{ "openapi": "3.0.1", "info": { "title": "Dataset Schema Guard — Validate & Quarantine Records", "description": "Validate any Apify dataset with required fields, types, ranges, regex, allowed values, lengths, uniqueness, and unexpected-field checks. Separate valid records from rejected records with exact failure reasons.", "version": "0.1", "x-build-id": "WLDweUtsa3QgZtOgK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/orangepinlabs~dataset-schema-guard/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-orangepinlabs-dataset-schema-guard", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/orangepinlabs~dataset-schema-guard/runs": { "post": { "operationId": "runs-sync-orangepinlabs-dataset-schema-guard", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/orangepinlabs~dataset-schema-guard/run-sync": { "post": { "operationId": "run-sync-orangepinlabs-dataset-schema-guard", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "rules" ], "properties": { "sourceDatasetId": { "title": "Source dataset", "type": "string", "description": "Dataset ID or name containing the records to validate. The source is read-only." }, "records": { "title": "Inline records", "maxItems": 10000, "type": "array", "description": "Optional JSON records for instant testing. Used only when Source dataset is blank.", "items": { "type": "object" }, "default": [ { "id": "lead-001", "contact": { "email": "ada@example.com" }, "score": 92 }, { "id": "lead-002", "contact": { "email": "grace@example.com" }, "score": 78 }, { "id": "lead-003", "contact": { "email": "not-an-email" }, "score": 110 } ] }, "rules": { "title": "Field rules", "minItems": 1, "maxItems": 100, "type": "array", "description": "Schema rules for nested dot-path fields. Use the JSON editor to add required fields, types, ranges, patterns, allowed values, and uniqueness checks.", "items": { "type": "object", "properties": { "field": { "title": "Field path", "type": "string", "description": "Dot path such as contact.email or product.price." }, "required": { "title": "Required", "type": "boolean", "description": "Reject the record when this field is missing, null, or undefined.", "default": true }, "type": { "title": "Data type", "type": "string", "description": "Expected JSON-compatible type.", "enum": [ "any", "string", "number", "integer", "boolean", "array", "object" ], "default": "any" }, "allowEmpty": { "title": "Allow empty values", "type": "boolean", "description": "Allow empty strings, arrays, and objects.", "default": true }, "min": { "title": "Minimum number", "type": "number", "description": "Inclusive minimum for numeric fields." }, "max": { "title": "Maximum number", "type": "number", "description": "Inclusive maximum for numeric fields." }, "minLength": { "title": "Minimum length", "type": "integer", "description": "Inclusive minimum length for strings and arrays.", "minimum": 0 }, "maxLength": { "title": "Maximum length", "type": "integer", "description": "Inclusive maximum length for strings and arrays.", "minimum": 0 }, "pattern": { "title": "Regular expression", "type": "string", "description": "JavaScript regular expression applied to string fields." }, "allowedValues": { "title": "Allowed values", "type": "array", "description": "Exact string values accepted for the field.", "editor": "stringList", "items": { "type": "string" } }, "unique": { "title": "Require unique values", "type": "boolean", "description": "Reject later records that repeat this value.", "default": false } }, "required": [ "field" ] }, "default": [ { "field": "id", "required": true, "type": "string", "allowEmpty": false, "unique": true }, { "field": "contact.email", "required": true, "type": "string", "pattern": "^[^@\\s]+@[^@\\s]+\\.[^@\\s]+$" }, { "field": "score", "required": false, "type": "number", "min": 0, "max": 100 } ] }, "rejectUnknownTopLevelFields": { "title": "Reject unexpected top-level fields", "type": "boolean", "description": "When enabled, a record is rejected if it contains a top-level field not represented by any rule.", "default": false }, "maxErrorsPerRecord": { "title": "Maximum errors per rejected record", "minimum": 1, "maximum": 100, "type": "integer", "description": "Caps the error list for badly malformed records while continuing validation.", "default": 20 }, "maxItems": { "title": "Maximum source records", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Safety limit. The run fails before validation if the source dataset is larger.", "default": 100000 } } }, "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 } } } } } } } } } }