;       /* Start of matched string */
    USPTR  end_match_ptr;         /* Subject position at end match */
+   USPTR  start_used_ptr;        /* Earliest consulted character */
+   int    partial;               /* PARTIAL options */
    int    end_offset_top;        /* Highwater mark at end of match */
    int    capture_last;          /* Most recent capture number */
    int    start_offset;          /* The start offset value */
-Line 1046 
 typedef struct dfa_match_data {
+Line 1673 
 typedef struct dfa_match_data {
    const uschar *start_code;     /* Start of the compiled pattern */
    const uschar *start_subject;  /* Start of the subject string */
    const uschar *end_subject;    /* End of subject string */
+   const uschar *start_used_ptr; /* Earliest consulted character */
    const uschar *tables;         /* Character tables */
+   int   start_offset;           /* The start offset value */
    int   moptions;               /* Match options */
    int   poptions;               /* Pattern options */
    int    nltype;                /* Newline type */
-Line 1125 
 extern const uschar _pcre_OP_lengths[];
+Line 1754 
 extern const uschar _pcre_OP_lengths[];
  one of the exported public functions. They have to be "external" in the C
  sense, but are not part of the PCRE public API. */
- extern BOOL         _pcre_is_newline(const uschar *, int, const uschar *,
+ extern const uschar *_pcre_find_bracket(const uschar *, BOOL, int);
-                       int *, BOOL);
+ extern BOOL          _pcre_is_newline(USPTR, int, USPTR, int *, BOOL);
- extern int          _pcre_ord2utf8(int, uschar *);
+ extern int           _pcre_ord2utf8(int, uschar *);
- extern real_pcre   *_pcre_try_flipped(const real_pcre *, real_pcre *,
+ extern real_pcre    *_pcre_try_flipped(const real_pcre *, real_pcre *,
-                       const pcre_study_data *, pcre_study_data *);
+                        const pcre_study_data *, pcre_study_data *);
- extern int          _pcre_valid_utf8(const uschar *, int);
+ extern int           _pcre_valid_utf8(USPTR, int);
- extern BOOL         _pcre_was_newline(const uschar *, int, const uschar *,
+ extern BOOL          _pcre_was_newline(USPTR, int, USPTR, int *, BOOL);
-                       int *, BOOL);
+ extern BOOL          _pcre_xclass(int, const uschar *);
- extern BOOL         _pcre_xclass(int, const uschar *);
  /* Unicode character database (UCD) */

 Legend:



Removed from v.351
 


changed lines


 
Added in v.488
 Legend:



Removed from v.351
 


changed lines


 
Added in v.488
-Removed from v.351
+Added in v.488

	ViewVC Help
Powered by ViewVC 1.1.5