# Builds a cached .tar.gz of the $CI_DEFAULT_BRANCH branch with full history and
# uploads it to Google Cloud Storage. This archive is downloaded by a
# script defined by a CI/CD variable named CI_PRE_CLONE_SCRIPT. This has
# two benefits:
#
# 1. It speeds up builds. A 800 MB download only takes seconds.
# 2. It significantly reduces load on the file server. Smaller deltas
#    means less time spent in git pack-objects.
#
# Since the destination directory of the archive depends on the project
# ID, this is only run on GitLab.com.
#
# CI_REPO_CACHE_CREDENTIALS contains the Google Cloud service account
# JSON for uploading to the gitlab-ci-git-repo-cache bucket. These
# credentials are stored in the Production vault.
#
# Note that this bucket should be located in the same continent as the
# runner, or network egress charges will apply:
# https://cloud.google.com/storage/pricing
cache-repo:
  extends: .cache-repo:rules
  image: gcr.io/google.com/cloudsdktool/cloud-sdk:alpine
  stage: sync
  variables:
    GIT_STRATEGY: none
    SHALLOW_CLONE_TAR_FILENAME: gitlab-master-shallow.tar
    FULL_CLONE_TAR_FILENAME: gitlab-master.tar
  before_script:
    - '[ -z "$CI_REPO_CACHE_CREDENTIALS" ] || gcloud auth activate-service-account --key-file=$CI_REPO_CACHE_CREDENTIALS'
  script:
    # Enable shallow repo caching unless the $DISABLE_SHALLOW_REPO_CACHING variable exists (in the case the shallow clone caching isn't working well)
    # The `git repack` call works around a Git bug with shallow clones: https://gitlab.com/gitlab-org/git/-/issues/86
    - if [ -z "$DISABLE_SHALLOW_REPO_CACHING" ]; then
        cd .. && rm -rf $CI_PROJECT_NAME;
        today=$(date +%Y-%m-%d);
        year=$(date +%Y);
        last_year=`expr $year - 1`;
        one_year_ago=$(echo $today | sed "s/$year/$last_year/");
        echo "Cloning $CI_REPOSITORY_URL into $CI_PROJECT_NAME with commits from $one_year_ago.";
        time git clone --progress --no-checkout --shallow-since=$one_year_ago $CI_REPOSITORY_URL $CI_PROJECT_NAME;
        cd $CI_PROJECT_NAME;
        time git repack -d;
        echo "Archiving $CI_PROJECT_NAME into /tmp/$SHALLOW_CLONE_TAR_FILENAME.";
        time git remote rm origin;
        time tar cf /tmp/$SHALLOW_CLONE_TAR_FILENAME .;
        echo "GZipping /tmp/$SHALLOW_CLONE_TAR_FILENAME.";
        time gzip /tmp/$SHALLOW_CLONE_TAR_FILENAME;
        [ -z "$CI_REPO_CACHE_CREDENTIALS" ] || (echo "Uploading /tmp/$SHALLOW_CLONE_TAR_FILENAME.gz to GCloud." && time gsutil cp /tmp/$SHALLOW_CLONE_TAR_FILENAME.gz gs://gitlab-ci-git-repo-cache/project-$CI_PROJECT_ID/$SHALLOW_CLONE_TAR_FILENAME.gz);
      fi
    # Disable the full repo caching unless the $DISABLE_SHALLOW_REPO_CACHING variable exists (in the case the shallow clone caching isn't working well)
    - if [ -n "$DISABLE_SHALLOW_REPO_CACHING" ]; then
        cd .. && rm -rf $CI_PROJECT_NAME;
        echo "Cloning $CI_REPOSITORY_URL into $CI_PROJECT_NAME.";
        time git clone --progress $CI_REPOSITORY_URL $CI_PROJECT_NAME;
        cd $CI_PROJECT_NAME;
        time git repack -d;
        echo "Archiving $CI_PROJECT_NAME into /tmp/$FULL_CLONE_TAR_FILENAME.";
        time git remote rm origin;
        time tar cf /tmp/$FULL_CLONE_TAR_FILENAME .;
        echo "GZipping /tmp/$FULL_CLONE_TAR_FILENAME.";
        time gzip /tmp/$FULL_CLONE_TAR_FILENAME;
        [ -z "$CI_REPO_CACHE_CREDENTIALS" ] || (echo "Uploading /tmp/$FULL_CLONE_TAR_FILENAME.gz to GCloud." && time gsutil cp /tmp/$FULL_CLONE_TAR_FILENAME.gz gs://gitlab-ci-git-repo-cache/project-$CI_PROJECT_ID/$FULL_CLONE_TAR_FILENAME.gz);
      fi