/* String search routines for GNU Emacs.
-Copyright (C) 1985-1987, 1993-1994, 1997-1999, 2001-2015 Free Software
+Copyright (C) 1985-1987, 1993-1994, 1997-1999, 2001-2016 Free Software
Foundation, Inc.
This file is part of GNU Emacs.
GNU Emacs is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
+the Free Software Foundation, either version 3 of the License, or (at
+your option) any later version.
GNU Emacs is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
#include <config.h>
#include "lisp.h"
-#include "category.h"
#include "character.h"
#include "buffer.h"
#include "syntax.h"
#include "charset.h"
#include "region-cache.h"
-#include "commands.h"
#include "blockinput.h"
#include "intervals.h"
Qnil if no searching has been done yet. */
static Lisp_Object last_thing_searched;
-/* Error condition signaled when regexp compile_pattern fails. */
-static Lisp_Object Qinvalid_regexp;
-
-/* Error condition used for failing searches. */
-static Lisp_Object Qsearch_failed;
-
static void set_search_regs (ptrdiff_t, ptrdiff_t);
static void save_search_regs (void);
static EMACS_INT simple_search (EMACS_INT, unsigned char *, ptrdiff_t,
return string_match_1 (regexp, string, start, 1);
}
-/* Match REGEXP against STRING, searching all of STRING,
- and return the index of the match, or negative on failure.
- This does not clobber the match data. */
+/* Match REGEXP against STRING using translation table TABLE,
+ searching all of STRING, and return the index of the match,
+ or negative on failure. This does not clobber the match data. */
ptrdiff_t
-fast_string_match (Lisp_Object regexp, Lisp_Object string)
+fast_string_match_internal (Lisp_Object regexp, Lisp_Object string,
+ Lisp_Object table)
{
ptrdiff_t val;
struct re_pattern_buffer *bufp;
- bufp = compile_pattern (regexp, 0, Qnil,
+ bufp = compile_pattern (regexp, 0, table,
0, STRING_MULTIBYTE (string));
immediate_quit = 1;
re_match_object = string;
return val;
}
-/* Like fast_string_match but ignore case. */
-
-ptrdiff_t
-fast_string_match_ignore_case (Lisp_Object regexp, Lisp_Object string)
-{
- ptrdiff_t val;
- struct re_pattern_buffer *bufp;
-
- bufp = compile_pattern (regexp, 0, Vascii_canon_table,
- 0, STRING_MULTIBYTE (string));
- immediate_quit = 1;
- re_match_object = string;
-
- val = re_search (bufp, SSDATA (string),
- SBYTES (string), 0,
- SBYTES (string), 0);
- immediate_quit = 0;
- return val;
-}
-\f
/* Match REGEXP against the characters after POS to LIMIT, and return
the number of matched characters. If STRING is non-nil, match
against the characters in it. In that case, POS and LIMIT are
return shortage;
}
+/* Like above, but always scan from point and report the
+ resulting position in *CHARPOS and *BYTEPOS. */
+
+ptrdiff_t
+scan_newline_from_point (ptrdiff_t count, ptrdiff_t *charpos,
+ ptrdiff_t *bytepos)
+{
+ ptrdiff_t shortage;
+
+ if (count <= 0)
+ *charpos = find_newline (PT, PT_BYTE, BEGV, BEGV_BYTE, count - 1,
+ &shortage, bytepos, 1);
+ else
+ *charpos = find_newline (PT, PT_BYTE, ZV, ZV_BYTE, count,
+ &shortage, bytepos, 1);
+ return shortage;
+}
+
/* Like find_newline, but doesn't allow QUITting and doesn't return
SHORTAGE. */
ptrdiff_t
translation. Otherwise set to zero later. */
int char_base = -1;
bool boyer_moore_ok = 1;
+ USE_SAFE_ALLOCA;
/* MULTIBYTE says whether the text to be searched is multibyte.
We must convert PATTERN to match that, or we will not really
raw_pattern_size_byte
= count_size_as_multibyte (SDATA (string),
raw_pattern_size);
- raw_pattern = alloca (raw_pattern_size_byte + 1);
+ raw_pattern = SAFE_ALLOCA (raw_pattern_size_byte + 1);
copy_text (SDATA (string), raw_pattern,
SCHARS (string), 0, 1);
}
the chosen single-byte character set can possibly match. */
raw_pattern_size = SCHARS (string);
raw_pattern_size_byte = SCHARS (string);
- raw_pattern = alloca (raw_pattern_size + 1);
+ raw_pattern = SAFE_ALLOCA (raw_pattern_size + 1);
copy_text (SDATA (string), raw_pattern,
SBYTES (string), 1, 0);
}
/* Copy and optionally translate the pattern. */
len = raw_pattern_size;
len_byte = raw_pattern_size_byte;
- patbuf = alloca (len * MAX_MULTIBYTE_LENGTH);
+ SAFE_NALLOCA (patbuf, MAX_MULTIBYTE_LENGTH, len);
pat = patbuf;
base_pat = raw_pattern;
if (multibyte)
while (boyer_moore_ok)
{
- if (ASCII_BYTE_P (inverse))
+ if (ASCII_CHAR_P (inverse))
{
if (this_char_base > 0)
boyer_moore_ok = 0;
len_byte = pat - patbuf;
pat = base_pat = patbuf;
- if (boyer_moore_ok)
- return boyer_moore (n, pat, len_byte, trt, inverse_trt,
- pos_byte, lim_byte,
- char_base);
- else
- return simple_search (n, pat, raw_pattern_size, len_byte, trt,
- pos, pos_byte, lim, lim_byte);
+ EMACS_INT result
+ = (boyer_moore_ok
+ ? boyer_moore (n, pat, len_byte, trt, inverse_trt,
+ pos_byte, lim_byte,
+ char_base)
+ : simple_search (n, pat, raw_pattern_size, len_byte, trt,
+ pos, pos_byte, lim, lim_byte));
+ SAFE_FREE ();
+ return result;
}
}
\f
matching with CHAR_BASE are to be checked. */
int ch = -1;
- if (ASCII_BYTE_P (*ptr) || ! multibyte)
+ if (ASCII_CHAR_P (*ptr) || ! multibyte)
ch = *ptr;
else if (char_base
&& ((pat_end - ptr) == 1 || CHAR_HEAD_P (ptr[1])))
{
FETCH_STRING_CHAR_ADVANCE_NO_CHECK (c, newtext, pos, pos_byte);
if (!buf_multibyte)
- c = multibyte_char_to_unibyte (c);
+ c = CHAR_TO_BYTE8 (c);
}
else
{
FETCH_STRING_CHAR_ADVANCE_NO_CHECK (c, newtext,
pos, pos_byte);
if (!buf_multibyte && !ASCII_CHAR_P (c))
- c = multibyte_char_to_unibyte (c);
+ c = CHAR_TO_BYTE8 (c);
}
else
{
}
if (really_changed)
- {
- if (buf_multibyte)
- {
- ptrdiff_t nchars =
- multibyte_chars_in_text (substed, substed_len);
-
- newtext = make_multibyte_string ((char *) substed, nchars,
- substed_len);
- }
- else
- newtext = make_unibyte_string ((char *) substed, substed_len);
- }
+ newtext = make_specified_string ((const char *) substed, -1,
+ substed_len, buf_multibyte);
xfree (substed);
}
regexp.
Value is nil if SUBEXPth pair didn't match, or there were less than
SUBEXP pairs.
-Zero means the entire text matched by the whole regexp or whole string. */)
+Zero means the entire text matched by the whole regexp or whole string.
+
+Return value is undefined if the last search failed. */)
(Lisp_Object subexp)
{
return match_limit (subexp, 1);
regexp.
Value is nil if SUBEXPth pair didn't match, or there were less than
SUBEXP pairs.
-Zero means the entire text matched by the whole regexp or whole string. */)
+Zero means the entire text matched by the whole regexp or whole string.
+
+Return value is undefined if the last search failed. */)
(Lisp_Object subexp)
{
return match_limit (subexp, 0);
}
DEFUN ("match-data", Fmatch_data, Smatch_data, 0, 3, 0,
- doc: /* Return a list containing all info on what the last search matched.
+ doc: /* Return a list describing what the last search matched.
Element 2N is `(match-beginning N)'; element 2N + 1 is `(match-end N)'.
All the elements are markers or nil (nil if the Nth pair didn't match)
if the last match was on a buffer; integers or nil if a string was matched.
Use `set-match-data' to reinstate the data in this list.
If INTEGERS (the optional first argument) is non-nil, always use
-integers \(rather than markers) to represent buffer positions. In
+integers (rather than markers) to represent buffer positions. In
this case, and if the last match was in a buffer, the buffer will get
stored as one additional element at the end of the list.
prev = Qnil;
- data = alloca ((2 * search_regs.num_regs + 1) * sizeof *data);
+ USE_SAFE_ALLOCA;
+ SAFE_NALLOCA (data, 1, 2 * search_regs.num_regs + 1);
len = 0;
for (i = 0; i < search_regs.num_regs; i++)
/* If REUSE is not usable, cons up the values and return them. */
if (! CONSP (reuse))
- return Flist (len, data);
-
- /* If REUSE is a list, store as many value elements as will fit
- into the elements of REUSE. */
- for (i = 0, tail = reuse; CONSP (tail);
- i++, tail = XCDR (tail))
+ reuse = Flist (len, data);
+ else
{
+ /* If REUSE is a list, store as many value elements as will fit
+ into the elements of REUSE. */
+ for (i = 0, tail = reuse; CONSP (tail);
+ i++, tail = XCDR (tail))
+ {
+ if (i < len)
+ XSETCAR (tail, data[i]);
+ else
+ XSETCAR (tail, Qnil);
+ prev = tail;
+ }
+
+ /* If we couldn't fit all value elements into REUSE,
+ cons up the rest of them and add them to the end of REUSE. */
if (i < len)
- XSETCAR (tail, data[i]);
- else
- XSETCAR (tail, Qnil);
- prev = tail;
+ XSETCDR (prev, Flist (len - i, data + i));
}
- /* If we couldn't fit all value elements into REUSE,
- cons up the rest of them and add them to the end of REUSE. */
- if (i < len)
- XSETCDR (prev, Flist (len - i, data + i));
-
+ SAFE_FREE ();
return reuse;
}
CHECK_STRING (string);
- temp = alloca (SBYTES (string) * 2);
+ USE_SAFE_ALLOCA;
+ SAFE_NALLOCA (temp, 2, SBYTES (string));
/* Now copy the data into the new string, inserting escapes. */
*out++ = *in;
}
- return make_specified_string (temp,
- SCHARS (string) + backslashes_added,
- out - temp,
- STRING_MULTIBYTE (string));
+ Lisp_Object result
+ = make_specified_string (temp,
+ SCHARS (string) + backslashes_added,
+ out - temp,
+ STRING_MULTIBYTE (string));
+ SAFE_FREE ();
+ return result;
}
/* Like find_newline, but doesn't use the cache, and only searches forward. */
}
searchbuf_head = &searchbufs[0];
+ /* Error condition used for failing searches. */
DEFSYM (Qsearch_failed, "search-failed");
+
+ /* Error condition signaled when regexp compile_pattern fails. */
DEFSYM (Qinvalid_regexp, "invalid-regexp");
Fput (Qsearch_failed, Qerror_conditions,