langchain/libs/community/tests/unit_tests/test_sql_database_schema.py
Bagatur a0c2281540
infra: update mypy 1.10, ruff 0.5 (#23721)
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path

import toml
import subprocess
import re

ROOT_DIR = Path(__file__).parents[1]


def main():
    for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
        print(path)
        with open(path, "rb") as f:
            pyproject = tomllib.load(f)
        try:
            pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
                "^1.10"
            )
            pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
                "^0.5"
            )
        except KeyError:
            continue
        with open(path, "w") as f:
            toml.dump(pyproject, f)
        cwd = "/".join(path.split("/")[:-1])
        completed = subprocess.run(
            "poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
            cwd=cwd,
            shell=True,
            capture_output=True,
            text=True,
        )
        logs = completed.stdout.split("\n")

        to_ignore = {}
        for l in logs:
            if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
                path, line_no, error_type = re.match(
                    "^(.*)\:(\d+)\: error:.*\[(.*)\]", l
                ).groups()
                if (path, line_no) in to_ignore:
                    to_ignore[(path, line_no)].append(error_type)
                else:
                    to_ignore[(path, line_no)] = [error_type]
        print(len(to_ignore))
        for (error_path, line_no), error_types in to_ignore.items():
            all_errors = ", ".join(error_types)
            full_path = f"{cwd}/{error_path}"
            try:
                with open(full_path, "r") as f:
                    file_lines = f.readlines()
            except FileNotFoundError:
                continue
            file_lines[int(line_no) - 1] = (
                file_lines[int(line_no) - 1][:-1] + f"  # type: ignore[{all_errors}]\n"
            )
            with open(full_path, "w") as f:
                f.write("".join(file_lines))

        subprocess.run(
            "poetry run ruff format .; poetry run ruff --select I --fix .",
            cwd=cwd,
            shell=True,
            capture_output=True,
            text=True,
        )


if __name__ == "__main__":
    main()

```
2024-07-03 10:33:27 -07:00

96 lines
2.7 KiB
Python

# flake8: noqa
"""Test SQL database wrapper with schema support.
Using DuckDB as SQLite does not support schemas.
"""
import pytest
from sqlalchemy import (
Column,
Integer,
MetaData,
Sequence,
String,
Table,
create_engine,
event,
insert,
schema,
)
from langchain_community.utilities.sql_database import SQLDatabase
metadata_obj = MetaData()
event.listen(metadata_obj, "before_create", schema.CreateSchema("schema_a"))
event.listen(metadata_obj, "before_create", schema.CreateSchema("schema_b"))
user = Table(
"user",
metadata_obj,
Column("user_id", Integer, Sequence("user_id_seq"), primary_key=True),
Column("user_name", String, nullable=False),
schema="schema_a",
)
company = Table(
"company",
metadata_obj,
Column("company_id", Integer, Sequence("company_id_seq"), primary_key=True),
Column("company_location", String, nullable=False),
schema="schema_b",
)
def test_table_info() -> None:
"""Test that table info is constructed properly."""
engine = create_engine("duckdb:///:memory:")
metadata_obj.create_all(engine)
db = SQLDatabase(engine, schema="schema_a", metadata=metadata_obj)
output = db.table_info
expected_output = """
CREATE TABLE schema_a."user" (
user_id INTEGER NOT NULL,
user_name VARCHAR NOT NULL,
PRIMARY KEY (user_id)
)
/*
3 rows from user table:
user_id user_name
*/
"""
assert sorted(" ".join(output.split())) == sorted(" ".join(expected_output.split()))
def test_sql_database_run() -> None:
"""Test that commands can be run successfully and returned in correct format."""
engine = create_engine("duckdb:///:memory:")
metadata_obj.create_all(engine)
stmt = insert(user).values(user_id=13, user_name="Harrison")
with engine.begin() as conn:
conn.execute(stmt)
with pytest.warns(Warning) as records:
db = SQLDatabase(engine, schema="schema_a")
# Metadata creation with duckdb raises 3 warnings at the moment about reflection.
# As a stop-gap to increase strictness of pytest to fail on warnings, we'll
# explicitly catch the warnings and assert that it's the one we expect.
# We may need to revisit at a later stage and determine why a warning is being
# raised here.
for record in records:
assert isinstance(record.message, Warning)
assert any(
record.message.args[0] # type: ignore
== "duckdb-engine doesn't yet support reflection on indices"
for record in records
)
command = 'select user_name from "user" where user_id = 13'
output = db.run(command)
expected_output = "[('Harrison',)]"
assert output == expected_output