{
  "openapi": "3.0.1",
  "info": {
    "title": "Advanced JSON / CSV Data Cleaner",
    "description": "Clean, deduplicate, validate and convert JSON, JSONL, CSV and XLSX files. Includes field mapping, optional type inference and heuristic PII redaction.",
    "version": "0.1",
    "x-build-id": "PwReM5e9rOZ2CzgYC"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/flyerlin~advanced-data-cleaner/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-flyerlin-advanced-data-cleaner",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/flyerlin~advanced-data-cleaner/runs": {
      "post": {
        "operationId": "runs-sync-flyerlin-advanced-data-cleaner",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/flyerlin~advanced-data-cleaner/run-sync": {
      "post": {
        "operationId": "run-sync-flyerlin-advanced-data-cleaner",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "properties": {
          "raw_text": {
            "title": "Input text",
            "type": "string",
            "description": "Input text. See README for behavior and limits."
          },
          "source_url": {
            "title": "Source file URL",
            "type": "string",
            "description": "Public downloadable file, up to 30 MB. Provide this OR input text."
          },
          "source_format": {
            "title": "Source format",
            "enum": [
              "auto",
              "json",
              "jsonl",
              "csv",
              "tsv",
              "xlsx"
            ],
            "type": "string",
            "description": "Source format. See README for behavior and limits.",
            "default": "auto"
          },
          "target_format": {
            "title": "Output format",
            "enum": [
              "json",
              "jsonl",
              "csv",
              "xlsx"
            ],
            "type": "string",
            "description": "Output format. See README for behavior and limits.",
            "default": "json"
          },
          "sheet_name": {
            "title": "Excel sheet name",
            "type": "string",
            "description": "Excel sheet name. See README for behavior and limits."
          },
          "delimiter": {
            "title": "CSV delimiter",
            "type": "string",
            "description": "CSV delimiter. See README for behavior and limits."
          },
          "field_mapping": {
            "title": "Field rename mapping",
            "type": "string",
            "description": "JSON object, e.g. {\"old_name\":\"new_name\"}. Top-level fields only."
          },
          "expected_schema": {
            "title": "JSON Schema",
            "type": "string",
            "description": "JSON Schema. See README for behavior and limits."
          },
          "trim_strings": {
            "title": "Trim top-level string values",
            "type": "boolean",
            "description": "Trim top-level string values. See README for behavior and limits.",
            "default": true
          },
          "dedupe": {
            "title": "Remove identical records",
            "type": "boolean",
            "description": "Remove identical records. See README for behavior and limits.",
            "default": true
          },
          "infer_types": {
            "title": "Infer booleans and numbers (may remove leading zeroes)",
            "type": "boolean",
            "description": "Infer booleans and numbers (may remove leading zeroes). See README for behavior and limits.",
            "default": false
          },
          "drop_empty": {
            "title": "Remove empty top-level fields",
            "type": "boolean",
            "description": "Remove empty top-level fields. See README for behavior and limits.",
            "default": false
          },
          "nest_headers": {
            "title": "Convert dotted headers to nested objects",
            "type": "boolean",
            "description": "Convert dotted headers to nested objects. See README for behavior and limits.",
            "default": false
          },
          "redact_pii": {
            "title": "Heuristic PII redaction",
            "type": "boolean",
            "description": "Heuristic PII redaction. See README for behavior and limits.",
            "default": false
          },
          "drop_invalid": {
            "title": "Drop records that fail Schema validation",
            "type": "boolean",
            "description": "Drop records that fail Schema validation. See README for behavior and limits.",
            "default": false
          },
          "max_records": {
            "title": "Maximum records",
            "minimum": 1,
            "maximum": 100000,
            "type": "integer",
            "description": "Maximum records. See README for behavior and limits.",
            "default": 20000
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}