{ "openapi": "3.0.1", "info": { "title": "Spreadsheet Doctor: Clean, Dedupe, Join & Reconcile CSV/Excel", "description": "Clean messy CSV/XLSX files (emails, E.164 phones, ISO dates, numbers, ZIPs), remove duplicates, join several files on a key, and reconcile two files cell by cell. Strict JSON schemas, fail-loud error codes, built for AI agents.", "version": "0.1", "x-build-id": "om6lO3V9k3rDH0svP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/errandkit~spreadsheet-doctor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-errandkit-spreadsheet-doctor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/errandkit~spreadsheet-doctor/runs": { "post": { "operationId": "runs-sync-errandkit-spreadsheet-doctor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/errandkit~spreadsheet-doctor/run-sync": { "post": { "operationId": "run-sync-errandkit-spreadsheet-doctor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "operation" ], "properties": { "operation": { "title": "Operation", "enum": [ "profile", "clean", "dedupe", "join", "reconcile" ], "type": "string", "description": "profile = inspect only; clean = fix formats; dedupe = remove duplicates; join = merge 2-10 files on a key; reconcile = compare exactly 2 files cell by cell." }, "fileUrls": { "title": "Files (upload or URLs)", "maxItems": 10, "type": "array", "description": "Upload CSV/TSV/XLSX files or paste public http(s) URLs. Order matters for join (left to right) and reconcile (left, right). Max 10 files, 10 MB each." }, "inlineFiles": { "title": "Inline files (for API / AI agents)", "maxItems": 10, "type": "array", "description": "Alternative to uploads: [{\"name\": \"a.csv\", \"text\": \"email,name\\nx@y.com,X\"}] or {\"name\": \"b.xlsx\", \"content_base64\": \"...\"}. Inline files come after uploaded files." }, "keys": { "title": "Key columns", "maxItems": 10, "type": "array", "description": "Columns that identify a record. dedupe: duplicate keys (empty = whole row). join: 'on' columns present in every file. reconcile: key columns of the left file. Original or snake_case names both work.", "items": { "type": "string" } }, "keysPerFile": { "title": "Key columns per file (join/reconcile)", "type": "object", "description": "Only when key names differ between files, e.g. {\"billing.xlsx\": [\"Customer Email\"]}. For reconcile, the entry for the second file is used as its keys." }, "how": { "title": "Join type", "enum": [ "inner", "left", "outer" ], "type": "string", "description": "inner = only matches; left = all rows of the first file; outer = all rows of all files.", "default": "left" }, "match": { "title": "Key matching", "enum": [ "normalized", "exact" ], "type": "string", "description": "normalized ignores case, spaces and punctuation in keys; exact compares as-is.", "default": "normalized" }, "keep": { "title": "Which duplicate to keep (dedupe)", "enum": [ "merge", "first", "last" ], "type": "string", "description": "merge = keep the first row and fill its empty cells from later duplicates.", "default": "merge" }, "compareColumns": { "title": "Columns to compare (reconcile)", "type": "array", "description": "Default: every non-key column present in both files.", "items": { "type": "string" } }, "numericTolerance": { "title": "Numeric tolerance (reconcile)", "minimum": 0, "type": "number", "description": "Treat numbers within this absolute difference as equal.", "default": 0 }, "cleanOptions": { "title": "Cleaning options", "type": "object", "description": "Optional overrides, e.g. {\"date_order\": \"DMY\", \"default_phone_region\": \"GB\", \"column_types\": {\"Mobile\": \"phone\"}}. See README for all fields." }, "outputFormat": { "title": "Output file format", "enum": [ "csv", "xlsx", "both" ], "type": "string", "description": "Files saved to the key-value store for each output table.", "default": "csv" }, "maxDatasetRows": { "title": "Max rows pushed to the dataset", "minimum": 0, "maximum": 200000, "type": "integer", "description": "Output rows are also pushed to the dataset (handy for agents). Full tables are always in the key-value store.", "default": 10000 } } }, "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 } } } } } } } } } }