Add new indexer application

Related to T4540

apps/swh-indexer/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 \
+      libsvn-dev libapr1-dev libaprutil1-dev subversion && \
+    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=1
+ENV LOGLEVEL=INFO
+
+ENTRYPOINT "/opt/swh/entrypoint.sh"

apps/swh-indexer/entrypoint.sh

+#!/bin/bash
+
+set -e
+
+case "$1" in
+  "shell")
+    shift
+    echo "Running command $@"
+    exec bash -i "$@"
+    ;;
+  *)
+    echo Starting the swh Celery worker for ${SWH_WORKER_INSTANCE}
+    exec python -m celery \
+       --app=swh.scheduler.celery_backend.config.app \
+       worker \
+       --pool=prefork \
+       --concurrency=${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-indexer/requirements.txt

+swh-indexer

[Phabricator Migration user]

Some references in the commit message have been migrated:

• T4540 is now infra/sysadm-environment#4540