[
https://issues.apache.org/jira/browse/HBASE-8930?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13749491#comment-13749491
]
Lars Hofhansl commented on HBASE-8930:
--------------------------------------
It turns out there *is* a desire to evaluate Filters on columns are not
"selected" in the Scan object.
See HBASE-4364, the problem there seems to stem from the fact that column
families are filters before the scanner process. Thus, columns of column
families that do not contain any of the selected columns will not be passed to
the filters.
Vasu's patch would make this behavior predictable.
I think we should have this in 0.94 and 0.95+. Comments? Do we need to raise
this on the DEV list?
> Filter evaluates KVs outside requested columns
> ----------------------------------------------
>
> Key: HBASE-8930
> URL: https://issues.apache.org/jira/browse/HBASE-8930
> Project: HBase
> Issue Type: Bug
> Components: Filters
> Affects Versions: 0.94.7
> Reporter: Federico Gaule
> Assignee: Vasu Mariyala
> Priority: Critical
> Labels: filters, hbase, keyvalue
> Attachments: HBASE-8930.patch, HBASE-8930-rev1.patch,
> HBASE-8930-rev2.patch
>
>
> 1- Fill row with some columns
> 2- Get row with some columns less than universe - Use filter to print kvs
> 3- Filter prints not requested columns
> Filter (AllwaysNextColFilter) always return ReturnCode.INCLUDE_AND_NEXT_COL
> and prints KV's qualifier
> SUFFIX_0 = 0
> SUFFIX_1 = 1
> SUFFIX_4 = 4
> SUFFIX_6 = 6
> P= Persisted
> R= Requested
> E= Evaluated
> X= Returned
> | 5580 | 5581 | 5584 | 5586 | 5590 | 5591 | 5594 | 5596 | 5600 | 5601 | 5604
> | 5606 |...
> | | P | P | | | P | P | | | P | P
> | |...
> | | R | R | R | | R | R | R | | |
> | |...
> | | E | E | | | E | E | | |
> {color:red}E{color} | | |...
> | | X | X | | | X | X | | | |
> | |
> {code:title=ExtraColumnTest.java|borderStyle=solid}
> @Test
> public void testFilter() throws Exception {
> Configuration config = HBaseConfiguration.create();
> config.set("hbase.zookeeper.quorum", "myZK");
> HTable hTable = new HTable(config, "testTable");
> byte[] cf = Bytes.toBytes("cf");
> byte[] row = Bytes.toBytes("row");
> byte[] col1 = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 558, (byte) SUFFIX_1));
> byte[] col2 = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 559, (byte) SUFFIX_1));
> byte[] col3 = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 560, (byte) SUFFIX_1));
> byte[] col4 = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 561, (byte) SUFFIX_1));
> byte[] col5 = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 562, (byte) SUFFIX_1));
> byte[] col6 = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 563, (byte) SUFFIX_1));
> byte[] col1g = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 558, (byte) SUFFIX_6));
> byte[] col2g = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 559, (byte) SUFFIX_6));
> byte[] col1v = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 558, (byte) SUFFIX_4));
> byte[] col2v = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 559, (byte) SUFFIX_4));
> byte[] col3v = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 560, (byte) SUFFIX_4));
> byte[] col4v = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 561, (byte) SUFFIX_4));
> byte[] col5v = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 562, (byte) SUFFIX_4));
> byte[] col6v = new QualifierConverter().objectToByteArray(new
> Qualifier((short) 563, (byte) SUFFIX_4));
> // =========== INSERTION =============//
> Put put = new Put(row);
> put.add(cf, col1, Bytes.toBytes((short) 1));
> put.add(cf, col2, Bytes.toBytes((short) 1));
> put.add(cf, col3, Bytes.toBytes((short) 3));
> put.add(cf, col4, Bytes.toBytes((short) 3));
> put.add(cf, col5, Bytes.toBytes((short) 3));
> put.add(cf, col6, Bytes.toBytes((short) 3));
> hTable.put(put);
> put = new Put(row);
> put.add(cf, col1v, Bytes.toBytes((short) 10));
> put.add(cf, col2v, Bytes.toBytes((short) 10));
> put.add(cf, col3v, Bytes.toBytes((short) 10));
> put.add(cf, col4v, Bytes.toBytes((short) 10));
> put.add(cf, col5v, Bytes.toBytes((short) 10));
> put.add(cf, col6v, Bytes.toBytes((short) 10));
> hTable.put(put);
> hTable.flushCommits();
> //==============READING=================//
> Filter allwaysNextColFilter = new AllwaysNextColFilter();
> Get get = new Get(row);
> get.addColumn(cf, col1); //5581
> get.addColumn(cf, col1v); //5584
> get.addColumn(cf, col1g); //5586
> get.addColumn(cf, col2); //5591
> get.addColumn(cf, col2v); //5594
> get.addColumn(cf, col2g); //5596
>
> get.setFilter(allwaysNextColFilter);
> get.setMaxVersions(1);
> System.out.println(get);
> Scan scan = new Scan(get);
> ResultScanner scanner = hTable.getScanner(scan);
> Iterator<Result> iterator = scanner.iterator();
> System.out.println("SCAN");
> while (iterator.hasNext()) {
> Result next = iterator.next();
> for (KeyValue kv : next.list()) {
> System.out.println(new
> QualifierConverter().byteArrayToObject(kv.getQualifier()));
> }
> }
> }
> }
> {code}
> Requested 5581 5584 5586 5591 5594 5596
> NOT REQUESTED: 5561
> Sysout Filter
> {noformat}
> \x00\x00\x1A\xBE\x00\x05^:\x00\x00\xA0X\x00\x00=\x1A/H0:\x02.\x01/1373577819267/Put/vlen=2/ts=2
> Qualifier{date=558, type=SUFFIX_1}
> \x00\x00\x1A\xBE\x00\x05^:\x00\x00\xA0X\x00\x00=\x1A/H0:\x02.\x02/1373577819272/Put/vlen=2/ts=3
> Qualifier{date=558, type=SUFFIX_4}
> \x00\x00\x1A\xBE\x00\x05^:\x00\x00\xA0X\x00\x00=\x1A/H0:\x02/\x01/1373577819267/Put/vlen=2/ts=2
> ualifier{date=559, type=SUFFIX_1}
> \x00\x00\x1A\xBE\x00\x05^:\x00\x00\xA0X\x00\x00=\x1A/H0:\x02/\x02/1373577819272/Put/vlen=2/ts=3
> Qualifier{date=559, type=SUFFIX_4}
>
> \x00\x00\x1A\xBE\x00\x05^:\x00\x00\xA0X\x00\x00=\x1A/H0:\x020\x01/1373577819267/Put/vlen=2/ts=2
> Qualifier{date=560, type=SUFFIX_1} (DATE 5601 NOT REQUESTED BUT EVALUATED)
> {noformat}
> Sysout ExtraColumnTest
> {noformat}
> {"timeRange":[0,9223372036854775807],"totalColumns":6,"cacheBlocks":true,"families":{"H0":["\\x02.\\x01","\\x02.\\x02","\\x02.\\x06","\\x02/\\x01"]},"maxVersions":1,"filter":"AllwaysNextColFilter","row":"\\x00\\x00\\x1A\\xBE\\x00\\x05^:\\x00\\x00\\xA0X\\x00\\x00=\\x1A"}
> SCAN
> Qualifier{date=558, type=SUFFIX_1}
> Qualifier{date=558, type=SUFFIX_4}
> Qualifier{date=559, type=SUFFIX_1}
> Qualifier{date=559, type=SUFFIX_4}
> {noformat}
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
