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

Jump to bottom

Feature/most recent unique #2570

Open
wants to merge 6 commits into
base: integration
Choose a base branch
from
Open

Feature/most recent unique #2570

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
5386632
Initial refactoring of the mostRecentUnique functionality to avoid th…
ivakegg Jul 10, 2024
3b642b1
Initial implementation of a file backed sorted map
ivakegg Aug 7, 2024
71715dd
WOrking through tests
ivakegg Aug 9, 2024
c0cf844
Worked through more tests for the sorted map implementations
ivakegg Aug 16, 2024
c2a9ad4
Finished working through test cases
ivakegg Aug 21, 2024
b504406
Merge branch 'integration' into feature/mostRecentUnique
ivakegg Sep 18, 2024
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
1 change: 1 addition & 0 deletions ...ce/src/main/java/datawave/core/mapreduce/bulkresults/map/BulkResultsFileOutputMapper.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,7 @@ protected void setup(org.apache.hadoop.mapreduce.Mapper<Key,Value,Key,Value>.Con

QueryLogic<?> logic = (QueryLogic<?>) super.applicationContext.getBean(logicName);
t = logic.getEnrichedTransformer(query);

Assert.notNull(logic.getMarkingFunctions());
Assert.notNull(logic.getResponseObjectFactory());
this.format = SerializationFormat.valueOf(context.getConfiguration().get(RESULT_SERIALIZATION_FORMAT));
Expand Down
16 changes: 16 additions & 0 deletions microservices/configcheck/src/test/resources/input/microservice/QueryLogicFactory.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -233,7 +233,23 @@
<bean class="datawave.query.language.functions.jexl.TimeFunction"/>
<bean class="datawave.query.language.functions.jexl.Jexl"/>
<bean class="datawave.query.language.functions.jexl.Options"/>
<bean class="datawave.query.language.functions.jexl.GroupBy"/>
<bean class="datawave.query.language.functions.jexl.Unique"/>
<bean class="datawave.query.language.functions.jexl.UniqueByDay"/>
<bean class="datawave.query.language.functions.jexl.UniqueByHour"/>
<bean class="datawave.query.language.functions.jexl.UniqueByMinute"/>
<bean class="datawave.query.language.functions.jexl.UniqueByMonth"/>
<bean class="datawave.query.language.functions.jexl.UniqueBySecond"/>
<bean class="datawave.query.language.functions.jexl.UniqueByTenthOfHour"/>
<bean class="datawave.query.language.functions.jexl.UniqueByYear"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUnique"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByDay"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByHour"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByMinute"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByMonth"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueBySecond"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByTenthOfHour"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByYear"/>
<bean class="datawave.query.language.functions.jexl.Geowave.Contains"/>
<bean class="datawave.query.language.functions.jexl.Geowave.CoveredBy"/>
<bean class="datawave.query.language.functions.jexl.Geowave.Covers"/>
Expand Down
12 changes: 10 additions & 2 deletions microservices/configcheck/src/test/resources/input/webservice/QueryLogicFactory.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,15 +38,23 @@
<bean class="datawave.query.language.functions.jexl.AtomValuesMatchFunction"/>
<bean class="datawave.query.language.functions.jexl.Options"/>
<bean class="datawave.query.language.functions.jexl.Rename"/>
<bean class="datawave.query.language.functions.jexl.Unique"/>
<bean class="datawave.query.language.functions.jexl.GroupBy"/>
<bean class="datawave.query.language.functions.jexl.Unique"/>
<bean class="datawave.query.language.functions.jexl.UniqueByDay"/>
<bean class="datawave.query.language.functions.jexl.UniqueByHour"/>
<bean class="datawave.query.language.functions.jexl.UniqueByMinute"/>
<bean class="datawave.query.language.functions.jexl.UniqueByMonth"/>
<bean class="datawave.query.language.functions.jexl.UniqueByYear"/>
<bean class="datawave.query.language.functions.jexl.UniqueBySecond"/>
<bean class="datawave.query.language.functions.jexl.UniqueByTenthOfHour"/>
<bean class="datawave.query.language.functions.jexl.UniqueByYear"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUnique"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByDay"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByHour"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByMinute"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByMonth"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueBySecond"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByTenthOfHour"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByYear"/>
<bean class="datawave.query.language.functions.jexl.NoExpansion"/>
<bean class="datawave.query.language.functions.jexl.Compare"/>
<bean class="datawave.query.language.functions.jexl.Geowave.Contains"/>
Expand Down
16 changes: 16 additions & 0 deletions microservices/configcheck/src/test/resources/rendered/microservice/QueryLogicFactory.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -233,7 +233,23 @@
<bean class="datawave.query.language.functions.jexl.TimeFunction"/>
<bean class="datawave.query.language.functions.jexl.Jexl"/>
<bean class="datawave.query.language.functions.jexl.Options"/>
<bean class="datawave.query.language.functions.jexl.GroupBy"/>
<bean class="datawave.query.language.functions.jexl.Unique"/>
<bean class="datawave.query.language.functions.jexl.UniqueByDay"/>
<bean class="datawave.query.language.functions.jexl.UniqueByHour"/>
<bean class="datawave.query.language.functions.jexl.UniqueByMinute"/>
<bean class="datawave.query.language.functions.jexl.UniqueByMonth"/>
<bean class="datawave.query.language.functions.jexl.UniqueBySecond"/>
<bean class="datawave.query.language.functions.jexl.UniqueByTenthOfHour"/>
<bean class="datawave.query.language.functions.jexl.UniqueByYear"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUnique"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByDay"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByHour"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByMinute"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByMonth"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueBySecond"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByTenthOfHour"/>
<bean class="datawave.query.language.functions.jexl.MostRecentUniqueByYear"/>
<bean class="datawave.query.language.functions.jexl.Geowave.Contains"/>
<bean class="datawave.query.language.functions.jexl.Geowave.CoveredBy"/>
<bean class="datawave.query.language.functions.jexl.Geowave.Covers"/>
Expand Down
7 changes: 5 additions & 2 deletions ...ery-core/src/main/java/datawave/core/iterators/DatawaveFieldIndexCachingIteratorJexl.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1296,8 +1296,11 @@ protected void setupRowBasedHdfsBackedSet(String row) throws IOException {
this.createdRowDir = false;
}

this.set = new HdfsBackedSortedSet<>(null, hdfsBackedSetBufferSize, ivaratorCacheDirs, row, maxOpenFiles, numRetries, persistOptions,
new FileKeySortedSet.Factory());
// noinspection unchecked
this.set = (HdfsBackedSortedSet<Key>) HdfsBackedSortedSet.builder().withBufferPersistThreshold(hdfsBackedSetBufferSize)
.withIvaratorCacheDirs(ivaratorCacheDirs).withUniqueSubPath(row).withMaxOpenFiles(maxOpenFiles).withNumRetries(numRetries)
.withPersistOptions(persistOptions).withSetFactory(new FileKeySortedSet.Factory()).build();

this.threadSafeSet = Collections.synchronizedSortedSet(this.set);
this.currentRow = row;
this.setControl.takeOwnership(row, this);
Expand Down
6 changes: 4 additions & 2 deletions warehouse/query-core/src/main/java/datawave/core/iterators/filesystem/FileSystemCache.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,8 +25,10 @@ public class FileSystemCache {

public FileSystemCache(String hdfsSiteConfigs) throws MalformedURLException {
conf = new Configuration();
for (String url : org.apache.commons.lang.StringUtils.split(hdfsSiteConfigs, ',')) {
conf.addResource(new URL(url));
if (hdfsSiteConfigs != null) {
for (String url : org.apache.commons.lang.StringUtils.split(hdfsSiteConfigs, ',')) {
conf.addResource(new URL(url));
}
}
}

Expand Down
1 change: 1 addition & 0 deletions warehouse/query-core/src/main/java/datawave/query/QueryParameters.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,6 +179,7 @@ public class QueryParameters {

public static final String GROUP_FIELDS_BATCH_SIZE = "group.fields.batch.size";
public static final String UNIQUE_FIELDS = "unique.fields";
public static final String MOST_RECENT_UNIQUE = "most.recent.unique";

/**
* Used to specify fields which are excluded from QueryModel expansion
Expand Down
5 changes: 5 additions & 0 deletions warehouse/query-core/src/main/java/datawave/query/attributes/Attribute.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,11 @@ public ColumnVisibility getColumnVisibility() {
return Constants.EMPTY_VISIBILITY;
}

@Override
public boolean equals(Object o) {
return false;
}

public void setColumnVisibility(ColumnVisibility columnVisibility) {
if (isMetadataSet()) {
metadata = new Key(metadata.getRow(), metadata.getColumnFamily(), metadata.getColumnQualifier(), columnVisibility, metadata.getTimestamp());
Expand Down
2 changes: 1 addition & 1 deletion warehouse/query-core/src/main/java/datawave/query/attributes/TypeAttribute.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,7 @@ public boolean equals(Object o) {

if (o instanceof TypeAttribute) {
TypeAttribute other = (TypeAttribute) o;
return this.getType().equals(other.getType()) && (0 == this.compareMetadata(other));
return this.getType().equals(other.getType());
}

return false;
Expand Down
Loading
Loading