[
https://issues.apache.org/jira/browse/PARQUET-2078?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17407243#comment-17407243
]
ASF GitHub Bot commented on PARQUET-2078:
-----------------------------------------
ggershinsky commented on a change in pull request #925:
URL: https://github.com/apache/parquet-mr/pull/925#discussion_r699207678
##########
File path:
parquet-hadoop/src/main/java/org/apache/parquet/format/converter/ParquetMetadataConverter.java
##########
@@ -1226,12 +1226,25 @@ public ParquetMetadata readParquetMetadata(InputStream
from) throws IOException
static FileMetaData filterFileMetaDataByMidpoint(FileMetaData metaData,
RangeMetadataFilter filter) {
List<RowGroup> rowGroups = metaData.getRow_groups();
List<RowGroup> newRowGroups = new ArrayList<RowGroup>();
+ long preStartIndex = 0;
+ long preCompressedSize = 0;
for (RowGroup rowGroup : rowGroups) {
long totalSize = 0;
long startIndex;
-
if (rowGroup.isSetFile_offset()) {
- startIndex = rowGroup.getFile_offset();
+ assert rowGroup.isSetTotal_compressed_size();
+
+ if (preStartIndex == 0) {
+ //the first block always holds the truth
+ startIndex = rowGroup.getFile_offset();
+ } else {
+ //calculate offset for other blocks
Review comment:
Could you expand the comment a bit, to briefly explain the problem?
(maybe with mentioning the jira number). To help ensure future changes don't
revert this to the more intuitive getFile_offset().
--
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: dev-unsubscr...@parquet.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
> Failed to read parquet file after writing with the same parquet version
> -----------------------------------------------------------------------
>
> Key: PARQUET-2078
> URL: https://issues.apache.org/jira/browse/PARQUET-2078
> Project: Parquet
> Issue Type: Bug
> Components: parquet-mr
> Affects Versions: 1.12.0
> Reporter: Nemon Lou
> Assignee: Nemon Lou
> Priority: Critical
> Fix For: 1.13.0, 1.12.1
>
> Attachments:
> PARQUET_2078_how_to_fix_rowgroup_fileoffset_for_branch_1.12.x.patch,
> tpcds_customer_footer.json
>
>
> Writing parquet file with version 1.12.0 in Apache Hive, then read that
> file, returns the following error:
> {noformat}
> Caused by: java.lang.IllegalStateException: All of the offsets in the split
> should be found in the file. expected: [4, 133961161] found:
> [BlockMetaData{1530100, 133961157 [ColumnMetaData{UNCOMPRESSED
> [c_customer_sk] optional int64 c_customer_sk [PLAIN, RLE, BIT_PACKED], 4},
> ColumnMetaData{UNCOMPRESSED [c_customer_id] optional binary c_customer_id
> (STRING) [PLAIN, RLE, BIT_PACKED], 12243647}, ColumnMetaData{UNCOMPRESSED
> [c_current_cdemo_sk] optional int64 c_current_cdemo_sk [PLAIN, RLE,
> BIT_PACKED], 42848491}, ColumnMetaData{UNCOMPRESSED [c_current_hdemo_sk]
> optional int64 c_current_hdemo_sk [RLE, PLAIN_DICTIONARY, BIT_PACKED],
> 54868535}, ColumnMetaData{UNCOMPRESSED [c_current_addr_sk] optional int64
> c_current_addr_sk [PLAIN, RLE, BIT_PACKED], 57421932},
> ColumnMetaData{UNCOMPRESSED [c_first_shipto_date_sk] optional int64
> c_first_shipto_date_sk [RLE, PLAIN_DICTIONARY, BIT_PACKED], 69694809},
> ColumnMetaData{UNCOMPRESSED [c_first_sales_date_sk] optional int64
> c_first_sales_date_sk [RLE, PLAIN_DICTIONARY, BIT_PACKED], 72093040},
> ColumnMetaData{UNCOMPRESSED [c_salutation] optional binary c_salutation
> (STRING) [RLE, PLAIN_DICTIONARY, BIT_PACKED], 74461508},
> ColumnMetaData{UNCOMPRESSED [c_first_name] optional binary c_first_name
> (STRING) [RLE, PLAIN_DICTIONARY, BIT_PACKED], 75092758},
> ColumnMetaData{UNCOMPRESSED [c_last_name] optional binary c_last_name
> (STRING) [RLE, PLAIN_DICTIONARY, BIT_PACKED], 77626525},
> ColumnMetaData{UNCOMPRESSED [c_preferred_cust_flag] optional binary
> c_preferred_cust_flag (STRING) [RLE, PLAIN_DICTIONARY, BIT_PACKED],
> 80116456}, ColumnMetaData{UNCOMPRESSED [c_birth_day] optional int32
> c_birth_day [RLE, PLAIN_DICTIONARY, BIT_PACKED], 80505351},
> ColumnMetaData{UNCOMPRESSED [c_birth_month] optional int32 c_birth_month
> [RLE, PLAIN_DICTIONARY, BIT_PACKED], 81581772}, ColumnMetaData{UNCOMPRESSED
> [c_birth_year] optional int32 c_birth_year [RLE, PLAIN_DICTIONARY,
> BIT_PACKED], 82473740}, ColumnMetaData{UNCOMPRESSED [c_birth_country]
> optional binary c_birth_country (STRING) [RLE, PLAIN_DICTIONARY,
> BIT_PACKED], 83921564}, ColumnMetaData{UNCOMPRESSED [c_login] optional binary
> c_login (STRING) [RLE, PLAIN_DICTIONARY, BIT_PACKED], 85457674},
> ColumnMetaData{UNCOMPRESSED [c_email_address] optional binary c_email_address
> (STRING) [PLAIN, RLE, BIT_PACKED], 85460523}, ColumnMetaData{UNCOMPRESSED
> [c_last_review_date_sk] optional int64 c_last_review_date_sk [RLE,
> PLAIN_DICTIONARY, BIT_PACKED], 132146109}]}]
> at
> org.apache.parquet.hadoop.ParquetRecordReader.initializeInternalReader(ParquetRecordReader.java:172)
> ~[parquet-hadoop-bundle-1.12.0.jar:1.12.0]
> at
> org.apache.parquet.hadoop.ParquetRecordReader.initialize(ParquetRecordReader.java:140)
> ~[parquet-hadoop-bundle-1.12.0.jar:1.12.0]
> at
> org.apache.hadoop.hive.ql.io.parquet.read.ParquetRecordReaderWrapper.<init>(ParquetRecordReaderWrapper.java:95)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.io.parquet.read.ParquetRecordReaderWrapper.<init>(ParquetRecordReaderWrapper.java:60)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat.getRecordReader(MapredParquetInputFormat.java:89)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.io.CombineHiveRecordReader.<init>(CombineHiveRecordReader.java:96)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native
> Method) ~[?:1.8.0_292]
> at
> sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
> ~[?:1.8.0_292]
> at
> sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
> ~[?:1.8.0_292]
> at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
> ~[?:1.8.0_292]
> at
> org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileRecordReader.initNextRecordReader(HadoopShimsSecure.java:254)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileRecordReader.<init>(HadoopShimsSecure.java:214)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileInputFormatShim.getRecordReader(HadoopShimsSecure.java:342)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.io.CombineHiveInputFormat.getRecordReader(CombineHiveInputFormat.java:716)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.mapred.MapTask$TrackedRecordReader.<init>(MapTask.java:175)
> ~[hadoop-mapreduce-client-core-3.1.4.jar:?]
> at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:444)
> ~[hadoop-mapreduce-client-core-3.1.4.jar:?]
> at org.apache.hadoop.mapred.MapTask.run(MapTask.java:349)
> ~[hadoop-mapreduce-client-core-3.1.4.jar:?]
> at
> org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:271)
> ~[hadoop-mapreduce-client-common-3.1.4.jar:?]
> at
> java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
> ~[?:1.8.0_292]
> at java.util.concurrent.FutureTask.run(FutureTask.java:266)
> ~[?:1.8.0_292]
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
> ~[?:1.8.0_292]
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
> ~[?:1.8.0_292]
> at java.lang.Thread.run(Thread.java:748) ~[?:1.8.0_292]
> {noformat}
> Repoduce Scenario:
> TPC-DS table customer, any parquet file witten by 1.12.0 that larger than
> 128MB(two row groups).
> {code:sql}
> create table if not exists customer(
> c_customer_sk bigint
> , c_customer_id char(16)
> , c_current_cdemo_sk bigint
> , c_current_hdemo_sk bigint
> , c_current_addr_sk bigint
> , c_first_shipto_date_sk bigint
> , c_first_sales_date_sk bigint
> , c_salutation char(10)
> , c_first_name char(20)
> , c_last_name char(30)
> , c_preferred_cust_flag char(1)
> , c_birth_day int
> , c_birth_month int
> , c_birth_year int
> , c_birth_country varchar(20)
> , c_login char(13)
> , c_email_address char(50)
> , c_last_review_date_sk bigint
> )
> stored as parquet location 'file:///home/username/data/customer';
> --after add file:
> select count(*) from customer;
> {code}
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
