X-Git-Url: https://code.delx.au/gnu-emacs/blobdiff_plain/33017fafd17d722e82a268e9b272f27df261e09d..fb39b937b0628f4592b07d0aa61a41cf696abd30:/src/search.c
diff --git a/src/search.c b/src/search.c
index 5608e344e7..7c084c62e2 100644
--- a/src/search.c
+++ b/src/search.c
@@ -20,12 +20,12 @@ along with GNU Emacs. If not, see . */
#include
-#include
+
#include "lisp.h"
#include "syntax.h"
#include "category.h"
-#include "buffer.h"
#include "character.h"
+#include "buffer.h"
#include "charset.h"
#include "region-cache.h"
#include "commands.h"
@@ -101,9 +101,8 @@ static EMACS_INT boyer_moore (EMACS_INT, unsigned char *, ptrdiff_t,
static EMACS_INT search_buffer (Lisp_Object, ptrdiff_t, ptrdiff_t,
ptrdiff_t, ptrdiff_t, EMACS_INT, int,
Lisp_Object, Lisp_Object, int);
-static void matcher_overflow (void) NO_RETURN;
-static void
+static _Noreturn void
matcher_overflow (void)
{
error ("Stack overflow in regexp matcher");
@@ -157,7 +156,7 @@ compile_pattern_1 (struct regexp_cache *cp, Lisp_Object pattern, Lisp_Object tra
re_set_whitespace_regexp (NULL);
re_set_syntax (old);
- /* UNBLOCK_INPUT; */
+ /* unblock_input (); */
if (val)
xsignal1 (Qinvalid_regexp, build_string (val));
@@ -176,8 +175,7 @@ shrink_regexp_cache (void)
for (cp = searchbuf_head; cp != 0; cp = cp->next)
{
cp->buf.allocated = cp->buf.used;
- cp->buf.buffer
- = (unsigned char *) xrealloc (cp->buf.buffer, cp->buf.used);
+ cp->buf.buffer = xrealloc (cp->buf.buffer, cp->buf.used);
}
}
@@ -280,8 +278,8 @@ looking_at_1 (Lisp_Object string, int posix)
save_search_regs ();
/* This is so set_image_of_range_1 in regex.c can find the EQV table. */
- XCHAR_TABLE (BVAR (current_buffer, case_canon_table))->extras[2]
- = BVAR (current_buffer, case_eqv_table);
+ set_char_table_extras (BVAR (current_buffer, case_canon_table), 2,
+ BVAR (current_buffer, case_eqv_table));
CHECK_STRING (string);
bufp = compile_pattern (string,
@@ -395,8 +393,8 @@ string_match_1 (Lisp_Object regexp, Lisp_Object string, Lisp_Object start, int p
}
/* This is so set_image_of_range_1 in regex.c can find the EQV table. */
- XCHAR_TABLE (BVAR (current_buffer, case_canon_table))->extras[2]
- = BVAR (current_buffer, case_eqv_table);
+ set_char_table_extras (BVAR (current_buffer, case_canon_table), 2,
+ BVAR (current_buffer, case_eqv_table));
bufp = compile_pattern (regexp,
(NILP (Vinhibit_changing_match_data)
@@ -492,11 +490,11 @@ fast_string_match (Lisp_Object regexp, Lisp_Object string)
We assume that STRING contains single-byte characters. */
ptrdiff_t
-fast_c_string_match_ignore_case (Lisp_Object regexp, const char *string)
+fast_c_string_match_ignore_case (Lisp_Object regexp,
+ const char *string, ptrdiff_t len)
{
ptrdiff_t val;
struct re_pattern_buffer *bufp;
- size_t len = strlen (string);
regexp = string_make_unibyte (regexp);
re_match_object = Qt;
@@ -676,7 +674,7 @@ scan_buffer (register int target, ptrdiff_t start, ptrdiff_t end,
obstacle --- the last character the dumb search loop should
examine. */
ptrdiff_t ceiling_byte = CHAR_TO_BYTE (end) - 1;
- ptrdiff_t start_byte = CHAR_TO_BYTE (start);
+ ptrdiff_t start_byte;
ptrdiff_t tem;
/* If we're looking for a newline, consult the newline cache
@@ -686,18 +684,22 @@ scan_buffer (register int target, ptrdiff_t start, ptrdiff_t end,
ptrdiff_t next_change;
immediate_quit = 0;
while (region_cache_forward
- (current_buffer, newline_cache, start_byte, &next_change))
- start_byte = next_change;
+ (current_buffer, newline_cache, start, &next_change))
+ start = next_change;
immediate_quit = allow_quit;
+ start_byte = CHAR_TO_BYTE (start);
+
/* START should never be after END. */
if (start_byte > ceiling_byte)
start_byte = ceiling_byte;
/* Now the text after start is an unknown region, and
next_change is the position of the next known region. */
- ceiling_byte = min (next_change - 1, ceiling_byte);
+ ceiling_byte = min (CHAR_TO_BYTE (next_change) - 1, ceiling_byte);
}
+ else
+ start_byte = CHAR_TO_BYTE (start);
/* The dumb loop can only scan text stored in contiguous
bytes. BUFFER_CEILING_OF returns the last character
@@ -749,7 +751,7 @@ scan_buffer (register int target, ptrdiff_t start, ptrdiff_t end,
{
/* The last character to check before the next obstacle. */
ptrdiff_t ceiling_byte = CHAR_TO_BYTE (end);
- ptrdiff_t start_byte = CHAR_TO_BYTE (start);
+ ptrdiff_t start_byte;
ptrdiff_t tem;
/* Consult the newline cache, if appropriate. */
@@ -758,18 +760,22 @@ scan_buffer (register int target, ptrdiff_t start, ptrdiff_t end,
ptrdiff_t next_change;
immediate_quit = 0;
while (region_cache_backward
- (current_buffer, newline_cache, start_byte, &next_change))
- start_byte = next_change;
+ (current_buffer, newline_cache, start, &next_change))
+ start = next_change;
immediate_quit = allow_quit;
+ start_byte = CHAR_TO_BYTE (start);
+
/* Start should never be at or before end. */
if (start_byte <= ceiling_byte)
start_byte = ceiling_byte + 1;
/* Now the text before start is an unknown region, and
next_change is the position of the next known region. */
- ceiling_byte = max (next_change, ceiling_byte);
+ ceiling_byte = max (CHAR_TO_BYTE (next_change), ceiling_byte);
}
+ else
+ start_byte = CHAR_TO_BYTE (start);
/* Stop scanning before the gap. */
tem = BUFFER_FLOOR_OF (start_byte - 1);
@@ -992,8 +998,8 @@ search_command (Lisp_Object string, Lisp_Object bound, Lisp_Object noerror,
}
/* This is so set_image_of_range_1 in regex.c can find the EQV table. */
- XCHAR_TABLE (BVAR (current_buffer, case_canon_table))->extras[2]
- = BVAR (current_buffer, case_eqv_table);
+ set_char_table_extras (BVAR (current_buffer, case_canon_table), 2,
+ BVAR (current_buffer, case_eqv_table));
np = search_buffer (string, PT, PT_BYTE, lim, lim_byte, n, RE,
(!NILP (BVAR (current_buffer, case_fold_search))
@@ -1011,7 +1017,7 @@ search_command (Lisp_Object string, Lisp_Object bound, Lisp_Object noerror,
if (!EQ (noerror, Qt))
{
if (lim < BEGV || lim > ZV)
- abort ();
+ emacs_abort ();
SET_PT_BOTH (lim, lim_byte);
return Qnil;
#if 0 /* This would be clean, but maybe programs depend on
@@ -1024,7 +1030,7 @@ search_command (Lisp_Object string, Lisp_Object bound, Lisp_Object noerror,
}
if (np < BEGV || np > ZV)
- abort ();
+ emacs_abort ();
SET_PT (np);
@@ -1160,24 +1166,12 @@ search_buffer (Lisp_Object string, ptrdiff_t pos, ptrdiff_t pos_byte,
{
ptrdiff_t val;
-#ifdef REL_ALLOC
- /* re_search_2 below is passed C pointers to buffer text.
- If some code called by it causes memory (re)allocation,
- buffer text could be relocated on platforms that use
- REL_ALLOC, which invalidates those C pointers. So we
- inhibit relocation of buffer text for as long as
- re_search_2 runs. */
- r_alloc_inhibit_buffer_relocation (1);
-#endif
val = re_search_2 (bufp, (char *) p1, s1, (char *) p2, s2,
pos_byte - BEGV_BYTE, lim_byte - pos_byte,
(NILP (Vinhibit_changing_match_data)
? &search_regs : &search_regs_1),
/* Don't allow match past current point */
pos_byte - BEGV_BYTE);
-#ifdef REL_ALLOC
- r_alloc_inhibit_buffer_relocation (0);
-#endif
if (val == -2)
{
matcher_overflow ();
@@ -1217,19 +1211,11 @@ search_buffer (Lisp_Object string, ptrdiff_t pos, ptrdiff_t pos_byte,
{
ptrdiff_t val;
-#ifdef REL_ALLOC
- /* See commentary above for the reasons for inhibiting
- buffer text relocation here. */
- r_alloc_inhibit_buffer_relocation (1);
-#endif
val = re_search_2 (bufp, (char *) p1, s1, (char *) p2, s2,
pos_byte - BEGV_BYTE, lim_byte - pos_byte,
(NILP (Vinhibit_changing_match_data)
? &search_regs : &search_regs_1),
lim_byte - BEGV_BYTE);
-#ifdef REL_ALLOC
- r_alloc_inhibit_buffer_relocation (0);
-#endif
if (val == -2)
{
matcher_overflow ();
@@ -1295,7 +1281,7 @@ search_buffer (Lisp_Object string, ptrdiff_t pos, ptrdiff_t pos_byte,
raw_pattern_size_byte
= count_size_as_multibyte (SDATA (string),
raw_pattern_size);
- raw_pattern = (unsigned char *) alloca (raw_pattern_size_byte + 1);
+ raw_pattern = alloca (raw_pattern_size_byte + 1);
copy_text (SDATA (string), raw_pattern,
SCHARS (string), 0, 1);
}
@@ -1309,7 +1295,7 @@ search_buffer (Lisp_Object string, ptrdiff_t pos, ptrdiff_t pos_byte,
the chosen single-byte character set can possibly match. */
raw_pattern_size = SCHARS (string);
raw_pattern_size_byte = SCHARS (string);
- raw_pattern = (unsigned char *) alloca (raw_pattern_size + 1);
+ raw_pattern = alloca (raw_pattern_size + 1);
copy_text (SDATA (string), raw_pattern,
SBYTES (string), 1, 0);
}
@@ -1317,7 +1303,7 @@ search_buffer (Lisp_Object string, ptrdiff_t pos, ptrdiff_t pos_byte,
/* Copy and optionally translate the pattern. */
len = raw_pattern_size;
len_byte = raw_pattern_size_byte;
- patbuf = (unsigned char *) alloca (len * MAX_MULTIBYTE_LENGTH);
+ patbuf = alloca (len * MAX_MULTIBYTE_LENGTH);
pat = patbuf;
base_pat = raw_pattern;
if (multibyte)
@@ -1472,7 +1458,7 @@ simple_search (EMACS_INT n, unsigned char *pat,
int forward = n > 0;
/* Number of buffer bytes matched. Note that this may be different
from len_byte in a multibyte buffer. */
- ptrdiff_t match_byte;
+ ptrdiff_t match_byte = PTRDIFF_MIN;
if (lim > pos && multibyte)
while (n > 0)
@@ -1643,6 +1629,7 @@ simple_search (EMACS_INT n, unsigned char *pat,
stop:
if (n == 0)
{
+ eassert (match_byte != PTRDIFF_MIN);
if (forward)
set_search_regs ((multibyte ? pos_byte : pos) - match_byte, match_byte);
else
@@ -2084,8 +2071,8 @@ set_search_regs (ptrdiff_t beg_byte, ptrdiff_t nbytes)
the match position. */
if (search_regs.num_regs == 0)
{
- search_regs.start = (regoff_t *) xmalloc (2 * sizeof (regoff_t));
- search_regs.end = (regoff_t *) xmalloc (2 * sizeof (regoff_t));
+ search_regs.start = xmalloc (2 * sizeof (regoff_t));
+ search_regs.end = xmalloc (2 * sizeof (regoff_t));
search_regs.num_regs = 2;
}
@@ -2233,29 +2220,29 @@ DEFUN ("replace-match", Freplace_match, Sreplace_match, 1, 5, 0,
doc: /* Replace text matched by last search with NEWTEXT.
Leave point at the end of the replacement text.
-If second arg FIXEDCASE is non-nil, do not alter case of replacement text.
-Otherwise maybe capitalize the whole text, or maybe just word initials,
-based on the replaced text.
-If the replaced text has only capital letters
-and has at least one multiletter word, convert NEWTEXT to all caps.
-Otherwise if all words are capitalized in the replaced text,
-capitalize each word in NEWTEXT.
+If optional second arg FIXEDCASE is non-nil, do not alter the case of
+the replacement text. Otherwise, maybe capitalize the whole text, or
+maybe just word initials, based on the replaced text. If the replaced
+text has only capital letters and has at least one multiletter word,
+convert NEWTEXT to all caps. Otherwise if all words are capitalized
+in the replaced text, capitalize each word in NEWTEXT.
-If third arg LITERAL is non-nil, insert NEWTEXT literally.
+If optional third arg LITERAL is non-nil, insert NEWTEXT literally.
Otherwise treat `\\' as special:
`\\&' in NEWTEXT means substitute original matched text.
`\\N' means substitute what matched the Nth `\\(...\\)'.
If Nth parens didn't match, substitute nothing.
`\\\\' means insert one `\\'.
+ `\\?' is treated literally
+ (for compatibility with `query-replace-regexp').
+ Any other character following `\\' signals an error.
Case conversion does not apply to these substitutions.
-FIXEDCASE and LITERAL are optional arguments.
-
-The optional fourth argument STRING can be a string to modify.
-This is meaningful when the previous match was done against STRING,
-using `string-match'. When used this way, `replace-match'
-creates and returns a new string made by copying STRING and replacing
-the part of STRING that was matched.
+If optional fourth argument STRING is non-nil, it should be a string
+to act on; this should be the string on which the previous match was
+done via `string-match'. In this case, `replace-match' creates and
+returns a new string, made by copying STRING and replacing the part of
+STRING that was matched (the original STRING itself is not altered).
The optional fifth argument SUBEXP specifies a subexpression;
it says to replace just that subexpression with NEWTEXT,
@@ -2449,7 +2436,7 @@ since only regular expressions have distinguished subexpressions. */)
}
else if (c == '\\')
delbackslash = 1;
- else
+ else if (c != '?')
error ("Invalid use of `\\' in replacement text");
}
if (substart >= 0)
@@ -2520,7 +2507,7 @@ since only regular expressions have distinguished subexpressions. */)
substed_alloc_size = ((STRING_BYTES_BOUND - 100) / 2 < length
? STRING_BYTES_BOUND
: length * 2 + 100);
- substed = (unsigned char *) xmalloc (substed_alloc_size);
+ substed = xmalloc (substed_alloc_size);
substed_len = 0;
/* Go thru NEWTEXT, producing the actual text to insert in
@@ -2761,8 +2748,7 @@ Return value is undefined if the last search failed. */)
prev = Qnil;
- data = (Lisp_Object *) alloca ((2 * search_regs.num_regs + 1)
- * sizeof (Lisp_Object));
+ data = alloca ((2 * search_regs.num_regs + 1) * sizeof *data);
len = 0;
for (i = 0; i < search_regs.num_regs; i++)
@@ -2789,7 +2775,7 @@ Return value is undefined if the last search failed. */)
}
else
/* last_thing_searched must always be Qt, a buffer, or Qnil. */
- abort ();
+ emacs_abort ();
len = 2 * i + 2;
}
@@ -3028,7 +3014,7 @@ DEFUN ("regexp-quote", Fregexp_quote, Sregexp_quote, 1, 1, 0,
CHECK_STRING (string);
- temp = (char *) alloca (SBYTES (string) * 2);
+ temp = alloca (SBYTES (string) * 2);
/* Now copy the data into the new string, inserting escapes. */
@@ -3060,7 +3046,7 @@ syms_of_search (void)
for (i = 0; i < REGEXP_CACHE_SIZE; ++i)
{
searchbufs[i].buf.allocated = 100;
- searchbufs[i].buf.buffer = (unsigned char *) xmalloc (100);
+ searchbufs[i].buf.buffer = xmalloc (100);
searchbufs[i].buf.fastmap = searchbufs[i].fastmap;
searchbufs[i].regexp = Qnil;
searchbufs[i].whitespace_regexp = Qnil;
@@ -3076,14 +3062,14 @@ syms_of_search (void)
DEFSYM (Qinvalid_regexp, "invalid-regexp");
Fput (Qsearch_failed, Qerror_conditions,
- pure_cons (Qsearch_failed, pure_cons (Qerror, Qnil)));
+ listn (CONSTYPE_PURE, 2, Qsearch_failed, Qerror));
Fput (Qsearch_failed, Qerror_message,
- make_pure_c_string ("Search failed"));
+ build_pure_c_string ("Search failed"));
Fput (Qinvalid_regexp, Qerror_conditions,
- pure_cons (Qinvalid_regexp, pure_cons (Qerror, Qnil)));
+ listn (CONSTYPE_PURE, 2, Qinvalid_regexp, Qerror));
Fput (Qinvalid_regexp, Qerror_message,
- make_pure_c_string ("Invalid regexp"));
+ build_pure_c_string ("Invalid regexp"));
last_thing_searched = Qnil;
staticpro (&last_thing_searched);