pcre_internal.h

来自「Ubuntu packages of security software。 相」· C头文件 代码 · 共 1,122 行 · 第 1/3 页

/* #define BACKCHAR(eptr) */

#else   /* SUPPORT_UTF8 */

/* Get the next UTF-8 character, not advancing the pointer. This is called when
we know we are in UTF-8 mode. */

#define GETCHAR(c, eptr) \
  c = *eptr; \
  if (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; \
      } \
    }

/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the
pointer. */

#define GETCHARTEST(c, eptr) \
  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; \
      } \
    }

/* Get the next UTF-8 character, advancing the pointer. This is called when we
know we are in UTF-8 mode. */

#define GETCHARINC(c, eptr) \
  c = *eptr++; \
  if (c >= 0xc0) \
    { \
    int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \
    int gcss = 6*gcaa; \
    c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
    while (gcaa-- > 0) \
      { \
      gcss -= 6; \
      c |= (*eptr++ & 0x3f) << gcss; \
      } \
    }

/* Get the next character, testing for UTF-8 mode, and advancing the pointer */

#define GETCHARINCTEST(c, eptr) \
  c = *eptr++; \
  if (utf8 && c >= 0xc0) \
    { \
    int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \
    int gcss = 6*gcaa; \
    c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
    while (gcaa-- > 0) \
      { \
      gcss -= 6; \
      c |= (*eptr++ & 0x3f) << gcss; \
      } \
    }

/* Get the next UTF-8 character, not advancing the pointer, incrementing length
if there are extra bytes. This is called when we know we are in UTF-8 mode. */

#define GETCHARLEN(c, eptr, len) \
  c = *eptr; \
  if (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. */

#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--

#endif


/* In case there is no definition of offsetof() provided - though any proper
Standard C system should have one. */

#ifndef offsetof
#define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field))
#endif


/* These are the public options that can change during matching. */

#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL)

/* 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. */

#define PCRE_NOPARTIAL     0x0001  /* can't use partial with this regex */
#define PCRE_FIRSTSET      0x0002  /* first_byte is set */
#define PCRE_REQCHSET      0x0004  /* req_byte is set */
#define PCRE_STARTLINE     0x0008  /* start after \n for multiline */
#define PCRE_JCHANGED      0x0010  /* j option used in regex */
#define PCRE_HASCRORLF     0x0020  /* explicit \r or \n in pattern */

/* Options for the "extra" block produced by pcre_study(). */

#define PCRE_STUDY_MAPPED   0x01     /* a map of starting chars exists */

/* Masks for identifying the public options that are permitted at compile
time, run time, or study time, respectively. */

#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \
                           PCRE_NEWLINE_ANYCRLF)

#define PUBLIC_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| \
   PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)

#define PUBLIC_EXEC_OPTIONS \
  (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
   PCRE_PARTIAL|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)

#define PUBLIC_DFA_EXEC_OPTIONS \
  (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
   PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS| \
   PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)

#define PUBLIC_STUDY_OPTIONS 0   /* None defined */

/* Magic number to provide a small check against being handed junk. Also used
to detect whether a pattern was compiled on a host of different endianness. */

#define MAGIC_NUMBER  0x50435245UL   /* 'PCRE' */

/* Negative values for the firstchar and reqchar variables */

#define REQ_UNSET (-2)
#define REQ_NONE  (-1)

/* The maximum remaining length of subject we are prepared to search for a
req_byte match. */

#define REQ_BYTE_MAX 1000

/* Flags added to firstbyte or reqbyte; a "non-literal" item is either a
variable-length repeat, or a anything other than literal characters. */

#define REQ_CASELESS 0x0100    /* indicates caselessness */
#define REQ_VARY     0x0200    /* reqbyte followed non-literal item */

/* Miscellaneous definitions */

typedef int BOOL;

#define FALSE   0
#define TRUE    1

/* Escape items that are just an encoding of a particular data value. */

#ifndef ESC_e
#define ESC_e 27
#endif

#ifndef ESC_f
#define ESC_f '\f'
#endif

#ifndef ESC_n
#define ESC_n '\n'
#endif

#ifndef ESC_r
#define ESC_r '\r'
#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'
#endif

/* Codes for different types of Unicode property */

#define PT_ANY        0    /* Any property - matches all chars */
#define PT_LAMP       1    /* L& - the union of Lu, Ll, Lt */
#define PT_GC         2    /* General characteristic (e.g. L) */
#define PT_PC         3    /* Particular characteristic (e.g. Lu) */
#define PT_SC         4    /* Script (e.g. Han) */

/* Flag bits and data types for the extended class (OP_XCLASS) for classes that
contain UTF-8 characters with values greater than 255. */

#define XCL_NOT    0x01    /* Flag: this is a negative class */
#define XCL_MAP    0x02    /* Flag: a 32-byte map is present */

#define XCL_END       0    /* Marks end of individual items */
#define XCL_SINGLE    1    /* Single item (one multibyte char) follows */
#define XCL_RANGE     2    /* A range (two multibyte chars) follows */
#define XCL_PROP      3    /* Unicode property (2-byte property code follows) */
#define XCL_NOTPROP   4    /* Unicode inverted property (ditto) */

/* These are escaped items that aren't just an encoding of a particular data
value such as \n. They must have non-zero values, as check_escape() returns
their negation. Also, they must appear in the same order as in the opcode
definitions below, up to ESC_z. There's a dummy for OP_ANY because it
corresponds to "." rather than an escape sequence. The final one must be
ESC_REF as subsequent values are used for backreferences (\1, \2, \3, etc).
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. */

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_dum1, 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_k, ESC_REF };


/* Opcode table: Starting from 1 (i.e. after OP_END), the values up to
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
"coptable" in pcre_dfa_exec.c that must be updated. */

enum {
  OP_END,            /* 0 End of pattern */

  /* Values corresponding to backslashed metacharacters */

  OP_SOD,            /* 1 Start of data: \A */
  OP_SOM,            /* 2 Start of match (subject + offset): \G */
  OP_SET_SOM,        /* 3 Set start of match (\K) */
  OP_NOT_WORD_BOUNDARY,  /*  4 \B */
  OP_WORD_BOUNDARY,      /*  5 \b */
  OP_NOT_DIGIT,          /*  6 \D */
  OP_DIGIT,              /*  7 \d */
  OP_NOT_WHITESPACE,     /*  8 \S */
  OP_WHITESPACE,         /*  9 \s */
  OP_NOT_WORDCHAR,       /* 10 \W */
  OP_WORDCHAR,           /* 11 \w */
  OP_ANY,            /* 12 Match any character */
  OP_ANYBYTE,        /* 13 Match any byte (\C); different to OP_ANY for UTF-8 */
  OP_NOTPROP,        /* 14 \P (not Unicode property) */
  OP_PROP,           /* 15 \p (Unicode property) */
  OP_ANYNL,          /* 16 \R (any newline sequence) */
  OP_NOT_HSPACE,     /* 17 \H (not horizontal whitespace) */
  OP_HSPACE,         /* 18 \h (horizontal whitespace) */
  OP_NOT_VSPACE,     /* 19 \V (not vertical whitespace) */
  OP_VSPACE,         /* 20 \v (vertical whitespace) */
  OP_EXTUNI,         /* 21 \X (extended Unicode sequence */
  OP_EODN,           /* 22 End of data or \n at end of data: \Z. */
  OP_EOD,            /* 23 End of data: \z */

  OP_OPT,            /* 24 Set runtime options */
  OP_CIRC,           /* 25 Start of line - varies with multiline switch */
  OP_DOLL,           /* 26 End of line - varies with multiline switch */
  OP_CHAR,           /* 27 Match one character, casefully */
  OP_CHARNC,         /* 28 Match one character, caselessly */
  OP_NOT,            /* 29 Match one character, not the following one */

  OP_STAR,           /* 30 The maximizing and minimizing versions of */
  OP_MINSTAR,        /* 31 these six opcodes must come in pairs, with */
  OP_PLUS,           /* 32 the minimizing one second. */
  OP_MINPLUS,        /* 33 This first set applies to single characters.*/
  OP_QUERY,          /* 34 */
  OP_MINQUERY,       /* 35 */

  OP_UPTO,           /* 36 From 0 to n matches */
  OP_MINUPTO,        /* 37 */
  OP_EXACT,          /* 38 Exactly n matches */

  OP_POSSTAR,        /* 39 Possessified star */
  OP_POSPLUS,        /* 40 Possessified plus */
  OP_POSQUERY,       /* 41 Posesssified query */
  OP_POSUPTO,        /* 42 Possessified upto */

  OP_NOTSTAR,        /* 43 The maximizing and minimizing versions of */
  OP_NOTMINSTAR,     /* 44 these six opcodes must come in pairs, with */
  OP_NOTPLUS,        /* 45 the minimizing one second. They must be in */
  OP_NOTMINPLUS,     /* 46 exactly the same order as those above. */
  OP_NOTQUERY,       /* 47 This set applies to "not" single characters. */
  OP_NOTMINQUERY,    /* 48 */

  OP_NOTUPTO,        /* 49 From 0 to n matches */
  OP_NOTMINUPTO,     /* 50 */
  OP_NOTEXACT,       /* 51 Exactly n matches */

  OP_NOTPOSSTAR,     /* 52 Possessified versions */
  OP_NOTPOSPLUS,     /* 53 */
  OP_NOTPOSQUERY,    /* 54 */
  OP_NOTPOSUPTO,     /* 55 */

  OP_TYPESTAR,       /* 56 The maximizing and minimizing versions of */
  OP_TYPEMINSTAR,    /* 57 these six opcodes must come in pairs, with */
  OP_TYPEPLUS,       /* 58 the minimizing one second. These codes must */
  OP_TYPEMINPLUS,    /* 59 be in exactly the same order as those above. */
  OP_TYPEQUERY,      /* 60 This set applies to character types such as \d */
  OP_TYPEMINQUERY,   /* 61 */

  OP_TYPEUPTO,       /* 62 From 0 to n matches */
  OP_TYPEMINUPTO,    /* 63 */
  OP_TYPEEXACT,      /* 64 Exactly n matches */

  OP_TYPEPOSSTAR,    /* 65 Possessified versions */
  OP_TYPEPOSPLUS,    /* 66 */
  OP_TYPEPOSQUERY,   /* 67 */
  OP_TYPEPOSUPTO,    /* 68 */

  OP_CRSTAR,         /* 69 The maximizing and minimizing versions of */
  OP_CRMINSTAR,      /* 70 all these opcodes must come in pairs, with */
  OP_CRPLUS,         /* 71 the minimizing one second. These codes must */
  OP_CRMINPLUS,      /* 72 be in exactly the same order as those above. */
  OP_CRQUERY,        /* 73 These are for character classes and back refs */
  OP_CRMINQUERY,     /* 74 */
  OP_CRRANGE,        /* 75 These are different to the three sets above. */
  OP_CRMINRANGE,     /* 76 */

  OP_CLASS,          /* 77 Match a character class, chars < 256 only */
  OP_NCLASS,         /* 78 Same, but the bitmap was created from a negative
                           class - the difference is relevant only when a UTF-8
                           character > 255 is encountered. */

  OP_XCLASS,         /* 79 Extended class for handling UTF-8 chars within the
                           class. This does both positive and negative. */

  OP_REF,            /* 80 Match a back reference */
  OP_RECURSE,        /* 81 Match a numbered subpattern (possibly recursive) */
  OP_CALLOUT,        /* 82 Call out to external function if provided */

  OP_ALT,            /* 83 Start of alternation */
  OP_KET,            /* 84 End of group that doesn't have an unbounded repeat */
  OP_KETRMAX,        /* 85 These two must remain together and in this */
  OP_KETRMIN,        /* 86 order. They are for groups the repeat for ever. */

  /* The assertions must come before BRA, CBRA, ONCE, and COND.*/

  OP_ASSERT,         /* 87 Positive lookahead */
  OP_ASSERT_NOT,     /* 88 Negative lookahead */
  OP_ASSERTBACK,     /* 89 Positive lookbehind */
  OP_ASSERTBACK_NOT, /* 90 Negative lookbehind */
  OP_REVERSE,        /* 91 Move pointer back - used in lookbehind assertions */

  /* ONCE, BRA, CBRA, and COND must come after the assertions, with ONCE first,
  as there's a test for >= ONCE for a subpattern that isn't an assertion. */

  OP_ONCE,           /* 92 Atomic group */
  OP_BRA,            /* 93 Start of non-capturing bracket */
  OP_CBRA,           /* 94 Start of capturing bracket */
  OP_COND,           /* 95 Conditional group */

  /* These three must follow the previous three, in the same order. There's a