Git-Raw
view release on metacpan or search on metacpan
deps/libgit2/deps/pcre/pcre_compile.c view on Meta::CPAN
-ESC_X, 0,
-ESC_Z, CHAR_LEFT_SQUARE_BRACKET,
CHAR_BACKSLASH, CHAR_RIGHT_SQUARE_BRACKET,
CHAR_CIRCUMFLEX_ACCENT, CHAR_UNDERSCORE,
CHAR_GRAVE_ACCENT, ESC_a,
-ESC_b, 0,
-ESC_d, ESC_e,
ESC_f, 0,
-ESC_h, 0,
0, -ESC_k,
0, 0,
ESC_n, 0,
-ESC_p, 0,
ESC_r, -ESC_s,
ESC_tee, 0,
-ESC_v, -ESC_w,
0, 0,
-ESC_z
};
#else
/* This is the "abnormal" table for EBCDIC systems without UTF-8 support. */
static const short int escapes[] = {
/* 48 */ 0, 0, 0, '.', '<', '(', '+', '|',
/* 50 */ '&', 0, 0, 0, 0, 0, 0, 0,
/* 58 */ 0, 0, '!', '$', '*', ')', ';', '~',
/* 60 */ '-', '/', 0, 0, 0, 0, 0, 0,
/* 68 */ 0, 0, '|', ',', '%', '_', '>', '?',
/* 70 */ 0, 0, 0, 0, 0, 0, 0, 0,
/* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"',
/* 80 */ 0, ESC_a, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0,
/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0,
/* 90 */ 0, 0, -ESC_k, 0, 0, ESC_n, 0, -ESC_p,
/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0,
/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0,
/* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0,
/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0,
/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-',
/* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G,
/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0,
/* D0 */ '}', 0, -ESC_K, 0, 0,-ESC_N, 0, -ESC_P,
/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0,
/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X,
/* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0,
/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0,
/* F8 */ 0, 0, 0, 0, 0, 0, 0, 0
};
/* We also need a table of characters that may follow \c in an EBCDIC
environment for characters 0-31. */
static unsigned char ebcdic_escape_c[] = "@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_";
#endif
/* Table of special "verbs" like (*PRUNE). This is a short table, so it is
searched linearly. Put all the names into a single string, in order to reduce
the number of relocations when a shared library is dynamically linked. The
string is built from string macros so that it works in UTF-8 mode on EBCDIC
platforms. */
typedef struct verbitem {
int len; /* Length of verb name */
int op; /* Op when no arg, or -1 if arg mandatory */
int op_arg; /* Op when arg present, or -1 if not allowed */
} verbitem;
static const char verbnames[] =
"\0" /* Empty name is a shorthand for MARK */
STRING_MARK0
STRING_ACCEPT0
STRING_COMMIT0
STRING_F0
STRING_FAIL0
STRING_PRUNE0
STRING_SKIP0
STRING_THEN;
static const verbitem verbs[] = {
{ 0, -1, OP_MARK },
{ 4, -1, OP_MARK },
{ 6, OP_ACCEPT, -1 },
{ 6, OP_COMMIT, -1 },
{ 1, OP_FAIL, -1 },
{ 4, OP_FAIL, -1 },
{ 5, OP_PRUNE, OP_PRUNE_ARG },
{ 4, OP_SKIP, OP_SKIP_ARG },
{ 4, OP_THEN, OP_THEN_ARG }
};
static const int verbcount = sizeof(verbs)/sizeof(verbitem);
/* Substitutes for [[:<:]] and [[:>:]], which mean start and end of word in
another regex library. */
static const pcre_uchar sub_start_of_word[] = {
CHAR_BACKSLASH, CHAR_b, CHAR_LEFT_PARENTHESIS, CHAR_QUESTION_MARK,
CHAR_EQUALS_SIGN, CHAR_BACKSLASH, CHAR_w, CHAR_RIGHT_PARENTHESIS, '\0' };
static const pcre_uchar sub_end_of_word[] = {
CHAR_BACKSLASH, CHAR_b, CHAR_LEFT_PARENTHESIS, CHAR_QUESTION_MARK,
CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN, CHAR_BACKSLASH, CHAR_w,
CHAR_RIGHT_PARENTHESIS, '\0' };
/* Tables of names of POSIX character classes and their lengths. The names are
now all in a single string, to reduce the number of relocations when a shared
library is dynamically loaded. The list of lengths is terminated by a zero
length entry. The first three must be alpha, lower, upper, as this is assumed
for handling case independence. The indices for graph, print, and punct are
needed, so identify them. */
static const char posix_names[] =
STRING_alpha0 STRING_lower0 STRING_upper0 STRING_alnum0
STRING_ascii0 STRING_blank0 STRING_cntrl0 STRING_digit0
STRING_graph0 STRING_print0 STRING_punct0 STRING_space0
STRING_word0 STRING_xdigit;
static const pcre_uint8 posix_name_lengths[] = {
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 };
#define PC_GRAPH 8
#define PC_PRINT 9
#define PC_PUNCT 10
/* Table of class bit maps for each POSIX class. Each class is formed from a
base map, with an optional addition or removal of another map. Then, for some
classes, there is some additional tweaking: for [:blank:] the vertical space
characters are removed, and for [:alpha:] and [:alnum:] the underscore
character is removed. The triples in the table consist of the base map offset,
second map offset or -1 if no second map, and a non-negative value for map
addition or a negative value for map subtraction (if there are two maps). The
absolute value of the third field has these meanings: 0 => no tweaking, 1 =>
remove vertical space characters, 2 => remove underscore. */
static const int posix_class_maps[] = {
cbit_word, cbit_digit, -2, /* alpha */
cbit_lower, -1, 0, /* lower */
cbit_upper, -1, 0, /* upper */
cbit_word, -1, 2, /* alnum - word without underscore */
cbit_print, cbit_cntrl, 0, /* ascii */
cbit_space, -1, 1, /* blank - a GNU extension */
cbit_cntrl, -1, 0, /* cntrl */
cbit_digit, -1, 0, /* digit */
cbit_graph, -1, 0, /* graph */
cbit_print, -1, 0, /* print */
cbit_punct, -1, 0, /* punct */
cbit_space, -1, 0, /* space */
cbit_word, -1, 0, /* word - a Perl extension */
cbit_xdigit,-1, 0 /* xdigit */
};
/* Table of substitutes for \d etc when PCRE_UCP is set. They are replaced by
Unicode property escapes. */
#ifdef SUPPORT_UCP
static const pcre_uchar string_PNd[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_pNd[] = {
CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PXsp[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_pXsp[] = {
deps/libgit2/deps/pcre/pcre_compile.c view on Meta::CPAN
CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PL[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PLl[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PLu[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PXan[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_H[] = {
CHAR_BACKSLASH, CHAR_H, '\0' };
static const pcre_uchar string_PXps[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar *posix_substitutes[] = {
string_pL, /* alpha */
string_pLl, /* lower */
string_pLu, /* upper */
string_pXan, /* alnum */
NULL, /* ascii */
string_h, /* blank */
NULL, /* cntrl */
string_pNd, /* digit */
NULL, /* graph */
NULL, /* print */
NULL, /* punct */
string_pXps, /* space */ /* Xps is POSIX space, but from 8.34 */
string_pXwd, /* word */ /* Perl and POSIX space are the same */
NULL, /* xdigit */
/* Negated cases */
string_PL, /* ^alpha */
string_PLl, /* ^lower */
string_PLu, /* ^upper */
string_PXan, /* ^alnum */
NULL, /* ^ascii */
string_H, /* ^blank */
NULL, /* ^cntrl */
string_PNd, /* ^digit */
NULL, /* ^graph */
NULL, /* ^print */
NULL, /* ^punct */
string_PXps, /* ^space */ /* Xps is POSIX space, but from 8.34 */
string_PXwd, /* ^word */ /* Perl and POSIX space are the same */
NULL /* ^xdigit */
};
#define POSIX_SUBSIZE (sizeof(posix_substitutes) / sizeof(pcre_uchar *))
#endif
#define STRING(a) # a
#define XSTRING(s) STRING(s)
/* The texts of compile-time error messages. These are "char *" because they
are passed to the outside world. Do not ever re-use any error number, because
they are documented. Always add a new error instead. Messages marked DEAD below
are no longer used. This used to be a table of strings, but in order to reduce
the number of relocations needed when a shared library is loaded dynamically,
it is now one long string. We cannot use a table of offsets, because the
lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we
simply count through to the one we want - this isn't a performance issue
because these strings are used only when there is a compilation error.
Each substring ends with \0 to insert a null character. This includes the final
substring, so that the whole string ends with \0\0, which can be detected when
counting through. */
static const char error_texts[] =
"no error\0"
"\\ at end of pattern\0"
"\\c at end of pattern\0"
"unrecognized character follows \\\0"
"numbers out of order in {} quantifier\0"
/* 5 */
"number too big in {} quantifier\0"
"missing terminating ] for character class\0"
"invalid escape sequence in character class\0"
"range out of order in character class\0"
"nothing to repeat\0"
/* 10 */
"internal error: invalid forward reference offset\0"
"internal error: unexpected repeat\0"
"unrecognized character after (? or (?-\0"
"POSIX named classes are supported only within a class\0"
"missing )\0"
/* 15 */
"reference to non-existent subpattern\0"
"erroffset passed as NULL\0"
"unknown option bit(s) set\0"
"missing ) after comment\0"
"parentheses nested too deeply\0" /** DEAD **/
/* 20 */
"regular expression is too large\0"
"failed to get memory\0"
"unmatched parentheses\0"
"internal error: code overflow\0"
"unrecognized character after (?<\0"
/* 25 */
"lookbehind assertion is not fixed length\0"
"malformed number or name after (?(\0"
"conditional group contains more than two branches\0"
"assertion expected after (?( or (?(?C)\0"
"(?R or (?[+-]digits must be followed by )\0"
/* 30 */
"unknown POSIX class name\0"
"POSIX collating elements are not supported\0"
"this version of PCRE is compiled without UTF support\0"
"spare error\0" /** DEAD **/
"character value in \\x{} or \\o{} is too large\0"
/* 35 */
"invalid condition (?(0)\0"
"\\C not allowed in lookbehind assertion\0"
"PCRE does not support \\L, \\l, \\N{name}, \\U, or \\u\0"
"number after (?C is > 255\0"
"closing ) for (?C expected\0"
/* 40 */
"recursive call could loop indefinitely\0"
"unrecognized character after (?P\0"
deps/libgit2/deps/pcre/pcre_compile.c view on Meta::CPAN
because all relevant opcodes are less than that. */
static const pcre_uint8 opcode_possessify[] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 15 */
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16 - 31 */
0, /* NOTI */
OP_POSSTAR, 0, /* STAR, MINSTAR */
OP_POSPLUS, 0, /* PLUS, MINPLUS */
OP_POSQUERY, 0, /* QUERY, MINQUERY */
OP_POSUPTO, 0, /* UPTO, MINUPTO */
0, /* EXACT */
0, 0, 0, 0, /* POS{STAR,PLUS,QUERY,UPTO} */
OP_POSSTARI, 0, /* STARI, MINSTARI */
OP_POSPLUSI, 0, /* PLUSI, MINPLUSI */
OP_POSQUERYI, 0, /* QUERYI, MINQUERYI */
OP_POSUPTOI, 0, /* UPTOI, MINUPTOI */
0, /* EXACTI */
0, 0, 0, 0, /* POS{STARI,PLUSI,QUERYI,UPTOI} */
OP_NOTPOSSTAR, 0, /* NOTSTAR, NOTMINSTAR */
OP_NOTPOSPLUS, 0, /* NOTPLUS, NOTMINPLUS */
OP_NOTPOSQUERY, 0, /* NOTQUERY, NOTMINQUERY */
OP_NOTPOSUPTO, 0, /* NOTUPTO, NOTMINUPTO */
0, /* NOTEXACT */
0, 0, 0, 0, /* NOTPOS{STAR,PLUS,QUERY,UPTO} */
OP_NOTPOSSTARI, 0, /* NOTSTARI, NOTMINSTARI */
OP_NOTPOSPLUSI, 0, /* NOTPLUSI, NOTMINPLUSI */
OP_NOTPOSQUERYI, 0, /* NOTQUERYI, NOTMINQUERYI */
OP_NOTPOSUPTOI, 0, /* NOTUPTOI, NOTMINUPTOI */
0, /* NOTEXACTI */
0, 0, 0, 0, /* NOTPOS{STARI,PLUSI,QUERYI,UPTOI} */
OP_TYPEPOSSTAR, 0, /* TYPESTAR, TYPEMINSTAR */
OP_TYPEPOSPLUS, 0, /* TYPEPLUS, TYPEMINPLUS */
OP_TYPEPOSQUERY, 0, /* TYPEQUERY, TYPEMINQUERY */
OP_TYPEPOSUPTO, 0, /* TYPEUPTO, TYPEMINUPTO */
0, /* TYPEEXACT */
0, 0, 0, 0, /* TYPEPOS{STAR,PLUS,QUERY,UPTO} */
OP_CRPOSSTAR, 0, /* CRSTAR, CRMINSTAR */
OP_CRPOSPLUS, 0, /* CRPLUS, CRMINPLUS */
OP_CRPOSQUERY, 0, /* CRQUERY, CRMINQUERY */
OP_CRPOSRANGE, 0, /* CRRANGE, CRMINRANGE */
0, 0, 0, 0, /* CRPOS{STAR,PLUS,QUERY,RANGE} */
0, 0, 0, /* CLASS, NCLASS, XCLASS */
0, 0, /* REF, REFI */
0, 0, /* DNREF, DNREFI */
0, 0 /* RECURSE, CALLOUT */
};
/*************************************************
* Find an error text *
*************************************************/
/* The error texts are now all in one long string, to save on relocations. As
some of the text is of unknown length, we can't use a table of offsets.
Instead, just count through the strings. This is not a performance issue
because it happens only when there has been a compilation error.
Argument: the error number
Returns: pointer to the error string
*/
static const char *
find_error_text(int n)
{
const char *s = error_texts;
for (; n > 0; n--)
{
while (*s++ != CHAR_NULL) {};
if (*s == CHAR_NULL) return "Error text not found (please report)";
}
return s;
}
/*************************************************
* Expand the workspace *
*************************************************/
/* This function is called during the second compiling phase, if the number of
forward references fills the existing workspace, which is originally a block on
the stack. A larger block is obtained from malloc() unless the ultimate limit
has been reached or the increase will be rather small.
Argument: pointer to the compile data block
Returns: 0 if all went well, else an error number
*/
static int
expand_workspace(compile_data *cd)
{
pcre_uchar *newspace;
int newsize = cd->workspace_size * 2;
if (newsize > COMPILE_WORK_SIZE_MAX) newsize = COMPILE_WORK_SIZE_MAX;
if (cd->workspace_size >= COMPILE_WORK_SIZE_MAX ||
newsize - cd->workspace_size < WORK_SIZE_SAFETY_MARGIN)
return ERR72;
newspace = (PUBL(malloc))(IN_UCHARS(newsize));
if (newspace == NULL) return ERR21;
memcpy(newspace, cd->start_workspace, cd->workspace_size * sizeof(pcre_uchar));
cd->hwm = (pcre_uchar *)newspace + (cd->hwm - cd->start_workspace);
if (cd->workspace_size > COMPILE_WORK_SIZE)
(PUBL(free))((void *)cd->start_workspace);
cd->start_workspace = newspace;
cd->workspace_size = newsize;
return 0;
}
/*************************************************
( run in 0.679 second using v1.01-cache-2.11-cpan-84de2e75c66 )