honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

RankEval: Check for duplicate keys in rated documents 

When multiple ratings for the same document (identified by _index, _type,
_id) are specified in the request we should throw an error. This change adds a
check for this in the RatedRequest setter (and ctor that uses that setter).

Closes #20997
This commit is contained in:
Christoph Büscher 2016-10-27 12:22:32 +02:00
parent 51102ee91c
commit 25565b9baa
2 changed files with 26 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
modules/rank-eval/src/main/java/org/elasticsearch/index/rankeval/RatedRequest.java
View File

@ -33,8 +33,10 @@ import org.elasticsearch.search.builder.SearchSourceBuilder;
import java.io.IOException; import java.io.IOException;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.HashMap; import java.util.HashMap;
import java.util.HashSet;
import java.util.List; import java.util.List;
import java.util.Objects; import java.util.Objects;
import java.util.Set;
import java.util.Map; import java.util.Map;
import java.util.Map.Entry; import java.util.Map.Entry;
@ -68,7 +70,7 @@ public class RatedRequest extends ToXContentToBytes implements Writeable {
this.testRequest = testRequest; this.testRequest = testRequest;
this.indices = indices; this.indices = indices;
this.types = types; this.types = types;
this.ratedDocs = ratedDocs; setRatedDocs(ratedDocs);
} }
public RatedRequest(StreamInput in) throws IOException { public RatedRequest(StreamInput in) throws IOException {
@ -159,8 +161,19 @@ public class RatedRequest extends ToXContentToBytes implements Writeable {
return ratedDocs; return ratedDocs;
} }
/** Set a list of rated documents for this query. */ /**
* Set a list of rated documents for this query.
* No documents with same _index/_type/id allowed.
**/
public void setRatedDocs(List<RatedDocument> ratedDocs) { public void setRatedDocs(List<RatedDocument> ratedDocs) {
Set<DocumentKey> docKeys = new HashSet<>();
for (RatedDocument doc : ratedDocs) {
if (docKeys.add(doc.getKey()) == false) {
String docKeyToString = doc.getKey().toString().replaceAll("\n", "").replaceAll(" ", " ");
throw new IllegalArgumentException(
"Found duplicate rated document key [" + docKeyToString + "]");
}
}
this.ratedDocs = ratedDocs; this.ratedDocs = ratedDocs;
} }

11
modules/rank-eval/src/test/java/org/elasticsearch/index/rankeval/RatedRequestsTests.java
View File

@ -39,6 +39,7 @@ import org.junit.BeforeClass;
import java.io.IOException; import java.io.IOException;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.HashMap; import java.util.HashMap;
import java.util.Arrays;
import java.util.List; import java.util.List;
import java.util.Map; import java.util.Map;
@ -131,6 +132,16 @@ public class RatedRequestsTests extends ESTestCase {
assertEquals(testItem.hashCode(), parsedItem.hashCode()); assertEquals(testItem.hashCode(), parsedItem.hashCode());
} }
public void testDuplicateRatedDocThrowsException() {
RatedRequest request = createTestItem(Arrays.asList("index"), Arrays.asList("type"));
List<RatedDocument> ratedDocs = Arrays.asList(new RatedDocument(new DocumentKey("index1", "type1", "id1"), 1),
new RatedDocument(new DocumentKey("index1", "type1", "id1"), 5));
IllegalArgumentException ex = expectThrows(IllegalArgumentException.class, () -> request.setRatedDocs(ratedDocs));
assertEquals(
"Found duplicate rated document key [{ \"_index\" : \"index1\", \"_type\" : \"type1\", \"_id\" : \"id1\"}]",
ex.getMessage());
}
public void testParseFromXContent() throws IOException { public void testParseFromXContent() throws IOException {
// we modify the order of index/type/docId to make sure it doesn't matter for parsing xContent // we modify the order of index/type/docId to make sure it doesn't matter for parsing xContent
String querySpecString = " {\n" String querySpecString = " {\n"