in gix-features, use libz-rs-sys directly, skipping flate2

Author: folkertdev

Cargo.lock

@@ -55,9 +55,9 @@ io-pipe = ["dep:bytes"]
 crc32 = ["dep:crc32fast"]
 
 ## Enable the usage of zlib-related utilities to compress or decompress data.
-## This enables the `flate2` crate, and always uses the high-performance `zlib-rs` backend.
+## This enables and uses the high-performance `zlib-rs` backend.
 ## Note that the various past features for selecting zlib backends are now deprecated and do nothing.
-zlib = ["dep:flate2", "dep:thiserror"]
+zlib = ["dep:libz-rs-sys", "dep:thiserror"]
 ## Deprecated: gix always uses zlib-rs.
 zlib-ng = ["zlib"]
 ## Deprecated: gix always uses zlib-rs now. As of zlib-rs 0.5.0 (used by flate2
@@ -121,7 +121,7 @@ bytesize = { version = "2.0.1", optional = true }
 bytes = { version = "1.0.0", optional = true }
 
 # zlib module
-flate2 = { version = "1.1.1", optional = true, default-features = false, features = ["zlib-rs"] }
+libz-rs-sys = { version = "0.5.2", optional = true }
 thiserror = { version = "2.0.0", optional = true }
 
 once_cell = { version = "1.21.3", optional = true }

gix-features/Cargo.toml

@@ -12,7 +12,7 @@
     doc = ::document_features::document_features!()
 )]
 #![cfg_attr(all(doc, feature = "document-features"), feature(doc_cfg, doc_auto_cfg))]
-#![deny(missing_docs, rust_2018_idioms, unsafe_code)]
+#![deny(rust_2018_idioms)]
 
 ///
 pub mod cache;

gix-features/src/lib.rs

@@ -1,4 +1,111 @@
-pub use flate2::{Decompress, Status};
+use std::fmt::Display;
+
+pub struct Decompress(Box<libz_rs_sys::z_stream>);
+
+unsafe impl Sync for Decompress {}
+unsafe impl Send for Decompress {}
+
+impl Decompress {
+    pub fn total_in(&self) -> u64 {
+        self.0.total_in
+    }
+
+    pub fn total_out(&self) -> u64 {
+        self.0.total_out
+    }
+
+    pub fn new(_zlib_header: bool) -> Self {
+        let mut this = Box::new(libz_rs_sys::z_stream::default());
+
+        unsafe {
+            libz_rs_sys::inflateInit_(
+                &mut *this,
+                libz_rs_sys::zlibVersion(),
+                core::mem::size_of::<libz_rs_sys::z_stream>() as core::ffi::c_int,
+            );
+        }
+
+        Self(this)
+    }
+
+    pub fn reset(&mut self, _: bool) {
+        unsafe { libz_rs_sys::inflateReset(&mut *self.0) };
+    }
+
+    pub fn decompress(
+        &mut self,
+        input: &[u8],
+        output: &mut [u8],
+        flush: FlushDecompress,
+    ) -> Result<Status, DecompressError> {
+        self.0.avail_in = input.len() as _;
+        self.0.avail_out = output.len() as _;
+
+        self.0.next_in = input.as_ptr();
+        self.0.next_out = output.as_mut_ptr();
+
+        match unsafe { libz_rs_sys::inflate(&mut *self.0, flush as _) } {
+            libz_rs_sys::Z_OK => Ok(Status::Ok),
+            libz_rs_sys::Z_BUF_ERROR => Ok(Status::BufError),
+            libz_rs_sys::Z_STREAM_END => Ok(Status::StreamEnd),
+
+            libz_rs_sys::Z_STREAM_ERROR => Err(DecompressError("stream error")),
+            libz_rs_sys::Z_DATA_ERROR => Err(DecompressError("data error")),
+            libz_rs_sys::Z_MEM_ERROR => Err(DecompressError("insufficient memory")),
+            libz_rs_sys::Z_NEED_DICT => Err(DecompressError("need dictionary")),
+            c => panic!("unknown return code: {}", c),
+        }
+    }
+}
+
+impl Drop for Decompress {
+    fn drop(&mut self) {
+        unsafe { libz_rs_sys::inflateEnd(&mut *self.0) };
+    }
+}
+
+#[derive(Debug, thiserror::Error)]
+pub struct DecompressError(&'static str);
+
+impl Display for DecompressError {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.write_str(self.0)
+    }
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum Status {
+    Ok,
+    BufError,
+    StreamEnd,
+}
+
+/// Values which indicate the form of flushing to be used when
+/// decompressing in-memory data.
+#[derive(Copy, Clone, PartialEq, Eq, Debug)]
+#[non_exhaustive]
+#[allow(clippy::unnecessary_cast)]
+pub enum FlushDecompress {
+    /// A typical parameter for passing to compression/decompression functions,
+    /// this indicates that the underlying stream to decide how much data to
+    /// accumulate before producing output in order to maximize compression.
+    None = libz_rs_sys::Z_NO_FLUSH as isize,
+
+    /// All pending output is flushed to the output buffer and the output is
+    /// aligned on a byte boundary so that the decompressor can get all input
+    /// data available so far.
+    ///
+    /// Flushing may degrade compression for some compression algorithms and so
+    /// it should only be used when necessary. This will complete the current
+    /// deflate block and follow it with an empty stored block.
+    Sync = libz_rs_sys::Z_SYNC_FLUSH as isize,
+
+    /// Pending input is processed and pending output is flushed.
+    ///
+    /// The return value may indicate that the stream is not yet done and more
+    /// data has yet to be processed.
+    Finish = libz_rs_sys::Z_FINISH as isize,
+}
 
 /// non-streaming interfaces for decompression
 pub mod inflate {
@@ -8,10 +115,10 @@ pub mod inflate {
     pub enum Error {
         #[error("Could not write all bytes when decompressing content")]
         WriteInflated(#[from] std::io::Error),
-        #[error("Could not decode zip stream, status was '{0:?}'")]
-        Inflate(#[from] flate2::DecompressError),
+        #[error("Could not decode zip stream, status was '{0}'")]
+        Inflate(#[from] super::DecompressError),
         #[error("The zlib status indicated an error, status was '{0:?}'")]
-        Status(flate2::Status),
+        Status(super::Status),
     }
 }
 
@@ -31,10 +138,10 @@ impl Default for Inflate {
 
 impl Inflate {
     /// Run the decompressor exactly once. Cannot be run multiple times
-    pub fn once(&mut self, input: &[u8], out: &mut [u8]) -> Result<(flate2::Status, usize, usize), inflate::Error> {
+    pub fn once(&mut self, input: &[u8], out: &mut [u8]) -> Result<(Status, usize, usize), inflate::Error> {
         let before_in = self.state.total_in();
         let before_out = self.state.total_out();
-        let status = self.state.decompress(input, out, flate2::FlushDecompress::None)?;
+        let status = self.state.decompress(input, out, FlushDecompress::None)?;
         Ok((
             status,
             (self.state.total_in() - before_in) as usize,

gix-features/src/zlib/mod.rs

@@ -1,4 +1,4 @@
-use flate2::Compress;
+use crate::zlib::Status;
 
 const BUF_SIZE: usize = 4096 * 8;
 
@@ -24,15 +24,124 @@ where
     }
 }
 
+pub struct Compress(Box<libz_rs_sys::z_stream>);
+
+unsafe impl Sync for Compress {}
+unsafe impl Send for Compress {}
+
+impl Compress {
+    pub fn total_in(&self) -> u64 {
+        self.0.total_in
+    }
+
+    pub fn total_out(&self) -> u64 {
+        self.0.total_out
+    }
+
+    pub fn new() -> Self {
+        let mut this = Box::new(libz_rs_sys::z_stream::default());
+
+        unsafe {
+            libz_rs_sys::deflateInit_(
+                &mut *this,
+                libz_rs_sys::Z_BEST_SPEED,
+                libz_rs_sys::zlibVersion(),
+                core::mem::size_of::<libz_rs_sys::z_stream>() as core::ffi::c_int,
+            );
+        }
+
+        Self(this)
+    }
+
+    pub fn reset(&mut self) {
+        unsafe { libz_rs_sys::deflateReset(&mut *self.0) };
+    }
+
+    pub fn compress(&mut self, input: &[u8], output: &mut [u8], flush: FlushCompress) -> Result<Status, CompressError> {
+        self.0.avail_in = input.len() as _;
+        self.0.avail_out = output.len() as _;
+
+        self.0.next_in = input.as_ptr();
+        self.0.next_out = output.as_mut_ptr();
+
+        match unsafe { libz_rs_sys::deflate(&mut *self.0, flush as _) } {
+            libz_rs_sys::Z_OK => Ok(Status::Ok),
+            libz_rs_sys::Z_BUF_ERROR => Ok(Status::BufError),
+            libz_rs_sys::Z_STREAM_END => Ok(Status::StreamEnd),
+
+            libz_rs_sys::Z_STREAM_ERROR => Err(CompressError("stream error")),
+            _ => todo!(),
+        }
+    }
+}
+
+impl Drop for Compress {
+    fn drop(&mut self) {
+        unsafe { libz_rs_sys::deflateEnd(&mut *self.0) };
+    }
+}
+
+#[derive(Debug, thiserror::Error)]
+pub struct CompressError(&'static str);
+
+impl std::fmt::Display for CompressError {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.write_str(self.0)
+    }
+}
+
+/// Values which indicate the form of flushing to be used when compressing
+/// in-memory data.
+#[derive(Copy, Clone, PartialEq, Eq, Debug)]
+#[non_exhaustive]
+#[allow(clippy::unnecessary_cast)]
+pub enum FlushCompress {
+    /// A typical parameter for passing to compression/decompression functions,
+    /// this indicates that the underlying stream to decide how much data to
+    /// accumulate before producing output in order to maximize compression.
+    None = libz_rs_sys::Z_NO_FLUSH as isize,
+
+    /// All pending output is flushed to the output buffer, but the output is
+    /// not aligned to a byte boundary.
+    ///
+    /// All input data so far will be available to the decompressor (as with
+    /// `Flush::Sync`). This completes the current deflate block and follows it
+    /// with an empty fixed codes block that is 10 bits long, and it assures
+    /// that enough bytes are output in order for the decompressor to finish the
+    /// block before the empty fixed code block.
+    Partial = libz_rs_sys::Z_PARTIAL_FLUSH as isize,
+
+    /// All pending output is flushed to the output buffer and the output is
+    /// aligned on a byte boundary so that the decompressor can get all input
+    /// data available so far.
+    ///
+    /// Flushing may degrade compression for some compression algorithms and so
+    /// it should only be used when necessary. This will complete the current
+    /// deflate block and follow it with an empty stored block.
+    Sync = libz_rs_sys::Z_SYNC_FLUSH as isize,
+
+    /// All output is flushed as with `Flush::Sync` and the compression state is
+    /// reset so decompression can restart from this point if previous
+    /// compressed data has been damaged or if random access is desired.
+    ///
+    /// Using this option too often can seriously degrade compression.
+    Full = libz_rs_sys::Z_FULL_FLUSH as isize,
+
+    /// Pending input is processed and pending output is flushed.
+    ///
+    /// The return value may indicate that the stream is not yet done and more
+    /// data has yet to be processed.
+    Finish = libz_rs_sys::Z_FINISH as isize,
+}
+
 mod impls {
     use std::io;
 
-    use flate2::{Compress, Compression, FlushCompress, Status};
-
-    use crate::zlib::stream::deflate;
+    use crate::zlib::stream::deflate::{self, Compress, FlushCompress};
+    use crate::zlib::Status;
 
     pub(crate) fn new_compress() -> Compress {
-        Compress::new(Compression::fast(), true)
+        Compress::new()
     }
 
     impl<W> deflate::Write<W>

gix-features/src/zlib/stream/deflate/mod.rs

@@ -5,9 +5,9 @@ mod deflate_stream {
     };
 
     use bstr::ByteSlice;
-    use flate2::Decompress;
 
     use crate::zlib::stream::deflate;
+    use crate::zlib::Decompress;
 
     /// Provide streaming decompression using the `std::io::Read` trait.
     /// If `std::io::BufReader` is used, an allocation for the input buffer will be performed.

gix-features/src/zlib/stream/deflate/tests.rs

@@ -1,6 +1,6 @@
 use std::{io, io::BufRead};
 
-use flate2::{Decompress, FlushDecompress, Status};
+use crate::zlib::{Decompress, FlushDecompress, Status};
 
 /// Read bytes from `rd` and decompress them using `state` into a pre-allocated fitting buffer `dst`, returning the amount of bytes written.
 pub fn read(rd: &mut impl BufRead, state: &mut Decompress, mut dst: &mut [u8]) -> io::Result<usize> {

gix-features/src/zlib/stream/inflate.rs

@@ -127,7 +127,7 @@ fn bad_objects_are_valid_until_they_are_actually_read_from_the_odb() {
         );
         assert_eq!(
             &format!("{:?}", parse_spec("cafea^{object}", &repo).unwrap_err())[..80],
-            r#"FindObject(Find(Loose(DecompressFile { source: Inflate(DecompressError(General {"#
+            r#"FindObject(Find(Loose(DecompressFile { source: Inflate(DecompressError("data err"#
         );
     }
 }