mirror of
https://github.com/c3lang/c3c.git
synced 2026-02-27 12:01:16 +00:00
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>
This commit is contained in:
@@ -104,28 +104,37 @@ fn void? ByteBuffer.pushback_byte(&self) @dynamic
|
||||
self.has_last = false;
|
||||
}
|
||||
|
||||
fn usz? ByteBuffer.seek(&self, isz offset, Seek seek) @dynamic
|
||||
fn long? ByteBuffer.cursor(&self) @dynamic
|
||||
{
|
||||
switch (seek)
|
||||
{
|
||||
case SET:
|
||||
if (offset < 0 || offset > self.write_idx) return INVALID_POSITION~;
|
||||
self.read_idx = offset;
|
||||
return offset;
|
||||
case CURSOR:
|
||||
if ((offset < 0 && self.read_idx < -offset) ||
|
||||
(offset > 0 && self.read_idx + offset > self.write_idx)) return INVALID_POSITION~;
|
||||
self.read_idx += offset;
|
||||
case END:
|
||||
if (offset < 0 || offset > self.write_idx) return INVALID_POSITION~;
|
||||
self.read_idx = self.write_idx - offset;
|
||||
}
|
||||
return self.read_idx;
|
||||
}
|
||||
|
||||
fn usz? ByteBuffer.available(&self) @inline @dynamic
|
||||
fn void? ByteBuffer.set_cursor(&self, long offset, SeekOrigin whence = FROM_START) @dynamic
|
||||
{
|
||||
return self.write_idx - self.read_idx;
|
||||
switch (whence)
|
||||
{
|
||||
case FROM_START:
|
||||
if (offset < 0 || offset > self.write_idx) return INVALID_POSITION~;
|
||||
self.read_idx = (usz)offset;
|
||||
case FROM_CURSOR:
|
||||
if ((offset < 0 && self.read_idx < -offset) ||
|
||||
(offset > 0 && self.read_idx + offset > self.write_idx)) return INVALID_POSITION~;
|
||||
self.read_idx += (usz)offset;
|
||||
case FROM_END:
|
||||
if (offset < 0 || offset > self.write_idx) return INVALID_POSITION~;
|
||||
self.read_idx = self.write_idx - (usz)offset;
|
||||
}
|
||||
}
|
||||
|
||||
fn usz? ByteBuffer.seek(&self, isz offset, Seek seek) @dynamic
|
||||
{
|
||||
self.set_cursor(offset, (SeekOrigin)seek.ordinal)!;
|
||||
return (usz)self.cursor();
|
||||
}
|
||||
|
||||
fn ulong? ByteBuffer.available(&self) @inline @dynamic
|
||||
{
|
||||
return (ulong)self.write_idx - self.read_idx;
|
||||
}
|
||||
|
||||
fn void ByteBuffer.grow(&self, usz n)
|
||||
|
||||
Reference in New Issue
Block a user