sqlite-utils 3.36__tar.gz → 3.37__tar.gz

{sqlite-utils-3.36/sqlite_utils.egg-info → sqlite_utils-3.37}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlite-utils
-Version: 3.36
+Version: 3.37
 Summary: CLI tool and Python library for manipulating SQLite databases
 Home-page: https://github.com/simonw/sqlite-utils
 Author: Simon Willison
@@ -16,13 +16,13 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: End Users/Desktop
 Classifier: Topic :: Database
 Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Python: >=3.7
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: sqlite-fts4
@@ -33,7 +33,7 @@ Requires-Dist: python-dateutil
 Requires-Dist: pluggy
 Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
-Requires-Dist: black; extra == "test"
+Requires-Dist: black>=24.1.1; extra == "test"
 Requires-Dist: hypothesis; extra == "test"
 Requires-Dist: cogapp; extra == "test"
 Provides-Extra: docs

{sqlite-utils-3.36 → sqlite_utils-3.37}/docs/changelog.rst

@@ -4,6 +4,15 @@
  Changelog
 ===========
 
+.. _v3_37:
+
+3.37 (2024-07-18)
+-----------------
+
+- The ``create-table`` and ``insert-files`` commands all now accept multiple ``--pk`` options for compound primary keys. (:issue:`620`)
+- Now tested against Python 3.13 pre-release. (`#619 <https://github.com/simonw/sqlite-utils/pull/619>`__)
+- Fixed a crash that can occur in environments with a broken ``numpy`` installation, producing a ``module 'numpy' has no attribute 'int8'``. (:issue:`632`)
+
 .. _v3_36:
 
 3.36 (2023-12-07)

{sqlite-utils-3.36 → sqlite_utils-3.37}/docs/cli-reference.rst

@@ -85,6 +85,7 @@ This page lists the ``--help`` for every ``sqlite-utils`` CLI sub-command.
         cog.out("::\n\n")
         result = CliRunner().invoke(cli.cli, [command, "--help"])
         output = result.output.replace("Usage: cli ", "Usage: sqlite-utils ")
+        output = output.replace('\b', '')
         cog.out(textwrap.indent(output, '    '))
         cog.out("\n\n")
 .. ]]]
@@ -603,9 +604,9 @@ See :ref:`cli_convert`.
 
       Convert columns using Python code you supply. For example:
 
-          sqlite-utils convert my.db mytable mycolumn \
-              '"\n".join(textwrap.wrap(value, 10))' \
-              --import=textwrap
+      sqlite-utils convert my.db mytable mycolumn \
+          '"\n".join(textwrap.wrap(value, 10))' \
+          --import=textwrap
 
       "value" is a variable with the column value to be converted.
 
@@ -615,30 +616,30 @@ See :ref:`cli_convert`.
 
       r.jsonsplit(value, delimiter=',', type=<class 'str'>)
 
-          Convert a string like a,b,c into a JSON array ["a", "b", "c"]
+      Convert a string like a,b,c into a JSON array ["a", "b", "c"]
 
       r.parsedate(value, dayfirst=False, yearfirst=False, errors=None)
 
-          Parse a date and convert it to ISO date format: yyyy-mm-dd
-          
-          - dayfirst=True: treat xx as the day in xx/yy/zz
-          - yearfirst=True: treat xx as the year in xx/yy/zz
-          - errors=r.IGNORE to ignore values that cannot be parsed
-          - errors=r.SET_NULL to set values that cannot be parsed to null
+      Parse a date and convert it to ISO date format: yyyy-mm-dd
+  
+      - dayfirst=True: treat xx as the day in xx/yy/zz
+      - yearfirst=True: treat xx as the year in xx/yy/zz
+      - errors=r.IGNORE to ignore values that cannot be parsed
+      - errors=r.SET_NULL to set values that cannot be parsed to null
 
       r.parsedatetime(value, dayfirst=False, yearfirst=False, errors=None)
 
-          Parse a datetime and convert it to ISO datetime format: yyyy-mm-ddTHH:MM:SS
-          
-          - dayfirst=True: treat xx as the day in xx/yy/zz
-          - yearfirst=True: treat xx as the year in xx/yy/zz
-          - errors=r.IGNORE to ignore values that cannot be parsed
-          - errors=r.SET_NULL to set values that cannot be parsed to null
+      Parse a datetime and convert it to ISO datetime format: yyyy-mm-ddTHH:MM:SS
+  
+      - dayfirst=True: treat xx as the day in xx/yy/zz
+      - yearfirst=True: treat xx as the year in xx/yy/zz
+      - errors=r.IGNORE to ignore values that cannot be parsed
+      - errors=r.SET_NULL to set values that cannot be parsed to null
 
       You can use these recipes like so:
 
-          sqlite-utils convert my.db mytable mycolumn \
-              'r.jsonsplit(value, delimiter=":")'
+      sqlite-utils convert my.db mytable mycolumn \
+          'r.jsonsplit(value, delimiter=":")'
 
     Options:
       --import TEXT                   Python modules to import

{sqlite-utils-3.36 → sqlite_utils-3.37}/docs/cli.rst

@@ -1088,11 +1088,13 @@ You can import all three records into an automatically created ``dogs`` table an
 
     sqlite-utils insert dogs.db dogs dogs.json --pk=id
 
+Pass ``--pk`` multiple times to define a compound primary key.
+
 You can skip inserting any records that have a primary key that already exists using ``--ignore``:
 
 .. code-block:: bash
 
-    sqlite-utils insert dogs.db dogs dogs.json --ignore
+    sqlite-utils insert dogs.db dogs dogs.json --pk=id --ignore
 
 You can delete all the existing rows in the table before inserting the new records using ``--truncate``:
 
@@ -1909,6 +1911,8 @@ This will create a table called ``mytable`` with two columns - an integer ``id``
 
 You can pass as many column-name column-type pairs as you like. Valid types are ``integer``, ``text``, ``float`` and ``blob``.
 
+Pass ``--pk`` more than once for a compound primary key that covers multiple columns.
+
 You can specify columns that should be NOT NULL using ``--not-null colname``. You can specify default values for columns using ``--default colname defaultvalue``.
 
 .. code-block:: bash

{sqlite-utils-3.36 → sqlite_utils-3.37}/docs/python-api.rst

@@ -890,7 +890,8 @@ You can delete all records in a table that match a specific WHERE statement usin
 
     >>> db = sqlite_utils.Database("dogs.db")
     >>> # Delete every dog with age less than 3
-    >>> db["dogs"].delete_where("age < ?", [3])
+    >>> with db.conn:
+    >>>     db["dogs"].delete_where("age < ?", [3])
 
 Calling ``table.delete_where()`` with no other arguments will delete every row in the table.
 
@@ -2177,7 +2178,7 @@ The ``.has_counts_triggers`` property shows if a table has been configured with
     >>> db["authors"].has_counts_triggers
     True
 
-.. _python_api_introspection_supports_strict
+.. _python_api_introspection_supports_strict:
 
 db.supports_strict
 ------------------

{sqlite-utils-3.36 → sqlite_utils-3.37}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 import io
 import os
 
-VERSION = "3.36"
+VERSION = "3.37"
 
 
 def get_long_description():
@@ -32,7 +32,7 @@ setup(
         "pluggy",
     ],
     extras_require={
-        "test": ["pytest", "black", "hypothesis", "cogapp"],
+        "test": ["pytest", "black>=24.1.1", "hypothesis", "cogapp"],
         "docs": [
             "furo",
             "sphinx-autobuild",
@@ -64,7 +64,7 @@ setup(
         "Issues": "https://github.com/simonw/sqlite-utils/issues",
         "CI": "https://github.com/simonw/sqlite-utils/actions",
     },
-    python_requires=">=3.7",
+    python_requires=">=3.8",
     classifiers=[
         "Development Status :: 5 - Production/Stable",
         "Intended Audience :: Developers",
@@ -72,12 +72,12 @@ setup(
         "Intended Audience :: End Users/Desktop",
         "Topic :: Database",
         "License :: OSI Approved :: Apache Software License",
-        "Programming Language :: Python :: 3.7",
         "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
         "Programming Language :: Python :: 3.12",
+        "Programming Language :: Python :: 3.13",
     ],
     # Needed to bundle py.typed so mypy can see it:
     zip_safe=False,

{sqlite-utils-3.36 → sqlite_utils-3.37}/sqlite_utils/cli.py

@@ -1489,7 +1489,7 @@ def create_database(path, enable_wal, init_spatialite, load_extension):
 )
 @click.argument("table")
 @click.argument("columns", nargs=-1, required=True)
-@click.option("--pk", help="Column to use as primary key")
+@click.option("pks", "--pk", help="Column to use as primary key", multiple=True)
 @click.option(
     "--not-null",
     multiple=True,
@@ -1532,7 +1532,7 @@ def create_table(
     path,
     table,
     columns,
-    pk,
+    pks,
     not_null,
     default,
     fk,
@@ -1581,7 +1581,7 @@ def create_table(
             )
     db[table].create(
         coltypes,
-        pk=pk,
+        pk=pks[0] if len(pks) == 1 else pks,
         not_null=not_null,
         defaults=dict(default),
         foreign_keys=fk,
@@ -2594,7 +2594,7 @@ def extract(
     multiple=True,
     help="Column definitions for the table",
 )
-@click.option("--pk", type=str, help="Column to use as primary key")
+@click.option("pks", "--pk", help="Column to use as primary key", multiple=True)
 @click.option("--alter", is_flag=True, help="Alter table to add missing columns")
 @click.option("--replace", is_flag=True, help="Replace files with matching primary key")
 @click.option("--upsert", is_flag=True, help="Upsert files with matching primary key")
@@ -2611,7 +2611,7 @@ def insert_files(
     table,
     file_or_dir,
     column,
-    pk,
+    pks,
     alter,
     replace,
     upsert,
@@ -2641,8 +2641,8 @@ def insert_files(
             column = ["path:path", "content_text:content_text", "size:size"]
         else:
             column = ["path:path", "content:content", "size:size"]
-        if not pk:
-            pk = "path"
+        if not pks:
+            pks = ["path"]
 
     def yield_paths_and_relative_paths():
         for f_or_d in file_or_dir:
@@ -2712,7 +2712,11 @@ def insert_files(
         try:
             with db.conn:
                 db[table].insert_all(
-                    to_insert(), pk=pk, alter=alter, replace=replace, upsert=upsert
+                    to_insert(),
+                    pk=pks[0] if len(pks) == 1 else pks,
+                    alter=alter,
+                    replace=replace,
+                    upsert=upsert,
                 )
         except UnicodeDecodeErrorForPath as e:
             raise click.ClickException(
@@ -2871,9 +2875,9 @@ def _generate_convert_help():
     Convert columns using Python code you supply. For example:
 
     \b
-        sqlite-utils convert my.db mytable mycolumn \\
-            '"\\n".join(textwrap.wrap(value, 10))' \\
-            --import=textwrap
+    sqlite-utils convert my.db mytable mycolumn \\
+        '"\\n".join(textwrap.wrap(value, 10))' \\
+        --import=textwrap
 
     "value" is a variable with the column value to be converted.
 
@@ -2892,7 +2896,7 @@ def _generate_convert_help():
     for name in recipe_names:
         fn = getattr(recipes, name)
         help += "\n\nr.{}{}\n\n\b{}".format(
-            name, str(inspect.signature(fn)), fn.__doc__.rstrip()
+            name, str(inspect.signature(fn)), textwrap.dedent(fn.__doc__.rstrip())
         )
     help += "\n\n"
     help += textwrap.dedent(
@@ -2900,8 +2904,8 @@ def _generate_convert_help():
     You can use these recipes like so:
 
     \b
-        sqlite-utils convert my.db mytable mycolumn \\
-            'r.jsonsplit(value, delimiter=":")'
+    sqlite-utils convert my.db mytable mycolumn \\
+        'r.jsonsplit(value, delimiter=":")'
     """
     ).strip()
     return help

{sqlite-utils-3.36 → sqlite_utils-3.37}/sqlite_utils/db.py

@@ -206,21 +206,25 @@ COLUMN_TYPE_MAPPING = {
 }
 # If numpy is available, add more types
 if np:
-    COLUMN_TYPE_MAPPING.update(
-        {
-            np.int8: "INTEGER",
-            np.int16: "INTEGER",
-            np.int32: "INTEGER",
-            np.int64: "INTEGER",
-            np.uint8: "INTEGER",
-            np.uint16: "INTEGER",
-            np.uint32: "INTEGER",
-            np.uint64: "INTEGER",
-            np.float16: "FLOAT",
-            np.float32: "FLOAT",
-            np.float64: "FLOAT",
-        }
-    )
+    try:
+        COLUMN_TYPE_MAPPING.update(
+            {
+                np.int8: "INTEGER",
+                np.int16: "INTEGER",
+                np.int32: "INTEGER",
+                np.int64: "INTEGER",
+                np.uint8: "INTEGER",
+                np.uint16: "INTEGER",
+                np.uint32: "INTEGER",
+                np.uint64: "INTEGER",
+                np.float16: "FLOAT",
+                np.float32: "FLOAT",
+                np.float64: "FLOAT",
+            }
+        )
+    except AttributeError:
+        # https://github.com/simonw/sqlite-utils/issues/632
+        pass
 
 # If pandas is available, add more types
 if pd:
@@ -457,8 +461,7 @@ class Database:
                         fn_name, arity, fn, **dict(kwargs, deterministic=True)
                     )
                     registered = True
-                except (sqlite3.NotSupportedError, TypeError):
-                    # TypeError is Python 3.7 "function takes at most 3 arguments"
+                except sqlite3.NotSupportedError:
                     pass
             if not registered:
                 self.conn.create_function(fn_name, arity, fn, **kwargs)
@@ -930,9 +933,9 @@ class Database:
                 "   [{column_name}] {column_type}{column_extras}".format(
                     column_name=column_name,
                     column_type=COLUMN_TYPE_MAPPING[column_type],
-                    column_extras=(" " + " ".join(column_extras))
-                    if column_extras
-                    else "",
+                    column_extras=(
+                        (" " + " ".join(column_extras)) if column_extras else ""
+                    ),
                 )
             )
         extra_pk = ""
@@ -1481,9 +1484,11 @@ class Table(Queryable):
     def __repr__(self) -> str:
         return "<Table {}{}>".format(
             self.name,
-            " (does not exist yet)"
-            if not self.exists()
-            else " ({})".format(", ".join(c.name for c in self.columns)),
+            (
+                " (does not exist yet)"
+                if not self.exists()
+                else " ({})".format(", ".join(c.name for c in self.columns))
+            ),
         )
 
     @property
@@ -2940,9 +2945,11 @@ class Table(Queryable):
                 value = jsonify_if_needed(
                     record.get(
                         key,
-                        None
-                        if key != hash_id
-                        else hash_record(record, hash_id_columns),
+                        (
+                            None
+                            if key != hash_id
+                            else hash_record(record, hash_id_columns)
+                        ),
                     )
                 )
                 if key in extracts:

{sqlite-utils-3.36 → sqlite_utils-3.37}/sqlite_utils/utils.py

@@ -304,10 +304,7 @@ def rows_from_file(
         rows = rows_from_file(
             fp, format=Format.CSV, dialect=csv.excel_tab, encoding=encoding
         )[0]
-        return (
-            _extra_key_strategy(rows, ignore_extras, extras_key),
-            Format.TSV,
-        )
+        return _extra_key_strategy(rows, ignore_extras, extras_key), Format.TSV
     elif format is None:
         # Detect the format, then call this recursively
         buffered = io.BufferedReader(cast(io.RawIOBase, fp), buffer_size=4096)

{sqlite-utils-3.36 → sqlite_utils-3.37/sqlite_utils.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlite-utils
-Version: 3.36
+Version: 3.37
 Summary: CLI tool and Python library for manipulating SQLite databases
 Home-page: https://github.com/simonw/sqlite-utils
 Author: Simon Willison
@@ -16,13 +16,13 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: End Users/Desktop
 Classifier: Topic :: Database
 Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Python: >=3.7
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: sqlite-fts4
@@ -33,7 +33,7 @@ Requires-Dist: python-dateutil
 Requires-Dist: pluggy
 Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
-Requires-Dist: black; extra == "test"
+Requires-Dist: black>=24.1.1; extra == "test"
 Requires-Dist: hypothesis; extra == "test"
 Requires-Dist: cogapp; extra == "test"
 Provides-Extra: docs

{sqlite-utils-3.36 → sqlite_utils-3.37}/sqlite_utils.egg-info/requires.txt

@@ -26,7 +26,7 @@ data-science-types
 
 [test]
 pytest
-black
+black>=24.1.1
 hypothesis
 cogapp
 

{sqlite-utils-3.36 → sqlite_utils-3.37}/tests/test_cli.py

@@ -1180,6 +1180,14 @@ def test_upsert_alter(db_path, tmpdir):
             ["age", "integer", "--default", "age", "3"],
             ("CREATE TABLE [t] (\n" "   [age] INTEGER DEFAULT '3'\n" ")"),
         ),
+        # Compound primary key
+        (
+            ["category", "text", "name", "text", "--pk", "category", "--pk", "name"],
+            (
+                "CREATE TABLE [t] (\n   [category] TEXT,\n   [name] TEXT,\n"
+                "   PRIMARY KEY ([category], [name])\n)"
+            ),
+        ),
     ],
 )
 def test_create_table(args, schema):
@@ -2082,11 +2090,10 @@ def test_schema(tmpdir, options, expected):
 def test_long_csv_column_value(tmpdir):
     db_path = str(tmpdir / "test.db")
     csv_path = str(tmpdir / "test.csv")
-    csv_file = open(csv_path, "w")
-    long_string = "a" * 131073
-    csv_file.write("id,text\n")
-    csv_file.write("1,{}\n".format(long_string))
-    csv_file.close()
+    with open(csv_path, "w") as csv_file:
+        long_string = "a" * 131073
+        csv_file.write("id,text\n")
+        csv_file.write("1,{}\n".format(long_string))
     result = CliRunner().invoke(
         cli.cli,
         ["insert", db_path, "bigtable", csv_path, "--csv"],
@@ -2110,11 +2117,10 @@ def test_long_csv_column_value(tmpdir):
 def test_import_no_headers(tmpdir, args, tsv):
     db_path = str(tmpdir / "test.db")
     csv_path = str(tmpdir / "test.csv")
-    csv_file = open(csv_path, "w")
-    sep = "\t" if tsv else ","
-    csv_file.write("Cleo{sep}Dog{sep}5\n".format(sep=sep))
-    csv_file.write("Tracy{sep}Spider{sep}7\n".format(sep=sep))
-    csv_file.close()
+    with open(csv_path, "w") as csv_file:
+        sep = "\t" if tsv else ","
+        csv_file.write("Cleo{sep}Dog{sep}5\n".format(sep=sep))
+        csv_file.write("Tracy{sep}Spider{sep}7\n".format(sep=sep))
     result = CliRunner().invoke(
         cli.cli,
         ["insert", db_path, "creatures", csv_path] + args,

{sqlite-utils-3.36 → sqlite_utils-3.37}/tests/test_cli_insert.py

@@ -77,19 +77,24 @@ def test_insert_json_flatten_nl(tmpdir):
     ]
 
 
-def test_insert_with_primary_key(db_path, tmpdir):
+@pytest.mark.parametrize(
+    "args,expected_pks",
+    (
+        (["--pk", "id"], ["id"]),
+        (["--pk", "id", "--pk", "name"], ["id", "name"]),
+    ),
+)
+def test_insert_with_primary_keys(db_path, tmpdir, args, expected_pks):
     json_path = str(tmpdir / "dog.json")
     with open(json_path, "w") as fp:
         fp.write(json.dumps({"id": 1, "name": "Cleo", "age": 4}))
-    result = CliRunner().invoke(
-        cli.cli, ["insert", db_path, "dogs", json_path, "--pk", "id"]
-    )
+    result = CliRunner().invoke(cli.cli, ["insert", db_path, "dogs", json_path] + args)
     assert result.exit_code == 0
     assert [{"id": 1, "age": 4, "name": "Cleo"}] == list(
         Database(db_path).query("select * from dogs")
     )
     db = Database(db_path)
-    assert ["id"] == db["dogs"].pks
+    assert db["dogs"].pks == expected_pks
 
 
 def test_insert_multiple_with_primary_key(db_path, tmpdir):

{sqlite-utils-3.36 → sqlite_utils-3.37}/tests/test_insert_files.py

@@ -7,7 +7,14 @@ import sys
 
 
 @pytest.mark.parametrize("silent", (False, True))
-def test_insert_files(silent):
+@pytest.mark.parametrize(
+    "pk_args,expected_pks",
+    (
+        (["--pk", "path"], ["path"]),
+        (["--pk", "path", "--pk", "name"], ["path", "name"]),
+    ),
+)
+def test_insert_files(silent, pk_args, expected_pks):
     runner = CliRunner()
     with runner.isolated_filesystem():
         tmpdir = pathlib.Path(".")
@@ -42,7 +49,7 @@ def test_insert_files(silent):
             cli.cli,
             ["insert-files", db_path, "files", str(tmpdir)]
             + cols
-            + ["--pk", "path"]
+            + pk_args
             + (["--silent"] if silent else []),
             catch_exceptions=False,
         )
@@ -105,6 +112,7 @@ def test_insert_files(silent):
         for colname, expected_type in expected_types.items():
             for row in (one, two, three):
                 assert isinstance(row[colname], expected_type)
+        assert set(db["files"].pks) == set(expected_pks)
 
 
 @pytest.mark.parametrize(