Dev

.github/workflows/build_and_test.yml

@@ -21,10 +21,14 @@ jobs:
     steps:
     - uses: actions/checkout@v4
 
-    - name: Setup
+    - name: Setup toolchain
       run: rustup update ${{ matrix.toolchain }} && rustup default ${{ matrix.toolchain }}
-    - name: Build
+
+    - name: Build binary
       run: cargo build --verbose
 
-    - name: Run tests
-      run: cargo test --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

Cargo.toml

@@ -2,6 +2,7 @@
 name = "sablast"
 version = "0.1.0"
 edition = "2021"
+rust-version = "1.77.0"
 authors = ["Tommi Mäklin <[email protected]>"]
 description = "Spectral Burrows-Wheeler transform accelerated local alignment search"
 readme = "README.md"
@@ -13,16 +14,19 @@ license = "MIT OR Apache-2.0"
 
 [dependencies]
 ## core
-needletail = "0.5.1"
+# 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 = "4.4.18", features = ["derive"] }
+clap = { version = "4", features = ["derive"] }
 
 ## logging
 log = "0.4.20"
 stderrlog = "0.6.0"
 
 [dev-dependencies]
 ## tests
-assert_approx_eq = "1.1.0"
+assert_approx_eq = "1"

src/cli.rs

@@ -29,43 +29,61 @@ pub enum Commands {
         #[arg(group = "input", required = true)]
         seq_files: Vec<String>,
 
-	// Input sequence list
-        #[arg(short = 'l', long = "input-list", group = "input", required = true, help_heading = "Input")]
-        input_list: Option<String>,
-
 	// Outputs
         #[arg(short = 'o', long = "out-prefix", required = false, help_heading = "Output")]
         output_prefix: Option<String>,
 
         // 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 = "memory", default_value_t = 4)]
         mem_gb: usize,
-	// Temporary directory
+	// // Temporary directory
         #[arg(long = "tmp-dir", required = false)]
         temp_dir: Option<String>,
 
+	// Verbosity
         #[arg(long = "verbose", default_value_t = false)]
         verbose: bool,
     },
 
-    // Map query against SBWT index
-    Map {
+    // Find indexed k-mers in a query
+    Find {
 	// Input fasta or fastq query file(s)
         #[arg(group = "input", required = true)]
         seq_files: Vec<String>,
 
-	// Input sequence list
-        #[arg(short = 'l', long = "input-list", group = "input", required = true, help_heading = "Input")]
-        input_list: Option<String>,
-
 	// Index name
         #[arg(short = 'i', long = "index", required = true, help_heading = "Index")]
         index_prefix: Option<String>,
 
+	// Resources
+	// // Threads
+        #[arg(short = 't', long = "threads", default_value_t = 1)]
+        num_threads: usize,
+
+	// 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)
+        #[arg(group = "input", required = true)]
+        query_file: String,
+
+	// Reference fasta
+        #[arg(short = 'r', long = "reference", required = true, help_heading = "Input")]
+        ref_file: String,
+
+	// Resources
+	// // Threads
+        #[arg(short = 't', long = "threads", default_value_t = 1)]
+        num_threads: usize,
+
 	// Verbosity
         #[arg(long = "verbose", default_value_t = false)]
         verbose: bool,