public void testGetTermVector() throws IOException {
createIndexWithAlias();
assertAcked(
client()
.admin()
.indices()
.preparePutMapping("test")
.setType("type1")
.setSource("field", "type=text,term_vector=with_positions_offsets_payloads")
.get());
ensureYellow("test");
client()
.prepareIndex(indexOrAlias(), "type1", "1")
.setSource("field", "the quick brown fox jumps over the lazy dog")
.get();
refresh();
TermVectorsResponse termVectorsResponse =
client().prepareTermVectors(indexOrAlias(), "type1", "1").get();
assertThat(termVectorsResponse.getIndex(), equalTo("test"));
assertThat(termVectorsResponse.isExists(), equalTo(true));
Fields fields = termVectorsResponse.getFields();
assertThat(fields.size(), equalTo(1));
assertThat(fields.terms("field").size(), equalTo(8L));
}
private void checkAllInfo(
int numDocs,
String[] values,
int[] freq,
int[][] pos,
int[][] startOffset,
int[][] endOffset,
int i)
throws IOException {
TermVectorsRequestBuilder resp =
client()
.prepareTermVectors("test", "type1", Integer.toString(i))
.setPayloads(true)
.setOffsets(true)
.setPositions(true)
.setFieldStatistics(true)
.setTermStatistics(true)
.setSelectedFields();
assertThat(resp.request().fieldStatistics(), equalTo(true));
TermVectorsResponse response = resp.execute().actionGet();
assertThat("doc id: " + i + " doesn't exists but should", response.isExists(), equalTo(true));
Fields fields = response.getFields();
assertThat(fields.size(), equalTo(1));
Terms terms = fields.terms("field");
assertThat(terms.size(), equalTo(8l));
assertThat(terms.getSumTotalTermFreq(), Matchers.equalTo((long) (9 * numDocs)));
assertThat(terms.getDocCount(), Matchers.equalTo(numDocs));
assertThat(terms.getSumDocFreq(), equalTo((long) numDocs * values.length));
TermsEnum iterator = terms.iterator();
for (int j = 0; j < values.length; j++) {
String string = values[j];
BytesRef next = iterator.next();
assertThat(next, Matchers.notNullValue());
assertThat("expected " + string, string, equalTo(next.utf8ToString()));
assertThat(next, Matchers.notNullValue());
if (string.equals("the")) {
assertThat(
"expected ttf of " + string, numDocs * 2, equalTo((int) iterator.totalTermFreq()));
} else {
assertThat("expected ttf of " + string, numDocs, equalTo((int) iterator.totalTermFreq()));
}
PostingsEnum docsAndPositions = iterator.postings(null, null, PostingsEnum.ALL);
assertThat(docsAndPositions.nextDoc(), equalTo(0));
assertThat(freq[j], equalTo(docsAndPositions.freq()));
assertThat(iterator.docFreq(), equalTo(numDocs));
int[] termPos = pos[j];
int[] termStartOffset = startOffset[j];
int[] termEndOffset = endOffset[j];
assertThat(termPos.length, equalTo(freq[j]));
assertThat(termStartOffset.length, equalTo(freq[j]));
assertThat(termEndOffset.length, equalTo(freq[j]));
for (int k = 0; k < freq[j]; k++) {
int nextPosition = docsAndPositions.nextPosition();
assertThat("term: " + string, nextPosition, equalTo(termPos[k]));
assertThat("term: " + string, docsAndPositions.startOffset(), equalTo(termStartOffset[k]));
assertThat("term: " + string, docsAndPositions.endOffset(), equalTo(termEndOffset[k]));
assertThat("term: " + string, docsAndPositions.getPayload(), equalTo(new BytesRef("word")));
}
}
assertThat(iterator.next(), Matchers.nullValue());
XContentBuilder xBuilder = XContentFactory.jsonBuilder();
xBuilder.startObject();
response.toXContent(xBuilder, ToXContent.EMPTY_PARAMS);
xBuilder.endObject();
BytesStream bytesStream = xBuilder.bytesStream();
String utf8 = bytesStream.bytes().toUtf8().replaceFirst("\"took\":\\d+,", "");
;
String expectedString =
"{\"_index\":\"test\",\"_type\":\"type1\",\"_id\":\""
+ i
+ "\",\"_version\":1,\"found\":true,\"term_vectors\":{\"field\":{\"field_statistics\":{\"sum_doc_freq\":120,\"doc_count\":15,\"sum_ttf\":135},\"terms\":{\"brown\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":2,\"start_offset\":10,\"end_offset\":15,\"payload\":\"d29yZA==\"}]},\"dog\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":8,\"start_offset\":40,\"end_offset\":43,\"payload\":\"d29yZA==\"}]},\"fox\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":3,\"start_offset\":16,\"end_offset\":19,\"payload\":\"d29yZA==\"}]},\"jumps\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":4,\"start_offset\":20,\"end_offset\":25,\"payload\":\"d29yZA==\"}]},\"lazy\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":7,\"start_offset\":35,\"end_offset\":39,\"payload\":\"d29yZA==\"}]},\"over\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":5,\"start_offset\":26,\"end_offset\":30,\"payload\":\"d29yZA==\"}]},\"quick\":{\"doc_freq\":15,\"ttf\":15,\"term_freq\":1,\"tokens\":[{\"position\":1,\"start_offset\":4,\"end_offset\":9,\"payload\":\"d29yZA==\"}]},\"the\":{\"doc_freq\":15,\"ttf\":30,\"term_freq\":2,\"tokens\":[{\"position\":0,\"start_offset\":0,\"end_offset\":3,\"payload\":\"d29yZA==\"},{\"position\":6,\"start_offset\":31,\"end_offset\":34,\"payload\":\"d29yZA==\"}]}}}}}";
assertThat(utf8, equalTo(expectedString));
}
public static void main(String[] args) throws IOException {
IndexReader reader = null;
/*
* Opening the index first simplifies the processing of the
* rest of the command line arguments.
*/
for (int i = 0; i < args.length; i++) {
if (("-index".equals(args[i])) && ((i + 1) < args.length)) {
reader = DirectoryReader.open(FSDirectory.open(new File(args[i + 1])));
if (reader == null) {
System.err.println("Error: Can't open index " + args[i + 1]);
System.exit(1);
}
;
break;
}
;
}
;
if (reader == null) {
System.err.println(usage);
System.exit(1);
}
;
/*
* Process the command line arguments sequentially.
*/
for (int i = 0; i < args.length; i++) {
if ("-index".equals(args[i])) {
/*
* Handled in the previous loop, so just skip the argument.
*/
i++;
} else if ("-list-edocid".equals(args[i])) {
System.out.println("-list-edocid:");
if ((i + 1) >= args.length) {
System.out.println(usage);
break;
}
;
Document d = reader.document(Integer.parseInt(args[i + 1]));
System.out.println(
"Internal docid --> External docid: " + args[i + 1] + " --> " + d.get("externalId"));
i += 1;
} else if ("-list-docids".equals(args[i])) {
System.out.println("-list-docids:");
for (int j = 0; j < reader.numDocs(); j++) {
Document d = reader.document(j);
System.out.println("Internal --> external docid: " + j + " --> " + d.get("externalId"));
}
;
} else if ("-list-fields".equals(args[i])) {
Fields fields = MultiFields.getFields(reader);
System.out.print("\nNumber of fields: ");
if (fields == null) System.out.println("0");
else {
System.out.println(fields.size());
Iterator<String> is = fields.iterator();
while (is.hasNext()) {
System.out.println("\t" + is.next());
}
;
}
;
} else if ("-list-postings".equals(args[i])) {
if ((i + 2) >= args.length) {
System.out.println(usage);
break;
}
;
listPostings(reader, args[i + 1], args[i + 2], Integer.MAX_VALUE);
i += 2;
} else if ("-list-postings-sample".equals(args[i])) {
if ((i + 2) >= args.length) {
System.out.println(usage);
break;
}
;
listPostings(reader, args[i + 1], args[i + 2], 5);
i += 2;
} else if ("-list-stats".equals(args[i])) {
System.out.println("Corpus statistics:");
System.out.println("\tnumdocs\t\t" + reader.numDocs());
System.out.println(
"\turl:\t"
+ "\tnumdocs="
+ reader.getDocCount("url")
+ "\tsumTotalTF="
+ reader.getSumTotalTermFreq("url")
+ "\tavglen="
+ reader.getSumTotalTermFreq("url") / (float) reader.getDocCount("url"));
System.out.println(
"\tkeywords:"
+ "\tnumdocs="
+ reader.getDocCount("keywords")
+ "\tsumTotalTF="
+ reader.getSumTotalTermFreq("keywords")
+ "\tavglen="
+ reader.getSumTotalTermFreq("keywords") / (float) reader.getDocCount("keywords"));
System.out.println(
"\ttitle:\t"
+ "\tnumdocs="
+ reader.getDocCount("title")
+ "\tsumTotalTF="
+ reader.getSumTotalTermFreq("title")
+ "\tavglen="
+ reader.getSumTotalTermFreq("title") / (float) reader.getDocCount("title"));
System.out.println(
"\tbody:\t"
+ "\tnumdocs="
+ reader.getDocCount("body")
+ "\tsumTotalTF="
+ reader.getSumTotalTermFreq("body")
+ "\tavglen="
+ reader.getSumTotalTermFreq("body") / (float) reader.getDocCount("body"));
System.out.println(
"\tinlink:\t"
+ "\tnumdocs="
+ reader.getDocCount("inlink")
+ "\tsumTotalTF="
+ reader.getSumTotalTermFreq("inlink")
+ "\tavglen="
+ reader.getSumTotalTermFreq("inlink") / (float) reader.getDocCount("inlink"));
} else if ("-list-terms".equals(args[i])) {
if ((i + 1) >= args.length) {
System.out.println(usage);
break;
}
;
listTermDictionary(reader, args[i + 1]);
i += 1;
} else if ("-list-termvector".equals(args[i])) {
if ((i + 1) >= args.length) {
System.out.println(usage);
break;
}
;
listTermVectors(reader, args[i + 1]);
i += 1;
} else if ("-list-termvector-field".equals(args[i])) {
if ((i + 2) >= args.length) {
System.out.println(usage);
break;
}
;
listTermVectorField(reader, args[i + 1], args[i + 2]);
i += 2;
} else System.err.println("\nWarning: Unknown argument " + args[i] + " ignored.");
}
;
/*
* Close the index and exit gracefully.
*/
reader.close();
}
public static void verifyEquals(Fields d1, Fields d2) throws IOException {
if (d1 == null) {
assertTrue(d2 == null || d2.size() == 0);
return;
}
assertTrue(d2 != null);
Iterator<String> fieldsEnum2 = d2.iterator();
for (String field1 : d1) {
String field2 = fieldsEnum2.next();
assertEquals(field1, field2);
Terms terms1 = d1.terms(field1);
assertNotNull(terms1);
TermsEnum termsEnum1 = terms1.iterator(null);
Terms terms2 = d2.terms(field2);
assertNotNull(terms2);
TermsEnum termsEnum2 = terms2.iterator(null);
DocsAndPositionsEnum dpEnum1 = null;
DocsAndPositionsEnum dpEnum2 = null;
DocsEnum dEnum1 = null;
DocsEnum dEnum2 = null;
BytesRef term1;
while ((term1 = termsEnum1.next()) != null) {
BytesRef term2 = termsEnum2.next();
assertEquals(term1, term2);
assertEquals(termsEnum1.totalTermFreq(), termsEnum2.totalTermFreq());
dpEnum1 = termsEnum1.docsAndPositions(null, dpEnum1);
dpEnum2 = termsEnum2.docsAndPositions(null, dpEnum2);
if (dpEnum1 != null) {
assertNotNull(dpEnum2);
int docID1 = dpEnum1.nextDoc();
dpEnum2.nextDoc();
// docIDs are not supposed to be equal
// int docID2 = dpEnum2.nextDoc();
// assertEquals(docID1, docID2);
assertTrue(docID1 != DocIdSetIterator.NO_MORE_DOCS);
int freq1 = dpEnum1.freq();
int freq2 = dpEnum2.freq();
assertEquals(freq1, freq2);
OffsetAttribute offsetAtt1 =
dpEnum1.attributes().hasAttribute(OffsetAttribute.class)
? dpEnum1.attributes().getAttribute(OffsetAttribute.class)
: null;
OffsetAttribute offsetAtt2 =
dpEnum2.attributes().hasAttribute(OffsetAttribute.class)
? dpEnum2.attributes().getAttribute(OffsetAttribute.class)
: null;
if (offsetAtt1 != null) {
assertNotNull(offsetAtt2);
} else {
assertNull(offsetAtt2);
}
for (int posUpto = 0; posUpto < freq1; posUpto++) {
int pos1 = dpEnum1.nextPosition();
int pos2 = dpEnum2.nextPosition();
assertEquals(pos1, pos2);
if (offsetAtt1 != null) {
assertEquals(offsetAtt1.startOffset(), offsetAtt2.startOffset());
assertEquals(offsetAtt1.endOffset(), offsetAtt2.endOffset());
}
}
assertEquals(DocIdSetIterator.NO_MORE_DOCS, dpEnum1.nextDoc());
assertEquals(DocIdSetIterator.NO_MORE_DOCS, dpEnum2.nextDoc());
} else {
dEnum1 = TestUtil.docs(random(), termsEnum1, null, dEnum1, DocsEnum.FLAG_FREQS);
dEnum2 = TestUtil.docs(random(), termsEnum2, null, dEnum2, DocsEnum.FLAG_FREQS);
assertNotNull(dEnum1);
assertNotNull(dEnum2);
int docID1 = dEnum1.nextDoc();
dEnum2.nextDoc();
// docIDs are not supposed to be equal
// int docID2 = dEnum2.nextDoc();
// assertEquals(docID1, docID2);
assertTrue(docID1 != DocIdSetIterator.NO_MORE_DOCS);
int freq1 = dEnum1.freq();
int freq2 = dEnum2.freq();
assertEquals(freq1, freq2);
assertEquals(DocIdSetIterator.NO_MORE_DOCS, dEnum1.nextDoc());
assertEquals(DocIdSetIterator.NO_MORE_DOCS, dEnum2.nextDoc());
}
}
assertNull(termsEnum2.next());
}
assertFalse(fieldsEnum2.hasNext());
}
/**
* Safe (but, slowish) default method to write every vector field in the document. This default
* implementation requires that the vectors implement both Fields.size and Terms.size.
*/
protected final void addAllDocVectors(Fields vectors, FieldInfos fieldInfos) throws IOException {
if (vectors == null) {
startDocument(0);
return;
}
final int numFields = vectors.size();
if (numFields == -1) {
throw new IllegalStateException("vectors.size() must be implemented (it returned -1)");
}
startDocument(numFields);
final FieldsEnum fieldsEnum = vectors.iterator();
String fieldName;
String lastFieldName = null;
while ((fieldName = fieldsEnum.next()) != null) {
final FieldInfo fieldInfo = fieldInfos.fieldInfo(fieldName);
assert lastFieldName == null || fieldName.compareTo(lastFieldName) > 0
: "lastFieldName=" + lastFieldName + " fieldName=" + fieldName;
lastFieldName = fieldName;
final Terms terms = fieldsEnum.terms();
if (terms == null) {
// FieldsEnum shouldn't lie...
continue;
}
final int numTerms = (int) terms.size();
if (numTerms == -1) {
throw new IllegalStateException("terms.size() must be implemented (it returned -1)");
}
final TermsEnum termsEnum = terms.iterator(null);
DocsAndPositionsEnum docsAndPositionsEnum = null;
boolean startedField = false;
// NOTE: this is tricky, because TermVectors allow
// indexing offsets but NOT positions. So we must
// lazily init the field by checking whether first
// position we see is -1 or not.
int termCount = 0;
while (termsEnum.next() != null) {
termCount++;
final int freq = (int) termsEnum.totalTermFreq();
if (startedField) {
startTerm(termsEnum.term(), freq);
}
// TODO: we need a "query" API where we can ask (via
// flex API) what this term was indexed with...
// Both positions & offsets:
docsAndPositionsEnum = termsEnum.docsAndPositions(null, null, true);
final boolean hasOffsets;
boolean hasPositions = false;
if (docsAndPositionsEnum == null) {
// Fallback: no offsets
docsAndPositionsEnum = termsEnum.docsAndPositions(null, null, false);
hasOffsets = false;
} else {
hasOffsets = true;
}
if (docsAndPositionsEnum != null) {
final int docID = docsAndPositionsEnum.nextDoc();
assert docID != DocIdSetIterator.NO_MORE_DOCS;
assert docsAndPositionsEnum.freq() == freq;
for (int posUpto = 0; posUpto < freq; posUpto++) {
final int pos = docsAndPositionsEnum.nextPosition();
if (!startedField) {
assert numTerms > 0;
hasPositions = pos != -1;
startField(fieldInfo, numTerms, hasPositions, hasOffsets);
startTerm(termsEnum.term(), freq);
startedField = true;
}
final int startOffset;
final int endOffset;
if (hasOffsets) {
startOffset = docsAndPositionsEnum.startOffset();
endOffset = docsAndPositionsEnum.endOffset();
assert startOffset != -1;
assert endOffset != -1;
} else {
startOffset = -1;
endOffset = -1;
}
assert !hasPositions || pos >= 0;
addPosition(pos, startOffset, endOffset);
}
} else {
if (!startedField) {
assert numTerms > 0;
startField(fieldInfo, numTerms, hasPositions, hasOffsets);
startTerm(termsEnum.term(), freq);
startedField = true;
}
}
}
assert termCount == numTerms;
}
}