summaryrefslogtreecommitdiffstats
path: root/src/libstore/references.cc
blob: 102e1592180a8e51db975bdfbb13f1652399aeab (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
#include "references.hh"
#include "hash.hh"
#include "util.hh"
#include "archive.hh"

#include <map>
#include <cstdlib>


namespace nix {


static unsigned int refLength = 32; /* characters */


static void search(const unsigned char * s, size_t len,
    StringSet & hashes, StringSet & seen)
{
    static bool initialised = false;
    static bool isBase32[256];
    if (!initialised) {
        for (unsigned int i = 0; i < 256; ++i) isBase32[i] = false;
        for (unsigned int i = 0; i < base32Chars.size(); ++i)
            isBase32[(unsigned char) base32Chars[i]] = true;
        initialised = true;
    }

    for (size_t i = 0; i + refLength <= len; ) {
        int j;
        bool match = true;
        for (j = refLength - 1; j >= 0; --j)
            if (!isBase32[(unsigned char) s[i + j]]) {
                i += j + 1;
                match = false;
                break;
            }
        if (!match) continue;
        string ref((const char *) s + i, refLength);
        if (hashes.erase(ref)) {
            debug(format("found reference to '%1%' at offset '%2%'")
                  % ref % i);
            seen.insert(ref);
        }
        ++i;
    }
}


struct RefScanSink : Sink
{
    HashSink hashSink;
    StringSet hashes;
    StringSet seen;

    string tail;

    RefScanSink() : hashSink(htSHA256) { }

    void operator () (const unsigned char * data, size_t len);
};


void RefScanSink::operator () (const unsigned char * data, size_t len)
{
    hashSink(data, len);

    /* It's possible that a reference spans the previous and current
       fragment, so search in the concatenation of the tail of the
       previous fragment and the start of the current fragment. */
    string s = tail + string((const char *) data, len > refLength ? refLength : len);
    search((const unsigned char *) s.data(), s.size(), hashes, seen);

    search(data, len, hashes, seen);

    size_t tailLen = len <= refLength ? len : refLength;
    tail =
        string(tail, tail.size() < refLength - tailLen ? 0 : tail.size() - (refLength - tailLen)) +
        string((const char *) data + len - tailLen, tailLen);
}


PathSet scanForReferences(const string & path,
    const PathSet & refs, HashResult & hash)
{
    RefScanSink sink;
    std::map<string, Path> backMap;

    /* For efficiency (and a higher hit rate), just search for the
       hash part of the file name.  (This assumes that all references
       have the form `HASH-bla'). */
    for (auto & i : refs) {
        auto baseName = std::string(baseNameOf(i));
        string::size_type pos = baseName.find('-');
        if (pos == string::npos)
            throw Error(format("bad reference '%1%'") % i);
        string s = string(baseName, 0, pos);
        assert(s.size() == refLength);
        assert(backMap.find(s) == backMap.end());
        // parseHash(htSHA256, s);
        sink.hashes.insert(s);
        backMap[s] = i;
    }

    /* Look for the hashes in the NAR dump of the path. */
    dumpPath(path, sink);

    /* Map the hashes found back to their store paths. */
    PathSet found;
    for (auto & i : sink.seen) {
        std::map<string, Path>::iterator j;
        if ((j = backMap.find(i)) == backMap.end()) abort();
        found.insert(j->second);
    }

    hash = sink.hashSink.finish();

    return found;
}


RewritingSink::RewritingSink(const std::string & from, const std::string & to, Sink & nextSink)
    : from(from), to(to), nextSink(nextSink)
{
    assert(from.size() == to.size());
}

void RewritingSink::operator () (const unsigned char * data, size_t len)
{
    std::string s(prev);
    s.append((const char *) data, len);

    size_t j = 0;
    while ((j = s.find(from, j)) != string::npos) {
        matches.push_back(pos + j);
        s.replace(j, from.size(), to);
    }

    prev = s.size() < from.size() ? s : std::string(s, s.size() - from.size() + 1, from.size() - 1);

    auto consumed = s.size() - prev.size();

    pos += consumed;

    if (consumed) nextSink((unsigned char *) s.data(), consumed);
}

void RewritingSink::flush()
{
    if (prev.empty()) return;
    pos += prev.size();
    nextSink((unsigned char *) prev.data(), prev.size());
    prev.clear();
}

HashModuloSink::HashModuloSink(HashType ht, const std::string & modulus)
    : hashSink(ht)
    , rewritingSink(modulus, std::string(modulus.size(), 0), hashSink)
{
}

void HashModuloSink::operator () (const unsigned char * data, size_t len)
{
    rewritingSink(data, len);
}

HashResult HashModuloSink::finish()
{
    rewritingSink.flush();

    /* Hash the positions of the self-references. This ensures that a
       NAR with self-references and a NAR with some of the
       self-references already zeroed out do not produce a hash
       collision. FIXME: proof. */
    for (auto & pos : rewritingSink.matches) {
        auto s = fmt("|%d", pos);
        hashSink((unsigned char *) s.data(), s.size());
    }

    auto h = hashSink.finish();
    return {h.first, rewritingSink.pos};
}

}