Add new swh-loader-package application

This deals with package loaders only: pypi, npm, maven, opam, ...

Related to T4144

apps/swh-loader-package/Dockerfile

+# Deeply inspired from the Dockerfile of the swh-graph project
+FROM python:3.10-bullseye
+
+RUN apt-get -y update && \
+    apt-get -y upgrade && \
+    apt-get install -y libcmph-dev librdkafka-dev && \
+    apt clean && \
+    addgroup --gid 1000 swh && \
+    useradd --gid 1000 --uid 1000 -m -d /opt/swh swh && \
+    mkdir /etc/swh
+
+USER swh
+WORKDIR /opt/swh
+
+COPY --chown=swh:swh requirements-frozen.txt /opt/swh
+COPY --chown=swh:swh entrypoint.sh /opt/swh
+
+ENV PYTHONPATH=/opt/swh
+ENV PATH=/opt/swh/.local/bin:$PATH
+
+RUN chmod u+x /opt/swh/entrypoint.sh && \
+    /usr/local/bin/python -m pip install --upgrade pip && \
+    pip install --no-cache-dir -r requirements-frozen.txt && \
+    pip install gunicorn
+
+ENV SWH_CONFIG_FILENAME=/etc/swh/config.yml
+ENV SWH_WORKER_INSTANCE=loader
+ENV CONCURRENCY=1
+ENV MAX_TASKS_PER_CHILD=5
+ENV LOGLEVEL=INFO
+
+ENTRYPOINT "/opt/swh/entrypoint.sh"

apps/swh-loader-package/entrypoint.sh

+#!/bin/bash
+
+set -e
+
+case "$1" in
+  "shell")
+    shift
+    echo "Running command $@"
+    exec bash -i "$@"
+    ;;
+  *)
+    echo Starting the swh Celery worker for ${SWH_WORKER_INSTANCE}
+    exec python -m celery \
+       --app=swh.scheduler.celery_backend.config.app \
+       worker \
+       --pool=prefork --events \
+       --concurrency=${CONCURRENCY} \
+       --max-tasks-per-child=${MAX_TASKS_PER_CHILD} \
+       -Ofair --loglevel=${LOGLEVEL} \
+       --without-gossip --without-mingle --without-heartbeat \
+       --hostname "${SWH_WORKER_INSTANCE}@%h"
+    ;;
+esac

apps/swh-loader-package/requirements-frozen.txt

+aiohttp==3.8.1
+aiohttp-utils==3.1.1
+aiosignal==1.2.0
+amqp==5.1.1
+async-timeout==4.0.2
+attrs==22.1.0
+attrs-strict==1.0.0
+billiard==3.6.4.0
+blinker==1.5
+cassandra-driver==3.25.0
+celery==5.2.7
+certifi==2022.6.15
+cffi==1.15.1
+chardet==5.0.0
+charset-normalizer==2.1.1
+click==8.1.3
+click-didyoumean==0.3.0
+click-plugins==1.1.1
+click-repl==0.2.0
+confluent-kafka==1.9.2
+Deprecated==1.2.13
+exceptiongroup==1.0.0rc9
+Flask==2.2.2
+frozenlist==1.3.1
+geomet==0.2.1.post1
+gunicorn==20.1.0
+humanize==4.3.0
+hypothesis==6.54.5
+idna==3.3
+importlib-metadata==4.12.0
+iniconfig==1.1.1
+iso8601==1.0.2
+itsdangerous==2.1.2
+Jinja2==3.1.2
+kombu==5.2.4
+MarkupSafe==2.1.1
+mirakuru==2.4.2
+msgpack==1.0.4
+multidict==6.0.2
+mypy-extensions==0.4.3
+packaging==21.3
+pika==1.3.0
+pkginfo==1.8.3
+pluggy==1.0.0
+port-for==0.6.2
+prompt-toolkit==3.0.31
+psutil==5.9.2
+psycopg2==2.9.3
+py==1.11.0
+pycparser==2.21
+pyparsing==3.0.9
+pytest==7.1.3
+pytest-postgresql==3.1.3
+python-dateutil==2.8.2
+python-debian==0.1.47
+python-magic==0.4.27
+python-mimeparse==1.6.0
+pytz==2022.2.1
+PyYAML==6.0
+redis==4.3.4
+requests==2.28.1
+sentry-sdk==1.9.8
+six==1.16.0
+sortedcontainers==2.4.0
+swh.core==2.14.0
+swh.counters==0.9.1
+swh.journal==1.1.0
+swh.loader.core==3.5.0
+swh.model==6.4.1
+swh.objstorage==2.0.1
+swh.perfecthash==0.1.2
+swh.scheduler==1.2.1
+swh.storage==1.6.0
+tenacity==8.0.1
+toml==0.10.2
+tomli==2.0.1
+typing_extensions==4.3.0
+urllib3==1.26.12
+vine==5.0.0
+wcwidth==0.2.5
+Werkzeug==2.2.2
+wrapt==1.14.1
+yarl==1.8.1
+zipp==3.8.1

apps/swh-loader-package/requirements.txt

+swh-loader-core
+

[Phabricator Migration user]

Some references in the commit message have been migrated:

• T4144 is now infra/sysadm-environment#4144