CLI development

.github/deploy/build_aarch64-apple-darwin.sh

@@ -32,7 +32,7 @@ echo "linker = \"aarch64-apple-darwin22-gcc\"" >> .cargo/config.toml
 export CC="aarch64-apple-darwin22-gcc"
 export CXX="aarch64-apple-darwin22-g++"
 
-RUSTFLAGS='-L /osxcross/SDK/MacOSX13.0.sdk/usr/lib' cargo build --release --target aarch64-apple-darwin
+RUSTFLAGS='-L /osxcross/SDK/MacOSX13.0.sdk/usr/lib' cargo build --all-features --release --target aarch64-apple-darwin
 
 ## gather the stuff to distribute
 target=sablast-candidate-aarch64-apple-darwin
@@ -45,7 +45,7 @@ cp LICENSE-APACHE $path/
 cp LICENSE-MIT $path/
 cd /io/tmp
 tar -zcvf $target.tar.gz $target
-sha256sum $target.tar.gz > $target".sha256sum"
+sha256sum $target.tar.gz > $target".tar.gz.sha256sum"
 mv $target.tar.gz /io/
-mv $target".sha256sum" /io/
+mv $target".tar.gz.sha256sum" /io/
 cd /io/

.github/deploy/build_x86_64-apple-darwin.sh

@@ -32,7 +32,7 @@ echo "linker = \"x86_64-apple-darwin22-gcc\"" >> .cargo/config.toml
 export CC="x86_64-apple-darwin22-gcc"
 export CXX="x86_64-apple-darwin22-g++"
 
-RUSTFLAGS='-L /osxcross/SDK/MacOSX13.0.sdk/usr/lib' cargo build --release --target x86_64-apple-darwin
+RUSTFLAGS='-L /osxcross/SDK/MacOSX13.0.sdk/usr/lib' cargo build --all-features --release --target x86_64-apple-darwin
 
 ## gather the stuff to distribute
 target=sablast-candidate-x86_64-apple-darwin
@@ -45,7 +45,7 @@ cp LICENSE-APACHE $path/
 cp LICENSE-MIT $path/
 cd /io/tmp
 tar -zcvf $target.tar.gz $target
-sha256sum $target.tar.gz > $target".sha256sum"
+sha256sum $target.tar.gz > $target".tar.gz.sha256sum"
 mv $target.tar.gz /io/
-mv $target".sha256sum" /io/
+mv $target".tar.gz.sha256sum" /io/
 cd /io/

.github/workflows/build_and_test.yml

@@ -25,10 +25,7 @@ jobs:
       run: rustup update ${{ matrix.toolchain }} && rustup default ${{ matrix.toolchain }}
 
     - name: Build binary
-      run: cargo build --verbose
+      run: cargo build --features cli --verbose
 
     - name: Run unit and integration tests
       run: cargo test --no-fail-fast --verbose
-
-    - name: Run documenation examples as tests
-      run: cargo test --doc --verbose

.github/workflows/build_artifacts.yml

@@ -17,6 +17,7 @@ jobs:
           ARCHIVE_TYPES: tar.gz
           ARCHIVE_NAME: sablast-candidate-x86_64-unknown-linux-musl
           RUSTTARGET: x86_64-unknown-linux-musl
+          EXTRA_FEATURES: "cli"
           EXTRA_FILES: "COPYRIGHT LICENSE-APACHE LICENSE-MIT README.md"
           TOOLCHAIN_VERSION: stable-2024-09-05
           UPLOAD_MODE: none

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "sablast"
-version = "0.2.0"
+version = "0.3.0"
 edition = "2021"
 rust-version = "1.77.0"
 authors = ["Tommi Mäklin <[email protected]>"]
@@ -12,24 +12,36 @@ license = "MIT OR Apache-2.0"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
+[features]
+cli = ["dep:needletail", "dep:clap", "dep:rayon", "dep:log", "dep:stderrlog"]
+
+[[bin]]
+name = "sablast"
+path = "src/cli/main.rs"
+required-features = ["cli"]
+
 [dependencies]
 ## core
-# TODO Re-enable reading compressed sequences in needletail
-# This requires resolving the libllzma linker issue in build_artifacts.yml
-needletail = { version = "0.5.1", default-features = false }
-rayon = "1"
 sbwt = "0.3.1"
 
 ## cli
-clap = { version = "4", features = ["derive"] }
+clap = { version = "4", features = ["derive"], optional = true}
+
+### io
+#### TODO Re-enable reading compressed sequences in needletail
+##### This requires resolving the libllzma linker issue in build_artifacts.yml
+needletail = { version = "0.5.1", default-features = false, optional = true }
+
+### logging
+log = { version = "0.4.20", optional = true }
+stderrlog = { version = "0.6.0", optional = true }
+
+### threading
+rayon = { version = "1", optional = true }
 
 ## docs
 embed-doc-image="0.1.4"
 
-## logging
-log = "0.4.20"
-stderrlog = "0.6.0"
-
 [dev-dependencies]
 ## tests
 assert_approx_eq = "1"

src/cli.rs → src/cli/cli.rs

@@ -16,125 +16,137 @@ use clap::{Parser, Subcommand};
 #[derive(Parser)]
 #[command(version)]
 #[command(propagate_version = true)]
+#[cfg(feature = "cli")]
 pub struct Cli {
     #[command(subcommand)]
     pub command: Option<Commands>,
 }
 
 #[derive(Subcommand)]
+#[cfg(feature = "cli")]
 pub enum Commands {
     // Build SBWT index
     Build {
         // Input fasta or fastq sequence file(s)
         #[arg(group = "input", required = true)]
         seq_files: Vec<String>,
 
-	// Outputs
+        // Outputs
         #[arg(short = 'o', long = "output-prefix", required = false, help_heading = "Output")]
         output_prefix: Option<String>,
 
-	// Build parameters
-	// // k-mer size
+        // Build parameters
+        // // k-mer size
         #[arg(short = 'k', default_value_t = 31, help_heading = "Build options")]
         kmer_size: usize,
-	// // prefix precalc
-	#[arg(short = 'p', long = "prefix-precalc", default_value_t = 8, help_heading = "Build options")]
+        // // prefix precalc
+        #[arg(short = 'p', long = "prefix-precalc", default_value_t = 8, help_heading = "Build options")]
         prefix_precalc: usize,
-	// // deduplicate k-mer batches
-	#[arg(short = 'd', long = "dedup-batches", default_value_t = false, help_heading = "Build options")]
+        // // deduplicate k-mer batches
+        #[arg(short = 'd', long = "dedup-batches", default_value_t = false, help_heading = "Build options")]
         dedup_batches: bool,
 
         // Resources
-	// // Threads
+        // // Threads
         #[arg(short = 't', long = "threads", default_value_t = 1)]
         num_threads: usize,
-	// // Memory in GB
+        // // Memory in GB
         #[arg(short = 'm', long = "mem-gb", default_value_t = 4, help_heading = "Build options")]
         mem_gb: usize,
-	// // Temporary directory
+        // // Temporary directory
         #[arg(long = "temp-dir", required = false, help_heading = "Build options")]
         temp_dir: Option<String>,
 
-	// Verbosity
+        // Verbosity
         #[arg(long = "verbose", default_value_t = false)]
         verbose: bool,
     },
 
     // Find indexed k-mers in a query
     Find {
-	// Input fasta or fastq query file(s)
+        // Input fasta or fastq query file(s)
         #[arg(group = "input", required = true)]
         query_files: Vec<String>,
 
-	// Reference
-	// // Sequence file
+        // Reference
+        // // Sequence file
         #[arg(short = 'r', long = "reference", group = "reference", help_heading = "Input")]
         ref_file: Option<String>,
-	// // ... or a prebuilt index
+        // // ... or a prebuilt index
         #[arg(short = 'i', long = "index", group = "reference", help_heading = "Input")]
         index_prefix: Option<String>,
 
-	// Resources
-	// // Threads
+        // Parameters
+        // // Upper bound for random match probability
+        #[arg(long = "max-error-prob", default_value_t = 0.0000001, help_heading = "Algorithm")]
+        max_error_prob: f64,
+
+        // Resources
+        // // Threads
         #[arg(short = 't', long = "threads", default_value_t = 1)]
         num_threads: usize,
 
-	// Build parameters
-	// // k-mer size
+        // Build parameters
+        // // k-mer size
         #[arg(short = 'k', default_value_t = 31, help_heading = "Build options")]
         kmer_size: usize,
-	// // prefix precalc
-	#[arg(short = 'p', long = "prefix-precalc", default_value_t = 8, help_heading = "Build options")]
+        // // prefix precalc
+        #[arg(short = 'p', long = "prefix-precalc", default_value_t = 8, help_heading = "Build options")]
         prefix_precalc: usize,
-	// // deduplicate k-mer batches
-	#[arg(short = 'd', long = "dedup-batches", default_value_t = false, help_heading = "Build options")]
+        // // deduplicate k-mer batches
+        #[arg(short = 'd', long = "dedup-batches", default_value_t = false, help_heading = "Build options")]
         dedup_batches: bool,
-	// // Memory in GB
+        // // Memory in GB
         #[arg(short = 'm', long = "mem-gb", default_value_t = 4, help_heading = "Build options")]
         mem_gb: usize,
-	// // Temporary directory
+        // // Temporary directory
         #[arg(long = "temp-dir", required = false, help_heading = "Build options")]
         temp_dir: Option<String>,
 
 
-	// Verbosity
+        // Verbosity
         #[arg(long = "verbose", default_value_t = false)]
         verbose: bool,
     },
 
     // Map a query or queries to a reference and return the alignment
     Map {
-	// Input fasta or fastq query file(s)
+        // Input fasta or fastq query file(s)
         #[arg(group = "input", required = true)]
         query_files: Vec<String>,
 
-	// Reference fasta
+        // Reference fasta
         #[arg(short = 'r', long = "reference", required = true, help_heading = "Input")]
         ref_file: String,
 
-	// Resources
-	// // Threads
+        // Parameters
+        // // Upper bound for random match probability
+        #[arg(long = "max-error-prob", default_value_t = 0.0000001, help_heading = "Algorithm")]
+        max_error_prob: f64,
+
+        // Resources
+        // // Threads
         #[arg(short = 't', long = "threads", default_value_t = 1)]
         num_threads: usize,
 
-	// Build parameters
-	// // k-mer size
+        // Build parameters
+        // // k-mer size
         #[arg(short = 'k', default_value_t = 31, help_heading = "Build options")]
         kmer_size: usize,
-	// // prefix precalc
-	#[arg(short = 'p', long = "prefix-precalc", default_value_t = 8, help_heading = "Build options")]
+        // // prefix precalc
+        #[arg(short = 'p', long = "prefix-precalc", default_value_t = 8, help_heading = "Build options")]
         prefix_precalc: usize,
-	// // deduplicate k-mer batches
-	#[arg(short = 'd', long = "dedup-batches", default_value_t = false, help_heading = "Build options")]
+        // // deduplicate k-mer batches
+        #[arg(short = 'd', long = "dedup-batches", default_value_t = false, help_heading = "Build options")]
         dedup_batches: bool,
-	// // Memory in GB
+        // // Memory in GB
         #[arg(short = 'm', long = "mem-gb", default_value_t = 4, help_heading = "Build options")]
         mem_gb: usize,
-	// // Temporary directory
+        // // Temporary directory
         #[arg(long = "temp-dir", required = false, help_heading = "Build options")]
         temp_dir: Option<String>,
 
-	// Verbosity
+        // Verbosity
         #[arg(long = "verbose", default_value_t = false)]
         verbose: bool,
     },