retention korjaus testien avulla

git-pages/files/retention-cleanup.sh

@@ -53,35 +53,8 @@ branch_exists() {
   return 0
 }
 
-default_max_age=$(jq -r '.branches.default.maxAgeDays // 90' "$CONFIG")
-default_keep_min=$(jq -r '.branches.default.keepMin // 5' "$CONFIG")
-
-rule_max_age() {
-  local branch="$1" v
-  v=$(jq -r --arg b "$branch" '.branches[$b].maxAgeDays // empty' "$CONFIG")
-  [ -n "$v" ] && echo "$v" || echo "$default_max_age"
-}
-
-rule_keep_min() {
-  local branch="$1" v
-  v=$(jq -r --arg b "$branch" '.branches[$b].keepMin // empty' "$CONFIG")
-  [ -n "$v" ] && echo "$v" || echo "$default_keep_min"
-}
-
-age_days() {
-  local published="$1" epoch_pub now
-  epoch_pub=$(date -u -d "$published" +%s 2>/dev/null || echo 0)
-  [ "$epoch_pub" -eq 0 ] && echo 99999 && return
-  now=$(date -u +%s)
-  echo $(( (now - epoch_pub) / 86400 ))
-}
-
-parse_path() {
-  local rel="$1"
-  OWNER="${rel%%/*}"
-  rest="${rel#*/}"
-  REPO="${rest%%/*}"
-}
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+source "$SCRIPT_DIR/retention-lib.sh"
 
 echo "Fetching manifest from ${PAGES_URL}/.git-pages/manifest.json"
 MANIFEST=$(curl_with_host "${PAGES_URL}/.git-pages/manifest.json")
@@ -144,31 +117,7 @@ done
 
 echo ""
 echo "=== Phase 3: apply retention rules to remaining reports ==="
-declare -A BRANCH_COUNTS
-if [ "${#KEEP[@]}" -gt 0 ]; then
-  IFS=$'\n'
-  for entry in $(printf '%s\n' "${KEEP[@]}" | sort -t'|' -k4,4 -k5,5rn); do
-    IFS='|' read -r dir owner repo branch days <<< "$entry"
-    max_age=$(rule_max_age "$branch")
-    keep_min=$(rule_keep_min "$branch")
-
-    if [ "$days" -gt "$max_age" ]; then
-      echo "  DELETE: ${dir} (age ${days}d > maxAge ${max_age}d, branch ${branch})"
-      TO_DELETE+=("$dir")
-      continue
-    fi
-
-    key="${branch}"
-    count="${BRANCH_COUNTS[$key]:-0}"
-    count=$((count + 1))
-    BRANCH_COUNTS["$key"]=$count
-    if [ "$count" -gt "$keep_min" ]; then
-      echo "  DELETE: ${dir} (kept ${keep_min}/${count}, exceeds keepMin, branch ${branch})"
-      TO_DELETE+=("$dir")
-    fi
-  done
-  unset IFS
-fi
+apply_retention "$CONFIG"
 
 if [ "${#TO_DELETE[@]}" -eq 0 ]; then
   echo "Nothing to delete"

git-pages/files/retention-lib.sh

@@ -0,0 +1,86 @@
+#!/usr/bin/env bash
+# Shared functions for retention-cleanup.sh
+# Can be sourced by tests for unit testing
+
+age_days() {
+  local published="$1" epoch_pub now
+  epoch_pub=$(date -d "$published" +%s 2>/dev/null || date -j -f "%Y-%m-%dT%H:%M:%SZ" "$published" +%s 2>/dev/null || echo 0)
+  [ "$epoch_pub" -eq 0 ] && echo 99999 && return
+  now=$(date -u +%s)
+  echo $(( (now - epoch_pub) / 86400 ))
+}
+
+parse_path() {
+  local rel="$1"
+  OWNER="${rel%%/*}"
+  rest="${rel#*/}"
+  REPO="${rest%%/*}"
+}
+
+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"
+}
+
+# Phase 3: apply retention rules to KEEP array, populate TO_DELETE
+# Reads from global KEEP array
+# Populates global TO_DELETE array
+# Usage: apply_retention <config_path>
+apply_retention() {
+  local config="$1"
+  local default_max_age default_keep_min
+  local max_age keep_min key count seen_key commit_dir report_type path
+  local entry dir owner repo branch days
+
+  default_max_age=$(jq -r '.branches.default.maxAgeDays // 90' "$config")
+  default_keep_min=$(jq -r '.branches.default.keepMin // 5' "$config")
+
+  TO_DELETE=()
+  declare -A BRANCH_COUNTS
+  declare -A SEEN_COMMITS
+  declare -A DELETED_COMMITS
+
+  if [ "${#KEEP[@]}" -eq 0 ]; then
+    return
+  fi
+
+  IFS=$'\n'
+  for entry in $(printf '%s\n' "${KEEP[@]}" | sort -t'|' -k4,4 -k5,5n); do
+    IFS='|' read -r dir owner repo branch days <<< "$entry"
+
+    max_age=$(read_rule "$config" "$branch" "maxAgeDays" "$default_max_age")
+    keep_min=$(read_rule "$config" "$branch" "keepMin" "$default_keep_min")
+
+    # Age check — per-report-type deletion
+    if [ "$days" -gt "$max_age" ]; then
+      echo "  DELETE: ${dir} (age ${days}d > maxAge ${max_age}d, branch ${branch})"
+      TO_DELETE+=("$dir")
+      continue
+    fi
+
+    # keepMin — per-commit counting
+    commit_dir=$(dirname "$dir")
+    key="$branch"
+    seen_key="${key}|${commit_dir}"
+
+    if [ -z "${SEEN_COMMITS[$seen_key]:-}" ]; then
+      SEEN_COMMITS["$seen_key"]=1
+      count="${BRANCH_COUNTS[$key]:-0}"
+      count=$((count + 1))
+      BRANCH_COUNTS["$key"]=$count
+    else
+      count="${BRANCH_COUNTS[$key]:-0}"
+    fi
+
+    if [ "$count" -gt "$keep_min" ]; then
+      if [ -z "${DELETED_COMMITS[$commit_dir]:-}" ]; then
+        DELETED_COMMITS[$commit_dir]=1
+        report_type="${dir##*/}"
+        echo "  DELETE: ${commit_dir} (kept ${keep_min}/${count} commits, exceeds keepMin, branch ${branch})"
+        TO_DELETE+=("$commit_dir")
+      fi
+    fi
+  done
+  unset IFS
+}