private Fields addGeneratedTermVectors(
Engine.GetResult get,
Fields termVectorsByField,
TermVectorRequest request,
Set<String> selectedFields)
throws IOException {
/* only keep valid fields */
Set<String> validFields = new HashSet<>();
for (String field : selectedFields) {
FieldMapper fieldMapper = indexShard.mapperService().smartNameFieldMapper(field);
if (!isValidField(fieldMapper)) {
continue;
}
// already retrieved, only if the analyzer hasn't been overridden at the field
if (fieldMapper.fieldType().storeTermVectors()
&& (request.perFieldAnalyzer() == null
|| !request.perFieldAnalyzer().containsKey(field))) {
continue;
}
validFields.add(field);
}
if (validFields.isEmpty()) {
return termVectorsByField;
}
/* generate term vectors from fetched document fields */
GetResult getResult =
indexShard
.getService()
.get(
get,
request.id(),
request.type(),
validFields.toArray(Strings.EMPTY_ARRAY),
null,
false);
Fields generatedTermVectors =
generateTermVectors(
getResult.getFields().values(), request.offsets(), request.perFieldAnalyzer());
/* merge with existing Fields */
if (termVectorsByField == null) {
return generatedTermVectors;
} else {
return mergeFields(termVectorsByField, generatedTermVectors);
}
}
private Fields generateTermVectorsFromDoc(TermVectorRequest request, boolean doAllFields)
throws IOException {
// parse the document, at the moment we do update the mapping, just like percolate
ParsedDocument parsedDocument =
parseDocument(indexShard.shardId().getIndex(), request.type(), request.doc());
// select the right fields and generate term vectors
ParseContext.Document doc = parsedDocument.rootDoc();
Collection<String> seenFields = new HashSet<>();
Collection<GetField> getFields = new HashSet<>();
for (IndexableField field : doc.getFields()) {
FieldMapper fieldMapper = indexShard.mapperService().smartNameFieldMapper(field.name());
if (seenFields.contains(field.name())) {
continue;
} else {
seenFields.add(field.name());
}
if (!isValidField(fieldMapper)) {
continue;
}
if (request.selectedFields() == null
&& !doAllFields
&& !fieldMapper.fieldType().storeTermVectors()) {
continue;
}
if (request.selectedFields() != null && !request.selectedFields().contains(field.name())) {
continue;
}
String[] values = doc.getValues(field.name());
getFields.add(new GetField(field.name(), Arrays.asList((Object[]) values)));
}
return generateTermVectors(getFields, request.offsets(), request.perFieldAnalyzer());
}
public TermVectorResponse getTermVector(TermVectorRequest request, String concreteIndex) {
final Engine.Searcher searcher = indexShard.acquireSearcher("term_vector");
IndexReader topLevelReader = searcher.reader();
final TermVectorResponse termVectorResponse =
new TermVectorResponse(concreteIndex, request.type(), request.id());
final Term uidTerm =
new Term(UidFieldMapper.NAME, Uid.createUidAsBytes(request.type(), request.id()));
Engine.GetResult get = indexShard.get(new Engine.Get(request.realtime(), uidTerm));
boolean docFromTranslog = get.source() != null;
AggregatedDfs dfs = null;
/* fetched from translog is treated as an artificial document */
if (docFromTranslog) {
request.doc(get.source().source, false);
termVectorResponse.setDocVersion(get.version());
}
/* handle potential wildcards in fields */
if (request.selectedFields() != null) {
handleFieldWildcards(request);
}
try {
Fields topLevelFields = MultiFields.getFields(topLevelReader);
Versions.DocIdAndVersion docIdAndVersion = get.docIdAndVersion();
/* from an artificial document */
if (request.doc() != null) {
Fields termVectorsByField = generateTermVectorsFromDoc(request, !docFromTranslog);
// if no document indexed in shard, take the queried document itself for stats
if (topLevelFields == null) {
topLevelFields = termVectorsByField;
}
if (termVectorsByField != null && useDfs(request)) {
dfs = getAggregatedDfs(termVectorsByField, request);
}
termVectorResponse.setFields(
termVectorsByField, request.selectedFields(), request.getFlags(), topLevelFields, dfs);
termVectorResponse.setExists(true);
termVectorResponse.setArtificial(!docFromTranslog);
}
/* or from an existing document */
else if (docIdAndVersion != null) {
// fields with stored term vectors
Fields termVectorsByField =
docIdAndVersion.context.reader().getTermVectors(docIdAndVersion.docId);
Set<String> selectedFields = request.selectedFields();
// generate tvs for fields where analyzer is overridden
if (selectedFields == null && request.perFieldAnalyzer() != null) {
selectedFields = getFieldsToGenerate(request.perFieldAnalyzer(), termVectorsByField);
}
// fields without term vectors
if (selectedFields != null) {
termVectorsByField =
addGeneratedTermVectors(get, termVectorsByField, request, selectedFields);
}
if (termVectorsByField != null && useDfs(request)) {
dfs = getAggregatedDfs(termVectorsByField, request);
}
termVectorResponse.setFields(
termVectorsByField, request.selectedFields(), request.getFlags(), topLevelFields, dfs);
termVectorResponse.setDocVersion(docIdAndVersion.version);
termVectorResponse.setExists(true);
} else {
termVectorResponse.setExists(false);
}
} catch (Throwable ex) {
throw new ElasticsearchException("failed to execute term vector request", ex);
} finally {
searcher.close();
get.release();
}
return termVectorResponse;
}