Browse zlib specs (32 of 62)

Proofs / zlib / The stream interface

api_dict_id

For data compressed with a preset dictionary (zlib wrapper), decompression asks for it and reports the dictionary's Adler-32.

spec
66 lines of C
with its headers
106 lines
status
Proved
32 of 62
On this page

The spec

The spec is the C program harness/api_dict_id.c, 66 lines, shown whole as it is in the repository at 37189f4. It includes harness/laws_common.h (40 lines). Its first comment states the property in full, with every bound.

C
// Law api_dict_id: For any dictionary (1 to 2^32 - 1 bytes, as much as deflateSetDictionary takes) and any data (any
// length the allocator provides) compressed with it (deflateInit2 with any windowBits 8..15 and any level, memLevel
// and strategy it accepts, deflateSetDictionary, then deflate: all of the data, in pieces of at most 2^32 - 1 bytes,
// Z_FINISH with the last, into deflateBound_z bytes; the run ends unless these succeed), inflate() offered the
// compressed bytes (at most 2^32 - 1 of them), room for the data (as much) and any flush returns Z_NEED_DICT with
// adler set to the Adler-32 of the dictionary, as a copy made before compression holds it.
#include "laws_common.h"

int main(void) {
	size_t dict_len = 1 + upto(UINT_MAX - 1);
	size_t data_len = upto(PTRDIFF_MAX);
	unsigned char *dict = alloc_any_bytes(dict_len);
	unsigned char *data = alloc_any_bytes(data_len);
	if (dict == NULL || data == NULL)
		return 0;
	unsigned char *dict_copy = copy_of(dict, dict_len);
	unsigned char *out = malloc(data_len);
	int level = (int) nondet_u32();
	int window_bits = 8 + (int) upto(7);
	int mem_level = (int) nondet_u32();
	int strategy = (int) nondet_u32();
	if (dict_copy == NULL || out == NULL)
		return 0;
	z_stream compressor;
	new_stream(&compressor);
	if (deflateInit2(&compressor, level, Z_DEFLATED, window_bits, mem_level, strategy) != Z_OK)
		return 0;
	if (deflateSetDictionary(&compressor, dict, (uInt) dict_len) != Z_OK)
		return 0;
	size_t out_size = deflateBound_z(&compressor, data_len);
	unsigned char *compressed = malloc(out_size);
	if (compressed == NULL)
		return 0;
	compressor.next_in = data;
	compressor.next_out = compressed;
	int code;
	do {
		size_t rest = data_len - (size_t) (compressor.next_in - data);
		int flush = Z_NO_FLUSH;
		if (rest <= UINT_MAX)
			flush = Z_FINISH;
		compressor.avail_in = clip(rest);
		compressor.avail_out = clip(out_size - (size_t) (compressor.next_out - compressed));

		code = deflate(&compressor, flush);
	} while (code == Z_OK);
	if (code != Z_STREAM_END)
		return 0;
	size_t compressed_len = (size_t) (compressor.next_out - compressed);
	z_stream decompressor;
	new_stream(&decompressor);
	// zlib.h, deflateInit2: "a request for 8 will result in 9"; "use 9 with inflateInit2()"
	if (window_bits == 8)
		window_bits = 9;
	if (inflateInit2(&decompressor, window_bits) != Z_OK)
		return 0;
	set_buffer(&decompressor, compressed, clip(compressed_len), out, clip(data_len));

	code = inflate(&decompressor, (int) nondet_u32());

	// RFC 1950 2.2, FDICT: "DICT is the Adler-32 checksum of this sequence of bytes". zlib.h, inflate: "If a preset
	// dictionary is needed after this call (see inflateSetDictionary below), inflate sets strm->adler to the
	// Adler-32 checksum of the dictionary chosen by the compressor and returns Z_NEED_DICT"
	gp_assert(code == Z_NEED_DICT && decompressor.adler == adler32_z(1, dict_copy, dict_len));
	return 0;
}
harness/laws_common.h, 40 lines
C
// laws_common.h: trivial helpers shared by the zlib laws (each law includes it once). No models, no algorithms.
#include <limits.h>
#include <stdlib.h>
#include "quickproof.h"
#include "zlib.h"
static size_t upto(size_t max) {
	size_t value = nondet_size();
	return value < max ? value : max;
}
static uInt clip(size_t n) { return n < UINT_MAX ? (uInt) n : UINT_MAX; }
static unsigned char *alloc_any_bytes(size_t n) {
	unsigned char *bytes = malloc(n);
	if (bytes != NULL)
		nondet_bytes(bytes, n);
	return bytes;
}
static unsigned char *copy_of(const unsigned char *source, size_t n) {
	unsigned char *copy = malloc(n);
	for (size_t i = 0; copy != NULL && i < n; i++)
		copy[i] = source[i];
	return copy;
}
static int bytes_eq(const unsigned char *a, const unsigned char *b, size_t n) {
	for (size_t i = 0; i < n; i++)
		if (a[i] != b[i])
			return 0;
	return 1;
}
static void set_buffer(z_stream *strm, unsigned char *in, size_t in_len, unsigned char *out, size_t out_len) {
	strm->next_in = in;
	strm->avail_in = (uInt) in_len;
	strm->next_out = out;
	strm->avail_out = (uInt) out_len;
}
static void new_stream(z_stream *strm) {
	strm->zalloc = Z_NULL;
	strm->zfree = Z_NULL;
	strm->opaque = Z_NULL;
	set_buffer(strm, Z_NULL, 0, Z_NULL, 0);
}

The theorem

QuickProof generated this statement from the spec, in src/contracts/api_dict_id.v:

Rocq
Theorem api_dict_id : harness_safe whole_prog.

src/contracts/laws.v states it on the spec's own program, whole_prog (the spec linked with the code under test), with its proof:

Rocq
Theorem api_dict_id : harness_safe Zlib.contracts.api_dict_id.whole_prog.
Proof. exact (proj1 (proj2 (proj2 (proj2 Zlib.contracts.suite.suite)))). Qed.

Read as a statement about runs, it says that no run of the program has undefined behaviour or a failing check, for every value the spec can draw. That reading rests on VST's adequacy theorem, which is not yet instantiated in Rocq (formerly Coq) for QuickProof's environment.

The C files (units) its program links
  • adler32.c
  • crc32.c
  • deflate.c
  • trees.c
  • inflate.c
  • inffast.c
  • inftrees.c
  • zutil.c
  • quickproof/libc/libc.c

What it leaves out

  • What the first comment of the spec excludes, and its bounds.
  • Like every spec of this proof: termination (a run that never returns is not a counterexample), and binaries built by a compiler (the theorem is about the code as CompCert defines C for x86_64, LP64), one thread.
  • Where zlib reports Z_MEM_ERROR, most specs end the run and claim nothing about it; the first comment of the spec says so.
  • The edits to zlib's code, listed in the repository, are tested, not proved.

The summary page says what the proof as a whole covers.

How it was proved

AI agents wrote the proof, and Rocq checks it. qp verify passes on this repository: this statement is the one generated from the spec at the contract commit, and its proof uses only Rocq's standard axioms and VST's abstract malloc library.