aboutsummaryrefslogtreecommitdiff
path: root/engines/wintermute/utils/string_util.cpp
blob: b17c5446b756dc21fee4c36d48646e6ae8265df0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
/* ScummVM - Graphic Adventure Engine
 *
 * ScummVM is the legal property of its developers, whose names
 * are too numerous to list here. Please refer to the COPYRIGHT
 * file distributed with this source distribution.
 *
 * 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 program 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 General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
 *
 */

/*
 * This file is based on WME Lite.
 * http://dead-code.org/redir.php?target=wmelite
 * Copyright (c) 2011 Jan Nedoma
 */

#include "common/language.h"
#include "common/tokenizer.h"
#include "engines/wintermute/base/base_engine.h"
#include "engines/wintermute/utils/string_util.h"
#include "engines/wintermute/utils/convert_utf.h"

namespace Wintermute {

//////////////////////////////////////////////////////////////////////////
bool StringUtil::compareNoCase(const AnsiString &str1, const AnsiString &str2) {
	return (str1.compareToIgnoreCase(str2) == 0);
}

//////////////////////////////////////////////////////////////////////////
/*bool StringUtil::CompareNoCase(const WideString &str1, const WideString &str2) {
    WideString str1lc = str1;
    WideString str2lc = str2;

    ToLowerCase(str1lc);
    ToLowerCase(str2lc);

    return (str1lc == str2lc);
}*/

//////////////////////////////////////////////////////////////////////////
WideString StringUtil::utf8ToWide(const Utf8String &Utf8Str) {
	size_t wideSize = Utf8Str.size();

	uint32 *wideStringNative = new uint32[wideSize + 1];

	const UTF8 *sourceStart = reinterpret_cast<const UTF8 *>(Utf8Str.c_str());
	const UTF8 *sourceEnd = sourceStart + wideSize;

	UTF32 *targetStart = reinterpret_cast<UTF32 *>(wideStringNative);
	UTF32 *targetEnd = targetStart + wideSize;

	ConversionResult res = ConvertUTF8toUTF32(&sourceStart, sourceEnd, &targetStart, targetEnd, strictConversion);
	if (res != conversionOK) {
		delete[] wideStringNative;
		return WideString();
	}
	*targetStart = 0;
	WideString resultString(wideStringNative);
	delete[] wideStringNative;
	return resultString;
}

//////////////////////////////////////////////////////////////////////////
Utf8String StringUtil::wideToUtf8(const WideString &WideStr) {
	size_t wideSize = WideStr.size();

	size_t utf8Size = 4 * wideSize + 1;
	char *utf8StringNative = new char[utf8Size];

	const UTF32 *sourceStart = reinterpret_cast<const UTF32 *>(WideStr.c_str());
	const UTF32 *sourceEnd = sourceStart + wideSize;

	UTF8 *targetStart = reinterpret_cast<UTF8 *>(utf8StringNative);
	UTF8 *targetEnd = targetStart + utf8Size;

	ConversionResult res = ConvertUTF32toUTF8(&sourceStart, sourceEnd, &targetStart, targetEnd, strictConversion);
	if (res != conversionOK) {
		delete[] utf8StringNative;
		return Utf8String();
	}
	*targetStart = 0;
	Utf8String resultString(utf8StringNative);
	delete[] utf8StringNative;
	return resultString;
}

//////////////////////////////////////////////////////////////////////////
Common::CodePage StringUtil::mapCodePage(TTextCharset charset) {
	switch (charset) {
	case CHARSET_EASTEUROPE:
		return Common::kWindows1250;

	case CHARSET_RUSSIAN:
		return Common::kWindows1251;

	case CHARSET_ANSI:
		return Common::kWindows1252;

	case CHARSET_GREEK:
		return Common::kWindows1253;

	case CHARSET_TURKISH:
		return Common::kWindows1254;

	case CHARSET_HEBREW:
		return Common::kWindows1255;

	case CHARSET_BALTIC:
		return Common::kWindows1257;

	case CHARSET_DEFAULT:
		switch (BaseEngine::instance().getLanguage()) {

		//cp1250: Central Europe
		case Common::CZ_CZE:
		case Common::HR_HRV:
		case Common::HU_HUN:
		case Common::PL_POL:
		case Common::SK_SVK:
			return Common::kWindows1250;

		//cp1251: Cyrillic
		case Common::RU_RUS:
		case Common::UA_UKR:
			return Common::kWindows1251;

		//cp1252: Western Europe
		case Common::DA_DAN:
		case Common::DE_DEU:
		case Common::EN_ANY:
		case Common::EN_GRB:
		case Common::EN_USA:
		case Common::ES_ESP:
		case Common::FI_FIN:
		case Common::FR_FRA:
		case Common::IT_ITA:
		case Common::NB_NOR:
		case Common::NL_NLD:
		case Common::PT_BRA:
		case Common::PT_POR:
		case Common::SE_SWE:
		case Common::UNK_LANG:
			return Common::kWindows1252;

		//cp1253: Greek
		case Common::GR_GRE:
			return Common::kWindows1253;

		//cp1254: Turkish
		case Common::TR_TUR:
			return Common::kWindows1254;

		//cp1255: Hebrew
		case Common::HE_ISR:
			return Common::kWindows1255;

		//cp1257: Baltic
		case Common::ET_EST:
		case Common::LV_LAT:
			return Common::kWindows1257;

		case Common::JA_JPN:
		case Common::KO_KOR:
		case Common::ZH_CNA:
		case Common::ZH_TWN:
		default:
			warning("Unsupported charset: %d", charset);
			return Common::kWindows1252;
		}

	case CHARSET_OEM:
	case CHARSET_CHINESEBIG5:
	case CHARSET_GB2312:
	case CHARSET_HANGUL:
	case CHARSET_MAC:
	case CHARSET_SHIFTJIS:
	case CHARSET_SYMBOL:
	case CHARSET_VIETNAMESE:
	case CHARSET_JOHAB:
	case CHARSET_ARABIC:
	case CHARSET_THAI:
	default:
		warning("Unsupported charset: %d", charset);
		return Common::kWindows1252;
	}
}

//////////////////////////////////////////////////////////////////////////
WideString StringUtil::ansiToWide(const AnsiString &str, TTextCharset charset) {
	return Common::convertToU32String(str.c_str(), mapCodePage(charset));
}

//////////////////////////////////////////////////////////////////////////
AnsiString StringUtil::wideToAnsi(const WideString &wstr, TTextCharset charset) {
	return Common::convertFromU32String(wstr, mapCodePage(charset));
}

//////////////////////////////////////////////////////////////////////////
bool StringUtil::isUtf8BOM(const byte *buffer, uint32 bufferSize) {
	if (bufferSize > 3 && buffer[0] == 0xEF && buffer[1] == 0xBB && buffer[2] == 0xBF) {
		return true;
	} else {
		return false;
	}
}

//////////////////////////////////////////////////////////////////////////
int StringUtil::indexOf(const WideString &str, const WideString &toFind, size_t startFrom) {
	return str.find(toFind, startFrom);
}

Common::String StringUtil::encodeSetting(const Common::String &str) {
	for (uint32 i = 0; i < str.size(); i++) {
		if ((str[i] < 33) || (str[i] == '=') || (str[i] > 126)) {
			error("Setting contains illegal characters: %s", str.c_str());
		}
	}
	return str;
}

Common::String StringUtil::decodeSetting(const Common::String &str) {
	return str;
}

//////////////////////////////////////////////////////////////////////////
AnsiString StringUtil::toString(int val) {
	return Common::String::format("%d", val);
}

} // End of namespace Wintermute