config:
  cache_resources:
    - label: dedup_cache
      memory:
        default_ttl: 1h

  input:
    http_server:
      address: '0.0.0.0:8080'
      path: /webhooks/signup

  pipeline:
    threads: 1
    processors:
      # Parse JSON
      - mapping: root = content().parse_json()
      # Generate content hash
      - mapping: |
          root = this
          # json_format() ensures stable key ordering
          let event_json = this.format_json()
          root.dedup_hash = $event_json.hash("sha256")
          root.dedup_timestamp = now()

      - group_by_value:
          value: '${! this.dedup_hash }'
      - mapping: |
          root = this
          meta batch_duplicate = batch_index() > 0

      - for_each:
          - branch:
              request_map: root = this.dedup_hash
              processors:
                - cache:
                    resource: dedup_cache
                    operator: exists
                    key: '${! content() }'
              result_map: |
                root.is_duplicate = meta("batch_duplicate").bool() || content().string().bool()
                meta cache = content().string()
                meta is_duplicate = root.is_duplicate
          - catch:
              - mapping: |
                  root = this
                  root.is_duplicate = false
                  meta cache = ""
                  meta is_duplicate = false
          - mapping: |
              root = this
              root.dedup_result = {
                "is_duplicate": this.is_duplicate,
                "dedup_hash": this.dedup_hash,
                "checked_at": now(),
                "strategy": "hash-based"
              }
              root.duplicate_metadata = if this.is_duplicate {
                {
                  "detected_at": now(),
                  "original_hash": this.dedup_hash,
                  "strategy": "hash-based"
                }
              } else { deleted() }
          - switch:
              - check: '!this.is_duplicate'
                processors:
                  - cache:
                      resource: dedup_cache
                      operator: set
                      key: '${! json("dedup_hash") }'
                      value: '${! json("dedup_timestamp") }'

  output:
    switch:
      cases:
        - check: '!this.is_duplicate'
          output:
            http_client:
              url: '${ANALYTICS_ENDPOINT}/events'
              verb: POST
        - output:
            file:
              path: "/var/expanso/duplicates/${!timestamp_unix_date('2006-01-02')}/dupes.jsonl"
              codec: lines