You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2010/10/20 16:51:14 UTC
svn commit: r1025606 [4/8] - in /lucene/dev/branches/branch_3x: ./ lucene/
lucene/backwards/src/ lucene/backwards/src/test/org/apache/lucene/analysis/
lucene/backwards/src/test/org/apache/lucene/document/
lucene/backwards/src/test/org/apache/lucene/ind...
Modified: lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/precedence/PrecedenceQueryParser.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/precedence/PrecedenceQueryParser.java?rev=1025606&r1=1025605&r2=1025606&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/precedence/PrecedenceQueryParser.java (original)
+++ lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/precedence/PrecedenceQueryParser.java Wed Oct 20 14:51:12 2010
@@ -1,1292 +1,57 @@
-/* Generated By:JavaCC: Do not edit this line. PrecedenceQueryParser.java */
package org.apache.lucene.queryParser.precedence;
-import java.io.IOException;
-import java.io.StringReader;
-import java.text.DateFormat;
-import java.util.ArrayList;
-import java.util.Date;
-import java.util.List;
-import java.util.Locale;
+/**
+ * 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.analysis.Analyzer;
-import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.tokenattributes.*;
-import org.apache.lucene.document.DateTools;
-import org.apache.lucene.index.Term;
-import org.apache.lucene.search.BooleanClause;
-import org.apache.lucene.search.BooleanQuery;
-import org.apache.lucene.search.FuzzyQuery;
-import org.apache.lucene.search.MultiPhraseQuery;
-import org.apache.lucene.search.PhraseQuery;
-import org.apache.lucene.search.PrefixQuery;
-import org.apache.lucene.search.Query;
-import org.apache.lucene.search.TermRangeQuery;
-import org.apache.lucene.search.TermQuery;
-import org.apache.lucene.search.WildcardQuery;
-import org.apache.lucene.util.AttributeSource;
+import org.apache.lucene.queryParser.precedence.processors.PrecedenceQueryNodeProcessorPipeline;
+import org.apache.lucene.queryParser.standard.StandardQueryParser;
+import org.apache.lucene.queryParser.standard.processors.StandardQueryNodeProcessorPipeline;
/**
- * Experimental query parser variant designed to handle operator precedence
- * in a more sensible fashion than QueryParser. There are still some
- * open issues with this parser. The following tests are currently failing
- * in TestPrecedenceQueryParser and are disabled to make this test pass:
- * <ul>
- * <li> testSimple
- * <li> testWildcard
- * <li> testPrecedence
- * </ul>
- *
- * This class is generated by JavaCC. The only method that clients should need
- * to call is {@link #parse(String)}.
- *
- * The syntax for query strings is as follows:
- * A Query is a series of clauses.
- * A clause may be prefixed by:
- * <ul>
- * <li> a plus (<code>+</code>) or a minus (<code>-</code>) sign, indicating
- * that the clause is required or prohibited respectively; or
- * <li> a term followed by a colon, indicating the field to be searched.
- * This enables one to construct queries which search multiple fields.
- * </ul>
- *
- * A clause may be either:
- * <ul>
- * <li> a term, indicating all the documents that contain this term; or
- * <li> a nested query, enclosed in parentheses. Note that this may be used
- * with a <code>+</code>/<code>-</code> prefix to require any of a set of
- * terms.
- * </ul>
- *
- * Thus, in BNF, the query grammar is:
- * <pre>
- * Query ::= ( Clause )*
- * Clause ::= ["+", "-"] [<TERM> ":"] ( <TERM> | "(" Query ")" )
- * </pre>
- *
* <p>
- * Examples of appropriately formatted queries can be found in the <a
- * href="../../../../../../../queryparsersyntax.html">query syntax
- * documentation</a>.
+ * This query parser works exactly as the standard query parser ( {@link StandardQueryParser} ),
+ * except that it respect the boolean precedence, so <a AND b OR c AND d> is parsed to <(+a +b) (+c +d)>
+ * instead of <+a +b +c +d>.
* </p>
+ * <p>
+ * EXPERT: This class extends {@link StandardQueryParser}, but uses {@link PrecedenceQueryNodeProcessorPipeline}
+ * instead of {@link StandardQueryNodeProcessorPipeline} to process the query tree.
+ * </p>
+ *
+ * @see StandardQueryParser
*/
-public class PrecedenceQueryParser implements PrecedenceQueryParserConstants {
-
- private static final int CONJ_NONE = 0;
- private static final int CONJ_AND = 1;
- private static final int CONJ_OR = 2;
-
- private static final int MOD_NONE = 0;
- private static final int MOD_NOT = 10;
- private static final int MOD_REQ = 11;
-
- // make it possible to call setDefaultOperator() without accessing
- // the nested class:
- public static final Operator AND_OPERATOR = Operator.AND;
- public static final Operator OR_OPERATOR = Operator.OR;
-
- /** The actual operator that parser uses to combine query terms */
- private Operator operator = OR_OPERATOR;
-
- boolean lowercaseExpandedTerms = true;
-
- Analyzer analyzer;
- String field;
- int phraseSlop = 0;
- float fuzzyMinSim = FuzzyQuery.defaultMinSimilarity;
- int fuzzyPrefixLength = FuzzyQuery.defaultPrefixLength;
- Locale locale = Locale.getDefault();
-
- static enum Operator { OR, AND }
-
- /** Constructs a query parser.
- * @param f the default field for query terms.
- * @param a used to find terms in the query text.
- */
- public PrecedenceQueryParser(String f, Analyzer a) {
- this(new FastCharStream(new StringReader("")));
- analyzer = a;
- field = f;
- }
-
- /** Parses a query string, returning a {@link org.apache.lucene.search.Query}.
- * @param expression the query string to be parsed.
- * @throws ParseException if the parsing fails
- */
- public Query parse(String expression) throws ParseException {
- // optimize empty query to be empty BooleanQuery
- if (expression == null || expression.trim().length() == 0) {
- return new BooleanQuery();
- }
-
- ReInit(new FastCharStream(new StringReader(expression)));
- try {
- Query query = Query(field);
- return (query != null) ? query : new BooleanQuery();
- }
- catch (TokenMgrError tme) {
- throw new ParseException(tme.getMessage());
- }
- catch (BooleanQuery.TooManyClauses tmc) {
- throw new ParseException("Too many boolean clauses");
- }
- }
-
- /**
- * @return Returns the analyzer.
- */
- public Analyzer getAnalyzer() {
- return analyzer;
- }
-
- /**
- * @return Returns the field.
- */
- public String getField() {
- return field;
- }
-
- /**
- * Get the minimal similarity for fuzzy queries.
- */
- public float getFuzzyMinSim() {
- return fuzzyMinSim;
- }
-
- /**
- * Set the minimum similarity for fuzzy queries.
- * Default is 0.5f.
- */
- public void setFuzzyMinSim(float fuzzyMinSim) {
- this.fuzzyMinSim = fuzzyMinSim;
- }
-
- /**
- * Get the prefix length for fuzzy queries.
- * @return Returns the fuzzyPrefixLength.
- */
- public int getFuzzyPrefixLength() {
- return fuzzyPrefixLength;
- }
-
- /**
- * Set the prefix length for fuzzy queries. Default is 0.
- * @param fuzzyPrefixLength The fuzzyPrefixLength to set.
- */
- public void setFuzzyPrefixLength(int fuzzyPrefixLength) {
- this.fuzzyPrefixLength = fuzzyPrefixLength;
- }
-
- /**
- * Sets the default slop for phrases. If zero, then exact phrase matches
- * are required. Default value is zero.
- */
- public void setPhraseSlop(int phraseSlop) {
- this.phraseSlop = phraseSlop;
- }
-
- /**
- * Gets the default slop for phrases.
- */
- public int getPhraseSlop() {
- return phraseSlop;
- }
-
- /**
- * Sets the boolean operator of the QueryParser.
- * In default mode (<code>OR_OPERATOR</code>) terms without any modifiers
- * are considered optional: for example <code>capital of Hungary</code> is equal to
- * <code>capital OR of OR Hungary</code>.<br/>
- * In <code>AND_OPERATOR</code> mode terms are considered to be in conjunction: the
- * above mentioned query is parsed as <code>capital AND of AND Hungary</code>
- */
- public void setDefaultOperator(Operator op) {
- this.operator = op;
- }
-
- /**
- * Gets implicit operator setting, which will be either AND_OPERATOR
- * or OR_OPERATOR.
- */
- public Operator getDefaultOperator() {
- return operator;
- }
-
- /**
- * Whether terms of wildcard, prefix, fuzzy and range queries are to be automatically
- * lower-cased or not. Default is <code>true</code>.
- */
- public void setLowercaseExpandedTerms(boolean lowercaseExpandedTerms) {
- this.lowercaseExpandedTerms = lowercaseExpandedTerms;
- }
-
- /**
- * @see #setLowercaseExpandedTerms(boolean)
- */
- public boolean getLowercaseExpandedTerms() {
- return lowercaseExpandedTerms;
- }
-
- /**
- * Set locale used by date range parsing.
- */
- public void setLocale(Locale locale) {
- this.locale = locale;
- }
-
- /**
- * Returns current locale, allowing access by subclasses.
- */
- public Locale getLocale() {
- return locale;
- }
-
- protected void addClause(List<BooleanClause> clauses, int conj, int modifier, Query q) {
- boolean required, prohibited;
-
- // If this term is introduced by AND, make the preceding term required,
- // unless it's already prohibited
- if (clauses.size() > 0 && conj == CONJ_AND) {
- BooleanClause c = clauses.get(clauses.size()-1);
- if (!c.isProhibited())
- c.setOccur(BooleanClause.Occur.MUST);
- }
-
- if (clauses.size() > 0 && operator == AND_OPERATOR && conj == CONJ_OR) {
- // If this term is introduced by OR, make the preceding term optional,
- // unless it's prohibited (that means we leave -a OR b but +a OR b-->a OR b)
- // notice if the input is a OR b, first term is parsed as required; without
- // this modification a OR b would parsed as +a OR b
- BooleanClause c = clauses.get(clauses.size()-1);
- if (!c.isProhibited())
- c.setOccur(BooleanClause.Occur.SHOULD);
- }
-
- // We might have been passed a null query; the term might have been
- // filtered away by the analyzer.
- if (q == null)
- return;
-
- if (operator == OR_OPERATOR) {
- // We set REQUIRED if we're introduced by AND or +; PROHIBITED if
- // introduced by NOT or -; make sure not to set both.
- prohibited = (modifier == MOD_NOT);
- required = (modifier == MOD_REQ);
- if (conj == CONJ_AND && !prohibited) {
- required = true;
- }
- } else {
- // We set PROHIBITED if we're introduced by NOT or -; We set REQUIRED
- // if not PROHIBITED and not introduced by OR
- prohibited = (modifier == MOD_NOT);
- required = (!prohibited && conj != CONJ_OR);
- }
- if (required && !prohibited)
- clauses.add(new BooleanClause(q, BooleanClause.Occur.MUST));
- else if (!required && !prohibited)
- clauses.add(new BooleanClause(q, BooleanClause.Occur.SHOULD));
- else if (!required && prohibited)
- clauses.add(new BooleanClause(q, BooleanClause.Occur.MUST_NOT));
- else
- throw new RuntimeException("Clause cannot be both required and prohibited");
- }
-
- /**
- * @exception ParseException throw in overridden method to disallow
- */
- protected Query getFieldQuery(String field, String queryText, boolean quoted) throws ParseException {
- // Use the analyzer to get all the tokens, and then build a TermQuery,
- // PhraseQuery, or nothing based on the term count
-
- TokenStream source = analyzer.tokenStream(field, new StringReader(queryText));
- List<AttributeSource.State> list = new ArrayList<AttributeSource.State>();
- int positionCount = 0;
- boolean severalTokensAtSamePosition = false;
- CharTermAttribute termAtt = source.addAttribute(CharTermAttribute.class);
- PositionIncrementAttribute posincrAtt = source.addAttribute(PositionIncrementAttribute.class);
-
- try {
- while (source.incrementToken()) {
- list.add(source.captureState());
- if (posincrAtt.getPositionIncrement() == 1)
- positionCount++;
- else
- severalTokensAtSamePosition = true;
- }
- source.end();
- source.close();
- } catch (IOException e) {
- // ignore, should never happen for StringReaders
- }
-
- if (list.size() == 0)
- return null;
- else if (list.size() == 1) {
- source.restoreState(list.get(0));
- return new TermQuery(new Term(field, termAtt.toString()));
- } else {
- if (severalTokensAtSamePosition || !quoted) {
- if (positionCount == 1 || !quoted) {
- // no phrase query:
- BooleanQuery q = new BooleanQuery(positionCount == 1);
-
- BooleanClause.Occur occur = positionCount > 1 && operator == AND_OPERATOR ?
- BooleanClause.Occur.MUST : BooleanClause.Occur.SHOULD;
-
- for (int i = 0; i < list.size(); i++) {
- source.restoreState(list.get(i));
- TermQuery currentQuery = new TermQuery(
- new Term(field, termAtt.toString()));
- q.add(currentQuery, occur);
- }
- return q;
- }
- else {
- // phrase query:
- MultiPhraseQuery mpq = new MultiPhraseQuery();
- List<Term> multiTerms = new ArrayList<Term>();
- for (int i = 0; i < list.size(); i++) {
- source.restoreState(list.get(i));
- if (posincrAtt.getPositionIncrement() == 1 && multiTerms.size() > 0) {
- mpq.add(multiTerms.toArray(new Term[0]));
- multiTerms.clear();
- }
- multiTerms.add(new Term(field, termAtt.toString()));
- }
- mpq.add(multiTerms.toArray(new Term[0]));
- return mpq;
- }
- }
- else {
- PhraseQuery q = new PhraseQuery();
- q.setSlop(phraseSlop);
- for (int i = 0; i < list.size(); i++) {
- source.restoreState(list.get(i));
- q.add(new Term(field, termAtt.toString()));
- }
- return q;
- }
- }
- }
-
- /**
- * Base implementation delegates to {@link #getFieldQuery(String,String,boolean)}.
- * This method may be overridden, for example, to return
- * a SpanNearQuery instead of a PhraseQuery.
- *
- * @exception ParseException throw in overridden method to disallow
- */
- protected Query getFieldQuery(String field, String queryText, int slop)
- throws ParseException {
- Query query = getFieldQuery(field, queryText, true);
-
- if (query instanceof PhraseQuery) {
- ((PhraseQuery) query).setSlop(slop);
- }
- if (query instanceof MultiPhraseQuery) {
- ((MultiPhraseQuery) query).setSlop(slop);
- }
-
- return query;
- }
-
- /**
- * @exception ParseException throw in overridden method to disallow
- */
- protected Query getRangeQuery(String field,
- String part1,
- String part2,
- boolean inclusive) throws ParseException
- {
- if (lowercaseExpandedTerms) {
- part1 = part1.toLowerCase();
- part2 = part2.toLowerCase();
- }
- try {
- DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT, locale);
- df.setLenient(true);
- Date d1 = df.parse(part1);
- Date d2 = df.parse(part2);
- part1 = DateTools.dateToString(d1, DateTools.Resolution.DAY);
- part2 = DateTools.dateToString(d2, DateTools.Resolution.DAY);
- }
- catch (Exception e) { }
-
- return new TermRangeQuery(field, part1, part2, inclusive, inclusive);
- }
-
- /**
- * Factory method for generating query, given a set of clauses.
- * By default creates a boolean query composed of clauses passed in.
- *
- * Can be overridden by extending classes, to modify query being
- * returned.
- *
- * @param clauses List that contains {@link BooleanClause} instances
- * to join.
- *
- * @return Resulting {@link Query} object.
- * @exception ParseException throw in overridden method to disallow
- */
- protected Query getBooleanQuery(List<BooleanClause> clauses) throws ParseException
- {
- return getBooleanQuery(clauses, false);
- }
-
- /**
- * Factory method for generating query, given a set of clauses.
- * By default creates a boolean query composed of clauses passed in.
- *
- * Can be overridden by extending classes, to modify query being
- * returned.
- *
- * @param clauses List that contains {@link BooleanClause} instances
- * to join.
- * @param disableCoord true if coord scoring should be disabled.
- *
- * @return Resulting {@link Query} object.
- * @exception ParseException throw in overridden method to disallow
- */
- protected Query getBooleanQuery(List<BooleanClause> clauses, boolean disableCoord)
- throws ParseException {
- if (clauses == null || clauses.size() == 0)
- return null;
-
- BooleanQuery query = new BooleanQuery(disableCoord);
- for (int i = 0; i < clauses.size(); i++) {
- query.add(clauses.get(i));
- }
- return query;
- }
-
- /**
- * Factory method for generating a query. Called when parser
- * parses an input term token that contains one or more wildcard
- * characters (? and *), but is not a prefix term token (one
- * that has just a single * character at the end)
- *<p>
- * Depending on settings, prefix term may be lower-cased
- * automatically. It will not go through the default Analyzer,
- * however, since normal Analyzers are unlikely to work properly
- * with wildcard templates.
- *<p>
- * Can be overridden by extending classes, to provide custom handling for
- * wildcard queries, which may be necessary due to missing analyzer calls.
- *
- * @param field Name of the field query will use.
- * @param termStr Term token that contains one or more wild card
- * characters (? or *), but is not simple prefix term
- *
- * @return Resulting {@link Query} built for the term
- * @exception ParseException throw in overridden method to disallow
- */
- protected Query getWildcardQuery(String field, String termStr) throws ParseException
- {
- if (lowercaseExpandedTerms) {
- termStr = termStr.toLowerCase();
- }
- Term t = new Term(field, termStr);
- return new WildcardQuery(t);
- }
-
- /**
- * Factory method for generating a query (similar to
- * {@link #getWildcardQuery}). Called when parser parses an input term
- * token that uses prefix notation; that is, contains a single '*' wildcard
- * character as its last character. Since this is a special case
- * of generic wildcard term, and such a query can be optimized easily,
- * this usually results in a different query object.
- *<p>
- * Depending on settings, a prefix term may be lower-cased
- * automatically. It will not go through the default Analyzer,
- * however, since normal Analyzers are unlikely to work properly
- * with wildcard templates.
- *<p>
- * Can be overridden by extending classes, to provide custom handling for
- * wild card queries, which may be necessary due to missing analyzer calls.
- *
- * @param field Name of the field query will use.
- * @param termStr Term token to use for building term for the query
- * (<b>without</b> trailing '*' character!)
- *
- * @return Resulting {@link Query} built for the term
- * @exception ParseException throw in overridden method to disallow
- */
- protected Query getPrefixQuery(String field, String termStr) throws ParseException
- {
- if (lowercaseExpandedTerms) {
- termStr = termStr.toLowerCase();
- }
- Term t = new Term(field, termStr);
- return new PrefixQuery(t);
- }
-
- /**
- * Factory method for generating a query (similar to
- * {@link #getWildcardQuery}). Called when parser parses
- * an input term token that has the fuzzy suffix (~) appended.
- *
- * @param field Name of the field query will use.
- * @param termStr Term token to use for building term for the query
- *
- * @return Resulting {@link Query} built for the term
- * @exception ParseException throw in overridden method to disallow
- */
- protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws ParseException
- {
- if (lowercaseExpandedTerms) {
- termStr = termStr.toLowerCase();
- }
- Term t = new Term(field, termStr);
- return new FuzzyQuery(t, minSimilarity, fuzzyPrefixLength);
- }
-
+public class PrecedenceQueryParser extends StandardQueryParser {
+
/**
- * Returns a String where the escape char has been
- * removed, or kept only once if there was a double escape.
+ * @see StandardQueryParser#StandardQueryParser()
*/
- private String discardEscapeChar(String input) {
- char[] caSource = input.toCharArray();
- char[] caDest = new char[caSource.length];
- int j = 0;
- for (int i = 0; i < caSource.length; i++) {
- if ((caSource[i] != '\\') || (i > 0 && caSource[i-1] == '\\')) {
- caDest[j++]=caSource[i];
- }
- }
- return new String(caDest, 0, j);
+ public PrecedenceQueryParser() {
+ setQueryNodeProcessor(new PrecedenceQueryNodeProcessorPipeline(getQueryConfigHandler()));
}
-
+
/**
- * Returns a String where those characters that QueryParser
- * expects to be escaped are escaped by a preceding <code>\</code>.
+ * @see StandardQueryParser#StandardQueryParser(Analyzer)
*/
- public static String escape(String s) {
- StringBuffer sb = new StringBuffer();
- for (int i = 0; i < s.length(); i++) {
- char c = s.charAt(i);
- // NOTE: keep this in sync with _ESCAPED_CHAR below!
- if (c == '\\' || c == '+' || c == '-' || c == '!' || c == '(' || c == ')' || c == ':'
- || c == '^' || c == '[' || c == ']' || c == '\"' || c == '{' || c == '}' || c == '~'
- || c == '*' || c == '?') {
- sb.append('\\');
- }
- sb.append(c);
- }
- return sb.toString();
- }
-
- /**
- * Command line tool to test QueryParser, using {@link org.apache.lucene.analysis.SimpleAnalyzer}.
- * Usage:<br>
- * <code>java org.apache.lucene.queryParser.QueryParser <input></code>
- */
- public static void main(String[] args) throws Exception {
- if (args.length == 0) {
- System.out.println("Usage: java org.apache.lucene.queryParser.QueryParser <input>");
- System.exit(0);
- }
- PrecedenceQueryParser qp = new PrecedenceQueryParser("field",
- new org.apache.lucene.analysis.SimpleAnalyzer());
- Query q = qp.parse(args[0]);
- System.out.println(q.toString("field"));
- }
-
-// * Query ::= ( Clause )*
-// * Clause ::= ["+", "-"] [<TERM> ":"] ( <TERM> | "(" Query ")" )
- final public int Conjunction() throws ParseException {
- int ret = CONJ_NONE;
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case AND:
- case OR:
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case AND:
- jj_consume_token(AND);
- ret = CONJ_AND;
- break;
- case OR:
- jj_consume_token(OR);
- ret = CONJ_OR;
- break;
- default:
- jj_la1[0] = jj_gen;
- jj_consume_token(-1);
- throw new ParseException();
- }
- break;
- default:
- jj_la1[1] = jj_gen;
- ;
- }
- {if (true) return ret;}
- throw new Error("Missing return statement in function");
- }
-
- final public int Modifier() throws ParseException {
- int ret = MOD_NONE;
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case NOT:
- case PLUS:
- case MINUS:
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case PLUS:
- jj_consume_token(PLUS);
- ret = MOD_REQ;
- break;
- case MINUS:
- jj_consume_token(MINUS);
- ret = MOD_NOT;
- break;
- case NOT:
- jj_consume_token(NOT);
- ret = MOD_NOT;
- break;
- default:
- jj_la1[2] = jj_gen;
- jj_consume_token(-1);
- throw new ParseException();
- }
- break;
- default:
- jj_la1[3] = jj_gen;
- ;
- }
- {if (true) return ret;}
- throw new Error("Missing return statement in function");
- }
-
- final public Query Query(String field) throws ParseException {
- List<BooleanClause> clauses = new ArrayList<BooleanClause>();
- Query q, firstQuery=null;
- boolean orPresent = false;
- int modifier;
- modifier = Modifier();
- q = andExpression(field);
- addClause(clauses, CONJ_NONE, modifier, q);
- if (modifier == MOD_NONE)
- firstQuery = q;
- label_1:
- while (true) {
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case OR:
- case NOT:
- case PLUS:
- case MINUS:
- case LPAREN:
- case QUOTED:
- case TERM:
- case PREFIXTERM:
- case WILDTERM:
- case RANGEIN_START:
- case RANGEEX_START:
- case NUMBER:
- ;
- break;
- default:
- jj_la1[4] = jj_gen;
- break label_1;
- }
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case OR:
- jj_consume_token(OR);
- orPresent=true;
- break;
- default:
- jj_la1[5] = jj_gen;
- ;
- }
- modifier = Modifier();
- q = andExpression(field);
- addClause(clauses, orPresent ? CONJ_OR : CONJ_NONE, modifier, q);
- }
- if (clauses.size() == 1 && firstQuery != null)
- {if (true) return firstQuery;}
- else {
- {if (true) return getBooleanQuery(clauses);}
- }
- throw new Error("Missing return statement in function");
- }
-
- final public Query andExpression(String field) throws ParseException {
- List<BooleanClause> clauses = new ArrayList<BooleanClause>();
- Query q, firstQuery=null;
- int modifier;
- q = Clause(field);
- addClause(clauses, CONJ_NONE, MOD_NONE, q);
- firstQuery = q;
- label_2:
- while (true) {
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case AND:
- ;
- break;
- default:
- jj_la1[6] = jj_gen;
- break label_2;
- }
- jj_consume_token(AND);
- modifier = Modifier();
- q = Clause(field);
- addClause(clauses, CONJ_AND, modifier, q);
- }
- if (clauses.size() == 1 && firstQuery != null)
- {if (true) return firstQuery;}
- else {
- {if (true) return getBooleanQuery(clauses);}
- }
- throw new Error("Missing return statement in function");
- }
-
- final public Query Clause(String field) throws ParseException {
- Query q;
- Token fieldToken=null, boost=null;
- if (jj_2_1(2)) {
- fieldToken = jj_consume_token(TERM);
- jj_consume_token(COLON);
- field=discardEscapeChar(fieldToken.image);
- } else {
- ;
- }
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case QUOTED:
- case TERM:
- case PREFIXTERM:
- case WILDTERM:
- case RANGEIN_START:
- case RANGEEX_START:
- case NUMBER:
- q = Term(field);
- break;
- case LPAREN:
- jj_consume_token(LPAREN);
- q = Query(field);
- jj_consume_token(RPAREN);
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case CARAT:
- jj_consume_token(CARAT);
- boost = jj_consume_token(NUMBER);
- break;
- default:
- jj_la1[7] = jj_gen;
- ;
- }
- break;
- default:
- jj_la1[8] = jj_gen;
- jj_consume_token(-1);
- throw new ParseException();
- }
- if (boost != null) {
- float f = (float)1.0;
- try {
- f = Float.valueOf(boost.image).floatValue();
- q.setBoost(f);
- } catch (Exception ignored) { }
- }
- {if (true) return q;}
- throw new Error("Missing return statement in function");
- }
-
- final public Query Term(String field) throws ParseException {
- Token term, boost=null, fuzzySlop=null, goop1, goop2;
- boolean prefix = false;
- boolean wildcard = false;
- boolean fuzzy = false;
- Query q;
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case TERM:
- case PREFIXTERM:
- case WILDTERM:
- case NUMBER:
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case TERM:
- term = jj_consume_token(TERM);
- break;
- case PREFIXTERM:
- term = jj_consume_token(PREFIXTERM);
- prefix=true;
- break;
- case WILDTERM:
- term = jj_consume_token(WILDTERM);
- wildcard=true;
- break;
- case NUMBER:
- term = jj_consume_token(NUMBER);
- break;
- default:
- jj_la1[9] = jj_gen;
- jj_consume_token(-1);
- throw new ParseException();
- }
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case FUZZY_SLOP:
- fuzzySlop = jj_consume_token(FUZZY_SLOP);
- fuzzy=true;
- break;
- default:
- jj_la1[10] = jj_gen;
- ;
- }
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case CARAT:
- jj_consume_token(CARAT);
- boost = jj_consume_token(NUMBER);
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case FUZZY_SLOP:
- fuzzySlop = jj_consume_token(FUZZY_SLOP);
- fuzzy=true;
- break;
- default:
- jj_la1[11] = jj_gen;
- ;
- }
- break;
- default:
- jj_la1[12] = jj_gen;
- ;
- }
- String termImage=discardEscapeChar(term.image);
- if (wildcard) {
- q = getWildcardQuery(field, termImage);
- } else if (prefix) {
- q = getPrefixQuery(field,
- discardEscapeChar(term.image.substring
- (0, term.image.length()-1)));
- } else if (fuzzy) {
- float fms = fuzzyMinSim;
- try {
- fms = Float.valueOf(fuzzySlop.image.substring(1)).floatValue();
- } catch (Exception ignored) { }
- if(fms < 0.0f || fms > 1.0f){
- {if (true) throw new ParseException("Minimum similarity for a FuzzyQuery has to be between 0.0f and 1.0f !");}
- }
- q = getFuzzyQuery(field, termImage, fms);
- } else {
- q = getFieldQuery(field, termImage, false);
- }
- break;
- case RANGEIN_START:
- jj_consume_token(RANGEIN_START);
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case RANGEIN_GOOP:
- goop1 = jj_consume_token(RANGEIN_GOOP);
- break;
- case RANGEIN_QUOTED:
- goop1 = jj_consume_token(RANGEIN_QUOTED);
- break;
- default:
- jj_la1[13] = jj_gen;
- jj_consume_token(-1);
- throw new ParseException();
- }
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case RANGEIN_TO:
- jj_consume_token(RANGEIN_TO);
- break;
- default:
- jj_la1[14] = jj_gen;
- ;
- }
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case RANGEIN_GOOP:
- goop2 = jj_consume_token(RANGEIN_GOOP);
- break;
- case RANGEIN_QUOTED:
- goop2 = jj_consume_token(RANGEIN_QUOTED);
- break;
- default:
- jj_la1[15] = jj_gen;
- jj_consume_token(-1);
- throw new ParseException();
- }
- jj_consume_token(RANGEIN_END);
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case CARAT:
- jj_consume_token(CARAT);
- boost = jj_consume_token(NUMBER);
- break;
- default:
- jj_la1[16] = jj_gen;
- ;
- }
- if (goop1.kind == RANGEIN_QUOTED) {
- goop1.image = goop1.image.substring(1, goop1.image.length()-1);
- } else {
- goop1.image = discardEscapeChar(goop1.image);
- }
- if (goop2.kind == RANGEIN_QUOTED) {
- goop2.image = goop2.image.substring(1, goop2.image.length()-1);
- } else {
- goop2.image = discardEscapeChar(goop2.image);
- }
- q = getRangeQuery(field, goop1.image, goop2.image, true);
- break;
- case RANGEEX_START:
- jj_consume_token(RANGEEX_START);
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case RANGEEX_GOOP:
- goop1 = jj_consume_token(RANGEEX_GOOP);
- break;
- case RANGEEX_QUOTED:
- goop1 = jj_consume_token(RANGEEX_QUOTED);
- break;
- default:
- jj_la1[17] = jj_gen;
- jj_consume_token(-1);
- throw new ParseException();
- }
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case RANGEEX_TO:
- jj_consume_token(RANGEEX_TO);
- break;
- default:
- jj_la1[18] = jj_gen;
- ;
- }
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case RANGEEX_GOOP:
- goop2 = jj_consume_token(RANGEEX_GOOP);
- break;
- case RANGEEX_QUOTED:
- goop2 = jj_consume_token(RANGEEX_QUOTED);
- break;
- default:
- jj_la1[19] = jj_gen;
- jj_consume_token(-1);
- throw new ParseException();
- }
- jj_consume_token(RANGEEX_END);
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case CARAT:
- jj_consume_token(CARAT);
- boost = jj_consume_token(NUMBER);
- break;
- default:
- jj_la1[20] = jj_gen;
- ;
- }
- if (goop1.kind == RANGEEX_QUOTED) {
- goop1.image = goop1.image.substring(1, goop1.image.length()-1);
- } else {
- goop1.image = discardEscapeChar(goop1.image);
- }
- if (goop2.kind == RANGEEX_QUOTED) {
- goop2.image = goop2.image.substring(1, goop2.image.length()-1);
- } else {
- goop2.image = discardEscapeChar(goop2.image);
- }
-
- q = getRangeQuery(field, goop1.image, goop2.image, false);
- break;
- case QUOTED:
- term = jj_consume_token(QUOTED);
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case FUZZY_SLOP:
- fuzzySlop = jj_consume_token(FUZZY_SLOP);
- break;
- default:
- jj_la1[21] = jj_gen;
- ;
- }
- switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
- case CARAT:
- jj_consume_token(CARAT);
- boost = jj_consume_token(NUMBER);
- break;
- default:
- jj_la1[22] = jj_gen;
- ;
- }
- int s = phraseSlop;
-
- if (fuzzySlop != null) {
- try {
- s = Float.valueOf(fuzzySlop.image.substring(1)).intValue();
- }
- catch (Exception ignored) { }
- }
- q = getFieldQuery(field, term.image.substring(1, term.image.length()-1), s);
- break;
- default:
- jj_la1[23] = jj_gen;
- jj_consume_token(-1);
- throw new ParseException();
- }
- if (boost != null) {
- float f = (float) 1.0;
- try {
- f = Float.valueOf(boost.image).floatValue();
- }
- catch (Exception ignored) {
- /* Should this be handled somehow? (defaults to "no boost", if
- * boost number is invalid)
- */
- }
-
- // avoid boosting null queries, such as those caused by stop words
- if (q != null) {
- q.setBoost(f);
- }
- }
- {if (true) return q;}
- throw new Error("Missing return statement in function");
- }
-
- private boolean jj_2_1(int xla) {
- jj_la = xla; jj_lastpos = jj_scanpos = token;
- try { return !jj_3_1(); }
- catch(LookaheadSuccess ls) { return true; }
- finally { jj_save(0, xla); }
- }
-
- private boolean jj_3_1() {
- if (jj_scan_token(TERM)) return true;
- if (jj_scan_token(COLON)) return true;
- return false;
- }
-
- /** Generated Token Manager. */
- public PrecedenceQueryParserTokenManager token_source;
- /** Current token. */
- public Token token;
- /** Next token. */
- public Token jj_nt;
- private int jj_ntk;
- private Token jj_scanpos, jj_lastpos;
- private int jj_la;
- private int jj_gen;
- final private int[] jj_la1 = new int[24];
- static private int[] jj_la1_0;
- static {
- jj_la1_init_0();
- }
- private static void jj_la1_init_0() {
- jj_la1_0 = new int[] {0x180,0x180,0xe00,0xe00,0xfb1f00,0x100,0x80,0x8000,0xfb1000,0x9a0000,0x40000,0x40000,0x8000,0xc000000,0x1000000,0xc000000,0x8000,0xc0000000,0x10000000,0xc0000000,0x8000,0x40000,0x8000,0xfb0000,};
- }
- final private JJCalls[] jj_2_rtns = new JJCalls[1];
- private boolean jj_rescan = false;
- private int jj_gc = 0;
-
- /** Constructor with user supplied CharStream. */
- public PrecedenceQueryParser(CharStream stream) {
- token_source = new PrecedenceQueryParserTokenManager(stream);
- token = new Token();
- jj_ntk = -1;
- jj_gen = 0;
- for (int i = 0; i < 24; i++) jj_la1[i] = -1;
- for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls();
- }
-
- /** Reinitialise. */
- public void ReInit(CharStream stream) {
- token_source.ReInit(stream);
- token = new Token();
- jj_ntk = -1;
- jj_gen = 0;
- for (int i = 0; i < 24; i++) jj_la1[i] = -1;
- for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls();
- }
-
- /** Constructor with generated Token Manager. */
- public PrecedenceQueryParser(PrecedenceQueryParserTokenManager tm) {
- token_source = tm;
- token = new Token();
- jj_ntk = -1;
- jj_gen = 0;
- for (int i = 0; i < 24; i++) jj_la1[i] = -1;
- for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls();
- }
-
- /** Reinitialise. */
- public void ReInit(PrecedenceQueryParserTokenManager tm) {
- token_source = tm;
- token = new Token();
- jj_ntk = -1;
- jj_gen = 0;
- for (int i = 0; i < 24; i++) jj_la1[i] = -1;
- for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls();
- }
-
- private Token jj_consume_token(int kind) throws ParseException {
- Token oldToken;
- if ((oldToken = token).next != null) token = token.next;
- else token = token.next = token_source.getNextToken();
- jj_ntk = -1;
- if (token.kind == kind) {
- jj_gen++;
- if (++jj_gc > 100) {
- jj_gc = 0;
- for (int i = 0; i < jj_2_rtns.length; i++) {
- JJCalls c = jj_2_rtns[i];
- while (c != null) {
- if (c.gen < jj_gen) c.first = null;
- c = c.next;
- }
- }
- }
- return token;
- }
- token = oldToken;
- jj_kind = kind;
- throw generateParseException();
- }
-
- static private final class LookaheadSuccess extends java.lang.Error { }
- final private LookaheadSuccess jj_ls = new LookaheadSuccess();
- private boolean jj_scan_token(int kind) {
- if (jj_scanpos == jj_lastpos) {
- jj_la--;
- if (jj_scanpos.next == null) {
- jj_lastpos = jj_scanpos = jj_scanpos.next = token_source.getNextToken();
- } else {
- jj_lastpos = jj_scanpos = jj_scanpos.next;
- }
- } else {
- jj_scanpos = jj_scanpos.next;
- }
- if (jj_rescan) {
- int i = 0; Token tok = token;
- while (tok != null && tok != jj_scanpos) { i++; tok = tok.next; }
- if (tok != null) jj_add_error_token(kind, i);
- }
- if (jj_scanpos.kind != kind) return true;
- if (jj_la == 0 && jj_scanpos == jj_lastpos) throw jj_ls;
- return false;
- }
-
-
-/** Get the next Token. */
- final public Token getNextToken() {
- if (token.next != null) token = token.next;
- else token = token.next = token_source.getNextToken();
- jj_ntk = -1;
- jj_gen++;
- return token;
- }
-
-/** Get the specific Token. */
- final public Token getToken(int index) {
- Token t = token;
- for (int i = 0; i < index; i++) {
- if (t.next != null) t = t.next;
- else t = t.next = token_source.getNextToken();
- }
- return t;
- }
-
- private int jj_ntk() {
- if ((jj_nt=token.next) == null)
- return (jj_ntk = (token.next=token_source.getNextToken()).kind);
- else
- return (jj_ntk = jj_nt.kind);
- }
-
- private java.util.List<int[]> jj_expentries = new java.util.ArrayList<int[]>();
- private int[] jj_expentry;
- private int jj_kind = -1;
- private int[] jj_lasttokens = new int[100];
- private int jj_endpos;
-
- private void jj_add_error_token(int kind, int pos) {
- if (pos >= 100) return;
- if (pos == jj_endpos + 1) {
- jj_lasttokens[jj_endpos++] = kind;
- } else if (jj_endpos != 0) {
- jj_expentry = new int[jj_endpos];
- for (int i = 0; i < jj_endpos; i++) {
- jj_expentry[i] = jj_lasttokens[i];
- }
- jj_entries_loop: for (java.util.Iterator it = jj_expentries.iterator(); it.hasNext();) {
- int[] oldentry = (int[])(it.next());
- if (oldentry.length == jj_expentry.length) {
- for (int i = 0; i < jj_expentry.length; i++) {
- if (oldentry[i] != jj_expentry[i]) {
- continue jj_entries_loop;
- }
- }
- jj_expentries.add(jj_expentry);
- break jj_entries_loop;
- }
- }
- if (pos != 0) jj_lasttokens[(jj_endpos = pos) - 1] = kind;
- }
- }
-
- /** Generate ParseException. */
- public ParseException generateParseException() {
- jj_expentries.clear();
- boolean[] la1tokens = new boolean[32];
- if (jj_kind >= 0) {
- la1tokens[jj_kind] = true;
- jj_kind = -1;
- }
- for (int i = 0; i < 24; i++) {
- if (jj_la1[i] == jj_gen) {
- for (int j = 0; j < 32; j++) {
- if ((jj_la1_0[i] & (1<<j)) != 0) {
- la1tokens[j] = true;
- }
- }
- }
- }
- for (int i = 0; i < 32; i++) {
- if (la1tokens[i]) {
- jj_expentry = new int[1];
- jj_expentry[0] = i;
- jj_expentries.add(jj_expentry);
- }
- }
- jj_endpos = 0;
- jj_rescan_token();
- jj_add_error_token(0, 0);
- int[][] exptokseq = new int[jj_expentries.size()][];
- for (int i = 0; i < jj_expentries.size(); i++) {
- exptokseq[i] = jj_expentries.get(i);
- }
- return new ParseException(token, exptokseq, tokenImage);
- }
-
- /** Enable tracing. */
- final public void enable_tracing() {
- }
-
- /** Disable tracing. */
- final public void disable_tracing() {
- }
-
- private void jj_rescan_token() {
- jj_rescan = true;
- for (int i = 0; i < 1; i++) {
- try {
- JJCalls p = jj_2_rtns[i];
- do {
- if (p.gen > jj_gen) {
- jj_la = p.arg; jj_lastpos = jj_scanpos = p.first;
- switch (i) {
- case 0: jj_3_1(); break;
- }
- }
- p = p.next;
- } while (p != null);
- } catch(LookaheadSuccess ls) { }
- }
- jj_rescan = false;
- }
-
- private void jj_save(int index, int xla) {
- JJCalls p = jj_2_rtns[index];
- while (p.gen > jj_gen) {
- if (p.next == null) { p = p.next = new JJCalls(); break; }
- p = p.next;
- }
- p.gen = jj_gen + xla - jj_la; p.first = token; p.arg = xla;
- }
-
- static final class JJCalls {
- int gen;
- Token first;
- int arg;
- JJCalls next;
+ public PrecedenceQueryParser(Analyzer analyer) {
+ super(analyer);
+
+ setQueryNodeProcessor(new PrecedenceQueryNodeProcessorPipeline(getQueryConfigHandler()));
+
}
}
Modified: lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/precedence/package.html
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/precedence/package.html?rev=1025606&r1=1025605&r2=1025606&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/precedence/package.html (original)
+++ lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/precedence/package.html Wed Oct 20 14:51:12 2010
@@ -16,7 +16,24 @@
limitations under the License.
-->
<html>
+<head>
+ <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
+</head>
<body>
-QueryParser designed to handle operator precedence in a more sensible fashion than the default QueryParser.
+
+This package contains the Precedence Query Parser Implementation
+
+<h2>Lucene Precedence Query Parser</h2>
+
+<p>
+The Precedence Query Parser extends the Standard Query Parser and enables
+the boolean precedence. So, the query <a AND b OR c AND d> is parsed to
+<(+a +b) (+c +d)> instead of <+a +b +c +d>.
+</p>
+<p>
+Check {@link org.apache.lucene.queryParser.standard.StandardQueryParser} for more details about the
+supported syntax and query parser functionalities.
+</p>
+
</body>
</html>
Modified: lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/test/org/apache/lucene/queryParser/precedence/TestPrecedenceQueryParser.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/test/org/apache/lucene/queryParser/precedence/TestPrecedenceQueryParser.java?rev=1025606&r1=1025605&r2=1025606&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/test/org/apache/lucene/queryParser/precedence/TestPrecedenceQueryParser.java (original)
+++ lucene/dev/branches/branch_3x/lucene/contrib/queryparser/src/test/org/apache/lucene/queryParser/precedence/TestPrecedenceQueryParser.java Wed Oct 20 14:51:12 2010
@@ -17,63 +17,86 @@ package org.apache.lucene.queryParser.pr
* limitations under the License.
*/
+import java.io.IOException;
+import java.io.Reader;
+import java.text.DateFormat;
+import java.util.Calendar;
+import java.util.Collections;
+import java.util.Date;
+import java.util.GregorianCalendar;
+import java.util.HashMap;
+import java.util.Map;
+
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.LowerCaseTokenizer;
import org.apache.lucene.analysis.SimpleAnalyzer;
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.CharTermAttribute;
+
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.document.DateField;
import org.apache.lucene.document.DateTools;
-import org.apache.lucene.index.Term;
-import org.apache.lucene.search.BooleanClause;
+import org.apache.lucene.queryParser.TestQueryParser;
+import org.apache.lucene.queryParser.core.QueryNodeException;
+import org.apache.lucene.queryParser.core.QueryNodeParseException;
+import org.apache.lucene.queryParser.standard.config.DefaultOperatorAttribute.Operator;
+import org.apache.lucene.queryParser.standard.parser.ParseException;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
-import org.apache.lucene.search.TermRangeQuery;
+
import org.apache.lucene.search.TermQuery;
+import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.util.LuceneTestCase;
-import java.io.IOException;
-import java.io.Reader;
-import java.text.DateFormat;
-import java.util.Calendar;
-import java.util.GregorianCalendar;
-import java.util.Collections;
-
+/**
+ * <p>
+ * This test case tests {@link PrecedenceQueryParser}.
+ * </p>
+ * <p>
+ * It contains all tests from {@link TestQueryParser} with some adjusted to
+ * fit the precedence requirement, plus some precedence test cases.
+ * </p>
+ *
+ * @see TestQueryParser
+ */
public class TestPrecedenceQueryParser extends LuceneTestCase {
+
public static Analyzer qpAnalyzer = new QPTestAnalyzer();
public static final class QPTestFilter extends TokenFilter {
/**
- * Filter which discards the token 'stop' and which expands the
- * token 'phrase' into 'phrase1 phrase2'
+ * Filter which discards the token 'stop' and which expands the token
+ * 'phrase' into 'phrase1 phrase2'
*/
public QPTestFilter(TokenStream in) {
super(in);
}
boolean inPhrase = false;
+
int savedStart = 0, savedEnd = 0;
CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+
OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
-
- @Override
+
public boolean incrementToken() throws IOException {
- clearAttributes();
if (inPhrase) {
inPhrase = false;
termAtt.setEmpty().append("phrase2");
offsetAtt.setOffset(savedStart, savedEnd);
return true;
} else
- while(input.incrementToken())
+ while (input.incrementToken())
if (termAtt.toString().equals("phrase")) {
inPhrase = true;
savedStart = offsetAtt.startOffset();
@@ -90,31 +113,13 @@ public class TestPrecedenceQueryParser e
public static final class QPTestAnalyzer extends Analyzer {
/** Filters LowerCaseTokenizer with StopFilter. */
- @Override
public final TokenStream tokenStream(String fieldName, Reader reader) {
return new QPTestFilter(new LowerCaseTokenizer(TEST_VERSION_CURRENT, reader));
}
}
- public static class QPTestParser extends PrecedenceQueryParser {
- public QPTestParser(String f, Analyzer a) {
- super(f, a);
- }
-
- @Override
- protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws ParseException {
- throw new ParseException("Fuzzy queries not allowed");
- }
-
- @Override
- protected Query getWildcardQuery(String field, String termStr) throws ParseException {
- throw new ParseException("Wildcard queries not allowed");
- }
- }
-
private int originalMaxClauses;
- @Override
public void setUp() throws Exception {
super.setUp();
originalMaxClauses = BooleanQuery.getMaxClauseCount();
@@ -123,40 +128,42 @@ public class TestPrecedenceQueryParser e
public PrecedenceQueryParser getParser(Analyzer a) throws Exception {
if (a == null)
a = new SimpleAnalyzer(TEST_VERSION_CURRENT);
- PrecedenceQueryParser qp = new PrecedenceQueryParser("field", a);
- qp.setDefaultOperator(PrecedenceQueryParser.OR_OPERATOR);
+ PrecedenceQueryParser qp = new PrecedenceQueryParser();
+ qp.setAnalyzer(a);
+ qp.setDefaultOperator(Operator.OR);
return qp;
}
public Query getQuery(String query, Analyzer a) throws Exception {
- return getParser(a).parse(query);
+ return getParser(a).parse(query, "field");
}
public void assertQueryEquals(String query, Analyzer a, String result)
- throws Exception {
+ throws Exception {
Query q = getQuery(query, a);
String s = q.toString("field");
if (!s.equals(result)) {
- fail("Query /" + query + "/ yielded /" + s
- + "/, expecting /" + result + "/");
+ fail("Query /" + query + "/ yielded /" + s + "/, expecting /" + result
+ + "/");
}
}
- public void assertWildcardQueryEquals(String query, boolean lowercase, String result)
- throws Exception {
+ public void assertWildcardQueryEquals(String query, boolean lowercase,
+ String result) throws Exception {
PrecedenceQueryParser qp = getParser(null);
qp.setLowercaseExpandedTerms(lowercase);
- Query q = qp.parse(query);
+ Query q = qp.parse(query, "field");
String s = q.toString("field");
if (!s.equals(result)) {
- fail("WildcardQuery /" + query + "/ yielded /" + s
- + "/, expecting /" + result + "/");
+ fail("WildcardQuery /" + query + "/ yielded /" + s + "/, expecting /"
+ + result + "/");
}
}
- public void assertWildcardQueryEquals(String query, String result) throws Exception {
+ public void assertWildcardQueryEquals(String query, String result)
+ throws Exception {
PrecedenceQueryParser qp = getParser(null);
- Query q = qp.parse(query);
+ Query q = qp.parse(query, "field");
String s = q.toString("field");
if (!s.equals(result)) {
fail("WildcardQuery /" + query + "/ yielded /" + s + "/, expecting /"
@@ -164,36 +171,30 @@ public class TestPrecedenceQueryParser e
}
}
- public Query getQueryDOA(String query, Analyzer a)
- throws Exception {
+ public Query getQueryDOA(String query, Analyzer a) throws Exception {
if (a == null)
a = new SimpleAnalyzer(TEST_VERSION_CURRENT);
- PrecedenceQueryParser qp = new PrecedenceQueryParser("field", a);
- qp.setDefaultOperator(PrecedenceQueryParser.AND_OPERATOR);
- return qp.parse(query);
+ PrecedenceQueryParser qp = new PrecedenceQueryParser();
+ qp.setAnalyzer(a);
+ qp.setDefaultOperator(Operator.AND);
+ return qp.parse(query, "field");
}
public void assertQueryEqualsDOA(String query, Analyzer a, String result)
- throws Exception {
+ throws Exception {
Query q = getQueryDOA(query, a);
String s = q.toString("field");
if (!s.equals(result)) {
- fail("Query /" + query + "/ yielded /" + s
- + "/, expecting /" + result + "/");
+ fail("Query /" + query + "/ yielded /" + s + "/, expecting /" + result
+ + "/");
}
}
- // failing tests disabled since PrecedenceQueryParser
- // is currently unmaintained
- public void _testSimple() throws Exception {
- assertQueryEquals("", null, "");
-
+ public void testSimple() throws Exception {
assertQueryEquals("term term term", null, "term term term");
assertQueryEquals("türm term term", null, "türm term term");
assertQueryEquals("ümlaut", null, "ümlaut");
- assertQueryEquals("+a", null, "+a");
- assertQueryEquals("-a", null, "-a");
assertQueryEquals("a AND b", null, "+a +b");
assertQueryEquals("(a AND b)", null, "+a +b");
assertQueryEquals("c OR (a AND b)", null, "c (+a +b)");
@@ -208,9 +209,9 @@ public class TestPrecedenceQueryParser e
assertQueryEquals("+term -term term", null, "+term -term term");
assertQueryEquals("foo:term AND field:anotherTerm", null,
- "+foo:term +anotherterm");
+ "+foo:term +anotherterm");
assertQueryEquals("term AND \"phrase phrase\"", null,
- "+term +\"phrase phrase\"");
+ "+term +\"phrase phrase\"");
assertQueryEquals("\"hello there\"", null, "\"hello there\"");
assertTrue(getQuery("a AND b", null) instanceof BooleanQuery);
assertTrue(getQuery("hello", null) instanceof TermQuery);
@@ -225,25 +226,25 @@ public class TestPrecedenceQueryParser e
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");
+ "+(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)");
+ "+(apple \"steve jobs\") -(foo bar baz)");
assertQueryEquals("+title:(dog OR cat) -author:\"bob dole\"", null,
- "+(title:dog title:cat) -author:\"bob dole\"");
-
- PrecedenceQueryParser qp = new PrecedenceQueryParser("field", new StandardAnalyzer(TEST_VERSION_CURRENT));
+ "+(title:dog title:cat) -author:\"bob dole\"");
+
+ PrecedenceQueryParser qp = new PrecedenceQueryParser();
+ qp.setAnalyzer(new StandardAnalyzer(TEST_VERSION_CURRENT));
// make sure OR is the default:
- assertEquals(PrecedenceQueryParser.OR_OPERATOR, qp.getDefaultOperator());
- qp.setDefaultOperator(PrecedenceQueryParser.AND_OPERATOR);
- assertEquals(PrecedenceQueryParser.AND_OPERATOR, qp.getDefaultOperator());
- qp.setDefaultOperator(PrecedenceQueryParser.OR_OPERATOR);
- assertEquals(PrecedenceQueryParser.OR_OPERATOR, qp.getDefaultOperator());
-
- assertQueryEquals("a OR !b", null, "a (-b)");
- assertQueryEquals("a OR ! b", null, "a (-b)");
- assertQueryEquals("a OR -b", null, "a (-b)");
+ assertEquals(Operator.OR, qp.getDefaultOperator());
+ qp.setDefaultOperator(Operator.AND);
+ assertEquals(Operator.AND, qp.getDefaultOperator());
+ qp.setDefaultOperator(Operator.OR);
+ assertEquals(Operator.OR, qp.getDefaultOperator());
+
+ assertQueryEquals("a OR !b", null, "a -b");
+ assertQueryEquals("a OR ! b", null, "a -b");
+ assertQueryEquals("a OR -b", null, "a -b");
}
public void testPunct() throws Exception {
@@ -262,7 +263,7 @@ public class TestPrecedenceQueryParser e
}
public void testNumber() throws Exception {
-// The numbers go away because SimpleAnalzyer ignores them
+ // 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");
@@ -272,74 +273,14 @@ public class TestPrecedenceQueryParser e
assertQueryEquals("term 1.0 1 2", a, "term 1.0 1 2");
assertQueryEquals("term term1 term2", a, "term term1 term2");
}
-
- public void testCJKTerm() throws Exception {
- // individual CJK chars as terms
- StandardAnalyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);
-
- BooleanQuery expected = new BooleanQuery();
- expected.add(new TermQuery(new Term("field", "ä¸")), BooleanClause.Occur.SHOULD);
- expected.add(new TermQuery(new Term("field", "å½")), BooleanClause.Occur.SHOULD);
-
- assertEquals(expected, getQuery("ä¸å½", analyzer));
- }
-
- public void testCJKBoostedTerm() throws Exception {
- // individual CJK chars as terms
- StandardAnalyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);
-
- BooleanQuery expected = new BooleanQuery();
- expected.setBoost(0.5f);
- expected.add(new TermQuery(new Term("field", "ä¸")), BooleanClause.Occur.SHOULD);
- expected.add(new TermQuery(new Term("field", "å½")), BooleanClause.Occur.SHOULD);
-
- assertEquals(expected, getQuery("ä¸å½^0.5", analyzer));
- }
-
- public void testCJKPhrase() throws Exception {
- // individual CJK chars as terms
- StandardAnalyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);
-
- PhraseQuery expected = new PhraseQuery();
- expected.add(new Term("field", "ä¸"));
- expected.add(new Term("field", "å½"));
-
- assertEquals(expected, getQuery("\"ä¸å½\"", analyzer));
- }
-
- public void testCJKBoostedPhrase() throws Exception {
- // individual CJK chars as terms
- StandardAnalyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);
-
- PhraseQuery expected = new PhraseQuery();
- expected.setBoost(0.5f);
- expected.add(new Term("field", "ä¸"));
- expected.add(new Term("field", "å½"));
-
- assertEquals(expected, getQuery("\"ä¸å½\"^0.5", analyzer));
- }
-
- public void testCJKSloppyPhrase() throws Exception {
- // individual CJK chars as terms
- StandardAnalyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);
-
- PhraseQuery expected = new PhraseQuery();
- expected.setSlop(3);
- expected.add(new Term("field", "ä¸"));
- expected.add(new Term("field", "å½"));
-
- assertEquals(expected, getQuery("\"ä¸å½\"~3", analyzer));
- }
- // failing tests disabled since PrecedenceQueryParser
- // is currently unmaintained
- public void _testWildcard() throws Exception {
+ 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^2.0~0.5");
- assertQueryEquals("term^2~", null, "term^2.0~0.5");
+ assertQueryEquals("term~^3", null, "term~0.5^3.0");
+ assertQueryEquals("term^3~", null, "term~0.5^3.0");
assertQueryEquals("term*germ", null, "term*germ");
assertQueryEquals("term*germ^3", null, "term*germ^3.0");
@@ -347,24 +288,25 @@ public class TestPrecedenceQueryParser e
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);
+ 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);
+ fq = (FuzzyQuery) getQuery("term~", null);
assertEquals(0.5f, fq.getMinSimilarity(), 0.1f);
assertEquals(FuzzyQuery.defaultPrefixLength, fq.getPrefixLength());
try {
- getQuery("term~1.1", null); // value > 1, throws exception
+ getQuery("term~1.1", null); // value > 1, throws exception
fail();
- } catch(ParseException pe) {
+ } catch (ParseException pe) {
// expected 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:
+ /*
+ * 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:
@@ -375,7 +317,7 @@ public class TestPrecedenceQueryParser e
assertWildcardQueryEquals("term*", false, "term*");
assertWildcardQueryEquals("Term*", false, "Term*");
assertWildcardQueryEquals("TERM*", false, "TERM*");
-// Then 'full' wildcard queries:
+ // Then 'full' wildcard queries:
// by default, convert to lowercase:
assertWildcardQueryEquals("Te?m", "te?m");
// explicitly set lowercase:
@@ -388,11 +330,11 @@ public class TestPrecedenceQueryParser e
assertWildcardQueryEquals("Te?m", false, "Te?m");
assertWildcardQueryEquals("TE?M", false, "TE?M");
assertWildcardQueryEquals("Te?m*gerM", false, "Te?m*gerM");
-// Fuzzy queries:
+ // Fuzzy queries:
assertWildcardQueryEquals("Term~", "term~0.5");
assertWildcardQueryEquals("Term~", true, "term~0.5");
assertWildcardQueryEquals("Term~", false, "Term~0.5");
-// Range queries:
+ // Range queries:
assertWildcardQueryEquals("[A TO C]", "[a TO c]");
assertWildcardQueryEquals("[A TO C]", true, "[a TO c]");
assertWildcardQueryEquals("[A TO C]", false, "[A TO C]");
@@ -404,11 +346,11 @@ public class TestPrecedenceQueryParser e
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");
+ "term (phrase1 phrase2) term");
// note the parens in this next assertion differ from the original
// QueryParser behavior
assertQueryEquals("term AND NOT phrase term", qpAnalyzer,
- "(+term -(phrase1 phrase2)) term");
+ "(+term -(phrase1 phrase2)) term");
assertQueryEquals("stop", qpAnalyzer, "");
assertQueryEquals("stop OR stop AND stop", qpAnalyzer, "");
assertTrue(getQuery("term term term", qpAnalyzer) instanceof BooleanQuery);
@@ -425,9 +367,10 @@ public class TestPrecedenceQueryParser e
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})");
+ assertQueryEquals("gack ( bar blar { a TO z}) ", null,
+ "gack (bar blar {a TO z})");
}
-
+
private String escapeDateString(String s) {
if (s.contains(" ")) {
return "\"" + s + "\"";
@@ -441,53 +384,106 @@ public class TestPrecedenceQueryParser e
return DateTools.dateToString(df.parse(s), DateTools.Resolution.DAY);
}
- public String getLocalizedDate(int year, int month, int day) {
+ private String getLocalizedDate(int year, int month, int day,
+ boolean extendLastDate) {
DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT);
Calendar calendar = new GregorianCalendar();
- calendar.clear();
calendar.set(year, month, day);
- calendar.set(Calendar.HOUR_OF_DAY, 23);
- calendar.set(Calendar.MINUTE, 59);
- calendar.set(Calendar.SECOND, 59);
- calendar.set(Calendar.MILLISECOND, 999);
+ 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());
}
public void testDateRange() throws Exception {
- String startDate = getLocalizedDate(2002, 1, 1);
- String endDate = getLocalizedDate(2002, 1, 4);
- assertQueryEquals("[ " + escapeDateString(startDate) + " TO " + escapeDateString(endDate) + "]", null,
- "[" + getDate(startDate) + " TO " + getDate(endDate) + "]");
- assertQueryEquals("{ " + escapeDateString(startDate) + " " + escapeDateString(endDate) + " }", null,
- "{" + getDate(startDate) + " TO " + getDate(endDate) + "}");
+ String startDate = getLocalizedDate(2002, 1, 1, false);
+ String endDate = getLocalizedDate(2002, 1, 4, false);
+ Calendar endDateExpected = new GregorianCalendar();
+ 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";
+ PrecedenceQueryParser qp = new PrecedenceQueryParser(new StandardAnalyzer(TEST_VERSION_CURRENT));
+
+ // Don't set any date resolution and verify if DateField is used
+ assertDateRangeQueryEquals(qp, defaultField, startDate, endDate,
+ endDateExpected.getTime(), null);
+
+ Map<CharSequence, DateTools.Resolution> fieldMap = new HashMap<CharSequence,DateTools.Resolution>();
+ // set a field specific date resolution
+ fieldMap.put(monthField, DateTools.Resolution.MONTH);
+ qp.setDateResolution(fieldMap);
+
+ // 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
+ fieldMap.put(hourField, DateTools.Resolution.HOUR);
+ qp.setDateResolution(fieldMap);
+
+ // 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);
+ }
+
+ /** 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);
+ }
+ }
+
+ public void assertQueryEquals(PrecedenceQueryParser qp, String field, String query,
+ String result) throws Exception {
+ Query q = qp.parse(query, field);
+ String s = q.toString(field);
+ if (!s.equals(result)) {
+ fail("Query /" + query + "/ yielded /" + s + "/, expecting /" + result
+ + "/");
+ }
+ }
+
+ public void assertDateRangeQueryEquals(PrecedenceQueryParser qp, String field,
+ String startDate, String endDate, Date endDateInclusive,
+ DateTools.Resolution resolution) throws Exception {
+ assertQueryEquals(qp, field, field + ":[" + escapeDateString(startDate)
+ + " TO " + escapeDateString(endDate) + "]", "["
+ + getDate(startDate, resolution) + " TO "
+ + getDate(endDateInclusive, resolution) + "]");
+ assertQueryEquals(qp, field, field + ":{" + escapeDateString(startDate)
+ + " TO " + escapeDateString(endDate) + "}", "{"
+ + getDate(startDate, resolution) + " TO "
+ + getDate(endDate, resolution) + "}");
}
public void testEscaped() throws Exception {
Analyzer a = new WhitespaceAnalyzer(TEST_VERSION_CURRENT);
-
- /*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\\-b:c", a, "a-b:c");
assertQueryEquals("a\\+b:c", a, "a+b:c");
@@ -521,44 +517,29 @@ public class TestPrecedenceQueryParser e
assertQueryEquals("[ a\\\\ TO a\\* ]", null, "[a\\ TO a*]");
}
- 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");
+ 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");
+ "+weltbank +worlbank");
- assertQueryEqualsDOA("+weltbank\t+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");
+ assertQueryEqualsDOA("weltbank \t+worlbank", null, "+weltbank +worlbank");
+ assertQueryEqualsDOA("weltbank \t +worlbank", null, "+weltbank +worlbank");
}
- public void testSimpleDAO()
- throws Exception {
+ 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");
@@ -566,22 +547,23 @@ public class TestPrecedenceQueryParser e
assertQueryEqualsDOA("-term term term", null, "-term +term +term");
}
- public void testBoost()
- throws Exception {
+ public void testBoost() throws Exception {
StandardAnalyzer oneStopAnalyzer = new StandardAnalyzer(TEST_VERSION_CURRENT, Collections.singleton("on"));
- PrecedenceQueryParser qp = new PrecedenceQueryParser("field", oneStopAnalyzer);
- Query q = qp.parse("on^1.0");
+
+ PrecedenceQueryParser qp = new PrecedenceQueryParser();
+ qp.setAnalyzer(oneStopAnalyzer);
+ Query q = qp.parse("on^1.0", "field");
assertNotNull(q);
- q = qp.parse("\"hello\"^2.0");
+ q = qp.parse("\"hello\"^2.0", "field");
assertNotNull(q);
assertEquals(q.getBoost(), (float) 2.0, (float) 0.5);
- q = qp.parse("hello^2.0");
+ q = qp.parse("hello^2.0", "field");
assertNotNull(q);
assertEquals(q.getBoost(), (float) 2.0, (float) 0.5);
- q = qp.parse("\"on\"^1.0");
+ q = qp.parse("\"on\"^1.0", "field");
assertNotNull(q);
- q = getParser(new StandardAnalyzer(TEST_VERSION_CURRENT)).parse("the^3");
+ q = getParser(new StandardAnalyzer(TEST_VERSION_CURRENT)).parse("the^3", "field");
assertNotNull(q);
}
@@ -589,76 +571,75 @@ public class TestPrecedenceQueryParser e
try {
assertQueryEquals("\"some phrase", null, "abc");
fail("ParseException expected, not thrown");
- } catch (ParseException expected) {
- }
- }
-
- public void testCustomQueryParserWildcard() {
- try {
- new QPTestParser("contents", new WhitespaceAnalyzer(TEST_VERSION_CURRENT)).parse("a?t");
- } catch (ParseException expected) {
- return;
+ } catch (QueryNodeParseException expected) {
}
- fail("Wildcard queries should not be allowed");
- }
-
- public void testCustomQueryParserFuzzy() throws Exception {
- try {
- new QPTestParser("contents", new WhitespaceAnalyzer(TEST_VERSION_CURRENT)).parse("xunit~");
- } catch (ParseException expected) {
- return;
- }
- fail("Fuzzy queries should not be allowed");
}
public void testBooleanQuery() throws Exception {
BooleanQuery.setMaxClauseCount(2);
try {
- getParser(new WhitespaceAnalyzer(TEST_VERSION_CURRENT)).parse("one two three");
+ getParser(new WhitespaceAnalyzer(TEST_VERSION_CURRENT)).parse("one two three", "field");
fail("ParseException expected due to too many boolean clauses");
- } catch (ParseException expected) {
+ } catch (QueryNodeException expected) {
// too many boolean clauses, so ParseException is expected
}
}
/**
- * This test differs from the original QueryParser, showing how the
- * precedence issue has been corrected.
+ * This test differs from the original QueryParser, showing how the precedence
+ * issue has been corrected.
*/
- // failing tests disabled since PrecedenceQueryParser
- // is currently unmaintained
- public void _testPrecedence() throws Exception {
+ public void testPrecedence() throws Exception {
PrecedenceQueryParser parser = getParser(new WhitespaceAnalyzer(TEST_VERSION_CURRENT));
- Query query1 = parser.parse("A AND B OR C AND D");
- Query query2 = parser.parse("(A AND B) OR (C AND D)");
+ Query query1 = parser.parse("A AND B OR C AND D", "field");
+ Query query2 = parser.parse("(A AND B) OR (C AND D)", "field");
assertEquals(query1, query2);
- query1 = parser.parse("A OR B C");
- query2 = parser.parse("A B C");
+ query1 = parser.parse("A OR B C", "field");
+ query2 = parser.parse("(A B) C", "field");
assertEquals(query1, query2);
- query1 = parser.parse("A AND B C");
- query2 = parser.parse("(+A +B) C");
+ query1 = parser.parse("A AND B C", "field");
+ query2 = parser.parse("(+A +B) C", "field");
assertEquals(query1, query2);
- query1 = parser.parse("A AND NOT B");
- query2 = parser.parse("+A -B");
+ query1 = parser.parse("A AND NOT B", "field");
+ query2 = parser.parse("+A -B", "field");
assertEquals(query1, query2);
- query1 = parser.parse("A OR NOT B");
- query2 = parser.parse("A -B");
+ query1 = parser.parse("A OR NOT B", "field");
+ query2 = parser.parse("A -B", "field");
assertEquals(query1, query2);
- query1 = parser.parse("A OR NOT B AND C");
- query2 = parser.parse("A (-B +C)");
+ query1 = parser.parse("A OR NOT B AND C", "field");
+ query2 = parser.parse("A (-B +C)", "field");
+ assertEquals(query1, query2);
+
+ parser.setDefaultOperator(Operator.AND);
+ query1 = parser.parse("A AND B OR C AND D", "field");
+ query2 = parser.parse("(A AND B) OR (C AND D)", "field");
+ assertEquals(query1, query2);
+
+ query1 = parser.parse("A AND B C", "field");
+ query2 = parser.parse("(A B) C", "field");
+ assertEquals(query1, query2);
+
+ query1 = parser.parse("A AND B C", "field");
+ query2 = parser.parse("(+A +B) C", "field");
assertEquals(query1, query2);
- }
+ query1 = parser.parse("A AND NOT B", "field");
+ query2 = parser.parse("+A -B", "field");
+ assertEquals(query1, query2);
+
+ query1 = parser.parse("A AND NOT B OR C", "field");
+ query2 = parser.parse("(+A -B) OR C", "field");
+ assertEquals(query1, query2);
+
+ }
- @Override
- public void tearDown() throws Exception {
+ public void tearDown() {
BooleanQuery.setMaxClauseCount(originalMaxClauses);
- super.tearDown();
}
}
Propchange: lucene/dev/branches/branch_3x/lucene/src/
------------------------------------------------------------------------------
--- svn:mergeinfo (original)
+++ svn:mergeinfo Wed Oct 20 14:51:12 2010
@@ -1,4 +1,4 @@
-/lucene/dev/trunk/lucene/src:931298,931337,931502,932129-932131,932163,932304,932369,932374,932398,932417,932541,932576,932587,932698,932731-932749,932752,932773,932795,932828,932856-932857,932862,932864,932878,932963,932998-932999,933541-933575,933598,933613,933679,933879,934339,934954,935014-935048,935065,935186-935513,935521-935522,935553-935962,936522,936544,936605,936657-936726,937039,937360,938582-938646,938989,939111,939611,939649,940433,940447,940451-940452,940666,940699,940730,940878-940892,940994,941270,941363,942166,942288,942676,942719,943142,943493,943931,945057,945090,945130,945245,945343,945420,946139,946330,946338,946599,948011,948082,948429,949288,949311,949445,949976,949997,950008,950042,950458,950613,951126,951355,951397,951521,953407,955547,955613,955615,955796-955797,955809-955996,956097,956125,956173,956316,956715,957465,957520,957634,957707,960367,960371,960374,960719,962555,963372,963654,963720,963781,963873,963906,963909,963920,964019,964054,964430,9
64459,964720,964753,964832,964856,965103,965110,965222,965230,965299,965327,965330,965585,966354,966878,967080,979453,979809,980369,980428,980436,980501,980909,980911,980917,981265,981550,981598,981650,981661,981857,981936,982073,982084,982201,982725,982824,983100,983212,983216,983313,983495,983500,983530,983622,983632,983778,984187,984202,984232,984510,984968,985453,985455,985672,985875,986158,986173,986612,987122,988087,988206,988216,988259,988346,988478,988527,988543,988592,988613,988688,988710,988736,988739,989004,989010,989013,989030,989035,989315,989321,989334,989785,990160-990161,990180,990189,990281,990301,990451,990459,990766,990781,990854,991053,991191,991310,991497,992424,992469,992567,992571,992623,993106,993194,993199,993287,993408,994935,994976,994979,995247,995250,995376,995772,996268,996357,996416,996511,996611,996623,996647-996653,996720,996942,996978,997180,997230,998055,998505,998684,999016,999223,999545,999842,1000424,1000581,1000675,1001006,1001420,10016
61,1001796,1002032,1003614,1003631,1003645,1003841-1003852,1003873,1003877,1003906,1003938,1003954,1003978,1003990,1004038,1004082,1004179,1004200,1004215,1004241,1004335,1005310,1005356,1005363,1006146,1006290,1006324,1021340,1021357,1021360,1021449,1021969-1021971,1022165,1022191,1022632,1022708-1022710,1022730-1022735,1022748-1022755,1022762-1022793,1022798-1022802,1022826,1022927,1022939,1022956,1022989,1022998,1023006,1023009,1023022,1023040,1023106,1023235-1023246,1023250,1023264-1023265,1023312,1023330,1023346,1023355,1023493,1023509-1023511,1023562,1023579-1023588,1023621,1023635,1023637,1023711,1023845,1023870,1024196,1024219,1024256,1024402,1024408,1024476
+/lucene/dev/trunk/lucene/src:931298,931337,931502,932129-932131,932163,932304,932369,932374,932398,932417,932541,932576,932587,932698,932731-932749,932752,932773,932795,932828,932856-932857,932862,932864,932878,932963,932998-932999,933541-933575,933598,933613,933679,933879,934339,934954,935014-935048,935065,935186-935513,935521-935522,935553-935962,936522,936544,936605,936657-936726,937039,937360,938582-938646,938989,939111,939611,939649,940433,940447,940451-940452,940666,940699,940730,940878-940892,940994,941270,941363,942166,942288,942676,942719,943142,943493,943931,945057,945090,945130,945245,945343,945420,946139,946330,946338,946599,948011,948082,948429,949288,949311,949445,949976,949997,950008,950042,950458,950613,951126,951355,951397,951521,953407,955547,955613,955615,955796-955797,955809-955996,956097,956125,956173,956316,956715,957465,957520,957634,957707,960367,960371,960374,960719,962555,963372,963654,963720,963781,963873,963906,963909,963920,964019,964054,964430,9
64459,964720,964753,964832,964856,965103,965110,965222,965230,965299,965327,965330,965585,966354,966878,967080,979453,979809,980369,980428,980436,980501,980909,980911,980917,981265,981550,981598,981650,981661,981857,981936,982073,982084,982201,982725,982824,983100,983212,983216,983313,983495,983500,983530,983622,983632,983778,984187,984202,984232,984510,984968,985453,985455,985672,985875,986158,986173,986612,987122,988087,988206,988216,988259,988346,988478,988527,988543,988592,988613,988688,988710,988736,988739,989004,989010,989013,989030,989035,989315,989321,989334,989785,990160-990161,990180,990189,990281,990301,990451,990459,990766,990781,990854,991053,991191,991310,991497,992424,992469,992567,992571,992623,993106,993194,993199,993287,993408,994935,994976,994979,995247,995250,995376,995772,996268,996357,996416,996511,996611,996623,996647-996653,996720,996942,996978,997180,997230,998055,998505,998684,999016,999223,999545,999842,1000424,1000581,1000675,1001006,1001420,10016
61,1001796,1002032,1003614,1003631,1003645,1003841-1003852,1003873,1003877,1003906,1003938,1003954,1003978,1003990,1004038,1004082,1004179,1004200,1004215,1004241,1004335,1005310,1005356,1005363,1006146,1006290,1006324,1021340,1021357,1021360,1021449,1021969-1021971,1022165,1022191,1022632,1022708-1022710,1022730-1022735,1022748-1022755,1022762-1022793,1022798-1022802,1022826,1022927,1022939,1022956,1022989,1022998,1023006,1023009,1023022,1023040,1023106,1023235-1023246,1023250,1023264-1023265,1023312,1023330,1023346,1023355,1023493,1023509-1023511,1023562,1023579-1023588,1023621,1023635,1023637,1023711,1023845,1023870,1024196,1024219,1024256,1024402,1024408,1024476,1025597
/lucene/dev/trunk/src:932749
/lucene/java/branches/flex_1458/src:924791,924850,930201
/lucene/java/branches/lucene_2_4/src:748824