1
0
Fork 0
forked from len0rd/rockbox
foxbox/firmware/include/rbunicode.h
Solomon Peachy a2c10f6189 unicode: Support characters beyond the first unicode plane
We used 16-bit variables to store the 'character code' everywhere but
this won't let us represent anything beyond U+FFFF.

This patch changes those variables to a custom type that can be 32 or 16
bits depending on the build, and adjusts numerous internal APIs and
datastructures to match.  This includes:

 * utf8decode() and friends
 * font manipulation, caching, rendering, and generation
 * on-screen keyboard
 * FAT filesystem (parsing and generating utf16 LFNs)
 * WIN32 simulator platform code

Note that this patch doesn't _enable_ >16bit unicode support; a followup
patch will turn that on for appropriate targets.

Appears to work on:

  * hosted linux, native, linux simulator in both 16/32-bit modes.

Needs testing on:

  * windows and macos simulator (16bit+32bit)

Change-Id: Iba111b27d2433019b6bff937cf1ebd2c4353a0e8
2025-09-12 09:24:30 -04:00

85 lines
3.2 KiB
C

/***************************************************************************
* __________ __ ___.
* Open \______ \ ____ ____ | | _\_ |__ _______ ___
* Source | _// _ \_/ ___\| |/ /| __ \ / _ \ \/ /
* Jukebox | | ( <_> ) \___| < | \_\ ( <_> > < <
* Firmware |____|_ /\____/ \___ >__|_ \|___ /\____/__/\_ \
* \/ \/ \/ \/ \/
* $Id$
*
* Copyright (c) 2004,2005 by Marcoen Hirschberg
*
* This program 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
* of the License, or (at your option) any later version.
*
* This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
* KIND, either express or implied.
*
****************************************************************************/
/* Some conversion functions for handling UTF-8
*
* I got all the info from:
* http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
* and
* http://en.wikipedia.org/wiki/Unicode
*/
#ifndef _RBUNICODE_H_
#define _RBUNICODE_H_
#include "config.h"
#include <stdbool.h>
#define MASK 0xC0 /* 11000000 */
#define COMP 0x80 /* 10x */
enum codepages {
ISO_8859_1 = 0, /* Latin1 */
ISO_8859_7, /* Greek */
ISO_8859_8, /* Hebrew */
WIN_1251, /* Cyrillic */
ISO_8859_11, /* Thai */
WIN_1256, /* Arabic */
ISO_8859_9, /* Turkish */
ISO_8859_2, /* Latin Extended */
WIN_1250, /* Central European */
WIN_1252, /* Western European */
SJIS, /* Japanese */
GB_2312, /* Simp. Chinese */
KSX_1001, /* Korean */
BIG_5, /* Trad. Chinese */
UTF_8, /* Unicode */
NUM_CODEPAGES,
INIT_CODEPAGE = ISO_8859_1,
};
/* Encode a UCS value as UTF-8 and return a pointer after this UTF-8 char. */
unsigned char* utf8encode(unsigned long ucs, unsigned char *utf8);
unsigned char* iso_decode(const unsigned char *latin1, unsigned char *utf8, int cp, int count);
unsigned char* iso_decode_ex(const unsigned char *iso, unsigned char *utf8, int cp, int count, int utf8_size);
unsigned char* utf16LEdecode(const unsigned char *utf16, unsigned char *utf8, int count);
unsigned char* utf16BEdecode(const unsigned char *utf16, unsigned char *utf8, int count);
unsigned char* utf16decode(const unsigned char *utf16, unsigned char *utf8, int count, int utf8_size, bool le);
bool utf16_has_bom(const unsigned char *utf16, bool *le);
unsigned long utf16len_utf8(const unsigned char *utf8);
unsigned long utf8length(const unsigned char *utf8);
const unsigned char* utf8decode(const unsigned char *utf8, ucschar_t *ucs);
void set_codepage(int cp);
int get_codepage(void);
int utf8seek(const unsigned char* utf8, int offset);
const char* get_codepage_name(int cp);
#ifdef APPLICATION
#if defined(__linux__)
const char *get_current_codepage_name_linux(void);
#endif
#endif /* APPLICATION */
#if 0 /* not needed just now */
void unicode_init(void);
#else
#define unicode_init() do {} while (0)
#endif
#endif /* _RBUNICODE_H_ */