view src/casefiddle.c @ 3767:6b2ef948e140

[xemacs-hg @ 2006-12-29 18:09:38 by aidan] etc/ChangeLog addition: 2006-12-21 Aidan Kehoe <kehoea@parhasard.net> * unicode/unicode-consortium/8859-7.TXT: Update the mapping to the 2003 version of ISO 8859-7. lisp/ChangeLog addition: 2006-12-21 Aidan Kehoe <kehoea@parhasard.net> * mule/cyrillic.el: * mule/cyrillic.el (iso-8859-5): * mule/cyrillic.el (cyrillic-koi8-r-encode-table): Add syntax, case support for Cyrillic; make some parentheses more Lispy. * mule/european.el: Content moved to latin.el, file deleted. * mule/general-late.el: If Unicode tables are to be loaded at dump time, do it here, not in loadup.el. * mule/greek.el: Add syntax, case support for Greek. * mule/latin.el: Move the content of european.el here. Change the case table mappings to use hexadecimal codes, to make cross reference to the standards easier. In all cases, take character syntax from similar characters in Latin-1 , rather than deciding separately what syntax they should take. Add (incomplete) support for case with Turkish. Remove description of the character sets used from the language environments' doc strings, since now that we create variant language environments on the fly, such descriptions will often be inaccurate. Set the native-coding-system language info property while setting the other coding-system properties of the language. * mule/misc-lang.el (ipa): Remove the language environment. The International Phonetic _Alphabet_ is not a language, it's inane to have a corresponding language environment in XEmacs. * mule/mule-cmds.el (create-variant-language-environment): Also modify the coding-priority when creating a new language environment; document that. * mule/mule-cmds.el (get-language-environment-from-locale): Recognise that the 'native-coding-system language-info property can be a list, interpret it correctly when it is one. 2006-12-21 Aidan Kehoe <kehoea@parhasard.net> * coding.el (coding-system-category): Use the new 'unicode-type property for finding what sort of Unicode coding system subtype a coding system is, instead of the overshadowed 'type property. * dumped-lisp.el (preloaded-file-list): mule/european.el has been removed. * loadup.el (really-early-error-handler): Unicode tables loaded at dump time are now in mule/general-late.el. * simple.el (count-lines): Add some backslashes to to parentheses in docstrings to help fontification along. * simple.el (what-cursor-position): Wrap a line to fit in 80 characters. * unicode.el: Use the 'unicode-type property, not 'type, for setting the Unicode coding-system subtype. src/ChangeLog addition: 2006-12-21 Aidan Kehoe <kehoea@parhasard.net> * file-coding.c: Update the make-coding-system docstring to reflect unicode-type * general-slots.h: New symbol, unicode-type, since 'type was being overridden when accessing a coding system's Unicode subtype. * intl-win32.c: Backslash a few parentheses, to help fontification along. * intl-win32.c (complex_vars_of_intl_win32): Use the 'unicode-type symbol, not 'type, when creating the Microsoft Unicode coding system. * unicode.c (unicode_putprop): * unicode.c (unicode_getprop): * unicode.c (unicode_print): Using 'type as the property name when working out what Unicode subtype a given coding system is was broken, since there's a general coding system property called 'type. Change the former to use 'unicode-type instead.
author aidan
date Fri, 29 Dec 2006 18:09:51 +0000
parents ecf1ebac70d8
children 6bc1f3f6cf0d
line wrap: on
line source

/* XEmacs case conversion functions.
   Copyright (C) 1985, 1992, 1993, 1994, 1997, 1998 Free Software Foundation, Inc.
   Copyright (C) 2002 Ben Wing.

This file is part of XEmacs.

XEmacs 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.

XEmacs 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 XEmacs; see the file COPYING.  If not, write to
the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA.  */

/* Synched up with: FSF 19.34, but substantially rewritten by Martin. */

#include <config.h>
#include "lisp.h"

#include "buffer.h"
#include "insdel.h"
#include "syntax.h"

enum case_action {CASE_UP, CASE_DOWN, CASE_CAPITALIZE, CASE_CAPITALIZE_UP};

static Lisp_Object
casify_object (enum case_action flag, Lisp_Object string_or_char,
	       Lisp_Object buffer)
{
  struct buffer *buf = decode_buffer (buffer, 0);

 retry:

  if (CHAR_OR_CHAR_INTP (string_or_char))
    {
      Ichar c;
      CHECK_CHAR_COERCE_INT (string_or_char);
      c = XCHAR (string_or_char);
      c = (flag == CASE_DOWN) ? DOWNCASE (buf, c) : UPCASE (buf, c);
      return make_char (c);
    }

  if (STRINGP (string_or_char))
    {
      Lisp_Object syntax_table = buf->mirror_syntax_table;
      Ibyte *storage =
	alloca_ibytes (XSTRING_LENGTH (string_or_char) * MAX_ICHAR_LEN);
      Ibyte *newp = storage;
      Ibyte *oldp = XSTRING_DATA (string_or_char);
      Ibyte *endp = oldp + XSTRING_LENGTH (string_or_char);
      int wordp = 0, wordp_prev;

      while (oldp < endp)
	{
	  Ichar c = itext_ichar (oldp);
	  switch (flag)
	    {
	    case CASE_UP:
	      c = UPCASE (buf, c);
	      break;
	    case CASE_DOWN:
	      c = DOWNCASE (buf, c);
	      break;
	    case CASE_CAPITALIZE:
	    case CASE_CAPITALIZE_UP:
	      wordp_prev = wordp;
	      wordp = WORD_SYNTAX_P (syntax_table, c);
	      if (!wordp) break;
	      if (wordp_prev)
		{
		  if (flag == CASE_CAPITALIZE)
		    c = DOWNCASE (buf, c);
		}
	      else
		c = UPCASE (buf, c);
	      break;
	    }

	  newp += set_itext_ichar (newp, c);
	  INC_IBYTEPTR (oldp);
	}

      return make_string (storage, newp - storage);
    }

  string_or_char = wrong_type_argument (Qchar_or_string_p, string_or_char);
  goto retry;
}

DEFUN ("upcase", Fupcase, 1, 2, 0, /*
Convert STRING-OR-CHAR to upper case and return that.
STRING-OR-CHAR may be a character or string.  The result has the same type.
STRING-OR-CHAR is not altered--the value is a copy.
See also `capitalize', `downcase' and `upcase-initials'.
Optional second arg BUFFER specifies which buffer's case tables to use,
 and defaults to the current buffer.
*/
       (string_or_char, buffer))
{
  return casify_object (CASE_UP, string_or_char, buffer);
}

DEFUN ("downcase", Fdowncase, 1, 2, 0, /*
Convert STRING-OR-CHAR to lower case and return that.
STRING-OR-CHAR may be a character or string.  The result has the same type.
STRING-OR-CHAR is not altered--the value is a copy.
Optional second arg BUFFER specifies which buffer's case tables to use,
 and defaults to the current buffer.
*/
       (string_or_char, buffer))
{
  return casify_object (CASE_DOWN, string_or_char, buffer);
}

DEFUN ("capitalize", Fcapitalize, 1, 2, 0, /*
Convert STRING-OR-CHAR to capitalized form and return that.
This means that each word's first character is upper case
and the rest is lower case.
STRING-OR-CHAR may be a character or string.  The result has the same type.
STRING-OR-CHAR is not altered--the value is a copy.
Optional second arg BUFFER specifies which buffer's case tables to use,
 and defaults to the current buffer.
*/
       (string_or_char, buffer))
{
  return casify_object (CASE_CAPITALIZE, string_or_char, buffer);
}

/* Like Fcapitalize but change only the initial characters.  */

DEFUN ("upcase-initials", Fupcase_initials, 1, 2, 0, /*
Convert the initial of each word in STRING-OR-CHAR to upper case.
Do not change the other letters of each word.
STRING-OR-CHAR may be a character or string.  The result has the same type.
STRING-OR-CHAR is not altered--the value is a copy.
Optional second arg BUFFER specifies which buffer's case tables to use,
 and defaults to the current buffer.
*/
       (string_or_char, buffer))
{
  return casify_object (CASE_CAPITALIZE_UP, string_or_char, buffer);
}

/* flag is CASE_UP, CASE_DOWN or CASE_CAPITALIZE or CASE_CAPITALIZE_UP.
   START and END specify range of buffer to operate on. */

static void
casify_region_internal (enum case_action flag, Lisp_Object start,
			Lisp_Object end, struct buffer *buf)
{
  /* This function can GC */
  Charbpos pos, s, e;
  Lisp_Object syntax_table = buf->mirror_syntax_table;
  int mccount;
  int wordp = 0, wordp_prev;

  if (EQ (start, end))
    /* Not modifying because nothing marked */
    return;

  get_buffer_range_char (buf, start, end, &s, &e, 0);

  mccount = begin_multiple_change (buf, s, e);
  record_change (buf, s, e - s);

  for (pos = s; pos < e; pos++)
    {
      Ichar oldc = BUF_FETCH_CHAR (buf, pos);
      Ichar c = oldc;

      switch (flag)
	{
	case CASE_UP:
	  c = UPCASE (buf, oldc);
	  break;
	case CASE_DOWN:
	  c = DOWNCASE (buf, oldc);
	  break;
	case CASE_CAPITALIZE:
	case CASE_CAPITALIZE_UP:
	  /* !!#### need to revalidate the start and end pointers in case
	     the buffer was changed */
	  wordp_prev = wordp;
	  wordp = WORD_SYNTAX_P (syntax_table, c);
	  if (!wordp) continue;
	  if (wordp_prev)
	    {
	      if (flag == CASE_CAPITALIZE)
		c = DOWNCASE (buf, c);
	    }
	  else
	    c = UPCASE (buf, c);
	  break;
	}

      if (oldc == c) continue;
      buffer_replace_char (buf, pos, c, 1, (pos == s));
      BUF_MODIFF (buf)++;
    }

  end_multiple_change (buf, mccount);
}

static Lisp_Object
casify_region (enum case_action flag, Lisp_Object start, Lisp_Object end,
	       Lisp_Object buffer)
{
  casify_region_internal (flag, start, end, decode_buffer (buffer, 1));
  return Qnil;
}

DEFUN ("upcase-region", Fupcase_region, 2, 3, "r", /*
Convert the region to upper case.  In programs, wants two arguments.
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.
See also `capitalize-region'.
Optional third arg BUFFER defaults to the current buffer.
*/
       (start, end, buffer))
{
  /* This function can GC */
  return casify_region (CASE_UP, start, end, buffer);
}

DEFUN ("downcase-region", Fdowncase_region, 2, 3, "r", /*
Convert the region to lower case.  In programs, wants two arguments.
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.
Optional third arg BUFFER defaults to the current buffer.
*/
       (start, end, buffer))
{
  /* This function can GC */
  return casify_region (CASE_DOWN, start, end, buffer);
}

DEFUN ("capitalize-region", Fcapitalize_region, 2, 3, "r", /*
Convert the region to capitalized form.
Capitalized form means each word's first character is upper case
 and the rest of it is lower case.
In programs, give two arguments, the starting and ending
 character positions to operate on.
Optional third arg BUFFER defaults to the current buffer.
*/
       (start, end, buffer))
{
  /* This function can GC */
  return casify_region (CASE_CAPITALIZE, start, end, buffer);
}

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

DEFUN ("upcase-initials-region", Fupcase_initials_region, 2, 3, "r", /*
Upcase the initial of each word in the region.
Subsequent letters of each word are not changed.
In programs, give two arguments, the starting and ending
 character positions to operate on.
Optional third arg BUFFER defaults to the current buffer.
*/
       (start, end, buffer))
{
  return casify_region (CASE_CAPITALIZE_UP, start, end, buffer);
}


static Lisp_Object
casify_word (enum case_action flag, Lisp_Object arg, Lisp_Object buffer)
{
  Charbpos farend;
  struct buffer *buf = decode_buffer (buffer, 1);

  CHECK_INT (arg);

  farend = scan_words (buf, BUF_PT (buf), XINT (arg));
  if (!farend)
    farend = XINT (arg) > 0 ? BUF_ZV (buf) : BUF_BEGV (buf);

  casify_region_internal (flag, make_int (BUF_PT (buf)), make_int (farend), buf);
  BUF_SET_PT (buf, max (BUF_PT (buf), farend));
  return Qnil;
}

DEFUN ("upcase-word", Fupcase_word, 1, 2, "p", /*
Convert following word (or COUNT words) to upper case, moving over.
With negative argument, convert previous words but do not move.
See also `capitalize-word'.
Optional second arg BUFFER defaults to the current buffer.
*/
       (count, buffer))
{
  /* This function can GC */
  return casify_word (CASE_UP, count, buffer);
}

DEFUN ("downcase-word", Fdowncase_word, 1, 2, "p", /*
Convert following word (or COUNT words) to lower case, moving over.
With negative argument, convert previous words but do not move.
Optional second arg BUFFER defaults to the current buffer.
*/
       (count, buffer))
{
  /* This function can GC */
  return casify_word (CASE_DOWN, count, buffer);
}

DEFUN ("capitalize-word", Fcapitalize_word, 1, 2, "p", /*
Capitalize the following word (or COUNT words), moving over.
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.
Optional second arg BUFFER defaults to the current buffer.
*/
       (count, buffer))
{
  /* This function can GC */
  return casify_word (CASE_CAPITALIZE, count, buffer);
}


void
syms_of_casefiddle (void)
{
  DEFSUBR (Fupcase);
  DEFSUBR (Fdowncase);
  DEFSUBR (Fcapitalize);
  DEFSUBR (Fupcase_initials);
  DEFSUBR (Fupcase_region);
  DEFSUBR (Fdowncase_region);
  DEFSUBR (Fcapitalize_region);
  DEFSUBR (Fupcase_initials_region);
  DEFSUBR (Fupcase_word);
  DEFSUBR (Fdowncase_word);
  DEFSUBR (Fcapitalize_word);
}