aboutsummaryrefslogtreecommitdiff
path: root/src/utilstrencodings.cpp
blob: 2cec3023b53bbc28926f134a3559837b9b399900 (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
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
// Copyright (c) 2009-2010 Satoshi Nakamoto
// Copyright (c) 2009-2014 The Bitcoin developers
// Distributed under the MIT/X11 software license, see the accompanying
// file COPYING or http://www.opensource.org/licenses/mit-license.php.

#include "utilstrencodings.h"

#include "tinyformat.h"

#include <errno.h>
#include <limits>

#include <boost/foreach.hpp>

using namespace std;

// safeChars chosen to allow simple messages/URLs/email addresses, but avoid anything
// even possibly remotely dangerous like & or >
static string safeChars("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890 .,;_/:?@");
string SanitizeString(const string& str)
{
    string strResult;
    for (std::string::size_type i = 0; i < str.size(); i++)
    {
        if (safeChars.find(str[i]) != std::string::npos)
            strResult.push_back(str[i]);
    }
    return strResult;
}

const signed char p_util_hexdigit[256] =
{ -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  0,1,2,3,4,5,6,7,8,9,-1,-1,-1,-1,-1,-1,
  -1,0xa,0xb,0xc,0xd,0xe,0xf,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,0xa,0xb,0xc,0xd,0xe,0xf,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
  -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, };

signed char HexDigit(char c)
{
    return p_util_hexdigit[(unsigned char)c];
}

bool IsHex(const string& str)
{
    BOOST_FOREACH(char c, str)
    {
        if (HexDigit(c) < 0)
            return false;
    }
    return (str.size() > 0) && (str.size()%2 == 0);
}

vector<unsigned char> ParseHex(const char* psz)
{
    // convert hex dump to vector
    vector<unsigned char> vch;
    while (true)
    {
        while (isspace(*psz))
            psz++;
        signed char c = HexDigit(*psz++);
        if (c == (signed char)-1)
            break;
        unsigned char n = (c << 4);
        c = HexDigit(*psz++);
        if (c == (signed char)-1)
            break;
        n |= c;
        vch.push_back(n);
    }
    return vch;
}

vector<unsigned char> ParseHex(const string& str)
{
    return ParseHex(str.c_str());
}

string EncodeBase64(const unsigned char* pch, size_t len)
{
    static const char *pbase64 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";

    string strRet="";
    strRet.reserve((len+2)/3*4);

    int mode=0, left=0;
    const unsigned char *pchEnd = pch+len;

    while (pch<pchEnd)
    {
        int enc = *(pch++);
        switch (mode)
        {
            case 0: // we have no bits
                strRet += pbase64[enc >> 2];
                left = (enc & 3) << 4;
                mode = 1;
                break;

            case 1: // we have two bits
                strRet += pbase64[left | (enc >> 4)];
                left = (enc & 15) << 2;
                mode = 2;
                break;

            case 2: // we have four bits
                strRet += pbase64[left | (enc >> 6)];
                strRet += pbase64[enc & 63];
                mode = 0;
                break;
        }
    }

    if (mode)
    {
        strRet += pbase64[left];
        strRet += '=';
        if (mode == 1)
            strRet += '=';
    }

    return strRet;
}

string EncodeBase64(const string& str)
{
    return EncodeBase64((const unsigned char*)str.c_str(), str.size());
}

vector<unsigned char> DecodeBase64(const char* p, bool* pfInvalid)
{
    static const int decode64_table[256] =
    {
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, 62, -1, -1, -1, 63, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, -1, -1,
        -1, -1, -1, -1, -1,  0,  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, -1, -1, -1, -1, -1, -1, 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, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
    };

    if (pfInvalid)
        *pfInvalid = false;

    vector<unsigned char> vchRet;
    vchRet.reserve(strlen(p)*3/4);

    int mode = 0;
    int left = 0;

    while (1)
    {
         int dec = decode64_table[(unsigned char)*p];
         if (dec == -1) break;
         p++;
         switch (mode)
         {
             case 0: // we have no bits and get 6
                 left = dec;
                 mode = 1;
                 break;

              case 1: // we have 6 bits and keep 4
                  vchRet.push_back((left<<2) | (dec>>4));
                  left = dec & 15;
                  mode = 2;
                  break;

             case 2: // we have 4 bits and get 6, we keep 2
                 vchRet.push_back((left<<4) | (dec>>2));
                 left = dec & 3;
                 mode = 3;
                 break;

             case 3: // we have 2 bits and get 6
                 vchRet.push_back((left<<6) | dec);
                 mode = 0;
                 break;
         }
    }

    if (pfInvalid)
        switch (mode)
        {
            case 0: // 4n base64 characters processed: ok
                break;

            case 1: // 4n+1 base64 character processed: impossible
                *pfInvalid = true;
                break;

            case 2: // 4n+2 base64 characters processed: require '=='
                if (left || p[0] != '=' || p[1] != '=' || decode64_table[(unsigned char)p[2]] != -1)
                    *pfInvalid = true;
                break;

            case 3: // 4n+3 base64 characters processed: require '='
                if (left || p[0] != '=' || decode64_table[(unsigned char)p[1]] != -1)
                    *pfInvalid = true;
                break;
        }

    return vchRet;
}

string DecodeBase64(const string& str)
{
    vector<unsigned char> vchRet = DecodeBase64(str.c_str());
    return (vchRet.size() == 0) ? string() : string((const char*)&vchRet[0], vchRet.size());
}

string EncodeBase32(const unsigned char* pch, size_t len)
{
    static const char *pbase32 = "abcdefghijklmnopqrstuvwxyz234567";

    string strRet="";
    strRet.reserve((len+4)/5*8);

    int mode=0, left=0;
    const unsigned char *pchEnd = pch+len;

    while (pch<pchEnd)
    {
        int enc = *(pch++);
        switch (mode)
        {
            case 0: // we have no bits
                strRet += pbase32[enc >> 3];
                left = (enc & 7) << 2;
                mode = 1;
                break;

            case 1: // we have three bits
                strRet += pbase32[left | (enc >> 6)];
                strRet += pbase32[(enc >> 1) & 31];
                left = (enc & 1) << 4;
                mode = 2;
                break;

            case 2: // we have one bit
                strRet += pbase32[left | (enc >> 4)];
                left = (enc & 15) << 1;
                mode = 3;
                break;

            case 3: // we have four bits
                strRet += pbase32[left | (enc >> 7)];
                strRet += pbase32[(enc >> 2) & 31];
                left = (enc & 3) << 3;
                mode = 4;
                break;

            case 4: // we have two bits
                strRet += pbase32[left | (enc >> 5)];
                strRet += pbase32[enc & 31];
                mode = 0;
        }
    }

    static const int nPadding[5] = {0, 6, 4, 3, 1};
    if (mode)
    {
        strRet += pbase32[left];
        for (int n=0; n<nPadding[mode]; n++)
             strRet += '=';
    }

    return strRet;
}

string EncodeBase32(const string& str)
{
    return EncodeBase32((const unsigned char*)str.c_str(), str.size());
}

vector<unsigned char> DecodeBase32(const char* p, bool* pfInvalid)
{
    static const int decode32_table[256] =
    {
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 26, 27, 28, 29, 30, 31, -1, -1, -1, -1,
        -1, -1, -1, -1, -1,  0,  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, -1, -1, -1, -1, -1, -1,  0,  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, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
    };

    if (pfInvalid)
        *pfInvalid = false;

    vector<unsigned char> vchRet;
    vchRet.reserve((strlen(p))*5/8);

    int mode = 0;
    int left = 0;

    while (1)
    {
         int dec = decode32_table[(unsigned char)*p];
         if (dec == -1) break;
         p++;
         switch (mode)
         {
             case 0: // we have no bits and get 5
                 left = dec;
                 mode = 1;
                 break;

              case 1: // we have 5 bits and keep 2
                  vchRet.push_back((left<<3) | (dec>>2));
                  left = dec & 3;
                  mode = 2;
                  break;

             case 2: // we have 2 bits and keep 7
                 left = left << 5 | dec;
                 mode = 3;
                 break;

             case 3: // we have 7 bits and keep 4
                 vchRet.push_back((left<<1) | (dec>>4));
                 left = dec & 15;
                 mode = 4;
                 break;

             case 4: // we have 4 bits, and keep 1
                 vchRet.push_back((left<<4) | (dec>>1));
                 left = dec & 1;
                 mode = 5;
                 break;

             case 5: // we have 1 bit, and keep 6
                 left = left << 5 | dec;
                 mode = 6;
                 break;

             case 6: // we have 6 bits, and keep 3
                 vchRet.push_back((left<<2) | (dec>>3));
                 left = dec & 7;
                 mode = 7;
                 break;

             case 7: // we have 3 bits, and keep 0
                 vchRet.push_back((left<<5) | dec);
                 mode = 0;
                 break;
         }
    }

    if (pfInvalid)
        switch (mode)
        {
            case 0: // 8n base32 characters processed: ok
                break;

            case 1: // 8n+1 base32 characters processed: impossible
            case 3: //   +3
            case 6: //   +6
                *pfInvalid = true;
                break;

            case 2: // 8n+2 base32 characters processed: require '======'
                if (left || p[0] != '=' || p[1] != '=' || p[2] != '=' || p[3] != '=' || p[4] != '=' || p[5] != '=' || decode32_table[(unsigned char)p[6]] != -1)
                    *pfInvalid = true;
                break;

            case 4: // 8n+4 base32 characters processed: require '===='
                if (left || p[0] != '=' || p[1] != '=' || p[2] != '=' || p[3] != '=' || decode32_table[(unsigned char)p[4]] != -1)
                    *pfInvalid = true;
                break;

            case 5: // 8n+5 base32 characters processed: require '==='
                if (left || p[0] != '=' || p[1] != '=' || p[2] != '=' || decode32_table[(unsigned char)p[3]] != -1)
                    *pfInvalid = true;
                break;

            case 7: // 8n+7 base32 characters processed: require '='
                if (left || p[0] != '=' || decode32_table[(unsigned char)p[1]] != -1)
                    *pfInvalid = true;
                break;
        }

    return vchRet;
}

string DecodeBase32(const string& str)
{
    vector<unsigned char> vchRet = DecodeBase32(str.c_str());
    return (vchRet.size() == 0) ? string() : string((const char*)&vchRet[0], vchRet.size());
}

bool ParseInt32(const std::string& str, int32_t *out)
{
    char *endp = NULL;
    errno = 0; // strtol will not set errno if valid
    long int n = strtol(str.c_str(), &endp, 10);
    if(out) *out = (int)n;
    // Note that strtol returns a *long int*, so even if strtol doesn't report a over/underflow
    // we still have to check that the returned value is within the range of an *int32_t*. On 64-bit
    // platforms the size of these types may be different.
    return endp && *endp == 0 && !errno &&
        n >= std::numeric_limits<int32_t>::min() &&
        n <= std::numeric_limits<int32_t>::max();
}

std::string FormatParagraph(const std::string in, size_t width, size_t indent)
{
    std::stringstream out;
    size_t col = 0;
    size_t ptr = 0;
    while(ptr < in.size())
    {
        // Find beginning of next word
        ptr = in.find_first_not_of(' ', ptr);
        if (ptr == std::string::npos)
            break;
        // Find end of next word
        size_t endword = in.find_first_of(' ', ptr);
        if (endword == std::string::npos)
            endword = in.size();
        // Add newline and indentation if this wraps over the allowed width
        if (col > 0)
        {
            if ((col + endword - ptr) > width)
            {
                out << '\n';
                for(size_t i=0; i<indent; ++i)
                    out << ' ';
                col = 0;
            } else
                out << ' ';
        }
        // Append word
        out << in.substr(ptr, endword - ptr);
        col += endword - ptr;
        ptr = endword;
    }
    return out.str();
}

std::string i64tostr(int64_t n)
{
    return strprintf("%d", n);
}

std::string itostr(int n)
{
    return strprintf("%d", n);
}

int64_t atoi64(const char* psz)
{
#ifdef _MSC_VER
    return _atoi64(psz);
#else
    return strtoll(psz, NULL, 10);
#endif
}

int64_t atoi64(const std::string& str)
{
#ifdef _MSC_VER
    return _atoi64(str.c_str());
#else
    return strtoll(str.c_str(), NULL, 10);
#endif
}

int atoi(const std::string& str)
{
    return atoi(str.c_str());
}