📦 Add obipipeline crate and refactor path handling

- Introduce new `obipackage` library with pipeline stages, scheduler and worker pool
- Refactor path expansion in `obiread`: replace old list_of_files with new PathIter iterator
- Add MIME type detection using `infer` crate (fastq/fasta)
- Update dependencies in Cargo.lock: add bumpalo, byteorder, cfb (with deps), fnv,
  infer, js-sys/uuid/wasm-bindgen ecosystem
- Fix formatting and improve tests in SuperKmer (canonical, revcomp)
  * Note: edition = "2024" in obipipeline/Cargo.toml is invalid; should be 2021

src/obiread/Cargo.toml

@@ -7,3 +7,5 @@ edition = "2024"
 obikrope = { path = "../obikrope" }
 niffler = { version = "2", default-features = false, features = ["gz", "bz2", "lzma", "zstd"] }
 ureq   = "2"
+tracing = "0.1.44"
+tracing-subscriber = { version = "0.3.23", features = ["fmt", "env-filter"] }

src/obiread/examples/expand_path.rs

@@ -0,0 +1,20 @@
+use obiread::expand_paths;
+use tracing::{info, subscriber};
+use tracing_subscriber::{EnvFilter, fmt};
+
+fn main() {
+    // Build a subscriber with environment-based filtering
+    tracing_subscriber::fmt()
+        .with_env_filter(tracing_subscriber::EnvFilter::from_default_env())
+        .init();
+
+    info!("Expanding paths...");
+    let paths = vec![
+        "/home/user/data".to_string(),
+        "/home/user/sample.fastq.gz".to_string(),
+    ];
+    let files = expand_paths(&paths);
+    for f in files {
+        println!("{}", f.display());
+    }
+}

src/obiread/src/lib.rs

@@ -5,12 +5,15 @@
 
 #![deny(missing_docs)]
 
+pub mod chunk;
 mod fasta;
 mod fastq;
-pub mod chunk;
+mod list_of_files;
 pub mod normalize;
 pub mod xopen;
 
+pub use list_of_files::expand_paths;
+
 use std::io::Read;
 
 use chunk::SeqChunkIter;

src/obiread/src/list_of_files.rs

@@ -0,0 +1,47 @@
+use std::fs;
+use std::path::Path;
+use std::path::PathBuf;
+use tracing::info;
+
+/// Returns true if the path ends with a fasta or fastq file extension.
+fn is_fasta_or_fastq(path: &Path) -> bool {
+    let name = path.file_name().and_then(|n| n.to_str()).unwrap_or("");
+    name.ends_with(".fasta")
+        || name.ends_with(".fa")
+        || name.ends_with(".fastq")
+        || name.ends_with(".fq")
+        || name.ends_with(".fasta.gz")
+        || name.ends_with(".fa.gz")
+        || name.ends_with(".fastq.gz")
+        || name.ends_with(".fq.gz")
+}
+
+/// Walks a directory, collecting fasta or fastq files into the output vector.
+fn walk_dir(dir: &Path, out: &mut Vec<PathBuf>) {
+    if let Ok(entries) = fs::read_dir(dir) {
+        for entry in entries.flatten() {
+            let path = entry.path();
+            if path.is_dir() {
+                walk_dir(&path, out);
+            } else if path.is_file() && is_fasta_or_fastq(&path) {
+                out.push(path);
+            }
+        }
+    }
+}
+
+/// Expands a list of paths, returning a vector of `PathBuf` for fasta or fastq files.
+pub fn expand_paths(paths: &[String]) -> Vec<PathBuf> {
+    let mut result = Vec::new();
+    for path_str in paths {
+        info!("Current step: {}", path_str);
+        let path = Path::new(path_str);
+        if path.is_dir() {
+            walk_dir(path, &mut result);
+        } else if path.is_file() && is_fasta_or_fastq(path) {
+            info!("Found fasta or fastq file: {}", path_str);
+            result.push(path.to_path_buf());
+        }
+    }
+    result
+}