cannam@85: /*
cannam@85:  * libid3tag - ID3 tag manipulation library
cannam@85:  * Copyright (C) 2000-2004 Underbit Technologies, Inc.
cannam@85:  *
cannam@85:  * This program is free software; you can redistribute it and/or modify
cannam@85:  * it under the terms of the GNU General Public License as published by
cannam@85:  * the Free Software Foundation; either version 2 of the License, or
cannam@85:  * (at your option) any later version.
cannam@85:  *
cannam@85:  * This program is distributed in the hope that it will be useful,
cannam@85:  * but WITHOUT ANY WARRANTY; without even the implied warranty of
cannam@85:  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
cannam@85:  * GNU General Public License for more details.
cannam@85:  *
cannam@85:  * You should have received a copy of the GNU General Public License
cannam@85:  * along with this program; if not, write to the Free Software
cannam@85:  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
cannam@85:  *
cannam@85:  * $Id: ucs4.c,v 1.13 2004/01/23 09:41:32 rob Exp $
cannam@85:  */
cannam@85: 
cannam@85: # ifdef HAVE_CONFIG_H
cannam@85: #  include "config.h"
cannam@85: # endif
cannam@85: 
cannam@85: # include "global.h"
cannam@85: 
cannam@85: # include <stdlib.h>
cannam@85: 
cannam@85: # include "id3tag.h"
cannam@85: # include "ucs4.h"
cannam@85: # include "latin1.h"
cannam@85: # include "utf16.h"
cannam@85: # include "utf8.h"
cannam@85: 
cannam@85: id3_ucs4_t const id3_ucs4_empty[] = { 0 };
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->length()
cannam@85:  * DESCRIPTION:	return the number of ucs4 chars represented by a ucs4 string
cannam@85:  */
cannam@85: id3_length_t id3_ucs4_length(id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   id3_ucs4_t const *ptr = ucs4;
cannam@85: 
cannam@85:   while (*ptr)
cannam@85:     ++ptr;
cannam@85: 
cannam@85:   return ptr - ucs4;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->size()
cannam@85:  * DESCRIPTION:	return the encoding size of a ucs4 string
cannam@85:  */
cannam@85: id3_length_t id3_ucs4_size(id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   return id3_ucs4_length(ucs4) + 1;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->latin1size()
cannam@85:  * DESCRIPTION:	return the encoding size of a latin1-encoded ucs4 string
cannam@85:  */
cannam@85: id3_length_t id3_ucs4_latin1size(id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   return id3_ucs4_size(ucs4);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->utf16size()
cannam@85:  * DESCRIPTION:	return the encoding size of a utf16-encoded ucs4 string
cannam@85:  */
cannam@85: id3_length_t id3_ucs4_utf16size(id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   id3_length_t size = 0;
cannam@85: 
cannam@85:   while (*ucs4) {
cannam@85:     ++size;
cannam@85:     if (*ucs4 >= 0x00010000L &&
cannam@85: 	*ucs4 <= 0x0010ffffL)
cannam@85:       ++size;
cannam@85: 
cannam@85:     ++ucs4;
cannam@85:   }
cannam@85: 
cannam@85:   return size + 1;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->utf8size()
cannam@85:  * DESCRIPTION:	return the encoding size of a utf8-encoded ucs4 string
cannam@85:  */
cannam@85: id3_length_t id3_ucs4_utf8size(id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   id3_length_t size = 0;
cannam@85: 
cannam@85:   while (*ucs4) {
cannam@85:     if (*ucs4 <= 0x0000007fL)
cannam@85:       size += 1;
cannam@85:     else if (*ucs4 <= 0x000007ffL)
cannam@85:       size += 2;
cannam@85:     else if (*ucs4 <= 0x0000ffffL)
cannam@85:       size += 3;
cannam@85:     else if (*ucs4 <= 0x001fffffL)
cannam@85:       size += 4;
cannam@85:     else if (*ucs4 <= 0x03ffffffL)
cannam@85:       size += 5;
cannam@85:     else if (*ucs4 <= 0x7fffffffL)
cannam@85:       size += 6;
cannam@85:     else
cannam@85:       size += 2;  /* based on U+00B7 replacement char */
cannam@85: 
cannam@85:     ++ucs4;
cannam@85:   }
cannam@85: 
cannam@85:   return size + 1;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->latin1duplicate()
cannam@85:  * DESCRIPTION:	duplicate and encode a ucs4 string into latin1
cannam@85:  */
cannam@85: id3_latin1_t *id3_ucs4_latin1duplicate(id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   id3_latin1_t *latin1;
cannam@85: 
cannam@85:   latin1 = malloc(id3_ucs4_latin1size(ucs4) * sizeof(*latin1));
cannam@85:   if (latin1)
cannam@85:     id3_latin1_encode(latin1, ucs4);
cannam@85: 
cannam@85:   return release(latin1);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->utf16duplicate()
cannam@85:  * DESCRIPTION:	duplicate and encode a ucs4 string into utf16
cannam@85:  */
cannam@85: id3_utf16_t *id3_ucs4_utf16duplicate(id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   id3_utf16_t *utf16;
cannam@85: 
cannam@85:   utf16 = malloc(id3_ucs4_utf16size(ucs4) * sizeof(*utf16));
cannam@85:   if (utf16)
cannam@85:     id3_utf16_encode(utf16, ucs4);
cannam@85: 
cannam@85:   return release(utf16);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->utf8duplicate()
cannam@85:  * DESCRIPTION:	duplicate and encode a ucs4 string into utf8
cannam@85:  */
cannam@85: id3_utf8_t *id3_ucs4_utf8duplicate(id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   id3_utf8_t *utf8;
cannam@85: 
cannam@85:   utf8 = malloc(id3_ucs4_utf8size(ucs4) * sizeof(*utf8));
cannam@85:   if (utf8)
cannam@85:     id3_utf8_encode(utf8, ucs4);
cannam@85: 
cannam@85:   return release(utf8);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->copy()
cannam@85:  * DESCRIPTION:	copy a ucs4 string
cannam@85:  */
cannam@85: void id3_ucs4_copy(id3_ucs4_t *dest, id3_ucs4_t const *src)
cannam@85: {
cannam@85:   while ((*dest++ = *src++))
cannam@85:     ;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->duplicate()
cannam@85:  * DESCRIPTION:	duplicate a ucs4 string
cannam@85:  */
cannam@85: id3_ucs4_t *id3_ucs4_duplicate(id3_ucs4_t const *src)
cannam@85: {
cannam@85:   id3_ucs4_t *ucs4;
cannam@85: 
cannam@85:   ucs4 = malloc(id3_ucs4_size(src) * sizeof(*ucs4));
cannam@85:   if (ucs4)
cannam@85:     id3_ucs4_copy(ucs4, src);
cannam@85: 
cannam@85:   return ucs4;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->putnumber()
cannam@85:  * DESCRIPTION:	write a ucs4 string containing a (positive) decimal number
cannam@85:  */
cannam@85: void id3_ucs4_putnumber(id3_ucs4_t *ucs4, unsigned long number)
cannam@85: {
cannam@85:   int digits[10], *digit;
cannam@85: 
cannam@85:   digit = digits;
cannam@85: 
cannam@85:   do {
cannam@85:     *digit++ = number % 10;
cannam@85:     number  /= 10;
cannam@85:   }
cannam@85:   while (number);
cannam@85: 
cannam@85:   while (digit != digits)
cannam@85:     *ucs4++ = '0' + *--digit;
cannam@85: 
cannam@85:   *ucs4 = 0;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	ucs4->getnumber()
cannam@85:  * DESCRIPTION:	read a ucs4 string containing a (positive) decimal number
cannam@85:  */
cannam@85: unsigned long id3_ucs4_getnumber(id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   unsigned long number = 0;
cannam@85: 
cannam@85:   while (*ucs4 >= '0' && *ucs4 <= '9')
cannam@85:     number = 10 * number + (*ucs4++ - '0');
cannam@85: 
cannam@85:   return number;
cannam@85: }