ObjFW  windows-1251.m at [5eaa7705ef]

File src/encodings/windows-1251.m artifact 18ae3df621 part of check-in 5eaa7705ef


/*
 * Copyright (c) 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017,
 *               2018, 2019, 2020
 *   Jonathan Schleifer <js@nil.im>
 *
 * All rights reserved.
 *
 * This file is part of ObjFW. It may be distributed under the terms of the
 * Q Public License 1.0, which can be found in the file LICENSE.QPL included in
 * the packaging of this file.
 *
 * Alternatively, it may be distributed under the terms of the GNU General
 * Public License, either version 2 or 3, which can be found in the file
 * LICENSE.GPLv2 or LICENSE.GPLv3 respectively included in the packaging of this
 * file.
 */

#include "config.h"

#import "OFString.h"

#import "common.h"

const of_char16_t of_windows_1251_table[] = {
	0x0402, 0x0403, 0x201A, 0x0453, 0x201E, 0x2026, 0x2020, 0x2021,
	0x20AC, 0x2030, 0x0409, 0x2039, 0x040A, 0x040C, 0x040B, 0x040F,
	0x0452, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
	0xFFFF, 0x2122, 0x0459, 0x203A, 0x045A, 0x045C, 0x045B, 0x045F,
	0x00A0, 0x040E, 0x045E, 0x0408, 0x00A4, 0x0490, 0x00A6, 0x00A7,
	0x0401, 0x00A9, 0x0404, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x0407,
	0x00B0, 0x00B1, 0x0406, 0x0456, 0x0491, 0x00B5, 0x00B6, 0x00B7,
	0x0451, 0x2116, 0x0454, 0x00BB, 0x0458, 0x0405, 0x0455, 0x0457,
	0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417,
	0x0418, 0x0419, 0x041A, 0x041B, 0x041C, 0x041D, 0x041E, 0x041F,
	0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427,
	0x0428, 0x0429, 0x042A, 0x042B, 0x042C, 0x042D, 0x042E, 0x042F,
	0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437,
	0x0438, 0x0439, 0x043A, 0x043B, 0x043C, 0x043D, 0x043E, 0x043F,
	0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447,
	0x0448, 0x0449, 0x044A, 0x044B, 0x044C, 0x044D, 0x044E, 0x044F
};
const size_t of_windows_1251_table_offset =
    256 - (sizeof(of_windows_1251_table) / sizeof(*of_windows_1251_table));

static const unsigned char page0[] = {
	0xA0, 0x00, 0x00, 0x00, 0xA4, 0x00, 0xA6, 0xA7,
	0x00, 0xA9, 0x00, 0xAB, 0xAC, 0xAD, 0xAE, 0x00,
	0xB0, 0xB1, 0x00, 0x00, 0x00, 0xB5, 0xB6, 0xB7,
	0x00, 0x00, 0x00, 0xBB
};
static const uint8_t page0Start = 0xA0;

static const unsigned char page4[] = {
	0xA8, 0x80, 0x81, 0xAA, 0xBD, 0xB2, 0xAF, 0xA3,
	0x8A, 0x8C, 0x8E, 0x8D, 0x00, 0xA1, 0x8F, 0xC0,
	0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8,
	0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xD0,
	0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7, 0xD8,
	0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0,
	0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8,
	0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xF0,
	0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8,
	0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF, 0x00,
	0xB8, 0x90, 0x83, 0xBA, 0xBE, 0xB3, 0xBF, 0xBC,
	0x9A, 0x9C, 0x9E, 0x9D, 0x00, 0xA2, 0x9F, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xA5,
	0xB4
};
static const uint8_t page4Start = 0x01;

static const unsigned char page20[] = {
	0x96, 0x97, 0x00, 0x00, 0x00, 0x91, 0x92, 0x82,
	0x00, 0x93, 0x94, 0x84, 0x00, 0x86, 0x87, 0x95,
	0x00, 0x00, 0x00, 0x85, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x89, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x8B, 0x9B,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x88
};
static const uint8_t page20Start = 0x13;

static const unsigned char page21[] = {
	0xB9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x99
};
static const uint8_t page21Start = 0x16;

bool
of_unicode_to_windows_1251(const of_unichar_t *input, unsigned char *output,
    size_t length, bool lossy)
{
	for (size_t i = 0; i < length; i++) {
		of_unichar_t c = input[i];

		if OF_UNLIKELY (c > 0x7F) {
			uint8_t idx;

			if OF_UNLIKELY (c > 0xFFFF) {
				if (lossy) {
					output[i] = '?';
					continue;
				} else
					return false;
			}

			switch (c >> 8) {
			CASE_MISSING_IS_ERROR(0)
			CASE_MISSING_IS_ERROR(4)
			CASE_MISSING_IS_ERROR(20)
			CASE_MISSING_IS_ERROR(21)
			default:
				if (lossy) {
					output[i] = '?';
					continue;
				} else
					return false;
			}
		} else
			output[i] = (unsigned char)c;
	}

	return true;
}