aboutsummaryrefslogtreecommitdiff
path: root/src/libutil/hash.cc
blob: 5735e4715db693760e8b8c40ab7a5880e7434123 (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
#include <iostream>
#include <cstring>

#include <openssl/md5.h>
#include <openssl/sha.h>

#include "args.hh"
#include "hash.hh"
#include "archive.hh"
#include "split.hh"
#include "util.hh"

#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>

namespace nix {


static size_t regularHashSize(HashType type) {
    switch (type) {
    case htMD5: return md5HashSize;
    case htSHA1: return sha1HashSize;
    case htSHA256: return sha256HashSize;
    case htSHA512: return sha512HashSize;
    }
    abort();
}


std::set<std::string> hashTypes = { "md5", "sha1", "sha256", "sha512" };


Hash::Hash(HashType type) : type(type)
{
    hashSize = regularHashSize(type);
    assert(hashSize <= maxHashSize);
    memset(hash, 0, maxHashSize);
}


bool Hash::operator == (const Hash & h2) const
{
    if (hashSize != h2.hashSize) return false;
    for (unsigned int i = 0; i < hashSize; i++)
        if (hash[i] != h2.hash[i]) return false;
    return true;
}


bool Hash::operator != (const Hash & h2) const
{
    return !(*this == h2);
}


bool Hash::operator < (const Hash & h) const
{
    if (hashSize < h.hashSize) return true;
    if (hashSize > h.hashSize) return false;
    for (unsigned int i = 0; i < hashSize; i++) {
        if (hash[i] < h.hash[i]) return true;
        if (hash[i] > h.hash[i]) return false;
    }
    return false;
}


const std::string base16Chars = "0123456789abcdef";


static std::string printHash16(const Hash & hash)
{
    std::string buf;
    buf.reserve(hash.hashSize * 2);
    for (unsigned int i = 0; i < hash.hashSize; i++) {
        buf.push_back(base16Chars[hash.hash[i] >> 4]);
        buf.push_back(base16Chars[hash.hash[i] & 0x0f]);
    }
    return buf;
}


// omitted: E O U T
const std::string base32Chars = "0123456789abcdfghijklmnpqrsvwxyz";


static std::string printHash32(const Hash & hash)
{
    assert(hash.hashSize);
    size_t len = hash.base32Len();
    assert(len);

    std::string s;
    s.reserve(len);

    for (int n = (int) len - 1; n >= 0; n--) {
        unsigned int b = n * 5;
        unsigned int i = b / 8;
        unsigned int j = b % 8;
        unsigned char c =
            (hash.hash[i] >> j)
            | (i >= hash.hashSize - 1 ? 0 : hash.hash[i + 1] << (8 - j));
        s.push_back(base32Chars[c & 0x1f]);
    }

    return s;
}


std::string printHash16or32(const Hash & hash)
{
    assert(hash.type);
    return hash.to_string(hash.type == htMD5 ? Base16 : Base32, false);
}


std::string Hash::to_string(Base base, bool includeType) const
{
    std::string s;
    if (base == SRI || includeType) {
        s += printHashType(type);
        s += base == SRI ? '-' : ':';
    }
    switch (base) {
    case Base16:
        s += printHash16(*this);
        break;
    case Base32:
        s += printHash32(*this);
        break;
    case Base64:
    case SRI:
        s += base64Encode(std::string_view((const char *) hash, hashSize));
        break;
    }
    return s;
}

Hash Hash::dummy(htSHA256);

Hash Hash::parseSRI(std::string_view original) {
    auto rest = original;

    // Parse the has type before the separater, if there was one.
    auto hashRaw = splitPrefixTo(rest, '-');
    if (!hashRaw)
        throw BadHash("hash '%s' is not SRI", original);
    HashType parsedType = parseHashType(*hashRaw);

    return Hash(rest, parsedType, true);
}

// Mutates the string to eliminate the prefixes when found
static std::pair<std::optional<HashType>, bool> getParsedTypeAndSRI(std::string_view & rest)
{
    bool isSRI = false;

    // Parse the hash type before the separator, if there was one.
    std::optional<HashType> optParsedType;
    {
        auto hashRaw = splitPrefixTo(rest, ':');

        if (!hashRaw) {
            hashRaw = splitPrefixTo(rest, '-');
            if (hashRaw)
                isSRI = true;
        }
        if (hashRaw)
            optParsedType = parseHashType(*hashRaw);
    }

    return {optParsedType, isSRI};
}

Hash Hash::parseAnyPrefixed(std::string_view original)
{
    auto rest = original;
    auto [optParsedType, isSRI] = getParsedTypeAndSRI(rest);

    // Either the string or user must provide the type, if they both do they
    // must agree.
    if (!optParsedType)
        throw BadHash("hash '%s' does not include a type", rest);

    return Hash(rest, *optParsedType, isSRI);
}

Hash Hash::parseAny(std::string_view original, std::optional<HashType> optType)
{
    auto rest = original;
    auto [optParsedType, isSRI] = getParsedTypeAndSRI(rest);

    // Either the string or user must provide the type, if they both do they
    // must agree.
    if (!optParsedType && !optType)
        throw BadHash("hash '%s' does not include a type, nor is the type otherwise known from context", rest);
    else if (optParsedType && optType && *optParsedType != *optType)
        throw BadHash("hash '%s' should have type '%s'", original, printHashType(*optType));

    HashType hashType = optParsedType ? *optParsedType : *optType;
    return Hash(rest, hashType, isSRI);
}

Hash Hash::parseNonSRIUnprefixed(std::string_view s, HashType type)
{
    return Hash(s, type, false);
}

Hash::Hash(std::string_view rest, HashType type, bool isSRI)
    : Hash(type)
{
    if (!isSRI && rest.size() == base16Len()) {

        auto parseHexDigit = [&](char c) {
            if (c >= '0' && c <= '9') return c - '0';
            if (c >= 'A' && c <= 'F') return c - 'A' + 10;
            if (c >= 'a' && c <= 'f') return c - 'a' + 10;
            throw BadHash("invalid base-16 hash '%s'", rest);
        };

        for (unsigned int i = 0; i < hashSize; i++) {
            hash[i] =
                parseHexDigit(rest[i * 2]) << 4
                | parseHexDigit(rest[i * 2 + 1]);
        }
    }

    else if (!isSRI && rest.size() == base32Len()) {

        for (unsigned int n = 0; n < rest.size(); ++n) {
            char c = rest[rest.size() - n - 1];
            unsigned char digit;
            for (digit = 0; digit < base32Chars.size(); ++digit) /* !!! slow */
                if (base32Chars[digit] == c) break;
            if (digit >= 32)
                throw BadHash("invalid base-32 hash '%s'", rest);
            unsigned int b = n * 5;
            unsigned int i = b / 8;
            unsigned int j = b % 8;
            hash[i] |= digit << j;

            if (i < hashSize - 1) {
                hash[i + 1] |= digit >> (8 - j);
            } else {
                if (digit >> (8 - j))
                    throw BadHash("invalid base-32 hash '%s'", rest);
            }
        }
    }

    else if (isSRI || rest.size() == base64Len()) {
        auto d = base64Decode(rest);
        if (d.size() != hashSize)
            throw BadHash("invalid %s hash '%s'", isSRI ? "SRI" : "base-64", rest);
        assert(hashSize);
        memcpy(hash, d.data(), hashSize);
    }

    else
        throw BadHash("hash '%s' has wrong length for hash type '%s'", rest, printHashType(this->type));
}

Hash newHashAllowEmpty(std::string_view hashStr, std::optional<HashType> ht)
{
    if (hashStr.empty()) {
        if (!ht)
            throw BadHash("empty hash requires explicit hash type");
        Hash h(*ht);
        warn("found empty hash, assuming '%s'", h.to_string(SRI, true));
        return h;
    } else
        return Hash::parseAny(hashStr, ht);
}


union Ctx
{
    MD5_CTX md5;
    SHA_CTX sha1;
    SHA256_CTX sha256;
    SHA512_CTX sha512;
};


static void start(HashType ht, Ctx & ctx)
{
    if (ht == htMD5) MD5_Init(&ctx.md5);
    else if (ht == htSHA1) SHA1_Init(&ctx.sha1);
    else if (ht == htSHA256) SHA256_Init(&ctx.sha256);
    else if (ht == htSHA512) SHA512_Init(&ctx.sha512);
}


static void update(HashType ht, Ctx & ctx,
    std::string_view data)
{
    if (ht == htMD5) MD5_Update(&ctx.md5, data.data(), data.size());
    else if (ht == htSHA1) SHA1_Update(&ctx.sha1, data.data(), data.size());
    else if (ht == htSHA256) SHA256_Update(&ctx.sha256, data.data(), data.size());
    else if (ht == htSHA512) SHA512_Update(&ctx.sha512, data.data(), data.size());
}


static void finish(HashType ht, Ctx & ctx, unsigned char * hash)
{
    if (ht == htMD5) MD5_Final(hash, &ctx.md5);
    else if (ht == htSHA1) SHA1_Final(hash, &ctx.sha1);
    else if (ht == htSHA256) SHA256_Final(hash, &ctx.sha256);
    else if (ht == htSHA512) SHA512_Final(hash, &ctx.sha512);
}


Hash hashString(HashType ht, std::string_view s)
{
    Ctx ctx;
    Hash hash(ht);
    start(ht, ctx);
    update(ht, ctx, s);
    finish(ht, ctx, hash.hash);
    return hash;
}


Hash hashFile(HashType ht, const Path & path)
{
    HashSink sink(ht);
    readFile(path, sink);
    return sink.finish().first;
}


HashSink::HashSink(HashType ht) : ht(ht)
{
    ctx = new Ctx;
    bytes = 0;
    start(ht, *ctx);
}

HashSink::~HashSink()
{
    bufPos = 0;
    delete ctx;
}

void HashSink::write(std::string_view data)
{
    bytes += data.size();
    update(ht, *ctx, data);
}

HashResult HashSink::finish()
{
    flush();
    Hash hash(ht);
    nix::finish(ht, *ctx, hash.hash);
    return HashResult(hash, bytes);
}

HashResult HashSink::currentHash()
{
    flush();
    Ctx ctx2 = *ctx;
    Hash hash(ht);
    nix::finish(ht, ctx2, hash.hash);
    return HashResult(hash, bytes);
}


HashResult hashPath(
    HashType ht, const Path & path, PathFilter & filter)
{
    HashSink sink(ht);
    dumpPath(path, sink, filter);
    return sink.finish();
}


Hash compressHash(const Hash & hash, unsigned int newSize)
{
    Hash h(hash.type);
    h.hashSize = newSize;
    for (unsigned int i = 0; i < hash.hashSize; ++i)
        h.hash[i % newSize] ^= hash.hash[i];
    return h;
}


std::optional<HashType> parseHashTypeOpt(std::string_view s)
{
    if (s == "md5") return htMD5;
    else if (s == "sha1") return htSHA1;
    else if (s == "sha256") return htSHA256;
    else if (s == "sha512") return htSHA512;
    else return std::optional<HashType> {};
}

HashType parseHashType(std::string_view s)
{
    auto opt_h = parseHashTypeOpt(s);
    if (opt_h)
        return *opt_h;
    else
        throw UsageError("unknown hash algorithm '%1%'", s);
}

std::string_view printHashType(HashType ht)
{
    switch (ht) {
    case htMD5: return "md5";
    case htSHA1: return "sha1";
    case htSHA256: return "sha256";
    case htSHA512: return "sha512";
    default:
        // illegal hash type enum value internally, as opposed to external input
        // which should be validated with nice error message.
        assert(false);
    }
}

}