Initial upload: shell-history-semantic-search v0.1.0

src/shell_history_search/db/__init__.py

@@ -0,0 +1,91 @@
+import os
+import sqlite3
+from pathlib import Path
+from typing import Optional
+import logging
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_DB_PATH = Path.home() / ".local" / "share" / "shell_history_search" / "history.db"
+
+
+def get_db_path() -> Path:
+    return Path(os.environ.get("SHELL_HISTORY_DB", str(DEFAULT_DB_PATH)))
+
+
+def ensure_db_directory(db_path: Path) -> None:
+    db_path.parent.mkdir(parents=True, exist_ok=True)
+
+
+def get_connection(db_path: Optional[Path] = None) -> sqlite3.Connection:
+    if db_path is None:
+        db_path = get_db_path()
+
+    ensure_db_directory(db_path)
+
+    conn = sqlite3.connect(str(db_path), check_same_thread=False)
+    conn.row_factory = sqlite3.Row
+
+    conn.execute("PRAGMA journal_mode=WAL")
+    conn.execute("PRAGMA foreign_keys=ON")
+
+    return conn
+
+
+def init_database(db_path: Optional[Path] = None) -> sqlite3.Connection:
+    conn = get_connection(db_path)
+
+    conn.execute("""
+        CREATE TABLE IF NOT EXISTS commands (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            command TEXT NOT NULL,
+            shell_type TEXT NOT NULL,
+            timestamp INTEGER,
+            hostname TEXT,
+            command_hash TEXT UNIQUE NOT NULL,
+            created_at INTEGER DEFAULT (strftime('%s', 'now')),
+            indexed_at INTEGER
+        )
+    """)
+
+    conn.execute("""
+        CREATE INDEX IF NOT EXISTS idx_commands_hash ON commands(command_hash)
+    """)
+
+    conn.execute("""
+        CREATE INDEX IF NOT EXISTS idx_commands_shell ON commands(shell_type)
+    """)
+
+    conn.execute("""
+        CREATE INDEX IF NOT EXISTS idx_commands_timestamp ON commands(timestamp)
+    """)
+
+    conn.execute("""
+        CREATE TABLE IF NOT EXISTS embeddings (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            command_id INTEGER NOT NULL,
+            embedding BLOB NOT NULL,
+            model_name TEXT NOT NULL,
+            created_at INTEGER DEFAULT (strftime('%s', 'now')),
+            FOREIGN KEY (command_id) REFERENCES commands(id) ON DELETE CASCADE,
+            UNIQUE(command_id)
+        )
+    """)
+
+    conn.execute("""
+        CREATE INDEX IF NOT EXISTS idx_embeddings_command ON embeddings(command_id)
+    """)
+
+    conn.execute("""
+        CREATE TABLE IF NOT EXISTS index_state (
+            shell_type TEXT PRIMARY KEY,
+            last_indexed_at INTEGER,
+            last_indexed_hash TEXT
+        )
+    """)
+
+    conn.commit()
+
+    logger.info(f"Database initialized at {db_path}")
+
+    return conn