lix/src/libutil/archive.hh
eldritch horrors 4ec87742a1 libstore: rewrite the nar parser as a contents generator
this is not completely necessary at this point because the parser right
now already returns a generator to pass through all input data it read,
but the nar parser *was* very lax and would accept nars that weren't in
canonical form (defined as the form dumpPath would return). nar hashing
depends on these things, and as such rewriting the parser now allows us
to reject non-canonical nars that extract to the same store contents as
their canonical counterpart but have different nar hashes despite that.

Change-Id: Iccd319e3bd5912d8297014c84c495edc59019bb7
2024-07-16 00:57:42 +00:00

180 lines
3.8 KiB
C++

#pragma once
///@file
#include "generator.hh"
#include "types.hh"
#include "serialise.hh"
#include "file-system.hh"
namespace nix {
/**
* dumpPath creates a Nix archive of the specified path.
*
* @param path the file system data to dump. Dumping is recursive so if
* this is a directory we dump it and all its children.
*
* @param [out] sink The serialised archive is fed into this sink.
*
* @param filter Can be used to skip certain files.
*
* The format is as follows:
*
* ```
* IF path points to a REGULAR FILE:
* dump(path) = attrs(
* [ ("type", "regular")
* , ("contents", contents(path))
* ])
*
* IF path points to a DIRECTORY:
* dump(path) = attrs(
* [ ("type", "directory")
* , ("entries", concat(map(f, sort(entries(path)))))
* ])
* where f(fn) = attrs(
* [ ("name", fn)
* , ("file", dump(path + "/" + fn))
* ])
*
* where:
*
* attrs(as) = concat(map(attr, as)) + encN(0)
* attrs((a, b)) = encS(a) + encS(b)
*
* encS(s) = encN(len(s)) + s + (padding until next 64-bit boundary)
*
* encN(n) = 64-bit little-endian encoding of n.
*
* contents(path) = the contents of a regular file.
*
* sort(strings) = lexicographic sort by 8-bit value (strcmp).
*
* entries(path) = the entries of a directory, without `.` and
* `..`.
*
* `+` denotes string concatenation.
* ```
*/
WireFormatGenerator dumpPath(Path path,
PathFilter & filter = defaultPathFilter);
/**
* Same as dumpPath(), but returns the last modified date of the path.
*/
WireFormatGenerator dumpPathAndGetMtime(Path path, time_t & mtime,
PathFilter & filter = defaultPathFilter);
/**
* Dump an archive with a single file with these contents.
*
* @param s Contents of the file.
*/
WireFormatGenerator dumpString(std::string_view s);
/**
* \todo Fix this API, it sucks.
*/
struct ParseSink
{
virtual void createDirectory(const Path & path) { };
virtual void createRegularFile(const Path & path) { };
virtual void closeRegularFile() { };
virtual void isExecutable() { };
virtual void preallocateContents(uint64_t size) { };
virtual void receiveContents(std::string_view data) { };
virtual void createSymlink(const Path & path, const std::string & target) { };
};
/**
* If the NAR archive contains a single file at top-level, then save
* the contents of the file to `s`. Otherwise barf.
*/
struct RetrieveRegularNARSink : ParseSink
{
bool regular = true;
Sink & sink;
RetrieveRegularNARSink(Sink & sink) : sink(sink) { }
void createDirectory(const Path & path) override
{
regular = false;
}
void receiveContents(std::string_view data) override
{
sink(data);
}
void createSymlink(const Path & path, const std::string & target) override
{
regular = false;
}
};
namespace nar {
struct MetadataString;
struct MetadataRaw;
struct File;
struct Symlink;
struct Directory;
using Entry = std::variant<MetadataString, MetadataRaw, File, Symlink, Directory>;
struct MetadataString
{
std::string_view data;
};
struct MetadataRaw
{
Bytes raw;
};
struct File
{
const Path & path;
bool executable;
uint64_t size;
Generator<Bytes> contents;
};
struct Symlink
{
const Path & path;
const Path & target;
};
struct Directory
{
const Path & path;
Generator<Entry> contents;
};
Generator<Entry> parse(Source & source);
}
WireFormatGenerator parseAndCopyDump(ParseSink & sink, Source & source);
void parseDump(ParseSink & sink, Source & source);
void restorePath(const Path & path, Source & source);
/**
* Read a NAR from 'source' and return it as a generator.
*/
WireFormatGenerator copyNAR(Source & source);
inline constexpr std::string_view narVersionMagic1 = "nix-archive-1";
inline constexpr std::string_view caseHackSuffix = "~nix~case~hack~";
}