version 0.12.
(Implements POSIX draft P1003.2/D11.2, except for some of the
internationalization features.)
- Copyright (C) 1993-1999, 2000, 2001 Free Software Foundation, Inc.
+ Copyright (C) 1993-1999, 2000, 2001, 2002 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
routines with an "x" prefix so they do not collide with the native regex
routines or with other components regex routines. */
/* AIX requires this to be the first thing in the file. */
-#if defined _AIX && !defined REGEX_MALLOC
+#if defined _AIX && !defined __GNUC__ && !defined REGEX_MALLOC
#pragma alloca
#endif
# include <config.h>
#endif
+#include <ansidecl.h>
+
#ifndef PARAMS
# if defined __GNUC__ || (defined __STDC__ && __STDC__)
# define PARAMS(args) args
# endif
/* This is for other GNU distributions with internationalized messages. */
-# if HAVE_LIBINTL_H || defined _LIBC
+# if (HAVE_LIBINTL_H && ENABLE_NLS) || defined _LIBC
# include <libintl.h>
# ifdef _LIBC
# undef gettext
# endif /* emacs */
\f
/* Integer type for pointers. */
-# if !defined _LIBC
+# if !defined _LIBC && !defined HAVE_UINTPTR_T
typedef unsigned long int uintptr_t;
# endif
static reg_errcode_t byte_regex_compile _RE_ARGS ((const char *pattern, size_t size,
reg_syntax_t syntax,
struct re_pattern_buffer *bufp));
-static reg_errcode_t wcs_regex_compile _RE_ARGS ((const char *pattern, size_t size,
- reg_syntax_t syntax,
- struct re_pattern_buffer *bufp));
static int byte_re_match_2_internal PARAMS ((struct re_pattern_buffer *bufp,
const char *string1, int size1,
int pos,
struct re_registers *regs,
int stop));
+static int byte_re_search_2 PARAMS ((struct re_pattern_buffer *bufp,
+ const char *string1, int size1,
+ const char *string2, int size2,
+ int startpos, int range,
+ struct re_registers *regs, int stop));
+static int byte_re_compile_fastmap PARAMS ((struct re_pattern_buffer *bufp));
+
+#ifdef MBS_SUPPORT
+static reg_errcode_t wcs_regex_compile _RE_ARGS ((const char *pattern, size_t size,
+ reg_syntax_t syntax,
+ struct re_pattern_buffer *bufp));
+
+
static int wcs_re_match_2_internal PARAMS ((struct re_pattern_buffer *bufp,
const char *cstring1, int csize1,
const char *cstring2, int csize2,
wchar_t *string1, int size1,
wchar_t *string2, int size2,
int *mbs_offset1, int *mbs_offset2));
-static int byte_re_search_2 PARAMS ((struct re_pattern_buffer *bufp,
- const char *string1, int size1,
- const char *string2, int size2,
- int startpos, int range,
- struct re_registers *regs, int stop));
static int wcs_re_search_2 PARAMS ((struct re_pattern_buffer *bufp,
const char *string1, int size1,
const char *string2, int size2,
int startpos, int range,
struct re_registers *regs, int stop));
-static int byte_re_compile_fastmap PARAMS ((struct re_pattern_buffer *bufp));
static int wcs_re_compile_fastmap PARAMS ((struct re_pattern_buffer *bufp));
-
+#endif
\f
/* These are the command codes that appear in compiled regular
expressions. Some opcodes are followed by argument bytes. A
# define UCHAR_T unsigned char
# define COMPILED_BUFFER_VAR bufp->buffer
# define OFFSET_ADDRESS_SIZE 2
-# define PREFIX(name) byte_##name
+# if defined (__STDC__) || defined (ALMOST_STDC) || defined (HAVE_STRINGIZE)
+# define PREFIX(name) byte_##name
+# else
+# define PREFIX(name) byte_/**/name
+# endif
# define ARG_PREFIX(name) name
# define PUT_CHAR(c) putchar (c)
-#elif defined WCHAR
-# define CHAR_T wchar_t
-# define UCHAR_T wchar_t
-# define COMPILED_BUFFER_VAR wc_buffer
-# define OFFSET_ADDRESS_SIZE 1 /* the size which STORE_NUMBER macro use */
-# define CHAR_CLASS_SIZE ((__alignof__(wctype_t)+sizeof(wctype_t))/sizeof(CHAR_T)+1)
-# define PREFIX(name) wcs_##name
-# define ARG_PREFIX(name) c##name
-/* Should we use wide stream?? */
-# define PUT_CHAR(c) printf ("%C", c);
-# define TRUE 1
-# define FALSE 0
#else
-# ifdef MBS_SUPPORT
-# define WCHAR
+# ifdef WCHAR
+# define CHAR_T wchar_t
+# define UCHAR_T wchar_t
+# define COMPILED_BUFFER_VAR wc_buffer
+# define OFFSET_ADDRESS_SIZE 1 /* the size which STORE_NUMBER macro use */
+# define CHAR_CLASS_SIZE ((__alignof__(wctype_t)+sizeof(wctype_t))/sizeof(CHAR_T)+1)
+# if defined (__STDC__) || defined (ALMOST_STDC) || defined (HAVE_STRINGIZE)
+# define PREFIX(name) wcs_##name
+# define ARG_PREFIX(name) c##name
+# else
+# define PREFIX(name) wcs_/**/name
+# define ARG_PREFIX(name) c/**/name
+# endif
+/* Should we use wide stream?? */
+# define PUT_CHAR(c) printf ("%C", c);
+# define TRUE 1
+# define FALSE 0
+# else
+# ifdef MBS_SUPPORT
+# define WCHAR
+# define INSIDE_RECURSION
+# include "regex.c"
+# undef INSIDE_RECURSION
+# endif
+# define BYTE
# define INSIDE_RECURSION
# include "regex.c"
# undef INSIDE_RECURSION
# endif
-# define BYTE
-# define INSIDE_RECURSION
-# include "regex.c"
-# undef INSIDE_RECURSION
#endif
#ifdef INSIDE_RECURSION
for( ; mb_remain > 0 ; ++wc_count, ++pdest, mb_remain -= consumed,
psrc += consumed)
{
+#ifdef _LIBC
+ consumed = __mbrtowc (pdest, psrc, mb_remain, &mbs);
+#else
consumed = mbrtowc (pdest, psrc, mb_remain, &mbs);
+#endif
if (consumed <= 0)
/* failed to convert. maybe src contains binary data.
POSIX doesn't require that we do anything for REG_NOERROR,
but why not be nice? */
-static const char re_error_msgid[] =
+static const char *re_error_msgid[] =
{
-# define REG_NOERROR_IDX 0
- gettext_noop ("Success") /* REG_NOERROR */
- "\0"
-# define REG_NOMATCH_IDX (REG_NOERROR_IDX + sizeof "Success")
- gettext_noop ("No match") /* REG_NOMATCH */
- "\0"
-# define REG_BADPAT_IDX (REG_NOMATCH_IDX + sizeof "No match")
- gettext_noop ("Invalid regular expression") /* REG_BADPAT */
- "\0"
-# define REG_ECOLLATE_IDX (REG_BADPAT_IDX + sizeof "Invalid regular expression")
- gettext_noop ("Invalid collation character") /* REG_ECOLLATE */
- "\0"
-# define REG_ECTYPE_IDX (REG_ECOLLATE_IDX + sizeof "Invalid collation character")
- gettext_noop ("Invalid character class name") /* REG_ECTYPE */
- "\0"
-# define REG_EESCAPE_IDX (REG_ECTYPE_IDX + sizeof "Invalid character class name")
- gettext_noop ("Trailing backslash") /* REG_EESCAPE */
- "\0"
-# define REG_ESUBREG_IDX (REG_EESCAPE_IDX + sizeof "Trailing backslash")
- gettext_noop ("Invalid back reference") /* REG_ESUBREG */
- "\0"
-# define REG_EBRACK_IDX (REG_ESUBREG_IDX + sizeof "Invalid back reference")
- gettext_noop ("Unmatched [ or [^") /* REG_EBRACK */
- "\0"
-# define REG_EPAREN_IDX (REG_EBRACK_IDX + sizeof "Unmatched [ or [^")
- gettext_noop ("Unmatched ( or \\(") /* REG_EPAREN */
- "\0"
-# define REG_EBRACE_IDX (REG_EPAREN_IDX + sizeof "Unmatched ( or \\(")
- gettext_noop ("Unmatched \\{") /* REG_EBRACE */
- "\0"
-# define REG_BADBR_IDX (REG_EBRACE_IDX + sizeof "Unmatched \\{")
- gettext_noop ("Invalid content of \\{\\}") /* REG_BADBR */
- "\0"
-# define REG_ERANGE_IDX (REG_BADBR_IDX + sizeof "Invalid content of \\{\\}")
- gettext_noop ("Invalid range end") /* REG_ERANGE */
- "\0"
-# define REG_ESPACE_IDX (REG_ERANGE_IDX + sizeof "Invalid range end")
- gettext_noop ("Memory exhausted") /* REG_ESPACE */
- "\0"
-# define REG_BADRPT_IDX (REG_ESPACE_IDX + sizeof "Memory exhausted")
- gettext_noop ("Invalid preceding regular expression") /* REG_BADRPT */
- "\0"
-# define REG_EEND_IDX (REG_BADRPT_IDX + sizeof "Invalid preceding regular expression")
- gettext_noop ("Premature end of regular expression") /* REG_EEND */
- "\0"
-# define REG_ESIZE_IDX (REG_EEND_IDX + sizeof "Premature end of regular expression")
- gettext_noop ("Regular expression too big") /* REG_ESIZE */
- "\0"
-# define REG_ERPAREN_IDX (REG_ESIZE_IDX + sizeof "Regular expression too big")
+ gettext_noop ("Success"), /* REG_NOERROR */
+ gettext_noop ("No match"), /* REG_NOMATCH */
+ gettext_noop ("Invalid regular expression"), /* REG_BADPAT */
+ gettext_noop ("Invalid collation character"), /* REG_ECOLLATE */
+ gettext_noop ("Invalid character class name"), /* REG_ECTYPE */
+ gettext_noop ("Trailing backslash"), /* REG_EESCAPE */
+ gettext_noop ("Invalid back reference"), /* REG_ESUBREG */
+ gettext_noop ("Unmatched [ or [^"), /* REG_EBRACK */
+ gettext_noop ("Unmatched ( or \\("), /* REG_EPAREN */
+ gettext_noop ("Unmatched \\{"), /* REG_EBRACE */
+ gettext_noop ("Invalid content of \\{\\}"), /* REG_BADBR */
+ gettext_noop ("Invalid range end"), /* REG_ERANGE */
+ gettext_noop ("Memory exhausted"), /* REG_ESPACE */
+ gettext_noop ("Invalid preceding regular expression"), /* REG_BADRPT */
+ gettext_noop ("Premature end of regular expression"), /* REG_EEND */
+ gettext_noop ("Regular expression too big"), /* REG_ESIZE */
gettext_noop ("Unmatched ) or \\)") /* REG_ERPAREN */
};
-
-static const size_t re_error_msgid_idx[] =
- {
- REG_NOERROR_IDX,
- REG_NOMATCH_IDX,
- REG_BADPAT_IDX,
- REG_ECOLLATE_IDX,
- REG_ECTYPE_IDX,
- REG_EESCAPE_IDX,
- REG_ESUBREG_IDX,
- REG_EBRACK_IDX,
- REG_EPAREN_IDX,
- REG_EBRACE_IDX,
- REG_BADBR_IDX,
- REG_ERANGE_IDX,
- REG_ESPACE_IDX,
- REG_BADRPT_IDX,
- REG_EEND_IDX,
- REG_ESIZE_IDX,
- REG_ERPAREN_IDX
- };
\f
#endif /* INSIDE_RECURSION */
/* First compare the hashing value. */
if (symb_table[2 * elem] == hash
&& c1 == extra[symb_table[2 * elem + 1]]
- && memcmp (str,
+ && memcmp (char_str,
&extra[symb_table[2 * elem + 1]
+ 1], c1) == 0)
{
in the table. */
idx += 1 + extra[idx];
/* Adjust for the alignment. */
- idx = (idx + 3) & ~4;
+ idx = (idx + 3) & ~3;
str[0] = (wchar_t) idx + 4;
}
truncate_wchar (c)
CHAR_T c;
{
- unsigned char buf[MB_LEN_MAX];
- int retval = wctomb(buf, c);
- return retval > 0 ? buf[0] : (unsigned char)c;
+ unsigned char buf[MB_CUR_MAX];
+ mbstate_t state;
+ int retval;
+ memset (&state, '\0', sizeof (state));
+# ifdef _LIBC
+ retval = __wcrtomb (buf, c, &state);
+# else
+ retval = wcrtomb (buf, c, &state);
+# endif
+ return retval > 0 ? buf[0] : (unsigned char) c;
}
#endif /* WCHAR */
while (1)
{
- if (p == pend || *p == succeed)
+ if (p == pend || *p == (UCHAR_T) succeed)
{
/* We have reached the (effective) end of pattern. */
if (!FAIL_STACK_EMPTY ())
#endif
#ifdef WCHAR
-# define FREE_WCS_BUFFERS() \
- do { \
- FREE_VAR (string1); \
- FREE_VAR (string2); \
- FREE_VAR (mbs_offset1); \
- FREE_VAR (mbs_offset2); \
+# define MAX_ALLOCA_SIZE 2000
+
+# define FREE_WCS_BUFFERS() \
+ do { \
+ if (size1 > MAX_ALLOCA_SIZE) \
+ { \
+ free (wcs_string1); \
+ free (mbs_offset1); \
+ } \
+ else \
+ { \
+ FREE_VAR (wcs_string1); \
+ FREE_VAR (mbs_offset1); \
+ } \
+ if (size2 > MAX_ALLOCA_SIZE) \
+ { \
+ free (wcs_string2); \
+ free (mbs_offset2); \
+ } \
+ else \
+ { \
+ FREE_VAR (wcs_string2); \
+ FREE_VAR (mbs_offset2); \
+ } \
} while (0)
#endif
+
static int
PREFIX(re_search_2) (bufp, string1, size1, string2, size2, startpos, range,
regs, stop)
fill them with converted string. */
if (size1 != 0)
{
- wcs_string1 = REGEX_TALLOC (size1 + 1, CHAR_T);
- mbs_offset1 = REGEX_TALLOC (size1 + 1, int);
- is_binary = REGEX_TALLOC (size1 + 1, char);
+ if (size1 > MAX_ALLOCA_SIZE)
+ {
+ wcs_string1 = TALLOC (size1 + 1, CHAR_T);
+ mbs_offset1 = TALLOC (size1 + 1, int);
+ is_binary = TALLOC (size1 + 1, char);
+ }
+ else
+ {
+ wcs_string1 = REGEX_TALLOC (size1 + 1, CHAR_T);
+ mbs_offset1 = REGEX_TALLOC (size1 + 1, int);
+ is_binary = REGEX_TALLOC (size1 + 1, char);
+ }
if (!wcs_string1 || !mbs_offset1 || !is_binary)
{
- FREE_VAR (wcs_string1);
- FREE_VAR (mbs_offset1);
- FREE_VAR (is_binary);
+ if (size1 > MAX_ALLOCA_SIZE)
+ {
+ free (wcs_string1);
+ free (mbs_offset1);
+ free (is_binary);
+ }
+ else
+ {
+ FREE_VAR (wcs_string1);
+ FREE_VAR (mbs_offset1);
+ FREE_VAR (is_binary);
+ }
return -2;
}
wcs_size1 = convert_mbs_to_wcs(wcs_string1, string1, size1,
mbs_offset1, is_binary);
wcs_string1[wcs_size1] = L'\0'; /* for a sentinel */
- FREE_VAR (is_binary);
+ if (size1 > MAX_ALLOCA_SIZE)
+ free (is_binary);
+ else
+ FREE_VAR (is_binary);
}
if (size2 != 0)
{
- wcs_string2 = REGEX_TALLOC (size2 + 1, CHAR_T);
- mbs_offset2 = REGEX_TALLOC (size2 + 1, int);
- is_binary = REGEX_TALLOC (size2 + 1, char);
+ if (size2 > MAX_ALLOCA_SIZE)
+ {
+ wcs_string2 = TALLOC (size2 + 1, CHAR_T);
+ mbs_offset2 = TALLOC (size2 + 1, int);
+ is_binary = TALLOC (size2 + 1, char);
+ }
+ else
+ {
+ wcs_string2 = REGEX_TALLOC (size2 + 1, CHAR_T);
+ mbs_offset2 = REGEX_TALLOC (size2 + 1, int);
+ is_binary = REGEX_TALLOC (size2 + 1, char);
+ }
if (!wcs_string2 || !mbs_offset2 || !is_binary)
{
FREE_WCS_BUFFERS ();
- FREE_VAR (is_binary);
+ if (size2 > MAX_ALLOCA_SIZE)
+ free (is_binary);
+ else
+ FREE_VAR (is_binary);
return -2;
}
wcs_size2 = convert_mbs_to_wcs(wcs_string2, string2, size2,
mbs_offset2, is_binary);
wcs_string2[wcs_size2] = L'\0'; /* for a sentinel */
- FREE_VAR (is_binary);
+ if (size2 > MAX_ALLOCA_SIZE)
+ free (is_binary);
+ else
+ FREE_VAR (is_binary);
}
#endif /* WCHAR */
& ~(uintptr_t)(__alignof__(wctype_t) - 1);
wctype = *((wctype_t*)alignedp);
workp += CHAR_CLASS_SIZE;
+# ifdef _LIBC
+ if (__iswctype((wint_t)c, wctype))
+ goto char_set_matched;
+# else
if (iswctype((wint_t)c, wctype))
goto char_set_matched;
+# endif
}
/* match with collating_symbol? */
for (workp2 = workp + coll_symbol_length ; workp < workp2 ;)
{
const CHAR_T *backup_d = d, *backup_dend = dend;
- length = wcslen(workp);
+# ifdef _LIBC
+ length = __wcslen (workp);
+# else
+ length = wcslen (workp);
+# endif
/* If wcscoll(the collating symbol, whole string) > 0,
any substring of the string never match with the
collating symbol. */
- if (wcscoll(workp, d) > 0)
+# ifdef _LIBC
+ if (__wcscoll (workp, d) > 0)
+# else
+ if (wcscoll (workp, d) > 0)
+# endif
{
workp += length + 1;
continue;
str_buf[i] = TRANSLATE(*d);
str_buf[i+1] = '\0';
- match = wcscoll(workp, str_buf);
+# ifdef _LIBC
+ match = __wcscoll (workp, str_buf);
+# else
+ match = wcscoll (workp, str_buf);
+# endif
if (match == 0)
goto char_set_matched;
for (workp2 = workp + equiv_class_length ; workp < workp2 ;)
{
const CHAR_T *backup_d = d, *backup_dend = dend;
- length = wcslen(workp);
+# ifdef _LIBC
+ length = __wcslen (workp);
+# else
+ length = wcslen (workp);
+# endif
/* If wcscoll(the collating symbol, whole string) > 0,
any substring of the string never match with the
collating symbol. */
- if (wcscoll(workp, d) > 0)
+# ifdef _LIBC
+ if (__wcscoll (workp, d) > 0)
+# else
+ if (wcscoll (workp, d) > 0)
+# endif
{
workp += length + 1;
break;
str_buf[i] = TRANSLATE(*d);
str_buf[i+1] = '\0';
- match = wcscoll(workp, str_buf);
+# ifdef _LIBC
+ match = __wcscoll (workp, str_buf);
+# else
+ match = wcscoll (workp, str_buf);
+# endif
if (match == 0)
goto char_set_matched;
}
/* match with char_range? */
-#ifdef _LIBC
+# ifdef _LIBC
if (nrules != 0)
{
uint32_t collseqval;
}
}
else
-#endif
+# endif
{
/* We set range_start_char at str_buf[0], range_end_char
at str_buf[4], and compared char at str_buf[2]. */
range_end_char = str_buf + 4;
}
- if (wcscoll(range_start_char, str_buf+2) <= 0 &&
- wcscoll(str_buf+2, range_end_char) <= 0)
-
+# ifdef _LIBC
+ if (__wcscoll (range_start_char, str_buf+2) <= 0
+ && __wcscoll (str_buf+2, range_end_char) <= 0)
+# else
+ if (wcscoll (range_start_char, str_buf+2) <= 0
+ && wcscoll (str_buf+2, range_end_char) <= 0)
+# endif
goto char_set_matched;
}
}
if (!ret)
return NULL;
- return gettext (re_error_msgid + re_error_msgid_idx[(int) ret]);
+ return gettext (re_error_msgid[(int) ret]);
}
#ifdef _LIBC
weak_alias (__re_compile_pattern, re_compile_pattern)
{
re_comp_buf.buffer = (unsigned char *) malloc (200);
if (re_comp_buf.buffer == NULL)
- return (char *) gettext (re_error_msgid
- + re_error_msgid_idx[(int) REG_ESPACE]);
+ return (char *) gettext (re_error_msgid[(int) REG_ESPACE]);
re_comp_buf.allocated = 200;
re_comp_buf.fastmap = (char *) malloc (1 << BYTEWIDTH);
if (re_comp_buf.fastmap == NULL)
- return (char *) gettext (re_error_msgid
- + re_error_msgid_idx[(int) REG_ESPACE]);
+ return (char *) gettext (re_error_msgid[(int) REG_ESPACE]);
}
/* Since `re_exec' always passes NULL for the `regs' argument, we
return NULL;
/* Yes, we're discarding `const' here if !HAVE_LIBINTL. */
- return (char *) gettext (re_error_msgid + re_error_msgid_idx[(int) ret]);
+ return (char *) gettext (re_error_msgid[(int) ret]);
}
/* Map uppercase characters to corresponding lowercase ones. */
for (i = 0; i < CHAR_SET_SIZE; i++)
- preg->translate[i] = ISUPPER (i) ? TOLOWER (i) : i;
+ preg->translate[i] = ISUPPER (i) ? TOLOWER (i) : (int) i;
}
else
preg->translate = NULL;
size_t
regerror (errcode, preg, errbuf, errbuf_size)
int errcode;
- const regex_t *preg;
+ const regex_t *preg ATTRIBUTE_UNUSED;
char *errbuf;
size_t errbuf_size;
{
size_t msg_size;
if (errcode < 0
- || errcode >= (int) (sizeof (re_error_msgid_idx)
- / sizeof (re_error_msgid_idx[0])))
+ || errcode >= (int) (sizeof (re_error_msgid)
+ / sizeof (re_error_msgid[0])))
/* Only error codes returned by the rest of the code should be passed
to this routine. If we are given anything else, or if other regex
code generates an invalid error code, then the program has a bug.
Dump core so we can fix it. */
abort ();
- msg = gettext (re_error_msgid + re_error_msgid_idx[errcode]);
+ msg = gettext (re_error_msgid[errcode]);
msg_size = strlen (msg) + 1; /* Includes the null. */
if (msg_size > errbuf_size)
{
#if defined HAVE_MEMPCPY || defined _LIBC
- *((char *) __mempcpy (errbuf, msg, errbuf_size - 1)) = '\0';
+ *((char *) mempcpy (errbuf, msg, errbuf_size - 1)) = '\0';
#else
memcpy (errbuf, msg, errbuf_size - 1);
errbuf[errbuf_size - 1] = 0;
projects / deliverable / binutils-gdb.git / blobdiff