Add basic skeleton for Integrations CLI with type checking command

cli/.gitignore

@@ -0,0 +1,176 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+# Usually these files are written by a python script from a template
+# before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+# For a library or package, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+# However, in case of collaboration, if having platform-specific dependencies or dependencies
+# having no cross-platform support, pipenv may install dependencies that don't work, or not
+# install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+# This is especially recommended for binary packages to ensure reproducibility, and is more
+# commonly ignored for libraries.
+# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+# in version control.
+# https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+# and can be added to the global gitignore or merged into this file. For a more nuclear
+# option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python

cli/README.md

@@ -0,0 +1,32 @@
+# OsInts: the OpenSearch Integrations CLI
+
+The OsInts CLI is a utility CLI for developing integrations with OpenSearch Integrations.
+It provides a few convenience methods:
+
+- `diff`: Type check your integration given a sample data record and the appropriate SS4O schema.
+
+## Installation
+
+Use the package manager [pip](https://pip.pypa.io/en/stable/) to install the CLI.
+
+```bash
+$ cd cli
+$ pip install .
+...
+Successfully installed osints-0.1.0
+```
+
+## Usage
+
+```bash
+$ osints --help
+Usage: osints [OPTIONS] COMMAND [ARGS]...
+
+ Various tools for working with OpenSearch Integrations.
+
+Options:
+ --help Show this message and exit.
+
+Commands:
+ diff Diff between a mapping and some data.
+```

cli/osints/diff.py

@@ -0,0 +1,154 @@
+from beartype import beartype
+import click
+import json
+import os.path
+import glob
+
+
+@beartype
+def load_mapping(mapping: str) -> dict[str, dict]:
+ with open(mapping, "r") as mapping_file:
+ data = json.load(mapping_file)
+ properties = data.get("template", {}).get("mappings", {}).get("properties")
+ if properties is None:
+ return {}
+ composed_of = data.get("composed_of", [])
+ curr_dir = os.path.dirname(mapping)
+ for item in composed_of:
+ item_glob = glob.glob(os.path.join(curr_dir, f"{item}*"))
+ if len(item_glob) == 0:
+ click.secho(
+ f"ERROR: mapping file {mapping} references component {item}, which does not exist.",
+ err=True,
+ fg="red",
+ )
+ raise click.Abort()
+ if properties.get(item) is not None:
+ click.secho(
+ f"ERROR: mapping file {mapping} references component {item} and defines conflicting key '{item}'",
+ err=True,
+ fg="red",
+ )
+ raise click.Abort()
+ # Greedily take any mapping that matches the name for now.
+ # Later, configuration will need to be implemented.
+ if len(item_glob) > 1:
+ click.secho(
+ f"WARNING: found more than one mapping for component {item}. Assuming {item_glob[0]}.",
+ err=True,
+ fg="yellow",
+ )
+ properties.update(load_mapping(item_glob[0]))
+ return properties
+
+
+@beartype
+def flat_type_check(expect: str, actual: object) -> dict[str, dict]:
+ match expect:
+ case "text" | "keyword":
+ if not isinstance(actual, str):
+ return {"expected": expect, "actual": actual}
+ case "long" | "integer":
+ if not isinstance(actual, int):
+ return {"expected": expect, "actual": actual}
+ case "alias":
+ # We assume aliases were already unwrapped by the caller and ignore them.
+ return {}
+ case "date":
+ if not isinstance(actual, str) and not isinstance(actual, int):
+ return {"expected": expect, "actual": actual}
+ case _:
+ click.secho(f"WARNING: unknown type '{expect}'", err=True, fg="yellow")
+ return {}
+
+
+@beartype
+def get_type(mapping: dict) -> str | dict:
+ if mapping.get("properties"):
+ return {
+ key: get_type(value) for key, value in mapping.get("properties").items()
+ }
+ return mapping.get("type", "unknown")
+
+
+@beartype
+def do_check(
+ mapping: dict[str, dict], data: dict[str, object], show_missing: bool = False
+) -> dict[str, dict]:
+ result = {}
+ for key, value in mapping.items():
+ if key not in data:
+ if show_missing and value.get("type") != "alias":
+ result[key] = {"expected": get_type(value), "actual": None}
+ continue
+ elif "properties" in value and isinstance(data[key], dict):
+ check = do_check(value["properties"], data[key], show_missing)
+ if check != {}:
+ result[key] = check
+ elif value.get("type") == "alias":
+ # Unwrap aliases split by '.'
+ value_path = value["path"].split(".")
+ curr_data = data
+ for step in value_path[:-1]:
+ if step not in curr_data:
+ curr_data[step] = {}
+ curr_data = curr_data[step]
+ curr_data[value_path[-1]] = data[key]
+ elif "type" in value:
+ check = flat_type_check(value["type"], data[key])
+ if check != {}:
+ result[key] = check
+ for key, value in data.items():
+ if key not in mapping:
+ result[key] = {"expected": None, "actual": value}
+ return result
+
+
+@beartype
+def output_diff(difference: dict[str, object], prefix: str = "") -> None:
+ for key, value in sorted(difference.items()):
+ out_key = prefix + key
+ if "expected" not in value and "actual" not in value:
+ output_diff(value, f"{prefix}{key}.")
+ if value.get("actual") is not None:
+ click.echo(f"- {out_key}: {json.dumps(value.get('actual'))}")
+ if value.get("expected") is not None:
+ click.echo(f"+ {out_key}: {json.dumps(value.get('expected'))}")
+
+
+@click.command()
+@click.option(
+ "--mapping",
+ type=click.Path(exists=True, readable=True),
+ help="The mapping for the format the data should have",
+)
+@click.option(
+ "--data",
+ type=click.Path(exists=True, readable=True),
+ help="The location of data to validate",
+)
+@click.option(
+ "--json",
+ "output_json",
+ is_flag=True,
+ help="Output machine-readable JSON instead of the default diff format",
+)
+@click.option(
+ "--show-missing",
+ "show_missing",
+ is_flag=True,
+ help="Output fields that are expected in the mappings but missing in the data",
+)
+def diff(mapping, data, output_json, show_missing):
+ """Type check your integration given a sample data record and the appropriate SS4O schema."""
+ properties = load_mapping(mapping)
+ with open(data, "r") as data_file:
+ data_json = json.load(data_file)
+ if isinstance(data_json, list):
+ # Unwrap list of data, assume first record is representative
+ data_json = data_json[0]
+ check = do_check(properties, data_json, show_missing)
+ if output_json:
+ click.echo(json.dumps(check, sort_keys=True))
+ else:
+ output_diff(check)

cli/osints/main.py

@@ -0,0 +1,11 @@
+import click
+from .diff import diff
+
+
+@click.group()
+def cli():
+ """Various tools for working with OpenSearch Integrations."""
+ pass
+
+
+cli.add_command(diff)

cli/setup.py

@@ -0,0 +1,14 @@
+from setuptools import setup, find_packages
+
+setup(
+ name="osints",
+ version="0.1.0",
+ packages=find_packages(),
+ include_package_data=True,
+ install_requires=[
+ "beartype",
+ "click",
+ ],
+ python_requires=">3.10.0",
+ entry_points={"console_scripts": ["osints = osints.main:cli"]},
+)