[ https://issues.apache.org/jira/browse/HIVE-6198?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14056060#comment-14056060 ]
Hive QA commented on HIVE-6198: ------------------------------- {color:red}Overall{color}: -1 at least one tests failed Here are the results of testing the latest attachment: https://issues.apache.org/jira/secure/attachment/12654773/HIVE-6198.2.patch.txt {color:red}ERROR:{color} -1 due to 98 failed/errored test(s), 5701 tests executed *Failed tests:* {noformat} org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_analyze_table_null_partition org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_annotate_stats_filter org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_annotate_stats_groupby org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_annotate_stats_join org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_annotate_stats_limit org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_annotate_stats_part org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_annotate_stats_select org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_annotate_stats_table org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_annotate_stats_union org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_avro_decimal org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_avro_nullable_fields org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_avro_schema_error_message org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_avro_schema_literal org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_case_sensitivity org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_char_udf1 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_columnarserde_create_shortcut org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_columnstats_partlvl org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_columnstats_partlvl_dp org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_columnstats_tbllvl org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_compute_stats_binary org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_compute_stats_boolean org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_compute_stats_decimal org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_compute_stats_double org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_compute_stats_empty_table org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_compute_stats_long org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_compute_stats_string org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_constant_prop org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_convert_enum_to_string org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_describe_xpath org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_display_colstats_tbllvl org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_distinct_stats org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_input17 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_input5 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_input_columnarserde org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_input_dynamicserde org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_input_lazyserde org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_input_testxpath org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_input_testxpath2 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_input_testxpath3 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_input_testxpath4 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_inputddl8 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_join_thrift org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_metadata_only_queries org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_metadata_only_queries_with_filters org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_orc_create org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_parquet_create org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_serde_reported_schema org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats10 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats12 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats13 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats14 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats16 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats5 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats6 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats7 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats8 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats9 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats_invalidation org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats_noscan_2 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_stats_only_null org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_statsfs org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_udf_case_thrift org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_udf_coalesce org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_udf_isnull_isnotnull org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_udf_size org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_union21 org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_varchar_udf1 org.apache.hadoop.hive.cli.TestContribCliDriver.testCliDriver_udaf_example_avg org.apache.hadoop.hive.cli.TestContribCliDriver.testCliDriver_udf_example_arraymapstruct org.apache.hadoop.hive.cli.TestHBaseCliDriver.testCliDriver_hbase_stats org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_metadata_only_queries org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_stats_counter org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_stats_counter_partitioned org.apache.hadoop.hive.cli.TestMinimrCliDriver.testCliDriver_stats_counter org.apache.hadoop.hive.cli.TestMinimrCliDriver.testCliDriver_stats_counter_partitioned org.apache.hadoop.hive.ql.parse.TestParse.testParse_case_sensitivity org.apache.hadoop.hive.ql.parse.TestParse.testParse_input1 org.apache.hadoop.hive.ql.parse.TestParse.testParse_input5 org.apache.hadoop.hive.ql.parse.TestParse.testParse_input_testxpath org.apache.hadoop.hive.ql.parse.TestParse.testParse_input_testxpath2 org.apache.hadoop.hive.serde2.avro.TestAvroDeserializer.canDeserializeMapWithNullablePrimitiveValues org.apache.hadoop.hive.serde2.avro.TestAvroDeserializer.canDeserializeMapsWithPrimitiveKeys org.apache.hadoop.hive.serde2.avro.TestAvroDeserializer.canDeserializeRecords org.apache.hadoop.hive.serde2.avro.TestAvroDeserializer.canDeserializeUnions org.apache.hadoop.hive.serde2.avro.TestAvroObjectInspectorGenerator.primitiveTypesWorkCorrectly org.apache.hadoop.hive.serde2.avro.TestAvroSerde.badSchemaURLProvidedReturnsErrorSchema org.apache.hadoop.hive.serde2.avro.TestAvroSerde.bothPropertiesSetToNoneReturnsErrorSchema org.apache.hadoop.hive.serde2.avro.TestAvroSerde.emptySchemaProvidedReturnsErrorSchema org.apache.hadoop.hive.serde2.avro.TestAvroSerde.emptySchemaURLProvidedReturnsErrorSchema org.apache.hadoop.hive.serde2.avro.TestAvroSerde.gibberishSchemaProvidedReturnsErrorSchema org.apache.hadoop.hive.serde2.avro.TestAvroSerde.noSchemaProvidedReturnsErrorSchema org.apache.hadoop.hive.serde2.objectinspector.TestStandardObjectInspectors.testStandardStructObjectInspector org.apache.hadoop.hive.serde2.objectinspector.TestStandardObjectInspectors.testStandardUnionObjectInspector org.apache.hadoop.hive.serde2.objectinspector.TestUnionStructObjectInspector.testUnionStructObjectInspector org.apache.hive.hcatalog.common.TestHCatUtil.testGetTableSchemaWithPtnColsSerDeReportedFields org.apache.hive.hcatalog.mapreduce.TestHCatHiveThriftCompatibility.testDynamicCols org.apache.hive.hcatalog.pig.TestOrcHCatLoader.testReadDataPrimitiveTypes org.apache.hive.jdbc.miniHS2.TestHiveServer2.testConnection {noformat} Test results: http://ec2-174-129-184-35.compute-1.amazonaws.com/jenkins/job/PreCommit-HIVE-Build/721/testReport Console output: http://ec2-174-129-184-35.compute-1.amazonaws.com/jenkins/job/PreCommit-HIVE-Build/721/console Test logs: http://ec2-174-129-184-35.compute-1.amazonaws.com/logs/PreCommit-HIVE-Build-721/ Messages: {noformat} Executing org.apache.hive.ptest.execution.PrepPhase Executing org.apache.hive.ptest.execution.ExecutionPhase Executing org.apache.hive.ptest.execution.ReportingPhase Tests exited with: TestsFailedException: 98 tests failed {noformat} This message is automatically generated. ATTACHMENT ID: 12654773 > ORC file and struct column names are case sensitive > --------------------------------------------------- > > Key: HIVE-6198 > URL: https://issues.apache.org/jira/browse/HIVE-6198 > Project: Hive > Issue Type: Bug > Components: CLI, File Formats > Affects Versions: 0.11.0, 0.12.0 > Reporter: Viraj Bhat > Assignee: Navis > Attachments: HIVE-6198.1.patch.txt, HIVE-6198.2.patch.txt > > > HiveQL document states that the "Table names and column names are case > insensitive". But the struct behavior for ORC file is different. > Consider a sample text file: > {code} > $ cat data.txt > line1|key11:value11,key12:value12,key13:value13|a,b,c|one,two > line2|key21:value21,key22:value22,key23:value23|d,e,f|three,four > line3|key31:value31,key32:value32,key33:value33|g,h,i|five,six > {code} > Creating a table stored as txt and then using this to create a table stored > as orc > {code} > CREATE TABLE orig ( > str STRING, > mp MAP<STRING,STRING>, > lst ARRAY<STRING>, > strct STRUCT<A:STRING,B:STRING> > ) ROW FORMAT DELIMITED > FIELDS TERMINATED BY '|' > COLLECTION ITEMS TERMINATED BY ',' > MAP KEYS TERMINATED BY ':'; > LOAD DATA LOCAL 'test.txt' INTO TABLE orig; > CREATE TABLE tableorc ( > str STRING, > mp MAP<STRING,STRING>, > lst ARRAY<STRING>, > strct STRUCT<A:STRING,B:STRING> > ) STORED AS ORC; > INSERT OVERWRITE TABLE tableorc SELECT * FROM orig; > {code} > Suppose we project columns or read the *strct* columns for both table types, > here are the results. I have also tested the same with *RC*. The behavior is > similar to *txt* files. > {code} > hive> SELECT * FROM orig; > line1 {"key11":"value11","key12":"value12","key13":"value13"} ["a","b","c"] > > {"a":"one","b":"two"} > line2 {"key21":"value21","key22":"value22","key23":"value23"} ["d","e","f"] > > {"a":"three","b":"four"} > line3 {"key31":"value31","key32":"value32","key33":"value33"} ["g","h","i"] > > {"a":"five","b":"six"} > Time taken: 0.126 seconds, Fetched: 3 row(s) > hive> SELECT * FROM tableorc; > line1 {"key12":"value12","key11":"value11","key13":"value13"} ["a","b","c"] > > {"A":"one","B":"two"} > line2 {"key21":"value21","key23":"value23","key22":"value22"} ["d","e","f"] > > {"A":"three","B":"four"} > line3 {"key33":"value33","key31":"value31","key32":"value32"} ["g","h","i"] > > {"A":"five","B":"six"} > Time taken: 0.178 seconds, Fetched: 3 row(s) > hive> SELECT strct FROM tableorc; > {"a":"one","b":"two"} > {"a":"three","b":"four"} > {"a":"five","b":"six"} > hive>SELECT strct.A FROM orig; > one > three > five > hive>SELECT strct.a FROM orig; > one > three > five > hive>SELECT strct.A FROM tableorc; > one > three > five > hive>SELECT strct.a FROM tableorc; > FAILED: Execution Error, return code 2 from > org.apache.hadoop.hive.ql.exec.mr.MapRedTask > MapReduce Jobs Launched: > Job 0: Map: 1 HDFS Read: 0 HDFS Write: 0 FAIL > {code} > So it seems that ORC behaves differently for struct columns. Also why are we > storing the column names for struct for the other types as CASE SENSITIVE? > What is the standard for Hive QL with respect to structs? > Regards > Viraj -- This message was sent by Atlassian JIRA (v6.2#6252)