refactor: Remove redundant doc comments throughout codebase

Removes module-level doc comments (//! lines) and excessive inline doc
comments that were duplicating information already evident from:
- Function/struct names (self-documenting code)
- Type signatures (the what is clear from types)
- Implementation context (the how is clear from code)

Affected modules:
- cli/* - Removed command descriptions duplicating clap help text
- core/* - Removed module headers and obvious function docs
- documents/* - Removed extractor/regenerator/truncation docs
- embedding/* - Removed pipeline and chunking docs
- gitlab/* - Removed client and transformer docs (kept type definitions)
- ingestion/* - Removed orchestrator and ingestion docs
- search/* - Removed FTS and vector search docs

Philosophy: Code should be self-documenting. Comments should explain
"why" (business decisions, non-obvious constraints) not "what" (which
the code itself shows). This change reduces noise and maintenance burden
while keeping the codebase just as understandable.

Retains comments for:
- Non-obvious business logic
- Important safety invariants
- Complex algorithm explanations
- Public API boundaries where generated docs matter

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Taylor Eernisse
2026-02-05 00:04:32 -05:00
parent 976ad92ef0
commit 65583ed5d6
57 changed files with 143 additions and 1693 deletions

View File

@@ -1,5 +1,3 @@
//! Search command: lexical (FTS5) search with filter support and single-query hydration.
use console::style;
use serde::Serialize;
@@ -15,7 +13,6 @@ use crate::search::{
search_fts,
};
/// Display-ready search result with all fields hydrated.
#[derive(Debug, Serialize)]
pub struct SearchResultDisplay {
pub document_id: i64,
@@ -34,7 +31,6 @@ pub struct SearchResultDisplay {
pub explain: Option<ExplainData>,
}
/// Ranking explanation for --explain output.
#[derive(Debug, Serialize)]
pub struct ExplainData {
pub vector_rank: Option<usize>,
@@ -42,7 +38,6 @@ pub struct ExplainData {
pub rrf_score: f64,
}
/// Search response wrapper.
#[derive(Debug, Serialize)]
pub struct SearchResponse {
pub query: String,
@@ -52,7 +47,6 @@ pub struct SearchResponse {
pub warnings: Vec<String>,
}
/// Build SearchFilters from CLI args.
pub struct SearchCliFilters {
pub source_type: Option<String>,
pub author: Option<String>,
@@ -64,7 +58,6 @@ pub struct SearchCliFilters {
pub limit: usize,
}
/// Run a lexical search query.
pub fn run_search(
config: &Config,
query: &str,
@@ -75,7 +68,6 @@ pub fn run_search(
let db_path = get_db_path(config.storage.db_path.as_deref());
let conn = create_connection(&db_path)?;
// Check if any documents exist
let doc_count: i64 = conn
.query_row("SELECT COUNT(*) FROM documents", [], |row| row.get(0))
.unwrap_or(0);
@@ -90,7 +82,6 @@ pub fn run_search(
});
}
// Build filters
let source_type = cli_filters
.source_type
.as_deref()
@@ -146,7 +137,6 @@ pub fn run_search(
limit: cli_filters.limit,
};
// Adaptive recall: wider initial fetch when filters applied
let requested = filters.clamp_limit();
let top_k = if filters.has_any_filter() {
(requested * 50).clamp(200, 1500)
@@ -154,24 +144,20 @@ pub fn run_search(
(requested * 10).clamp(50, 1500)
};
// FTS search
let fts_results = search_fts(&conn, query, top_k, fts_mode)?;
let fts_tuples: Vec<(i64, f64)> = fts_results
.iter()
.map(|r| (r.document_id, r.bm25_score))
.collect();
// Build snippet map before ranking
let snippet_map: std::collections::HashMap<i64, String> = fts_results
.iter()
.map(|r| (r.document_id, r.snippet.clone()))
.collect();
// RRF ranking (single-list for lexical mode)
let ranked = rank_rrf(&[], &fts_tuples);
let ranked_ids: Vec<i64> = ranked.iter().map(|r| r.document_id).collect();
// Apply post-retrieval filters
let filtered_ids = apply_filters(&conn, &ranked_ids, &filters)?;
if filtered_ids.is_empty() {
@@ -184,10 +170,8 @@ pub fn run_search(
});
}
// Hydrate results in single round-trip
let hydrated = hydrate_results(&conn, &filtered_ids)?;
// Build display results preserving filter order
let rrf_map: std::collections::HashMap<i64, &crate::search::RrfResult> =
ranked.iter().map(|r| (r.document_id, r)).collect();
@@ -233,7 +217,6 @@ pub fn run_search(
})
}
/// Raw row from hydration query.
struct HydratedRow {
document_id: i64,
source_type: String,
@@ -248,10 +231,6 @@ struct HydratedRow {
paths: Vec<String>,
}
/// Hydrate document IDs into full display rows in a single query.
///
/// Uses json_each() to pass ranked IDs and preserve ordering via ORDER BY j.key.
/// Labels and paths fetched via correlated json_group_array subqueries.
fn hydrate_results(conn: &rusqlite::Connection, document_ids: &[i64]) -> Result<Vec<HydratedRow>> {
if document_ids.is_empty() {
return Ok(Vec::new());
@@ -299,7 +278,6 @@ fn hydrate_results(conn: &rusqlite::Connection, document_ids: &[i64]) -> Result<
Ok(rows)
}
/// Parse a JSON array string into a Vec<String>, filtering out null/empty.
fn parse_json_array(json: &str) -> Vec<String> {
serde_json::from_str::<Vec<serde_json::Value>>(json)
.unwrap_or_default()
@@ -309,7 +287,6 @@ fn parse_json_array(json: &str) -> Vec<String> {
.collect()
}
/// Print human-readable search results.
pub fn print_search_results(response: &SearchResponse) {
if !response.warnings.is_empty() {
for w in &response.warnings {
@@ -364,7 +341,6 @@ pub fn print_search_results(response: &SearchResponse) {
println!(" Labels: {}", result.labels.join(", "));
}
// Strip HTML tags from snippet for terminal display
let clean_snippet = result.snippet.replace("<mark>", "").replace("</mark>", "");
println!(" {}", style(clean_snippet).dim());
@@ -384,7 +360,6 @@ pub fn print_search_results(response: &SearchResponse) {
}
}
/// JSON output structures.
#[derive(Serialize)]
struct SearchJsonOutput<'a> {
ok: bool,
@@ -397,7 +372,6 @@ struct SearchMeta {
elapsed_ms: u64,
}
/// Print JSON robot-mode output.
pub fn print_search_results_json(response: &SearchResponse, elapsed_ms: u64) {
let output = SearchJsonOutput {
ok: true,