pyproject.toml

[project]
name = "sqlmesh"
dynamic = ["version"]
description = "Next-generation data transformation framework"
readme = "README.md"
authors = [{ name = "TobikoData Inc.", email = "engineering@tobikodata.com" }]
license = { file = "LICENSE" }
requires-python = ">= 3.9"
dependencies = [
    "astor",
    "click",
    "croniter",
    "duckdb>=0.10.0,!=0.10.3",
    "dateparser<=1.2.1",
    "humanize",
    "hyperscript>=0.1.0",
    "importlib-metadata; python_version<'3.12'",
    "ipywidgets",
    "jinja2",
    "packaging",
    "pandas<3.0.0",
    "pydantic>=2.0.0",
    "python-dotenv",
    "requests",
    "rich[jupyter]",
    "ruamel.yaml",
    "sqlglot[rs]~=28.10.1",
    "tenacity",
    "time-machine",
    "json-stream"
]
classifiers = [
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: Apache Software License",
    "Operating System :: OS Independent",
    "Programming Language :: SQL",
    "Programming Language :: Python :: 3 :: Only",
]

[project.optional-dependencies]
athena = ["PyAthena[Pandas]"]
azuresql = ["pymssql"]
azuresql-odbc = ["pyodbc>=5.0.0"]
bigquery = [
    "google-cloud-bigquery[pandas]",
    "google-cloud-bigquery-storage"
]
# bigframes has to be separate to support environments with an older google-cloud-bigquery pin
# this is because that pin pulls in an older bigframes and the bigframes team
# pinned an older SQLGlot which is incompatible with SQLMesh
bigframes = ["bigframes>=1.32.0"]
clickhouse = ["clickhouse-connect"]
databricks = ["databricks-sql-connector[pyarrow]"]
dev = [
    "agate",
    "beautifulsoup4",
    "clickhouse-connect",
    "cryptography",
    "databricks-sql-connector",
    "dbt-bigquery",
    "dbt-core",
    "dbt-duckdb>=1.7.1",
    # version 1.10.1 of dbt-snowflake declares that it's compatible with dbt-adapters>=1.16 but in reality
    # it depends on the 'InvalidCatalogIntegrationConfigError' class that only exists as of dbt-adapters==1.16.6
    # so we exclude it to prevent failures and hope that upstream releases a new version with the correct constraint
    "dbt-snowflake!=1.10.1",
    "dbt-athena-community",
    "dbt-clickhouse",
    "dbt-databricks",
    "dbt-redshift",
    "dbt-trino",
    "Faker",
    "google-auth",
    "google-cloud-bigquery",
    "google-cloud-bigquery-storage",
    "httpx",
    "mypy~=1.13.0",
    "numpy",
    "pandas-stubs",
    "pre-commit",
    "psycopg2-binary",
    "pydantic",
    "PyAthena[Pandas]",
    "PyGithub>=2.6.0",
    "pyodbc>=5.0.0",
    "pyperf",
    "pyspark~=3.5.0",
    "pytest",
    "pytest-asyncio",
    "pytest-mock",
    "pytest-rerunfailures",
    "pytest-xdist",
    "pytz",
    "redshift_connector",
    "ruff~=0.11.0",
    "snowflake-connector-python[pandas,secure-local-storage]>=3.0.2",
    "sqlalchemy-stubs",
    "trino",
    "types-croniter",
    "types-dateparser",
    "types-PyMySQL",
    "types-python-dateutil",
    "types-pytz",
    "types-requests==2.28.8",
    "typing-extensions",
]
dbt = ["dbt-core<2"]
dlt = ["dlt"]
duckdb = []
fabric = ["pyodbc>=5.0.0"]
gcppostgres = ["cloud-sql-python-connector[pg8000]>=1.8.0"]
github = ["PyGithub>=2.6.0"]
motherduck = ["duckdb>=1.3.2"]
mssql = ["pymssql"]
mssql-odbc = ["pyodbc>=5.0.0"]
mysql = ["pymysql"]
mwaa = ["boto3"]
postgres = ["psycopg2"]
redshift = ["redshift_connector"]
slack = ["slack_sdk"]
snowflake = [
    "cryptography",
    "snowflake-connector-python[pandas,secure-local-storage]",
    "snowflake-snowpark-python",
]
trino = ["trino"]
web = [
    "fastapi==0.120.1",
    "watchfiles>=0.19.0",
    "uvicorn[standard]==0.22.0",
    "sse-starlette>=0.2.2",
    "pyarrow",
]
lsp = [
    # Duplicate of web
    "fastapi==0.120.1",
    "watchfiles>=0.19.0",
    # "uvicorn[standard]==0.22.0",
    "sse-starlette>=0.2.2",
    "pyarrow",
    # For lsp
    "pygls>=1.2.0,<2.0.0",
    "lsprotocol",
]
risingwave = ["psycopg2"]

[project.scripts]
sqlmesh = "sqlmesh.cli.main:cli"
sqlmesh_dbt = "sqlmesh_dbt.cli:dbt"
sqlmesh_cicd = "sqlmesh.cicd.bot:bot"
sqlmesh_lsp = "sqlmesh.lsp.main:main"

[project.urls]
Homepage = "https://sqlmesh.com/"
Documentation = "https://sqlmesh.readthedocs.io/en/stable/"
Repository = "https://github.com/TobikoData/sqlmesh"
Issues = "https://github.com/TobikoData/sqlmesh/issues"

[build-system]
requires = ["setuptools >= 61.0", "setuptools_scm"]
build-backend = "setuptools.build_meta"

[tool.setuptools]
include-package-data = false

[tool.setuptools_scm]
version_file = "sqlmesh/_version.py"
fallback_version = "0.0.0"
local_scheme = "no-local-version"

[tool.setuptools.packages.find]
include = ["sqlmesh", "sqlmesh.*", "sqlmesh_dbt", "sqlmesh_dbt.*", "web*"]

[tool.setuptools.package-data]
web = ["client/dist/**"]
"*" = ["py.typed"]

# MyPy Rules
[tool.mypy]
plugins = "pydantic.mypy"
no_implicit_optional = true
disallow_untyped_defs = true

[[tool.mypy.overrides]]
module = [
    "examples.*.macros.*",
    "tests.*",
    "sqlmesh.migrations.*"
]
disallow_untyped_defs = false
# Sometimes it's helpful to use types within an "untyped" function because it allows IDE assistance
# Unfortunately this causes MyPy to print an annoying 'By default the bodies of untyped functions are not checked'
# warning so we disable that warning here
disable_error_code = "annotation-unchecked"

[[tool.mypy.overrides]]
module = [
    "api.*",
    "astor.*",
    "IPython.*",
    "hyperscript.*",
    "py.*",
    "ruamel.*",
    "setuptools.*",
    "graphviz.*",
    "ipywidgets.*",
    "google.*",
    "snowflake.*",
    "redshift_connector",
    "databricks.*",
    "faker.*",
    "agate.*",
    "databricks_cli.*",
    "mysql.*",
    "pymssql.*",
    "pyodbc.*",
    "psycopg2.*",
    "pytest_lazyfixture.*",
    "dbt.adapters.*",
    "slack_sdk.*",
    "py4j.*",
    "boto3.*",
    "trino.*",
    "bs4.*",
    "pydantic_core.*",
    "dlt.*",
    "bigframes.*",
    "json_stream.*",
    "duckdb.*"
]
ignore_missing_imports = true

[tool.pytest.ini_options]
markers = [
    # Test Type Markers
    # Tests are ordered from fastest to slowest
    "fast: fast tests (automatically applied if no type markers)",
    "slow: slow tests that typically involve interacting with a local DB (like DuckDB)",
    "docker: test that involves interacting with a Docker container",
    "remote: test that involves interacting with a remote DB",
    "cicdonly: test that only runs on CI/CD",
    "isolated: tests that need to run sequentially usually because they use fork",
    "dialect_isolated: tests that need to run separately due to global dialect overrides",

    # Test Domain Markers
    # default: core functionality
    "cli: test for CLI",
    "dbt: test for dbt adapter",
    "github: test for Github CI/CD bot",
    "jupyter: tests for Jupyter integration",
    "web: tests for web UI",

    # Engine Adapters
    "engine: test all engine adapters",
    "athena: test for Athena",
    "bigquery: test for BigQuery",
    "clickhouse: test for Clickhouse (standalone mode / cluster mode)",
    "clickhouse_cloud: test for Clickhouse (cloud mode)",
    "databricks: test for Databricks",
    "duckdb: test for DuckDB",
    "fabric: test for Fabric",
    "motherduck: test for MotherDuck",
    "mssql: test for MSSQL",
    "mysql: test for MySQL",
    "postgres: test for Postgres",
    "gcp_postgres: test for Postgres on GCP",
    "redshift: test for Redshift",
    "snowflake: test for Snowflake",
    "spark: test for Spark",
    "pyspark: test for PySpark that need to run separately from the other spark tests",
    "trino: test for Trino (all connectors)",
    "risingwave: test for Risingwave",

    # Other
    "set_default_connection",
    "registry_isolation"
]
addopts = "-n 0 --dist=loadgroup"
asyncio_default_fixture_loop_scope = "session"
log_cli = false # Set this to true to enable logging during tests
log_cli_format = "%(asctime)s.%(msecs)03d %(filename)s:%(lineno)d %(levelname)s %(message)s"
log_cli_level = "INFO"
filterwarnings = [
    "ignore:The localize method is no longer necessary, as this time zone supports the fold attribute"
]
reruns_delay = 10

[tool.ruff]
line-length = 100

[tool.ruff.lint]
select = [
    "F401",
    "RET505",
    "T100",
]
extend-select = ["TID"]


[tool.ruff.lint.flake8-tidy-imports]
banned-module-level-imports = [
    "duckdb",
    "numpy",
    "pandas",
]

# Bans imports from sqlmesh.lsp in files outside of sqlmesh/lsp
[tool.ruff.lint.flake8-tidy-imports.banned-api]
"sqlmesh.lsp".msg = "Only files within sqlmesh/lsp can import from sqlmesh.lsp"

[tool.ruff.lint.per-file-ignores]
# TID251 is used to ignore the import of sqlmesh.lsp in files outside sqlmesh/lsp
"sqlmesh/lsp/**/*.py" = ["TID251"]
"tests/lsp/**/*.py" = ["TID251"]
"benchmarks/lsp*.py" = ["TID251"]
"sqlmesh/dbt/builtin.py" = ["T100"]