def guess_format(self, data): """ Input: data: {'type': 'file', 'path': '/user/hue/logs.csv'} Output: {'format': { type: 'csv', fieldSeparator : ",", recordSeparator: '\n', quoteChar : "\"" }, 'columns': [ {name: business_id, type: string}, {name: cool, type: integer}, {name: date, type: date} ] } """ file_format = get_file_format_instance(data['file']) return file_format.get_format()
def guess_format(self, data): """ Input: data: {'type': 'file', 'path': '/user/hue/logs.csv'} Output: {'format': { type: 'csv', fieldSeparator : ",", recordSeparator: '\n', quoteChar : "\"" }, 'columns': [ {name: business_id, type: string}, {name: cool, type: integer}, {name: date, type: date} ] } """ file_format = get_file_format_instance(data['file']) return file_format.get_format()
def guess_field_types(self, data): file_format = get_file_format_instance(data['file'], data['format']) return file_format.get_fields() if file_format else {'columns': []}
def guess_format(self, data): file_format = get_file_format_instance(data['file']) return file_format.get_format()
def guess_field_types(self, data): file_format = get_file_format_instance(data['file'], data['format']) return file_format.get_fields() if file_format else {'columns':[]}
def guess_field_types(self, data): file_format = get_file_format_instance(data['file'], data['format']) fields = file_format.get_fields() if file_format else {'columns': []} for field in fields['columns']: self._port_field_types(field) return fields
def guess_format(self, data): file_format = get_file_format_instance(data['file']) return file_format.get_format()