You are viewing a plain text version of this content. The canonical link for it is here.
Posted to java-commits@lucene.apache.org by bu...@apache.org on 2009/08/03 05:38:50 UTC
svn commit: r800191 [11/12] - in /lucene/java/trunk: ./ contrib/
contrib/queryparser/ contrib/queryparser/src/ contrib/queryparser/src/java/
contrib/queryparser/src/java/org/ contrib/queryparser/src/java/org/apache/
contrib/queryparser/src/java/org/apa...
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/original/TestQueryParserWrapper.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/original/TestQueryParserWrapper.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/original/TestQueryParserWrapper.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/original/TestQueryParserWrapper.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,1122 @@
+package org.apache.lucene.queryParser.original;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.IOException;
+import java.io.Reader;
+import java.text.Collator;
+import java.text.DateFormat;
+import java.util.Calendar;
+import java.util.Date;
+import java.util.List;
+import java.util.Locale;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.KeywordAnalyzer;
+import org.apache.lucene.analysis.LowerCaseTokenizer;
+import org.apache.lucene.analysis.SimpleAnalyzer;
+import org.apache.lucene.analysis.StopAnalyzer;
+import org.apache.lucene.analysis.StopFilter;
+import org.apache.lucene.analysis.Token;
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.WhitespaceAnalyzer;
+import org.apache.lucene.analysis.standard.StandardAnalyzer;
+import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
+import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.document.DateField;
+import org.apache.lucene.document.DateTools;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.index.IndexWriter;
+import org.apache.lucene.index.Term;
+import org.apache.lucene.messages.MessageImpl;
+import org.apache.lucene.queryParser.ParseException;
+import org.apache.lucene.queryParser.core.QueryNodeException;
+import org.apache.lucene.queryParser.core.messages.QueryParserMessages;
+import org.apache.lucene.queryParser.core.nodes.FuzzyQueryNode;
+import org.apache.lucene.queryParser.core.nodes.QueryNode;
+import org.apache.lucene.queryParser.core.nodes.WildcardQueryNode;
+import org.apache.lucene.queryParser.core.processors.QueryNodeProcessorImpl;
+import org.apache.lucene.queryParser.core.processors.QueryNodeProcessorPipeline;
+import org.apache.lucene.search.BooleanQuery;
+import org.apache.lucene.search.FuzzyQuery;
+import org.apache.lucene.search.IndexSearcher;
+import org.apache.lucene.search.MatchAllDocsQuery;
+import org.apache.lucene.search.MultiTermQuery;
+import org.apache.lucene.search.PhraseQuery;
+import org.apache.lucene.search.PrefixQuery;
+import org.apache.lucene.search.Query;
+import org.apache.lucene.search.ScoreDoc;
+import org.apache.lucene.search.TermQuery;
+import org.apache.lucene.search.TermRangeQuery;
+import org.apache.lucene.search.WildcardQuery;
+import org.apache.lucene.store.RAMDirectory;
+import org.apache.lucene.util.LuceneTestCase;
+
+/**
+ * This test case is a copy of the core Lucene query parser test, it was adapted
+ * to use new {@link QueryParserWrapper} instead of the old query parser.
+ *
+ * Tests QueryParser.
+ */
+public class TestQueryParserWrapper extends LuceneTestCase {
+
+ public static Analyzer qpAnalyzer = new QPTestAnalyzer();
+
+ public static class QPTestFilter extends TokenFilter {
+ TermAttribute termAtt;
+ OffsetAttribute offsetAtt;
+
+ /**
+ * Filter which discards the token 'stop' and which expands the token
+ * 'phrase' into 'phrase1 phrase2'
+ */
+ public QPTestFilter(TokenStream in) {
+ super(in);
+ termAtt = (TermAttribute) addAttribute(TermAttribute.class);
+ offsetAtt = (OffsetAttribute) addAttribute(OffsetAttribute.class);
+ }
+
+ boolean inPhrase = false;
+ int savedStart = 0, savedEnd = 0;
+
+ public Token next(Token reusableToken) throws IOException {
+ Token token = reusableToken;
+
+ if (inPhrase) {
+ inPhrase = false;
+ token.setTermBuffer("phrase2");
+ token.setStartOffset(savedStart);
+ token.setEndOffset(savedEnd);
+ return reusableToken;
+ } else
+ while ((token = this.input.next(reusableToken)) != null) {
+ if (token.term().equals("phrase")) {
+ inPhrase = true;
+ savedStart = token.startOffset();
+ savedEnd = token.endOffset();
+ token.setTermBuffer("phrase1");
+ token.setStartOffset(savedStart);
+ token.setEndOffset(savedEnd);
+ return token;
+ } else if (!token.term().equals("stop"))
+ return token;
+ }
+
+ return null;
+
+ }
+
+ public boolean incrementToken() throws IOException {
+ if (inPhrase) {
+ inPhrase = false;
+ termAtt.setTermBuffer("phrase2");
+ offsetAtt.setOffset(savedStart, savedEnd);
+ return true;
+ } else
+ while (input.incrementToken()) {
+ if (termAtt.term().equals("phrase")) {
+ inPhrase = true;
+ savedStart = offsetAtt.startOffset();
+ savedEnd = offsetAtt.endOffset();
+ termAtt.setTermBuffer("phrase1");
+ offsetAtt.setOffset(savedStart, savedEnd);
+ return true;
+ } else if (!termAtt.term().equals("stop"))
+ return true;
+ }
+ return false;
+ }
+ }
+
+ public static class QPTestAnalyzer extends Analyzer {
+
+ /** Filters LowerCaseTokenizer with StopFilter. */
+ public final TokenStream tokenStream(String fieldName, Reader reader) {
+ return new QPTestFilter(new LowerCaseTokenizer(reader));
+ }
+ }
+
+ public static class QPTestParser extends QueryParserWrapper {
+ public QPTestParser(String f, Analyzer a) {
+ super(f, a);
+
+ QueryNodeProcessorPipeline newProcessorPipeline = new QueryNodeProcessorPipeline(
+ getQueryProcessor().getQueryConfigHandler());
+ newProcessorPipeline.addProcessor(new QPTestParserQueryNodeProcessor());
+ newProcessorPipeline.addProcessor(getQueryProcessor());
+
+ setQueryProcessor(newProcessorPipeline);
+
+ }
+
+ protected Query getFuzzyQuery(String field, String termStr,
+ float minSimilarity) throws ParseException {
+ throw new ParseException("Fuzzy queries not allowed");
+ }
+
+ protected Query getWildcardQuery(String field, String termStr)
+ throws ParseException {
+ throw new ParseException("Wildcard queries not allowed");
+ }
+
+ private static class QPTestParserQueryNodeProcessor extends
+ QueryNodeProcessorImpl {
+
+ protected QueryNode postProcessNode(QueryNode node)
+ throws QueryNodeException {
+
+ return node;
+
+ }
+
+ protected QueryNode preProcessNode(QueryNode node)
+ throws QueryNodeException {
+
+ if (node instanceof WildcardQueryNode || node instanceof FuzzyQueryNode) {
+
+ throw new QueryNodeException(new MessageImpl(
+ QueryParserMessages.EMPTY_MESSAGE));
+
+ }
+
+ return node;
+
+ }
+
+ protected List<QueryNode> setChildrenOrder(List<QueryNode> children)
+ throws QueryNodeException {
+
+ return children;
+
+ }
+
+ }
+
+ }
+
+ private int originalMaxClauses;
+
+ public void setUp() throws Exception {
+ super.setUp();
+ originalMaxClauses = BooleanQuery.getMaxClauseCount();
+ }
+
+ public QueryParserWrapper getParser(Analyzer a) throws Exception {
+ if (a == null)
+ a = new SimpleAnalyzer();
+ QueryParserWrapper qp = new QueryParserWrapper("field", a);
+ qp.setDefaultOperator(QueryParserWrapper.OR_OPERATOR);
+ return qp;
+ }
+
+ public Query getQuery(String query, Analyzer a) throws Exception {
+ return getParser(a).parse(query);
+ }
+
+ public void assertQueryEquals(String query, Analyzer a, String result)
+ throws Exception {
+ Query q = getQuery(query, a);
+ String s = q.toString("field");
+ if (!s.equals(result)) {
+ fail("Query /" + query + "/ yielded /" + s + "/, expecting /" + result
+ + "/");
+ }
+ }
+
+ public void assertQueryEquals(QueryParserWrapper qp, String field,
+ String query, String result) throws Exception {
+ Query q = qp.parse(query);
+ String s = q.toString(field);
+ if (!s.equals(result)) {
+ fail("Query /" + query + "/ yielded /" + s + "/, expecting /" + result
+ + "/");
+ }
+ }
+
+ public void assertEscapedQueryEquals(String query, Analyzer a, String result)
+ throws Exception {
+ String escapedQuery = QueryParserWrapper.escape(query);
+ if (!escapedQuery.equals(result)) {
+ fail("Query /" + query + "/ yielded /" + escapedQuery + "/, expecting /"
+ + result + "/");
+ }
+ }
+
+ public void assertWildcardQueryEquals(String query, boolean lowercase,
+ String result, boolean allowLeadingWildcard) throws Exception {
+ QueryParserWrapper qp = getParser(null);
+ qp.setLowercaseExpandedTerms(lowercase);
+ qp.setAllowLeadingWildcard(allowLeadingWildcard);
+ Query q = qp.parse(query);
+ String s = q.toString("field");
+ if (!s.equals(result)) {
+ fail("WildcardQuery /" + query + "/ yielded /" + s + "/, expecting /"
+ + result + "/");
+ }
+ }
+
+ public void assertWildcardQueryEquals(String query, boolean lowercase,
+ String result) throws Exception {
+ assertWildcardQueryEquals(query, lowercase, result, false);
+ }
+
+ public void assertWildcardQueryEquals(String query, String result)
+ throws Exception {
+ QueryParserWrapper qp = getParser(null);
+ Query q = qp.parse(query);
+ String s = q.toString("field");
+ if (!s.equals(result)) {
+ fail("WildcardQuery /" + query + "/ yielded /" + s + "/, expecting /"
+ + result + "/");
+ }
+ }
+
+ public Query getQueryDOA(String query, Analyzer a) throws Exception {
+ if (a == null)
+ a = new SimpleAnalyzer();
+ QueryParserWrapper qp = new QueryParserWrapper("field", a);
+ qp.setDefaultOperator(QueryParserWrapper.AND_OPERATOR);
+ return qp.parse(query);
+ }
+
+ public void assertQueryEqualsDOA(String query, Analyzer a, String result)
+ throws Exception {
+ Query q = getQueryDOA(query, a);
+ String s = q.toString("field");
+ if (!s.equals(result)) {
+ fail("Query /" + query + "/ yielded /" + s + "/, expecting /" + result
+ + "/");
+ }
+ }
+
+ public void testCJK() throws Exception {
+ // Test Ideographic Space - As wide as a CJK character cell (fullwidth)
+ // used google to translate the word "term" to japanese -> ??
+ assertQueryEquals("term\u3000term\u3000term", null,
+ "term\u0020term\u0020term");
+ assertQueryEquals("??\u3000??\u3000??", null, "??\u0020??\u0020??");
+ }
+
+ public void testSimple() throws Exception {
+ assertQueryEquals("\"term germ\"~2", null, "\"term germ\"~2");
+ assertQueryEquals("term term term", null, "term term term");
+ assertQueryEquals("t�rm term term", new WhitespaceAnalyzer(),
+ "t�rm term term");
+ assertQueryEquals("�mlaut", new WhitespaceAnalyzer(), "�mlaut");
+
+ assertQueryEquals("\"\"", new KeywordAnalyzer(), "");
+ assertQueryEquals("foo:\"\"", new KeywordAnalyzer(), "foo:");
+
+ assertQueryEquals("a AND b", null, "+a +b");
+ assertQueryEquals("(a AND b)", null, "+a +b");
+ assertQueryEquals("c OR (a AND b)", null, "c (+a +b)");
+
+ assertQueryEquals("a AND NOT b", null, "+a -b");
+
+ assertQueryEquals("a AND -b", null, "+a -b");
+
+ assertQueryEquals("a AND !b", null, "+a -b");
+
+ assertQueryEquals("a && b", null, "+a +b");
+
+ assertQueryEquals("a && ! b", null, "+a -b");
+
+ assertQueryEquals("a OR b", null, "a b");
+ assertQueryEquals("a || b", null, "a b");
+
+ assertQueryEquals("a OR !b", null, "a -b");
+
+ assertQueryEquals("a OR ! b", null, "a -b");
+
+ assertQueryEquals("a OR -b", null, "a -b");
+
+ assertQueryEquals("+term -term term", null, "+term -term term");
+ assertQueryEquals("foo:term AND field:anotherTerm", null,
+ "+foo:term +anotherterm");
+ assertQueryEquals("term AND \"phrase phrase\"", null,
+ "+term +\"phrase phrase\"");
+ assertQueryEquals("\"hello there\"", null, "\"hello there\"");
+ assertTrue(getQuery("a AND b", null) instanceof BooleanQuery);
+ assertTrue(getQuery("hello", null) instanceof TermQuery);
+ assertTrue(getQuery("\"hello there\"", null) instanceof PhraseQuery);
+
+ assertQueryEquals("germ term^2.0", null, "germ term^2.0");
+ assertQueryEquals("(term)^2.0", null, "term^2.0");
+ assertQueryEquals("(germ term)^2.0", null, "(germ term)^2.0");
+ assertQueryEquals("term^2.0", null, "term^2.0");
+ assertQueryEquals("term^2", null, "term^2.0");
+ assertQueryEquals("\"germ term\"^2.0", null, "\"germ term\"^2.0");
+ assertQueryEquals("\"term germ\"^2", null, "\"term germ\"^2.0");
+
+ assertQueryEquals("(foo OR bar) AND (baz OR boo)", null,
+ "+(foo bar) +(baz boo)");
+ assertQueryEquals("((a OR b) AND NOT c) OR d", null, "(+(a b) -c) d");
+ assertQueryEquals("+(apple \"steve jobs\") -(foo bar baz)", null,
+ "+(apple \"steve jobs\") -(foo bar baz)");
+ assertQueryEquals("+title:(dog OR cat) -author:\"bob dole\"", null,
+ "+(title:dog title:cat) -author:\"bob dole\"");
+
+ QueryParserWrapper qp = new QueryParserWrapper("field",
+ new StandardAnalyzer());
+ // make sure OR is the default:
+ assertEquals(QueryParserWrapper.OR_OPERATOR, qp.getDefaultOperator());
+ qp.setDefaultOperator(QueryParserWrapper.AND_OPERATOR);
+ assertEquals(QueryParserWrapper.AND_OPERATOR, qp.getDefaultOperator());
+ qp.setDefaultOperator(QueryParserWrapper.OR_OPERATOR);
+ assertEquals(QueryParserWrapper.OR_OPERATOR, qp.getDefaultOperator());
+ }
+
+ public void testPunct() throws Exception {
+ Analyzer a = new WhitespaceAnalyzer();
+ assertQueryEquals("a&b", a, "a&b");
+ assertQueryEquals("a&&b", a, "a&&b");
+ assertQueryEquals(".NET", a, ".NET");
+ }
+
+ public void testSlop() throws Exception {
+
+ assertQueryEquals("\"term germ\"~2", null, "\"term germ\"~2");
+ assertQueryEquals("\"term germ\"~2 flork", null, "\"term germ\"~2 flork");
+ assertQueryEquals("\"term\"~2", null, "term");
+ assertQueryEquals("\" \"~2 germ", null, "germ");
+ assertQueryEquals("\"term germ\"~2^2", null, "\"term germ\"~2^2.0");
+ }
+
+ public void testNumber() throws Exception {
+ // The numbers go away because SimpleAnalzyer ignores them
+ assertQueryEquals("3", null, "");
+ assertQueryEquals("term 1.0 1 2", null, "term");
+ assertQueryEquals("term term1 term2", null, "term term term");
+
+ Analyzer a = new StandardAnalyzer();
+ assertQueryEquals("3", a, "3");
+ assertQueryEquals("term 1.0 1 2", a, "term 1.0 1 2");
+ assertQueryEquals("term term1 term2", a, "term term1 term2");
+ }
+
+ public void testWildcard() throws Exception {
+ assertQueryEquals("term*", null, "term*");
+ assertQueryEquals("term*^2", null, "term*^2.0");
+ assertQueryEquals("term~", null, "term~0.5");
+ assertQueryEquals("term~0.7", null, "term~0.7");
+
+ assertQueryEquals("term~^2", null, "term~0.5^2.0");
+
+ assertQueryEquals("term^2~", null, "term~0.5^2.0");
+ assertQueryEquals("term*germ", null, "term*germ");
+ assertQueryEquals("term*germ^3", null, "term*germ^3.0");
+
+ assertTrue(getQuery("term*", null) instanceof PrefixQuery);
+ assertTrue(getQuery("term*^2", null) instanceof PrefixQuery);
+ assertTrue(getQuery("term~", null) instanceof FuzzyQuery);
+ assertTrue(getQuery("term~0.7", null) instanceof FuzzyQuery);
+ FuzzyQuery fq = (FuzzyQuery) getQuery("term~0.7", null);
+ assertEquals(0.7f, fq.getMinSimilarity(), 0.1f);
+ assertEquals(FuzzyQuery.defaultPrefixLength, fq.getPrefixLength());
+ fq = (FuzzyQuery) getQuery("term~", null);
+ assertEquals(0.5f, fq.getMinSimilarity(), 0.1f);
+ assertEquals(FuzzyQuery.defaultPrefixLength, fq.getPrefixLength());
+
+ assertParseException("term~1.1"); // value > 1, throws exception
+
+ assertTrue(getQuery("term*germ", null) instanceof WildcardQuery);
+
+ /*
+ * Tests to see that wild card terms are (or are not) properly lower-cased
+ * with propery parser configuration
+ */
+ // First prefix queries:
+ // by default, convert to lowercase:
+ assertWildcardQueryEquals("Term*", true, "term*");
+ // explicitly set lowercase:
+ assertWildcardQueryEquals("term*", true, "term*");
+ assertWildcardQueryEquals("Term*", true, "term*");
+ assertWildcardQueryEquals("TERM*", true, "term*");
+ // explicitly disable lowercase conversion:
+ assertWildcardQueryEquals("term*", false, "term*");
+ assertWildcardQueryEquals("Term*", false, "Term*");
+ assertWildcardQueryEquals("TERM*", false, "TERM*");
+ // Then 'full' wildcard queries:
+ // by default, convert to lowercase:
+ assertWildcardQueryEquals("Te?m", "te?m");
+ // explicitly set lowercase:
+ assertWildcardQueryEquals("te?m", true, "te?m");
+ assertWildcardQueryEquals("Te?m", true, "te?m");
+ assertWildcardQueryEquals("TE?M", true, "te?m");
+ assertWildcardQueryEquals("Te?m*gerM", true, "te?m*germ");
+ // explicitly disable lowercase conversion:
+ assertWildcardQueryEquals("te?m", false, "te?m");
+ assertWildcardQueryEquals("Te?m", false, "Te?m");
+ assertWildcardQueryEquals("TE?M", false, "TE?M");
+ assertWildcardQueryEquals("Te?m*gerM", false, "Te?m*gerM");
+ // Fuzzy queries:
+ assertWildcardQueryEquals("Term~", "term~0.5");
+ assertWildcardQueryEquals("Term~", true, "term~0.5");
+ assertWildcardQueryEquals("Term~", false, "Term~0.5");
+ // Range queries:
+
+ // TODO: implement this on QueryParser
+ // Q0002E_INVALID_SYNTAX_CANNOT_PARSE: Syntax Error, cannot parse '[A TO
+ // C]': Lexical error at line 1, column 1. Encountered: "[" (91), after : ""
+ assertWildcardQueryEquals("[A TO C]", "[a TO c]");
+ assertWildcardQueryEquals("[A TO C]", true, "[a TO c]");
+ assertWildcardQueryEquals("[A TO C]", false, "[A TO C]");
+ // Test suffix queries: first disallow
+ try {
+ assertWildcardQueryEquals("*Term", true, "*term");
+ fail();
+ } catch (ParseException pe) {
+ // expected exception
+ }
+ try {
+ assertWildcardQueryEquals("?Term", true, "?term");
+ fail();
+ } catch (ParseException pe) {
+ // expected exception
+ }
+ // Test suffix queries: then allow
+ assertWildcardQueryEquals("*Term", true, "*term", true);
+ assertWildcardQueryEquals("?Term", true, "?term", true);
+ }
+
+ public void testLeadingWildcardType() throws Exception {
+ QueryParserWrapper qp = getParser(null);
+ qp.setAllowLeadingWildcard(true);
+ assertEquals(WildcardQuery.class, qp.parse("t*erm*").getClass());
+ assertEquals(WildcardQuery.class, qp.parse("?term*").getClass());
+ assertEquals(WildcardQuery.class, qp.parse("*term*").getClass());
+ }
+
+ public void testQPA() throws Exception {
+ assertQueryEquals("term term^3.0 term", qpAnalyzer, "term term^3.0 term");
+ assertQueryEquals("term stop^3.0 term", qpAnalyzer, "term term");
+
+ assertQueryEquals("term term term", qpAnalyzer, "term term term");
+ assertQueryEquals("term +stop term", qpAnalyzer, "term term");
+ assertQueryEquals("term -stop term", qpAnalyzer, "term term");
+
+ assertQueryEquals("drop AND (stop) AND roll", qpAnalyzer, "+drop +roll");
+ assertQueryEquals("term +(stop) term", qpAnalyzer, "term term");
+ assertQueryEquals("term -(stop) term", qpAnalyzer, "term term");
+
+ assertQueryEquals("drop AND stop AND roll", qpAnalyzer, "+drop +roll");
+ assertQueryEquals("term phrase term", qpAnalyzer,
+ "term \"phrase1 phrase2\" term");
+
+ assertQueryEquals("term AND NOT phrase term", qpAnalyzer,
+ "+term -\"phrase1 phrase2\" term");
+
+ assertQueryEquals("stop^3", qpAnalyzer, "");
+ assertQueryEquals("stop", qpAnalyzer, "");
+ assertQueryEquals("(stop)^3", qpAnalyzer, "");
+ assertQueryEquals("((stop))^3", qpAnalyzer, "");
+ assertQueryEquals("(stop^3)", qpAnalyzer, "");
+ assertQueryEquals("((stop)^3)", qpAnalyzer, "");
+ assertQueryEquals("(stop)", qpAnalyzer, "");
+ assertQueryEquals("((stop))", qpAnalyzer, "");
+ assertTrue(getQuery("term term term", qpAnalyzer) instanceof BooleanQuery);
+ assertTrue(getQuery("term +stop", qpAnalyzer) instanceof TermQuery);
+ }
+
+ public void testRange() throws Exception {
+ assertQueryEquals("[ a TO z]", null, "[a TO z]");
+ assertEquals(MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT, ((TermRangeQuery)getQuery("[ a TO z]", null)).getRewriteMethod());
+
+ QueryParserWrapper qp = new QueryParserWrapper("field",
+ new SimpleAnalyzer());
+
+ qp.setMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
+ assertEquals(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE,((TermRangeQuery)qp.parse("[ a TO z]")).getRewriteMethod());
+
+ assertQueryEquals("[ a TO z ]", null, "[a TO z]");
+ assertQueryEquals("{ a TO z}", null, "{a TO z}");
+ assertQueryEquals("{ a TO z }", null, "{a TO z}");
+ assertQueryEquals("{ a TO z }^2.0", null, "{a TO z}^2.0");
+ assertQueryEquals("[ a TO z] OR bar", null, "[a TO z] bar");
+ assertQueryEquals("[ a TO z] AND bar", null, "+[a TO z] +bar");
+ assertQueryEquals("( bar blar { a TO z}) ", null, "bar blar {a TO z}");
+ assertQueryEquals("gack ( bar blar { a TO z}) ", null,
+ "gack (bar blar {a TO z})");
+ }
+
+ public void testFarsiRangeCollating() throws Exception {
+
+ RAMDirectory ramDir = new RAMDirectory();
+ IndexWriter iw = new IndexWriter(ramDir, new WhitespaceAnalyzer(), true,
+ IndexWriter.MaxFieldLength.LIMITED);
+ Document doc = new Document();
+ doc.add(new Field("content", "\u0633\u0627\u0628", Field.Store.YES,
+ Field.Index.UN_TOKENIZED));
+ iw.addDocument(doc);
+ iw.close();
+ IndexSearcher is = new IndexSearcher(ramDir);
+
+ QueryParserWrapper qp = new QueryParserWrapper("content",
+ new WhitespaceAnalyzer());
+
+ // Neither Java 1.4.2 nor 1.5.0 has Farsi Locale collation available in
+ // RuleBasedCollator. However, the Arabic Locale seems to order the Farsi
+ // characters properly.
+ Collator c = Collator.getInstance(new Locale("ar"));
+ qp.setRangeCollator(c);
+
+ // Unicode order would include U+0633 in [ U+062F - U+0698 ], but Farsi
+ // orders the U+0698 character before the U+0633 character, so the single
+ // index Term below should NOT be returned by a ConstantScoreRangeQuery
+ // with a Farsi Collator (or an Arabic one for the case when Farsi is not
+ // supported).
+
+ // Test ConstantScoreRangeQuery
+ qp.setMultiTermRewriteMethod(MultiTermQuery.CONSTANT_SCORE_FILTER_REWRITE);
+ ScoreDoc[] result = is.search(qp.parse("[ \u062F TO \u0698 ]"), null, 1000).scoreDocs;
+ assertEquals("The index Term should not be included.", 0, result.length);
+
+ result = is.search(qp.parse("[ \u0633 TO \u0638 ]"), null, 1000).scoreDocs;
+ assertEquals("The index Term should be included.", 1, result.length);
+
+ // Test RangeQuery
+ qp.setMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
+ result = is.search(qp.parse("[ \u062F TO \u0698 ]"), null, 1000).scoreDocs;
+ assertEquals("The index Term should not be included.", 0, result.length);
+
+ result = is.search(qp.parse("[ \u0633 TO \u0638 ]"), null, 1000).scoreDocs;
+ assertEquals("The index Term should be included.", 1, result.length);
+
+ is.close();
+ }
+
+ /** for testing legacy DateField support */
+ private String getLegacyDate(String s) throws Exception {
+ DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT);
+ return DateField.dateToString(df.parse(s));
+ }
+
+ /** for testing DateTools support */
+ private String getDate(String s, DateTools.Resolution resolution)
+ throws Exception {
+ DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT);
+ return getDate(df.parse(s), resolution);
+ }
+
+ /** for testing DateTools support */
+ private String getDate(Date d, DateTools.Resolution resolution)
+ throws Exception {
+ if (resolution == null) {
+ return DateField.dateToString(d);
+ } else {
+ return DateTools.dateToString(d, resolution);
+ }
+ }
+
+ private String getLocalizedDate(int year, int month, int day,
+ boolean extendLastDate) {
+ DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT);
+ Calendar calendar = Calendar.getInstance();
+ calendar.set(year, month, day);
+ if (extendLastDate) {
+ calendar.set(Calendar.HOUR_OF_DAY, 23);
+ calendar.set(Calendar.MINUTE, 59);
+ calendar.set(Calendar.SECOND, 59);
+ calendar.set(Calendar.MILLISECOND, 999);
+ }
+ return df.format(calendar.getTime());
+ }
+
+ /** for testing legacy DateField support */
+ public void testLegacyDateRange() throws Exception {
+ String startDate = getLocalizedDate(2002, 1, 1, false);
+ String endDate = getLocalizedDate(2002, 1, 4, false);
+ Calendar endDateExpected = Calendar.getInstance();
+ endDateExpected.set(2002, 1, 4, 23, 59, 59);
+ endDateExpected.set(Calendar.MILLISECOND, 999);
+ assertQueryEquals("[ " + startDate + " TO " + endDate + "]", null, "["
+ + getLegacyDate(startDate) + " TO "
+ + DateField.dateToString(endDateExpected.getTime()) + "]");
+ assertQueryEquals("{ " + startDate + " " + endDate + " }", null, "{"
+ + getLegacyDate(startDate) + " TO " + getLegacyDate(endDate) + "}");
+ }
+
+ public void testDateRange() throws Exception {
+ String startDate = getLocalizedDate(2002, 1, 1, false);
+ String endDate = getLocalizedDate(2002, 1, 4, false);
+ Calendar endDateExpected = Calendar.getInstance();
+ endDateExpected.set(2002, 1, 4, 23, 59, 59);
+ endDateExpected.set(Calendar.MILLISECOND, 999);
+ final String defaultField = "default";
+ final String monthField = "month";
+ final String hourField = "hour";
+ QueryParserWrapper qp = new QueryParserWrapper("field",
+ new SimpleAnalyzer());
+
+ // Don't set any date resolution and verify if DateField is used
+ assertDateRangeQueryEquals(qp, defaultField, startDate, endDate,
+ endDateExpected.getTime(), null);
+
+ // set a field specific date resolution
+ qp.setDateResolution(monthField, DateTools.Resolution.MONTH);
+
+ // DateField should still be used for defaultField
+ assertDateRangeQueryEquals(qp, defaultField, startDate, endDate,
+ endDateExpected.getTime(), null);
+
+ // set default date resolution to MILLISECOND
+ qp.setDateResolution(DateTools.Resolution.MILLISECOND);
+
+ // set second field specific date resolution
+ qp.setDateResolution(hourField, DateTools.Resolution.HOUR);
+
+ // for this field no field specific date resolution has been set,
+ // so verify if the default resolution is used
+ assertDateRangeQueryEquals(qp, defaultField, startDate, endDate,
+ endDateExpected.getTime(), DateTools.Resolution.MILLISECOND);
+
+ // verify if field specific date resolutions are used for these two fields
+ assertDateRangeQueryEquals(qp, monthField, startDate, endDate,
+ endDateExpected.getTime(), DateTools.Resolution.MONTH);
+
+ assertDateRangeQueryEquals(qp, hourField, startDate, endDate,
+ endDateExpected.getTime(), DateTools.Resolution.HOUR);
+ }
+
+ public void assertDateRangeQueryEquals(QueryParserWrapper qp, String field,
+ String startDate, String endDate, Date endDateInclusive,
+ DateTools.Resolution resolution) throws Exception {
+ assertQueryEquals(qp, field, field + ":[" + startDate + " TO " + endDate
+ + "]", "[" + getDate(startDate, resolution) + " TO "
+ + getDate(endDateInclusive, resolution) + "]");
+ assertQueryEquals(qp, field, field + ":{" + startDate + " TO " + endDate
+ + "}", "{" + getDate(startDate, resolution) + " TO "
+ + getDate(endDate, resolution) + "}");
+ }
+
+ public void testEscaped() throws Exception {
+ Analyzer a = new WhitespaceAnalyzer();
+
+ /*
+ * assertQueryEquals("\\[brackets", a, "\\[brackets");
+ * assertQueryEquals("\\[brackets", null, "brackets");
+ * assertQueryEquals("\\\\", a, "\\\\"); assertQueryEquals("\\+blah", a,
+ * "\\+blah"); assertQueryEquals("\\(blah", a, "\\(blah");
+ *
+ * assertQueryEquals("\\-blah", a, "\\-blah"); assertQueryEquals("\\!blah",
+ * a, "\\!blah"); assertQueryEquals("\\{blah", a, "\\{blah");
+ * assertQueryEquals("\\}blah", a, "\\}blah"); assertQueryEquals("\\:blah",
+ * a, "\\:blah"); assertQueryEquals("\\^blah", a, "\\^blah");
+ * assertQueryEquals("\\[blah", a, "\\[blah"); assertQueryEquals("\\]blah",
+ * a, "\\]blah"); assertQueryEquals("\\\"blah", a, "\\\"blah");
+ * assertQueryEquals("\\(blah", a, "\\(blah"); assertQueryEquals("\\)blah",
+ * a, "\\)blah"); assertQueryEquals("\\~blah", a, "\\~blah");
+ * assertQueryEquals("\\*blah", a, "\\*blah"); assertQueryEquals("\\?blah",
+ * a, "\\?blah"); //assertQueryEquals("foo \\&\\& bar", a,
+ * "foo \\&\\& bar"); //assertQueryEquals("foo \\|| bar", a,
+ * "foo \\|| bar"); //assertQueryEquals("foo \\AND bar", a,
+ * "foo \\AND bar");
+ */
+
+ assertQueryEquals("\\a", a, "a");
+
+ assertQueryEquals("a\\-b:c", a, "a-b:c");
+ assertQueryEquals("a\\+b:c", a, "a+b:c");
+ assertQueryEquals("a\\:b:c", a, "a:b:c");
+ assertQueryEquals("a\\\\b:c", a, "a\\b:c");
+
+ assertQueryEquals("a:b\\-c", a, "a:b-c");
+ assertQueryEquals("a:b\\+c", a, "a:b+c");
+ assertQueryEquals("a:b\\:c", a, "a:b:c");
+ assertQueryEquals("a:b\\\\c", a, "a:b\\c");
+
+ assertQueryEquals("a:b\\-c*", a, "a:b-c*");
+ assertQueryEquals("a:b\\+c*", a, "a:b+c*");
+ assertQueryEquals("a:b\\:c*", a, "a:b:c*");
+
+ assertQueryEquals("a:b\\\\c*", a, "a:b\\c*");
+
+ assertQueryEquals("a:b\\-?c", a, "a:b-?c");
+ assertQueryEquals("a:b\\+?c", a, "a:b+?c");
+ assertQueryEquals("a:b\\:?c", a, "a:b:?c");
+
+ assertQueryEquals("a:b\\\\?c", a, "a:b\\?c");
+
+ assertQueryEquals("a:b\\-c~", a, "a:b-c~0.5");
+ assertQueryEquals("a:b\\+c~", a, "a:b+c~0.5");
+ assertQueryEquals("a:b\\:c~", a, "a:b:c~0.5");
+ assertQueryEquals("a:b\\\\c~", a, "a:b\\c~0.5");
+
+ // TODO: implement Range queries on QueryParser
+ assertQueryEquals("[ a\\- TO a\\+ ]", null, "[a- TO a+]");
+ assertQueryEquals("[ a\\: TO a\\~ ]", null, "[a: TO a~]");
+ assertQueryEquals("[ a\\\\ TO a\\* ]", null, "[a\\ TO a*]");
+
+ assertQueryEquals(
+ "[\"c\\:\\\\temp\\\\\\~foo0.txt\" TO \"c\\:\\\\temp\\\\\\~foo9.txt\"]",
+ a, "[c:\\temp\\~foo0.txt TO c:\\temp\\~foo9.txt]");
+
+ assertQueryEquals("a\\\\\\+b", a, "a\\+b");
+
+ assertQueryEquals("a \\\"b c\\\" d", a, "a \"b c\" d");
+ assertQueryEquals("\"a \\\"b c\\\" d\"", a, "\"a \"b c\" d\"");
+ assertQueryEquals("\"a \\+b c d\"", a, "\"a +b c d\"");
+
+ assertQueryEquals("c\\:\\\\temp\\\\\\~foo.txt", a, "c:\\temp\\~foo.txt");
+
+ assertParseException("XY\\"); // there must be a character after the escape
+ // char
+
+ // test unicode escaping
+ assertQueryEquals("a\\u0062c", a, "abc");
+ assertQueryEquals("XY\\u005a", a, "XYZ");
+ assertQueryEquals("XY\\u005A", a, "XYZ");
+ assertQueryEquals("\"a \\\\\\u0028\\u0062\\\" c\"", a, "\"a \\(b\" c\"");
+
+ assertParseException("XY\\u005G"); // test non-hex character in escaped
+ // unicode sequence
+ assertParseException("XY\\u005"); // test incomplete escaped unicode
+ // sequence
+
+ // Tests bug LUCENE-800
+ assertQueryEquals("(item:\\\\ item:ABCD\\\\)", a, "item:\\ item:ABCD\\");
+ assertParseException("(item:\\\\ item:ABCD\\\\))"); // unmatched closing
+ // paranthesis
+ assertQueryEquals("\\*", a, "*");
+ assertQueryEquals("\\\\", a, "\\"); // escaped backslash
+
+ assertParseException("\\"); // a backslash must always be escaped
+
+ // LUCENE-1189
+ assertQueryEquals("(\"a\\\\\") or (\"b\")", a, "a\\ or b");
+ }
+
+ public void testQueryStringEscaping() throws Exception {
+ Analyzer a = new WhitespaceAnalyzer();
+
+ assertEscapedQueryEquals("a-b:c", a, "a\\-b\\:c");
+ assertEscapedQueryEquals("a+b:c", a, "a\\+b\\:c");
+ assertEscapedQueryEquals("a:b:c", a, "a\\:b\\:c");
+ assertEscapedQueryEquals("a\\b:c", a, "a\\\\b\\:c");
+
+ assertEscapedQueryEquals("a:b-c", a, "a\\:b\\-c");
+ assertEscapedQueryEquals("a:b+c", a, "a\\:b\\+c");
+ assertEscapedQueryEquals("a:b:c", a, "a\\:b\\:c");
+ assertEscapedQueryEquals("a:b\\c", a, "a\\:b\\\\c");
+
+ assertEscapedQueryEquals("a:b-c*", a, "a\\:b\\-c\\*");
+ assertEscapedQueryEquals("a:b+c*", a, "a\\:b\\+c\\*");
+ assertEscapedQueryEquals("a:b:c*", a, "a\\:b\\:c\\*");
+
+ assertEscapedQueryEquals("a:b\\\\c*", a, "a\\:b\\\\\\\\c\\*");
+
+ assertEscapedQueryEquals("a:b-?c", a, "a\\:b\\-\\?c");
+ assertEscapedQueryEquals("a:b+?c", a, "a\\:b\\+\\?c");
+ assertEscapedQueryEquals("a:b:?c", a, "a\\:b\\:\\?c");
+
+ assertEscapedQueryEquals("a:b?c", a, "a\\:b\\?c");
+
+ assertEscapedQueryEquals("a:b-c~", a, "a\\:b\\-c\\~");
+ assertEscapedQueryEquals("a:b+c~", a, "a\\:b\\+c\\~");
+ assertEscapedQueryEquals("a:b:c~", a, "a\\:b\\:c\\~");
+ assertEscapedQueryEquals("a:b\\c~", a, "a\\:b\\\\c\\~");
+
+ assertEscapedQueryEquals("[ a - TO a+ ]", null, "\\[ a \\- TO a\\+ \\]");
+ assertEscapedQueryEquals("[ a : TO a~ ]", null, "\\[ a \\: TO a\\~ \\]");
+ assertEscapedQueryEquals("[ a\\ TO a* ]", null, "\\[ a\\\\ TO a\\* \\]");
+
+ // LUCENE-881
+ assertEscapedQueryEquals("|| abc ||", a, "\\|\\| abc \\|\\|");
+ assertEscapedQueryEquals("&& abc &&", a, "\\&\\& abc \\&\\&");
+ }
+
+ public void testTabNewlineCarriageReturn() throws Exception {
+ assertQueryEqualsDOA("+weltbank +worlbank", null, "+weltbank +worlbank");
+
+ assertQueryEqualsDOA("+weltbank\n+worlbank", null, "+weltbank +worlbank");
+ assertQueryEqualsDOA("weltbank \n+worlbank", null, "+weltbank +worlbank");
+ assertQueryEqualsDOA("weltbank \n +worlbank", null, "+weltbank +worlbank");
+
+ assertQueryEqualsDOA("+weltbank\r+worlbank", null, "+weltbank +worlbank");
+ assertQueryEqualsDOA("weltbank \r+worlbank", null, "+weltbank +worlbank");
+ assertQueryEqualsDOA("weltbank \r +worlbank", null, "+weltbank +worlbank");
+
+ assertQueryEqualsDOA("+weltbank\r\n+worlbank", null, "+weltbank +worlbank");
+ assertQueryEqualsDOA("weltbank \r\n+worlbank", null, "+weltbank +worlbank");
+ assertQueryEqualsDOA("weltbank \r\n +worlbank", null, "+weltbank +worlbank");
+ assertQueryEqualsDOA("weltbank \r \n +worlbank", null,
+ "+weltbank +worlbank");
+
+ assertQueryEqualsDOA("+weltbank\t+worlbank", null, "+weltbank +worlbank");
+ assertQueryEqualsDOA("weltbank \t+worlbank", null, "+weltbank +worlbank");
+ assertQueryEqualsDOA("weltbank \t +worlbank", null, "+weltbank +worlbank");
+ }
+
+ public void testSimpleDAO() throws Exception {
+ assertQueryEqualsDOA("term term term", null, "+term +term +term");
+ assertQueryEqualsDOA("term +term term", null, "+term +term +term");
+ assertQueryEqualsDOA("term term +term", null, "+term +term +term");
+ assertQueryEqualsDOA("term +term +term", null, "+term +term +term");
+ assertQueryEqualsDOA("-term term term", null, "-term +term +term");
+ }
+
+ public void testBoost() throws Exception {
+ StandardAnalyzer oneStopAnalyzer = new StandardAnalyzer(
+ new String[] { "on" });
+ QueryParserWrapper qp = new QueryParserWrapper("field", oneStopAnalyzer);
+ Query q = qp.parse("on^1.0");
+ assertNotNull(q);
+ q = qp.parse("\"hello\"^2.0");
+ assertNotNull(q);
+ assertEquals(q.getBoost(), (float) 2.0, (float) 0.5);
+ q = qp.parse("hello^2.0");
+ assertNotNull(q);
+ assertEquals(q.getBoost(), (float) 2.0, (float) 0.5);
+ q = qp.parse("\"on\"^1.0");
+ assertNotNull(q);
+
+ QueryParserWrapper qp2 = new QueryParserWrapper("field",
+ new StandardAnalyzer());
+ q = qp2.parse("the^3");
+ // "the" is a stop word so the result is an empty query:
+ assertNotNull(q);
+ assertEquals("", q.toString());
+ assertEquals(1.0f, q.getBoost(), 0.01f);
+ }
+
+ public void assertParseException(String queryString) throws Exception {
+ try {
+ getQuery(queryString, null);
+ } catch (ParseException expected) {
+ return;
+ }
+ fail("ParseException expected, not thrown");
+ }
+
+ public void testException() throws Exception {
+ assertParseException("\"some phrase");
+ assertParseException("(foo bar");
+ assertParseException("foo bar))");
+ assertParseException("field:term:with:colon some more terms");
+ assertParseException("(sub query)^5.0^2.0 plus more");
+ assertParseException("secret AND illegal) AND access:confidential");
+ }
+
+ public void testCustomQueryParserWildcard() {
+ try {
+ new QPTestParser("contents", new WhitespaceAnalyzer()).parse("a?t");
+ fail("Wildcard queries should not be allowed");
+ } catch (ParseException expected) {
+ // expected exception
+ }
+ }
+
+ public void testCustomQueryParserFuzzy() throws Exception {
+ try {
+ new QPTestParser("contents", new WhitespaceAnalyzer()).parse("xunit~");
+ fail("Fuzzy queries should not be allowed");
+ } catch (ParseException expected) {
+ // expected exception
+ }
+ }
+
+ public void testBooleanQuery() throws Exception {
+ BooleanQuery.setMaxClauseCount(2);
+ try {
+ QueryParserWrapper qp = new QueryParserWrapper("field",
+ new WhitespaceAnalyzer());
+ qp.parse("one two three");
+ fail("ParseException expected due to too many boolean clauses");
+ } catch (ParseException expected) {
+ // too many boolean clauses, so ParseException is expected
+ }
+ }
+
+ /**
+ * This test differs from TestPrecedenceQueryParser
+ */
+ public void testPrecedence() throws Exception {
+ QueryParserWrapper qp = new QueryParserWrapper("field",
+ new WhitespaceAnalyzer());
+ Query query1 = qp.parse("A AND B OR C AND D");
+ Query query2 = qp.parse("+A +B +C +D");
+
+ assertEquals(query1, query2);
+ }
+
+ public void testLocalDateFormat() throws IOException, ParseException {
+
+ RAMDirectory ramDir = new RAMDirectory();
+ IndexWriter iw = new IndexWriter(ramDir, new WhitespaceAnalyzer(), true,
+ IndexWriter.MaxFieldLength.LIMITED);
+ addDateDoc("a", 2005, 12, 2, 10, 15, 33, iw);
+ addDateDoc("b", 2005, 12, 4, 22, 15, 00, iw);
+ iw.close();
+ IndexSearcher is = new IndexSearcher(ramDir);
+ assertHits(1, "[12/1/2005 TO 12/3/2005]", is);
+ assertHits(2, "[12/1/2005 TO 12/4/2005]", is);
+ assertHits(1, "[12/3/2005 TO 12/4/2005]", is);
+ assertHits(1, "{12/1/2005 TO 12/3/2005}", is);
+ assertHits(1, "{12/1/2005 TO 12/4/2005}", is);
+ assertHits(0, "{12/3/2005 TO 12/4/2005}", is);
+ is.close();
+ }
+
+ public void testStarParsing() throws Exception {
+ // final int[] type = new int[1];
+ // QueryParser qp = new QueryParserWrapper("field", new
+ // WhitespaceAnalyzer()) {
+ // protected Query getWildcardQuery(String field, String termStr) throws
+ // ParseException {
+ // // override error checking of superclass
+ // type[0]=1;
+ // return new TermQuery(new Term(field,termStr));
+ // }
+ // protected Query getPrefixQuery(String field, String termStr) throws
+ // ParseException {
+ // // override error checking of superclass
+ // type[0]=2;
+ // return new TermQuery(new Term(field,termStr));
+ // }
+ //
+ // protected Query getFieldQuery(String field, String queryText) throws
+ // ParseException {
+ // type[0]=3;
+ // return super.getFieldQuery(field, queryText);
+ // }
+ // };
+ //
+ // TermQuery tq;
+ //
+ // tq = (TermQuery)qp.parse("foo:zoo*");
+ // assertEquals("zoo",tq.getTerm().text());
+ // assertEquals(2,type[0]);
+ //
+ // tq = (TermQuery)qp.parse("foo:zoo*^2");
+ // assertEquals("zoo",tq.getTerm().text());
+ // assertEquals(2,type[0]);
+ // assertEquals(tq.getBoost(),2,0);
+ //
+ // tq = (TermQuery)qp.parse("foo:*");
+ // assertEquals("*",tq.getTerm().text());
+ // assertEquals(1,type[0]); // could be a valid prefix query in the future
+ // too
+ //
+ // tq = (TermQuery)qp.parse("foo:*^2");
+ // assertEquals("*",tq.getTerm().text());
+ // assertEquals(1,type[0]);
+ // assertEquals(tq.getBoost(),2,0);
+ //
+ // tq = (TermQuery)qp.parse("*:foo");
+ // assertEquals("*",tq.getTerm().field());
+ // assertEquals("foo",tq.getTerm().text());
+ // assertEquals(3,type[0]);
+ //
+ // tq = (TermQuery)qp.parse("*:*");
+ // assertEquals("*",tq.getTerm().field());
+ // assertEquals("*",tq.getTerm().text());
+ // assertEquals(1,type[0]); // could be handled as a prefix query in the
+ // future
+ //
+ // tq = (TermQuery)qp.parse("(*:*)");
+ // assertEquals("*",tq.getTerm().field());
+ // assertEquals("*",tq.getTerm().text());
+ // assertEquals(1,type[0]);
+
+ }
+
+ public void testStopwords() throws Exception {
+ QueryParserWrapper qp = new QueryParserWrapper("a", new StopAnalyzer(
+ new String[] { "the", "foo" }));
+ Query result = qp.parse("a:the OR a:foo");
+ assertNotNull("result is null and it shouldn't be", result);
+ assertTrue("result is not a BooleanQuery", result instanceof BooleanQuery);
+ assertTrue(((BooleanQuery) result).clauses().size() + " does not equal: "
+ + 0, ((BooleanQuery) result).clauses().size() == 0);
+ result = qp.parse("a:woo OR a:the");
+ assertNotNull("result is null and it shouldn't be", result);
+ assertTrue("result is not a TermQuery", result instanceof TermQuery);
+ result = qp
+ .parse("(fieldX:xxxxx OR fieldy:xxxxxxxx)^2 AND (fieldx:the OR fieldy:foo)");
+ assertNotNull("result is null and it shouldn't be", result);
+ assertTrue("result is not a BooleanQuery", result instanceof BooleanQuery);
+ System.out.println("Result: " + result);
+ assertTrue(((BooleanQuery) result).clauses().size() + " does not equal: "
+ + 2, ((BooleanQuery) result).clauses().size() == 2);
+ }
+
+ public void testPositionIncrement() throws Exception {
+ boolean dflt = StopFilter.getEnablePositionIncrementsDefault();
+ StopFilter.setEnablePositionIncrementsDefault(true);
+ try {
+ QueryParserWrapper qp = new QueryParserWrapper("a", new StopAnalyzer(
+ new String[] { "the", "in", "are", "this" }));
+ qp.setEnablePositionIncrements(true);
+ String qtxt = "\"the words in poisitions pos02578 are stopped in this phrasequery\"";
+ // 0 2 5 7 8
+ int expectedPositions[] = { 1, 3, 4, 6, 9 };
+ PhraseQuery pq = (PhraseQuery) qp.parse(qtxt);
+ // System.out.println("Query text: "+qtxt);
+ // System.out.println("Result: "+pq);
+ Term t[] = pq.getTerms();
+ int pos[] = pq.getPositions();
+ for (int i = 0; i < t.length; i++) {
+ // System.out.println(i+". "+t[i]+" pos: "+pos[i]);
+ assertEquals("term " + i + " = " + t[i] + " has wrong term-position!",
+ expectedPositions[i], pos[i]);
+ }
+
+ } finally {
+ StopFilter.setEnablePositionIncrementsDefault(dflt);
+ }
+ }
+
+ public void testMatchAllDocs() throws Exception {
+ QueryParserWrapper qp = new QueryParserWrapper("field",
+ new WhitespaceAnalyzer());
+ assertEquals(new MatchAllDocsQuery(), qp.parse("*:*"));
+ assertEquals(new MatchAllDocsQuery(), qp.parse("(*:*)"));
+ BooleanQuery bq = (BooleanQuery) qp.parse("+*:* -*:*");
+ assertTrue(bq.getClauses()[0].getQuery() instanceof MatchAllDocsQuery);
+ assertTrue(bq.getClauses()[1].getQuery() instanceof MatchAllDocsQuery);
+ }
+
+ private void assertHits(int expected, String query, IndexSearcher is)
+ throws ParseException, IOException {
+ QueryParserWrapper qp = new QueryParserWrapper("date",
+ new WhitespaceAnalyzer());
+ qp.setLocale(Locale.ENGLISH);
+ Query q = qp.parse(query);
+ ScoreDoc[] hits = is.search(q, null, 1000).scoreDocs;
+ assertEquals(expected, hits.length);
+ }
+
+ private static void addDateDoc(String content, int year, int month, int day,
+ int hour, int minute, int second, IndexWriter iw) throws IOException {
+ Document d = new Document();
+ d.add(new Field("f", content, Field.Store.YES, Field.Index.ANALYZED));
+ Calendar cal = Calendar.getInstance();
+ cal.set(year, month - 1, day, hour, minute, second);
+ d.add(new Field("date", DateField.dateToString(cal.getTime()),
+ Field.Store.YES, Field.Index.NOT_ANALYZED));
+ iw.addDocument(d);
+ }
+
+ public void tearDown() throws Exception {
+ super.tearDown();
+ BooleanQuery.setMaxClauseCount(originalMaxClauses);
+ }
+
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/original/TestQueryParserWrapper.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpanOrQueryNodeBuilder.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpanOrQueryNodeBuilder.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpanOrQueryNodeBuilder.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpanOrQueryNodeBuilder.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,56 @@
+package org.apache.lucene.queryParser.spans;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.util.List;
+
+import org.apache.lucene.queryParser.core.QueryNodeException;
+import org.apache.lucene.queryParser.core.builders.QueryTreeBuilder;
+import org.apache.lucene.queryParser.core.nodes.BooleanQueryNode;
+import org.apache.lucene.queryParser.core.nodes.QueryNode;
+import org.apache.lucene.queryParser.original.builders.OriginalQueryBuilder;
+import org.apache.lucene.search.spans.SpanOrQuery;
+import org.apache.lucene.search.spans.SpanQuery;
+
+/**
+ * This builder creates {@link SpanOrQuery}s from a {@link BooleanQueryNode}.<br/>
+ * <br/>
+ *
+ * It assumes that the {@link BooleanQueryNode} instance has at least one child.
+ */
+public class SpanOrQueryNodeBuilder implements OriginalQueryBuilder {
+
+ public SpanOrQuery build(QueryNode node) throws QueryNodeException {
+
+ // validates node
+ BooleanQueryNode booleanNode = (BooleanQueryNode) node;
+
+ List<QueryNode> children = booleanNode.getChildren();
+ SpanQuery[] spanQueries = new SpanQuery[children.size()];
+
+ int i = 0;
+ for (QueryNode child : children) {
+ spanQueries[i++] = (SpanQuery) child
+ .getTag(QueryTreeBuilder.QUERY_TREE_BUILDER_TAGID);
+ }
+
+ return new SpanOrQuery(spanQueries);
+
+ }
+
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpanOrQueryNodeBuilder.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpanTermQueryNodeBuilder.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpanTermQueryNodeBuilder.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpanTermQueryNodeBuilder.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpanTermQueryNodeBuilder.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,41 @@
+package org.apache.lucene.queryParser.spans;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import org.apache.lucene.index.Term;
+import org.apache.lucene.queryParser.core.QueryNodeException;
+import org.apache.lucene.queryParser.core.nodes.FieldQueryNode;
+import org.apache.lucene.queryParser.core.nodes.QueryNode;
+import org.apache.lucene.queryParser.original.builders.OriginalQueryBuilder;
+import org.apache.lucene.search.spans.SpanTermQuery;
+
+/**
+ * This builder creates {@link SpanTermQuery}s from a {@link FieldQueryNode}
+ * object.
+ */
+public class SpanTermQueryNodeBuilder implements OriginalQueryBuilder {
+
+ public SpanTermQuery build(QueryNode node) throws QueryNodeException {
+ FieldQueryNode fieldQueryNode = (FieldQueryNode) node;
+
+ return new SpanTermQuery(new Term(fieldQueryNode.getFieldAsString(),
+ fieldQueryNode.getTextAsString()));
+
+ }
+
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpanTermQueryNodeBuilder.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansQueryConfigHandler.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansQueryConfigHandler.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansQueryConfigHandler.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansQueryConfigHandler.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,43 @@
+package org.apache.lucene.queryParser.spans;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import org.apache.lucene.queryParser.core.config.FieldConfig;
+import org.apache.lucene.queryParser.core.config.QueryConfigHandler;
+
+/**
+ * This query config handler only adds the {@link UniqueFieldAttribute} to it.<br/>
+ * <br/>
+ *
+ * It does not return any configuration for a field in specific.
+ */
+public class SpansQueryConfigHandler extends QueryConfigHandler {
+
+ public SpansQueryConfigHandler() {
+ addAttribute(UniqueFieldAttribute.class);
+ }
+
+ @Override
+ public FieldConfig getFieldConfig(CharSequence fieldName) {
+
+ // there is no field configuration, always return null
+ return null;
+
+ }
+
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansQueryConfigHandler.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansQueryTreeBuilder.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansQueryTreeBuilder.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansQueryTreeBuilder.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansQueryTreeBuilder.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,51 @@
+package org.apache.lucene.queryParser.spans;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import org.apache.lucene.queryParser.core.QueryNodeException;
+import org.apache.lucene.queryParser.core.builders.QueryTreeBuilder;
+import org.apache.lucene.queryParser.core.nodes.BooleanQueryNode;
+import org.apache.lucene.queryParser.core.nodes.FieldQueryNode;
+import org.apache.lucene.queryParser.core.nodes.QueryNode;
+import org.apache.lucene.queryParser.original.builders.OriginalQueryBuilder;
+import org.apache.lucene.search.spans.SpanQuery;
+
+/**
+ * Sets up a query tree builder to build a span query tree from a query node
+ * tree.<br/>
+ * <br/>
+ *
+ * The defined map is:<br/>
+ * - every BooleanQueryNode instance is delegated to the SpanOrQueryNodeBuilder<br/>
+ * - every FieldQueryNode instance is delegated to the SpanTermQueryNodeBuilder <br/>
+ *
+ */
+public class SpansQueryTreeBuilder extends QueryTreeBuilder implements
+ OriginalQueryBuilder {
+
+ public SpansQueryTreeBuilder() {
+ setBuilder(BooleanQueryNode.class, new SpanOrQueryNodeBuilder());
+ setBuilder(FieldQueryNode.class, new SpanTermQueryNodeBuilder());
+
+ }
+
+ public SpanQuery build(QueryNode queryTree) throws QueryNodeException {
+ return (SpanQuery) super.build(queryTree);
+ }
+
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansQueryTreeBuilder.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansValidatorQueryNodeProcessor.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansValidatorQueryNodeProcessor.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansValidatorQueryNodeProcessor.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansValidatorQueryNodeProcessor.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,72 @@
+package org.apache.lucene.queryParser.spans;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.util.List;
+
+import org.apache.lucene.messages.MessageImpl;
+import org.apache.lucene.queryParser.core.QueryNodeException;
+import org.apache.lucene.queryParser.core.messages.QueryParserMessages;
+import org.apache.lucene.queryParser.core.nodes.AndQueryNode;
+import org.apache.lucene.queryParser.core.nodes.BooleanQueryNode;
+import org.apache.lucene.queryParser.core.nodes.FieldQueryNode;
+import org.apache.lucene.queryParser.core.nodes.OrQueryNode;
+import org.apache.lucene.queryParser.core.nodes.QueryNode;
+import org.apache.lucene.queryParser.core.processors.QueryNodeProcessorImpl;
+
+/**
+ * Validates every query node in a query node tree. This processor will pass
+ * fine if the query nodes are only {@link BooleanQueryNode}s,
+ * {@link OrQueryNode}s or {@link FieldQueryNode}s, otherwise an exception will
+ * be thrown. <br/>
+ * <br/>
+ *
+ * If they are {@link AndQueryNode} or an instance of anything else that
+ * implements {@link FieldQueryNode} the exception will also be thrown.
+ */
+public class SpansValidatorQueryNodeProcessor extends QueryNodeProcessorImpl {
+
+ @Override
+ protected QueryNode postProcessNode(QueryNode node) throws QueryNodeException {
+
+ return node;
+
+ }
+
+ @Override
+ protected QueryNode preProcessNode(QueryNode node) throws QueryNodeException {
+
+ if (!((node instanceof BooleanQueryNode && !(node instanceof AndQueryNode)) || node
+ .getClass() == FieldQueryNode.class)) {
+ throw new QueryNodeException(new MessageImpl(
+ QueryParserMessages.NODE_ACTION_NOT_SUPPORTED));
+ }
+
+ return node;
+
+ }
+
+ @Override
+ protected List<QueryNode> setChildrenOrder(List<QueryNode> children)
+ throws QueryNodeException {
+
+ return children;
+
+ }
+
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/SpansValidatorQueryNodeProcessor.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParser.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParser.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParser.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParser.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,233 @@
+package org.apache.lucene.queryParser.spans;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import javax.management.Query;
+
+import junit.framework.TestCase;
+
+import org.apache.lucene.queryParser.core.QueryNodeException;
+import org.apache.lucene.queryParser.core.nodes.OrQueryNode;
+import org.apache.lucene.queryParser.core.nodes.QueryNode;
+import org.apache.lucene.queryParser.core.parser.SyntaxParser;
+import org.apache.lucene.queryParser.core.processors.QueryNodeProcessorPipeline;
+import org.apache.lucene.queryParser.original.parser.OriginalSyntaxParser;
+import org.apache.lucene.search.spans.SpanOrQuery;
+import org.apache.lucene.search.spans.SpanQuery;
+import org.apache.lucene.search.spans.SpanTermQuery;
+
+/**
+ * This test case demonstrates how the new query parser can be used.<br/>
+ * <br/>
+ *
+ * It tests queries likes "term", "field:term" "term1 term2" "term1 OR term2",
+ * which are all already supported by the current syntax parser (
+ * {@link OriginalSyntaxParser}).<br/>
+ * <br/>
+ *
+ * The goals is to create a new query parser that supports only the pair
+ * "field:term" or a list of pairs separated or not by an OR operator, and from
+ * this query generate {@link SpanQuery} objects instead of the regular
+ * {@link Query} objects. Basically, every pair will be converted to a
+ * {@link SpanTermQuery} object and if there are more than one pair they will be
+ * grouped by an {@link OrQueryNode}.<br/>
+ * <br/>
+ *
+ * Another functionality that will be added is the ability to convert every
+ * field defined in the query to an unique specific field.<br/>
+ * <br/>
+ *
+ * The query generation is divided in three different steps: parsing (syntax),
+ * processing (semantic) and building.<br/>
+ * <br/>
+ *
+ * The parsing phase, as already mentioned will be performed by the current
+ * query parser: {@link OriginalSyntaxParser}.<br/>
+ * <br/>
+ *
+ * The processing phase will be performed by a processor pipeline which is
+ * compound by 2 processors: {@link SpansValidatorQueryNodeProcessor} and
+ * {@link UniqueFieldQueryNodeProcessor}.
+ *
+ * <pre>
+ *
+ * {@link SpansValidatorQueryNodeProcessor}: as it's going to use the current
+ * query parser to parse the syntax, it will support more features than we want,
+ * this processor basically validates the query node tree generated by the parser
+ * and just let got through the elements we want, all the other elements as
+ * wildcards, range queries, etc...if found, an exception is thrown.
+ *
+ * {@link UniqueFieldQueryNodeProcessor}: this processor will take care of reading
+ * what is the "unique field" from the configuration and convert every field defined
+ * in every pair to this "unique field". For that, a {@link SpansQueryConfigHandler} is
+ * used, which has the {@link UniqueFieldAttribute} defined in it.
+ * </pre>
+ *
+ * The building phase is performed by the {@link SpansQueryTreeBuilder}, which
+ * basically contains a map that defines which builder will be used to generate
+ * {@link SpanQuery} objects from {@link QueryNode} objects.<br/>
+ * <br/>
+ *
+ * @see SpansQueryConfigHandler
+ * @see SpansQueryTreeBuilder
+ * @see SpansValidatorQueryNodeProcessor
+ * @see SpanOrQueryNodeBuilder
+ * @see SpanTermQueryNodeBuilder
+ * @see OriginalSyntaxParser
+ * @see UniqueFieldQueryNodeProcessor
+ * @see UniqueFieldAttribute
+ */
+public class TestSpanQueryParser extends TestCase {
+
+ private QueryNodeProcessorPipeline spanProcessorPipeline;
+
+ private SpansQueryConfigHandler spanQueryConfigHandler;
+
+ private SpansQueryTreeBuilder spansQueryTreeBuilder;
+
+ private SyntaxParser queryParser = new OriginalSyntaxParser();
+
+ public TestSpanQueryParser() {
+ // empty constructor
+ }
+
+ @Override
+ protected void setUp() throws Exception {
+ super.setUp();
+
+ this.spanProcessorPipeline = new QueryNodeProcessorPipeline();
+ this.spanQueryConfigHandler = new SpansQueryConfigHandler();
+ this.spansQueryTreeBuilder = new SpansQueryTreeBuilder();
+
+ // set up the processor pipeline
+ this.spanProcessorPipeline
+ .setQueryConfigHandler(this.spanQueryConfigHandler);
+
+ this.spanProcessorPipeline
+ .addProcessor(new SpansValidatorQueryNodeProcessor());
+ this.spanProcessorPipeline
+ .addProcessor(new UniqueFieldQueryNodeProcessor());
+
+ }
+
+ public SpanQuery getSpanQuery(CharSequence query) throws QueryNodeException {
+ return getSpanQuery("", query);
+ }
+
+ public SpanQuery getSpanQuery(CharSequence uniqueField, CharSequence query)
+ throws QueryNodeException {
+ UniqueFieldAttribute uniqueFieldAtt = (UniqueFieldAttribute) this.spanQueryConfigHandler
+ .getAttribute(UniqueFieldAttribute.class);
+ uniqueFieldAtt.setUniqueField(uniqueField);
+
+ QueryNode queryTree = this.queryParser.parse(query, "defaultField");
+ queryTree = this.spanProcessorPipeline.process(queryTree);
+
+ return this.spansQueryTreeBuilder.build(queryTree);
+
+ }
+
+ public void testTermSpans() throws Exception {
+ assertEquals(getSpanQuery("field:term").toString(), "term");
+ assertEquals(getSpanQuery("term").toString(), "term");
+
+ assertTrue(getSpanQuery("field:term") instanceof SpanTermQuery);
+ assertTrue(getSpanQuery("term") instanceof SpanTermQuery);
+
+ }
+
+ public void testUniqueField() throws Exception {
+ assertEquals(getSpanQuery("field", "term").toString(), "field:term");
+ assertEquals(getSpanQuery("field", "field:term").toString(), "field:term");
+ assertEquals(getSpanQuery("field", "anotherField:term").toString(),
+ "field:term");
+
+ }
+
+ public void testOrSpans() throws Exception {
+ assertEquals(getSpanQuery("term1 term2").toString(),
+ "spanOr([term1, term2])");
+ assertEquals(getSpanQuery("term1 OR term2").toString(),
+ "spanOr([term1, term2])");
+
+ assertTrue(getSpanQuery("term1 term2") instanceof SpanOrQuery);
+ assertTrue(getSpanQuery("term1 term2") instanceof SpanOrQuery);
+
+ }
+
+ public void testQueryValidator() throws QueryNodeException {
+
+ try {
+ getSpanQuery("term*");
+ fail("QueryNodeException was expected, wildcard queries should not be supported");
+
+ } catch (QueryNodeException ex) {
+ // expected exception
+ }
+
+ try {
+ getSpanQuery("[a TO z]");
+ fail("QueryNodeException was expected, range queries should not be supported");
+
+ } catch (QueryNodeException ex) {
+ // expected exception
+ }
+
+ try {
+ getSpanQuery("a~0.5");
+ fail("QueryNodeException was expected, boost queries should not be supported");
+
+ } catch (QueryNodeException ex) {
+ // expected exception
+ }
+
+ try {
+ getSpanQuery("a^0.5");
+ fail("QueryNodeException was expected, fuzzy queries should not be supported");
+
+ } catch (QueryNodeException ex) {
+ // expected exception
+ }
+
+ try {
+ getSpanQuery("\"a b\"");
+ fail("QueryNodeException was expected, quoted queries should not be supported");
+
+ } catch (QueryNodeException ex) {
+ // expected exception
+ }
+
+ try {
+ getSpanQuery("(a b)");
+ fail("QueryNodeException was expected, parenthesized queries should not be supported");
+
+ } catch (QueryNodeException ex) {
+ // expected exception
+ }
+
+ try {
+ getSpanQuery("a AND b");
+ fail("QueryNodeException was expected, and queries should not be supported");
+
+ } catch (QueryNodeException ex) {
+ // expected exception
+ }
+
+ }
+
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParser.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParserSimpleSample.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParserSimpleSample.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParserSimpleSample.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParserSimpleSample.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,155 @@
+package org.apache.lucene.queryParser.spans;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import javax.management.Query;
+
+import junit.framework.TestCase;
+
+import org.apache.lucene.queryParser.core.config.QueryConfigHandler;
+import org.apache.lucene.queryParser.core.nodes.OrQueryNode;
+import org.apache.lucene.queryParser.core.nodes.QueryNode;
+import org.apache.lucene.queryParser.core.parser.SyntaxParser;
+import org.apache.lucene.queryParser.core.processors.QueryNodeProcessorPipeline;
+import org.apache.lucene.queryParser.original.parser.OriginalSyntaxParser;
+import org.apache.lucene.search.spans.SpanQuery;
+import org.apache.lucene.search.spans.SpanTermQuery;
+
+/**
+ * This test case demonstrates how the new query parser can be used.<br/>
+ * <br/>
+ *
+ * It tests queries likes "term", "field:term" "term1 term2" "term1 OR term2",
+ * which are all already supported by the current syntax parser (
+ * {@link OriginalSyntaxParser}).<br/>
+ * <br/>
+ *
+ * The goals is to create a new query parser that supports only the pair
+ * "field:term" or a list of pairs separated or not by an OR operator, and from
+ * this query generate {@link SpanQuery} objects instead of the regular
+ * {@link Query} objects. Basically, every pair will be converted to a
+ * {@link SpanTermQuery} object and if there are more than one pair they will be
+ * grouped by an {@link OrQueryNode}.<br/>
+ * <br/>
+ *
+ * Another functionality that will be added is the ability to convert every
+ * field defined in the query to an unique specific field.<br/>
+ * <br/>
+ *
+ * The query generation is divided in three different steps: parsing (syntax),
+ * processing (semantic) and building.<br/>
+ * <br/>
+ *
+ * The parsing phase, as already mentioned will be performed by the current
+ * query parser: {@link OriginalSyntaxParser}.<br/>
+ * <br/>
+ *
+ * The processing phase will be performed by a processor pipeline which is
+ * compound by 2 processors: {@link SpansValidatorQueryNodeProcessor} and
+ * {@link UniqueFieldQueryNodeProcessor}.
+ *
+ * <pre>
+ *
+ * {@link SpansValidatorQueryNodeProcessor}: as it's going to use the current
+ * query parser to parse the syntax, it will support more features than we want,
+ * this processor basically validates the query node tree generated by the parser
+ * and just let got through the elements we want, all the other elements as
+ * wildcards, range queries, etc...if found, an exception is thrown.
+ *
+ * {@link UniqueFieldQueryNodeProcessor}: this processor will take care of reading
+ * what is the "unique field" from the configuration and convert every field defined
+ * in every pair to this "unique field". For that, a {@link SpansQueryConfigHandler} is
+ * used, which has the {@link UniqueFieldAttribute} defined in it.
+ * </pre>
+ *
+ * The building phase is performed by the {@link SpansQueryTreeBuilder}, which
+ * basically contains a map that defines which builder will be used to generate
+ * {@link SpanQuery} objects from {@link QueryNode} objects.<br/>
+ * <br/>
+ *
+ * @see TestSpanQueryParser for a more advanced example
+ *
+ * @see SpansQueryConfigHandler
+ * @see SpansQueryTreeBuilder
+ * @see SpansValidatorQueryNodeProcessor
+ * @see SpanOrQueryNodeBuilder
+ * @see SpanTermQueryNodeBuilder
+ * @see OriginalSyntaxParser
+ * @see UniqueFieldQueryNodeProcessor
+ * @see UniqueFieldAttribute
+ *
+ */
+public class TestSpanQueryParserSimpleSample extends TestCase {
+
+ public TestSpanQueryParserSimpleSample() {
+ // empty constructor
+ }
+
+ public TestSpanQueryParserSimpleSample(String testName) {
+ super(testName);
+ }
+
+ public static junit.framework.Test suite() {
+ junit.framework.TestSuite suite = new junit.framework.TestSuite(
+ TestSpanQueryParserSimpleSample.class);
+ return suite;
+ }
+
+ public void testBasicDemo() throws Exception {
+ SyntaxParser queryParser = new OriginalSyntaxParser();
+
+ // convert the CharSequence into a QueryNode tree
+ QueryNode queryTree = queryParser.parse("body:text", null);
+
+ // create a config handler with a attribute used in
+ // UniqueFieldQueryNodeProcessor
+ QueryConfigHandler spanQueryConfigHandler = new SpansQueryConfigHandler();
+ UniqueFieldAttribute uniqueFieldAtt = (UniqueFieldAttribute) spanQueryConfigHandler
+ .getAttribute(UniqueFieldAttribute.class);
+ uniqueFieldAtt.setUniqueField("index");
+
+ // set up the processor pipeline with the ConfigHandler
+ // and create the pipeline for this simple demo
+ QueryNodeProcessorPipeline spanProcessorPipeline = new QueryNodeProcessorPipeline(
+ spanQueryConfigHandler);
+ // @see SpansValidatorQueryNodeProcessor
+ spanProcessorPipeline.addProcessor(new SpansValidatorQueryNodeProcessor());
+ // @see UniqueFieldQueryNodeProcessor
+ spanProcessorPipeline.addProcessor(new UniqueFieldQueryNodeProcessor());
+
+ // print to show out the QueryNode tree before being processed
+ System.out.println(queryTree);
+
+ // Process the QueryTree using our new Processors
+ queryTree = spanProcessorPipeline.process(queryTree);
+
+ // print to show out the QueryNode tree after being processed
+ System.out.println(queryTree);
+
+ // create a instance off the Builder
+ SpansQueryTreeBuilder spansQueryTreeBuilder = new SpansQueryTreeBuilder();
+
+ // convert QueryNode tree to span query Objects
+ SpanQuery spanquery = spansQueryTreeBuilder.build(queryTree);
+
+ assertTrue(spanquery instanceof SpanTermQuery);
+ assertEquals(spanquery.toString(), "index:text");
+
+ }
+
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParserSimpleSample.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttribute.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttribute.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttribute.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttribute.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,35 @@
+package org.apache.lucene.queryParser.spans;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import org.apache.lucene.queryParser.core.nodes.FieldableNode;
+import org.apache.lucene.util.Attribute;
+
+/**
+ * This attribute is used by the {@link UniqueFieldQueryNodeProcessor}
+ * processor. It holds a value that defines which is the unique field name that
+ * should be set in every {@link FieldableNode}.<br/>
+ * <br/>
+ *
+ * @see UniqueFieldQueryNodeProcessor
+ */
+public interface UniqueFieldAttribute extends Attribute {
+ public void setUniqueField(CharSequence uniqueField);
+
+ public CharSequence getUniqueField();
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttribute.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttributeImpl.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttributeImpl.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttributeImpl.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttributeImpl.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,93 @@
+package org.apache.lucene.queryParser.spans;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import org.apache.lucene.queryParser.core.nodes.FieldableNode;
+import org.apache.lucene.util.AttributeImpl;
+
+/**
+ * This attribute is used by the {@link UniqueFieldQueryNodeProcessor}
+ * processor. It holds a value that defines which is the unique field name that
+ * should be set in every {@link FieldableNode}.<br/>
+ * <br/>
+ *
+ * @see UniqueFieldQueryNodeProcessor
+ */
+public class UniqueFieldAttributeImpl extends AttributeImpl implements
+ UniqueFieldAttribute {
+
+ private static final long serialVersionUID = 8553318595851064232L;
+
+ private CharSequence uniqueField;
+
+ public UniqueFieldAttributeImpl() {
+ clear();
+ }
+
+ @Override
+ public void clear() {
+ this.uniqueField = "";
+ }
+
+ public void setUniqueField(CharSequence uniqueField) {
+ this.uniqueField = uniqueField;
+ }
+
+ public CharSequence getUniqueField() {
+ return this.uniqueField;
+ }
+
+ @Override
+ public void copyTo(AttributeImpl target) {
+
+ if (!(target instanceof UniqueFieldAttributeImpl)) {
+ throw new IllegalArgumentException(
+ "cannot copy the values from attribute UniqueFieldAttribute to an instance of "
+ + target.getClass().getName());
+ }
+
+ UniqueFieldAttributeImpl uniqueFieldAttr = (UniqueFieldAttributeImpl) target;
+ uniqueFieldAttr.uniqueField = uniqueField.toString();
+
+ }
+
+ @Override
+ public boolean equals(Object other) {
+
+ if (other instanceof UniqueFieldAttributeImpl) {
+
+ return ((UniqueFieldAttributeImpl) other).uniqueField
+ .equals(this.uniqueField);
+
+ }
+
+ return false;
+
+ }
+
+ @Override
+ public int hashCode() {
+ return this.uniqueField.hashCode();
+ }
+
+ @Override
+ public String toString() {
+ return "<uniqueField uniqueField='" + this.uniqueField + "'/>";
+ }
+
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttributeImpl.java
------------------------------------------------------------------------------
svn:eol-style = native
Added: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldQueryNodeProcessor.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldQueryNodeProcessor.java?rev=800191&view=auto
==============================================================================
--- lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldQueryNodeProcessor.java (added)
+++ lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldQueryNodeProcessor.java Mon Aug 3 03:38:44 2009
@@ -0,0 +1,84 @@
+package org.apache.lucene.queryParser.spans;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.util.List;
+
+import org.apache.lucene.queryParser.core.QueryNodeException;
+import org.apache.lucene.queryParser.core.config.QueryConfigHandler;
+import org.apache.lucene.queryParser.core.nodes.FieldableNode;
+import org.apache.lucene.queryParser.core.nodes.QueryNode;
+import org.apache.lucene.queryParser.core.processors.QueryNodeProcessorImpl;
+
+/**
+ * This processor changes every field name of each {@link FieldableNode} query
+ * node contained in the query tree to the field name defined in the
+ * {@link UniqueFieldAttribute}. So, the {@link UniqueFieldAttribute} must be
+ * defined in the {@link QueryConfigHandler} object set in this processor,
+ * otherwise it throws an exception.<br/>
+ * <br/>
+ *
+ * @see UniqueFieldAttribute
+ */
+public class UniqueFieldQueryNodeProcessor extends QueryNodeProcessorImpl {
+
+ @Override
+ protected QueryNode postProcessNode(QueryNode node) throws QueryNodeException {
+
+ return node;
+
+ }
+
+ @Override
+ protected QueryNode preProcessNode(QueryNode node) throws QueryNodeException {
+
+ if (node instanceof FieldableNode) {
+ FieldableNode fieldNode = (FieldableNode) node;
+
+ QueryConfigHandler queryConfig = getQueryConfigHandler();
+
+ if (queryConfig == null) {
+ throw new IllegalArgumentException(
+ "A config handler is expected by the processor UniqueFieldQueryNodeProcessor!");
+ }
+
+ if (!queryConfig.hasAttribute(UniqueFieldAttribute.class)) {
+ throw new IllegalArgumentException(
+ "UniqueFieldAttribute should be defined in the config handler!");
+ }
+
+ CharSequence uniqueField = ((UniqueFieldAttribute) queryConfig
+ .getAttribute(UniqueFieldAttribute.class)).getUniqueField();
+
+ fieldNode.setField(uniqueField);
+
+ }
+
+ return node;
+
+ }
+
+ @Override
+ protected List<QueryNode> setChildrenOrder(List<QueryNode> children)
+ throws QueryNodeException {
+
+ return children;
+
+ }
+
+}
Propchange: lucene/java/trunk/contrib/queryparser/src/test/org/apache/lucene/queryParser/spans/UniqueFieldQueryNodeProcessor.java
------------------------------------------------------------------------------
svn:eol-style = native
Modified: lucene/java/trunk/src/java/org/apache/lucene/queryParser/CharStream.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/queryParser/CharStream.java?rev=800191&r1=800190&r2=800191&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/queryParser/CharStream.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/queryParser/CharStream.java Mon Aug 3 03:38:44 2009
@@ -15,6 +15,8 @@
* column number and the String that constitutes a token and are not used
* by the lexer. Hence their implementation won't affect the generated lexer's
* operation.
+ *
+ * @deprecated this class will be removed in Lucene 3.0, when the {@link QueryParser} is removed
*/
public interface CharStream {
Modified: lucene/java/trunk/src/java/org/apache/lucene/queryParser/ComplexPhraseQueryParser.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/queryParser/ComplexPhraseQueryParser.java?rev=800191&r1=800190&r2=800191&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/queryParser/ComplexPhraseQueryParser.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/queryParser/ComplexPhraseQueryParser.java Mon Aug 3 03:38:44 2009
@@ -54,8 +54,8 @@
* currently simply feeds all phrase content through an analyzer to select
* phrase terms - any "special" syntax such as * ~ * etc are not given special
* status
- *
- *
+ *
+ * @deprecated use new the flexible query parser instead
*/
public class ComplexPhraseQueryParser extends QueryParser {
private ArrayList/*<ComplexPhraseQuery>*/complexPhrases = null;