summaryrefslogtreecommitdiffstats
path: root/src/common/string_util.cpp
blob: 54943d306c7e623e6eaeba271665d16e10a928b2 (plain) (blame)
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
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
// Copyright 2013 Dolphin Emulator Project
// Licensed under GPLv2
// Refer to the license.txt file included.

#include <algorithm>

#include "common/common.h"
#include "common/string_util.h"

#ifdef _WIN32
    #include <Windows.h>
    #include <codecvt>
#else
    #include <iconv.h>
#endif

namespace Common {

/// Make a string lowercase
std::string ToLower(std::string str) {
    std::transform(str.begin(), str.end(), str.begin(), ::tolower);
    return str;
}

/// Make a string uppercase
std::string ToUpper(std::string str) {
    std::transform(str.begin(), str.end(), str.begin(), ::toupper);
    return str;
}

// faster than sscanf
bool AsciiToHex(const char* _szValue, u32& result)
{
    char *endptr = NULL;
    const u32 value = strtoul(_szValue, &endptr, 16);

    if (!endptr || *endptr)
        return false;

    result = value;
    return true;
}

bool CharArrayFromFormatV(char* out, int outsize, const char* format, va_list args)
{
    int writtenCount;

#ifdef _WIN32
    // You would think *printf are simple, right? Iterate on each character,
    // if it's a format specifier handle it properly, etc.
    //
    // Nooooo. Not according to the C standard.
    //
    // According to the C99 standard (7.19.6.1 "The fprintf function")
    //     The format shall be a multibyte character sequence
    //
    // Because some character encodings might have '%' signs in the middle of
    // a multibyte sequence (SJIS for example only specifies that the first
    // byte of a 2 byte sequence is "high", the second byte can be anything),
    // printf functions have to decode the multibyte sequences and try their
    // best to not screw up.
    //
    // Unfortunately, on Windows, the locale for most languages is not UTF-8
    // as we would need. Notably, for zh_TW, Windows chooses EUC-CN as the
    // locale, and completely fails when trying to decode UTF-8 as EUC-CN.
    //
    // On the other hand, the fix is simple: because we use UTF-8, no such
    // multibyte handling is required as we can simply assume that no '%' char
    // will be present in the middle of a multibyte sequence.
    //
    // This is why we lookup an ANSI (cp1252) locale here and use _vsnprintf_l.
    static locale_t c_locale = NULL;
    if (!c_locale)
        c_locale = _create_locale(LC_ALL, ".1252");
    writtenCount = _vsnprintf_l(out, outsize, format, c_locale, args);
#else
    writtenCount = vsnprintf(out, outsize, format, args);
#endif

    if (writtenCount > 0 && writtenCount < outsize)
    {
        out[writtenCount] = '\0';
        return true;
    }
    else
    {
        out[outsize - 1] = '\0';
        return false;
    }
}

std::string StringFromFormat(const char* format, ...)
{
    va_list args;
    char *buf = NULL;
#ifdef _WIN32
    int required = 0;

    va_start(args, format);
    required = _vscprintf(format, args);
    buf = new char[required + 1];
    CharArrayFromFormatV(buf, required + 1, format, args);
    va_end(args);

    std::string temp = buf;
    delete[] buf;
#else
    va_start(args, format);
    if (vasprintf(&buf, format, args) < 0)
        ERROR_LOG(COMMON, "Unable to allocate memory for string");
    va_end(args);

    std::string temp = buf;
    free(buf);
#endif
    return temp;
}

// For Debugging. Read out an u8 array.
std::string ArrayToString(const u8 *data, u32 size, int line_len, bool spaces)
{
    std::ostringstream oss;
    oss << std::setfill('0') << std::hex;
    
    for (int line = 0; size; ++data, --size)
    {
        oss << std::setw(2) << (int)*data;
        
        if (line_len == ++line)
        {
            oss << '\n';
            line = 0;
        }
        else if (spaces)
            oss << ' ';
    }

    return oss.str();
}

// Turns "  hej " into "hej". Also handles tabs.
std::string StripSpaces(const std::string &str)
{
    const size_t s = str.find_first_not_of(" \t\r\n");

    if (str.npos != s)
        return str.substr(s, str.find_last_not_of(" \t\r\n") - s + 1);
    else
        return "";
}

// "\"hello\"" is turned to "hello"
// This one assumes that the string has already been space stripped in both
// ends, as done by StripSpaces above, for example.
std::string StripQuotes(const std::string& s)
{
    if (s.size() && '\"' == s[0] && '\"' == *s.rbegin())
        return s.substr(1, s.size() - 2);
    else
        return s;
}

bool TryParse(const std::string &str, u32 *const output)
{
    char *endptr = NULL;

    // Reset errno to a value other than ERANGE
    errno = 0;

    unsigned long value = strtoul(str.c_str(), &endptr, 0);
    
    if (!endptr || *endptr)
        return false;

    if (errno == ERANGE)
        return false;

#if ULONG_MAX > UINT_MAX
    if (value >= 0x100000000ull
        && value <= 0xFFFFFFFF00000000ull)
        return false;
#endif

    *output = static_cast<u32>(value);
    return true;
}

bool TryParse(const std::string &str, bool *const output)
{
    if ("1" == str || "true" == ToLower(str))
        *output = true;
    else if ("0" == str || "false" == ToLower(str))
        *output = false;
    else
        return false;

    return true;
}

std::string StringFromBool(bool value)
{
    return value ? "True" : "False";
}

bool SplitPath(const std::string& full_path, std::string* _pPath, std::string* _pFilename, std::string* _pExtension)
{
    if (full_path.empty())
        return false;

    size_t dir_end = full_path.find_last_of("/"
    // windows needs the : included for something like just "C:" to be considered a directory
#ifdef _WIN32
        ":"
#endif
    );
    if (std::string::npos == dir_end)
        dir_end = 0;
    else
        dir_end += 1;

    size_t fname_end = full_path.rfind('.');
    if (fname_end < dir_end || std::string::npos == fname_end)
        fname_end = full_path.size();

    if (_pPath)
        *_pPath = full_path.substr(0, dir_end);

    if (_pFilename)
        *_pFilename = full_path.substr(dir_end, fname_end - dir_end);

    if (_pExtension)
        *_pExtension = full_path.substr(fname_end);

    return true;
}

void BuildCompleteFilename(std::string& _CompleteFilename, const std::string& _Path, const std::string& _Filename)
{
    _CompleteFilename = _Path;

    // check for seperator
    if (DIR_SEP_CHR != *_CompleteFilename.rbegin())
        _CompleteFilename += DIR_SEP_CHR;

    // add the filename
    _CompleteFilename += _Filename;
}

void SplitString(const std::string& str, const char delim, std::vector<std::string>& output)
{
    std::istringstream iss(str);
    output.resize(1);

    while (std::getline(iss, *output.rbegin(), delim))
        output.push_back("");

    output.pop_back();
}

std::string TabsToSpaces(int tab_size, const std::string &in)
{
    const std::string spaces(tab_size, ' ');
    std::string out(in);

    size_t i = 0;
    while (out.npos != (i = out.find('\t')))
        out.replace(i, 1, spaces);

    return out;
}

std::string ReplaceAll(std::string result, const std::string& src, const std::string& dest)
{
    size_t pos = 0;

    if (src == dest)
        return result;

    while ((pos = result.find(src, pos)) != std::string::npos)
    {
        result.replace(pos, src.size(), dest);
        pos += dest.length();
    }

    return result;
}

// UriDecode and UriEncode are from http://www.codeguru.com/cpp/cpp/string/conversions/print.php/c12759
// by jinq0123 (November 2, 2006)

// Uri encode and decode.
// RFC1630, RFC1738, RFC2396

//#include <string>
//#include <assert.h>

const char HEX2DEC[256] = 
{
    /*       0  1  2  3   4  5  6  7   8  9  A  B   C  D  E  F */
    /* 0 */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,
    /* 1 */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,
    /* 2 */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,
    /* 3 */  0, 1, 2, 3,  4, 5, 6, 7,  8, 9,16,16, 16,16,16,16,

    /* 4 */ 16,10,11,12, 13,14,15,16, 16,16,16,16, 16,16,16,16,
    /* 5 */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,
    /* 6 */ 16,10,11,12, 13,14,15,16, 16,16,16,16, 16,16,16,16,
    /* 7 */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,

    /* 8 */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,
    /* 9 */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,
    /* A */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,
    /* B */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,

    /* C */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,
    /* D */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,
    /* E */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16,
    /* F */ 16,16,16,16, 16,16,16,16, 16,16,16,16, 16,16,16,16
};

std::string UriDecode(const std::string & sSrc)
{
    // Note from RFC1630:  "Sequences which start with a percent sign
    // but are not followed by two hexadecimal characters (0-9, A-F) are reserved
    // for future extension"

    const unsigned char * pSrc = (const unsigned char *)sSrc.c_str();
    const size_t SRC_LEN = sSrc.length();
    const unsigned char * const SRC_END = pSrc + SRC_LEN;
    const unsigned char * const SRC_LAST_DEC = SRC_END - 2;   // last decodable '%' 

    char * const pStart = new char[SRC_LEN];
    char * pEnd = pStart;

    while (pSrc < SRC_LAST_DEC)
    {
        if (*pSrc == '%')
        {
            char dec1, dec2;
            if (16 != (dec1 = HEX2DEC[*(pSrc + 1)])
                && 16 != (dec2 = HEX2DEC[*(pSrc + 2)]))
            {
                *pEnd++ = (dec1 << 4) + dec2;
                pSrc += 3;
                continue;
            }
        }

        *pEnd++ = *pSrc++;
    }

    // the last 2- chars
    while (pSrc < SRC_END)
        *pEnd++ = *pSrc++;

    std::string sResult(pStart, pEnd);
    delete [] pStart;
    return sResult;
}

// Only alphanum is safe.
const char SAFE[256] =
{
    /*      0 1 2 3  4 5 6 7  8 9 A B  C D E F */
    /* 0 */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
    /* 1 */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
    /* 2 */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
    /* 3 */ 1,1,1,1, 1,1,1,1, 1,1,0,0, 0,0,0,0,

    /* 4 */ 0,1,1,1, 1,1,1,1, 1,1,1,1, 1,1,1,1,
    /* 5 */ 1,1,1,1, 1,1,1,1, 1,1,1,0, 0,0,0,0,
    /* 6 */ 0,1,1,1, 1,1,1,1, 1,1,1,1, 1,1,1,1,
    /* 7 */ 1,1,1,1, 1,1,1,1, 1,1,1,0, 0,0,0,0,

    /* 8 */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
    /* 9 */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
    /* A */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
    /* B */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,

    /* C */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
    /* D */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
    /* E */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
    /* F */ 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0
};

std::string UriEncode(const std::string & sSrc)
{
    const char DEC2HEX[16 + 1] = "0123456789ABCDEF";
    const unsigned char * pSrc = (const unsigned char *)sSrc.c_str();
    const size_t SRC_LEN = sSrc.length();
    unsigned char * const pStart = new unsigned char[SRC_LEN * 3];
    unsigned char * pEnd = pStart;
    const unsigned char * const SRC_END = pSrc + SRC_LEN;

    for (; pSrc < SRC_END; ++pSrc)
    {
        if (SAFE[*pSrc]) 
            *pEnd++ = *pSrc;
        else
        {
            // escape this char
            *pEnd++ = '%';
            *pEnd++ = DEC2HEX[*pSrc >> 4];
            *pEnd++ = DEC2HEX[*pSrc & 0x0F];
        }
    }

    std::string sResult((char *)pStart, (char *)pEnd);
    delete [] pStart;
    return sResult;
}

#ifdef _WIN32

std::string UTF16ToUTF8(const std::u16string& input)
{
    std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> convert;
    return convert.to_bytes(input);
}

std::u16string UTF8ToUTF16(const std::string& input)
{
    std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> convert;
    return convert.from_bytes(input);
}

static std::string UTF16ToUTF8(const std::wstring& input)
{
    auto const size = WideCharToMultiByte(CP_UTF8, 0, input.data(), input.size(), nullptr, 0, nullptr, nullptr);

    std::string output;
    output.resize(size);

    if (size == 0 || size != WideCharToMultiByte(CP_UTF8, 0, input.data(), input.size(), &output[0], output.size(), nullptr, nullptr))
        output.clear();

    return output;
}

static std::wstring CPToUTF16(u32 code_page, const std::string& input)
{
    auto const size = MultiByteToWideChar(code_page, 0, input.data(), input.size(), nullptr, 0);

    std::wstring output;
    output.resize(size);

    if (size == 0 || size != MultiByteToWideChar(code_page, 0, input.data(), input.size(), &output[0], output.size()))
        output.clear();

    return output;
}

std::wstring UTF8ToUTF16W(const std::string &input)
{
    return CPToUTF16(CP_UTF8, input);
}

std::string SHIFTJISToUTF8(const std::string& input)
{
    return UTF16ToUTF8(CPToUTF16(932, input));
}

std::string CP1252ToUTF8(const std::string& input)
{
    return UTF16ToUTF8(CPToUTF16(1252, input));
}

#else

template <typename T>
static std::string CodeToUTF8(const char* fromcode, const std::basic_string<T>& input)
{
    std::string result;

    iconv_t const conv_desc = iconv_open("UTF-8", fromcode);
    if ((iconv_t)(-1) == conv_desc)
    {
        ERROR_LOG(COMMON, "Iconv initialization failure [%s]: %s", fromcode, strerror(errno));
        iconv_close(conv_desc);
        return {};
    }

    const size_t in_bytes = sizeof(T) * input.size();
    // Multiply by 4, which is the max number of bytes to encode a codepoint
    const size_t out_buffer_size = 4 * in_bytes;

    std::string out_buffer;
    out_buffer.resize(out_buffer_size);

    auto src_buffer = &input[0];
    size_t src_bytes = in_bytes;
    auto dst_buffer = &out_buffer[0];
    size_t dst_bytes = out_buffer.size();

    while (0 != src_bytes)
    {
        size_t const iconv_result = iconv(conv_desc, (char**)(&src_buffer), &src_bytes,
            &dst_buffer, &dst_bytes);

        if (static_cast<size_t>(-1) == iconv_result)
        {
            if (EILSEQ == errno || EINVAL == errno)
            {
                // Try to skip the bad character
                if (0 != src_bytes)
                {
                    --src_bytes;
                    ++src_buffer;
                }
            }
            else
            {
                ERROR_LOG(COMMON, "iconv failure [%s]: %s", fromcode, strerror(errno));
                break;
            }
        }
    }

    out_buffer.resize(out_buffer_size - dst_bytes);
    out_buffer.swap(result);
    
    iconv_close(conv_desc);
    
    return result;
}

std::u16string UTF8ToUTF16(const std::string& input)
{
    std::u16string result;

    iconv_t const conv_desc = iconv_open("UTF-16", "UTF-8");
    if ((iconv_t)(-1) == conv_desc)
    {
        ERROR_LOG(COMMON, "Iconv initialization failure [UTF-8]: %s", strerror(errno));
        iconv_close(conv_desc);
        return {};
    }

    const size_t in_bytes = sizeof(char) * input.size();
    // Multiply by 4, which is the max number of bytes to encode a codepoint
    const size_t out_buffer_size = 4 * sizeof(char16_t) * in_bytes;

    std::u16string out_buffer;
    out_buffer.resize(out_buffer_size);

    char* src_buffer = const_cast<char*>(&input[0]);
    size_t src_bytes = in_bytes;
    char* dst_buffer = (char*)(&out_buffer[0]);
    size_t dst_bytes = out_buffer.size();

    while (0 != src_bytes)
    {
        size_t const iconv_result = iconv(conv_desc, &src_buffer, &src_bytes,
                                          &dst_buffer, &dst_bytes);

        if (static_cast<size_t>(-1) == iconv_result)
        {
            if (EILSEQ == errno || EINVAL == errno)
            {
                // Try to skip the bad character
                if (0 != src_bytes)
                {
                    --src_bytes;
                    ++src_buffer;
                }
            }
            else
            {
                ERROR_LOG(COMMON, "iconv failure [UTF-8]: %s", strerror(errno));
                break;
            }
        }
    }

    out_buffer.resize(out_buffer_size - dst_bytes);
    out_buffer.swap(result);

    iconv_close(conv_desc);
    
    return result;
}

std::string UTF16ToUTF8(const std::u16string& input)
{
    return CodeToUTF8("UTF-16", input);
}

std::string CP1252ToUTF8(const std::string& input)
{
    //return CodeToUTF8("CP1252//TRANSLIT", input);
    //return CodeToUTF8("CP1252//IGNORE", input);
    return CodeToUTF8("CP1252", input);
}

std::string SHIFTJISToUTF8(const std::string& input)
{
    //return CodeToUTF8("CP932", input);
    return CodeToUTF8("SJIS", input);
}

#endif

}