Repository navigation
Expand file tree
/
Copy pathUnicode.cpp
More file actions
423 lines (402 loc) · 10.5 KB
/
Copy pathUnicode.cpp
File metadata and controls
423 lines (402 loc) · 10.5 KB
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
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
/*
* Copyright 2010-2016 OpenXcom Developers.
*
* This file is part of OpenXcom.
*
* OpenXcom 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 3 of the License, or
* (at your option) any later version.
*
* OpenXcom 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 OpenXcom. If not, see <http://www.gnu.org/licenses/>.
*/
#include "Unicode.h"
#include <sstream>
#include <locale>
#include <stdexcept>
#include "Logger.h"
#ifdef _WIN32
#ifndef NOMINMAX
#define NOMINMAX
#endif
#define WIN32_LEAN_AND_MEAN
#include <windows.h>
#include <shlwapi.h>
#else
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <assert.h>
#endif
namespace OpenXcom
{
namespace Unicode
{
std::locale utf8;
/**
* Store a UTF-8 locale to use when dealing with character conversions.
* Windows doesn't have a UTF-8 locale so we just use its APIs directly.
*/
void getUtf8Locale()
{
std::string loc;
#ifndef _WIN32
// Find any UTF-8 locale
FILE *fp = popen("locale -a", "r");
if (fp != NULL)
{
char buf[50];
while (fgets(buf, sizeof(buf), fp) != NULL)
{
if (strstr(buf, ".utf8") != NULL ||
strstr(buf, ".UTF-8") != NULL)
{
// Trim newline
size_t end = strlen(buf) - 1;
if (buf[end] == '\n')
buf[end] = '\0';
loc = buf;
break;
}
}
pclose(fp);
}
#endif
// Try a UTF-8 locale (or default if none was found)
try
{
utf8 = std::locale(loc.c_str());
}
catch (const std::runtime_error &)
{
// Well we're stuck with the C locale, hope for the best
}
Log(LOG_INFO) << "Detected locale: " << utf8.name();
}
/**
* Takes a Unicode 32-bit string and converts it
* to a 8-bit string encoded in UTF-8.
* Used for rendering text.
* @note Adapted from https://stackoverflow.com/a/148766/2683561
* @param src UTF-8 string.
* @return Unicode string.
*/
UString convUtf8ToUtf32(const std::string &src)
{
if (src.empty())
return UString();
UString out;
out.reserve(src.size());
UCode codepoint = 0;
for (std::string::const_iterator i = src.begin(); i != src.end();)
{
unsigned char ch = static_cast<unsigned char>(*i);
if (ch <= 0x7f)
codepoint = ch;
else if (ch <= 0xbf)
codepoint = (codepoint << 6) | (ch & 0x3f);
else if (ch <= 0xdf)
codepoint = ch & 0x1f;
else if (ch <= 0xef)
codepoint = ch & 0x0f;
else
codepoint = ch & 0x07;
++i;
if (i == src.end() || ((*i & 0xc0) != 0x80 && codepoint <= 0x10ffff))
{
out.append(1, codepoint);
}
}
return out;
}
/**
* Takes a Unicode 32-bit string and converts it
* to a 8-bit string encoded in UTF-8.
* Used for rendering text.
* @note Adapted from https://stackoverflow.com/a/148766/2683561
* @param src Unicode string.
* @return UTF-8 string.
*/
std::string convUtf32ToUtf8(const UString &src)
{
if (src.empty())
return std::string();
std::string out;
out.reserve(src.size());
for (UString::const_iterator i = src.begin(); i != src.end(); ++i)
{
UCode codepoint = *i;
if (codepoint <= 0x7f)
{
out.append(1, static_cast<char>(codepoint));
}
else if (codepoint <= 0x7ff)
{
out.append(1, static_cast<char>(0xc0 | ((codepoint >> 6) & 0x1f)));
out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
}
else if (codepoint <= 0xffff)
{
out.append(1, static_cast<char>(0xe0 | ((codepoint >> 12) & 0x0f)));
out.append(1, static_cast<char>(0x80 | ((codepoint >> 6) & 0x3f)));
out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
}
else
{
out.append(1, static_cast<char>(0xf0 | ((codepoint >> 18) & 0x07)));
out.append(1, static_cast<char>(0x80 | ((codepoint >> 12) & 0x3f)));
out.append(1, static_cast<char>(0x80 | ((codepoint >> 6) & 0x3f)));
out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
}
}
return out;
}
/**
* Takes a wide-character string and converts it to a
* multibyte 8-bit string in a given encoding.
* Used for Win32 APIs.
* @param src Wide-character string.
* @param cp Codepage of the destination string.
* @return Multibyte string.
*/
std::string convWcToMb(const std::wstring &src, unsigned int cp)
{
if (src.empty())
return std::string();
#ifdef _WIN32
int size = WideCharToMultiByte(cp, 0, &src[0], (int)src.size(), NULL, 0, NULL, NULL);
std::string str(size, 0);
WideCharToMultiByte(cp, 0, &src[0], (int)src.size(), &str[0], size, NULL, NULL);
return str;
#else
(void)cp;
assert(sizeof(wchar_t) == sizeof(UCode));
const UString *ustr = reinterpret_cast<const UString*>(&src);
return convUtf32ToUtf8(*ustr);
#endif
}
/**
* Takes a multibyte 8-bit string in a given encoding
* and converts it to a wide-character string.
* Used for Win32 APIs.
* @param src Multibyte string.
* @param cp Codepage of the source string.
* @return Wide-character string.
*/
std::wstring convMbToWc(const std::string &src, unsigned int cp)
{
if (src.empty())
return std::wstring();
#ifdef _WIN32
int size = MultiByteToWideChar(cp, 0, &src[0], (int)src.size(), NULL, 0);
std::wstring wstr(size, 0);
MultiByteToWideChar(cp, 0, &src[0], (int)src.size(), &wstr[0], size);
return wstr;
#else
(void)cp;
assert(sizeof(wchar_t) == sizeof(UCode));
UString ustr = convUtf8ToUtf32(src);
const std::wstring *wstr = reinterpret_cast<const std::wstring*>(&ustr);
return *wstr;
#endif
}
/**
* Takes a filesystem path and converts it to a UTF-8 string.
* On Windows the C paths use the local ANSI codepage.
* Used for SDL APIs.
* @param src Filesystem path.
* @return UTF-8 string.
*/
std::string convPathToUtf8(const std::string &src)
{
#ifdef _WIN32
return convWcToMb(convMbToWc(src, CP_ACP), CP_UTF8);
#else
return src;
#endif
}
/**
* Takes a UTF-8 string and converts it to a filesystem path.
* On Windows the C paths use the local ANSI codepage.
* Used for SDL APIs.
* @param src UTF-8 string.
* @return Filesystem path.
*/
std::string convUtf8ToPath(const std::string &src)
{
#ifdef _WIN32
return convWcToMb(convMbToWc(src, CP_UTF8), CP_ACP);
#else
return src;
#endif
}
/**
* Compares two UTF-8 strings using natural human ordering.
* @param a String A.
* @param b String B.
* @return String A comes before String B.
*/
bool naturalCompare(const std::string &a, const std::string &b)
{
#ifdef _WIN32
typedef int (WINAPI *WinStrCmp)(PCWSTR, PCWSTR);
WinStrCmp pWinStrCmp = (WinStrCmp)GetProcAddress(GetModuleHandleA("shlwapi.dll"), "StrCmpLogicalW");
if (pWinStrCmp)
{
std::wstring wa = convMbToWc(a, CP_UTF8);
std::wstring wb = convMbToWc(b, CP_UTF8);
return (pWinStrCmp(wa.c_str(), wb.c_str()) < 0);
}
else
#endif
{
// fallback to lexical sort
return caseCompare(a, b);
}
}
/**
* Compares two UTF-8 strings ignoring case.
* @param a String A.
* @param b String B.
* @return String A comes before String B.
*/
bool caseCompare(const std::string &a, const std::string &b)
{
#ifdef _WIN32
std::wstring wa = convMbToWc(a, CP_UTF8);
std::wstring wb = convMbToWc(b, CP_UTF8);
return (StrCmpIW(wa.c_str(), wb.c_str()) < 0);
#else
return (std::use_facet< std::collate<char> >(utf8).compare(&a[0], &a[0] + a.size(), &b[0], &b[0] + b.size()) < 0);
#endif
}
/**
* Searches for a substring in another string ignoring case.
* @param haystack String to search.
* @param needle String to find.
* @return True if the needle is in the haystack.
*/
bool caseFind(const std::string &haystack, const std::string &needle)
{
#ifdef _WIN32
std::wstring wa = convMbToWc(haystack, CP_UTF8);
std::wstring wb = convMbToWc(needle, CP_UTF8);
return (StrStrIW(wa.c_str(), wb.c_str()) != NULL);
#else
std::wstring wa = convMbToWc(haystack, 0);
std::wstring wb = convMbToWc(needle, 0);
std::use_facet< std::ctype<wchar_t> >(utf8).toupper(&wa[0], &wa[0] + wa.size());
std::use_facet< std::ctype<wchar_t> >(utf8).toupper(&wb[0], &wb[0] + wb.size());
return (wa.find(wb) != std::wstring::npos);
#endif
}
/**
* Uppercases a UTF-8 string, modified in place.
* Used for case-insensitive comparisons.
* @param s Source string.
*/
void upperCase(std::string &s)
{
if (s.empty())
return;
#ifdef _WIN32
std::wstring ws = convMbToWc(s, CP_UTF8);
CharUpperW(&ws[0]);
s = convWcToMb(ws, CP_UTF8);
#else
std::wstring ws = convMbToWc(s, 0);
std::use_facet< std::ctype<wchar_t> >(utf8).toupper(&ws[0], &ws[0] + ws.size());
s = convWcToMb(ws, 0);
#endif
}
/**
* Lowercases a UTF-8 string, modified in place.
* Used for case-insensitive comparisons.
* @param s Source string.
*/
void lowerCase(std::string &s)
{
if (s.empty())
return;
#ifdef _WIN32
std::wstring ws = convMbToWc(s, CP_UTF8);
CharLowerW(&ws[0]);
s = convWcToMb(ws, CP_UTF8);
#else
std::wstring ws = convMbToWc(s, 0);
std::use_facet< std::ctype<wchar_t> >(utf8).tolower(&ws[0], &ws[0] + ws.size());
s = convWcToMb(ws, 0);
#endif
}
/**
* Replaces every instance of a substring.
* @param str The string to modify.
* @param find The substring to find.
* @param replace The substring to replace it with.
*/
void replace(std::string &str, const std::string &find, const std::string &replace)
{
for (size_t i = str.find(find); i != std::string::npos; i = str.find(find, i + replace.length()))
{
str.replace(i, find.length(), replace);
}
}
/**
* Takes an integer value and formats it as number with separators (spacing the thousands).
* @param value The value.
* @param currency Currency symbol.
* @return The formatted string.
*/
std::string formatNumber(int64_t value, const std::string ¤cy)
{
const std::string thousands_sep = "\xC2\xA0"; // TOK_NBSP
bool negative = (value < 0);
std::ostringstream ss;
ss << (negative ? -value : value);
std::string s = ss.str();
size_t spacer = s.size() - 3;
while (spacer > 0 && spacer < s.size())
{
s.insert(spacer, thousands_sep);
spacer -= 3;
}
if (!currency.empty())
{
s.insert(0, currency);
}
if (negative)
{
s.insert(0, "-");
}
return s;
}
/**
* Takes an integer value and formats it as currency,
* spacing the thousands and adding a $ sign to the front.
* @param funds The funding value.
* @return The formatted string.
*/
std::string formatFunding(int64_t funds)
{
return formatNumber(funds, "$");
}
/**
* Takes an integer value and formats it as percentage,
* adding a % sign.
* @param value The percentage value.
* @return The formatted string.
*/
std::string formatPercentage(int value)
{
std::ostringstream ss;
ss << value << "%";
return ss.str();
}
}
}