Update to liblzma and make kmer-counters the defaults

README.md

@@ -198,20 +198,13 @@ To build the tool the Rust stable (>= 1.75) toolchain is required, and can be do
 ```
 curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
 rustup toolchain install stable
-
 ```
 
 ### Windows
 
 Follow the instructions at the site:
 https://rustup.rs/
 
-### Additional opt-in features
-
-Additional features can be enabled by specifying them in the command line while building/installing GGCAT (ex. --features "feature1,feature2"):
-
-- **kmer-counters**: Adds kmer abundance for each unitig, in a BCALM2 compatible format. If enabled GGCAT uses more memory while building colored graphs
-
 ### Building
 
 Then the tool can be installed with the commands:
@@ -226,6 +219,15 @@ the binary is automatically copied to `$HOME/.cargo/bin`
 
 To launch the tool directly from the command line, the above directory should be added to the `$PATH` variable.
 
+### Features list
+
+GGCAT ships with some features enabled by default. These default features can be disabled by specifying --no-default-features in the command line while building/installing GGCAT.
+Individual features can be enabled by specifying them (ex. --features "feature1,feature2") in the command line while building/installing GGCAT.
+
+| Feature name    | Default | Description |
+| -------- | ------- | ------- |
+| **kmer-counters** | Yes | Adds kmer abundance for each unitig, in a BCALM2 compatible format. Disable to reduce memory usage while building colored graphs. |
+
 ## API usage
 
 GGCAT has an API for both Rust and C++.

crates/cmdline/Cargo.toml

@@ -63,7 +63,7 @@ clap = { version = "4.5.50", features = ["derive"] }
 
 
 [features]
-default = ["full"]
+default = ["full", "kmer-counters"]
 memory-guards = ["parallel-processor/memory-guards"]
 mem-analysis = ["parallel-processor/track-usage"]
 no-stats = ["parallel-processor/no-stats"]

crates/io/Cargo.toml

@@ -27,7 +27,7 @@ parking_lot = "0.12.3"
 byteorder = "1.5.0"
 lz4 = "1.25.0"
 bzip2 = "0.4.4"
-xz2 = "0.1.7"
+liblzma = "0.4.7"
 zstd = "0.13.2"
 flate2 = "1.0.30"
 bstr = "1.9.1"

crates/io/src/lines_reader.rs

@@ -100,7 +100,7 @@ impl LinesReader {
                     );
                 });
         } else if path.as_ref().extension().filter(|x| *x == "xz").is_some() {
-            let file = xz2::read::XzDecoder::new(
+            let file = liblzma::read::XzDecoder::new(
                 File::open(&path).expect(&format!("Cannot open file {}", path.as_ref().display())),
             );
             self.read_stream_buffered(file, callback)

crates/querier/Cargo.toml

@@ -35,7 +35,7 @@ lz4 = "1.25.0"
 flate2 = "1.0.30"
 zstd = "0.13.2"
 bzip2 = "0.6.1"
-xz2 = "0.1.7"
+liblzma = "0.4.7"
 ggcat-logging = { version = "2.2.0", path = "../logging" }
 anyhow = "1.0.89"
 typenum = "1.18.0"

crates/querier/src/pipeline/colored_query_output.rs

@@ -34,7 +34,7 @@ enum QueryOutputFileWriter {
     GzipCompressed(Option<flate2::write::GzEncoder<File>>),
     ZstdCompressed(Option<zstd::stream::write::Encoder<'static, File>>),
     BZ2Compressed(Option<bzip2::write::BzEncoder<File>>),
-    XZCompressed(Option<xz2::write::XzEncoder<File>>),
+    XZCompressed(Option<liblzma::write::XzEncoder<File>>),
 }
 
 impl Write for QueryOutputFileWriter {
@@ -137,12 +137,10 @@ pub fn colored_query_output<MH: HashFunctionFactory, CX: ColorsManager>(
                         .unwrap(),
                 )),
                 Some("gz") => {
-                    QueryOutputFileWriter::GzipCompressed(Some(
-                        flate2::GzBuilder::new().write(
-                            query_output_file,
-                            Compression::new(output_compression_level.min(9)),
-                        ),
-                    ))
+                    QueryOutputFileWriter::GzipCompressed(Some(flate2::GzBuilder::new().write(
+                        query_output_file,
+                        Compression::new(output_compression_level.min(9)),
+                    )))
                 }
                 Some("zst") | Some("zstd") => QueryOutputFileWriter::ZstdCompressed(Some(
                     zstd::stream::write::Encoder::new(
@@ -151,15 +149,18 @@ pub fn colored_query_output<MH: HashFunctionFactory, CX: ColorsManager>(
                     )
                     .unwrap(),
                 )),
-                Some("bz2") => QueryOutputFileWriter::BZ2Compressed(Some(
-                    bzip2::write::BzEncoder::new(
+                Some("bz2") => {
+                    QueryOutputFileWriter::BZ2Compressed(Some(bzip2::write::BzEncoder::new(
                         query_output_file,
                         bzip2::Compression::new(output_compression_level.min(9)),
-                    ),
-                )),
-                Some("xz") => QueryOutputFileWriter::XZCompressed(Some(
-                    xz2::write::XzEncoder::new(query_output_file, output_compression_level.min(9)),
-                )),
+                    )))
+                }
+                Some("xz") => {
+                    QueryOutputFileWriter::XZCompressed(Some(liblzma::write::XzEncoder::new(
+                        query_output_file,
+                        output_compression_level.min(9),
+                    )))
+                }
                 _ => QueryOutputFileWriter::Plain(Some(query_output_file)),
             },
         ),

crates/sequence_output/Cargo.toml

@@ -30,7 +30,7 @@ parking_lot = "0.12.5"
 serde = "1.0.228"
 zstd = "0.13.3"
 bzip2 = "0.6.1"
-xz2 = "0.1.7"
+liblzma = "0.4.7"
 
 
 [features]

crates/sequence_output/src/structured_sequences/fasta.rs

@@ -114,7 +114,7 @@ impl<CX: ColorsManager, LinksInfo: IdentSequenceWriter> StructuredSequenceBacken
     }
 
     fn new_compressed_xz(path: impl AsRef<Path>, level: u32) -> Self {
-        let compress_stream = xz2::write::XzEncoder::new(
+        let compress_stream = liblzma::write::XzEncoder::new(
             BufWriter::with_capacity(DEFAULT_OUTPUT_BUFFER_SIZE, File::create(&path).unwrap()),
             level,
         );

crates/sequence_output/src/structured_sequences/gfa.rs

@@ -128,7 +128,7 @@ impl<const VERSION: u32, CX: ColorsManager, LinksInfo: IdentSequenceWriter>
     }
 
     fn new_compressed_xz(path: impl AsRef<Path>, level: u32) -> Self {
-        let compress_stream = xz2::write::XzEncoder::new(
+        let compress_stream = liblzma::write::XzEncoder::new(
             BufWriter::with_capacity(DEFAULT_OUTPUT_BUFFER_SIZE, File::create(&path).unwrap()),
             level,
         );

crates/sequence_output/src/structured_sequences/stream_finish.rs

@@ -1,10 +1,10 @@
 use bzip2::write::BzEncoder;
 use flate2::write::GzEncoder;
+use liblzma::write::XzEncoder;
 use std::{
     fs::File,
     io::{BufWriter, Write},
 };
-use xz2::write::XzEncoder;
 
 pub(crate) trait SequencesFileFinish: Write {
     fn finalize(self);