gitlore/src/ingestion/surgical_tests.rs

use std::path::Path;

use super::*;
use crate::core::config::{
    Config, EmbeddingConfig, GitLabConfig, LoggingConfig, ProjectConfig, ScoringConfig,
    StorageConfig, SyncConfig,
};
use crate::core::db::{create_connection, run_migrations};
use crate::gitlab::types::{GitLabAuthor, GitLabMergeRequest};

// ---------------------------------------------------------------------------
// Test helpers
// ---------------------------------------------------------------------------

fn setup_db() -> rusqlite::Connection {
    let conn = create_connection(Path::new(":memory:")).expect("in-memory DB");
    run_migrations(&conn).expect("migrations");
    conn.execute(
        "INSERT INTO projects (gitlab_project_id, path_with_namespace, web_url)
         VALUES (100, 'group/repo', 'https://example.com/group/repo')",
        [],
    )
    .expect("insert project");
    conn
}

fn test_config() -> Config {
    Config {
        gitlab: GitLabConfig {
            base_url: "https://gitlab.example.com".to_string(),
            token_env_var: "GITLAB_TOKEN".to_string(),
            token: None,
            username: None,
        },
        projects: vec![ProjectConfig {
            path: "group/repo".to_string(),
        }],
        default_project: None,
        sync: SyncConfig::default(),
        storage: StorageConfig::default(),
        embedding: EmbeddingConfig::default(),
        logging: LoggingConfig::default(),
        scoring: ScoringConfig::default(),
    }
}

fn make_test_issue(iid: i64, updated_at: &str) -> GitLabIssue {
    GitLabIssue {
        id: iid * 1000, // unique gitlab_id
        iid,
        project_id: 100,
        title: format!("Test issue {iid}"),
        description: Some("Description".to_string()),
        state: "opened".to_string(),
        created_at: "2026-01-01T00:00:00.000+00:00".to_string(),
        updated_at: updated_at.to_string(),
        closed_at: None,
        author: GitLabAuthor {
            id: 1,
            username: "testuser".to_string(),
            name: "Test User".to_string(),
        },
        assignees: vec![],
        labels: vec![],
        milestone: None,
        due_date: None,
        web_url: format!("https://example.com/group/repo/-/issues/{iid}"),
    }
}

fn make_test_mr(iid: i64, updated_at: &str) -> GitLabMergeRequest {
    GitLabMergeRequest {
        id: iid * 1000,
        iid,
        project_id: 100,
        title: format!("Test MR {iid}"),
        description: Some("MR description".to_string()),
        state: "opened".to_string(),
        draft: false,
        work_in_progress: false,
        source_branch: "feature".to_string(),
        target_branch: "main".to_string(),
        sha: Some("abc123".to_string()),
        references: None,
        detailed_merge_status: None,
        merge_status_legacy: None,
        created_at: "2026-01-01T00:00:00.000+00:00".to_string(),
        updated_at: updated_at.to_string(),
        merged_at: None,
        closed_at: None,
        author: GitLabAuthor {
            id: 1,
            username: "testuser".to_string(),
            name: "Test User".to_string(),
        },
        merge_user: None,
        merged_by: None,
        labels: vec![],
        assignees: vec![],
        reviewers: vec![],
        web_url: format!("https://example.com/group/repo/-/merge_requests/{iid}"),
        merge_commit_sha: None,
        squash_commit_sha: None,
    }
}

fn get_db_updated_at_helper(conn: &rusqlite::Connection, table: &str, iid: i64) -> Option<i64> {
    let sql = match table {
        "issues" => "SELECT updated_at FROM issues WHERE project_id = 1 AND iid = ?1",
        "merge_requests" => {
            "SELECT updated_at FROM merge_requests WHERE project_id = 1 AND iid = ?1"
        }
        _ => return None,
    };
    conn.query_row(sql, [iid], |row| row.get(0)).ok()
}

fn get_dirty_keys(conn: &rusqlite::Connection) -> Vec<(String, i64)> {
    let mut stmt = conn
        .prepare("SELECT source_type, source_id FROM dirty_sources ORDER BY source_type, source_id")
        .expect("prepare dirty_sources query");
    stmt.query_map([], |row| {
        let st: String = row.get(0)?;
        let id: i64 = row.get(1)?;
        Ok((st, id))
    })
    .expect("query dirty_sources")
    .collect::<std::result::Result<Vec<_>, _>>()
    .expect("collect dirty_sources")
}

// ---------------------------------------------------------------------------
// is_stale unit tests
// ---------------------------------------------------------------------------

#[test]
fn test_is_stale_parses_iso8601() {
    // 2026-02-17T12:00:00.000+00:00 -> 1771243200000 ms
    let result = is_stale("2026-02-17T12:00:00.000+00:00", Some(1_771_329_600_000));
    assert!(result.is_ok());
    // Same timestamp => stale
    assert!(result.unwrap());
}

#[test]
fn test_is_stale_handles_none_db_value() {
    let result = is_stale("2026-02-17T12:00:00.000+00:00", None);
    assert!(result.is_ok());
    assert!(!result.unwrap(), "no DB row means not stale");
}

#[test]
fn test_is_stale_with_z_suffix() {
    let result = is_stale("2026-02-17T12:00:00Z", Some(1_771_329_600_000));
    assert!(result.is_ok());
    assert!(result.unwrap(), "Z suffix should parse same as +00:00");
}

// ---------------------------------------------------------------------------
// Issue ingestion tests
// ---------------------------------------------------------------------------

#[test]
fn test_ingest_issue_by_iid_upserts_and_marks_dirty() {
    let conn = setup_db();
    let config = test_config();
    let issue = make_test_issue(42, "2026-02-17T12:00:00.000+00:00");

    let result = ingest_issue_by_iid(&conn, &config, 1, &issue).unwrap();

    assert!(!result.skipped_stale);
    assert!(!result.dirty_source_keys.is_empty());

    // Verify DB row exists
    let db_ts = get_db_updated_at_helper(&conn, "issues", 42);
    assert!(db_ts.is_some(), "issue should exist in DB");

    // Verify dirty marking
    let dirty = get_dirty_keys(&conn);
    assert!(
        dirty.iter().any(|(t, _)| t == "issue"),
        "dirty_sources should contain an issue entry"
    );
}

#[test]
fn test_toctou_skips_stale_issue() {
    let conn = setup_db();
    let config = test_config();
    let issue = make_test_issue(42, "2026-02-17T12:00:00.000+00:00");

    // First ingest succeeds
    let r1 = ingest_issue_by_iid(&conn, &config, 1, &issue).unwrap();
    assert!(!r1.skipped_stale);

    // Clear dirty to check second ingest doesn't re-mark
    conn.execute("DELETE FROM dirty_sources", []).unwrap();

    // Second ingest with same timestamp should be skipped
    let r2 = ingest_issue_by_iid(&conn, &config, 1, &issue).unwrap();
    assert!(r2.skipped_stale);
    assert!(r2.dirty_source_keys.is_empty());

    // No new dirty mark
    let dirty = get_dirty_keys(&conn);
    assert!(dirty.is_empty(), "stale skip should not create dirty marks");
}

#[test]
fn test_toctou_allows_newer_issue() {
    let conn = setup_db();
    let config = test_config();

    // Ingest at T1
    let issue_t1 = make_test_issue(42, "2026-02-17T12:00:00.000+00:00");
    ingest_issue_by_iid(&conn, &config, 1, &issue_t1).unwrap();

    conn.execute("DELETE FROM dirty_sources", []).unwrap();

    // Ingest at T2 (newer) — should succeed
    let issue_t2 = make_test_issue(42, "2026-02-17T13:00:00.000+00:00");
    let result = ingest_issue_by_iid(&conn, &config, 1, &issue_t2).unwrap();

    assert!(!result.skipped_stale);
}

#[test]
fn test_ingest_issue_returns_dirty_source_keys() {
    let conn = setup_db();
    let config = test_config();
    let issue = make_test_issue(42, "2026-02-17T12:00:00.000+00:00");

    let result = ingest_issue_by_iid(&conn, &config, 1, &issue).unwrap();

    assert_eq!(result.dirty_source_keys.len(), 1);
    let (source_type, local_id) = &result.dirty_source_keys[0];
    assert_eq!(source_type.as_str(), "issue");
    assert!(*local_id > 0, "local_id should be positive");
}

#[test]
fn test_ingest_issue_updates_existing() {
    let conn = setup_db();
    let config = test_config();

    let issue_v1 = make_test_issue(42, "2026-02-17T12:00:00.000+00:00");
    ingest_issue_by_iid(&conn, &config, 1, &issue_v1).unwrap();

    let ts1 = get_db_updated_at_helper(&conn, "issues", 42).unwrap();

    // Newer version
    let issue_v2 = make_test_issue(42, "2026-02-17T14:00:00.000+00:00");
    let result = ingest_issue_by_iid(&conn, &config, 1, &issue_v2).unwrap();

    assert!(!result.skipped_stale);
    let ts2 = get_db_updated_at_helper(&conn, "issues", 42).unwrap();
    assert!(ts2 > ts1, "DB timestamp should increase after update");
}

// ---------------------------------------------------------------------------
// MR ingestion tests
// ---------------------------------------------------------------------------

#[test]
fn test_ingest_mr_by_iid_upserts_and_marks_dirty() {
    let conn = setup_db();
    let config = test_config();
    let mr = make_test_mr(101, "2026-02-17T12:00:00.000+00:00");

    let result = ingest_mr_by_iid(&conn, &config, 1, &mr).unwrap();

    assert!(!result.skipped_stale);
    assert!(!result.dirty_source_keys.is_empty());

    let db_ts = get_db_updated_at_helper(&conn, "merge_requests", 101);
    assert!(db_ts.is_some(), "MR should exist in DB");

    let dirty = get_dirty_keys(&conn);
    assert!(
        dirty.iter().any(|(t, _)| t == "merge_request"),
        "dirty_sources should contain a merge_request entry"
    );
}

#[test]
fn test_toctou_skips_stale_mr() {
    let conn = setup_db();
    let config = test_config();
    let mr = make_test_mr(101, "2026-02-17T12:00:00.000+00:00");

    let r1 = ingest_mr_by_iid(&conn, &config, 1, &mr).unwrap();
    assert!(!r1.skipped_stale);

    conn.execute("DELETE FROM dirty_sources", []).unwrap();

    let r2 = ingest_mr_by_iid(&conn, &config, 1, &mr).unwrap();
    assert!(r2.skipped_stale);
    assert!(r2.dirty_source_keys.is_empty());
}

#[test]
fn test_toctou_allows_newer_mr() {
    let conn = setup_db();
    let config = test_config();

    let mr_t1 = make_test_mr(101, "2026-02-17T12:00:00.000+00:00");
    ingest_mr_by_iid(&conn, &config, 1, &mr_t1).unwrap();

    conn.execute("DELETE FROM dirty_sources", []).unwrap();

    let mr_t2 = make_test_mr(101, "2026-02-17T13:00:00.000+00:00");
    let result = ingest_mr_by_iid(&conn, &config, 1, &mr_t2).unwrap();

    assert!(!result.skipped_stale);
}

#[test]
fn test_ingest_mr_returns_dirty_source_keys() {
    let conn = setup_db();
    let config = test_config();
    let mr = make_test_mr(101, "2026-02-17T12:00:00.000+00:00");

    let result = ingest_mr_by_iid(&conn, &config, 1, &mr).unwrap();

    assert_eq!(result.dirty_source_keys.len(), 1);
    let (source_type, local_id) = &result.dirty_source_keys[0];
    assert_eq!(source_type.as_str(), "merge_request");
    assert!(*local_id > 0);
}

#[test]
fn test_ingest_mr_updates_existing() {
    let conn = setup_db();
    let config = test_config();

    let mr_v1 = make_test_mr(101, "2026-02-17T12:00:00.000+00:00");
    ingest_mr_by_iid(&conn, &config, 1, &mr_v1).unwrap();

    let ts1 = get_db_updated_at_helper(&conn, "merge_requests", 101).unwrap();

    let mr_v2 = make_test_mr(101, "2026-02-17T14:00:00.000+00:00");
    let result = ingest_mr_by_iid(&conn, &config, 1, &mr_v2).unwrap();

    assert!(!result.skipped_stale);
    let ts2 = get_db_updated_at_helper(&conn, "merge_requests", 101).unwrap();
    assert!(ts2 > ts1, "DB timestamp should increase after update");
}

// ---------------------------------------------------------------------------
// Preflight fetch test (wiremock)
// ---------------------------------------------------------------------------

#[tokio::test]
async fn test_preflight_fetch_returns_issues_and_mrs() {
    use wiremock::matchers::{method, path};
    use wiremock::{Mock, MockServer, ResponseTemplate};

    let mock_server = MockServer::start().await;

    // Issue fixture
    let issue_json = serde_json::json!({
        "id": 42000,
        "iid": 42,
        "project_id": 100,
        "title": "Test issue 42",
        "description": "desc",
        "state": "opened",
        "created_at": "2026-01-01T00:00:00.000+00:00",
        "updated_at": "2026-02-17T12:00:00.000+00:00",
        "author": {"id": 1, "username": "testuser", "name": "Test User"},
        "assignees": [],
        "labels": [],
        "web_url": "https://example.com/group/repo/-/issues/42"
    });

    // MR fixture
    let mr_json = serde_json::json!({
        "id": 101000,
        "iid": 101,
        "project_id": 100,
        "title": "Test MR 101",
        "description": "mr desc",
        "state": "opened",
        "draft": false,
        "work_in_progress": false,
        "source_branch": "feature",
        "target_branch": "main",
        "sha": "abc123",
        "created_at": "2026-01-01T00:00:00.000+00:00",
        "updated_at": "2026-02-17T12:00:00.000+00:00",
        "author": {"id": 1, "username": "testuser", "name": "Test User"},
        "labels": [],
        "assignees": [],
        "reviewers": [],
        "web_url": "https://example.com/group/repo/-/merge_requests/101"
    });

    Mock::given(method("GET"))
        .and(path("/api/v4/projects/100/issues/42"))
        .respond_with(ResponseTemplate::new(200).set_body_json(&issue_json))
        .mount(&mock_server)
        .await;

    Mock::given(method("GET"))
        .and(path("/api/v4/projects/100/merge_requests/101"))
        .respond_with(ResponseTemplate::new(200).set_body_json(&mr_json))
        .mount(&mock_server)
        .await;

    let client = GitLabClient::new(&mock_server.uri(), "test-token", None);
    let targets = vec![
        ("issue".to_string(), 42i64),
        ("merge_request".to_string(), 101i64),
    ];

    let result = preflight_fetch(&client, 100, &targets).await;

    assert_eq!(result.issues.len(), 1);
    assert_eq!(result.issues[0].iid, 42);
    assert_eq!(result.merge_requests.len(), 1);
    assert_eq!(result.merge_requests[0].iid, 101);
    assert!(result.failures.is_empty());
}

// ---------------------------------------------------------------------------
// Dependent helper tests (bd-kanh)
// ---------------------------------------------------------------------------

#[tokio::test]
async fn test_fetch_dependents_for_issue_empty_events() {
    use wiremock::matchers::{method, path};
    use wiremock::{Mock, MockServer, ResponseTemplate};

    let mock_server = MockServer::start().await;
    let conn = setup_db();
    let config = test_config();

    // Insert an issue so we have a local_id
    let issue = make_test_issue(42, "2026-02-17T12:00:00.000+00:00");
    ingest_issue_by_iid(&conn, &config, 1, &issue).unwrap();
    let local_id: i64 = conn
        .query_row(
            "SELECT id FROM issues WHERE project_id = 1 AND iid = 42",
            [],
            |row| row.get(0),
        )
        .unwrap();

    // Mock empty resource event endpoints
    Mock::given(method("GET"))
        .and(path("/api/v4/projects/100/issues/42/resource_state_events"))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;
    Mock::given(method("GET"))
        .and(path("/api/v4/projects/100/issues/42/resource_label_events"))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;
    Mock::given(method("GET"))
        .and(path(
            "/api/v4/projects/100/issues/42/resource_milestone_events",
        ))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;

    // Mock empty discussions endpoint
    Mock::given(method("GET"))
        .and(path("/api/v4/projects/100/issues/42/discussions"))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;

    let client = GitLabClient::new(&mock_server.uri(), "test-token", None);

    let result = fetch_dependents_for_issue(&client, &conn, 1, 100, 42, local_id, &config)
        .await
        .unwrap();

    assert_eq!(result.resource_events_fetched, 0);
    assert_eq!(result.discussions_fetched, 0);
}

#[tokio::test]
async fn test_fetch_dependents_for_mr_empty_events() {
    use wiremock::matchers::{method, path};
    use wiremock::{Mock, MockServer, ResponseTemplate};

    let mock_server = MockServer::start().await;
    let conn = setup_db();
    let config = test_config();

    // Insert an MR so we have a local_id
    let mr = make_test_mr(101, "2026-02-17T12:00:00.000+00:00");
    ingest_mr_by_iid(&conn, &config, 1, &mr).unwrap();
    let local_id: i64 = conn
        .query_row(
            "SELECT id FROM merge_requests WHERE project_id = 1 AND iid = 101",
            [],
            |row| row.get(0),
        )
        .unwrap();

    // Mock empty resource event endpoints for MR
    Mock::given(method("GET"))
        .and(path(
            "/api/v4/projects/100/merge_requests/101/resource_state_events",
        ))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;
    Mock::given(method("GET"))
        .and(path(
            "/api/v4/projects/100/merge_requests/101/resource_label_events",
        ))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;
    Mock::given(method("GET"))
        .and(path(
            "/api/v4/projects/100/merge_requests/101/resource_milestone_events",
        ))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;

    // Mock empty discussions endpoint for MR
    Mock::given(method("GET"))
        .and(path("/api/v4/projects/100/merge_requests/101/discussions"))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;

    // Mock empty closes_issues endpoint
    Mock::given(method("GET"))
        .and(path(
            "/api/v4/projects/100/merge_requests/101/closes_issues",
        ))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;

    // Mock empty diffs endpoint
    Mock::given(method("GET"))
        .and(path("/api/v4/projects/100/merge_requests/101/diffs"))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;

    let client = GitLabClient::new(&mock_server.uri(), "test-token", None);

    let result = fetch_dependents_for_mr(&client, &conn, 1, 100, 101, local_id, &config)
        .await
        .unwrap();

    assert_eq!(result.resource_events_fetched, 0);
    assert_eq!(result.discussions_fetched, 0);
    assert_eq!(result.closes_issues_stored, 0);
    assert_eq!(result.file_changes_stored, 0);
}

#[tokio::test]
async fn test_fetch_dependents_for_mr_with_closes_issues() {
    use wiremock::matchers::{method, path};
    use wiremock::{Mock, MockServer, ResponseTemplate};

    let mock_server = MockServer::start().await;
    let conn = setup_db();
    let config = test_config();

    // Insert issue and MR so references can resolve
    let issue = make_test_issue(42, "2026-02-17T12:00:00.000+00:00");
    ingest_issue_by_iid(&conn, &config, 1, &issue).unwrap();

    let mr = make_test_mr(101, "2026-02-17T12:00:00.000+00:00");
    ingest_mr_by_iid(&conn, &config, 1, &mr).unwrap();
    let mr_local_id: i64 = conn
        .query_row(
            "SELECT id FROM merge_requests WHERE project_id = 1 AND iid = 101",
            [],
            |row| row.get(0),
        )
        .unwrap();

    // Mock empty resource events
    for endpoint in [
        "resource_state_events",
        "resource_label_events",
        "resource_milestone_events",
    ] {
        Mock::given(method("GET"))
            .and(path(format!(
                "/api/v4/projects/100/merge_requests/101/{endpoint}"
            )))
            .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
            .mount(&mock_server)
            .await;
    }

    // Mock empty discussions
    Mock::given(method("GET"))
        .and(path("/api/v4/projects/100/merge_requests/101/discussions"))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;

    // Mock closes_issues with one reference
    Mock::given(method("GET"))
        .and(path(
            "/api/v4/projects/100/merge_requests/101/closes_issues",
        ))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([
            {
                "id": 42000,
                "iid": 42,
                "project_id": 100,
                "title": "Test issue 42",
                "state": "opened",
                "web_url": "https://example.com/group/repo/-/issues/42"
            }
        ])))
        .mount(&mock_server)
        .await;

    // Mock empty diffs
    Mock::given(method("GET"))
        .and(path("/api/v4/projects/100/merge_requests/101/diffs"))
        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!([])))
        .mount(&mock_server)
        .await;

    let client = GitLabClient::new(&mock_server.uri(), "test-token", None);

    let result = fetch_dependents_for_mr(&client, &conn, 1, 100, 101, mr_local_id, &config)
        .await
        .unwrap();

    assert_eq!(result.closes_issues_stored, 1);
}