charset.c

在ｅｃｏｓ 下mingui 的移植开发

//
// $Id: charset.c,v 1.18 2000/11/17 12:28:04 ymwei Exp $
// 
// charset.c: The charset operation set.
// 
// Copyright (C) 2000, Wei Yongming.
// Copyright (C) 2000, BluePoint Software.
//
// Current maintainer: Wei Yongming.
//

/*
**  This library is free software; you can redistribute it and/or
**  modify it under the terms of the GNU Library General Public
**  License as published by the Free Software Foundation; either
**  version 2 of the License, or (at your option) any later version.
**
**  This library 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
**  Library General Public License for more details.
**
**  You should have received a copy of the GNU Library General Public
**  License along with this library; if not, write to the Free
**  Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
**  MA 02111-1307, USA
*/

// Create date: 2000/06/13
//
// Modify records:
//
//  Who             When        Where       For What                Status
//-----------------------------------------------------------------------------
//
// TODO:
//

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <assert.h>
#include <pthread.h>

#include "common.h"
#include "minigui.h"
#include "gdi.h"

#include "charset.h"

#ifndef lint
static char fileid[] = "$Id: charset.c,v 1.18 2000/11/17 12:28:04 ymwei Exp $";
#endif

/***************************** Common Operations *****************************/
static int sb_nr_chars_in_str (const unsigned char* mstr, int mstrlen)
{
    return mstrlen;
}

static int sb_len_first_substr (const unsigned char* mstr, int mstrlen)
{
    return mstrlen;
}

static int sb_pos_first_char (const unsigned char* mstr, int mstrlen)
{
    return 0;
}

#if defined(_GB_SUPPORT) | defined(_BIG5_SUPPORT) | defined(_JIS_SUPPORT)
static int db_nr_chars_in_str (const unsigned char* mstr, int mstrlen)
{
    assert ((mstrlen % 2) == 0);
    return mstrlen >> 1;
}

static const unsigned char* db_get_next_word (const unsigned char* mstr,
                int mstrlen, WORDINFO* word_info)
{
    assert ((mstrlen % 2) == 0);

    if (mstrlen == 0) return NULL;

    word_info->len = 2;
    word_info->delimiter = '\0';
    word_info->nr_delimiters = 0;

    return mstr + 2;
}
#endif

static unsigned short sb_conv_to_uc16 (const unsigned char* mchar, int len)
{
    return (unsigned short) (*mchar);
}

/************************* ISO8859-1 Specific Operations **********************/
static int iso8859_1_len_first_char (const unsigned char* mstr, int len)
{
    if (len < 1) return 0;
    if (*mstr != '\0')  return 1;
    return 0;
}

static int iso8859_1_char_offset (const unsigned char* mchar)
{
    return (int)(*mchar);
}

static int iso8859_1_is_this_charset (const unsigned char* charset)
{
    int i;
    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);        
    }
    name [i] = '\0';

    if (strstr (name, "ISO") && strstr (name, "8859") && strstr (name, "1"))
        return 0;

    return 1;
}

static const unsigned char* iso8859_1_get_next_word (const unsigned char* mstr,
                int mstrlen, WORDINFO* word_info)
{
    int i;

    if (mstrlen == 0) return NULL;

    word_info->len = 0;
    word_info->delimiter = '\0';
    word_info->nr_delimiters = 0;

    for (i = 0; i < mstrlen; i++) {
        switch (mstr [i]) {
        case ' ':
        case '\t':
        case '\n':
        case '\r':
            if (word_info->delimiter == '\0') {
                word_info->delimiter = mstr [i];
                word_info->nr_delimiters ++;
            }
            else if (word_info->delimiter == mstr[i])
                word_info->nr_delimiters ++;
            else
                return mstr + word_info->len + word_info->nr_delimiters;
        break;

        default:
            if (word_info->delimiter != '\0')
                break;

            word_info->len ++;
        }
    }
            
    return mstr + word_info->len + word_info->nr_delimiters;
}

static CHARSETOPS CharsetOps_iso8859_1 = {
    256,
    1,
    1,
    FONT_CHARSET_ISO8859_1,
    {' '},
    iso8859_1_len_first_char,
    iso8859_1_char_offset,
    sb_nr_chars_in_str,
    iso8859_1_is_this_charset,
    sb_len_first_substr,
    iso8859_1_get_next_word,
    sb_pos_first_char,
    sb_conv_to_uc16
};

#ifdef _GB_SUPPORT
/************************* GB2312 Specific Operations ************************/
static int gb2312_len_first_char (const unsigned char* mstr, int len)
{
    unsigned char ch1;
    unsigned char ch2;

    if (len < 2) return 0;

    ch1 = mstr [0];
    if (ch1 == '\0')
        return 0;

    ch2 = mstr [1];
    if (ch1 >= 0xA1 && ch1 <= 0xFE && ch2 >= 0xA1 && ch2 <= 0xFE)
        return 2;

    return 0;
}

static int gb2312_char_offset (const unsigned char* mchar)
{
    return ((mchar [0] - 0xA1) * 94 + mchar [1] - 0xA1);
}

static int gb2312_is_this_charset (const unsigned char* charset)
{
    int i;
    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);        
    }
    name [i] = '\0';

    if (strstr (name, "GB") && strstr (name, "2312"))
        return 0;

    return 1;
}

static int gb2312_len_first_substr (const unsigned char* mstr, int mstrlen)
{
    unsigned char ch1;
    unsigned char ch2;
    int i, left;
    int sub_len = 0;

    left = mstrlen;
    for (i = 0; i < mstrlen; i += 2) {
        if (left < 2) return sub_len;

        ch1 = mstr [i];
        if (ch1 == '\0') return sub_len;

        ch2 = mstr [i + 1];
        if (ch1 >= 0xA1 && ch1 <= 0xFE && ch2 >= 0xA1 && ch2 <= 0xFE)
            sub_len += 2;
        else
            return sub_len;

        left -= 2;
    }

    return sub_len;
}

static int gb2312_pos_first_char (const unsigned char* mstr, int mstrlen)
{
    unsigned char ch1;
    unsigned char ch2;
    int i, left;

    i = 0;
    left = mstrlen;
    while (left) {
        if (left < 2) return -1;

        ch1 = mstr [i];
        if (ch1 == '\0') return -1;

        ch2 = mstr [i + 1];
        if (ch1 >= 0xA1 && ch1 <= 0xFE && ch2 >= 0xA1 && ch2 <= 0xFE)
            return i;

        i += 1;
        left -= 1;
    }

    return -1;
}

static unsigned short gb2312_conv_to_uc16 (const unsigned char* mchar, int len)
{
    return gbunicode_map [gb2312_char_offset (mchar)];
}

static CHARSETOPS CharsetOps_gb2312 = {
    8836,
    2,
    2,
    FONT_CHARSET_GB2312_1980_0,
    {'\xA1', '\xA1'},
    gb2312_len_first_char,
    gb2312_char_offset,
    db_nr_chars_in_str,
    gb2312_is_this_charset,
    gb2312_len_first_substr,
    db_get_next_word,
    gb2312_pos_first_char,
    gb2312_conv_to_uc16
};
#endif /* _GB_SUPPORT */

#ifdef _BIG5_SUPPORT
/************************** BIG5 Specific Operations ************************/
static int big5_len_first_char (const unsigned char* mstr, int len)
{
    unsigned char ch1;
    unsigned char ch2;

    if (len < 2) return 0;

    ch1 = mstr [0];
    if (ch1 == '\0')
        return 0;

    ch2 = mstr [1];
    if (ch1 >= 0xA1 && ch1 <= 0xFE && 
            ((ch2 >=0x40 && ch2 <= 0x7E) || (ch2 >= 0xA1 && ch2 <= 0xFE)))
        return 2;

    return 0;
}

static int big5_char_offset (const unsigned char* mchar)
{
    if (mchar [1] & 0x80)
        return (mchar [0] - 0xA1) * 94 + mchar [1] - 0xA1;
    else
        return 94 * 94 + (mchar [0] - 0xa1) * 63 + (mchar [1] - 0x40);
}

static int big5_is_this_charset (const unsigned char* charset)
{
    int i;
    char name [LEN_FONT_NAME + 1];

    for (i = 0; i < LEN_FONT_NAME + 1; i++) {
        if (charset [i] == '\0')
            break;
        name [i] = toupper (charset [i]);        
    }
    name [i] = '\0';

    if (strstr (name, "BIG5"))
        return 0;

    return 1;
}

static int big5_len_first_substr (const unsigned char* mstr, int mstrlen)
{
    unsigned char ch1;
    unsigned char ch2;
    int i, left;
    int sub_len = 0;

    left = mstrlen;
    for (i = 0; i < mstrlen; i += 2) {
        if (left < 2) return sub_len;

        ch1 = mstr [i];
        if (ch1 == '\0') return sub_len;

        ch2 = mstr [i + 1];
        if (ch1 >= 0xA1 && ch1 <= 0xFE && 
                ((ch2 >=0x40 && ch2 <= 0x7E) || (ch2 >= 0xA1 && ch2 <= 0xFE)))
            sub_len += 2;
        else
            return sub_len;

        left -= 2;
    }

    return sub_len;
}

static int big5_pos_first_char (const unsigned char* mstr, int mstrlen)
{
    unsigned char ch1;
    unsigned char ch2;
    int i, left;

    i = 0;
    left = mstrlen;
    while (left) {
        if (left < 2) return -1;

        ch1 = mstr [i];
        if (ch1 == '\0') return -1;

        ch2 = mstr [i + 1];
        if (ch1 >= 0xA1 && ch1 <= 0xFE && 
                ((ch2 >=0x40 && ch2 <= 0x7E) || (ch2 >= 0xA1 && ch2 <= 0xFE)))
            return i;

        i += 1;
        left -= 1;
    }

    return -1;
}

static unsigned short big5_conv_to_uc16 (const unsigned char* mchar, int len)
{
    /* FIXME */
    return '?';
}

static CHARSETOPS CharsetOps_big5 = {
    14758,
    2,
    2,
    FONT_CHARSET_BIG5,
    {'\xA1', '\x40'},
    big5_len_first_char,
    big5_char_offset,
    db_nr_chars_in_str,
    big5_is_this_charset,
    big5_len_first_substr,
    db_get_next_word,
    big5_pos_first_char,
    big5_conv_to_uc16
};
#endif /* _BIG5_SUPPORT */

#ifdef _JIS_SUPPORT
/* TODO */
#endif

static CHARSETOPS* Charsets [] =
{
    &CharsetOps_iso8859_1,
#ifdef _GB_SUPPORT
    &CharsetOps_gb2312,
#endif
#ifdef _BIG5_SUPPORT
    &CharsetOps_big5,
#endif
#ifdef _JIS_SUPPORT
#endif
};

#define NR_CHARSETS     (sizeof(Charsets)/sizeof(CHARSETOPS*))

CHARSETOPS* GetCharsetOps (const char* charset_name)
{
    int i;

    for (i = 0; i < NR_CHARSETS; i++) {
        if ((*Charsets [i]->is_this_charset) (charset_name) == 0)
            return Charsets [i];
    }

    return NULL;
}