view src/casefiddle.c @ 26088:b7aa6ac26872

Add support for large files, 64-bit Solaris, system locale codings. * Makefile.in (emacs): Set the LC_ALL environment variable to "C" when dumping, so that the dumped Emacs doesn't have stray locale info. (dired.o): Depend on systime.h. (editfns.o): Depend on coding.h. * alloc.c, buffer.c, callproc.c, ccl.c, charset.c, coding.c, data.c, dispnew.c, editfns.c, emacs.c, filelock.c, floatfns.c, hftctl.c, keyboard.c, process.c, sysdep.c, unexelf.c, unexhp9k800.c, unexsunos4.c, vmsfns.c, vmsgmalloc.c, w32faces.c, w32menu.c, w32term.c, w32xfns.c, xfaces.c, xfns.c, xmenu.c, xterm.c: Include <config.h> before any system include files. * alloc.c, buffer.c, ccl.c, data.c, editfns.c, emacs.c, eval.c, fileio.c, filelock.c, frame.c, insdel.c, keymap.c, lread.c, m/alpha.h, print.c, search.c, sysdep.c, xdisp.c, xfaces.c, xfns.c, xmenu.c, xterm.c: Do not include <stdlib.h>, as <config.h> does this now. * callproc.c (Fcall_process): Synchronize messages locale before invoking strerror. Decode resulting string with locale-coding-system. * coding.c (Vlocale_coding_system): New var. (syms_of_coding): Adjust to above change. (emacs_strerror): New function. * coding.h (emacs_strerror, Vlocale_coding_system): New decls. * config.in (HAVE_STDIO_EXT_H, HAVE_TM_GMTOFF, HAVE___FPENDING, HAVE_FTELLO, HAVE_GETLOADAVG, HAVE_MBLEN, HAVE_MBRLEN, HAVE_STRSIGNAL): New macros. (BITS_PER_LONG): Default to 64 if _LP64 is defined. <stdlib.h>: Include if HAVE_STDLIB_H is defined and NOT_C_CODE isn't. * dired.c: Include "systime.h". (Ffile_attributes): Do not cast s.st_size to int; this loses information if int is 32 bits but st_size and EMACS_INT are larger. Treat large device numbers like large inode numbers. * dispnew.c (PENDING_OUTPUT_COUNT): Use __fpending if available. * editfns.c: Include coding.h. (emacs_strftime): Remove decl. (emacs_strftimeu): New decl. (emacs_memftimeu): Renamed from emacs_memftime; new arg UT. Use emacs_strftimeu instead of emacs_strftime. (Fformat_time_string): Convert format string using Vlocale_coding_system, and convert result back. Synchronize time locale before invoking lower level function. Invoke emacs_memftimeu, passing ut, instead of emacs_memftime. * emacs.c: Include <locale.h> if HAVE_SETLOCALE is defined. (Vmessages_locale, Vprevious_messages_locale, Vtime_locale, Vprevious_time_locale): New variables. (main): Invoke setlocale early, so that initial error messages are localized properly. But skip locale-setting if LC_ALL is "C". Fix up locale when it's safe to do so. (fixup_locale): Moved here from xterm.c. (synchronize_locale, synchronize_time_locale, synchronize_messages_locale): New functions. (syms_of_emacs): Accommodate above changes. * fileio.c (report_file_error): Convert strerror output according to Vlocale_coding_system. (Finsert_file_contents): Check for arithmetic overflow in computations that depend on file size. Report IO errors with emacs_strerror, not strerror. * fns.c (Fgethash): Declare dflt parameter. * gmalloc.c: Do not define const to nothing if HAVE_CONFIG_H is defined; that's config.h's job. * lisp.h (EMACS_INT, BITS_PER_EMACS_INT, EMACS_UINT): If _LP64, default these values to long, BITS_PER_LONG, and unsigned long. (VALBITS, MARKBIT, XINT): Do not assume 32-bit EMACS_INT. (PNTR_COMPARISON_TYPE): Default to EMACS_UINT, not to unsigned int. (code_convert_string_norecord, fixup_locale, synchronize_messages_locale, synchronize_time_locale, emacs_open, emacs_close, emacs_read, emacs_write): New decls. All Emacs callers of open, close, read, write changed to use emacs_open, emacs_close, emacs_read, emacs_write. * lread.c (file_offset, file_tell): New macros. All uses of ftell changed to file_tell. (saved_doc_string_position, prev_saved_doc_string_position): Now of type file_offset. (init_lread): Do not fix locale here; fixup_locale now does this. * m/amdahl.h, s/usg5-4.h: (NSIG): Remove. (NSIG_MINIMUM): New macro. * m/cydra5.h, m/dpx2.h, m/mips.h, m/pfa50.h, m/sps7.h, m/stride.h, m/ustation.h, s/gnu-linux.h, s/hpux.h, s/iris3-5.h, s/iris3-6.h, s/umips.h, s/usg5-4.h: (SIGIO): Do not undef. (BROKEN_SIGIO): New macro. * m/ustation.h: (SIGTSTP): Do not undef. (BROKEN_SIGTSTP): New macro. * s/gnu-linux.h: (SIGPOLL, SIGURG): Do not undef. (BROKEN_SIGPOLL, BROKEN_SIGURG): New macros. * s/ptx4.h: (SIGINFO): Do not undef. (BROKEN_SIGINFO): New macros. * m/delta.h, s/ptx.h, s/template.h: Doc fix. * mktime.c, strftime.c: Update to glibc 2.1.2 version, with some Emacs-related changes merged. * print.c (float_to_string): Prepend "-" to representation of a NaN if the NaN is negative. * process.c (sys_siglist): Omit if HAVE_STRSIGNAL. (wait_reading_process_input): Use emacs_strerror, not strerror. * process.c (status_message, sigchld_handler): Synchronize locale, then use strsignal istead of sys_siglist. * w32proc.c (sys_wait): Likewise. * s/aix3-1.h, s/bsd4-1.h, s/dgux.h, s/gnu-linux.h, s/hiuxmpp.h, s/hpux.h, s/iris3-5.h, s/iris3-6.h, s/irix3-3.h, s/osf1.h, s/rtu.h, s/sunos4-1.h, s/unipl5-0.h, s/unipl5-2.h, s/usg5-0.h, s/usg5-2-2.h, s/usg5-2.h, s/usg5-3.h, s/xenix.h: (open, close, read, write, INTERRUPTIBLE_OPEN, INTERRUPTIBLE_CLOSE, INTERRUPTIBLE_IO): Remove. * s/sol2-5.h (_LARGEFILE_SOURCE, _FILE_OFFSET_BITS): New macros. * sysdep.c (sys_read, sys_write, read, write, sys_close, close, sys_open, open): Remove. (emacs_open, emacs_close, emacs_read, emacs_write): Always define; the old INTERRUPTIBLE_OPEN, INTERRUPTIBLE_CLOSE, and INTERRUPTIBLE_IO macros are no longer used. (emacs_open): Renamed from sys_open. Merge BSD4_1 version. (emacs_close): Renamed from sys_close. (emacs_read): Renamed from sys_read. (emacs_write): Renamed from sys_write. (sys_siglist): Do not declare if HAVE_STRSIGNAL. (dup2): Do not print error on failure; the real dup2 doesn't. (strsignal): New function, defined if !HAVE_STRSIGNAL. * syssignal.h (SIGINFO): Undef if defined and if BROKEN_SIGINFO is defined. (SIGIO, SIGPOLL, SIGTSTP, SIGURG): Likewise. (NSIG): If less than NSIG_MINIMUM, define to NSIG_MINIMUM. (strsignal): Declare if !HAVE_STRSIGNAL. * unexelf.c (ElfBitsW, ELFSIZE, ElfExpandBitsW): New macros. (ElfW): Define in terms of ElfExpandBitsW. * w32proc.c (sys_siglist): Remove decl. * xdisp.c (decode_mode_spec): 3rd arg is int, not char, to comply with ANSI C. (display_string): Declare face_string_pos arg. * xfns.c (Fx_show_tip): Declare timeout param. * xterm.c: No need to include locale.h. (x_alloc_lighter_color, x_setup_relief_color): Pass arg as double, not float, for compatibility with ANSI C. (fixup_locale): Move to emacs.c. (x_term_init): Do not setlocale or fixup locale; the main program does this now.
author Paul Eggert <eggert@twinsun.com>
date Tue, 19 Oct 1999 07:25:11 +0000
parents 4065a85ee695
children 936b39bd05b4
line wrap: on
line source

/* GNU Emacs case conversion functions.
   Copyright (C) 1985, 1994, 1997 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 2, 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
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
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., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA.  */


#include <config.h>
#include "lisp.h"
#include "buffer.h"
#include "charset.h"
#include "commands.h"
#include "syntax.h"

enum case_action {CASE_UP, CASE_DOWN, CASE_CAPITALIZE, CASE_CAPITALIZE_UP};

Lisp_Object Qidentity;

Lisp_Object
casify_object (flag, obj)
     enum case_action flag;
     Lisp_Object obj;
{
  register int i, c, len;
  register int inword = flag == CASE_DOWN;

  /* If the case table is flagged as modified, rescan it.  */
  if (NILP (XCHAR_TABLE (current_buffer->downcase_table)->extras[1]))
    Fset_case_table (current_buffer->downcase_table);

  while (1)
    {
      if (INTEGERP (obj))
	{
	  int flagbits = (CHAR_ALT | CHAR_SUPER | CHAR_HYPER
			  | CHAR_SHIFT | CHAR_CTL | CHAR_META);
	  int flags = XINT (obj) & flagbits;

	  c = DOWNCASE (XFASTINT (obj) & ~flagbits);
	  if (inword)
	    XSETFASTINT (obj, c | flags);
	  else if (c == (XFASTINT (obj) & ~flagbits))
	    {
	      c = UPCASE1 ((XFASTINT (obj) & ~flagbits));
	      XSETFASTINT (obj, c | flags);
	    }
	  return obj;
	}

      if (STRINGP (obj))
	{
	  int multibyte = STRING_MULTIBYTE (obj);

	  obj = Fcopy_sequence (obj);
	  len = STRING_BYTES (XSTRING (obj));

	  /* Scan all single-byte characters from start of string.  */
	  for (i = 0; i < len;)
	    {
	      c = XSTRING (obj)->data[i];

	      if (multibyte && c >= 0x80)
		/* A multibyte character can't be handled in this
                   simple loop.  */
		break;
	      if (inword && flag != CASE_CAPITALIZE_UP)
		c = DOWNCASE (c);
	      else if (!UPPERCASEP (c)
		       && (!inword || flag != CASE_CAPITALIZE_UP))
		c = UPCASE1 (c);
	      /* If this char won't fit in a single-byte string.
		 fall out to the multibyte case.  */
	      if (multibyte ? ! ASCII_BYTE_P (c)
		  : ! SINGLE_BYTE_CHAR_P (c))
		break;

	      XSTRING (obj)->data[i] = c;
	      if ((int) flag >= (int) CASE_CAPITALIZE)
		inword = SYNTAX (c) == Sword;
	      i++;
	    }

	  /* If we didn't do the whole string as single-byte,
	     scan the rest in a more complex way.  */
	  if (i < len)
	    {
	      /* The work is not yet finished because of a multibyte
		 character just encountered.  */
	      int fromlen, tolen, j_byte = i;
	      char *buf
		= (char *) alloca ((len - i) * MAX_LENGTH_OF_MULTI_BYTE_FORM
				   + i);
	      unsigned char *str, workbuf[4];

	      /* Copy data already handled.  */
	      bcopy (XSTRING (obj)->data, buf, i);

	      /* From now on, I counts bytes.  */
	      while (i < len)
		{
		  c = STRING_CHAR_AND_LENGTH (XSTRING (obj)->data + i,
					      len - i, fromlen);
		  if (inword && flag != CASE_CAPITALIZE_UP)
		    c = DOWNCASE (c);
		  else if (!UPPERCASEP (c)
			   && (!inword || flag != CASE_CAPITALIZE_UP))
		    c = UPCASE1 (c);
		  tolen = CHAR_STRING (c, workbuf, str);
		  bcopy (str, buf + j_byte, tolen);
		  i += fromlen;
		  j_byte += tolen;
		  if ((int) flag >= (int) CASE_CAPITALIZE)
		    inword = SYNTAX (c) == Sword;
		}
	      obj = make_multibyte_string (buf, XSTRING (obj)->size,
					   j_byte);
	    }
	  return obj;
	}
      obj = wrong_type_argument (Qchar_or_string_p, obj);
    }
}

DEFUN ("upcase", Fupcase, Supcase, 1, 1, 0,
  "Convert argument to upper case and return that.\n\
The argument may be a character or string.  The result has the same type.\n\
The argument object is not altered--the value is a copy.\n\
See also `capitalize', `downcase' and `upcase-initials'.")
  (obj)
     Lisp_Object obj;
{
  return casify_object (CASE_UP, obj);
}

DEFUN ("downcase", Fdowncase, Sdowncase, 1, 1, 0,
  "Convert argument to lower case and return that.\n\
The argument may be a character or string.  The result has the same type.\n\
The argument object is not altered--the value is a copy.")
  (obj)
     Lisp_Object obj;
{
  return casify_object (CASE_DOWN, obj);
}

DEFUN ("capitalize", Fcapitalize, Scapitalize, 1, 1, 0,
  "Convert argument to capitalized form and return that.\n\
This means that each word's first character is upper case\n\
and the rest is lower case.\n\
The argument may be a character or string.  The result has the same type.\n\
The argument object is not altered--the value is a copy.")
  (obj)
     Lisp_Object obj;
{
  return casify_object (CASE_CAPITALIZE, obj);
}

/* Like Fcapitalize but change only the initials.  */

DEFUN ("upcase-initials", Fupcase_initials, Supcase_initials, 1, 1, 0,
  "Convert the initial of each word in the argument to upper case.\n\
Do not change the other letters of each word.\n\
The argument may be a character or string.  The result has the same type.\n\
The argument object is not altered--the value is a copy.")
  (obj)
     Lisp_Object obj;
{
  return casify_object (CASE_CAPITALIZE_UP, obj);
}

/* flag is CASE_UP, CASE_DOWN or CASE_CAPITALIZE or CASE_CAPITALIZE_UP.
   b and e specify range of buffer to operate on. */

void
casify_region (flag, b, e)
     enum case_action flag;
     Lisp_Object b, e;
{
  register int i;
  register int c;
  register int inword = flag == CASE_DOWN;
  register int multibyte = !NILP (current_buffer->enable_multibyte_characters);
  int start, end;
  int start_byte, end_byte;

  if (EQ (b, e))
    /* Not modifying because nothing marked */
    return;

  /* If the case table is flagged as modified, rescan it.  */
  if (NILP (XCHAR_TABLE (current_buffer->downcase_table)->extras[1]))
    Fset_case_table (current_buffer->downcase_table);

  validate_region (&b, &e);
  start = XFASTINT (b);
  end = XFASTINT (e);
  modify_region (current_buffer, start, end);
  record_change (start, end - start);
  start_byte = CHAR_TO_BYTE (start);
  end_byte = CHAR_TO_BYTE (end);

  for (i = start_byte; i < end_byte; i++)
    {
      c = FETCH_BYTE (i);
      if (multibyte && c >= 0x80)
	/* A multibyte character can't be handled in this simple loop.  */
	break;
      if (inword && flag != CASE_CAPITALIZE_UP)
	c = DOWNCASE (c);
      else if (!UPPERCASEP (c)
	       && (!inword || flag != CASE_CAPITALIZE_UP))
	c = UPCASE1 (c);
      FETCH_BYTE (i) = c;
      if ((int) flag >= (int) CASE_CAPITALIZE)
	inword = SYNTAX (c) == Sword;
    }
  if (i < end_byte)
    {
      /* The work is not yet finished because of a multibyte character
	 just encountered.  */
      int opoint = PT;
      int opoint_byte = PT_BYTE;
      int c2;

      while (i < end_byte)
	{
	  if ((c = FETCH_BYTE (i)) >= 0x80)
	    c = FETCH_MULTIBYTE_CHAR (i);
	  c2 = c;
	  if (inword && flag != CASE_CAPITALIZE_UP)
	    c2 = DOWNCASE (c);
	  else if (!UPPERCASEP (c)
		   && (!inword || flag != CASE_CAPITALIZE_UP))
	    c2 = UPCASE1 (c);
	  if (c != c2)
	    {
	      int fromlen, tolen, j;
	      unsigned char workbuf[4], *str;

	      /* Handle the most likely case */
	      if (c < 0400 && c2 < 0400)
		FETCH_BYTE (i) = c2;
	      else if (fromlen = CHAR_STRING (c, workbuf, str),
		       tolen = CHAR_STRING (c2, workbuf, str),
		       fromlen == tolen)
		{
		  for (j = 0; j < tolen; ++j)
		    FETCH_BYTE (i + j) = str[j];
		}
	      else
		{
		  error ("Can't casify letters that change length");
#if 0 /* This is approximately what we'd like to be able to do here */
		  if (tolen < fromlen)
		    del_range_1 (i + tolen, i + fromlen, 0);
		  else if (tolen > fromlen)
		    {
		      TEMP_SET_PT (i + fromlen);
		      insert_1 (str + fromlen, tolen - fromlen, 1, 0, 0);
		    }
#endif
		}
	    }
	  if ((int) flag >= (int) CASE_CAPITALIZE)
	    inword = SYNTAX (c2) == Sword;
	  INC_POS (i);
	}
      TEMP_SET_PT_BOTH (opoint, opoint_byte);
    }

  signal_after_change (start, end - start, end - start);
}

DEFUN ("upcase-region", Fupcase_region, Supcase_region, 2, 2, "r",
  "Convert the region to upper case.  In programs, wants two arguments.\n\
These arguments specify the starting and ending character numbers of\n\
the region to operate on.  When used as a command, the text between\n\
point and the mark is operated on.\n\
See also `capitalize-region'.")
  (beg, end)
     Lisp_Object beg, end;
{
  casify_region (CASE_UP, beg, end);
  return Qnil;
}

DEFUN ("downcase-region", Fdowncase_region, Sdowncase_region, 2, 2, "r",
  "Convert the region to lower case.  In programs, wants two arguments.\n\
These arguments specify the starting and ending character numbers of\n\
the region to operate on.  When used as a command, the text between\n\
point and the mark is operated on.")
  (beg, end)
     Lisp_Object beg, end;
{
  casify_region (CASE_DOWN, beg, end);
  return Qnil;
}

DEFUN ("capitalize-region", Fcapitalize_region, Scapitalize_region, 2, 2, "r",
  "Convert the region to capitalized form.\n\
Capitalized form means each word's first character is upper case\n\
and the rest of it is lower case.\n\
In programs, give two arguments, the starting and ending\n\
character positions to operate on.")
  (beg, end)
     Lisp_Object beg, end;
{
  casify_region (CASE_CAPITALIZE, beg, end);
  return Qnil;
}

/* Like Fcapitalize_region but change only the initials.  */

DEFUN ("upcase-initials-region", Fupcase_initials_region,
       Supcase_initials_region, 2, 2, "r",
  "Upcase the initial of each word in the region.\n\
Subsequent letters of each word are not changed.\n\
In programs, give two arguments, the starting and ending\n\
character positions to operate on.")
  (beg, end)
     Lisp_Object beg, end;
{
  casify_region (CASE_CAPITALIZE_UP, beg, end);
  return Qnil;
}

Lisp_Object
operate_on_word (arg, newpoint)
     Lisp_Object arg;
     int *newpoint;
{
  Lisp_Object val;
  int farend;
  int iarg;

  CHECK_NUMBER (arg, 0);
  iarg = XINT (arg);
  farend = scan_words (PT, iarg);
  if (!farend)
    farend = iarg > 0 ? ZV : BEGV;

  *newpoint = PT > farend ? PT : farend;
  XSETFASTINT (val, farend);

  return val;
}

DEFUN ("upcase-word", Fupcase_word, Supcase_word, 1, 1, "p",
  "Convert following word (or ARG words) to upper case, moving over.\n\
With negative argument, convert previous words but do not move.\n\
See also `capitalize-word'.")
  (arg)
     Lisp_Object arg;
{
  Lisp_Object beg, end;
  int newpoint;
  XSETFASTINT (beg, PT);
  end = operate_on_word (arg, &newpoint);
  casify_region (CASE_UP, beg, end);
  SET_PT (newpoint);
  return Qnil;
}

DEFUN ("downcase-word", Fdowncase_word, Sdowncase_word, 1, 1, "p",
  "Convert following word (or ARG words) to lower case, moving over.\n\
With negative argument, convert previous words but do not move.")
  (arg)
     Lisp_Object arg;
{
  Lisp_Object beg, end;
  int newpoint;
  XSETFASTINT (beg, PT);
  end = operate_on_word (arg, &newpoint);
  casify_region (CASE_DOWN, beg, end);
  SET_PT (newpoint);
  return Qnil;
}

DEFUN ("capitalize-word", Fcapitalize_word, Scapitalize_word, 1, 1, "p",
  "Capitalize the following word (or ARG words), moving over.\n\
This gives the word(s) a first character in upper case\n\
and the rest lower case.\n\
With negative argument, capitalize previous words but do not move.")
  (arg)
     Lisp_Object arg;
{
  Lisp_Object beg, end;
  int newpoint;
  XSETFASTINT (beg, PT);
  end = operate_on_word (arg, &newpoint);
  casify_region (CASE_CAPITALIZE, beg, end);
  SET_PT (newpoint);
  return Qnil;
}

void
syms_of_casefiddle ()
{
  Qidentity = intern ("identity");
  staticpro (&Qidentity);
  defsubr (&Supcase);
  defsubr (&Sdowncase);
  defsubr (&Scapitalize);
  defsubr (&Supcase_initials);
  defsubr (&Supcase_region);
  defsubr (&Sdowncase_region);
  defsubr (&Scapitalize_region);
  defsubr (&Supcase_initials_region);
  defsubr (&Supcase_word);
  defsubr (&Sdowncase_word);
  defsubr (&Scapitalize_word);
}

void
keys_of_casefiddle ()
{
  initial_define_key (control_x_map, Ctl('U'), "upcase-region");
  Fput (intern ("upcase-region"), Qdisabled, Qt);
  initial_define_key (control_x_map, Ctl('L'), "downcase-region");
  Fput (intern ("downcase-region"), Qdisabled, Qt);

  initial_define_key (meta_map, 'u', "upcase-word");
  initial_define_key (meta_map, 'l', "downcase-word");
  initial_define_key (meta_map, 'c', "capitalize-word");
}