alpha-id/tests/packed_load_tests.rs

use alpha_id::model::{AlphaIdEntry, Config, IndexStatus};
use alpha_id::packed::{packed_path, write_packed, PackedHeader};
use alpha_id::packed::corpus_sha256;
use alpha_id::pipeline::load_packed_or_store;

fn entry(text: &str) -> AlphaIdEntry {
    AlphaIdEntry {
        alpha_id: "X".to_string(),
        valid: true,
        icd_primary: "A00".to_string(),
        icd_star: String::new(),
        icd_addon: String::new(),
        icd_primary2: String::new(),
        orpha: String::new(),
        text: text.to_string(),
    }
}

fn cfg_in(dir: &std::path::Path) -> Config {
    let mut cfg = Config::load("config/default.toml").unwrap();
    cfg.index_dir = dir.to_str().unwrap().to_string();
    cfg.embed_model = "test/model".to_string();
    cfg
}

#[test]
fn index_status_defaults_to_absent() {
    assert_eq!(IndexStatus::default(), IndexStatus::Absent);
}

#[test]
fn index_status_serializes_externally_tagged() {
    let j = serde_json::to_string(&IndexStatus::Mismatch("x".to_string())).unwrap();
    assert!(j.contains("Mismatch"), "got {j}");
}

#[test]
fn packed_beats_store_builds_without_store() {
    let dir = tempfile::tempdir().unwrap();
    let mut cfg = cfg_in(dir.path());
    // Hermetic corpus so the header's corpus_sha256 can match the live config
    // under iteration-2 semantic enforcement.
    let corpus = dir.path().join("corpus.txt");
    std::fs::write(&corpus, b"some corpus bytes").unwrap();
    cfg.alpha_id_path = corpus.to_str().unwrap().to_string();
    let entries = vec![entry("a"), entry("b")];
    let rows = vec![vec![1.0f32, 0.0], vec![0.0f32, 1.0]];
    let h = PackedHeader {
        n_rows: 2,
        dim: 2,
        embed_model: cfg.embed_model.clone(),
        corpus_sha256: corpus_sha256(&cfg.alpha_id_path).unwrap(),
        corpus_name: "c.txt".to_string(),
    };
    write_packed(&packed_path(&cfg.index_dir, &cfg.embed_model), &h, &rows).unwrap();
    // No per-file store populated in `dir`; the index must come from the packed file.
    let (vector, status) = load_packed_or_store(&cfg, &entries);
    assert!(vector.is_some());
    assert_eq!(status, IndexStatus::Ok);
}

#[test]
fn n_rows_mismatch_yields_mismatch_none() {
    let dir = tempfile::tempdir().unwrap();
    let cfg = cfg_in(dir.path());
    let entries = vec![entry("a"), entry("b"), entry("c")]; // 3 entries
    let rows = vec![vec![1.0f32, 0.0], vec![0.0f32, 1.0]]; // packed claims 2 rows
    let h = PackedHeader {
        n_rows: 2,
        dim: 2,
        embed_model: cfg.embed_model.clone(),
        corpus_sha256: "x".to_string(),
        corpus_name: "c.txt".to_string(),
    };
    write_packed(&packed_path(&cfg.index_dir, &cfg.embed_model), &h, &rows).unwrap();
    let (vector, status) = load_packed_or_store(&cfg, &entries);
    assert!(vector.is_none());
    assert!(matches!(status, IndexStatus::Mismatch(_)));
}

fn header_for(cfg: &Config, n_rows: u32, model: &str, corpus_hash: &str) -> PackedHeader {
    let _ = cfg;
    PackedHeader {
        n_rows,
        dim: 2,
        embed_model: model.to_string(),
        corpus_sha256: corpus_hash.to_string(),
        corpus_name: "c.txt".to_string(),
    }
}

#[test]
fn index_status_display_renders_spec_tokens() {
    assert_eq!(format!("{}", IndexStatus::Ok), "ok");
    assert_eq!(format!("{}", IndexStatus::Absent), "absent");
    assert_eq!(
        format!("{}", IndexStatus::Mismatch("corpus sha256".to_string())),
        "mismatch: corpus sha256"
    );
}

#[test]
fn model_mismatch_yields_mismatch_none() {
    let dir = tempfile::tempdir().unwrap();
    let cfg = cfg_in(dir.path()); // cfg.embed_model == "test/model"
    let entries = vec![entry("a"), entry("b")];
    let rows = vec![vec![1.0f32, 0.0], vec![0.0f32, 1.0]];
    // n_rows matches (2) so the structural check passes; the header declares a
    // different model, so the semantic check must reject it.
    let h = header_for(&cfg, 2, "other/model", "irrelevant");
    write_packed(&packed_path(&cfg.index_dir, &cfg.embed_model), &h, &rows).unwrap();
    let (vector, status) = load_packed_or_store(&cfg, &entries);
    assert!(vector.is_none());
    assert!(matches!(status, IndexStatus::Mismatch(_)));
}

#[test]
fn corpus_hash_mismatch_yields_mismatch_none() {
    let dir = tempfile::tempdir().unwrap();
    let mut cfg = cfg_in(dir.path());
    // Point the corpus at a tiny temp file so the hash is hermetic.
    let corpus = dir.path().join("corpus.txt");
    std::fs::write(&corpus, b"some corpus bytes").unwrap();
    cfg.alpha_id_path = corpus.to_str().unwrap().to_string();
    let entries = vec![entry("a"), entry("b")];
    let rows = vec![vec![1.0f32, 0.0], vec![0.0f32, 1.0]];
    // Model matches, but the header's corpus hash does not match the file's.
    let h = header_for(&cfg, 2, &cfg.embed_model, "deadbeef-not-the-real-hash");
    write_packed(&packed_path(&cfg.index_dir, &cfg.embed_model), &h, &rows).unwrap();
    let (vector, status) = load_packed_or_store(&cfg, &entries);
    assert!(vector.is_none());
    assert!(matches!(status, IndexStatus::Mismatch(_)));
}

#[test]
fn matching_model_and_corpus_yields_ok() {
    let dir = tempfile::tempdir().unwrap();
    let mut cfg = cfg_in(dir.path());
    let corpus = dir.path().join("corpus.txt");
    std::fs::write(&corpus, b"some corpus bytes").unwrap();
    cfg.alpha_id_path = corpus.to_str().unwrap().to_string();
    let entries = vec![entry("a"), entry("b")];
    let rows = vec![vec![1.0f32, 0.0], vec![0.0f32, 1.0]];
    let real_hash = corpus_sha256(&cfg.alpha_id_path).unwrap();
    let h = header_for(&cfg, 2, &cfg.embed_model, &real_hash);
    write_packed(&packed_path(&cfg.index_dir, &cfg.embed_model), &h, &rows).unwrap();
    let (vector, status) = load_packed_or_store(&cfg, &entries);
    assert!(vector.is_some());
    assert_eq!(status, IndexStatus::Ok);
}