parisni commented on issue #7531:
URL: https://github.com/apache/hudi/issues/7531#issuecomment-1362582189

   @yihua  reproductible example
   ```
   # add uuid column with comment foo bar
   from pyspark.sql.types import StructType, StructField, StringType, 
IntegerType
   data = [
       (1, "f5c2ebfd-f57b-4ff3-ac5c-f30674037b21", "A", "BC", "C"),
       (2, "f5c2ebfd-f57b-4ff3-ac5c-f30674037b22", "A", "BC", "C"),
       (3, "f5c2ebfd-f57b-4ff3-ac5c-f30674037b21", "A", "BC", "C"),
       (4, "f5c2ebfd-f57b-4ff3-ac5c-f30674037b22", "A", "BC", "C"),
   ]
   
   schema = StructType(
       [
           StructField("uuid", IntegerType(), True, {"comment": "foo bar"}),
           StructField("user_id", StringType(), True),
           StructField("col1", StringType(), True),
           StructField("ts", StringType(), True),
           StructField("part", StringType(), True),
       ]
   )
   df = spark.createDataFrame(data=data, schema=schema)
   
   
   tableName = "test_hudi_comment"
   basePath = f"/tmp/hudi/"
   
   hudi_options = {
       "hoodie.table.name": tableName,
       "hoodie.datasource.write.recordkey.field": "uuid",
       "hoodie.datasource.write.partitionpath.field": "part",
       "hoodie.datasource.write.table.name": tableName,
       "hoodie.datasource.write.operation": "insert",
       "hoodie.datasource.write.precombine.field": "ts",
       "hoodie.upsert.shuffle.parallelism": 1,
       "hoodie.insert.shuffle.parallelism": 1,
       "hoodie.datasource.hive_sync.enable": "false",
   }
   
(df.write.format("hudi").options(**hudi_options).mode("append").save(basePath))
   spark.read.format("hudi").load(basePath).registerTempTable("foo")
   spark.sql("desc extended foo").show()
   
   # there is no foo bar on the hudi side
   +--------------------+---------+-------+
   |            col_name|data_type|comment|
   +--------------------+---------+-------+
   | _hoodie_commit_time|   string|   null|
   |_hoodie_commit_seqno|   string|   null|
   |  _hoodie_record_key|   string|   null|
   |_hoodie_partition...|   string|   null|
   |   _hoodie_file_name|   string|   null|
   |                uuid|      int|   null|
   |             user_id|   string|   null|
   |                col1|   string|   null|
   |                  ts|   string|   null|
   |                part|   string|   null|
   +--------------------+---------+-------+
   
   # the avro has foo bar doc
     "partitionToWriteStats" : {
       "C" : [ {
         "fileId" : "e90400c1-5311-4fdc-83f2-757326c7560d-0",
         "path" : 
"C/e90400c1-5311-4fdc-83f2-757326c7560d-0_0-17-36_20221222095833220.parquet",
         "prevCommit" : "null",
         "numWrites" : 4,
         "numDeletes" : 0,
         "numUpdateWrites" : 0,
         "numInserts" : 4,
         "totalWriteBytes" : 435614,
         "totalWriteErrors" : 0,
         "tempPath" : null,
         "partitionPath" : "C",
         "totalLogRecords" : 0,
         "totalLogFilesCompacted" : 0,
         "totalLogSizeCompacted" : 0,
         "totalUpdatedRecordsCompacted" : 0,
         "totalLogBlocks" : 0,
         "totalCorruptLogBlock" : 0,
         "totalRollbackBlocks" : 0,
         "fileSizeInBytes" : 435614,
         "minEventTime" : null,
         "maxEventTime" : null
       } ]
     },
     "compacted" : false,
     "extraMetadata" : {
       "schema" : 
"{\"type\":\"record\",\"name\":\"test_hudi_comment_record\",\"namespace\":\"hoodie.test_hudi_comment\",\"fields\":[{\"name\":\"uuid\",\"type\":[\"null\",\"int\"],\"doc\":\"foo
 
bar\",\"default\":null},{\"name\":\"user_id\",\"type\":[\"null\",\"string\"],\"default\":null},{\"name\":\"col1\",\"type\":[\"null\",\"string\"],\"default\":null},{\"name\":\"ts\",\"type\":[\"null\",\"string\"],\"default\":null},{\"name\":\"part\",\"type\":[\"null\",\"string\"],\"default\":null}]}"
     },
     "operationType" : "INSERT"
   }
   
   
   ```


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to