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

Deduplicate _field_names. #26550

Merged
merged 1 commit into from
Sep 11, 2017
Merged

Deduplicate _field_names. #26550

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
14 changes: 12 additions & 2 deletions core/src/main/java/org/elasticsearch/index/mapper/FieldNamesFieldMapper.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -258,9 +258,19 @@ protected void parseCreateField(ParseContext context, List<IndexableField> field
return;
}
for (ParseContext.Document document : context.docs()) {
final List<String> paths = new ArrayList<>();
final List<String> paths = new ArrayList<>(document.getFields().size());
String previousPath = ""; // used as a sentinel - field names can't be empty
for (IndexableField field : document.getFields()) {
paths.add(field.name());
final String path = field.name();
if (path.equals(previousPath)) {
// Sometimes mappers create multiple Lucene fields, eg. one for indexing,
// one for doc values and one for storing. Deduplicating is not required
// for correctness but this simple check helps save utf-8 conversions and
// gives Lucene fewer values to deal with.
continue;
}
paths.add(path);
previousPath = path;
}
for (String path : paths) {
for (String fieldName : extractFieldNames(path)) {
Expand Down
23 changes: 22 additions & 1 deletion core/src/test/java/org/elasticsearch/index/mapper/FieldNamesFieldMapperTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@
import java.util.Collections;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.SortedSet;
import java.util.TreeSet;
import java.util.function.Supplier;
Expand All @@ -56,7 +57,7 @@ private static <T> SortedSet<T> set(T... values) {
return new TreeSet<>(Arrays.asList(values));
}

void assertFieldNames(SortedSet<String> expected, ParsedDocument doc) {
void assertFieldNames(Set<String> expected, ParsedDocument doc) {
String[] got = doc.rootDoc().getValues("_field_names");
assertEquals(expected, set(got));
}
Expand Down Expand Up @@ -120,6 +121,26 @@ public void testExplicitEnabled() throws Exception {
assertFieldNames(set("field", "field.keyword", "_id", "_version", "_seq_no", "_primary_term", "_source"), doc);
}

public void testDedup() throws Exception {
String mapping = XContentFactory.jsonBuilder().startObject().startObject("type")
.startObject("_field_names").field("enabled", true).endObject()
.endObject().endObject().string();
DocumentMapper docMapper = createIndex("test").mapperService().documentMapperParser().parse("type", new CompressedXContent(mapping));
FieldNamesFieldMapper fieldNamesMapper = docMapper.metadataMapper(FieldNamesFieldMapper.class);
assertTrue(fieldNamesMapper.fieldType().isEnabled());

ParsedDocument doc = docMapper.parse(SourceToParse.source("test", "type", "1", XContentFactory.jsonBuilder()
.startObject()
.field("field", 3) // will create 2 lucene fields under the hood: index and doc values
.endObject()
.bytes(),
XContentType.JSON));

Set<String> fields = set("field", "_id", "_version", "_seq_no", "_primary_term", "_source");
assertFieldNames(fields, doc);
assertEquals(fields.size(), doc.rootDoc().getValues("_field_names").length);
}

public void testDisabled() throws Exception {
String mapping = XContentFactory.jsonBuilder().startObject().startObject("type")
.startObject("_field_names").field("enabled", false).endObject()
Expand Down