Schema enrichment: - transcripts table: +engine, +model_id, +inference_ms, +sample_rate, +audio_channels, +format_mode, +remove_fillers, +british_english, +anti_hallucination - New error_log table: context, error_code, message, metadata (JSON) - 5 indices on frequently queried columns Metadata pipeline: - TranscriptMetadata struct in kon-core for full provenance capture - LocalEngine tracks loaded ModelId, returns TimedTranscript with inference_ms - std::time::Instant timing around transcribe-rs inference calls - Tauri transcription commands emit inference_ms in event payloads - InsertTranscriptParams accepts all provenance fields - log_error() for structured error logging to SQLite Every transcript is now fully reproducible from its stored metadata. 23 tests passing, clippy clean. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
484 lines
15 KiB
Rust
484 lines
15 KiB
Rust
use std::path::Path;
|
|
|
|
use sqlx::sqlite::{SqliteConnectOptions, SqlitePoolOptions};
|
|
use sqlx::{Row, SqlitePool};
|
|
|
|
use kon_core::error::{KonError, Result};
|
|
|
|
/// Initialise the SQLite database with connection pool and run migrations.
|
|
pub async fn init(db_path: &Path) -> Result<SqlitePool> {
|
|
if let Some(parent) = db_path.parent() {
|
|
std::fs::create_dir_all(parent)?;
|
|
}
|
|
|
|
let options = SqliteConnectOptions::new()
|
|
.filename(db_path)
|
|
.create_if_missing(true);
|
|
|
|
let pool = SqlitePoolOptions::new()
|
|
.max_connections(5)
|
|
.connect_with(options)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Database connect failed: {e}")))?;
|
|
|
|
run_migrations(&pool).await?;
|
|
|
|
Ok(pool)
|
|
}
|
|
|
|
/// Run schema migrations.
|
|
async fn run_migrations(pool: &SqlitePool) -> Result<()> {
|
|
sqlx::query(
|
|
"CREATE TABLE IF NOT EXISTS transcripts (
|
|
id TEXT PRIMARY KEY,
|
|
text TEXT NOT NULL DEFAULT '',
|
|
source TEXT NOT NULL DEFAULT 'microphone',
|
|
title TEXT,
|
|
audio_path TEXT,
|
|
duration REAL NOT NULL DEFAULT 0.0,
|
|
engine TEXT,
|
|
model_id TEXT,
|
|
inference_ms INTEGER,
|
|
sample_rate INTEGER,
|
|
audio_channels INTEGER,
|
|
format_mode TEXT,
|
|
remove_fillers INTEGER NOT NULL DEFAULT 0,
|
|
british_english INTEGER NOT NULL DEFAULT 0,
|
|
anti_hallucination INTEGER NOT NULL DEFAULT 0,
|
|
created_at TEXT NOT NULL DEFAULT (datetime('now'))
|
|
)",
|
|
)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Migration failed: {e}")))?;
|
|
|
|
sqlx::query(
|
|
"CREATE TABLE IF NOT EXISTS segments (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
transcript_id TEXT NOT NULL REFERENCES transcripts(id) ON DELETE CASCADE,
|
|
start_time REAL NOT NULL,
|
|
end_time REAL NOT NULL,
|
|
text TEXT NOT NULL DEFAULT ''
|
|
)",
|
|
)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Migration failed: {e}")))?;
|
|
|
|
sqlx::query(
|
|
"CREATE TABLE IF NOT EXISTS tasks (
|
|
id TEXT PRIMARY KEY,
|
|
text TEXT NOT NULL,
|
|
bucket TEXT NOT NULL DEFAULT 'inbox',
|
|
list_id TEXT,
|
|
effort TEXT,
|
|
done INTEGER NOT NULL DEFAULT 0,
|
|
done_at TEXT,
|
|
created_at TEXT NOT NULL DEFAULT (datetime('now')),
|
|
source_transcript_id TEXT
|
|
)",
|
|
)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Migration failed: {e}")))?;
|
|
|
|
sqlx::query(
|
|
"CREATE TABLE IF NOT EXISTS task_lists (
|
|
id TEXT PRIMARY KEY,
|
|
name TEXT NOT NULL,
|
|
built_in INTEGER NOT NULL DEFAULT 0,
|
|
profile_id TEXT,
|
|
created_at TEXT NOT NULL DEFAULT (datetime('now'))
|
|
)",
|
|
)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Migration failed: {e}")))?;
|
|
|
|
sqlx::query(
|
|
"CREATE TABLE IF NOT EXISTS settings (
|
|
key TEXT PRIMARY KEY,
|
|
value TEXT NOT NULL
|
|
)",
|
|
)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Migration failed: {e}")))?;
|
|
|
|
sqlx::query(
|
|
"CREATE TABLE IF NOT EXISTS error_log (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
timestamp TEXT NOT NULL DEFAULT (datetime('now')),
|
|
context TEXT NOT NULL,
|
|
error_code TEXT,
|
|
message TEXT NOT NULL,
|
|
metadata TEXT
|
|
)",
|
|
)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Migration failed: {e}")))?;
|
|
|
|
// Indices for frequently queried columns
|
|
for ddl in [
|
|
"CREATE INDEX IF NOT EXISTS idx_transcripts_created ON transcripts(created_at)",
|
|
"CREATE INDEX IF NOT EXISTS idx_segments_transcript ON segments(transcript_id)",
|
|
"CREATE INDEX IF NOT EXISTS idx_tasks_bucket ON tasks(bucket)",
|
|
"CREATE INDEX IF NOT EXISTS idx_tasks_transcript ON tasks(source_transcript_id)",
|
|
"CREATE INDEX IF NOT EXISTS idx_error_log_context ON error_log(context)",
|
|
] {
|
|
sqlx::query(ddl)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Index creation failed: {e}")))?;
|
|
}
|
|
|
|
Ok(())
|
|
}
|
|
|
|
// --- Transcript CRUD ---
|
|
|
|
/// Parameters for inserting a transcript with full provenance.
|
|
pub struct InsertTranscriptParams<'a> {
|
|
pub id: &'a str,
|
|
pub text: &'a str,
|
|
pub source: &'a str,
|
|
pub title: Option<&'a str>,
|
|
pub audio_path: Option<&'a str>,
|
|
pub duration: f64,
|
|
pub engine: Option<&'a str>,
|
|
pub model_id: Option<&'a str>,
|
|
pub inference_ms: Option<i64>,
|
|
pub sample_rate: Option<i32>,
|
|
pub audio_channels: Option<i32>,
|
|
pub format_mode: Option<&'a str>,
|
|
pub remove_fillers: bool,
|
|
pub british_english: bool,
|
|
pub anti_hallucination: bool,
|
|
}
|
|
|
|
pub async fn insert_transcript(
|
|
pool: &SqlitePool,
|
|
params: &InsertTranscriptParams<'_>,
|
|
) -> Result<()> {
|
|
sqlx::query(
|
|
"INSERT INTO transcripts (id, text, source, title, audio_path, duration, engine, model_id, inference_ms, sample_rate, audio_channels, format_mode, remove_fillers, british_english, anti_hallucination)
|
|
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
|
|
)
|
|
.bind(params.id)
|
|
.bind(params.text)
|
|
.bind(params.source)
|
|
.bind(params.title)
|
|
.bind(params.audio_path)
|
|
.bind(params.duration)
|
|
.bind(params.engine)
|
|
.bind(params.model_id)
|
|
.bind(params.inference_ms)
|
|
.bind(params.sample_rate)
|
|
.bind(params.audio_channels)
|
|
.bind(params.format_mode)
|
|
.bind(params.remove_fillers)
|
|
.bind(params.british_english)
|
|
.bind(params.anti_hallucination)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Insert transcript failed: {e}")))?;
|
|
Ok(())
|
|
}
|
|
|
|
pub async fn get_transcript(
|
|
pool: &SqlitePool,
|
|
id: &str,
|
|
) -> Result<Option<TranscriptRow>> {
|
|
let row = sqlx::query(
|
|
"SELECT id, text, source, title, audio_path, duration, engine, model_id, inference_ms, sample_rate, audio_channels, format_mode, remove_fillers, british_english, anti_hallucination, created_at FROM transcripts WHERE id = ?",
|
|
)
|
|
.bind(id)
|
|
.fetch_optional(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Get transcript failed: {e}")))?;
|
|
|
|
Ok(row.map(|r| transcript_row_from(&r)))
|
|
}
|
|
|
|
pub async fn list_transcripts(pool: &SqlitePool, limit: i64) -> Result<Vec<TranscriptRow>> {
|
|
let rows = sqlx::query(
|
|
"SELECT id, text, source, title, audio_path, duration, engine, model_id, inference_ms, sample_rate, audio_channels, format_mode, remove_fillers, british_english, anti_hallucination, created_at FROM transcripts ORDER BY created_at DESC LIMIT ?",
|
|
)
|
|
.bind(limit)
|
|
.fetch_all(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("List transcripts failed: {e}")))?;
|
|
|
|
Ok(rows.iter().map(transcript_row_from).collect())
|
|
}
|
|
|
|
pub async fn delete_transcript(pool: &SqlitePool, id: &str) -> Result<()> {
|
|
sqlx::query("DELETE FROM transcripts WHERE id = ?")
|
|
.bind(id)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Delete transcript failed: {e}")))?;
|
|
Ok(())
|
|
}
|
|
|
|
// --- Task CRUD ---
|
|
|
|
pub async fn insert_task(
|
|
pool: &SqlitePool,
|
|
id: &str,
|
|
text: &str,
|
|
bucket: &str,
|
|
source_transcript_id: Option<&str>,
|
|
) -> Result<()> {
|
|
sqlx::query(
|
|
"INSERT INTO tasks (id, text, bucket, source_transcript_id) VALUES (?, ?, ?, ?)",
|
|
)
|
|
.bind(id)
|
|
.bind(text)
|
|
.bind(bucket)
|
|
.bind(source_transcript_id)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Insert task failed: {e}")))?;
|
|
Ok(())
|
|
}
|
|
|
|
pub async fn list_tasks(pool: &SqlitePool) -> Result<Vec<TaskRow>> {
|
|
let rows =
|
|
sqlx::query("SELECT id, text, bucket, list_id, effort, done, done_at, created_at, source_transcript_id FROM tasks ORDER BY created_at DESC")
|
|
.fetch_all(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("List tasks failed: {e}")))?;
|
|
|
|
Ok(rows
|
|
.into_iter()
|
|
.map(|r| TaskRow {
|
|
id: r.get("id"),
|
|
text: r.get("text"),
|
|
bucket: r.get("bucket"),
|
|
list_id: r.get("list_id"),
|
|
effort: r.get("effort"),
|
|
done: r.get("done"),
|
|
done_at: r.get("done_at"),
|
|
created_at: r.get("created_at"),
|
|
source_transcript_id: r.get("source_transcript_id"),
|
|
})
|
|
.collect())
|
|
}
|
|
|
|
pub async fn complete_task(pool: &SqlitePool, id: &str) -> Result<()> {
|
|
sqlx::query("UPDATE tasks SET done = 1, done_at = datetime('now') WHERE id = ?")
|
|
.bind(id)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Complete task failed: {e}")))?;
|
|
Ok(())
|
|
}
|
|
|
|
pub async fn delete_task(pool: &SqlitePool, id: &str) -> Result<()> {
|
|
sqlx::query("DELETE FROM tasks WHERE id = ?")
|
|
.bind(id)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Delete task failed: {e}")))?;
|
|
Ok(())
|
|
}
|
|
|
|
// --- Settings CRUD ---
|
|
|
|
pub async fn set_setting(pool: &SqlitePool, key: &str, value: &str) -> Result<()> {
|
|
sqlx::query("INSERT OR REPLACE INTO settings (key, value) VALUES (?, ?)")
|
|
.bind(key)
|
|
.bind(value)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Set setting failed: {e}")))?;
|
|
Ok(())
|
|
}
|
|
|
|
pub async fn get_setting(pool: &SqlitePool, key: &str) -> Result<Option<String>> {
|
|
let row = sqlx::query("SELECT value FROM settings WHERE key = ?")
|
|
.bind(key)
|
|
.fetch_optional(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Get setting failed: {e}")))?;
|
|
Ok(row.map(|r| r.get("value")))
|
|
}
|
|
|
|
// --- Row types ---
|
|
|
|
#[derive(Debug, Clone)]
|
|
pub struct TranscriptRow {
|
|
pub id: String,
|
|
pub text: String,
|
|
pub source: String,
|
|
pub title: Option<String>,
|
|
pub audio_path: Option<String>,
|
|
pub duration: f64,
|
|
pub engine: Option<String>,
|
|
pub model_id: Option<String>,
|
|
pub inference_ms: Option<i64>,
|
|
pub sample_rate: Option<i32>,
|
|
pub audio_channels: Option<i32>,
|
|
pub format_mode: Option<String>,
|
|
pub remove_fillers: bool,
|
|
pub british_english: bool,
|
|
pub anti_hallucination: bool,
|
|
pub created_at: String,
|
|
}
|
|
|
|
#[derive(Debug, Clone)]
|
|
pub struct TaskRow {
|
|
pub id: String,
|
|
pub text: String,
|
|
pub bucket: String,
|
|
pub list_id: Option<String>,
|
|
pub effort: Option<String>,
|
|
pub done: bool,
|
|
pub done_at: Option<String>,
|
|
pub created_at: String,
|
|
pub source_transcript_id: Option<String>,
|
|
}
|
|
|
|
fn transcript_row_from(r: &sqlx::sqlite::SqliteRow) -> TranscriptRow {
|
|
TranscriptRow {
|
|
id: r.get("id"),
|
|
text: r.get("text"),
|
|
source: r.get("source"),
|
|
title: r.get("title"),
|
|
audio_path: r.get("audio_path"),
|
|
duration: r.get("duration"),
|
|
engine: r.get("engine"),
|
|
model_id: r.get("model_id"),
|
|
inference_ms: r.get("inference_ms"),
|
|
sample_rate: r.get("sample_rate"),
|
|
audio_channels: r.get("audio_channels"),
|
|
format_mode: r.get("format_mode"),
|
|
remove_fillers: r.get("remove_fillers"),
|
|
british_english: r.get("british_english"),
|
|
anti_hallucination: r.get("anti_hallucination"),
|
|
created_at: r.get("created_at"),
|
|
}
|
|
}
|
|
|
|
// --- Error Logging ---
|
|
|
|
/// Log a structured error to the error_log table.
|
|
pub async fn log_error(
|
|
pool: &SqlitePool,
|
|
context: &str,
|
|
error_code: Option<&str>,
|
|
message: &str,
|
|
metadata: Option<&str>,
|
|
) -> Result<()> {
|
|
sqlx::query(
|
|
"INSERT INTO error_log (context, error_code, message, metadata) VALUES (?, ?, ?, ?)",
|
|
)
|
|
.bind(context)
|
|
.bind(error_code)
|
|
.bind(message)
|
|
.bind(metadata)
|
|
.execute(pool)
|
|
.await
|
|
.map_err(|e| KonError::StorageError(format!("Error log failed: {e}")))?;
|
|
Ok(())
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::*;
|
|
|
|
async fn test_pool() -> SqlitePool {
|
|
let pool = SqlitePoolOptions::new()
|
|
.connect("sqlite::memory:")
|
|
.await
|
|
.unwrap();
|
|
run_migrations(&pool).await.unwrap();
|
|
pool
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn transcript_crud_roundtrip() {
|
|
let pool = test_pool().await;
|
|
|
|
insert_transcript(
|
|
&pool,
|
|
&InsertTranscriptParams {
|
|
id: "t1",
|
|
text: "Hello world",
|
|
source: "microphone",
|
|
title: Some("Test"),
|
|
audio_path: None,
|
|
duration: 1.5,
|
|
engine: Some("whisper"),
|
|
model_id: Some("whisper-tiny-en"),
|
|
inference_ms: Some(250),
|
|
sample_rate: Some(48000),
|
|
audio_channels: Some(1),
|
|
format_mode: Some("Clean"),
|
|
remove_fillers: true,
|
|
british_english: true,
|
|
anti_hallucination: false,
|
|
},
|
|
)
|
|
.await
|
|
.unwrap();
|
|
|
|
let t = get_transcript(&pool, "t1").await.unwrap().unwrap();
|
|
assert_eq!(t.text, "Hello world");
|
|
assert_eq!(t.source, "microphone");
|
|
assert_eq!(t.duration, 1.5);
|
|
assert_eq!(t.engine.as_deref(), Some("whisper"));
|
|
assert_eq!(t.model_id.as_deref(), Some("whisper-tiny-en"));
|
|
assert_eq!(t.inference_ms, Some(250));
|
|
assert!(t.remove_fillers);
|
|
assert!(t.british_english);
|
|
|
|
let list = list_transcripts(&pool, 10).await.unwrap();
|
|
assert_eq!(list.len(), 1);
|
|
|
|
delete_transcript(&pool, "t1").await.unwrap();
|
|
let deleted = get_transcript(&pool, "t1").await.unwrap();
|
|
assert!(deleted.is_none());
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn task_crud_roundtrip() {
|
|
let pool = test_pool().await;
|
|
|
|
insert_task(&pool, "task1", "Buy groceries", "today", None)
|
|
.await
|
|
.unwrap();
|
|
|
|
let tasks = list_tasks(&pool).await.unwrap();
|
|
assert_eq!(tasks.len(), 1);
|
|
assert_eq!(tasks[0].text, "Buy groceries");
|
|
assert!(!tasks[0].done);
|
|
|
|
complete_task(&pool, "task1").await.unwrap();
|
|
let tasks = list_tasks(&pool).await.unwrap();
|
|
assert!(tasks[0].done);
|
|
|
|
delete_task(&pool, "task1").await.unwrap();
|
|
let tasks = list_tasks(&pool).await.unwrap();
|
|
assert!(tasks.is_empty());
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn settings_crud_roundtrip() {
|
|
let pool = test_pool().await;
|
|
|
|
set_setting(&pool, "theme", "dark").await.unwrap();
|
|
let val = get_setting(&pool, "theme").await.unwrap();
|
|
assert_eq!(val.as_deref(), Some("dark"));
|
|
|
|
set_setting(&pool, "theme", "light").await.unwrap();
|
|
let val = get_setting(&pool, "theme").await.unwrap();
|
|
assert_eq!(val.as_deref(), Some("light"));
|
|
|
|
let missing = get_setting(&pool, "nonexistent").await.unwrap();
|
|
assert!(missing.is_none());
|
|
}
|
|
}
|