refactor: extract pipeline stages and centralize partition directory paths

Extracts the scatter, dereplicate/count, and index pipeline stages into a new `steps` module to improve modularity. Centralizes partition directory path construction by introducing a `part_dir()` helper, replacing manual string formatting across multiple command files. Adds `--with-counts` and `--keep-intermediate` CLI flags to the index command and fixes a typo in the `partition_dir` parameter name.

src/obikpartitionner/src/lib.rs

@@ -1,4 +1,4 @@
 mod kmer_sort;
 mod partition;
 
-pub use partition::KmerPartition;
+pub use partition::{KmerPartition, PARTITIONS_SUBDIR};

src/obikpartitionner/src/partition.rs

@@ -30,6 +30,7 @@ type Mphf = PtrHash<u64, CubicEps, CachelineEfVec<Vec<CachelineEf>>, Xx64, Vec<u
 
 const META_FILENAME: &str = "partition.meta";
 const SK_EXT: &str = "skmer.zst";
+pub const PARTITIONS_SUBDIR: &str = "partitions";
 
 #[derive(Serialize, Deserialize)]
 struct PartitionMeta {
@@ -84,7 +85,7 @@ impl KmerPartition {
                 .into());
             }
         }
-        fs::create_dir_all(&root_path)?;
+        fs::create_dir_all(root_path.join(PARTITIONS_SUBDIR))?;
         let n_partitions = 1usize << n_bits;
         let writers = (0..n_partitions).map(|_| None).collect();
         let partition = Self {
@@ -175,6 +176,11 @@ impl KmerPartition {
         &self.root_path
     }
 
+    /// Path of partition `i` directory.
+    pub fn part_dir(&self, i: usize) -> PathBuf {
+        self.root_path.join(PARTITIONS_SUBDIR).join(format!("part_{i:05}"))
+    }
+
     pub fn kmer_size(&self) -> usize {
         self.kmer_size
     }
@@ -208,7 +214,6 @@ impl KmerPartition {
     /// more temporary file descriptors — all managed by the global fd pool.
     pub fn dereplicate(&self) -> SKResult<()> {
         let level = self.level;
-        let root = &self.root_path;
         let sys = System::new_all();
         // available_memory() can return 0 on macOS when the compressor page count exceeds
         // free+inactive+purgeable pages (sysinfo saturating_sub). Fall back to half of total.
@@ -222,7 +227,7 @@ impl KmerPartition {
         let results: Vec<SKResult<()>> = (0..self.n_partitions)
             .into_par_iter()
             .map(|i| {
-                let dir = root.join(format!("part_{:05}", i));
+                let dir = self.part_dir(i);
                 if !dir.exists() {
                     return Ok(());
                 }
@@ -249,8 +254,6 @@ impl KmerPartition {
     /// Partitions are processed in parallel via Rayon (one task per thread).
     /// Peak memory per partition is ~80 MB, so n_threads partitions run simultaneously.
     pub fn count_kmer(&self) -> SKResult<()> {
-        let root = &self.root_path;
-
         let sys = System::new_all();
         let available = match sys.available_memory() {
             0 => sys.total_memory() / 2,
@@ -271,7 +274,7 @@ impl KmerPartition {
         let results: Vec<SKResult<()>> = (0..self.n_partitions)
             .into_par_iter()
             .map(|i| {
-                let dir = root.join(format!("part_{:05}", i));
+                let dir = self.part_dir(i);
                 let dedup_path = dir.join(format!("dereplicated.{SK_EXT}"));
                 if !dedup_path.exists() {
                     pb.inc(1);
@@ -296,9 +299,7 @@ impl KmerPartition {
         let mut global_f1: u64 = 0;
 
         for i in 0..self.n_partitions {
-            let path = root
-                .join(format!("part_{:05}", i))
-                .join("kmer_spectrum_raw.json");
+            let path = self.part_dir(i).join("kmer_spectrum_raw.json");
             if !path.exists() {
                 continue;
             }
@@ -320,7 +321,7 @@ impl KmerPartition {
             .map(|(&c, &f)| (format!("{c:010}"), f))
             .collect();
         serde_json::to_writer_pretty(
-            fs::File::create(root.join("kmer_spectrum_raw.json"))?,
+            fs::File::create(self.root_path.join("kmer_spectrum_raw.json"))?,
             &serde_json::json!({ "f0": global_f0, "f1": global_f1, "spectrum": &global_spectrum_map }),
         )
         .map_err(io::Error::other)?;
@@ -352,7 +353,7 @@ impl KmerPartition {
 
     fn ensure_writer(&mut self, partition: usize) -> SKResult<&mut SKFileWriter> {
         if self.writers[partition].is_none() {
-            let dir = self.root_path.join(format!("part_{:05}", partition));
+            let dir = self.root_path.join(PARTITIONS_SUBDIR).join(format!("part_{:05}", partition));
             fs::create_dir_all(&dir)?;
             let file_path = dir.join(format!("raw.{SK_EXT}"));
             let writer = SKFileWriter::create_with(file_path, Format::Zstd, self.level)?;
@@ -645,7 +646,7 @@ mod tests {
         kp.close().unwrap();
         kp.dereplicate().unwrap();
 
-        let part_dir = dir.path().join("part_00000");
+        let part_dir = dir.path().join(PARTITIONS_SUBDIR).join("part_00000");
         let dedup_path = part_dir.join("dereplicated.skmer.zst");
         if !dedup_path.exists() {
             return (0, 0);