Dataset Cleaner & Exporter

{'type': 'object', 'required': ['rows'], 'properties': {'rows': {'type': 'array', 'items': {'type': 'object'}, 'description': 'The rows to clean. Each row is a JSON object; keys may differ between rows and values may be nested.'}, 'flatten': {'type': 'boolean', 'description': 'Default true. Turn nested objects into flat columns. Arrays become one JSON-text cell.'}, 'maxItems': {'type': 'integer', 'minimum': 0, 'description': 'Optional cap: read at most this many rows and return at most this many. 0 (default) means no cap.'}, 'dedupKeys': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Fields that identify a duplicate, for example ["Email"]. Empty compares the whole row. Use the final column names: flattened (Details_founded) and renamed. Exact and case-sensitive. Rows where every key is empty count as duplicates of each other.'}, 'dedupMode': {'enum': ['none', 'exact', 'normalized', 'fuzzy'], 'type': 'string', 'description': 'How duplicates are found. normalized (default) ignores case and whitespace; exact needs identical values; fuzzy also merges near-duplicates (up to 100 rows and 1000 characters of key text, so name a short field in dedupKeys); none keeps every row.'}, 'stripHtml': {'type': 'boolean', 'description': 'Default false. Remove HTML tags and decode common entities in text.'}, 'cleanFields': {'type': 'boolean', 'description': 'Default true. Normalize emails, phone numbers and URLs, detected by field name or value shape.'}, 'coerceTypes': {'type': 'boolean', 'description': 'Default false. Turn "42" into 42 and "true" into true. Leading-zero values like "007" stay text.'}, 'emptyToNull': {'type': 'boolean', 'description': 'Default true. Blank text becomes null.'}, 'keepStrategy': {'enum': ['most_complete', 'first', 'last'], 'type': 'string', 'description': 'Which duplicate survives: most_complete (default, fewest empty fields), first or last.'}, 'outputFormat': {'enum': ['json', 'csv'], 'type': 'string', 'description': 'json (default) returns rows; csv returns the same result as CSV text in "csv" instead.'}, 'columnsToKeep': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Keep only these columns (flattened names). Takes priority over columnsToRemove.'}, 'columnRenameMap': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'object', 'additionalProperties': {'type': 'string'}}], 'description': 'Rename columns after keep/remove, as ["oldName:newName"] or {"oldName":"newName"}, for example {"Details_founded":"founded"}.'}, 'columnsToRemove': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Drop these columns (flattened names). Ignored if columnsToKeep is set.'}, 'dropEmptyFields': {'type': 'boolean', 'description': 'Default false. Remove null and empty fields from each row.'}, 'expandArrayField': {'type': 'string', 'description': 'Optional. One top-level array field (for example "offers") to explode into one row per entry, repeating the other fields. Object entries become columns. The expanded total must stay within the row limit.'}, 'flattenSeparator': {'type': 'string', 'description': 'Joins nested key paths when flattening. Default "_".'}, 'similarityThreshold': {'type': 'number', 'maximum': 0.99, 'minimum': 0.5, 'description': 'Fuzzy mode only. 0.5 to 0.99, default 0.9. Higher is stricter.'}}, 'additionalProperties': False}

{'type': 'object', 'properties': {}, 'additionalProperties': False}