Skip to content

Flex status update [SOURCES] #1011

Flex status update [SOURCES]

Flex status update [SOURCES] #1011

name: Direct download URLs test for sources
on:
pull_request:
branches: [ main ]
paths-ignore:
- 'scripts/**'
- '.github/workflows/add_new_or_updated_feeds.yml'
- '.github/workflows/**'
jobs:
get-urls:
if: contains(github.event.pull_request.title, '[SOURCES]')
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Set up Python 3.9
uses: actions/setup-python@v5
with:
python-version: 3.9
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install wheel numpy
- name: Get added and modified files
id: files
uses: jitterbit/get-changed-files@v1
- name: Create the direct download URLs matrix
shell: python
run: |
import os
import json
import numpy as np
# OS constants
ROOT = os.getcwd()
GTFS_SCHEDULE_CATALOG_PATH_FROM_ROOT = "catalogs/sources/gtfs/schedule"
MATRIX_FILE = "urls_matrix.json"
# File constants
URLS = "urls"
DIRECT_DOWNLOAD = "direct_download"
AUTHENTICATION_TYPE = "authentication_type"
API_KEY_PARAMETER_NAME = "api_key_parameter_name"
# Github constants
MAX_JOB_NUMBER = 256
# Matrix constants
INCLUDE = "include"
DATA = "data"
BASE = "base"
changed_files = "${{ steps.files.outputs.added_modified }}".split()
changed_files = [file for file in changed_files if GTFS_SCHEDULE_CATALOG_PATH_FROM_ROOT in file]
urls = {}
for file in changed_files:
base = os.path.splitext(os.path.basename(file))[0]
with open(os.path.join(ROOT, file), "r") as fp:
file_json = json.load(fp)
direct_download_url = file_json.get(URLS, {}).get(DIRECT_DOWNLOAD)
if direct_download_url is None:
raise ValueError(f"{base}: Missing direct download url.")
authentication_type = file_json.get(URLS, {}).get(AUTHENTICATION_TYPE)
api_key_parameter_name = file_json.get(URLS, {}).get(API_KEY_PARAMETER_NAME)
urls[base] = {
DIRECT_DOWNLOAD: direct_download_url,
AUTHENTICATION_TYPE: authentication_type,
API_KEY_PARAMETER_NAME: api_key_parameter_name
}
urls_data = []
jobs = np.array_split(list(urls.keys()), min(MAX_JOB_NUMBER, len(list(urls.keys()))))
jobs = [list(job) for job in jobs]
for job in jobs:
urls_data_string = ""
while len(job) > 0:
file_base = job.pop()
file_information = {
BASE: file_base,
DIRECT_DOWNLOAD: urls[file_base][DIRECT_DOWNLOAD],
AUTHENTICATION_TYPE: urls[file_base][AUTHENTICATION_TYPE],
API_KEY_PARAMETER_NAME: urls[file_base][API_KEY_PARAMETER_NAME]
}
urls_data_string = urls_data_string + json.dumps(
file_information, separators=(",", ":")
)
job_data = {DATA: urls_data_string.replace("}{", "} {")}
urls_data.append(job_data)
matrix_data = {INCLUDE: urls_data}
with open(os.path.join(ROOT, MATRIX_FILE), "w") as fp:
file_json = json.dump(matrix_data, fp)
- name: Set URLs matrix
id: set-matrix
run: |
DATASETS=$(jq . ./urls_matrix.json -c)
echo $DATASETS
echo "matrix=$DATASETS" >> $GITHUB_OUTPUT
- name: Persist URLs matrix artifact
if: always()
uses: actions/upload-artifact@v4
with:
name: urls_matrix
path: ./urls_matrix.json
outputs:
matrix: ${{ steps.set-matrix.outputs.matrix }}
download-datasets:
name: Validate and download - ${{ fromJson(matrix.data).base }}
needs: [ get-urls ]
runs-on: ubuntu-latest
strategy:
matrix: ${{ fromJson(needs.get-urls.outputs.matrix) }}
steps:
- uses: actions/checkout@v4
- name: Set up Python 3.9
uses: actions/setup-python@v5
with:
python-version: 3.9
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install pytest wheel numpy
sudo add-apt-repository ppa:ubuntugis/ubuntugis-unstable
sudo apt-get update
sudo apt-get install gdal-bin python3-gdal
sudo apt-get install libgdal-dev
pip install GDAL==$(gdal-config --version) --global-option=build_ext --global-option="-I/usr/include/gdal"
sudo apt-get install libspatialindex-dev
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
- name: Validate and download the datasets
shell: python
env:
API_SOURCE_SECRETS: ${{ secrets.API_SOURCE_SECRETS }}
run: |
import os
import json
import gtfs_kit
import requests
# OS constants
ROOT = os.getcwd()
DATASETS = "datasets"
# Jobs constants
BASE = "base"
DIRECT_DOWNLOAD = "direct_download"
AUTHENTICATION_TYPE = "authentication_type"
API_KEY_PARAMETER_NAME = "api_key_parameter_name"
# Secrets constants
API_SOURCE_SECRETS = "API_SOURCE_SECRETS"
# Requests constants
USER_AGENT = "User-Agent"
# Selecting a default user agent instead of using a library like fake-useragent.
# We want to make sure we always use the same user agent for reproducibility purposes.
DEFAULT_USER_AGENT = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36"
jobs = """${{ matrix.data }}""".split()
for job in jobs:
job_json = json.loads(job)
base = job_json[BASE]
url = job_json[DIRECT_DOWNLOAD]
authentication_type = job_json[AUTHENTICATION_TYPE]
api_key_parameter_name = job_json[API_KEY_PARAMETER_NAME]
params = {}
headers = {USER_AGENT: DEFAULT_USER_AGENT}
if authentication_type in [1, 2]:
# Load API source secrets only if authentication is required
# This will allow users to add or update
# sources that do not require authentication via forks.
api_source_secrets = json.loads(os.environ[API_SOURCE_SECRETS])
api_key_parameter_value = api_source_secrets.get(base)
if authentication_type == 1:
params[api_key_parameter_name] = api_key_parameter_value
elif authentication_type == 2:
headers[api_key_parameter_name] = api_key_parameter_value
# Download the dataset
zip_path = os.path.join(ROOT, DATASETS, f"{base}.zip")
os.makedirs(os.path.dirname(zip_path), exist_ok=True)
try:
zip_file_req = requests.get(url, params=params, headers=headers, allow_redirects=True)
zip_file_req.raise_for_status()
except Exception as e:
raise Exception(
f"{base}: Exception {e} occurred when downloading the URL {url}.\n"
)
zip_file = zip_file_req.content
with open(zip_path, "wb") as f:
f.write(zip_file)
# Make sure that the dataset is a readable GTFS Schedule dataset
try:
gtfs_kit.read_feed(zip_path, dist_units="km")
except Exception as e:
# Delete the zip file if an exception occurs
os.remove(zip_path)
raise Exception(
f"{base}: Exception {e} found while parsing the GTFS Schedule dataset with the GTFS Kit library."
f"The dataset for the source must be a valid GTFS Schedule zip file or URL.\n"
)
- name: Persist datasets artifact
uses: actions/upload-artifact@v4
with:
name: datasets-${{ fromJson(matrix.data).base }}
path: datasets