/* String search routines for GNU Emacs.
Copyright (C) 1985, 1986, 1987, 1993, 1994, 1997, 1998, 1999, 2001, 2002,
- 2003, 2004, 2005, 2006, 2007, 2008
+ 2003, 2004, 2005, 2006, 2007, 2008, 2009
Free Software Foundation, Inc.
This file is part of GNU Emacs.
immediate_quit = 0;
return val;
}
+\f
+/* Match REGEXP atainst 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
+ indices into the string. This function doesn't modify the match
+ data. */
+
+EMACS_INT
+fast_looking_at (regexp, pos, pos_byte, limit, limit_byte, string)
+ Lisp_Object regexp;
+ EMACS_INT pos, pos_byte, limit, limit_byte;
+ Lisp_Object string;
+{
+ int multibyte;
+ struct re_pattern_buffer *buf;
+ unsigned char *p1, *p2;
+ int s1, s2;
+ EMACS_INT len;
+
+ if (STRINGP (string))
+ {
+ if (pos_byte < 0)
+ pos_byte = string_char_to_byte (string, pos);
+ if (limit_byte < 0)
+ limit_byte = string_char_to_byte (string, limit);
+ p1 = NULL;
+ s1 = 0;
+ p2 = SDATA (string);
+ s2 = SBYTES (string);
+ re_match_object = string;
+ multibyte = STRING_MULTIBYTE (string);
+ }
+ else
+ {
+ if (pos_byte < 0)
+ pos_byte = CHAR_TO_BYTE (pos);
+ if (limit_byte < 0)
+ limit_byte = CHAR_TO_BYTE (limit);
+ pos_byte -= BEGV_BYTE;
+ limit_byte -= BEGV_BYTE;
+ p1 = BEGV_ADDR;
+ s1 = GPT_BYTE - BEGV_BYTE;
+ p2 = GAP_END_ADDR;
+ s2 = ZV_BYTE - GPT_BYTE;
+ if (s1 < 0)
+ {
+ p2 = p1;
+ s2 = ZV_BYTE - BEGV_BYTE;
+ s1 = 0;
+ }
+ if (s2 < 0)
+ {
+ s1 = ZV_BYTE - BEGV_BYTE;
+ s2 = 0;
+ }
+ re_match_object = Qnil;
+ multibyte = ! NILP (current_buffer->enable_multibyte_characters);
+ }
+
+ buf = compile_pattern (regexp, 0, Qnil, 0, multibyte);
+ immediate_quit = 1;
+ len = re_match_2 (buf, (char *) p1, s1, (char *) p2, s2,
+ pos_byte, NULL, limit_byte);
+ immediate_quit = 0;
+
+ return len;
+}
+
\f
/* The newline cache: remembering which sections of text have no newlines. */
XSETBUFFER (last_thing_searched, current_buffer);
}
\f
-/* Given a string of words separated by word delimiters,
- compute a regexp that matches those exact words
- separated by arbitrary punctuation. */
+/* Given STRING, a string of words separated by word delimiters,
+ compute a regexp that matches those exact words separated by
+ arbitrary punctuation. If LAX is nonzero, the end of the string
+ need not match a word boundary unless it ends in whitespace. */
static Lisp_Object
-wordify (string)
+wordify (string, lax)
Lisp_Object string;
+ int lax;
{
register unsigned char *p, *o;
register int i, i_byte, len, punct_count = 0, word_count = 0;
Lisp_Object val;
int prev_c = 0;
- int adjust;
+ int adjust, whitespace_at_end;
CHECK_STRING (string);
p = SDATA (string);
}
if (SYNTAX (prev_c) == Sword)
- word_count++;
+ {
+ word_count++;
+ whitespace_at_end = 0;
+ }
+ else
+ whitespace_at_end = 1;
+
if (!word_count)
return empty_unibyte_string;
- adjust = - punct_count + 5 * (word_count - 1) + 4;
+ adjust = - punct_count + 5 * (word_count - 1)
+ + ((lax && !whitespace_at_end) ? 2 : 4);
if (STRING_MULTIBYTE (string))
val = make_uninit_multibyte_string (len + adjust,
SBYTES (string)
prev_c = c;
}
- *o++ = '\\';
- *o++ = 'b';
+ if (!lax || whitespace_at_end)
+ {
+ *o++ = '\\';
+ *o++ = 'b';
+ }
return val;
}
(string, bound, noerror, count)
Lisp_Object string, bound, noerror, count;
{
- return search_command (wordify (string), bound, noerror, count, -1, 1, 0);
+ return search_command (wordify (string, 0), bound, noerror, count, -1, 1, 0);
}
DEFUN ("word-search-forward", Fword_search_forward, Sword_search_forward, 1, 4,
(string, bound, noerror, count)
Lisp_Object string, bound, noerror, count;
{
- return search_command (wordify (string), bound, noerror, count, 1, 1, 0);
+ return search_command (wordify (string, 0), bound, noerror, count, 1, 1, 0);
+}
+
+DEFUN ("word-search-backward-lax", Fword_search_backward_lax, Sword_search_backward_lax, 1, 4,
+ "sWord search backward: ",
+ doc: /* Search backward from point for STRING, ignoring differences in punctuation.
+Set point to the beginning of the occurrence found, and return point.
+
+Unlike `word-search-backward', the end of STRING need not match a word
+boundary unless it ends in whitespace.
+
+An optional second argument bounds the search; it is a buffer position.
+The match found must not extend before that position.
+Optional third argument, if t, means if fail just return nil (no error).
+ If not nil and not t, move to limit of search and return nil.
+Optional fourth argument is repeat count--search for successive occurrences. */)
+ (string, bound, noerror, count)
+ Lisp_Object string, bound, noerror, count;
+{
+ return search_command (wordify (string, 1), bound, noerror, count, -1, 1, 0);
+}
+
+DEFUN ("word-search-forward-lax", Fword_search_forward_lax, Sword_search_forward_lax, 1, 4,
+ "sWord search: ",
+ doc: /* Search forward from point for STRING, ignoring differences in punctuation.
+Set point to the end of the occurrence found, and return point.
+
+Unlike `word-search-forward', the end of STRING need not match a word
+boundary unless it ends in whitespace.
+
+An optional second argument bounds the search; it is a buffer position.
+The match found must not extend after that position.
+Optional third argument, if t, means if fail just return nil (no error).
+ If not nil and not t, move to limit of search and return nil.
+Optional fourth argument is repeat count--search for successive occurrences. */)
+ (string, bound, noerror, count)
+ Lisp_Object string, bound, noerror, count;
+{
+ return search_command (wordify (string, 1), bound, noerror, count, 1, 1, 0);
}
DEFUN ("re-search-backward", Fre_search_backward, Sre_search_backward, 1, 4,
defsubr (&Ssearch_backward);
defsubr (&Sword_search_forward);
defsubr (&Sword_search_backward);
+ defsubr (&Sword_search_forward_lax);
+ defsubr (&Sword_search_backward_lax);
defsubr (&Sre_search_forward);
defsubr (&Sre_search_backward);
defsubr (&Sposix_search_forward);