mirror of
https://github.com/NixOS/nix.git
synced 2025-11-15 15:02:42 +01:00
2e3ebfb829
The implicit dependency on refLength (which is the StorePath::HashLen) is not good. Also the companion tests and benchmarks are already in libstore-tests.
126 lines
3.3 KiB
C++
126 lines
3.3 KiB
C++
#include "nix/store/references.hh"
|
|
#include "nix/store/path.hh"
|
|
#include "nix/util/hash.hh"
|
|
#include "nix/util/base-nix-32.hh"
|
|
|
|
#include <map>
|
|
#include <cstdlib>
|
|
#include <mutex>
|
|
#include <algorithm>
|
|
|
|
namespace nix {
|
|
|
|
static constexpr auto refLength = StorePath::HashLen;
|
|
|
|
static void search(std::string_view s, StringSet & hashes, StringSet & seen)
|
|
{
|
|
for (size_t i = 0; i + refLength <= s.size();) {
|
|
int j;
|
|
bool match = true;
|
|
for (j = refLength - 1; j >= 0; --j)
|
|
if (!BaseNix32::lookupReverse(s[i + j])) {
|
|
i += j + 1;
|
|
match = false;
|
|
break;
|
|
}
|
|
if (!match)
|
|
continue;
|
|
std::string ref(s.substr(i, refLength));
|
|
if (hashes.erase(ref)) {
|
|
debug("found reference to '%1%' at offset '%2%'", ref, i);
|
|
seen.insert(ref);
|
|
}
|
|
++i;
|
|
}
|
|
}
|
|
|
|
void RefScanSink::operator()(std::string_view data)
|
|
{
|
|
/* 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. */
|
|
auto s = tail;
|
|
auto tailLen = std::min(data.size(), refLength);
|
|
s.append(data.data(), tailLen);
|
|
search(s, hashes, seen);
|
|
|
|
search(data, hashes, seen);
|
|
|
|
auto rest = refLength - tailLen;
|
|
if (rest < tail.size())
|
|
tail = tail.substr(tail.size() - rest);
|
|
tail.append(data.data() + data.size() - tailLen, tailLen);
|
|
}
|
|
|
|
RewritingSink::RewritingSink(const std::string & from, const std::string & to, Sink & nextSink)
|
|
: RewritingSink({{from, to}}, nextSink)
|
|
{
|
|
}
|
|
|
|
RewritingSink::RewritingSink(const StringMap & rewrites, Sink & nextSink)
|
|
: rewrites(rewrites)
|
|
, nextSink(nextSink)
|
|
{
|
|
std::string::size_type maxRewriteSize = 0;
|
|
for (auto & [from, to] : rewrites) {
|
|
assert(from.size() == to.size());
|
|
maxRewriteSize = std::max(maxRewriteSize, from.size());
|
|
}
|
|
this->maxRewriteSize = maxRewriteSize;
|
|
}
|
|
|
|
void RewritingSink::operator()(std::string_view data)
|
|
{
|
|
std::string s(prev);
|
|
s.append(data);
|
|
|
|
s = rewriteStrings(s, rewrites);
|
|
|
|
prev = s.size() < maxRewriteSize ? s
|
|
: maxRewriteSize == 0 ? ""
|
|
: std::string(s, s.size() - maxRewriteSize + 1, maxRewriteSize - 1);
|
|
|
|
auto consumed = s.size() - prev.size();
|
|
|
|
pos += consumed;
|
|
|
|
if (consumed)
|
|
nextSink(s.substr(0, consumed));
|
|
}
|
|
|
|
void RewritingSink::flush()
|
|
{
|
|
if (prev.empty())
|
|
return;
|
|
pos += prev.size();
|
|
nextSink(prev);
|
|
prev.clear();
|
|
}
|
|
|
|
HashModuloSink::HashModuloSink(HashAlgorithm ha, const std::string & modulus)
|
|
: hashSink(ha)
|
|
, rewritingSink(modulus, std::string(modulus.size(), 0), hashSink)
|
|
{
|
|
}
|
|
|
|
void HashModuloSink::operator()(std::string_view data)
|
|
{
|
|
rewritingSink(data);
|
|
}
|
|
|
|
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)
|
|
hashSink(fmt("|%d", pos));
|
|
|
|
auto h = hashSink.finish();
|
|
return {.hash = h.hash, .numBytesDigested = rewritingSink.pos};
|
|
}
|
|
|
|
} // namespace nix
|