/* String search routines for GNU Emacs.
- Copyright (C) 1985-1987, 1993-1994, 1997-1999, 2001-2011
+ Copyright (C) 1985-1987, 1993-1994, 1997-1999, 2001-2012
Free Software Foundation, Inc.
This file is part of GNU Emacs.
Qnil if no searching has been done yet. */
static Lisp_Object last_thing_searched;
-/* error condition signaled when regexp compile_pattern fails */
-
+/* Error condition signaled when regexp compile_pattern fails. */
static Lisp_Object Qinvalid_regexp;
-/* Error condition used for failing searches */
+/* Error condition used for failing searches. */
static Lisp_Object Qsearch_failed;
static void set_search_regs (EMACS_INT, EMACS_INT);
the region from start to cursor is free of them. */
if (target == '\n' && newline_cache)
know_region_cache (current_buffer, newline_cache,
- start_byte + scan_start - base,
- start_byte + cursor - base);
+ BYTE_TO_CHAR (start_byte + scan_start - base),
+ BYTE_TO_CHAR (start_byte + cursor - base));
/* Did we find the target character? */
if (cursor < ceiling_addr)
the region from after the cursor to start is free of them. */
if (target == '\n' && newline_cache)
know_region_cache (current_buffer, newline_cache,
- start_byte + cursor - base,
- start_byte + scan_start - base);
+ BYTE_TO_CHAR (start_byte + cursor - base),
+ BYTE_TO_CHAR (start_byte + scan_start - base));
/* Did we find the target character? */
if (cursor >= ceiling_addr)
checking if we can use boyer-moore search. If TRT is
non-nil, we can use boyer-moore search only if TRT can be
represented by the byte array of 256 elements. For that,
- all non-ASCII case-equivalents of all case-senstive
+ all non-ASCII case-equivalents of all case-sensitive
characters in STRING must belong to the same charset and
row. */
ch = -1;
}
- if (ch >= 0200)
+ if (ch >= 0200 && multibyte)
j = (ch & 0x3F) | 0200;
else
j = *ptr;
while (1)
{
TRANSLATE (ch, inverse_trt, ch);
- if (ch >= 0200)
+ if (ch >= 0200 && multibyte)
j = (ch & 0x3F) | 0200;
else
j = ch;
|| CHAR_HEAD_P (cursor[1]))
&& (CHAR_HEAD_P (cursor[0])
/* Check if this is the last byte of
- a translable character. */
+ a translatable character. */
|| (translate_prev_byte1 == cursor[-1]
&& (CHAR_HEAD_P (translate_prev_byte1)
|| (translate_prev_byte2 == cursor[-2]
|| CHAR_HEAD_P (ptr[1]))
&& (CHAR_HEAD_P (ptr[0])
/* Check if this is the last byte of a
- translable character. */
+ translatable character. */
|| (translate_prev_byte1 == ptr[-1]
&& (CHAR_HEAD_P (translate_prev_byte1)
|| (translate_prev_byte2 == ptr[-2]
XSETBUFFER (last_thing_searched, current_buffer);
}
\f
-/* 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 (Lisp_Object string, int lax)
+DEFUN ("word-search-regexp", Fword_search_regexp, Sword_search_regexp, 1, 2, 0,
+ doc: /* Return a regexp which matches words, ignoring 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 non-nil, the end of the string
+need not match a word boundary unless it ends in whitespace.
+
+Used in `word-search-forward', `word-search-backward',
+`word-search-forward-lax', `word-search-backward-lax'. */)
+ (Lisp_Object string, Lisp_Object lax)
{
register unsigned char *o;
register EMACS_INT i, i_byte, len, punct_count = 0, word_count = 0;
}
adjust = - punct_count + 5 * (word_count - 1)
- + ((lax && !whitespace_at_end) ? 2 : 4);
+ + ((!NILP (lax) && !whitespace_at_end) ? 2 : 4);
if (STRING_MULTIBYTE (string))
val = make_uninit_multibyte_string (len + adjust,
SBYTES (string)
prev_c = c;
}
- if (!lax || whitespace_at_end)
+ if (NILP (lax) || whitespace_at_end)
{
*o++ = '\\';
*o++ = 'b';
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. */)
+Optional fourth argument is repeat count--search for successive occurrences.
+
+Relies on the function `word-search-regexp' to convert a sequence
+of words in STRING to a regexp used to search words without regard
+to punctuation. */)
(Lisp_Object string, Lisp_Object bound, Lisp_Object noerror, Lisp_Object count)
{
- return search_command (wordify (string, 0), bound, noerror, count, -1, 1, 0);
+ return search_command (Fword_search_regexp (string, Qnil), bound, noerror, count, -1, 1, 0);
}
DEFUN ("word-search-forward", Fword_search_forward, Sword_search_forward, 1, 4,
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. */)
+Optional fourth argument is repeat count--search for successive occurrences.
+
+Relies on the function `word-search-regexp' to convert a sequence
+of words in STRING to a regexp used to search words without regard
+to punctuation. */)
(Lisp_Object string, Lisp_Object bound, Lisp_Object noerror, Lisp_Object count)
{
- return search_command (wordify (string, 0), bound, noerror, count, 1, 1, 0);
+ return search_command (Fword_search_regexp (string, Qnil), bound, noerror, count, 1, 1, 0);
}
DEFUN ("word-search-backward-lax", Fword_search_backward_lax, Sword_search_backward_lax, 1, 4,
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. */)
+Optional fourth argument is repeat count--search for successive occurrences.
+
+Relies on the function `word-search-regexp' to convert a sequence
+of words in STRING to a regexp used to search words without regard
+to punctuation. */)
(Lisp_Object string, Lisp_Object bound, Lisp_Object noerror, Lisp_Object count)
{
- return search_command (wordify (string, 1), bound, noerror, count, -1, 1, 0);
+ return search_command (Fword_search_regexp (string, Qt), bound, noerror, count, -1, 1, 0);
}
DEFUN ("word-search-forward-lax", Fword_search_forward_lax, Sword_search_forward_lax, 1, 4,
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. */)
+Optional fourth argument is repeat count--search for successive occurrences.
+
+Relies on the function `word-search-regexp' to convert a sequence
+of words in STRING to a regexp used to search words without regard
+to punctuation. */)
(Lisp_Object string, Lisp_Object bound, Lisp_Object noerror, Lisp_Object count)
{
- return search_command (wordify (string, 1), bound, noerror, count, 1, 1, 0);
+ return search_command (Fword_search_regexp (string, Qt), bound, noerror, count, 1, 1, 0);
}
DEFUN ("re-search-backward", Fre_search_backward, Sre_search_backward, 1, 4,
int some_uppercase;
int some_nonuppercase_initial;
register int c, prevc;
- int sub;
+ ptrdiff_t sub;
EMACS_INT opoint, newpoint;
CHECK_STRING (newtext);
else
{
CHECK_NUMBER (subexp);
- sub = XINT (subexp);
- if (sub < 0 || sub >= search_regs.num_regs)
+ if (! (0 <= XINT (subexp) && XINT (subexp) < search_regs.num_regs))
args_out_of_range (subexp, make_number (search_regs.num_regs));
+ sub = XINT (subexp);
}
if (NILP (string))
unsigned char str[MAX_MULTIBYTE_LENGTH];
const unsigned char *add_stuff = NULL;
ptrdiff_t add_len = 0;
- int idx = -1;
+ ptrdiff_t idx = -1;
if (str_multibyte)
{
static Lisp_Object
match_limit (Lisp_Object num, int beginningp)
{
- register int n;
+ EMACS_INT n;
CHECK_NUMBER (num);
n = XINT (num);
Fmatch_data (Qnil, Qnil, Qnil));
}
-/* Quote a string to inactivate reg-expr chars */
+/* Quote a string to deactivate reg-expr chars */
DEFUN ("regexp-quote", Fregexp_quote, Sregexp_quote, 1, 1, 0,
doc: /* Return a regexp string which matches exactly STRING and nothing else. */)
defsubr (&Sposix_string_match);
defsubr (&Ssearch_forward);
defsubr (&Ssearch_backward);
+ defsubr (&Sword_search_regexp);
defsubr (&Sword_search_forward);
defsubr (&Sword_search_backward);
defsubr (&Sword_search_forward_lax);