Files
c3c/test/compression/zip_compare_7z.c3
Manu Linares eae7d0c4a1 stdlib: std::compression::zip and std::compression::deflate (#2930)
* stdlib: implement `std::compression::zip` and `std::compression::deflate`

- C3 implementation of DEFLATE (RFC 1951) and ZIP archive handling.
- Support for reading and writing archives using STORE and DEFLATE
methods.
- Decompression supports both fixed and dynamic Huffman blocks.
- Compression using greedy LZ77 matching.
- Zero dependencies on libc.
- Stream-based entry reading and writing.
- Full unit test coverage.

NOTE: This is an initial implementation. Future improvements could be:

- Optimization of the LZ77 matching (lazy matching).
- Support for dynamic Huffman blocks in compression.
- ZIP64 support for large files/archives.
- Support for encryption and additional compression methods.

* optimizations+refactoring

deflate:
- replace linear search with hash-based match finding.
- implement support for dynamic Huffman blocks using the Package-Merge
algorithm.
- add streaming decompression.
- add buffered StreamBitReader.

zip:
- add ZIP64 support.
- add CP437 and UTF-8 filename encoding detection.
- add DOS date/time conversion and timestamp preservation.
- add ZipEntryReader for streaming entry reads.
- implement ZipArchive.extract and ZipArchive.recover helpers.

other:
- Add `set_modified_time` to std::io;
- Add benchmarks and a few more unit tests.

* zip: add archive comment support

add tests

* forgot to rename the benchmark :(

* detect utf8 names on weird zips

fix method not passed to open_writer

* another edge case where directory doesn't end with /

* testing utilities

- detect encrypted zip
- `ZipArchive.open_writer` default to DEFLATE

* fix zip64 creation, add tests

* fix ZIP header endianness for big-endian compatibility

Update ZipLFH, ZipCDH, ZipEOCD, Zip64EOCD, and Zip64Locator structs to
use little-endian bitstruct types from std::core::bitorder

* fix ZipEntryReader position tracking and seek logic ZIP_METHOD_STORE

added a test to track this

* add package-merge algorithm attribution

Thanks @konimarti

* standalone deflate_benchmark.c3 against `miniz`

* fix integer overflows, leaks and improve safety

* a few safety for 32-bit systems and tests

* deflate compress optimization

* improve match finding, hash updates, and buffer usage

* use ulong for zip offsets

* style changes (#18)

* style changes

* update tests

* style changes in `deflate.c3`

* fix typo

* Allocator first. Some changes to deflate to use `copy_to`

* Fix missing conversion on 32 bits.

* Fix deflate stream. Formatting. Prefer switch over if-elseif

* - Stream functions now use long/ulong rather than isz/usz for seek/available.
- `instream.seek` is replaced by `set_cursor` and `cursor`.
- `instream.available`, `cursor` etc are long/ulong rather than isz/usz to be correct on 32-bit.

* Update to constdef

* Fix test

---------

Co-authored-by: Book-reader <thevoid@outlook.co.nz>
Co-authored-by: Christoffer Lerno <christoffer@aegik.com>
2026-02-20 20:41:34 +01:00

195 lines
4.2 KiB
Plaintext

<*
Compare `C3 zip` vs `7z` extraction
External dependencies: 7z, diff
*>
module verify_zip;
import std;
import libc;
fn int main(String[] args)
{
if (args.len < 2)
{
io::printfn("Usage: %s [-r|--recursive] [-o|--output <dir>] <zip_dir>", args[0]);
return 1;
}
bool recursive = false;
String zip_dir;
String output_dir;
for (int i = 1; i < args.len; i++)
{
String arg = args[i];
switch (arg)
{
case "-r":
case "--recursive":
recursive = true;
case "-o":
case "--output":
if (++i >= args.len)
{
io::printfn("Error: %s requires a directory path", arg);
return 1;
}
output_dir = args[i];
default:
if (arg.starts_with("-"))
{
io::printfn("Error: unknown option %s", arg);
return 1;
}
if (zip_dir)
{
io::printfn("Error: multiple zip directories specified ('%s' and '%s')", zip_dir, arg);
return 1;
}
zip_dir = arg;
}
}
if (!zip_dir)
{
io::printfn("Error: no zip directory specified.");
return 1;
}
return process_dir(zip_dir, recursive, output_dir);
}
fn int process_dir(String dir, bool recursive, String output_dir)
{
PathList? files = path::ls(tmem, path::temp(dir)!!);
if (catch excuse = files)
{
io::printfn("Could not open directory: %s (Excuse: %s)", dir, excuse);
return 1;
}
foreach (p : files)
{
String name = p.basename();
if (name == "." || name == "..") continue;
String zip_path = path::temp(dir)!!.tappend(name)!!.str_view();
if (file::is_dir(zip_path))
{
if (recursive)
{
if (process_dir(zip_path, recursive, output_dir) != 0) return 1;
}
continue;
}
if (!name.ends_with(".zip")) continue;
ulong size = 0;
File? f = file::open(zip_path, "rb");
if (try fh = f)
{
(void)fh.seek(0, Seek.END);
size = fh.seek(0, Seek.CURSOR) ?? 0;
fh.close()!!;
}
io::printf("Verifying %-40s [%7d KB] ", name[:(min(name.len, 40))], size / 1024);
switch (verify_one(zip_path, output_dir))
{
case 0:
io::printfn("%sFAILED%s ❌", Ansi.RED, Ansi.RESET);
return 1;
case 1:
io::printfn("%sPASSED%s ✅", Ansi.GREEN, Ansi.RESET);
default:
io::printn();
}
}
return 0;
}
fn int verify_one(String zip_path, String output_dir)
{
Path extract_root;
if (output_dir)
{
extract_root = path::temp(output_dir)!!;
}
else
{
extract_root = path::temp_directory(tmem)!!;
}
String name = (String)path::temp(zip_path)!!.basename();
Path temp_c3 = extract_root.tappend(name.tconcat("_c3"))!!;
Path temp_7z = extract_root.tappend(name.tconcat("_7z"))!!;
(void)path::mkdir(temp_c3, true);
(void)path::mkdir(temp_7z, true);
ZipArchive? archive = zip::open(zip_path, "r");
if (catch excuse = archive)
{
io::printfn("%sFAIL%s (open: %s)", Ansi.RED, Ansi.RESET, excuse);
return 0;
}
defer (void)archive.close();
Time start = time::now();
if (catch excuse = archive.extract(temp_c3.str_view()))
{
if (excuse == zip::ENCRYPTED_FILE)
{
io::printf("%sSKIPPED%s (Encrypted)", Ansi.YELLOW, Ansi.RESET);
return 2;
}
io::printfn("%sFAIL%s (extract: %s)", Ansi.RED, Ansi.RESET, excuse);
return 0;
}
Duration c3_time = time::now() - start;
start = time::now();
if (!extract_7z(zip_path, temp_7z.str_view()))
{
io::printfn("%sFAIL%s (7z extract)", Ansi.RED, Ansi.RESET);
return 0;
}
Duration p7_time = time::now() - start;
io::printf(" [C3: %5d ms, 7z: %5d ms]", (long)c3_time / 1000, (long)p7_time / 1000);
io::print(" Comparing... ");
if (!compare_dirs(temp_c3.str_view(), temp_7z.str_view()))
{
io::printfn("%sFAIL%s (Differences found)", Ansi.RED, Ansi.RESET);
return 0;
}
// keep files on error for manual verification
(void)path::rmtree(temp_c3);
(void)path::rmtree(temp_7z);
return 1;
}
fn bool extract_7z(String zip_path, String output_dir)
{
String out_opt = "-o".tconcat(output_dir);
String[] cmd = { "7z", "x", zip_path, out_opt, "-y", "-bb0" };
SubProcess? proc = process::create(cmd, { .search_user_path = true });
if (catch excuse = proc) return false;
return (int)proc.join()!! == 0;
}
fn bool compare_dirs(String dir1, String dir2)
{
String[] cmd = { "diff", "-r", dir1, dir2 };
SubProcess? proc = process::create(cmd, { .search_user_path = true, .inherit_stdio = true });
if (catch excuse = proc) return false;
int res = (int)proc.join()!!;
return res == 0;
}