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: latin1.c,v 1.10 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 "latin1.h"
cannam@85: # include "ucs4.h"
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->length()
cannam@85:  * DESCRIPTION:	return the number of ucs4 chars represented by a latin1 string
cannam@85:  */
cannam@85: id3_length_t id3_latin1_length(id3_latin1_t const *latin1)
cannam@85: {
cannam@85:   id3_latin1_t const *ptr = latin1;
cannam@85: 
cannam@85:   while (*ptr)
cannam@85:     ++ptr;
cannam@85: 
cannam@85:   return ptr - latin1;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->size()
cannam@85:  * DESCRIPTION:	return the encoding size of a latin1 string
cannam@85:  */
cannam@85: id3_length_t id3_latin1_size(id3_latin1_t const *latin1)
cannam@85: {
cannam@85:   return id3_latin1_length(latin1) + 1;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->copy()
cannam@85:  * DESCRIPTION:	copy a latin1 string
cannam@85:  */
cannam@85: void id3_latin1_copy(id3_latin1_t *dest, id3_latin1_t const *src)
cannam@85: {
cannam@85:   while ((*dest++ = *src++))
cannam@85:     ;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->duplicate()
cannam@85:  * DESCRIPTION:	duplicate a latin1 string
cannam@85:  */
cannam@85: id3_latin1_t *id3_latin1_duplicate(id3_latin1_t const *src)
cannam@85: {
cannam@85:   id3_latin1_t *latin1;
cannam@85: 
cannam@85:   latin1 = malloc(id3_latin1_size(src) * sizeof(*latin1));
cannam@85:   if (latin1)
cannam@85:     id3_latin1_copy(latin1, src);
cannam@85: 
cannam@85:   return latin1;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->ucs4duplicate()
cannam@85:  * DESCRIPTION:	duplicate and decode a latin1 string into ucs4
cannam@85:  */
cannam@85: id3_ucs4_t *id3_latin1_ucs4duplicate(id3_latin1_t const *latin1)
cannam@85: {
cannam@85:   id3_ucs4_t *ucs4;
cannam@85: 
cannam@85:   ucs4 = malloc((id3_latin1_length(latin1) + 1) * sizeof(*ucs4));
cannam@85:   if (ucs4)
cannam@85:     id3_latin1_decode(latin1, ucs4);
cannam@85: 
cannam@85:   return release(ucs4);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->decodechar()
cannam@85:  * DESCRIPTION:	decode a (single) latin1 char into a single ucs4 char
cannam@85:  */
cannam@85: id3_length_t id3_latin1_decodechar(id3_latin1_t const *latin1,
cannam@85: 				   id3_ucs4_t *ucs4)
cannam@85: {
cannam@85:   *ucs4 = *latin1;
cannam@85: 
cannam@85:   return 1;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->encodechar()
cannam@85:  * DESCRIPTION:	encode a single ucs4 char into a (single) latin1 char
cannam@85:  */
cannam@85: id3_length_t id3_latin1_encodechar(id3_latin1_t *latin1, id3_ucs4_t ucs4)
cannam@85: {
cannam@85:   *latin1 = ucs4;
cannam@85:   if (ucs4 > 0x000000ffL)
cannam@85:     *latin1 = ID3_UCS4_REPLACEMENTCHAR;
cannam@85: 
cannam@85:   return 1;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->decode()
cannam@85:  * DESCRIPTION:	decode a complete latin1 string into a ucs4 string
cannam@85:  */
cannam@85: void id3_latin1_decode(id3_latin1_t const *latin1, id3_ucs4_t *ucs4)
cannam@85: {
cannam@85:   do
cannam@85:     latin1 += id3_latin1_decodechar(latin1, ucs4);
cannam@85:   while (*ucs4++);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->encode()
cannam@85:  * DESCRIPTION:	encode a complete ucs4 string into a latin1 string
cannam@85:  */
cannam@85: void id3_latin1_encode(id3_latin1_t *latin1, id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   do
cannam@85:     latin1 += id3_latin1_encodechar(latin1, *ucs4);
cannam@85:   while (*ucs4++);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->put()
cannam@85:  * DESCRIPTION:	serialize a single latin1 character
cannam@85:  */
cannam@85: id3_length_t id3_latin1_put(id3_byte_t **ptr, id3_latin1_t latin1)
cannam@85: {
cannam@85:   if (ptr)
cannam@85:     *(*ptr)++ = latin1;
cannam@85: 
cannam@85:   return 1;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->get()
cannam@85:  * DESCRIPTION:	deserialize a single latin1 character
cannam@85:  */
cannam@85: id3_latin1_t id3_latin1_get(id3_byte_t const **ptr)
cannam@85: {
cannam@85:   return *(*ptr)++;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->serialize()
cannam@85:  * DESCRIPTION:	serialize a ucs4 string using latin1 encoding
cannam@85:  */
cannam@85: id3_length_t id3_latin1_serialize(id3_byte_t **ptr, id3_ucs4_t const *ucs4,
cannam@85: 				  int terminate)
cannam@85: {
cannam@85:   id3_length_t size = 0;
cannam@85:   id3_latin1_t latin1[1], *out;
cannam@85: 
cannam@85:   while (*ucs4) {
cannam@85:     switch (id3_latin1_encodechar(out = latin1, *ucs4++)) {
cannam@85:     case 1: size += id3_latin1_put(ptr, *out++);
cannam@85:     case 0: break;
cannam@85:     }
cannam@85:   }
cannam@85: 
cannam@85:   if (terminate)
cannam@85:     size += id3_latin1_put(ptr, 0);
cannam@85: 
cannam@85:   return size;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	latin1->deserialize()
cannam@85:  * DESCRIPTION:	deserialize a ucs4 string using latin1 encoding
cannam@85:  */
cannam@85: id3_ucs4_t *id3_latin1_deserialize(id3_byte_t const **ptr, id3_length_t length)
cannam@85: {
cannam@85:   id3_byte_t const *end;
cannam@85:   id3_latin1_t *latin1ptr, *latin1;
cannam@85:   id3_ucs4_t *ucs4;
cannam@85: 
cannam@85:   end = *ptr + length;
cannam@85: 
cannam@85:   latin1 = malloc((length + 1) * sizeof(*latin1));
cannam@85:   if (latin1 == 0)
cannam@85:     return 0;
cannam@85: 
cannam@85:   latin1ptr = latin1;
cannam@85:   while (end - *ptr > 0 && (*latin1ptr = id3_latin1_get(ptr)))
cannam@85:     ++latin1ptr;
cannam@85: 
cannam@85:   *latin1ptr = 0;
cannam@85: 
cannam@85:   ucs4 = malloc((id3_latin1_length(latin1) + 1) * sizeof(*ucs4));
cannam@85:   if (ucs4)
cannam@85:     id3_latin1_decode(latin1, ucs4);
cannam@85: 
cannam@85:   free(latin1);
cannam@85: 
cannam@85:   return ucs4;
cannam@85: }