{ "openapi": "3.0.1", "info": { "title": "Mojibake Text Repair", "description": "Repair garbled Unicode strings or selected text fields in supplied JSON records. Export corrected records, preserved identities, changed flags and bounded repair summaries with ftfy; no scraping or remote file access.", "version": "0.1", "x-build-id": "DG43Zgai6HV14xnEs" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~mojibake-text-repair/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-mojibake-text-repair", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation-lab~mojibake-text-repair/runs": { "post": { "operationId": "runs-sync-automation-lab-mojibake-text-repair", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation-lab~mojibake-text-repair/run-sync": { "post": { "operationId": "run-sync-automation-lab-mojibake-text-repair", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "texts": { "title": "Text strings", "type": "array", "description": "1–1000 supplied strings, including empty strings. Mutually exclusive with records. Each string is at most 100000 JavaScript UTF-16 code units; total selected text across all supplied entries is at most 200000.", "items": { "type": "string" } }, "records": { "title": "JSON records", "type": "array", "description": "1–1000 JSON objects. Mutually exclusive with texts. Requires fields. Unselected properties are preserved; nested paths are not supported.", "items": { "type": "object" } }, "fields": { "title": "Selected text fields", "type": "array", "description": "Required with records; rejected with texts. 1–20 distinct case-sensitive top-level keys, each present with a string value in every record. Dots are literal key characters, not path separators. Missing or non-string values fail the whole run.", "items": { "type": "string" } }, "idField": { "title": "Record identity field", "type": "string", "description": "Optional with records only. Exact case-sensitive top-level key containing a string or number in every record. Identity is taken from the original record. Otherwise recordId is the zero-based input index. Duplicate identities are preserved, not deduplicated." }, "cleanText": { "title": "Additional text cleanup", "type": "boolean", "description": "Both modes: when true, also straighten quotes, expand Latin ligatures, normalize character width and line breaks, and remove terminal escapes and control characters. When false these transformations are disabled. HTML entities are never unescaped. Unicode normalization is controlled separately.", "default": false }, "normalization": { "title": "Unicode normalization", "enum": [ "NFC", "NFKC", "none" ], "type": "string", "description": "Both modes: NFC composes canonical characters; NFKC also folds compatibility characters and may alter intentional formatting. none disables normalization. This does not disable mojibake repair or surrogate repair.", "default": "NFC" }, "maxItems": { "title": "Maximum output records", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Global output-record cap, not text-field count. Outputs the first N entries in supplied order without deduplication. All supplied entries are validated first, including omitted entries. Zero/unlimited is unsupported. SUMMARY reports omitted entries.", "default": 1000 } } }, "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 } } } } } } } } } }