/* GNU Emacs case conversion functions.
- Copyright (C) 1985, 1994, 1997, 1998, 1999, 2001, 2002, 2003, 2004,
- 2005, 2006, 2007, 2008 Free Software Foundation, Inc.
+
+Copyright (C) 1985, 1994, 1997-1999, 2001-2011 Free Software Foundation, Inc.
This file is part of GNU Emacs.
-GNU Emacs is free software; you can redistribute it and/or modify
+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, 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
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
-along with GNU Emacs; see the file COPYING. If not, write to
-the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
-Boston, MA 02110-1301, USA. */
+along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
+#include <setjmp.h>
#include "lisp.h"
#include "buffer.h"
#include "character.h"
Lisp_Object Qidentity;
\f
Lisp_Object
-casify_object (flag, obj)
- enum case_action flag;
- Lisp_Object obj;
+casify_object (enum case_action flag, Lisp_Object obj)
{
register int c, c1;
register int inword = flag == CASE_DOWN;
return obj;
c1 = XFASTINT (obj) & ~flagbits;
+ /* FIXME: Even if enable-multibyte-characters is nil, we may
+ manipulate multibyte chars. This means we have a bug for latin-1
+ chars since when we receive an int 128-255 we can't tell whether
+ it's an eight-bit byte or a latin-1 char. */
+ if (c1 >= 256)
+ multibyte = 1;
if (! multibyte)
MAKE_CHAR_MULTIBYTE (c1);
c = DOWNCASE (c1);
return obj;
}
- if (STRINGP (obj))
+ if (!STRINGP (obj))
+ wrong_type_argument (Qchar_or_string_p, obj);
+ else if (!STRING_MULTIBYTE (obj))
{
- int multibyte = STRING_MULTIBYTE (obj);
- int i, i_byte, len;
- int size = SCHARS (obj);
+ EMACS_INT i;
+ EMACS_INT size = SCHARS (obj);
obj = Fcopy_sequence (obj);
- for (i = i_byte = 0; i < size; i++, i_byte += len)
+ for (i = 0; i < size; i++)
{
- if (multibyte)
- c = STRING_CHAR_AND_LENGTH (SDATA (obj) + i_byte, 0, len);
- else
- {
- c = SREF (obj, i_byte);
- len = 1;
- MAKE_CHAR_MULTIBYTE (c);
- }
+ c = SREF (obj, i);
+ MAKE_CHAR_MULTIBYTE (c);
c1 = c;
if (inword && flag != CASE_CAPITALIZE_UP)
c = DOWNCASE (c);
inword = (SYNTAX (c) == Sword);
if (c != c1)
{
- if (! multibyte)
- {
MAKE_CHAR_UNIBYTE (c);
- SSET (obj, i_byte, c);
- }
- else if (ASCII_CHAR_P (c1) && ASCII_CHAR_P (c))
- SSET (obj, i_byte, c);
- else
- {
- Faset (obj, make_number (i), make_number (c));
- i_byte += CHAR_BYTES (c) - len;
- }
+ /* If the char can't be converted to a valid byte, just don't
+ change it. */
+ if (c >= 0 && c < 256)
+ SSET (obj, i, c);
}
}
return obj;
}
+ else
+ {
+ EMACS_INT i, i_byte, size = SCHARS (obj);
+ int len;
+ USE_SAFE_ALLOCA;
+ unsigned char *dst, *o;
+ /* Over-allocate by 12%: this is a minor overhead, but should be
+ sufficient in 99.999% of the cases to avoid a reallocation. */
+ EMACS_INT o_size = SBYTES (obj) + SBYTES (obj) / 8 + MAX_MULTIBYTE_LENGTH;
+ SAFE_ALLOCA (dst, void *, o_size);
+ o = dst;
- wrong_type_argument (Qchar_or_string_p, obj);
+ for (i = i_byte = 0; i < size; i++, i_byte += len)
+ {
+ if ((o - dst) + MAX_MULTIBYTE_LENGTH > o_size)
+ { /* Not enough space for the next char: grow the destination. */
+ unsigned char *old_dst = dst;
+ o_size += o_size; /* Probably overkill, but extremely rare. */
+ SAFE_ALLOCA (dst, void *, o_size);
+ memcpy (dst, old_dst, o - old_dst);
+ o = dst + (o - old_dst);
+ }
+ c = STRING_CHAR_AND_LENGTH (SDATA (obj) + i_byte, len);
+ if (inword && flag != CASE_CAPITALIZE_UP)
+ c = DOWNCASE (c);
+ else if (!UPPERCASEP (c)
+ && (!inword || flag != CASE_CAPITALIZE_UP))
+ c = UPCASE1 (c);
+ if ((int) flag >= (int) CASE_CAPITALIZE)
+ inword = (SYNTAX (c) == Sword);
+ o += CHAR_STRING (c, o);
+ }
+ eassert (o - dst <= o_size);
+ obj = make_multibyte_string (dst, size, o - dst);
+ SAFE_FREE ();
+ return obj;
+ }
}
DEFUN ("upcase", Fupcase, Supcase, 1, 1, 0,
The argument may be a character or string. The result has the same type.
The argument object is not altered--the value is a copy.
See also `capitalize', `downcase' and `upcase-initials'. */)
- (obj)
- Lisp_Object obj;
+ (Lisp_Object obj)
{
return casify_object (CASE_UP, obj);
}
doc: /* Convert argument to lower case and return that.
The argument may be a character or string. The result has the same type.
The argument object is not altered--the value is a copy. */)
- (obj)
- Lisp_Object obj;
+ (Lisp_Object obj)
{
return casify_object (CASE_DOWN, obj);
}
and the rest is lower case.
The argument may be a character or string. The result has the same type.
The argument object is not altered--the value is a copy. */)
- (obj)
- Lisp_Object obj;
+ (Lisp_Object obj)
{
return casify_object (CASE_CAPITALIZE, obj);
}
Do not change the other letters of each word.
The argument may be a character or string. The result has the same type.
The argument object is not altered--the value is a copy. */)
- (obj)
- Lisp_Object obj;
+ (Lisp_Object obj)
{
return casify_object (CASE_CAPITALIZE_UP, obj);
}
b and e specify range of buffer to operate on. */
void
-casify_region (flag, b, e)
- enum case_action flag;
- Lisp_Object b, e;
+casify_region (enum case_action flag, Lisp_Object b, Lisp_Object e)
{
register int c;
register int inword = flag == CASE_DOWN;
start_byte = CHAR_TO_BYTE (start);
end_byte = CHAR_TO_BYTE (end);
+ SETUP_BUFFER_SYNTAX_TABLE(); /* For syntax_prefix_flag_p. */
+
while (start < end)
{
int c2, len;
&& (!inword || flag != CASE_CAPITALIZE_UP))
c = UPCASE1 (c);
if ((int) flag >= (int) CASE_CAPITALIZE)
- inword = ((SYNTAX (c) == Sword) && (inword || !SYNTAX_PREFIX (c)));
+ inword = ((SYNTAX (c) == Sword)
+ && (inword || !syntax_prefix_flag_p (c)));
if (c != c2)
{
last = start;
the region to operate on. When used as a command, the text between
point and the mark is operated on.
See also `capitalize-region'. */)
- (beg, end)
- Lisp_Object beg, end;
+ (Lisp_Object beg, Lisp_Object end)
{
casify_region (CASE_UP, beg, end);
return Qnil;
These arguments specify the starting and ending character numbers of
the region to operate on. When used as a command, the text between
point and the mark is operated on. */)
- (beg, end)
- Lisp_Object beg, end;
+ (Lisp_Object beg, Lisp_Object end)
{
casify_region (CASE_DOWN, beg, end);
return Qnil;
and the rest of it is lower case.
In programs, give two arguments, the starting and ending
character positions to operate on. */)
- (beg, end)
- Lisp_Object beg, end;
+ (Lisp_Object beg, Lisp_Object end)
{
casify_region (CASE_CAPITALIZE, beg, end);
return Qnil;
Subsequent letters of each word are not changed.
In programs, give two arguments, the starting and ending
character positions to operate on. */)
- (beg, end)
- Lisp_Object beg, end;
+ (Lisp_Object beg, Lisp_Object end)
{
casify_region (CASE_CAPITALIZE_UP, beg, end);
return Qnil;
}
\f
-Lisp_Object
-operate_on_word (arg, newpoint)
- Lisp_Object arg;
- int *newpoint;
+static Lisp_Object
+operate_on_word (Lisp_Object arg, EMACS_INT *newpoint)
{
Lisp_Object val;
- int farend;
- int iarg;
+ EMACS_INT farend;
+ EMACS_INT iarg;
CHECK_NUMBER (arg);
iarg = XINT (arg);
doc: /* Convert following word (or ARG words) to upper case, moving over.
With negative argument, convert previous words but do not move.
See also `capitalize-word'. */)
- (arg)
- Lisp_Object arg;
+ (Lisp_Object arg)
{
Lisp_Object beg, end;
- int newpoint;
+ EMACS_INT newpoint;
XSETFASTINT (beg, PT);
end = operate_on_word (arg, &newpoint);
casify_region (CASE_UP, beg, end);
DEFUN ("downcase-word", Fdowncase_word, Sdowncase_word, 1, 1, "p",
doc: /* Convert following word (or ARG words) to lower case, moving over.
With negative argument, convert previous words but do not move. */)
- (arg)
- Lisp_Object arg;
+ (Lisp_Object arg)
{
Lisp_Object beg, end;
- int newpoint;
+ EMACS_INT newpoint;
XSETFASTINT (beg, PT);
end = operate_on_word (arg, &newpoint);
casify_region (CASE_DOWN, beg, end);
This gives the word(s) a first character in upper case
and the rest lower case.
With negative argument, capitalize previous words but do not move. */)
- (arg)
- Lisp_Object arg;
+ (Lisp_Object arg)
{
Lisp_Object beg, end;
- int newpoint;
+ EMACS_INT newpoint;
XSETFASTINT (beg, PT);
end = operate_on_word (arg, &newpoint);
casify_region (CASE_CAPITALIZE, beg, end);
}
\f
void
-syms_of_casefiddle ()
+syms_of_casefiddle (void)
{
- Qidentity = intern ("identity");
+ Qidentity = intern_c_string ("identity");
staticpro (&Qidentity);
defsubr (&Supcase);
defsubr (&Sdowncase);
}
void
-keys_of_casefiddle ()
+keys_of_casefiddle (void)
{
initial_define_key (control_x_map, Ctl('U'), "upcase-region");
Fput (intern ("upcase-region"), Qdisabled, Qt);
initial_define_key (meta_map, 'c', "capitalize-word");
}
-/* arch-tag: 60a73c66-5489-47e7-a81f-cead4057c526
- (do not change this comment) */