Merge pull request #1 from datacommonsorg/master

Update forked repo

cloudbuild.py.yaml

@@ -18,7 +18,7 @@ steps:
   entrypoint: python3
   args: ["-m", "unittest", "discover", "-v", "-s", "util/", "-p", "*_test.py"]
   # In cloudbuild, everything happens under /workspace path
-  env: ["PYTHONPATH=/workspace"]
+  env: ["PYTHONPATH=/workspace:/workspace/scripts"]
   waitFor:
   - python_install
 
@@ -27,7 +27,7 @@ steps:
   entrypoint: python3
   args: ["-m", "unittest", "discover", "-v", "-s", "scripts/", "-p", "*_test.py"]
   # In cloudbuild, everything happens under /workspace path
-  env: ["PYTHONPATH=/workspace"]
+  env: ["PYTHONPATH=/workspace:/workspace/scripts"]
   waitFor:
   - python_install
 
@@ -36,7 +36,7 @@ steps:
   entrypoint: python3
   args: ["-m", "unittest", "discover", "-v", "-s", "import-automation/", "-p", "*_test.py"]
   # In cloudbuild, everything happens under /workspace path
-  env: ["PYTHONPATH=/workspace"]
+  env: ["PYTHONPATH=/workspace:/workspace/scripts"]
   waitFor:
   - python_install
 
@@ -45,7 +45,7 @@ steps:
   entrypoint: python3
   args: ["-m", "yapf", "--recursive", "--diff", "--style", "google", "util/", "scripts/", "tools/", "docs/", "schema/"]
   # In cloudbuild, everything happens under /workspace path
-  env: ["PYTHONPATH=/workspace"]
+  env: ["PYTHONPATH=/workspace:/workspace/scripts"]
   waitFor:
   - python_install
 

docs/mcf_format.md

@@ -259,6 +259,9 @@ containedInPlace: geoId/06
     letter is lower-cased.
     [(EXAMPLE)](https://browser.datacommons.org/kg?dcid=healthOutcome)
 
+-   DCIDs have a length limit of 256 characters. Nodes with a DCID longer than
+    256 characters will throw a syntax error upon uploading to DataCommons.
+
 ## MCF Types in Data Commons
 
 We employ two main types of MCF nodes: instance MCF and template MCF. We may

import-automation/executor/.gitignore

@@ -0,0 +1,142 @@
+.idea
+.DS_Store
+
+# 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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__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/
+

import-automation/executor/app.yaml

@@ -0,0 +1,11 @@
+runtime: python37
+entrypoint: gunicorn --timeout 600 -b :$PORT app.main:FLASK_APP
+env_variables:
+    EXECUTOR_PRODUCTION: "True"
+    TMPDIR: "/tmp"
+basic_scaling:
+  max_instances: 5
+  idle_timeout: 10m
+# 2048 MB RAM and 4.8 GHz CPU.
+# See https://cloud.google.com/appengine/docs/standard#instance_classes.
+instance_class: B8

import-automation/executor/app/__main__.py

@@ -0,0 +1,21 @@
+# Copyright 2020 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Entry point when run as a module.
+See https://docs.python.org/3/library/__main__.html.
+"""
+
+from app import main
+
+main.main()

import-automation/executor/app/configs.py

@@ -0,0 +1,102 @@
+# Copyright 2020 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Configurations for the executor.
+
+The app endpoints accept a configs field that allows customization of all the
+configurations. See main.py.
+"""
+
+import os
+import typing
+import dataclasses
+
+from google.cloud import logging
+
+
+def _production():
+    return 'EXECUTOR_PRODUCTION' in os.environ
+
+
+@dataclasses.dataclass
+class ExecutorConfig:
+    """Configurations for the executor."""
+    # ID of the Google Cloud project that hosts the executor. The project
+    # needs to enable App Engine, Cloud Storage, and Cloud Scheduler.
+    gcp_project_id: str = 'google.com:datcom-data'
+    # Oauth Client ID used to authenticate with the import progress dashboard.
+    # which is protected by Identity-Aware Proxy. This can be found by going
+    # to the Identity-Aware Proxy of the Google Cloud project that hosts
+    # the dashboard and clicking 'Edit OAuth Client'.
+    dashboard_oauth_client_id: str = ''
+    # Access token of the account used to authenticate with GitHub. This is not
+    # the account password. See
+    # https://docs.github.com/en/github/authenticating-to-github/creating-a-personal-access-token.
+    github_auth_access_token: str = ''
+    # Username of the account used to authenticate with GitHub.
+    github_auth_username: str = 'intrepiditee'
+    # Name of the repository that contains all the imports.
+    # On commits, this is the repository to which the pull requests must be sent
+    # to trigger the executor. The source repositories of the pull requests
+    # are downloaded.
+    # On updates, this is the repository that is downloaded.
+    github_repo_name: str = 'data'
+    # Username of the owner of the repository that contains all the imports.
+    github_repo_owner_username: str = 'datacommonsorg'
+    # Manifest filename. The executor uses this name to identify manifests.
+    manifest_filename: str = 'manifest.json'
+    # Python module requirements filename. The executor installs the modules
+    # listed in these files before running the user scripts.
+    requirements_filename: str = 'requirements.txt'
+    # Name of the Cloud Storage bucket to store the generated data files.
+    storage_bucket_name: str = 'import-inputs'
+    # Name of the file that specifies the most recently generated data files
+    # of an import. These files are stored in the bucket at a level higher
+    # than the data files. For example,
+    # import-inputs
+    # -- scripts
+    # ---- us_fed
+    # ------ treasury
+    # -------- latest_version.txt
+    # -------- 2020_07_15T12_07_17_365264_07_00
+    # ---------- data.csv
+    # -------- 2020_07_14T12_07_12_552234_07_00
+    # ---------- data.csv
+    # The content of latest_version.txt would be a single line of
+    # '2020_07_15T12_07_17_365264_07_00'.
+    storage_version_filename: str = 'latest_version.txt'
+    # Types of inputs accepted by the Data Commons importer. These are
+    # also the accepted fields of an import_inputs value in the manifest.
+    import_input_types: typing.List[str] = ('template_mcf', 'cleaned_csv',
+                                            'node_mcf')
+    # ID of the location where Cloud Scheduler is hosted.
+    scheduler_location: str = 'us-central1'
+    # Maximum time a user script can run for in seconds.
+    user_script_timeout: float = 600
+    # Maximum time venv creation can take in seconds.
+    venv_create_timeout: float = 600
+    # Maximum time downloading a file can take in seconds.
+    file_download_timeout: float = 600
+    # Maximum time downloading the repo can take in seconds.
+    repo_download_timeout: float = 600
+
+
+def _setup_logging():
+    client = logging.Client(project=ExecutorConfig.gcp_project_id)
+    client.get_default_handler()
+    client.setup_logging()
+
+
+if _production():
+    _setup_logging()