1 package org.apache.lucene.queryParser.standard;
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
20 import java.io.IOException;
21 import java.io.Reader;
22 import java.text.Collator;
23 import java.text.DateFormat;
24 import java.util.Calendar;
25 import java.util.Date;
26 import java.util.GregorianCalendar;
27 import java.util.HashMap;
28 import java.util.List;
29 import java.util.Locale;
31 import java.util.Collections;
33 import org.apache.lucene.analysis.Analyzer;
34 import org.apache.lucene.analysis.KeywordAnalyzer;
35 import org.apache.lucene.analysis.LowerCaseTokenizer;
36 import org.apache.lucene.analysis.MockAnalyzer;
37 import org.apache.lucene.analysis.MockTokenizer;
38 import org.apache.lucene.analysis.SimpleAnalyzer;
39 import org.apache.lucene.analysis.StopAnalyzer;
40 import org.apache.lucene.analysis.StopFilter;
41 import org.apache.lucene.analysis.TokenFilter;
42 import org.apache.lucene.analysis.TokenStream;
43 import org.apache.lucene.analysis.Tokenizer;
44 import org.apache.lucene.analysis.WhitespaceAnalyzer;
45 import org.apache.lucene.analysis.standard.StandardAnalyzer;
46 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
47 import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
48 import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
49 import org.apache.lucene.document.DateField;
50 import org.apache.lucene.document.DateTools;
51 import org.apache.lucene.document.Document;
52 import org.apache.lucene.document.Field;
53 import org.apache.lucene.index.IndexWriter;
54 import org.apache.lucene.index.IndexReader;
55 import org.apache.lucene.index.Term;
56 import org.apache.lucene.messages.MessageImpl;
57 import org.apache.lucene.queryParser.core.QueryNodeException;
58 import org.apache.lucene.queryParser.core.messages.QueryParserMessages;
59 import org.apache.lucene.queryParser.core.nodes.FuzzyQueryNode;
60 import org.apache.lucene.queryParser.core.nodes.QueryNode;
61 import org.apache.lucene.queryParser.core.processors.QueryNodeProcessorImpl;
62 import org.apache.lucene.queryParser.core.processors.QueryNodeProcessorPipeline;
63 import org.apache.lucene.queryParser.standard.config.StandardQueryConfigHandler;
64 import org.apache.lucene.queryParser.standard.config.StandardQueryConfigHandler.Operator;
65 import org.apache.lucene.queryParser.standard.nodes.WildcardQueryNode;
66 import org.apache.lucene.search.BooleanClause;
67 import org.apache.lucene.search.BooleanQuery;
68 import org.apache.lucene.search.FuzzyQuery;
69 import org.apache.lucene.search.IndexSearcher;
70 import org.apache.lucene.search.MatchAllDocsQuery;
71 import org.apache.lucene.search.MultiPhraseQuery;
72 import org.apache.lucene.search.MultiTermQuery;
73 import org.apache.lucene.search.PhraseQuery;
74 import org.apache.lucene.search.PrefixQuery;
75 import org.apache.lucene.search.Query;
76 import org.apache.lucene.search.ScoreDoc;
77 import org.apache.lucene.search.TermQuery;
78 import org.apache.lucene.search.TermRangeQuery;
79 import org.apache.lucene.search.WildcardQuery;
80 import org.apache.lucene.store.Directory;
81 import org.apache.lucene.util.LuceneTestCase;
84 * This test case is a copy of the core Lucene query parser test, it was adapted
85 * to use new QueryParserHelper instead of the old query parser.
89 public class TestQPHelper extends LuceneTestCase {
91 public static Analyzer qpAnalyzer = new QPTestAnalyzer();
93 public static final class QPTestFilter extends TokenFilter {
94 private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
95 private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
98 * Filter which discards the token 'stop' and which expands the token
99 * 'phrase' into 'phrase1 phrase2'
101 public QPTestFilter(TokenStream in) {
105 private boolean inPhrase = false;
106 private int savedStart = 0;
107 private int savedEnd = 0;
110 public boolean incrementToken() throws IOException {
114 termAtt.setEmpty().append("phrase2");
115 offsetAtt.setOffset(savedStart, savedEnd);
118 while (input.incrementToken()) {
119 if (termAtt.toString().equals("phrase")) {
121 savedStart = offsetAtt.startOffset();
122 savedEnd = offsetAtt.endOffset();
123 termAtt.setEmpty().append("phrase1");
124 offsetAtt.setOffset(savedStart, savedEnd);
126 } else if (!termAtt.toString().equals("stop"))
133 public void reset() throws IOException {
135 this.inPhrase = false;
141 public static final class QPTestAnalyzer extends Analyzer {
143 /** Filters LowerCaseTokenizer with StopFilter. */
145 public final TokenStream tokenStream(String fieldName, Reader reader) {
146 return new QPTestFilter(new LowerCaseTokenizer(TEST_VERSION_CURRENT, reader));
150 public static class QPTestParser extends StandardQueryParser {
151 public QPTestParser(Analyzer a) {
152 ((QueryNodeProcessorPipeline)getQueryNodeProcessor())
153 .add(new QPTestParserQueryNodeProcessor());
158 private static class QPTestParserQueryNodeProcessor extends
159 QueryNodeProcessorImpl {
162 protected QueryNode postProcessNode(QueryNode node)
163 throws QueryNodeException {
170 protected QueryNode preProcessNode(QueryNode node)
171 throws QueryNodeException {
173 if (node instanceof WildcardQueryNode || node instanceof FuzzyQueryNode) {
175 throw new QueryNodeException(new MessageImpl(
176 QueryParserMessages.EMPTY_MESSAGE));
185 protected List<QueryNode> setChildrenOrder(List<QueryNode> children)
186 throws QueryNodeException {
196 private int originalMaxClauses;
199 public void setUp() throws Exception {
201 originalMaxClauses = BooleanQuery.getMaxClauseCount();
204 public StandardQueryParser getParser(Analyzer a) throws Exception {
206 a = new SimpleAnalyzer(TEST_VERSION_CURRENT);
207 StandardQueryParser qp = new StandardQueryParser();
210 qp.setDefaultOperator(StandardQueryConfigHandler.Operator.OR);
216 public Query getQuery(String query, Analyzer a) throws Exception {
217 return getParser(a).parse(query, "field");
220 public Query getQueryAllowLeadingWildcard(String query, Analyzer a) throws Exception {
221 StandardQueryParser parser = getParser(a);
222 parser.setAllowLeadingWildcard(true);
223 return parser.parse(query, "field");
226 public void assertQueryEquals(String query, Analyzer a, String result)
228 Query q = getQuery(query, a);
229 String s = q.toString("field");
230 if (!s.equals(result)) {
231 fail("Query /" + query + "/ yielded /" + s + "/, expecting /" + result
236 public void assertQueryEqualsAllowLeadingWildcard(String query, Analyzer a, String result)
238 Query q = getQueryAllowLeadingWildcard(query, a);
239 String s = q.toString("field");
240 if (!s.equals(result)) {
241 fail("Query /" + query + "/ yielded /" + s + "/, expecting /" + result
246 public void assertQueryEquals(StandardQueryParser qp, String field,
247 String query, String result) throws Exception {
248 Query q = qp.parse(query, field);
249 String s = q.toString(field);
250 if (!s.equals(result)) {
251 fail("Query /" + query + "/ yielded /" + s + "/, expecting /" + result
256 public void assertEscapedQueryEquals(String query, Analyzer a, String result)
258 String escapedQuery = QueryParserUtil.escape(query);
259 if (!escapedQuery.equals(result)) {
260 fail("Query /" + query + "/ yielded /" + escapedQuery + "/, expecting /"
265 public void assertWildcardQueryEquals(String query, boolean lowercase,
266 String result, boolean allowLeadingWildcard) throws Exception {
267 StandardQueryParser qp = getParser(null);
268 qp.setLowercaseExpandedTerms(lowercase);
269 qp.setAllowLeadingWildcard(allowLeadingWildcard);
270 Query q = qp.parse(query, "field");
271 String s = q.toString("field");
272 if (!s.equals(result)) {
273 fail("WildcardQuery /" + query + "/ yielded /" + s + "/, expecting /"
278 public void assertWildcardQueryEquals(String query, boolean lowercase,
279 String result) throws Exception {
280 assertWildcardQueryEquals(query, lowercase, result, false);
283 public void assertWildcardQueryEquals(String query, String result)
285 StandardQueryParser qp = getParser(null);
286 Query q = qp.parse(query, "field");
287 String s = q.toString("field");
288 if (!s.equals(result)) {
289 fail("WildcardQuery /" + query + "/ yielded /" + s + "/, expecting /"
294 public Query getQueryDOA(String query, Analyzer a) throws Exception {
296 a = new SimpleAnalyzer(TEST_VERSION_CURRENT);
297 StandardQueryParser qp = new StandardQueryParser();
299 qp.setDefaultOperator(Operator.AND);
301 return qp.parse(query, "field");
305 public void assertQueryEqualsDOA(String query, Analyzer a, String result)
307 Query q = getQueryDOA(query, a);
308 String s = q.toString("field");
309 if (!s.equals(result)) {
310 fail("Query /" + query + "/ yielded /" + s + "/, expecting /" + result
315 public void testConstantScoreAutoRewrite() throws Exception {
316 StandardQueryParser qp = new StandardQueryParser(new MockAnalyzer(random, MockTokenizer.WHITESPACE, false));
317 Query q = qp.parse("foo*bar", "field");
318 assertTrue(q instanceof WildcardQuery);
319 assertEquals(MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT, ((MultiTermQuery) q).getRewriteMethod());
321 q = qp.parse("foo*", "field");
322 assertTrue(q instanceof PrefixQuery);
323 assertEquals(MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT, ((MultiTermQuery) q).getRewriteMethod());
325 q = qp.parse("[a TO z]", "field");
326 assertTrue(q instanceof TermRangeQuery);
327 assertEquals(MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT, ((MultiTermQuery) q).getRewriteMethod());
330 public void testCJK() throws Exception {
331 // Test Ideographic Space - As wide as a CJK character cell (fullwidth)
332 // used google to translate the word "term" to japanese -> ??
333 assertQueryEquals("term\u3000term\u3000term", null,
334 "term\u0020term\u0020term");
335 assertQueryEqualsAllowLeadingWildcard("??\u3000??\u3000??", null, "??\u0020??\u0020??");
338 public void testCJKTerm() throws Exception {
339 // individual CJK chars as terms
340 StandardAnalyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);
342 BooleanQuery expected = new BooleanQuery();
343 expected.add(new TermQuery(new Term("field", "ä¸")), BooleanClause.Occur.SHOULD);
344 expected.add(new TermQuery(new Term("field", "国")), BooleanClause.Occur.SHOULD);
345 assertEquals(expected, getQuery("ä¸å›½", analyzer));
347 expected = new BooleanQuery();
348 expected.add(new TermQuery(new Term("field", "ä¸")), BooleanClause.Occur.MUST);
349 BooleanQuery inner = new BooleanQuery();
350 inner.add(new TermQuery(new Term("field", "ä¸")), BooleanClause.Occur.SHOULD);
351 inner.add(new TermQuery(new Term("field", "国")), BooleanClause.Occur.SHOULD);
352 expected.add(inner, BooleanClause.Occur.MUST);
353 assertEquals(expected, getQuery("ä¸ AND ä¸å›½", analyzer));
357 public void testCJKBoostedTerm() throws Exception {
358 // individual CJK chars as terms
359 StandardAnalyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);
361 BooleanQuery expected = new BooleanQuery();
362 expected.setBoost(0.5f);
363 expected.add(new TermQuery(new Term("field", "ä¸")), BooleanClause.Occur.SHOULD);
364 expected.add(new TermQuery(new Term("field", "国")), BooleanClause.Occur.SHOULD);
366 assertEquals(expected, getQuery("ä¸å›½^0.5", analyzer));
369 public void testCJKPhrase() throws Exception {
370 // individual CJK chars as terms
371 StandardAnalyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);
373 PhraseQuery expected = new PhraseQuery();
374 expected.add(new Term("field", "ä¸"));
375 expected.add(new Term("field", "国"));
377 assertEquals(expected, getQuery("\"ä¸å›½\"", analyzer));
380 public void testCJKBoostedPhrase() throws Exception {
381 // individual CJK chars as terms
382 StandardAnalyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);
384 PhraseQuery expected = new PhraseQuery();
385 expected.setBoost(0.5f);
386 expected.add(new Term("field", "ä¸"));
387 expected.add(new Term("field", "国"));
389 assertEquals(expected, getQuery("\"ä¸å›½\"^0.5", analyzer));
392 public void testCJKSloppyPhrase() throws Exception {
393 // individual CJK chars as terms
394 StandardAnalyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);
396 PhraseQuery expected = new PhraseQuery();
398 expected.add(new Term("field", "ä¸"));
399 expected.add(new Term("field", "国"));
401 assertEquals(expected, getQuery("\"ä¸å›½\"~3", analyzer));
404 public void testSimple() throws Exception {
405 assertQueryEquals("\"term germ\"~2", null, "\"term germ\"~2");
406 assertQueryEquals("term term term", null, "term term term");
407 assertQueryEquals("t�rm term term", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false),
409 assertQueryEquals("�mlaut", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false), "�mlaut");
411 assertQueryEquals("\"\"", new KeywordAnalyzer(), "");
412 assertQueryEquals("foo:\"\"", new KeywordAnalyzer(), "foo:");
414 assertQueryEquals("a AND b", null, "+a +b");
415 assertQueryEquals("(a AND b)", null, "+a +b");
416 assertQueryEquals("c OR (a AND b)", null, "c (+a +b)");
418 assertQueryEquals("a AND NOT b", null, "+a -b");
420 assertQueryEquals("a AND -b", null, "+a -b");
422 assertQueryEquals("a AND !b", null, "+a -b");
424 assertQueryEquals("a && b", null, "+a +b");
426 assertQueryEquals("a && ! b", null, "+a -b");
428 assertQueryEquals("a OR b", null, "a b");
429 assertQueryEquals("a || b", null, "a b");
431 assertQueryEquals("a OR !b", null, "a -b");
433 assertQueryEquals("a OR ! b", null, "a -b");
435 assertQueryEquals("a OR -b", null, "a -b");
437 assertQueryEquals("+term -term term", null, "+term -term term");
438 assertQueryEquals("foo:term AND field:anotherTerm", null,
439 "+foo:term +anotherterm");
440 assertQueryEquals("term AND \"phrase phrase\"", null,
441 "+term +\"phrase phrase\"");
442 assertQueryEquals("\"hello there\"", null, "\"hello there\"");
443 assertTrue(getQuery("a AND b", null) instanceof BooleanQuery);
444 assertTrue(getQuery("hello", null) instanceof TermQuery);
445 assertTrue(getQuery("\"hello there\"", null) instanceof PhraseQuery);
447 assertQueryEquals("germ term^2.0", null, "germ term^2.0");
448 assertQueryEquals("(term)^2.0", null, "term^2.0");
449 assertQueryEquals("(germ term)^2.0", null, "(germ term)^2.0");
450 assertQueryEquals("term^2.0", null, "term^2.0");
451 assertQueryEquals("term^2", null, "term^2.0");
452 assertQueryEquals("\"germ term\"^2.0", null, "\"germ term\"^2.0");
453 assertQueryEquals("\"term germ\"^2", null, "\"term germ\"^2.0");
455 assertQueryEquals("(foo OR bar) AND (baz OR boo)", null,
456 "+(foo bar) +(baz boo)");
457 assertQueryEquals("((a OR b) AND NOT c) OR d", null, "(+(a b) -c) d");
458 assertQueryEquals("+(apple \"steve jobs\") -(foo bar baz)", null,
459 "+(apple \"steve jobs\") -(foo bar baz)");
460 assertQueryEquals("+title:(dog OR cat) -author:\"bob dole\"", null,
461 "+(title:dog title:cat) -author:\"bob dole\"");
465 public void testPunct() throws Exception {
466 Analyzer a = new MockAnalyzer(random, MockTokenizer.WHITESPACE, false);
467 assertQueryEquals("a&b", a, "a&b");
468 assertQueryEquals("a&&b", a, "a&&b");
469 assertQueryEquals(".NET", a, ".NET");
472 public void testSlop() throws Exception {
474 assertQueryEquals("\"term germ\"~2", null, "\"term germ\"~2");
475 assertQueryEquals("\"term germ\"~2 flork", null, "\"term germ\"~2 flork");
476 assertQueryEquals("\"term\"~2", null, "term");
477 assertQueryEquals("\" \"~2 germ", null, "germ");
478 assertQueryEquals("\"term germ\"~2^2", null, "\"term germ\"~2^2.0");
481 public void testNumber() throws Exception {
482 // The numbers go away because SimpleAnalzyer ignores them
483 assertQueryEquals("3", null, "");
484 assertQueryEquals("term 1.0 1 2", null, "term");
485 assertQueryEquals("term term1 term2", null, "term term term");
487 Analyzer a = new MockAnalyzer(random, MockTokenizer.WHITESPACE, false);
488 assertQueryEquals("3", a, "3");
489 assertQueryEquals("term 1.0 1 2", a, "term 1.0 1 2");
490 assertQueryEquals("term term1 term2", a, "term term1 term2");
493 public void testWildcard() throws Exception {
494 assertQueryEquals("term*", null, "term*");
495 assertQueryEquals("term*^2", null, "term*^2.0");
496 assertQueryEquals("term~", null, "term~0.5");
497 assertQueryEquals("term~0.7", null, "term~0.7");
499 assertQueryEquals("term~^2", null, "term~0.5^2.0");
501 assertQueryEquals("term^2~", null, "term~0.5^2.0");
502 assertQueryEquals("term*germ", null, "term*germ");
503 assertQueryEquals("term*germ^3", null, "term*germ^3.0");
505 assertTrue(getQuery("term*", null) instanceof PrefixQuery);
506 assertTrue(getQuery("term*^2", null) instanceof PrefixQuery);
507 assertTrue(getQuery("term~", null) instanceof FuzzyQuery);
508 assertTrue(getQuery("term~0.7", null) instanceof FuzzyQuery);
509 FuzzyQuery fq = (FuzzyQuery) getQuery("term~0.7", null);
510 assertEquals(0.7f, fq.getMinSimilarity(), 0.1f);
511 assertEquals(FuzzyQuery.defaultPrefixLength, fq.getPrefixLength());
512 fq = (FuzzyQuery) getQuery("term~", null);
513 assertEquals(0.5f, fq.getMinSimilarity(), 0.1f);
514 assertEquals(FuzzyQuery.defaultPrefixLength, fq.getPrefixLength());
516 assertQueryNodeException("term~1.1"); // value > 1, throws exception
518 assertTrue(getQuery("term*germ", null) instanceof WildcardQuery);
521 * Tests to see that wild card terms are (or are not) properly lower-cased
522 * with propery parser configuration
524 // First prefix queries:
525 // by default, convert to lowercase:
526 assertWildcardQueryEquals("Term*", true, "term*");
527 // explicitly set lowercase:
528 assertWildcardQueryEquals("term*", true, "term*");
529 assertWildcardQueryEquals("Term*", true, "term*");
530 assertWildcardQueryEquals("TERM*", true, "term*");
531 // explicitly disable lowercase conversion:
532 assertWildcardQueryEquals("term*", false, "term*");
533 assertWildcardQueryEquals("Term*", false, "Term*");
534 assertWildcardQueryEquals("TERM*", false, "TERM*");
535 // Then 'full' wildcard queries:
536 // by default, convert to lowercase:
537 assertWildcardQueryEquals("Te?m", "te?m");
538 // explicitly set lowercase:
539 assertWildcardQueryEquals("te?m", true, "te?m");
540 assertWildcardQueryEquals("Te?m", true, "te?m");
541 assertWildcardQueryEquals("TE?M", true, "te?m");
542 assertWildcardQueryEquals("Te?m*gerM", true, "te?m*germ");
543 // explicitly disable lowercase conversion:
544 assertWildcardQueryEquals("te?m", false, "te?m");
545 assertWildcardQueryEquals("Te?m", false, "Te?m");
546 assertWildcardQueryEquals("TE?M", false, "TE?M");
547 assertWildcardQueryEquals("Te?m*gerM", false, "Te?m*gerM");
549 assertWildcardQueryEquals("Term~", "term~0.5");
550 assertWildcardQueryEquals("Term~", true, "term~0.5");
551 assertWildcardQueryEquals("Term~", false, "Term~0.5");
554 // TODO: implement this on QueryParser
555 // Q0002E_INVALID_SYNTAX_CANNOT_PARSE: Syntax Error, cannot parse '[A TO
556 // C]': Lexical error at line 1, column 1. Encountered: "[" (91), after
558 assertWildcardQueryEquals("[A TO C]", "[a TO c]");
559 assertWildcardQueryEquals("[A TO C]", true, "[a TO c]");
560 assertWildcardQueryEquals("[A TO C]", false, "[A TO C]");
561 // Test suffix queries: first disallow
563 assertWildcardQueryEquals("*Term", true, "*term");
565 } catch (QueryNodeException pe) {
566 // expected exception
569 assertWildcardQueryEquals("?Term", true, "?term");
571 } catch (QueryNodeException pe) {
572 // expected exception
574 // Test suffix queries: then allow
575 assertWildcardQueryEquals("*Term", true, "*term", true);
576 assertWildcardQueryEquals("?Term", true, "?term", true);
579 public void testLeadingWildcardType() throws Exception {
580 StandardQueryParser qp = getParser(null);
581 qp.setAllowLeadingWildcard(true);
582 assertEquals(WildcardQuery.class, qp.parse("t*erm*", "field").getClass());
583 assertEquals(WildcardQuery.class, qp.parse("?term*", "field").getClass());
584 assertEquals(WildcardQuery.class, qp.parse("*term*", "field").getClass());
587 public void testQPA() throws Exception {
588 assertQueryEquals("term term^3.0 term", qpAnalyzer, "term term^3.0 term");
589 assertQueryEquals("term stop^3.0 term", qpAnalyzer, "term term");
591 assertQueryEquals("term term term", qpAnalyzer, "term term term");
592 assertQueryEquals("term +stop term", qpAnalyzer, "term term");
593 assertQueryEquals("term -stop term", qpAnalyzer, "term term");
595 assertQueryEquals("drop AND (stop) AND roll", qpAnalyzer, "+drop +roll");
596 assertQueryEquals("term +(stop) term", qpAnalyzer, "term term");
597 assertQueryEquals("term -(stop) term", qpAnalyzer, "term term");
599 assertQueryEquals("drop AND stop AND roll", qpAnalyzer, "+drop +roll");
600 assertQueryEquals("term phrase term", qpAnalyzer,
601 "term (phrase1 phrase2) term");
603 assertQueryEquals("term AND NOT phrase term", qpAnalyzer,
604 "+term -(phrase1 phrase2) term");
606 assertQueryEquals("stop^3", qpAnalyzer, "");
607 assertQueryEquals("stop", qpAnalyzer, "");
608 assertQueryEquals("(stop)^3", qpAnalyzer, "");
609 assertQueryEquals("((stop))^3", qpAnalyzer, "");
610 assertQueryEquals("(stop^3)", qpAnalyzer, "");
611 assertQueryEquals("((stop)^3)", qpAnalyzer, "");
612 assertQueryEquals("(stop)", qpAnalyzer, "");
613 assertQueryEquals("((stop))", qpAnalyzer, "");
614 assertTrue(getQuery("term term term", qpAnalyzer) instanceof BooleanQuery);
615 assertTrue(getQuery("term +stop", qpAnalyzer) instanceof TermQuery);
618 public void testRange() throws Exception {
619 assertQueryEquals("[ a TO z]", null, "[a TO z]");
620 assertEquals(MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT, ((TermRangeQuery)getQuery("[ a TO z]", null)).getRewriteMethod());
622 StandardQueryParser qp = new StandardQueryParser();
624 qp.setMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
625 assertEquals(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE,((TermRangeQuery)qp.parse("[ a TO z]", "field")).getRewriteMethod());
627 assertQueryEquals("[ a TO z ]", null, "[a TO z]");
628 assertQueryEquals("{ a TO z}", null, "{a TO z}");
629 assertQueryEquals("{ a TO z }", null, "{a TO z}");
630 assertQueryEquals("{ a TO z }^2.0", null, "{a TO z}^2.0");
631 assertQueryEquals("[ a TO z] OR bar", null, "[a TO z] bar");
632 assertQueryEquals("[ a TO z] AND bar", null, "+[a TO z] +bar");
633 assertQueryEquals("( bar blar { a TO z}) ", null, "bar blar {a TO z}");
634 assertQueryEquals("gack ( bar blar { a TO z}) ", null,
635 "gack (bar blar {a TO z})");
638 public void testFarsiRangeCollating() throws Exception {
639 Directory ramDir = newDirectory();
640 IndexWriter iw = new IndexWriter(ramDir, newIndexWriterConfig(TEST_VERSION_CURRENT, new WhitespaceAnalyzer(TEST_VERSION_CURRENT)));
641 Document doc = new Document();
642 doc.add(newField("content", "\u0633\u0627\u0628", Field.Store.YES,
643 Field.Index.NOT_ANALYZED));
646 IndexSearcher is = new IndexSearcher(ramDir, true);
648 StandardQueryParser qp = new StandardQueryParser();
649 qp.setAnalyzer(new WhitespaceAnalyzer(TEST_VERSION_CURRENT));
651 // Neither Java 1.4.2 nor 1.5.0 has Farsi Locale collation available in
652 // RuleBasedCollator. However, the Arabic Locale seems to order the
654 // characters properly.
655 Collator c = Collator.getInstance(new Locale("ar"));
656 qp.setRangeCollator(c);
658 // Unicode order would include U+0633 in [ U+062F - U+0698 ], but Farsi
659 // orders the U+0698 character before the U+0633 character, so the
661 // index Term below should NOT be returned by a ConstantScoreRangeQuery
662 // with a Farsi Collator (or an Arabic one for the case when Farsi is
666 // Test ConstantScoreRangeQuery
667 qp.setMultiTermRewriteMethod(MultiTermQuery.CONSTANT_SCORE_FILTER_REWRITE);
668 ScoreDoc[] result = is.search(qp.parse("[ \u062F TO \u0698 ]", "content"),
669 null, 1000).scoreDocs;
670 assertEquals("The index Term should not be included.", 0, result.length);
672 result = is.search(qp.parse("[ \u0633 TO \u0638 ]", "content"), null, 1000).scoreDocs;
673 assertEquals("The index Term should be included.", 1, result.length);
676 qp.setMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
677 result = is.search(qp.parse("[ \u062F TO \u0698 ]", "content"), null, 1000).scoreDocs;
678 assertEquals("The index Term should not be included.", 0, result.length);
680 result = is.search(qp.parse("[ \u0633 TO \u0638 ]", "content"), null, 1000).scoreDocs;
681 assertEquals("The index Term should be included.", 1, result.length);
687 /** for testing legacy DateField support */
688 private String getLegacyDate(String s) throws Exception {
689 DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT);
690 return DateField.dateToString(df.parse(s));
693 /** for testing DateTools support */
694 private String getDate(String s, DateTools.Resolution resolution)
696 DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT);
697 return getDate(df.parse(s), resolution);
700 /** for testing DateTools support */
701 private String getDate(Date d, DateTools.Resolution resolution)
703 if (resolution == null) {
704 return DateField.dateToString(d);
706 return DateTools.dateToString(d, resolution);
710 private String escapeDateString(String s) {
711 if (s.contains(" ")) {
712 return "\"" + s + "\"";
718 private String getLocalizedDate(int year, int month, int day) {
719 DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT);
720 Calendar calendar = new GregorianCalendar();
722 calendar.set(year, month, day);
723 calendar.set(Calendar.HOUR_OF_DAY, 23);
724 calendar.set(Calendar.MINUTE, 59);
725 calendar.set(Calendar.SECOND, 59);
726 calendar.set(Calendar.MILLISECOND, 999);
727 return df.format(calendar.getTime());
730 /** for testing legacy DateField support */
731 public void testLegacyDateRange() throws Exception {
732 String startDate = getLocalizedDate(2002, 1, 1);
733 String endDate = getLocalizedDate(2002, 1, 4);
734 Calendar endDateExpected = new GregorianCalendar();
735 endDateExpected.clear();
736 endDateExpected.set(2002, 1, 4, 23, 59, 59);
737 endDateExpected.set(Calendar.MILLISECOND, 999);
738 assertQueryEquals("[ " + escapeDateString(startDate) + " TO " + escapeDateString(endDate) + "]", null, "["
739 + getLegacyDate(startDate) + " TO "
740 + DateField.dateToString(endDateExpected.getTime()) + "]");
741 assertQueryEquals("{ " + escapeDateString(startDate) + " " + escapeDateString(endDate) + " }", null, "{"
742 + getLegacyDate(startDate) + " TO " + getLegacyDate(endDate) + "}");
745 public void testDateRange() throws Exception {
746 String startDate = getLocalizedDate(2002, 1, 1);
747 String endDate = getLocalizedDate(2002, 1, 4);
748 Calendar endDateExpected = new GregorianCalendar();
749 endDateExpected.clear();
750 endDateExpected.set(2002, 1, 4, 23, 59, 59);
751 endDateExpected.set(Calendar.MILLISECOND, 999);
752 final String defaultField = "default";
753 final String monthField = "month";
754 final String hourField = "hour";
755 StandardQueryParser qp = new StandardQueryParser();
757 // Don't set any date resolution and verify if DateField is used
758 assertDateRangeQueryEquals(qp, defaultField, startDate, endDate,
759 endDateExpected.getTime(), null);
761 Map<CharSequence, DateTools.Resolution> dateRes = new HashMap<CharSequence, DateTools.Resolution>();
763 // set a field specific date resolution
764 dateRes.put(monthField, DateTools.Resolution.MONTH);
765 qp.setDateResolution(dateRes);
767 // DateField should still be used for defaultField
768 assertDateRangeQueryEquals(qp, defaultField, startDate, endDate,
769 endDateExpected.getTime(), null);
771 // set default date resolution to MILLISECOND
772 qp.setDateResolution(DateTools.Resolution.MILLISECOND);
774 // set second field specific date resolution
775 dateRes.put(hourField, DateTools.Resolution.HOUR);
776 qp.setDateResolution(dateRes);
778 // for this field no field specific date resolution has been set,
779 // so verify if the default resolution is used
780 assertDateRangeQueryEquals(qp, defaultField, startDate, endDate,
781 endDateExpected.getTime(), DateTools.Resolution.MILLISECOND);
783 // verify if field specific date resolutions are used for these two
785 assertDateRangeQueryEquals(qp, monthField, startDate, endDate,
786 endDateExpected.getTime(), DateTools.Resolution.MONTH);
788 assertDateRangeQueryEquals(qp, hourField, startDate, endDate,
789 endDateExpected.getTime(), DateTools.Resolution.HOUR);
792 public void assertDateRangeQueryEquals(StandardQueryParser qp,
793 String field, String startDate, String endDate, Date endDateInclusive,
794 DateTools.Resolution resolution) throws Exception {
795 assertQueryEquals(qp, field, field + ":[" + escapeDateString(startDate) + " TO " + escapeDateString(endDate)
796 + "]", "[" + getDate(startDate, resolution) + " TO "
797 + getDate(endDateInclusive, resolution) + "]");
798 assertQueryEquals(qp, field, field + ":{" + escapeDateString(startDate) + " TO " + escapeDateString(endDate)
799 + "}", "{" + getDate(startDate, resolution) + " TO "
800 + getDate(endDate, resolution) + "}");
803 public void testEscaped() throws Exception {
804 Analyzer a = new MockAnalyzer(random, MockTokenizer.WHITESPACE, false);
807 * assertQueryEquals("\\[brackets", a, "\\[brackets");
808 * assertQueryEquals("\\[brackets", null, "brackets");
809 * assertQueryEquals("\\\\", a, "\\\\"); assertQueryEquals("\\+blah", a,
810 * "\\+blah"); assertQueryEquals("\\(blah", a, "\\(blah");
812 * assertQueryEquals("\\-blah", a, "\\-blah"); assertQueryEquals("\\!blah",
813 * a, "\\!blah"); assertQueryEquals("\\{blah", a, "\\{blah");
814 * assertQueryEquals("\\}blah", a, "\\}blah"); assertQueryEquals("\\:blah",
815 * a, "\\:blah"); assertQueryEquals("\\^blah", a, "\\^blah");
816 * assertQueryEquals("\\[blah", a, "\\[blah"); assertQueryEquals("\\]blah",
817 * a, "\\]blah"); assertQueryEquals("\\\"blah", a, "\\\"blah");
818 * assertQueryEquals("\\(blah", a, "\\(blah"); assertQueryEquals("\\)blah",
819 * a, "\\)blah"); assertQueryEquals("\\~blah", a, "\\~blah");
820 * assertQueryEquals("\\*blah", a, "\\*blah"); assertQueryEquals("\\?blah",
821 * a, "\\?blah"); //assertQueryEquals("foo \\&\\& bar", a,
822 * "foo \\&\\& bar"); //assertQueryEquals("foo \\|| bar", a,
823 * "foo \\|| bar"); //assertQueryEquals("foo \\AND bar", a,
827 assertQueryEquals("\\*", a, "*");
829 assertQueryEquals("\\a", a, "a");
831 assertQueryEquals("a\\-b:c", a, "a-b:c");
832 assertQueryEquals("a\\+b:c", a, "a+b:c");
833 assertQueryEquals("a\\:b:c", a, "a:b:c");
834 assertQueryEquals("a\\\\b:c", a, "a\\b:c");
836 assertQueryEquals("a:b\\-c", a, "a:b-c");
837 assertQueryEquals("a:b\\+c", a, "a:b+c");
838 assertQueryEquals("a:b\\:c", a, "a:b:c");
839 assertQueryEquals("a:b\\\\c", a, "a:b\\c");
841 assertQueryEquals("a:b\\-c*", a, "a:b-c*");
842 assertQueryEquals("a:b\\+c*", a, "a:b+c*");
843 assertQueryEquals("a:b\\:c*", a, "a:b:c*");
845 assertQueryEquals("a:b\\\\c*", a, "a:b\\c*");
847 assertQueryEquals("a:b\\-?c", a, "a:b-?c");
848 assertQueryEquals("a:b\\+?c", a, "a:b+?c");
849 assertQueryEquals("a:b\\:?c", a, "a:b:?c");
851 assertQueryEquals("a:b\\\\?c", a, "a:b\\?c");
853 assertQueryEquals("a:b\\-c~", a, "a:b-c~0.5");
854 assertQueryEquals("a:b\\+c~", a, "a:b+c~0.5");
855 assertQueryEquals("a:b\\:c~", a, "a:b:c~0.5");
856 assertQueryEquals("a:b\\\\c~", a, "a:b\\c~0.5");
858 // TODO: implement Range queries on QueryParser
859 assertQueryEquals("[ a\\- TO a\\+ ]", null, "[a- TO a+]");
860 assertQueryEquals("[ a\\: TO a\\~ ]", null, "[a: TO a~]");
861 assertQueryEquals("[ a\\\\ TO a\\* ]", null, "[a\\ TO a*]");
864 "[\"c\\:\\\\temp\\\\\\~foo0.txt\" TO \"c\\:\\\\temp\\\\\\~foo9.txt\"]",
865 a, "[c:\\temp\\~foo0.txt TO c:\\temp\\~foo9.txt]");
867 assertQueryEquals("a\\\\\\+b", a, "a\\+b");
869 assertQueryEquals("a \\\"b c\\\" d", a, "a \"b c\" d");
870 assertQueryEquals("\"a \\\"b c\\\" d\"", a, "\"a \"b c\" d\"");
871 assertQueryEquals("\"a \\+b c d\"", a, "\"a +b c d\"");
873 assertQueryEquals("c\\:\\\\temp\\\\\\~foo.txt", a, "c:\\temp\\~foo.txt");
875 assertQueryNodeException("XY\\"); // there must be a character after the
878 // test unicode escaping
879 assertQueryEquals("a\\u0062c", a, "abc");
880 assertQueryEquals("XY\\u005a", a, "XYZ");
881 assertQueryEquals("XY\\u005A", a, "XYZ");
882 assertQueryEquals("\"a \\\\\\u0028\\u0062\\\" c\"", a, "\"a \\(b\" c\"");
884 assertQueryNodeException("XY\\u005G"); // test non-hex character in escaped
886 assertQueryNodeException("XY\\u005"); // test incomplete escaped unicode
889 // Tests bug LUCENE-800
890 assertQueryEquals("(item:\\\\ item:ABCD\\\\)", a, "item:\\ item:ABCD\\");
891 assertQueryNodeException("(item:\\\\ item:ABCD\\\\))"); // unmatched closing
893 assertQueryEquals("\\*", a, "*");
894 assertQueryEquals("\\\\", a, "\\"); // escaped backslash
896 assertQueryNodeException("\\"); // a backslash must always be escaped
899 assertQueryEquals("(\"a\\\\\") or (\"b\")", a, "a\\ or b");
902 public void testQueryStringEscaping() throws Exception {
903 Analyzer a = new MockAnalyzer(random, MockTokenizer.WHITESPACE, false);
905 assertEscapedQueryEquals("a-b:c", a, "a\\-b\\:c");
906 assertEscapedQueryEquals("a+b:c", a, "a\\+b\\:c");
907 assertEscapedQueryEquals("a:b:c", a, "a\\:b\\:c");
908 assertEscapedQueryEquals("a\\b:c", a, "a\\\\b\\:c");
910 assertEscapedQueryEquals("a:b-c", a, "a\\:b\\-c");
911 assertEscapedQueryEquals("a:b+c", a, "a\\:b\\+c");
912 assertEscapedQueryEquals("a:b:c", a, "a\\:b\\:c");
913 assertEscapedQueryEquals("a:b\\c", a, "a\\:b\\\\c");
915 assertEscapedQueryEquals("a:b-c*", a, "a\\:b\\-c\\*");
916 assertEscapedQueryEquals("a:b+c*", a, "a\\:b\\+c\\*");
917 assertEscapedQueryEquals("a:b:c*", a, "a\\:b\\:c\\*");
919 assertEscapedQueryEquals("a:b\\\\c*", a, "a\\:b\\\\\\\\c\\*");
921 assertEscapedQueryEquals("a:b-?c", a, "a\\:b\\-\\?c");
922 assertEscapedQueryEquals("a:b+?c", a, "a\\:b\\+\\?c");
923 assertEscapedQueryEquals("a:b:?c", a, "a\\:b\\:\\?c");
925 assertEscapedQueryEquals("a:b?c", a, "a\\:b\\?c");
927 assertEscapedQueryEquals("a:b-c~", a, "a\\:b\\-c\\~");
928 assertEscapedQueryEquals("a:b+c~", a, "a\\:b\\+c\\~");
929 assertEscapedQueryEquals("a:b:c~", a, "a\\:b\\:c\\~");
930 assertEscapedQueryEquals("a:b\\c~", a, "a\\:b\\\\c\\~");
932 assertEscapedQueryEquals("[ a - TO a+ ]", null, "\\[ a \\- TO a\\+ \\]");
933 assertEscapedQueryEquals("[ a : TO a~ ]", null, "\\[ a \\: TO a\\~ \\]");
934 assertEscapedQueryEquals("[ a\\ TO a* ]", null, "\\[ a\\\\ TO a\\* \\]");
937 assertEscapedQueryEquals("|| abc ||", a, "\\|\\| abc \\|\\|");
938 assertEscapedQueryEquals("&& abc &&", a, "\\&\\& abc \\&\\&");
941 public void testTabNewlineCarriageReturn() throws Exception {
942 assertQueryEqualsDOA("+weltbank +worlbank", null, "+weltbank +worlbank");
944 assertQueryEqualsDOA("+weltbank\n+worlbank", null, "+weltbank +worlbank");
945 assertQueryEqualsDOA("weltbank \n+worlbank", null, "+weltbank +worlbank");
946 assertQueryEqualsDOA("weltbank \n +worlbank", null, "+weltbank +worlbank");
948 assertQueryEqualsDOA("+weltbank\r+worlbank", null, "+weltbank +worlbank");
949 assertQueryEqualsDOA("weltbank \r+worlbank", null, "+weltbank +worlbank");
950 assertQueryEqualsDOA("weltbank \r +worlbank", null, "+weltbank +worlbank");
952 assertQueryEqualsDOA("+weltbank\r\n+worlbank", null, "+weltbank +worlbank");
953 assertQueryEqualsDOA("weltbank \r\n+worlbank", null, "+weltbank +worlbank");
954 assertQueryEqualsDOA("weltbank \r\n +worlbank", null, "+weltbank +worlbank");
955 assertQueryEqualsDOA("weltbank \r \n +worlbank", null,
956 "+weltbank +worlbank");
958 assertQueryEqualsDOA("+weltbank\t+worlbank", null, "+weltbank +worlbank");
959 assertQueryEqualsDOA("weltbank \t+worlbank", null, "+weltbank +worlbank");
960 assertQueryEqualsDOA("weltbank \t +worlbank", null, "+weltbank +worlbank");
963 public void testSimpleDAO() throws Exception {
964 assertQueryEqualsDOA("term term term", null, "+term +term +term");
965 assertQueryEqualsDOA("term +term term", null, "+term +term +term");
966 assertQueryEqualsDOA("term term +term", null, "+term +term +term");
967 assertQueryEqualsDOA("term +term +term", null, "+term +term +term");
968 assertQueryEqualsDOA("-term term term", null, "-term +term +term");
971 public void testBoost() throws Exception {
972 StandardAnalyzer oneStopAnalyzer = new StandardAnalyzer(TEST_VERSION_CURRENT, Collections.singleton("on"));
973 StandardQueryParser qp = new StandardQueryParser();
974 qp.setAnalyzer(oneStopAnalyzer);
976 Query q = qp.parse("on^1.0", "field");
978 q = qp.parse("\"hello\"^2.0", "field");
980 assertEquals(q.getBoost(), (float) 2.0, (float) 0.5);
981 q = qp.parse("hello^2.0", "field");
983 assertEquals(q.getBoost(), (float) 2.0, (float) 0.5);
984 q = qp.parse("\"on\"^1.0", "field");
987 StandardQueryParser qp2 = new StandardQueryParser();
988 qp2.setAnalyzer(new StandardAnalyzer(TEST_VERSION_CURRENT));
990 q = qp2.parse("the^3", "field");
991 // "the" is a stop word so the result is an empty query:
993 assertEquals("", q.toString());
994 assertEquals(1.0f, q.getBoost(), 0.01f);
997 public void assertQueryNodeException(String queryString) throws Exception {
999 getQuery(queryString, null);
1000 } catch (QueryNodeException expected) {
1003 fail("ParseException expected, not thrown");
1006 public void testException() throws Exception {
1007 assertQueryNodeException("*leadingWildcard"); // disallowed by default
1008 assertQueryNodeException("\"some phrase");
1009 assertQueryNodeException("(foo bar");
1010 assertQueryNodeException("foo bar))");
1011 assertQueryNodeException("field:term:with:colon some more terms");
1012 assertQueryNodeException("(sub query)^5.0^2.0 plus more");
1013 assertQueryNodeException("secret AND illegal) AND access:confidential");
1016 public void testCustomQueryParserWildcard() {
1018 new QPTestParser(new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("a?t", "contents");
1019 fail("Wildcard queries should not be allowed");
1020 } catch (QueryNodeException expected) {
1021 // expected exception
1025 public void testCustomQueryParserFuzzy() throws Exception {
1027 new QPTestParser(new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("xunit~", "contents");
1028 fail("Fuzzy queries should not be allowed");
1029 } catch (QueryNodeException expected) {
1030 // expected exception
1034 public void testBooleanQuery() throws Exception {
1035 BooleanQuery.setMaxClauseCount(2);
1037 StandardQueryParser qp = new StandardQueryParser();
1038 qp.setAnalyzer(new MockAnalyzer(random, MockTokenizer.WHITESPACE, false));
1039 qp.parse("one two three", "field");
1040 fail("ParseException expected due to too many boolean clauses");
1041 } catch (QueryNodeException expected) {
1042 // too many boolean clauses, so ParseException is expected
1047 * This test differs from TestPrecedenceQueryParser
1049 public void testPrecedence() throws Exception {
1050 StandardQueryParser qp = new StandardQueryParser();
1051 qp.setAnalyzer(new MockAnalyzer(random, MockTokenizer.WHITESPACE, false));
1053 Query query1 = qp.parse("A AND B OR C AND D", "field");
1054 Query query2 = qp.parse("+A +B +C +D", "field");
1056 assertEquals(query1, query2);
1059 public void testLocalDateFormat() throws IOException, QueryNodeException {
1060 Directory ramDir = newDirectory();
1061 IndexWriter iw = new IndexWriter(ramDir, newIndexWriterConfig(TEST_VERSION_CURRENT, new WhitespaceAnalyzer(TEST_VERSION_CURRENT)));
1062 addDateDoc("a", 2005, 12, 2, 10, 15, 33, iw);
1063 addDateDoc("b", 2005, 12, 4, 22, 15, 00, iw);
1065 IndexSearcher is = new IndexSearcher(ramDir, true);
1066 assertHits(1, "[12/1/2005 TO 12/3/2005]", is);
1067 assertHits(2, "[12/1/2005 TO 12/4/2005]", is);
1068 assertHits(1, "[12/3/2005 TO 12/4/2005]", is);
1069 assertHits(1, "{12/1/2005 TO 12/3/2005}", is);
1070 assertHits(1, "{12/1/2005 TO 12/4/2005}", is);
1071 assertHits(0, "{12/3/2005 TO 12/4/2005}", is);
1076 public void testStarParsing() throws Exception {
1077 // final int[] type = new int[1];
1078 // StandardQueryParser qp = new StandardQueryParser("field", new
1079 // WhitespaceAnalyzer()) {
1080 // protected Query getWildcardQuery(String field, String termStr) throws
1082 // // override error checking of superclass
1084 // return new TermQuery(new Term(field,termStr));
1086 // protected Query getPrefixQuery(String field, String termStr) throws
1088 // // override error checking of superclass
1090 // return new TermQuery(new Term(field,termStr));
1093 // protected Query getFieldQuery(String field, String queryText) throws
1096 // return super.getFieldQuery(field, queryText);
1102 // tq = (TermQuery)qp.parse("foo:zoo*");
1103 // assertEquals("zoo",tq.getTerm().text());
1104 // assertEquals(2,type[0]);
1106 // tq = (TermQuery)qp.parse("foo:zoo*^2");
1107 // assertEquals("zoo",tq.getTerm().text());
1108 // assertEquals(2,type[0]);
1109 // assertEquals(tq.getBoost(),2,0);
1111 // tq = (TermQuery)qp.parse("foo:*");
1112 // assertEquals("*",tq.getTerm().text());
1113 // assertEquals(1,type[0]); // could be a valid prefix query in the
1116 // tq = (TermQuery)qp.parse("foo:*^2");
1117 // assertEquals("*",tq.getTerm().text());
1118 // assertEquals(1,type[0]);
1119 // assertEquals(tq.getBoost(),2,0);
1121 // tq = (TermQuery)qp.parse("*:foo");
1122 // assertEquals("*",tq.getTerm().field());
1123 // assertEquals("foo",tq.getTerm().text());
1124 // assertEquals(3,type[0]);
1126 // tq = (TermQuery)qp.parse("*:*");
1127 // assertEquals("*",tq.getTerm().field());
1128 // assertEquals("*",tq.getTerm().text());
1129 // assertEquals(1,type[0]); // could be handled as a prefix query in the
1132 // tq = (TermQuery)qp.parse("(*:*)");
1133 // assertEquals("*",tq.getTerm().field());
1134 // assertEquals("*",tq.getTerm().text());
1135 // assertEquals(1,type[0]);
1139 public void testStopwords() throws Exception {
1140 StandardQueryParser qp = new StandardQueryParser();
1142 new StopAnalyzer(TEST_VERSION_CURRENT, StopFilter.makeStopSet(TEST_VERSION_CURRENT, "the", "foo" )));
1144 Query result = qp.parse("a:the OR a:foo", "a");
1145 assertNotNull("result is null and it shouldn't be", result);
1146 assertTrue("result is not a BooleanQuery", result instanceof BooleanQuery);
1147 assertTrue(((BooleanQuery) result).clauses().size() + " does not equal: "
1148 + 0, ((BooleanQuery) result).clauses().size() == 0);
1149 result = qp.parse("a:woo OR a:the", "a");
1150 assertNotNull("result is null and it shouldn't be", result);
1151 assertTrue("result is not a TermQuery", result instanceof TermQuery);
1153 "(fieldX:xxxxx OR fieldy:xxxxxxxx)^2 AND (fieldx:the OR fieldy:foo)",
1155 assertNotNull("result is null and it shouldn't be", result);
1156 assertTrue("result is not a BooleanQuery", result instanceof BooleanQuery);
1158 System.out.println("Result: " + result);
1159 assertTrue(((BooleanQuery) result).clauses().size() + " does not equal: "
1160 + 2, ((BooleanQuery) result).clauses().size() == 2);
1163 public void testPositionIncrement() throws Exception {
1164 StandardQueryParser qp = new StandardQueryParser();
1166 new StopAnalyzer(TEST_VERSION_CURRENT, StopFilter.makeStopSet(TEST_VERSION_CURRENT, "the", "in", "are", "this" )));
1168 qp.setEnablePositionIncrements(true);
1170 String qtxt = "\"the words in poisitions pos02578 are stopped in this phrasequery\"";
1172 int expectedPositions[] = { 1, 3, 4, 6, 9 };
1173 PhraseQuery pq = (PhraseQuery) qp.parse(qtxt, "a");
1174 // System.out.println("Query text: "+qtxt);
1175 // System.out.println("Result: "+pq);
1176 Term t[] = pq.getTerms();
1177 int pos[] = pq.getPositions();
1178 for (int i = 0; i < t.length; i++) {
1179 // System.out.println(i+". "+t[i]+" pos: "+pos[i]);
1180 assertEquals("term " + i + " = " + t[i] + " has wrong term-position!",
1181 expectedPositions[i], pos[i]);
1185 public void testMatchAllDocs() throws Exception {
1186 StandardQueryParser qp = new StandardQueryParser();
1187 qp.setAnalyzer(new MockAnalyzer(random, MockTokenizer.WHITESPACE, false));
1189 assertEquals(new MatchAllDocsQuery(), qp.parse("*:*", "field"));
1190 assertEquals(new MatchAllDocsQuery(), qp.parse("(*:*)", "field"));
1191 BooleanQuery bq = (BooleanQuery) qp.parse("+*:* -*:*", "field");
1192 assertTrue(bq.getClauses()[0].getQuery() instanceof MatchAllDocsQuery);
1193 assertTrue(bq.getClauses()[1].getQuery() instanceof MatchAllDocsQuery);
1196 private void assertHits(int expected, String query, IndexSearcher is)
1197 throws IOException, QueryNodeException {
1198 StandardQueryParser qp = new StandardQueryParser();
1199 qp.setAnalyzer(new MockAnalyzer(random, MockTokenizer.WHITESPACE, false));
1200 qp.setLocale(Locale.ENGLISH);
1202 Query q = qp.parse(query, "date");
1203 ScoreDoc[] hits = is.search(q, null, 1000).scoreDocs;
1204 assertEquals(expected, hits.length);
1207 private void addDateDoc(String content, int year, int month, int day,
1208 int hour, int minute, int second, IndexWriter iw) throws IOException {
1209 Document d = new Document();
1210 d.add(newField("f", content, Field.Store.YES, Field.Index.ANALYZED));
1211 Calendar cal = Calendar.getInstance(Locale.ENGLISH);
1212 cal.set(year, month - 1, day, hour, minute, second);
1213 d.add(newField("date", DateField.dateToString(cal.getTime()),
1214 Field.Store.YES, Field.Index.NOT_ANALYZED));
1219 public void tearDown() throws Exception {
1220 BooleanQuery.setMaxClauseCount(originalMaxClauses);
1224 private class CannedTokenStream extends Tokenizer {
1225 private int upto = 0;
1226 private final PositionIncrementAttribute posIncr = addAttribute(PositionIncrementAttribute.class);
1227 private final CharTermAttribute term = addAttribute(CharTermAttribute.class);
1230 public boolean incrementToken() {
1236 posIncr.setPositionIncrement(1);
1237 term.setEmpty().append("a");
1238 } else if (upto == 1) {
1239 posIncr.setPositionIncrement(1);
1240 term.setEmpty().append("b");
1241 } else if (upto == 2) {
1242 posIncr.setPositionIncrement(0);
1243 term.setEmpty().append("c");
1245 posIncr.setPositionIncrement(0);
1246 term.setEmpty().append("d");
1253 public void reset() throws IOException {
1259 private class CannedAnalyzer extends Analyzer {
1261 public TokenStream tokenStream(String ignored, Reader alsoIgnored) {
1262 return new CannedTokenStream();
1266 public void testMultiPhraseQuery() throws Exception {
1267 Directory dir = newDirectory();
1268 IndexWriter w = new IndexWriter(dir, newIndexWriterConfig(TEST_VERSION_CURRENT, new CannedAnalyzer()));
1269 Document doc = new Document();
1270 doc.add(newField("field", "", Field.Store.NO, Field.Index.ANALYZED));
1272 IndexReader r = IndexReader.open(w, true);
1273 IndexSearcher s = newSearcher(r);
1275 Query q = new StandardQueryParser(new CannedAnalyzer()).parse("\"a\"", "field");
1276 assertTrue(q instanceof MultiPhraseQuery);
1277 assertEquals(1, s.search(q, 10).totalHits);