in athena_glue_service_logs/cloudfront.py [0:0]
def _build_storage_descriptor(self, partition_values=None):
if partition_values is None:
partition_values = []
return {
"Columns": [
{"Name": "time", "Type": "timestamp"},
{"Name": "location", "Type": "string"},
{"Name": "bytes", "Type": "bigint"},
{"Name": "requestip", "Type": "string"},
{"Name": "method", "Type": "string"},
{"Name": "host", "Type": "string"},
{"Name": "uri", "Type": "string"},
{"Name": "status", "Type": "int"},
{"Name": "referrer", "Type": "string"},
{"Name": "useragent", "Type": "string"},
{"Name": "querystring", "Type": "string"},
{"Name": "cookie", "Type": "string"},
{"Name": "resulttype", "Type": "string"},
{"Name": "requestid", "Type": "string"},
{"Name": "hostheader", "Type": "string"},
{"Name": "requestprotocol", "Type": "string"},
{"Name": "requestbytes", "Type": "bigint"},
{"Name": "timetaken", "Type": "double"},
{"Name": "xforwardedfor", "Type": "string"},
{"Name": "sslprotocol", "Type": "string"},
{"Name": "sslcipher", "Type": "string"},
{"Name": "responseresulttype", "Type": "string"},
{"Name": "httpversion", "Type": "string"}
],
"Location": self.partitioner.build_partitioned_path(partition_values),
"InputFormat": "org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat",
"OutputFormat": "org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat",
"SerdeInfo": {
"SerializationLibrary": "org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe",
"Parameters": {}
},
"BucketColumns": [], # Required or SHOW CREATE TABLE fails
"Parameters": {} # Required or create_dynamic_frame.from_catalog fails for partitions
}