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: utf16.c,v 1.9 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 "utf16.h"
cannam@85: # include "ucs4.h"
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->length()
cannam@85:  * DESCRIPTION:	return the number of ucs4 chars represented by a utf16 string
cannam@85:  */
cannam@85: id3_length_t id3_utf16_length(id3_utf16_t const *utf16)
cannam@85: {
cannam@85:   id3_length_t length = 0;
cannam@85: 
cannam@85:   while (*utf16) {
cannam@85:     if (utf16[0] < 0xd800 || utf16[0] > 0xdfff)
cannam@85:       ++length;
cannam@85:     else if (utf16[0] >= 0xd800 && utf16[0] <= 0xdbff &&
cannam@85: 	     utf16[1] >= 0xdc00 && utf16[1] <= 0xdfff) {
cannam@85:       ++length;
cannam@85:       ++utf16;
cannam@85:     }
cannam@85: 
cannam@85:     ++utf16;
cannam@85:   }
cannam@85: 
cannam@85:   return length;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->size()
cannam@85:  * DESCRIPTION:	return the encoding size of a utf16 string
cannam@85:  */
cannam@85: id3_length_t id3_utf16_size(id3_utf16_t const *utf16)
cannam@85: {
cannam@85:   id3_utf16_t const *ptr = utf16;
cannam@85: 
cannam@85:   while (*ptr)
cannam@85:     ++ptr;
cannam@85: 
cannam@85:   return ptr - utf16 + 1;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->ucs4duplicate()
cannam@85:  * DESCRIPTION:	duplicate and decode a utf16 string into ucs4
cannam@85:  */
cannam@85: id3_ucs4_t *id3_utf16_ucs4duplicate(id3_utf16_t const *utf16)
cannam@85: {
cannam@85:   id3_ucs4_t *ucs4;
cannam@85: 
cannam@85:   ucs4 = malloc((id3_utf16_length(utf16) + 1) * sizeof(*ucs4));
cannam@85:   if (ucs4)
cannam@85:     id3_utf16_decode(utf16, ucs4);
cannam@85: 
cannam@85:   return release(ucs4);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->decodechar()
cannam@85:  * DESCRIPTION:	decode a series of utf16 chars into a single ucs4 char
cannam@85:  */
cannam@85: id3_length_t id3_utf16_decodechar(id3_utf16_t const *utf16, id3_ucs4_t *ucs4)
cannam@85: {
cannam@85:   id3_utf16_t const *start = utf16;
cannam@85: 
cannam@85:   while (1) {
cannam@85:     if (utf16[0] < 0xd800 || utf16[0] > 0xdfff) {
cannam@85:       *ucs4 = utf16[0];
cannam@85:       return utf16 - start + 1;
cannam@85:     }
cannam@85:     else if (utf16[0] >= 0xd800 && utf16[0] <= 0xdbff &&
cannam@85: 	     utf16[1] >= 0xdc00 && utf16[1] <= 0xdfff) {
cannam@85:       *ucs4 = (((utf16[0] & 0x03ffL) << 10) |
cannam@85: 	       ((utf16[1] & 0x03ffL) <<  0)) + 0x00010000L;
cannam@85:       return utf16 - start + 2;
cannam@85:     }
cannam@85: 
cannam@85:     ++utf16;
cannam@85:   }
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->encodechar()
cannam@85:  * DESCRIPTION:	encode a single ucs4 char into a series of up to 2 utf16 chars
cannam@85:  */
cannam@85: id3_length_t id3_utf16_encodechar(id3_utf16_t *utf16, id3_ucs4_t ucs4)
cannam@85: {
cannam@85:   if (ucs4 < 0x00010000L) {
cannam@85:     utf16[0] = ucs4;
cannam@85: 
cannam@85:     return 1;
cannam@85:   }
cannam@85:   else if (ucs4 < 0x00110000L) {
cannam@85:     ucs4 -= 0x00010000L;
cannam@85: 
cannam@85:     utf16[0] = ((ucs4 >> 10) & 0x3ff) | 0xd800;
cannam@85:     utf16[1] = ((ucs4 >>  0) & 0x3ff) | 0xdc00;
cannam@85: 
cannam@85:     return 2;
cannam@85:   }
cannam@85: 
cannam@85:   /* default */
cannam@85: 
cannam@85:   return id3_utf16_encodechar(utf16, ID3_UCS4_REPLACEMENTCHAR);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->decode()
cannam@85:  * DESCRIPTION:	decode a complete utf16 string into a ucs4 string
cannam@85:  */
cannam@85: void id3_utf16_decode(id3_utf16_t const *utf16, id3_ucs4_t *ucs4)
cannam@85: {
cannam@85:   do
cannam@85:     utf16 += id3_utf16_decodechar(utf16, ucs4);
cannam@85:   while (*ucs4++);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->encode()
cannam@85:  * DESCRIPTION:	encode a complete ucs4 string into a utf16 string
cannam@85:  */
cannam@85: void id3_utf16_encode(id3_utf16_t *utf16, id3_ucs4_t const *ucs4)
cannam@85: {
cannam@85:   do
cannam@85:     utf16 += id3_utf16_encodechar(utf16, *ucs4);
cannam@85:   while (*ucs4++);
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->put()
cannam@85:  * DESCRIPTION:	serialize a single utf16 character
cannam@85:  */
cannam@85: id3_length_t id3_utf16_put(id3_byte_t **ptr, id3_utf16_t utf16,
cannam@85: 			   enum id3_utf16_byteorder byteorder)
cannam@85: {
cannam@85:   if (ptr) {
cannam@85:     switch (byteorder) {
cannam@85:     default:
cannam@85:     case ID3_UTF16_BYTEORDER_BE:
cannam@85:       (*ptr)[0] = (utf16 >> 8) & 0xff;
cannam@85:       (*ptr)[1] = (utf16 >> 0) & 0xff;
cannam@85:       break;
cannam@85: 
cannam@85:     case ID3_UTF16_BYTEORDER_LE:
cannam@85:       (*ptr)[0] = (utf16 >> 0) & 0xff;
cannam@85:       (*ptr)[1] = (utf16 >> 8) & 0xff;
cannam@85:       break;
cannam@85:     }
cannam@85: 
cannam@85:     *ptr += 2;
cannam@85:   }
cannam@85: 
cannam@85:   return 2;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->get()
cannam@85:  * DESCRIPTION:	deserialize a single utf16 character
cannam@85:  */
cannam@85: id3_utf16_t id3_utf16_get(id3_byte_t const **ptr,
cannam@85: 			  enum id3_utf16_byteorder byteorder)
cannam@85: {
cannam@85:   id3_utf16_t utf16;
cannam@85: 
cannam@85:   switch (byteorder) {
cannam@85:   default:
cannam@85:   case ID3_UTF16_BYTEORDER_BE:
cannam@85:     utf16 =
cannam@85:       ((*ptr)[0] << 8) |
cannam@85:       ((*ptr)[1] << 0);
cannam@85:     break;
cannam@85: 
cannam@85:   case ID3_UTF16_BYTEORDER_LE:
cannam@85:     utf16 =
cannam@85:       ((*ptr)[0] << 0) |
cannam@85:       ((*ptr)[1] << 8);
cannam@85:     break;
cannam@85:   }
cannam@85: 
cannam@85:   *ptr += 2;
cannam@85: 
cannam@85:   return utf16;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->serialize()
cannam@85:  * DESCRIPTION:	serialize a ucs4 string using utf16 encoding
cannam@85:  */
cannam@85: id3_length_t id3_utf16_serialize(id3_byte_t **ptr, id3_ucs4_t const *ucs4,
cannam@85: 				 enum id3_utf16_byteorder byteorder,
cannam@85: 				 int terminate)
cannam@85: {
cannam@85:   id3_length_t size = 0;
cannam@85:   id3_utf16_t utf16[2], *out;
cannam@85: 
cannam@85:   if (byteorder == ID3_UTF16_BYTEORDER_ANY)
cannam@85:     size += id3_utf16_put(ptr, 0xfeff, byteorder);
cannam@85: 
cannam@85:   while (*ucs4) {
cannam@85:     switch (id3_utf16_encodechar(out = utf16, *ucs4++)) {
cannam@85:     case 2: size += id3_utf16_put(ptr, *out++, byteorder);
cannam@85:     case 1: size += id3_utf16_put(ptr, *out++, byteorder);
cannam@85:     case 0: break;
cannam@85:     }
cannam@85:   }
cannam@85: 
cannam@85:   if (terminate)
cannam@85:     size += id3_utf16_put(ptr, 0, byteorder);
cannam@85: 
cannam@85:   return size;
cannam@85: }
cannam@85: 
cannam@85: /*
cannam@85:  * NAME:	utf16->deserialize()
cannam@85:  * DESCRIPTION:	deserialize a ucs4 string using utf16 encoding
cannam@85:  */
cannam@85: id3_ucs4_t *id3_utf16_deserialize(id3_byte_t const **ptr, id3_length_t length,
cannam@85: 				  enum id3_utf16_byteorder byteorder)
cannam@85: {
cannam@85:   id3_byte_t const *end;
cannam@85:   id3_utf16_t *utf16ptr, *utf16;
cannam@85:   id3_ucs4_t *ucs4;
cannam@85: 
cannam@85:   end = *ptr + (length & ~1);
cannam@85: 
cannam@85:   utf16 = malloc((length / 2 + 1) * sizeof(*utf16));
cannam@85:   if (utf16 == 0)
cannam@85:     return 0;
cannam@85: 
cannam@85:   if (byteorder == ID3_UTF16_BYTEORDER_ANY && end - *ptr > 0) {
cannam@85:     switch (((*ptr)[0] << 8) |
cannam@85: 	    ((*ptr)[1] << 0)) {
cannam@85:     case 0xfeff:
cannam@85:       byteorder = ID3_UTF16_BYTEORDER_BE;
cannam@85:       *ptr += 2;
cannam@85:       break;
cannam@85: 
cannam@85:     case 0xfffe:
cannam@85:       byteorder = ID3_UTF16_BYTEORDER_LE;
cannam@85:       *ptr += 2;
cannam@85:       break;
cannam@85:     }
cannam@85:   }
cannam@85: 
cannam@85:   utf16ptr = utf16;
cannam@85:   while (end - *ptr > 0 && (*utf16ptr = id3_utf16_get(ptr, byteorder)))
cannam@85:     ++utf16ptr;
cannam@85: 
cannam@85:   *utf16ptr = 0;
cannam@85: 
cannam@85:   ucs4 = malloc((id3_utf16_length(utf16) + 1) * sizeof(*ucs4));
cannam@85:   if (ucs4)
cannam@85:     id3_utf16_decode(utf16, ucs4);
cannam@85: 
cannam@85:   free(utf16);
cannam@85: 
cannam@85:   return ucs4;
cannam@85: }