Progress bar for sqlite-utils insert command, closes #173

docs/cli.rst

@@ -360,6 +360,8 @@ Data is expected to be encoded as Unicode UTF-8. If your data is an another char
 
     $ sqlite-utils insert dogs.db dogs docs.tsv --tsv --encoding=latin-1
 
+A progress bar is displayed when inserting data from a file. You can hide the progress bar using the ``--silent`` option.
+
 .. _cli_insert_replace:
 
 Insert-replacing data

sqlite_utils/cli.py

@@ -13,7 +13,7 @@ import os
 import sys
 import csv as csv_std
 import tabulate
-from .utils import find_spatialite, sqlite3, decode_base64_values
+from .utils import file_progress, find_spatialite, sqlite3, decode_base64_values
 
 VALID_COLUMN_TYPES = ("INTEGER", "TEXT", "FLOAT", "BLOB")
 
@@ -584,6 +584,7 @@ def insert_upsert_options(fn):
                 help="Character encoding for input, defaults to utf-8",
             ),
             load_extension_option,
+            click.option("--silent", is_flag=True, help="Do not show progress bar"),
         )
     ):
         fn = decorator(fn)
@@ -608,6 +609,7 @@ def insert_upsert_implementation(
     default=None,
     encoding=None,
     load_extension=None,
+    silent=False,
 ):
     db = sqlite_utils.Database(path)
     _load_extensions(db, load_extension)
@@ -621,9 +623,10 @@ def insert_upsert_implementation(
         pk = pk[0]
     if csv or tsv:
         dialect = "excel-tab" if tsv else "excel"
-        reader = csv_std.reader(json_file, dialect=dialect)
-        headers = next(reader)
-        docs = (dict(zip(headers, row)) for row in reader)
+        with file_progress(json_file, silent=silent) as json_file:
+            reader = csv_std.reader(json_file, dialect=dialect)
+            headers = next(reader)
+            docs = (dict(zip(headers, row)) for row in reader)
     elif nl:
         docs = (json.loads(line) for line in json_file)
     else:
@@ -673,6 +676,7 @@ def insert(
     alter,
     encoding,
     load_extension,
+    silent,
     ignore,
     replace,
     truncate,
@@ -702,6 +706,7 @@ def insert(
             truncate=truncate,
             encoding=encoding,
             load_extension=load_extension,
+            silent=silent,
             not_null=not_null,
             default=default,
         )
@@ -725,6 +730,7 @@ def upsert(
     default,
     encoding,
     load_extension,
+    silent,
 ):
     """
     Upsert records based on their primary key. Works like 'insert' but if
@@ -747,6 +753,7 @@ def upsert(
             default=default,
             encoding=encoding,
             load_extension=load_extension,
+            silent=silent,
         )
     except UnicodeDecodeError as ex:
         raise click.ClickException(UNICODE_ERROR.format(ex))

sqlite_utils/utils.py

@@ -1,4 +1,7 @@
 import base64
+import click
+import contextlib
+import io
 import os
 
 try:
@@ -87,3 +90,24 @@ def find_spatialite():
         if os.path.exists(path):
             return path
     return None
+
+
+class UpdateWrapper:
+    def __init__(self, wrapped, update):
+        self._wrapped = wrapped
+        self._update = update
+
+    def __iter__(self):
+        for line in self._wrapped:
+            self._update(len(line))
+            yield line
+
+
+@contextlib.contextmanager
+def file_progress(file, silent=False, **kwargs):
+    if silent or file.raw.fileno() == 0:  # 0 = stdin
+        yield file
+    else:
+        file_length = os.path.getsize(file.raw.name)
+        with click.progressbar(length=file_length, **kwargs) as bar:
+            yield UpdateWrapper(file, bar.update)

tests/test_cli.py

@@ -1640,7 +1640,9 @@ def test_insert_encoding(tmpdir):
     open(csv_path, "wb").write(latin1_csv)
     # First attempt should error:
     bad_result = CliRunner().invoke(
-        cli.cli, ["insert", db_path, "places", csv_path, "--csv"]
+        cli.cli,
+        ["insert", db_path, "places", csv_path, "--csv"],
+        catch_exceptions=False,
     )
     assert bad_result.exit_code == 1
     assert (
@@ -1651,6 +1653,7 @@ def test_insert_encoding(tmpdir):
     good_result = CliRunner().invoke(
         cli.cli,
         ["insert", db_path, "places", csv_path, "--encoding", "latin-1", "--csv"],
+        catch_exceptions=False,
     )
     assert good_result.exit_code == 0
     db = Database(db_path)