sqlite-utils memory --analyze, closes #320

Author: simonw

docs/cli.rst

@@ -328,10 +328,10 @@ The CSV data that was piped into the script is available in the ``stdin`` table,
 
 .. _cli_memory_schema_dump_save:
 
-\-\-schema, \-\-dump and \-\-save
----------------------------------
+\-\-schema, \-\-analyze, \-\-dump and \-\-save
+----------------------------------------------
 
-To see the schema that will be created for a file or multiple files, use ``--schema``::
+To see the in-memory datbase schema that would be used for a file or for multiple files, use ``--schema``::
 
     % sqlite-utils memory dogs.csv --schema
     CREATE TABLE [dogs] (
@@ -342,6 +342,33 @@ To see the schema that will be created for a file or multiple files, use ``--sch
     CREATE VIEW t1 AS select * from [dogs];
     CREATE VIEW t AS select * from [dogs];
 
+You can run the equivalent of the :ref:`analyze-tables <cli_analyze_tables>` command using ``--analyze``::
+
+    % sqlite-utils memory dogs.csv --analyze
+    dogs.id: (1/3)
+
+      Total rows: 2
+      Null rows: 0
+      Blank rows: 0
+
+      Distinct values: 2
+
+    dogs.name: (2/3)
+
+      Total rows: 2
+      Null rows: 0
+      Blank rows: 0
+
+      Distinct values: 2
+
+    dogs.age: (3/3)
+
+      Total rows: 2
+      Null rows: 0
+      Blank rows: 0
+
+      Distinct values: 2
+
 You can output SQL that will both create the tables and insert the full data used to populate the in-memory database using ``--dump``::
 
     % sqlite-utils memory dogs.csv --dump

sqlite_utils/cli.py

@@ -1216,6 +1216,11 @@ def query(
     type=click.Path(file_okay=True, dir_okay=False, allow_dash=False),
     help="Save in-memory database to this file",
 )
+@click.option(
+    "--analyze",
+    is_flag=True,
+    help="Analyze resulting tables and output results",
+)
 @load_extension_option
 def memory(
     paths,
@@ -1236,6 +1241,7 @@ def memory(
     schema,
     dump,
     save,
+    analyze,
     load_extension,
 ):
     """Execute SQL query against an in-memory database, optionally populated by imported data
@@ -1265,8 +1271,8 @@ def memory(
         sqlite-utils memory animals.csv --schema
     """
     db = sqlite_utils.Database(memory=True)
-    # If --dump or --save used but no paths detected, assume SQL query is a path:
-    if (dump or save or schema) and not paths:
+    # If --dump or --save or --analyze used but no paths detected, assume SQL query is a path:
+    if (dump or save or schema or analyze) and not paths:
         paths = [sql]
         sql = None
     for i, path in enumerate(paths):
@@ -1299,6 +1305,10 @@ def memory(
             if not db[view_name].exists():
                 db.create_view(view_name, "select * from [{}]".format(csv_table))
 
+    if analyze:
+        _analyze(db, tables=None, columns=None, save=False)
+        return
+
     if dump:
         for line in db.conn.iterdump():
             click.echo(line)
@@ -1922,6 +1932,10 @@ def analyze_tables(
     "Analyze the columns in one or more tables"
     db = sqlite_utils.Database(path)
     _load_extensions(db, load_extension)
+    _analyze(db, tables, columns, save)
+
+
+def _analyze(db, tables, columns, save):
     if not tables:
         tables = db.table_names()
     todo = []

tests/test_cli_memory.py

@@ -220,3 +220,24 @@ def test_memory_no_detect_types(option):
         {"id": "1", "name": "Cleo", "weight": "45.5"},
         {"id": "2", "name": "Bants", "weight": "3.5"},
     ]
+
+
+def test_memory_analyze():
+    result = CliRunner().invoke(
+        cli.cli,
+        ["memory", "-", "--analyze"],
+        input="id,name\n1,Cleo\n2,Bants",
+    )
+    assert result.exit_code == 0
+    assert result.output == (
+        "stdin.id: (1/2)\n\n"
+        "  Total rows: 2\n"
+        "  Null rows: 0\n"
+        "  Blank rows: 0\n\n"
+        "  Distinct values: 2\n\n"
+        "stdin.name: (2/2)\n\n"
+        "  Total rows: 2\n"
+        "  Null rows: 0\n"
+        "  Blank rows: 0\n\n"
+        "  Distinct values: 2\n\n"
+    )