{ "openapi": "3.0.1", "info": { "title": "Lunar Data Cleaner", "description": "Clean CSV, Excel, or JSON files with audit trails, PII masking, and budget control. Remove duplicates, fix missing values, standardize dates/numbers, and get quality reports.", "version": "0.0", "x-build-id": "Eh2pF5M6BNCqrZGUJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/liuyu.digitaltwin~lunar-data-cleaner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-liuyu.digitaltwin-lunar-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/liuyu.digitaltwin~lunar-data-cleaner/runs": { "post": { "operationId": "runs-sync-liuyu.digitaltwin-lunar-data-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/liuyu.digitaltwin~lunar-data-cleaner/run-sync": { "post": { "operationId": "run-sync-liuyu.digitaltwin-lunar-data-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "sourceData" ], "properties": { "sourceData": { "title": "Source Data", "type": "string", "description": "URL or local path to CSV/Excel/JSON file", "default": "https://raw.githubusercontent.com/yuliu-digitaltwin/apify-lunar-data-cleaner/main/example-data.csv" }, "delimiter": { "title": "Delimiter", "enum": [ "auto", ",", ";", "\t", "|" ], "type": "string", "description": "Column delimiter (auto-detect or manual)", "default": "auto" }, "encoding": { "title": "Encoding", "type": "string", "description": "File encoding (auto-detect or manual, e.g., utf-8, iso-8859-1)", "default": "auto" }, "auditLevel": { "title": "Audit Level", "enum": [ "task", "rule" ], "type": "string", "description": "Detailed audit logs: task only or rule-level", "default": "rule" }, "maxChargeUsd": { "title": "Max Charge (USD)", "minimum": 1, "maximum": 10, "type": "number", "description": "Budget limit (soft cap, system hard cap is $10.00)", "default": 5 }, "previewMode": { "title": "Preview Mode", "type": "boolean", "description": "Process only first N rows to test", "default": false }, "previewRows": { "title": "Preview Rows", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Number of rows in preview mode", "default": 100 }, "enablePiiMasking": { "title": "Enable PII Masking", "type": "boolean", "description": "Mask SSN, credit cards, emails (irreversible)", "default": false }, "piiMaskingRules": { "title": "Custom PII Rules", "type": "string", "description": "Comma-separated column names or regex patterns (e.g., phone,ssn)" }, "cellErrorPolicy": { "title": "Cell Error Policy", "enum": [ "skip_cell", "stop_rule" ], "type": "string", "description": "How to handle cell conversion errors", "default": "skip_cell" }, "outputFormat": { "title": "Output Format", "enum": [ "csv", "excel", "json" ], "type": "string", "description": "Format of the cleaned output", "default": "csv" }, "locale": { "title": "Locale", "enum": [ "US", "EU" ], "type": "string", "description": "Date and number format (US or European)", "default": "US" } } }, "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 } } }, "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 } } } } } } } } } }