Feature/git pages -> oma nginx perusteinen raporointipalvelu (#48)

Co-authored-by: moilanik <niko.moilanen@tietoevry.com>
Reviewed-on: #48

gitea-reports/files/retention-cleanup.sh

@@ -0,0 +1,66 @@
+#!/usr/bin/env bash
+# Retention cleanup: read PV directly, no git-pages API.
+# Removes old commit-level report dirs based on branch existence + age rules.
+set -euo pipefail
+
+DATA_ROOT="${DATA_ROOT:-/app/data}"
+CONFIG="${RETENTION_CONFIG:-/etc/retention/retention.json}"
+GITEA_API_URL="${GITEA_API_URL:-}"
+GITEA_TOKEN="${GITEA_TOKEN:-}"
+
+[ -f "$CONFIG" ] || { echo "ERROR: config missing: $CONFIG" >&2; exit 1; }
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+source "$SCRIPT_DIR/retention-lib.sh"
+
+DELETED_COUNT=0
+ERROR_COUNT=0
+
+for owner_dir in "$DATA_ROOT"/*/; do
+  [ -d "$owner_dir" ] || continue
+  owner=$(basename "$owner_dir")
+
+  for repo_dir in "$owner_dir"*/; do
+    [ -d "$repo_dir" ] || continue
+    repo=$(basename "$repo_dir")
+
+    for branch_dir in "$repo_dir"*/; do
+      [ -d "$branch_dir" ] || continue
+      branch=$(basename "$branch_dir")
+
+      echo "=== ${owner}/${repo}/${branch} ==="
+
+      if ! branch_exists "$owner" "$repo" "$branch"; then
+        echo "  Branch does not exist in Gitea -> DELETE ALL"
+        rm -rf "$branch_dir"
+        DELETED_COUNT=$((DELETED_COUNT + 1))
+        continue
+      fi
+
+      rules=$(jq -r ".branches.\"$branch\" // .branches.default" "$CONFIG")
+      keep_min=$(echo "$rules" | jq -r '.keepMin // 5')
+      min_age=$(echo "$rules" | jq -r '.minAgeDays // 7')
+
+      commits=$(ls -1t "$branch_dir" 2>/dev/null || true)
+      count=0
+      for sha8 in $commits; do
+        [ -d "$branch_dir/$sha8" ] || continue
+        count=$((count + 1))
+
+        [ "$count" -le "$keep_min" ] && continue
+
+        age=$(age_days_from_stat "$branch_dir/$sha8")
+        [ "$age" -lt "$min_age" ] && continue
+
+        echo "  DELETE: ${owner}/${repo}/${branch}/${sha8} (age=${age}d, keepMin=${keep_min})"
+        rm -rf "$branch_dir/$sha8"
+        DELETED_COUNT=$((DELETED_COUNT + 1))
+      done
+    done
+  done
+done
+
+echo ""
+echo "=== Summary ==="
+echo "  Deleted: ${DELETED_COUNT}"
+echo "  Errors:  ${ERROR_COUNT}"

gitea-reports/files/retention-lib.sh

@@ -0,0 +1,32 @@
+#!/usr/bin/env bash
+# Shared functions for retention-cleanup.sh
+# Can be sourced by tests for unit testing
+
+age_days_from_stat() {
+  local dir="$1" epoch_dir now
+  epoch_dir=$(stat -c %Y "$dir" 2>/dev/null || stat -f %m "$dir" 2>/dev/null || echo 0)
+  [ "$epoch_dir" -eq 0 ] && echo 99999 && return
+  now=$(date +%s)
+  echo $(( (now - epoch_dir) / 86400 ))
+}
+
+read_rule() {
+  local config="$1" branch="$2" key="$3" default="$4"
+  v=$(jq -r --arg b "$branch" --arg k "$key" '.branches[$b][$k] // empty' "$config")
+  [ -n "$v" ] && echo "$v" || echo "$default"
+}
+
+branch_exists() {
+  local owner="$1" repo="$2" branch="$3"
+  local branch_urlenc code
+
+  [ -z "$GITEA_API_URL" ] && return 0
+  [ -z "$GITEA_TOKEN" ] && return 0
+
+  branch_urlenc=$(echo "$branch" | sed 's/\//%2F/g')
+  code=$(curl -s -o /dev/null -w "%{http_code}" \
+    -H "Authorization: token $GITEA_TOKEN" \
+    "$GITEA_API_URL/api/v1/repos/$owner/$repo/branches/$branch_urlenc" 2>/dev/null || echo "000")
+
+  [ "$code" = "200" ]
+}

gitea-reports/files/retention-run.sh

@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+# Run retention cleanup on PVC directly (no git-pages API).
+set -euo pipefail
+
+/scripts/retention-cleanup.sh
+echo "Retention job done."