From 231224ba1a4de42f3d3885a0accd05dcf85570e7 Mon Sep 17 00:00:00 2001
From: Simon Willison <swillison@gmail.com>
Date: Thu, 24 Jan 2019 19:39:04 -0800
Subject: [PATCH] Added vacuum to CLI and Python API

---
 docs/cli.rst         |  7 +++++++
 docs/python-api.rst  |  9 +++++++++
 sqlite_utils/cli.py  | 11 +++++++++++
 sqlite_utils/db.py   |  3 +++
 tests/test_cli.py    |  5 +++++
 tests/test_create.py |  5 +++++
 6 files changed, 40 insertions(+)

diff --git a/docs/cli.rst b/docs/cli.rst
index cf46853..93b343a 100644
--- a/docs/cli.rst
+++ b/docs/cli.rst
@@ -15,3 +15,10 @@ You can list the names of tables in a database using the ``table_names`` subcomm
     dogs
     cats
     chickens
+
+Vacuum
+======
+
+You can run VACUUM to optimize your database like so::
+
+    $ sqlite-utils vacuum mydb.db
diff --git a/docs/python-api.rst b/docs/python-api.rst
index 194a309..b3a29a5 100644
--- a/docs/python-api.rst
+++ b/docs/python-api.rst
@@ -313,3 +313,12 @@ By default the index will be named ``idx_{table-name}_{columns}`` - if you want
         ["is_good_dog", "age"],
         index_name="good_dogs_by_age"
     )
+
+Vacuum
+======
+
+You can optimize your database by running VACUUM against it like so:
+
+.. code-block:: python
+
+    Database("my_database.py").vacuum()
diff --git a/sqlite_utils/cli.py b/sqlite_utils/cli.py
index 8b252e4..1a86379 100644
--- a/sqlite_utils/cli.py
+++ b/sqlite_utils/cli.py
@@ -20,3 +20,14 @@ def table_names(path):
     db = sqlite_utils.Database(path)
     for name in db.table_names:
         print(name)
+
+
+@cli.command()
+@click.argument(
+    "path",
+    type=click.Path(exists=True, file_okay=True, dir_okay=False, allow_dash=False),
+    required=True,
+)
+def vacuum(path):
+    """Run VACUUM against the database"""
+    sqlite_utils.Database(path).vacuum()
diff --git a/sqlite_utils/db.py b/sqlite_utils/db.py
index 4127057..ae8c57c 100644
--- a/sqlite_utils/db.py
+++ b/sqlite_utils/db.py
@@ -98,6 +98,9 @@ class Database:
             )
         )
 
+    def vacuum(self):
+        self.conn.execute("VACUUM;")
+
 
 class Table:
     def __init__(self, db, name):
diff --git a/tests/test_cli.py b/tests/test_cli.py
index 8b8c061..f24ddb1 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -21,3 +21,8 @@ def db_path(tmpdir):
 def test_table_names(db_path):
     result = CliRunner().invoke(cli.cli, ["table_names", db_path])
     assert "Gosh\nGosh2" == result.output.strip()
+
+
+def test_vacuum(db_path):
+    result = CliRunner().invoke(cli.cli, ["vacuum", db_path])
+    assert 0 == result.exit_code
diff --git a/tests/test_create.py b/tests/test_create.py
index 82eb7ed..af0c39f 100644
--- a/tests/test_create.py
+++ b/tests/test_create.py
@@ -176,3 +176,8 @@ def test_create_view(fresh_db):
     fresh_db.create_view("bar", "select bar from data")
     rows = fresh_db.conn.execute("select * from bar").fetchall()
     assert [("bar",)] == rows
+
+
+def test_vacuum(fresh_db):
+    fresh_db["data"].insert({"foo": "foo", "bar": "bar"})
+    fresh_db.vacuum()