Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[HUDI-4192] HoodieHFileReader scan top cells after bottom cells throw… #5755

Merged
merged 1 commit into from
Jun 6, 2022
Merged

[HUDI-4192] HoodieHFileReader scan top cells after bottom cells throw… #5755

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 32 additions & 0 deletions ...i-client-common/src/test/java/org/apache/hudi/io/storage/TestHoodieHFileReaderWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,6 +294,38 @@ public void testReaderGetRecordIteratorByKeyPrefixes() throws Exception {
StreamSupport.stream(Spliterators.spliteratorUnknownSize(iterator, Spliterator.ORDERED), false)
.collect(Collectors.toList());
assertEquals(Collections.emptyList(), recordsByPrefix);

// filter for "key50" and "key1" : entries from key50 and 'key10 to key19' should be matched.
List<GenericRecord> expectedKey50and1s = allRecords.stream().filter(entry -> (entry.get("_row_key").toString()).contains("key1")
|| (entry.get("_row_key").toString()).contains("key50")).collect(Collectors.toList());
iterator =
hfileReader.getRecordsByKeyPrefixIterator(Arrays.asList("key50", "key1"), avroSchema);
recordsByPrefix =
StreamSupport.stream(Spliterators.spliteratorUnknownSize(iterator, Spliterator.ORDERED), false)
.collect(Collectors.toList());
assertEquals(expectedKey50and1s, recordsByPrefix);

// filter for "key50" and "key0" : entries from key50 and 'key00 to key09' should be matched.
List<GenericRecord> expectedKey50and0s = allRecords.stream().filter(entry -> (entry.get("_row_key").toString()).contains("key0")
|| (entry.get("_row_key").toString()).contains("key50")).collect(Collectors.toList());
iterator =
hfileReader.getRecordsByKeyPrefixIterator(Arrays.asList("key50", "key0"), avroSchema);
recordsByPrefix =
StreamSupport.stream(Spliterators.spliteratorUnknownSize(iterator, Spliterator.ORDERED), false)
.collect(Collectors.toList());
assertEquals(expectedKey50and0s, recordsByPrefix);

// filter for "key1" and "key0" : entries from 'key10 to key19' and 'key00 to key09' should be matched.
List<GenericRecord> expectedKey1sand0s = expectedKey1s;
expectedKey1sand0s.addAll(allRecords.stream()
.filter(entry -> (entry.get("_row_key").toString()).contains("key0"))
.collect(Collectors.toList()));
iterator =
hfileReader.getRecordsByKeyPrefixIterator(Arrays.asList("key1", "key0"), avroSchema);
recordsByPrefix =
StreamSupport.stream(Spliterators.spliteratorUnknownSize(iterator, Spliterator.ORDERED), false)
.collect(Collectors.toList());
assertEquals(expectedKey1sand0s, recordsByPrefix);
}

@ParameterizedTest
Expand Down
6 changes: 6 additions & 0 deletions hudi-common/src/main/java/org/apache/hudi/io/storage/HoodieHFileReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -258,6 +258,12 @@ private static Iterator<GenericRecord> getRecordByKeyPrefixIteratorInternal(HFil
if (!scanner.next()) {
return Collections.emptyIterator();
}
} else if (val == -1) {
// If scanner is aleady on the top of hfile. avoid trigger seekTo again.
Option<Cell> headerCell = Option.fromJavaOptional(scanner.getReader().getFirstKey());
if (headerCell.isPresent() && !headerCell.get().equals(scanner.getCell())) {
scanner.seekTo();
}
}

class KeyPrefixIterator implements Iterator<GenericRecord> {
Expand Down