refactor: replace single spectrum file with per-partition outputs

Replace the single `kmer_spectrum_raw.json` output with per-partition JSON files in a `spectrums/` directory. Add a `keep_intermediate` parameter to control intermediate file cleanup, and introduce a `write_spectrum` helper for serialization. Update the completion sentinel to `count.done` and align state documentation accordingly.

src/obikindex/src/index.rs

@@ -1,17 +1,18 @@
+use std::collections::BTreeMap;
 use std::fs;
 use std::path::{Path, PathBuf};
 use std::sync::atomic::{AtomicUsize, Ordering};
 use std::sync::{Arc, Mutex};
 
 use indicatif::{ProgressBar, ProgressStyle};
-use obikpartitionner::KmerPartition;
+use obikpartitionner::{KmerPartition, KmerSpectrum};
 use obisys::{Reporter, Stage};
 use rayon::prelude::*;
 use tracing::info;
 
 use crate::error::{OKIError, OKIResult};
 use crate::meta::{IndexConfig, IndexMeta};
-use crate::state::{IndexState, SENTINEL_INDEXED, SENTINEL_SCATTERED};
+use crate::state::{IndexState, SENTINEL_COUNTED, SENTINEL_INDEXED, SENTINEL_SCATTERED};
 
 pub struct KmerIndex {
     root_path: PathBuf,
@@ -96,16 +97,37 @@ impl KmerIndex {
 
     /// Dereplicate all partitions then compute kmer counts.
     ///
-    /// Writes `kmer_spectrum_raw.json` at the index root upon completion
-    /// (this file doubles as the `Counted` sentinel).
-    pub fn dereplicate_and_count(&self, rep: &mut Reporter) -> OKIResult<()> {
+    /// Writes `spectrums/{label}.json` and touches `count.done` upon completion.
+    /// Per-partition spectrum files are removed unless `keep_intermediate` is true.
+    pub fn dereplicate_and_count(&self, keep_intermediate: bool, rep: &mut Reporter) -> OKIResult<()> {
         let t = Stage::start("dereplicate");
         self.partition.dereplicate()?;
         rep.push(t.stop());
 
         let t = Stage::start("count_kmer");
-        self.partition.count_kmer()?;
+        let spectrum = self.partition.count_kmer(keep_intermediate)?;
         rep.push(t.stop());
+
+        self.write_spectrum(&spectrum)?;
+        touch(&self.root_path.join(SENTINEL_COUNTED))?;
+        Ok(())
+    }
+
+    fn write_spectrum(&self, sp: &KmerSpectrum) -> OKIResult<()> {
+        let label = self.meta.genomes.first().map(String::as_str).unwrap_or("unknown");
+        let spectrums_dir = self.root_path.join("spectrums");
+        fs::create_dir_all(&spectrums_dir)?;
+        let path = spectrums_dir.join(format!("{label}.json"));
+        let spectrum_map: BTreeMap<String, u64> = sp.counts
+            .iter()
+            .map(|(&c, &f)| (format!("{c:010}"), f))
+            .collect();
+        let f = fs::File::create(&path)?;
+        serde_json::to_writer_pretty(
+            f,
+            &serde_json::json!({ "f0": sp.f0, "f1": sp.f1, "spectrum": spectrum_map }),
+        )
+        .map_err(OKIError::Json)?;
         Ok(())
     }
 

src/obikindex/src/state.rs

@@ -3,7 +3,7 @@ use std::path::Path;
 use crate::meta::META_FILENAME;
 
 pub const SENTINEL_SCATTERED: &str = "scatter.done";
-pub const SENTINEL_COUNTED:   &str = "kmer_spectrum_raw.json";
+pub const SENTINEL_COUNTED:   &str = "count.done";
 pub const SENTINEL_INDEXED:   &str = "index.done";
 
 /// Progression state of a `KmerIndex`.
@@ -17,7 +17,7 @@ pub enum IndexState {
     Empty,
     /// `scatter.done` sentinel present — all super-kmers have been routed.
     Scattered,
-    /// `kmer_spectrum_raw.json` present — dereplicate + count complete.
+    /// `count.done` sentinel present — dereplicate + count complete.
     Counted,
     /// `index.done` sentinel present — layered MPHF index fully built.
     Indexed,