update dist, update deps, reorganize help menu, add defaults

.github/workflows/release.yml

@@ -62,7 +62,7 @@ jobs:
         # we specify bash to get pipefail; it guards against the `curl` command
         # failing. otherwise `sh` won't catch that `curl` returned non-0
         shell: bash
-        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.9.0/cargo-dist-installer.sh | sh"
+        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.10.0/cargo-dist-installer.sh | sh"
       # sure would be cool if github gave us proper conditionals...
       # so here's a doubly-nested ternary-via-truthiness to try to provide the best possible
       # functionality based on whether this is a pull_request, and whether it's from a fork.
@@ -161,7 +161,7 @@ jobs:
         with:
           submodules: recursive
       - name: Install cargo-dist
-        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.9.0/cargo-dist-installer.sh | sh"
+        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.10.0/cargo-dist-installer.sh | sh"
       # Get all the local artifacts for the global tasks to use (for e.g. checksums)
       - name: Fetch local artifacts
         uses: actions/download-artifact@v4
@@ -206,7 +206,7 @@ jobs:
         with:
           submodules: recursive
       - name: Install cargo-dist
-        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.9.0/cargo-dist-installer.sh | sh"
+        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.10.0/cargo-dist-installer.sh | sh"
       # Fetch artifacts from scratch-storage
       - name: Fetch artifacts
         uses: actions/download-artifact@v4

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "piscem"
-version = "0.7.2"
+version = "0.7.3"
 edition = "2021"
 build = "build.rs"
 repository = "https://github.com/COMBINE-lab/piscem"
@@ -13,7 +13,7 @@ cmake = "0.1"
 [dependencies]
 num_cpus = "1.16.0"
 anyhow = "1.0"
-clap = { version = "4.4.18", features = ["cargo", "derive", "env", "wrap_help"] }
+clap = { version = "4.5.1", features = ["cargo", "derive", "env", "wrap_help"] }
 tracing = "0.1.40"
 tracing-subscriber = { version = "0.3.18", default-features = true, features = ["env-filter"] }
 prepare_fasta = "0.1.0"
@@ -29,7 +29,7 @@ inherits = "release"
 # Config for 'cargo dist'
 [workspace.metadata.dist]
 # The preferred cargo-dist version to use in CI (Cargo.toml SemVer syntax)
-cargo-dist-version = "0.9.0"
+cargo-dist-version = "0.10.0"
 # The installers to generate for each app
 installers = ["shell"]
 # Target platforms to build apps for (Rust target-triple syntax)

clean_build.sh

@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+
+echo "cleaning external dependency directories of cuttlefish and piscem-cpp."
+rm -fr ${SCRIPT_DIR}/cuttlefish/external/*
+rm -fr ${SCRIPT_DIR}/piscem-cpp/external/zlib-cloudflare
+
+echo "invoking cargo clean"
+cargo clean --target-dir ${SCRIPT_DIR}/target

src/main.rs

@@ -4,7 +4,6 @@ use std::io;
 use std::os::raw::{c_char, c_int};
 use std::path::PathBuf;
 
-use prepare_fasta;
 use anyhow::{bail, Result};
 use clap::{Parser, Subcommand};
 use tracing::{error, info, warn, Level};
@@ -175,12 +174,13 @@ fn main() -> Result<(), anyhow::Error> {
 
             if let Some(seqs) = ref_seqs {
                 if !seqs.is_empty() {
-                    let out_stem = PathBuf::from(output.as_path().to_string_lossy().into_owned() + ".sigs");
-                    let configs = prepare_fasta::RecordParseConfig{
-                            input: seqs.clone(),
-                            output_stem: out_stem,
-                            polya_clip_length: None
-                        };
+                    let out_stem =
+                        PathBuf::from(output.as_path().to_string_lossy().into_owned() + ".sigs");
+                    let configs = prepare_fasta::RecordParseConfig {
+                        input: seqs.clone(),
+                        output_stem: out_stem,
+                        polya_clip_length: None,
+                    };
                     info!("Computing and recording reference signatures...");
                     prepare_fasta::parse_records(configs)?;
                     info!("done.");

src/piscem_commands.rs

@@ -1,4 +1,4 @@
-use anyhow::{bail, Result};
+use anyhow::{anyhow, bail, Result};
 use clap::{ArgGroup, Args};
 use std::ffi::CString;
 use std::path::{Path, PathBuf};
@@ -30,6 +30,19 @@ pub trait AsArgv {
     fn as_argv(&self) -> Result<Vec<CString>>;
 }
 
+fn klen_is_good(s: &str) -> Result<usize> {
+    let k: usize = s
+        .parse()
+        .map_err(|_| anyhow!("`{s}` can't be parsed as a number"))?;
+    if k > 31 {
+        bail!("klen = {k} must be <= 31");
+    } else if (k & 1) == 0 {
+        bail!("klen = {k} must be odd");
+    } else {
+        Ok(k)
+    }
+}
+
 #[derive(Args, Clone, Debug)]
 #[command(arg_required_else_help = true)]
 #[command(group(
@@ -39,28 +52,33 @@ pub trait AsArgv {
 ))]
 pub(crate) struct BuildOpts {
     /// ',' separated list of reference FASTA files
-    #[arg(short = 's', long, value_delimiter = ',', required = true)]
+    #[arg(short = 's', long, help_heading = "Input", value_delimiter = ',')]
     pub ref_seqs: Option<Vec<String>>,
 
     /// ',' separated list of files (each listing input FASTA files)
-    #[arg(short = 'l', long, value_delimiter = ',', required = true)]
+    #[arg(short = 'l', long, help_heading = "Input", value_delimiter = ',')]
     pub ref_lists: Option<Vec<String>>,
 
     /// ',' separated list of directories (all FASTA files in each directory will be indexed,
     /// but not recursively).
-    #[arg(short = 'd', long, value_delimiter = ',', required = true)]
+    #[arg(short = 'd', long, help_heading = "Input", value_delimiter = ',')]
     pub ref_dirs: Option<Vec<String>>,
 
-    /// length of k-mer to use
-    #[arg(short, long)]
+    /// length of k-mer to use, must be <= 31 and odd
+    #[arg(short, long, help_heading = "Index Construction Parameters", default_value_t = 31, value_parser = klen_is_good)]
     pub klen: usize,
 
-    /// length of minimizer to use
-    #[arg(short, long)]
+    /// length of minimizer to use; must be < `klen`
+    #[arg(
+        short,
+        long,
+        help_heading = "Index Construction Parameters",
+        default_value_t = 19
+    )]
     pub mlen: usize,
 
     /// number of threads to use
-    #[arg(short, long)]
+    #[arg(short, long, help_heading = "Index Construction Parameters")]
     pub threads: usize,
 
     /// output file stem
@@ -69,50 +87,65 @@ pub(crate) struct BuildOpts {
 
     /// retain the reduced format GFA files produced by cuttlefish that
     /// describe the reference cDBG (the default is to remove these).
-    #[arg(long)]
+    #[arg(long, help_heading = "Indexing Details")]
     pub keep_intermediate_dbg: bool,
 
     /// working directory where temporary files should be placed.
-    #[arg(short = 'w', long, default_value_os_t = PathBuf::from("."))]
+    #[arg(short = 'w', long, help_heading = "Indexing Details", default_value_os_t = PathBuf::from("./workdir.noindex"))]
     pub work_dir: PathBuf,
 
     /// overwite an existing index if the output path is the same.
-    #[arg(long)]
+    #[arg(long, help_heading = "Indexing Details")]
     pub overwrite: bool,
 
     /// skip the construction of the equivalence class lookup table
     /// when building the index (not recommended).
-    #[arg(long)]
+    #[arg(long, help_heading = "Index Construction Parameters")]
     pub no_ec_table: bool,
 
     /// path to (optional) ',' sparated list of decoy sequences used to insert poison
     /// k-mer information into the index.
     #[arg(long, value_delimiter = ',')]
     pub decoy_paths: Option<Vec<PathBuf>>,
 
-
     /// index construction seed (seed value passed to SSHash index construction; useful if empty
     /// buckets occur).
-    #[arg(long = "seed", default_value_t = 1)]
+    #[arg(
+        long = "seed",
+        help_heading = "Index Construction Parameters",
+        default_value_t = 1
+    )]
     pub seed: u64,
 }
 
 #[derive(Args, Clone, Debug)]
 pub(crate) struct MapSCOpts {
     /// input index prefix
-    #[arg(short, long)]
+    #[arg(short, long, help_heading = "Input")]
     pub index: String,
 
     /// geometry of barcode, umi and read
     #[arg(short, long)]
     pub geometry: String,
 
     /// path to list of read 1 files
-    #[arg(short = '1', long, value_delimiter = ',', required = true)]
+    #[arg(
+        short = '1',
+        long,
+        help_heading = "Input",
+        value_delimiter = ',',
+        required = true
+    )]
     pub read1: Vec<String>,
 
     /// path to list of read 2 files
-    #[arg(short = '2', long, value_delimiter = ',', required = true)]
+    #[arg(
+        short = '2',
+        long,
+        help_heading = "Input",
+        value_delimiter = ',',
+        required = true
+    )]
     pub read2: Vec<String>,
 
     /// number of threads to use
@@ -178,19 +211,31 @@ pub(crate) struct MapSCOpts {
 ))]
 pub(crate) struct MapBulkOpts {
     /// input index prefix
-    #[arg(short, long)]
+    #[arg(short, long, help_heading = "Input")]
     pub index: String,
 
     /// path to list of read 1 files
-    #[arg(short = '1', long, value_delimiter = ',', requires = "read2")]
+    #[arg(
+        short = '1',
+        long,
+        help_heading = "Input",
+        value_delimiter = ',',
+        requires = "read2"
+    )]
     pub read1: Option<Vec<String>>,
 
     /// path to list of read 2 files
-    #[arg(short = '2', long, value_delimiter = ',', requires = "read1")]
+    #[arg(
+        short = '2',
+        long,
+        help_heading = "Input",
+        value_delimiter = ',',
+        requires = "read1"
+    )]
     pub read2: Option<Vec<String>>,
 
     /// path to list of read unpaired read files
-    #[arg(short = 'r', long, value_delimiter = ',', conflicts_with_all = ["read1", "read2"])]
+    #[arg(short = 'r', long, help_heading = "Input", value_delimiter = ',', conflicts_with_all = ["read1", "read2"])]
     pub reads: Option<Vec<String>>,
 
     /// number of threads to use