theirongolddev/gitlore
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test: Remove redundant comments from test files

Browse Source 
Applies the same doc comment cleanup to test files:
- Removes test module headers (//! lines)
- Removes obvious test function comments
- Retains comments explaining non-obvious test scenarios

Test names should be descriptive enough to convey intent without
additional comments. Complex test setup or assertions that need
explanation retain their comments.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Taylor Eernisse
2026-02-05 00:04:39 -05:00
parent 65583ed5d6
commit dd2869fd98
9 changed files with 7 additions and 158 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
tests/embedding.rs
View File

@@ -1,16 +1,8 @@
//! Integration tests for embedding storage and vector search.
//!
//! These tests create an in-memory SQLite database with sqlite-vec loaded,
//! apply all migrations through 010 (chunk config), and verify KNN search
//! and metadata operations.
use lore::core::db::create_connection;
use rusqlite::Connection;
use std::path::PathBuf;
use tempfile::TempDir;
/// Create a test DB on disk (required for sqlite-vec which needs the extension loaded).
/// Uses create_connection to get the sqlite-vec extension registered.
fn create_test_db() -> (TempDir, Connection) {
let tmp = TempDir::new().unwrap();
let db_path = tmp.path().join("test.db");
@@ -35,7 +27,6 @@ fn create_test_db() -> (TempDir, Connection) {
.unwrap_or_else(|e| panic!("Migration {} failed: {}", version, e));
}
// Seed a project
conn.execute(
"INSERT INTO projects (id, gitlab_project_id, path_with_namespace) VALUES (1, 100, 'group/project')",
[],
@@ -54,7 +45,6 @@ fn insert_document(conn: &Connection, id: i64, title: &str, content: &str) {
.unwrap();
}
/// Create a 768-dim vector with a specific dimension set to 1.0 (unit vector along axis).
fn axis_vector(dim: usize) -> Vec<f32> {
let mut v = vec![0.0f32; 768];
v[dim] = 1.0;
@@ -89,12 +79,10 @@ fn knn_search_returns_nearest_neighbors() {
insert_document(&conn, 2, "Doc B", "Content about database optimization.");
insert_document(&conn, 3, "Doc C", "Content about logging infrastructure.");
// Doc 1: axis 0, Doc 2: axis 1, Doc 3: axis 2
insert_embedding(&conn, 1, 0, &axis_vector(0));
insert_embedding(&conn, 2, 0, &axis_vector(1));
insert_embedding(&conn, 3, 0, &axis_vector(2));
// Query vector close to axis 0 (should match doc 1)
let mut query = vec![0.0f32; 768];
query[0] = 0.9;
query[1] = 0.1;
@@ -132,7 +120,6 @@ fn knn_search_deduplicates_chunks() {
"Very long content that was chunked.",
);
// Same document, two chunks, both similar to query
let mut v1 = vec![0.0f32; 768];
v1[0] = 1.0;
let mut v2 = vec![0.0f32; 768];
@@ -144,7 +131,6 @@ fn knn_search_deduplicates_chunks() {
let results = lore::search::search_vector(&conn, &axis_vector(0), 10).unwrap();
// Should deduplicate: same document_id appears at most once
let unique_docs: std::collections::HashSet<i64> =
results.iter().map(|r| r.document_id).collect();
assert_eq!(
@@ -161,7 +147,6 @@ fn orphan_trigger_deletes_embeddings_on_document_delete() {
insert_document(&conn, 1, "Will be deleted", "Content.");
insert_embedding(&conn, 1, 0, &axis_vector(0));
// Verify embedding exists
let count: i64 = conn
.query_row(
"SELECT COUNT(*) FROM embeddings WHERE rowid = 1000",
@@ -171,11 +156,9 @@ fn orphan_trigger_deletes_embeddings_on_document_delete() {
.unwrap();
assert_eq!(count, 1, "Embedding should exist before delete");
// Delete the document
conn.execute("DELETE FROM documents WHERE id = 1", [])
.unwrap();
// Verify embedding was cascade-deleted via trigger
let count: i64 = conn
.query_row(
"SELECT COUNT(*) FROM embeddings WHERE rowid = 1000",
@@ -188,7 +171,6 @@ fn orphan_trigger_deletes_embeddings_on_document_delete() {
"Trigger should delete embeddings when document is deleted"
);
// Verify metadata was cascade-deleted via FK
let meta_count: i64 = conn
.query_row(
"SELECT COUNT(*) FROM embedding_metadata WHERE document_id = 1",
@@ -207,19 +189,12 @@ fn empty_database_returns_no_results() {
assert!(results.is_empty(), "Empty DB should return no results");
}
// --- Bug-fix regression tests ---
#[test]
fn overflow_doc_with_error_sentinel_not_re_detected_as_pending() {
// Bug 2: Documents skipped for chunk overflow must record a sentinel error
// in embedding_metadata so they are not re-detected as pending on subsequent
// pipeline runs (which would cause an infinite re-processing loop).
let (_tmp, conn) = create_test_db();
insert_document(&conn, 1, "Overflow doc", "Some content");
// Simulate what the pipeline does when a document exceeds CHUNK_ROWID_MULTIPLIER:
// it records an error sentinel at chunk_index=0.
let now = chrono::Utc::now().timestamp_millis();
conn.execute(
"INSERT INTO embedding_metadata
@@ -230,7 +205,6 @@ fn overflow_doc_with_error_sentinel_not_re_detected_as_pending() {
)
.unwrap();
// Now find_pending_documents should NOT return this document
let pending =
lore::embedding::find_pending_documents(&conn, 100, 0, "nomic-embed-text").unwrap();
assert!(
@@ -239,7 +213,6 @@ fn overflow_doc_with_error_sentinel_not_re_detected_as_pending() {
pending.len()
);
// count_pending_documents should also return 0
let count = lore::embedding::count_pending_documents(&conn, "nomic-embed-text").unwrap();
assert_eq!(
count, 0,
@@ -249,11 +222,8 @@ fn overflow_doc_with_error_sentinel_not_re_detected_as_pending() {
#[test]
fn count_and_find_pending_agree() {
// Bug 1: count_pending_documents and find_pending_documents must use
// logically equivalent WHERE clauses to produce consistent results.
let (_tmp, conn) = create_test_db();
// Case 1: No documents at all
let count = lore::embedding::count_pending_documents(&conn, "nomic-embed-text").unwrap();
let found =
lore::embedding::find_pending_documents(&conn, 1000, 0, "nomic-embed-text").unwrap();
@@ -263,7 +233,6 @@ fn count_and_find_pending_agree() {
"Empty DB: count and find should agree"
);
// Case 2: New document (no metadata)
insert_document(&conn, 1, "New doc", "Content");
let count = lore::embedding::count_pending_documents(&conn, "nomic-embed-text").unwrap();
let found =
@@ -275,7 +244,6 @@ fn count_and_find_pending_agree() {
);
assert_eq!(count, 1);
// Case 3: Document with matching metadata (not pending)
let now = chrono::Utc::now().timestamp_millis();
conn.execute(
"INSERT INTO embedding_metadata
@@ -295,7 +263,6 @@ fn count_and_find_pending_agree() {
);
assert_eq!(count, 0);
// Case 4: Config drift (chunk_max_bytes mismatch)
conn.execute(
"UPDATE embedding_metadata SET chunk_max_bytes = 999 WHERE document_id = 1",
[],
@@ -314,14 +281,11 @@ fn count_and_find_pending_agree() {
#[test]
fn full_embed_delete_is_atomic() {
// Bug 7: The --full flag's two DELETE statements should be atomic.
// This test verifies that both tables are cleared together.
let (_tmp, conn) = create_test_db();
insert_document(&conn, 1, "Doc", "Content");
insert_embedding(&conn, 1, 0, &axis_vector(0));
// Verify data exists
let meta_count: i64 = conn
.query_row("SELECT COUNT(*) FROM embedding_metadata", [], |r| r.get(0))
.unwrap();
@@ -331,7 +295,6 @@ fn full_embed_delete_is_atomic() {
assert_eq!(meta_count, 1);
assert_eq!(embed_count, 1);
// Execute the atomic delete (same as embed.rs --full)
conn.execute_batch(
"BEGIN;
DELETE FROM embedding_metadata;