CLOUDP-301527: Migrate from custom pre-commit to official pre-commit framework

This commit migrates from the custom .githooks/pre-commit bash script to
the official pre-commit framework (https://pre-commit.com).

Changes:
- Add .pre-commit-config.yaml with all existing hooks migrated
- Add .yamllint.yaml for YAML linting configuration
- Create scripts/dev/generate_files.sh - extracted file generation logic
- Create scripts/dev/regenerate_multicluster_rbac.sh - extracted RBAC regeneration
- Simplify .githooks/pre-commit to delegate to pre-commit framework
- Update scripts/evergreen/check_precommit.sh for CI integration
- Update Makefile precommit targets
- Add pre-commit to requirements.txt
- Fix prepare-openshift-bundles-for-e2e.sh to call generate_files.sh directly
- Fix validate_snippets.py to ignore git-ignored directories
- Fix pyproject.toml isort config to use line_length=120 (matching black)

Note: trailing-whitespace and end-of-file-fixer hooks are commented out
for now (they modify 200+ files). These will be enabled in a follow-up PR.

Author: nammn

.githooks/pre-commit

@@ -1,289 +1,18 @@
 #!/usr/bin/env bash
+#
+# Git pre-commit hook that delegates to the pre-commit framework.
+# This file is kept for backwards compatibility with existing dev setups.
+#
+# To set up: git config core.hooksPath .githooks
+#
 
 set -Eeou pipefail
 
 source scripts/dev/set_env_context.sh
-source scripts/funcs/printing
 
-if [ -f "${PROJECT_DIR}"/venv/bin/activate ]; then
-  source "${PROJECT_DIR}"/venv/bin/activate
+if [ -f "${PROJECT_DIR}/venv/bin/activate" ]; then
+  source "${PROJECT_DIR}/venv/bin/activate"
 fi
 
-if [[ -z "${EVERGREEN_MODE:-}" ]]; then
-  # According to the latest SSDLC recommendations, the CI needs to always check all the files. Not just delta.
-  git_last_changed=$(git ls-tree -r origin/master --name-only)
-else
-  git_last_changed=$(git diff --cached --name-only --diff-filter=ACM origin/master)
-fi
-
-mkdir -p "$(go env GOPATH)/bin"
-
-update_mco_tests() {
-  echo "Regenerating MCO evergreen tests configuration"
-  python scripts/evergreen/e2e/mco/create_mco_tests.py >.evergreen-mco.yml
-  git add .evergreen-mco.yml
-}
-
-# Generates a yaml file to install the operator from the helm sources.
-generate_standalone_yaml() {
-  HELM_OPTS=$@
-
-  charttmpdir=$(mktemp -d 2>/dev/null || mktemp -d -t 'charttmpdir')
-  charttmpdir=${charttmpdir}/chart
-  mkdir -p "${charttmpdir}"
-
-  FILES=(
-    "${charttmpdir}/mongodb-kubernetes/templates/operator-roles-base.yaml"
-    "${charttmpdir}/mongodb-kubernetes/templates/operator-roles-clustermongodbroles.yaml"
-    "${charttmpdir}/mongodb-kubernetes/templates/operator-roles-pvc-resize.yaml"
-    "${charttmpdir}/mongodb-kubernetes/templates/operator-roles-telemetry.yaml"
-    "${charttmpdir}/mongodb-kubernetes/templates/operator-roles-webhook.yaml"
-    "${charttmpdir}/mongodb-kubernetes/templates/database-roles.yaml"
-    "${charttmpdir}/mongodb-kubernetes/templates/operator-sa.yaml"
-    "${charttmpdir}/mongodb-kubernetes/templates/operator.yaml"
-  )
-
-  # generate normal public example
-  helm template --namespace mongodb -f helm_chart/values.yaml helm_chart --output-dir "${charttmpdir}" ${HELM_OPTS[@]}
-  cat "${FILES[@]}" >public/mongodb-kubernetes.yaml
-  cat "helm_chart/crds/"* >public/crds.yaml
-
-  # generate openshift public example
-  rm -rf "${charttmpdir:?}"/*
-  helm template --namespace mongodb -f helm_chart/values.yaml helm_chart --output-dir "${charttmpdir}" --values helm_chart/values-openshift.yaml ${HELM_OPTS[@]}
-  cat "${FILES[@]}" >public/mongodb-kubernetes-openshift.yaml
-
-  # generate openshift files for kustomize used for generating OLM bundle
-  rm -rf "${charttmpdir:?}"/*
-  helm template --namespace mongodb -f helm_chart/values.yaml helm_chart --output-dir "${charttmpdir}" --values helm_chart/values-openshift.yaml \
-    --set operator.webhook.registerConfiguration=false --set operator.webhook.installClusterRole=false ${HELM_OPTS[@]}
-
-  # update kustomize files for OLM bundle with files generated for openshift
-  cp "${charttmpdir}/mongodb-kubernetes/templates/operator.yaml" config/manager/manager.yaml
-  cp "${charttmpdir}/mongodb-kubernetes/templates/database-roles.yaml" config/rbac/database-roles.yaml
-  cp "${charttmpdir}/mongodb-kubernetes/templates/operator-roles-base.yaml" config/rbac/operator-roles-base.yaml
-  cp "${charttmpdir}/mongodb-kubernetes/templates/operator-roles-clustermongodbroles.yaml" config/rbac/operator-roles-clustermongodbroles.yaml
-  cp "${charttmpdir}/mongodb-kubernetes/templates/operator-roles-pvc-resize.yaml" config/rbac/operator-roles-pvc-resize.yaml
-  cp "${charttmpdir}/mongodb-kubernetes/templates/operator-roles-telemetry.yaml" config/rbac/operator-roles-telemetry.yaml
-
-  # generate multi-cluster public example
-  rm -rf "${charttmpdir:?}"/*
-  helm template --namespace mongodb -f helm_chart/values.yaml helm_chart --output-dir "${charttmpdir}" --values helm_chart/values-multi-cluster.yaml ${HELM_OPTS[@]}
-  cat "${FILES[@]}" >public/mongodb-kubernetes-multi-cluster.yaml
-
-}
-
-python_formatting() {
-  # installing Black
-  if ! command -v "black" >/dev/null; then
-    pip install -r requirements.txt
-  fi
-
-  echo "formatting isort"
-  isort .
-  echo "formatting black"
-  black .
-}
-
-generate_manifests() {
-  make manifests
-
-  git add config/crd/bases
-  git add helm_chart/crds
-  git add public/crds.yaml
-}
-
-update_values_yaml_files() {
-  # ensure that all helm values files are up to date.
-  # shellcheck disable=SC2154
-  python scripts/evergreen/release/update_helm_values_files.py
-
-  # commit any changes we made
-  git add helm_chart/values.yaml
-  git add helm_chart/values-openshift.yaml
-
-  # these can change if the version of community operator is different
-  git add go.mod
-  git add go.sum
-}
-
-update_release_json() {
-  # ensure that release.json is up 2 date
-  # shellcheck disable=SC2154
-  python scripts/evergreen/release/update_release.py
-
-  # commit any changes we made
-  git add release.json
-}
-
-regenerate_public_rbac_multi_cluster() {
-    if echo "$git_last_changed" | grep -q -e 'cmd/kubectl-mongodb' -e 'pkg/kubectl-mongodb'; then
-      echo 'regenerating multicluster RBAC public example'
-      pushd pkg/kubectl-mongodb/common/
-      EXPORT_RBAC_SAMPLES="true" go test ./... -run TestPrintingOutRolesServiceAccountsAndRoleBindings
-      popd
-      git add public/samples/multi-cluster-cli-gitops
-    fi
-}
-
-update_licenses() {
-    if [[ "${MDB_UPDATE_LICENSES:-""}" == "true" ]]; then
-      echo 'regenerating licenses'
-      time scripts/evergreen/update_licenses.sh 2>&1 | prepend "update_licenses"
-      git add LICENSE-THIRD-PARTY
-    fi
-}
-
-check_erroneous_kubebuilder_annotations() {
-  # Makes sure there are not erroneous kubebuilder annotations that can
-  # end up in CRDs as descriptions.
-  if grep "// kubebuilder" ./* -r --exclude-dir=vendor --include=\*.go; then
-    echo -e "${RED}Found an erroneous kubebuilder annotation${NO_COLOR}"
-    exit 1
-  fi
-}
-
-check_incorrect_makefile_variable_brackets() {
-  if find . -name "Makefile" | grep -v vendor | xargs grep "\${"; then
-    echo -e "${RED}ERROR: Makefiles should NEVER contain curly brackets variables${NO_COLOR}"
-    exit 1
-  fi
-}
-
-update_jobs() {
-     # Update release.json first in case there is a newer version
-    time update_release_json
-    # We need to generate the values files first
-    time update_values_yaml_files
-    # The values files are used for generating the standalone yaml
-    time generate_standalone_yaml
-}
-
-lint_code() {
-  scripts/evergreen/lint_code.sh
-}
-
-lint_helm_chart() {
-  scripts/dev/lint_helm_chart.sh
-}
-
-function validate_snippets() {
-  scripts/code_snippets/validate_snippets.py
-}
-
-# bg_job_ vars are global; run_job_in_background function is appending to them on each call
-bg_job_pids=()
-bg_job_pids_with_names=()
-
-get_job_name() {
-  local search_pid="$1"
-  local match
-  match=$(printf '%s\n' "${bg_job_pids_with_names[@]}" | grep "^${search_pid}:")
-  echo "${match#*:}"  # Remove everything up to and including the colon
-}
-
-# Executes function given on the first argument as background job.
-# It's ensuring logs are properly prefixed by the name and
-# the job's pid is captured in bg_jobs array in order to wait for completion.
-run_job_in_background() {
-  job_name=$1
-  time ${job_name} 2>&1 | prepend "${job_name}" &
-
-  local job_pid=$!
-  bg_job_pids+=("${job_pid}")
-  bg_job_pids_with_names+=("${job_pid}:${job_name}")
-  echo "Started ${job_name} with PID: ${job_pid}"
-}
-
-# Waits for all background jobs stored in bg_job_pids and check their exit codes.
-wait_for_all_background_jobs() {
-    failures=()
-    for pid in "${bg_job_pids[@]}"; do
-      wait "${pid}" || {
-        job_name=$(get_job_name "${pid}")
-        failures+=("    ${RED}${job_name} (PID ${pid})${NO_COLOR}")
-      }
-    done
-
-    if [[ ${#failures[@]} -gt 0 ]]; then
-      echo -e "${RED}Some checks have failed:${NO_COLOR}"
-      for failure in "${failures[@]}"; do
-        echo -e "$failure"
-      done
-      echo -e "${RED}To see the details look/filter for the job's logs by it's prefixed name (e.g. \"start_shellcheck:\", \"lint_code:\", \"shellcheck failed\").${NO_COLOR}"
-      return 1
-    fi
-
-    return 0
-}
-
-pre_commit() {
-  run_job_in_background "update_jobs"
-  run_job_in_background "update_licenses"
-  run_job_in_background "lint_code"
-  run_job_in_background "start_shellcheck"
-  run_job_in_background "regenerate_public_rbac_multi_cluster"
-  run_job_in_background "python_formatting"
-  run_job_in_background "check_erroneous_kubebuilder_annotations"
-  run_job_in_background "validate_snippets"
-
-  if wait_for_all_background_jobs; then
-    # lint_helm_chart must be run after all the background jobs are finished because one of the BG jobs (update_jobs)
-    # updates the helm chart. And lint_helm_chart requires the helm chart to be updated already.
-    lint_helm_chart
-
-    local lint_helm_chart_status=$?
-    if [ "$lint_helm_chart_status" -eq 0 ]; then
-      echo -e "${GREEN}pre-commit: All checks passed!${NO_COLOR}"
-      return 0
-    else
-      return 1
-    fi
-  else
-    return 1
-  fi
-}
-
-# Function to run shellcheck on a single file
-run_shellcheck() {
-  local file="$1"
-
-  local diff_output
-  diff_output=$(shellcheck -f diff "$file" -e SC2154 -e SC1091 -e SC1090 -e SC2148 -o require-variable-braces -P "scripts" 2>&1)
-
-  if [[ -n "$diff_output" && "$diff_output" != *"Issues were detected, but none were auto-fixable"* ]]; then
-    echo "$diff_output" | git apply
-    echo "Applied auto-fixes for $file"
-  elif [[ "$diff_output" == *"Issues were detected, but none were auto-fixable"* ]]; then
-    echo -e "${RED}shellcheck failed on $file${NO_COLOR}"
-    shellcheck --color=always -x "$file" -e SC2154 -e SC1091 -e SC1090 -e SC2148 -o require-variable-braces -P "scripts"
-    return 1
-  fi
-}
-
-# Export function so it's available in subshells (for xargs)
-export -f run_shellcheck
-
-start_shellcheck() {
-  # shellcheck disable=SC2016
-  {
-    find scripts -type f -name "*.sh"
-    find scripts/dev/contexts -type f | grep -v private-context
-    find scripts/funcs -type f
-    find public/architectures -type f -name "*.sh"
-    find docs/ -type f -name "*.sh"
-  } | xargs -I {} -P 20 bash -c 'run_shellcheck "$1"' _ {}
-}
-
-cmd=${1:-"pre-commit"}
-
-if [[ "${cmd}" == "generate_standalone_yaml" ]]; then
-  shift 1
-  generate_standalone_yaml "$@"
-elif [[ "${cmd}" == "pre-commit" ]]; then
- time pre_commit
-elif [[ "${cmd}" == "shellcheck" ]]; then
-  start_shellcheck
-elif [[ "${cmd}" == "lint" ]]; then
-  lint_code
-fi
+# Run pre-commit framework
+exec pre-commit run --all-files