merge: Merge pull request #3 from St4NNi/feat/compare

[0.1.0-beta.1] Feat/compare

Author: St4NNi

.github/workflows/release.yaml

@@ -0,0 +1,17 @@
+name: automatic_test_build_publish
+on: 
+  release:
+    types: [created]
+  workflow_dispatch: {}
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository with submodules
+        uses: actions/checkout@v3
+        with:
+          submodules: recursive
+      - name: Cargo publish    
+        run: cargo publish --token ${CRATES_TOKEN}
+        env:
+          CRATES_TOKEN: ${{ secrets.CRATES_TOKEN }}

Cargo.lock

@@ -1,17 +1,17 @@
 [package]
 name = "jam-rs"
-version = "0.1.0"
+version = "0.1.0-beta.1"
 edition = "2021"
 repository = "https://github.com/St4NNi/jam-rs"
 license = "MIT"
-description = "Just another minhash (Jam) implementation in Rust"
+description = "Just another (genomic) minhash (Jam) implementation in Rust"
 
 [dependencies]
 anyhow = "1.0.75"
 bincode = "1.3.3"
-flate2 = "1.0.27"
+flate2 = "1.0.28"
 needletail = "0.5.1"
-rayon = "1.7.0"
+rayon = "1.8.0"
 xxhash-rust = { version = "0.8.7", features = ["xxh3"]}
 bytemuck = "1.14.0"
 serde = { version = "1", features = ["derive"] }

Cargo.toml

@@ -11,6 +11,20 @@ Implements parts of the ScaledMinHash / FracMinHash algorithm described in [sour
 
 Unlike traditional implementations like [sourmash](https://joss.theoj.org/papers/10.21105/joss.00027) or [mash](https://doi.org/10.1186/s13059-016-0997-x) this version tries to specialise more on estimating the containment of small sequences in large sets. This is intended to be used to screen terabytes of data in just a few seconds / minutes.
 
+### Installation
+
+A pre-release is published via [crates.io](https://crates.io/) to install it use (you need to have `cargo` and the `rust-toolchain` installed, the easiest way is via [rustup.rs](https://rustup.rs/)):
+
+```bash
+cargo install jam-rs
+```
+
+If you want the bleeding edge development release you can install via git:
+
+```bash
+cargo install --git https://github.com/St4NNi/jam-rs
+```
+
 ### Comparison
 
 - [xxhash3](https://github.com/DoumanAsh/xxhash-rust) or [ahash-fallback](https://github.com/tkaitchuck/aHash/wiki/AHash-fallback-algorithm) (for kmer < 32) instead of [murmurhash3](https://github.com/mhallin/murmurhash3-rs)

README.md

@@ -5,7 +5,7 @@ use std::path::PathBuf;
 #[derive(Debug, Parser)]
 #[command(name = "jam")]
 #[command(bin_name = "jam")]
-#[command(version = "0.1.0")]
+#[command(version = "0.1.0-beta.1")]
 #[command(
     about = "Just another minhasher, obviously blazingly fast",
     long_about = "A heavily optimized minhash implementation that focuses less on accuracy and more on quick scans of large datasets."
@@ -93,13 +93,22 @@ pub enum Commands {
         input: PathBuf,
         /// Database sketch(es)
         #[arg(short, long)]
-        database: PathBuf,
+        database: Vec<PathBuf>,
         /// Output to file instead of stdout
         #[arg(short, long)]
         #[arg(value_parser = clap::value_parser!(std::path::PathBuf))]
         output: Option<PathBuf>,
         /// Cut-off value for similarity
         #[arg(short, long, default_value = "0.0")]
         cutoff: f64,
+        /// Use the Stats params for restricting results
+        #[arg(long)]
+        stats: bool,
+        /// Use GC stats with an upper bound of x% and a lower bound of y%
+        #[arg(long)]
+        gc_lower: Option<u8>,
+        /// Use GC stats with an upper bound of x% and a lower bound of y%
+        #[arg(long)]
+        gc_upper: Option<u8>,
     },
 }