Merge pull request #90 from image-rs/weezl

Replace lzw decoder with weezl

Cargo.toml

@@ -17,7 +17,15 @@ repository = "https://github.com/image-rs/image-tiff"
 exclude = ["tests/images/*", "tests/fuzz_images/*"]
 
 [dependencies]
-lzw = "0.10"
+weezl = "0.1.0"
+
 [dependencies.miniz_oxide]
 version = "0.4.1"
 features = ["no_extern_crate_alloc"]
+
+[dev-dependencies]
+criterion = "0.3.1"
+
+[[bench]]
+name = "lzw"
+harness = false

benches/lzw.rs

@@ -0,0 +1,72 @@
+extern crate criterion;
+extern crate tiff;
+
+use criterion::{black_box, BenchmarkId, BenchmarkGroup, Criterion, Throughput, measurement::Measurement};
+use tiff::decoder::Decoder;
+
+fn read_image(image: &[u8]) {
+    let image = std::io::Cursor::new(image);
+    let decoder = Decoder::new(black_box(image));
+    let mut reader = decoder.unwrap();
+
+    while {
+        reader.read_image().unwrap();
+        reader.more_images()
+    } {}
+}
+
+fn main() {
+    struct BenchDef {
+        data: &'static [u8],
+        id: &'static str,
+        sample_size: usize,
+    }
+
+    fn run_bench_def<M: Measurement>(group: &mut BenchmarkGroup<M>, def: BenchDef) {
+        group
+            .sample_size(def.sample_size)
+            .throughput(Throughput::Bytes(def.data.len() as u64))
+            .bench_with_input(
+                BenchmarkId::new(def.id, def.data.len()),
+                def.data,
+                |b, input| {
+                    b.iter(|| read_image(input))
+                }
+            );
+    };
+
+    let mut c = Criterion::default().configure_from_args();
+    let mut group = c.benchmark_group("tiff-lzw");
+
+    /*
+    run_bench_def(&mut group, BenchDef {
+        data: include_bytes!(concat!(env!("CARGO_MANIFEST_DIR"), "/tests/images/quad-lzw-compat.tiff")),
+        id: "quad-lzw.tif",
+        sample_size: 500,
+    });
+    */
+
+    run_bench_def(&mut group, BenchDef {
+        data: include_bytes!(concat!(env!("CARGO_MANIFEST_DIR"), "/tests/images/issue_69_lzw.tiff")),
+        id: "issue-69-lzw.tif",
+        sample_size: 500,
+    });
+
+    run_bench_def(&mut group, BenchDef {
+        data: include_bytes!(concat!(env!("CARGO_MANIFEST_DIR"), "/tests/benches/kodim02-lzw.tif")),
+        id: "kodim02-lzw.tif",
+        sample_size: 20,
+    });
+
+    run_bench_def(&mut group, BenchDef {
+        data: include_bytes!(concat!(env!("CARGO_MANIFEST_DIR"), "/tests/benches/kodim07-lzw.tif")),
+        id: "kodim07-lzw.tif",
+        sample_size: 20,
+    });
+
+    run_bench_def(&mut group, BenchDef {
+        data: include_bytes!(concat!(env!("CARGO_MANIFEST_DIR"), "/tests/benches/Transparency-lzw.tif")),
+        id: "Transparency-lzw.tif",
+        sample_size: 20,
+    });
+}

src/decoder/stream.rs

@@ -2,7 +2,6 @@
 
 use crate::bytecast;
 use crate::error::{TiffError, TiffResult};
-use lzw;
 use miniz_oxide::inflate;
 use std::io::{self, Read, Seek};
 
@@ -244,12 +243,27 @@ impl LZWReader {
         let mut compressed = vec![0; compressed_length as usize];
         reader.read_exact(&mut compressed[..])?;
         let mut uncompressed = Vec::with_capacity(max_uncompressed_length);
-        let mut decoder = lzw::DecoderEarlyChange::new(lzw::MsbReader::new(), 8);
+        let mut decoder = weezl::decode::Decoder::with_tiff_size_switch(weezl::BitOrder::Msb, 8);
         let mut bytes_read = 0;
         while bytes_read < compressed_length && uncompressed.len() < max_uncompressed_length {
-            let (len, bytes) = decoder.decode_bytes(&compressed[bytes_read..])?;
-            bytes_read += len;
-            uncompressed.extend_from_slice(bytes);
+            let bytes_written = uncompressed.len();
+            uncompressed.reserve(1 << 12);
+            let buffer_space = uncompressed.capacity();
+            uncompressed.resize(buffer_space, 0u8);
+
+            let result = decoder.decode_bytes(&compressed[bytes_read..], &mut uncompressed[bytes_written..]);
+            bytes_read += result.consumed_in;
+            uncompressed.truncate(bytes_written + result.consumed_out);
+
+            match result.status {
+                Ok(weezl::LzwStatus::Ok) => {},
+                Ok(weezl::LzwStatus::Done) => break,
+                Ok(weezl::LzwStatus::NoProgress) => return Err(io::Error::new(
+                    io::ErrorKind::UnexpectedEof,
+                    "no lzw end code found",
+                )),
+                Err(err) => return Err(io::Error::new(io::ErrorKind::InvalidData, err)),
+            }
         }
 
         let bytes = uncompressed.len();

src/lib.rs

@@ -6,7 +6,7 @@
 //! # Related Links
 //! * <https://www.adobe.io/open/standards/TIFF.html> - The TIFF specification
 
-extern crate lzw;
+extern crate weezl;
 extern crate miniz_oxide;
 
 mod bytecast;

tests/benches/README.md

@@ -0,0 +1,4 @@
+Copyrights:
+
+kodim*.png: Eastman Kodak Company, released for unrestricted use
+Transparency.png: Public Domain, according to Wikimedia