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 2011/02/09 02:04:13 UTC
svn commit: r1068718 [6/21] - in /lucene/dev/branches/bulkpostings: ./
dev-tools/eclipse/ dev-tools/idea/.idea/ dev-tools/idea/lucene/
dev-tools/maven/ dev-tools/maven/lucene/ dev-tools/maven/lucene/contrib/ant/
dev-tools/maven/lucene/contrib/db/bdb-je...
Modified: lucene/dev/branches/bulkpostings/lucene/src/java/org/apache/lucene/queryParser/QueryParserBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/bulkpostings/lucene/src/java/org/apache/lucene/queryParser/QueryParserBase.java?rev=1068718&r1=1068717&r2=1068718&view=diff
==============================================================================
--- lucene/dev/branches/bulkpostings/lucene/src/java/org/apache/lucene/queryParser/QueryParserBase.java (original)
+++ lucene/dev/branches/bulkpostings/lucene/src/java/org/apache/lucene/queryParser/QueryParserBase.java Wed Feb 9 01:03:49 2011
@@ -1,1150 +1,1150 @@
-/**
- * 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.
- */
-
-package org.apache.lucene.queryParser;
-
-import java.io.IOException;
-import java.io.StringReader;
-import java.text.Collator;
-import java.text.DateFormat;
-import java.util.*;
-
-import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.analysis.CachingTokenFilter;
-import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermToBytesRefAttribute;
-import org.apache.lucene.document.DateTools;
-import org.apache.lucene.index.Term;
-import org.apache.lucene.queryParser.QueryParser.Operator;
-import org.apache.lucene.search.*;
-import org.apache.lucene.util.BytesRef;
-import org.apache.lucene.util.Version;
-
-/** This class is overridden by QueryParser in QueryParser.jj
- * and acts to separate the majority of the Java code from the .jj grammar file.
- */
-public abstract class QueryParserBase {
-
- /** Do not catch this exception in your code, it means you are using methods that you should no longer use. */
- public static class MethodRemovedUseAnother extends Throwable {}
-
- static final int CONJ_NONE = 0;
- static final int CONJ_AND = 1;
- static final int CONJ_OR = 2;
-
- static final int MOD_NONE = 0;
- static final int MOD_NOT = 10;
- static final int MOD_REQ = 11;
-
- // make it possible to call setDefaultOperator() without accessing
- // the nested class:
- /** Alternative form of QueryParser.Operator.AND */
- public static final Operator AND_OPERATOR = Operator.AND;
- /** Alternative form of QueryParser.Operator.OR */
- public static final Operator OR_OPERATOR = Operator.OR;
-
- /** The actual operator that parser uses to combine query terms */
- Operator operator = OR_OPERATOR;
-
- boolean lowercaseExpandedTerms = true;
- MultiTermQuery.RewriteMethod multiTermRewriteMethod = MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT;
- boolean allowLeadingWildcard = false;
- boolean enablePositionIncrements = true;
-
- Analyzer analyzer;
- String field;
- int phraseSlop = 0;
- float fuzzyMinSim = FuzzyQuery.defaultMinSimilarity;
- int fuzzyPrefixLength = FuzzyQuery.defaultPrefixLength;
- Locale locale = Locale.getDefault();
-
- // the default date resolution
- DateTools.Resolution dateResolution = null;
- // maps field names to date resolutions
- Map<String,DateTools.Resolution> fieldToDateResolution = null;
-
- // The collator to use when determining range inclusion,
- // for use when constructing RangeQuerys.
- Collator rangeCollator = null;
-
- boolean autoGeneratePhraseQueries;
-
- // So the generated QueryParser(CharStream) won't error out
- protected QueryParserBase() {
- }
-
- /** Initializes a query parser. Called by the QueryParser constructor
- * @param matchVersion Lucene version to match. See <a href="#version">above</a>.
- * @param f the default field for query terms.
- * @param a used to find terms in the query text.
- */
- public void init(Version matchVersion, String f, Analyzer a) {
- analyzer = a;
- field = f;
- if (matchVersion.onOrAfter(Version.LUCENE_31)) {
- setAutoGeneratePhraseQueries(false);
- } else {
- setAutoGeneratePhraseQueries(true);
- }
- }
-
- // the generated parser will create these in QueryParser
- public abstract void ReInit(CharStream stream);
- public abstract Query TopLevelQuery(String field) throws ParseException;
-
-
- /** Parses a query string, returning a {@link org.apache.lucene.search.Query}.
- * @param query the query string to be parsed.
- * @throws ParseException if the parsing fails
- */
- public Query parse(String query) throws ParseException {
- ReInit(new FastCharStream(new StringReader(query)));
- try {
- // TopLevelQuery is a Query followed by the end-of-input (EOF)
- Query res = TopLevelQuery(field);
- return res!=null ? res : newBooleanQuery(false);
- }
- catch (ParseException tme) {
- // rethrow to include the original query:
- ParseException e = new ParseException("Cannot parse '" +query+ "': " + tme.getMessage());
- e.initCause(tme);
- throw e;
- }
- catch (TokenMgrError tme) {
- ParseException e = new ParseException("Cannot parse '" +query+ "': " + tme.getMessage());
- e.initCause(tme);
- throw e;
- }
- catch (BooleanQuery.TooManyClauses tmc) {
- ParseException e = new ParseException("Cannot parse '" +query+ "': too many boolean clauses");
- e.initCause(tmc);
- throw e;
- }
- }
-
-
- /**
- * @return Returns the analyzer.
- */
- public Analyzer getAnalyzer() {
- return analyzer;
- }
-
- /**
- * @return Returns the default field.
- */
- public String getField() {
- return field;
- }
-
- /**
- * @see #setAutoGeneratePhraseQueries(boolean)
- */
- public final boolean getAutoGeneratePhraseQueries() {
- return autoGeneratePhraseQueries;
- }
-
- /**
- * Set to true if phrase queries will be automatically generated
- * when the analyzer returns more than one term from whitespace
- * delimited text.
- * NOTE: this behavior may not be suitable for all languages.
- * <p>
- * Set to false if phrase queries should only be generated when
- * surrounded by double quotes.
- */
- public final void setAutoGeneratePhraseQueries(boolean value) {
- this.autoGeneratePhraseQueries = value;
- }
-
- /**
- * Get the minimal similarity for fuzzy queries.
- */
- public float getFuzzyMinSim() {
- return fuzzyMinSim;
- }
-
- /**
- * Set the minimum similarity for fuzzy queries.
- * Default is 2f.
- */
- 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;
- }
-
-
- /**
- * Set to <code>true</code> to allow leading wildcard characters.
- * <p>
- * When set, <code>*</code> or <code>?</code> are allowed as
- * the first character of a PrefixQuery and WildcardQuery.
- * Note that this can produce very slow
- * queries on big indexes.
- * <p>
- * Default: false.
- */
- public void setAllowLeadingWildcard(boolean allowLeadingWildcard) {
- this.allowLeadingWildcard = allowLeadingWildcard;
- }
-
- /**
- * @see #setAllowLeadingWildcard(boolean)
- */
- public boolean getAllowLeadingWildcard() {
- return allowLeadingWildcard;
- }
-
- /**
- * Set to <code>true</code> to enable position increments in result query.
- * <p>
- * When set, result phrase and multi-phrase queries will
- * be aware of position increments.
- * Useful when e.g. a StopFilter increases the position increment of
- * the token that follows an omitted token.
- * <p>
- * Default: true.
- */
- public void setEnablePositionIncrements(boolean enable) {
- this.enablePositionIncrements = enable;
- }
-
- /**
- * @see #setEnablePositionIncrements(boolean)
- */
- public boolean getEnablePositionIncrements() {
- return enablePositionIncrements;
- }
-
- /**
- * 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;
- }
-
- /**
- * By default QueryParser uses {@link org.apache.lucene.search.MultiTermQuery#CONSTANT_SCORE_AUTO_REWRITE_DEFAULT}
- * when creating a PrefixQuery, WildcardQuery or RangeQuery. This implementation is generally preferable because it
- * a) Runs faster b) Does not have the scarcity of terms unduly influence score
- * c) avoids any "TooManyBooleanClauses" exception.
- * However, if your application really needs to use the
- * old-fashioned BooleanQuery expansion rewriting and the above
- * points are not relevant then use this to change
- * the rewrite method.
- */
- public void setMultiTermRewriteMethod(MultiTermQuery.RewriteMethod method) {
- multiTermRewriteMethod = method;
- }
-
-
- /**
- * @see #setMultiTermRewriteMethod
- */
- public MultiTermQuery.RewriteMethod getMultiTermRewriteMethod() {
- return multiTermRewriteMethod;
- }
-
- /**
- * 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;
- }
-
- /**
- * Sets the default date resolution used by RangeQueries for fields for which no
- * specific date resolutions has been set. Field specific resolutions can be set
- * with {@link #setDateResolution(String, org.apache.lucene.document.DateTools.Resolution)}.
- *
- * @param dateResolution the default date resolution to set
- */
- public void setDateResolution(DateTools.Resolution dateResolution) {
- this.dateResolution = dateResolution;
- }
-
- /**
- * Sets the date resolution used by RangeQueries for a specific field.
- *
- * @param fieldName field for which the date resolution is to be set
- * @param dateResolution date resolution to set
- */
- public void setDateResolution(String fieldName, DateTools.Resolution dateResolution) {
- if (fieldName == null) {
- throw new IllegalArgumentException("Field cannot be null.");
- }
-
- if (fieldToDateResolution == null) {
- // lazily initialize HashMap
- fieldToDateResolution = new HashMap<String,DateTools.Resolution>();
- }
-
- fieldToDateResolution.put(fieldName, dateResolution);
- }
-
- /**
- * Returns the date resolution that is used by RangeQueries for the given field.
- * Returns null, if no default or field specific date resolution has been set
- * for the given field.
- *
- */
- public DateTools.Resolution getDateResolution(String fieldName) {
- if (fieldName == null) {
- throw new IllegalArgumentException("Field cannot be null.");
- }
-
- if (fieldToDateResolution == null) {
- // no field specific date resolutions set; return default date resolution instead
- return this.dateResolution;
- }
-
- DateTools.Resolution resolution = fieldToDateResolution.get(fieldName);
- if (resolution == null) {
- // no date resolutions set for the given field; return default date resolution instead
- resolution = this.dateResolution;
- }
-
- return resolution;
- }
-
- /**
- * Sets the collator used to determine index term inclusion in ranges
- * for RangeQuerys.
- * <p/>
- * <strong>WARNING:</strong> Setting the rangeCollator to a non-null
- * collator using this method will cause every single index Term in the
- * Field referenced by lowerTerm and/or upperTerm to be examined.
- * Depending on the number of index Terms in this Field, the operation could
- * be very slow.
- *
- * @param rc the collator to use when constructing RangeQuerys
- */
- public void setRangeCollator(Collator rc) {
- rangeCollator = rc;
- }
-
- /**
- * @return the collator used to determine index term inclusion in ranges
- * for RangeQuerys.
- */
- public Collator getRangeCollator() {
- return rangeCollator;
- }
-
- protected void addClause(List<BooleanClause> clauses, int conj, int mods, 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 = (mods == MOD_NOT);
- required = (mods == 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 = (mods == MOD_NOT);
- required = (!prohibited && conj != CONJ_OR);
- }
- if (required && !prohibited)
- clauses.add(newBooleanClause(q, BooleanClause.Occur.MUST));
- else if (!required && !prohibited)
- clauses.add(newBooleanClause(q, BooleanClause.Occur.SHOULD));
- else if (!required && prohibited)
- clauses.add(newBooleanClause(q, BooleanClause.Occur.MUST_NOT));
- else
- throw new RuntimeException("Clause cannot be both required and prohibited");
- }
-
- /**
- * @exception org.apache.lucene.queryParser.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;
- try {
- source = analyzer.reusableTokenStream(field, new StringReader(queryText));
- source.reset();
- } catch (IOException e) {
- source = analyzer.tokenStream(field, new StringReader(queryText));
- }
- CachingTokenFilter buffer = new CachingTokenFilter(source);
- TermToBytesRefAttribute termAtt = null;
- PositionIncrementAttribute posIncrAtt = null;
- int numTokens = 0;
-
- boolean success = false;
- try {
- buffer.reset();
- success = true;
- } catch (IOException e) {
- // success==false if we hit an exception
- }
- if (success) {
- if (buffer.hasAttribute(TermToBytesRefAttribute.class)) {
- termAtt = buffer.getAttribute(TermToBytesRefAttribute.class);
- }
- if (buffer.hasAttribute(PositionIncrementAttribute.class)) {
- posIncrAtt = buffer.getAttribute(PositionIncrementAttribute.class);
- }
- }
-
- int positionCount = 0;
- boolean severalTokensAtSamePosition = false;
-
- boolean hasMoreTokens = false;
- if (termAtt != null) {
- try {
- hasMoreTokens = buffer.incrementToken();
- while (hasMoreTokens) {
- numTokens++;
- int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() : 1;
- if (positionIncrement != 0) {
- positionCount += positionIncrement;
- } else {
- severalTokensAtSamePosition = true;
- }
- hasMoreTokens = buffer.incrementToken();
- }
- } catch (IOException e) {
- // ignore
- }
- }
- try {
- // rewind the buffer stream
- buffer.reset();
-
- // close original stream - all tokens buffered
- source.close();
- }
- catch (IOException e) {
- // ignore
- }
-
- if (numTokens == 0)
- return null;
- else if (numTokens == 1) {
- BytesRef term = new BytesRef();
- try {
- boolean hasNext = buffer.incrementToken();
- assert hasNext == true;
- termAtt.toBytesRef(term);
- } catch (IOException e) {
- // safe to ignore, because we know the number of tokens
- }
- return newTermQuery(new Term(field, term));
- } else {
- if (severalTokensAtSamePosition || (!quoted && !autoGeneratePhraseQueries)) {
- if (positionCount == 1 || (!quoted && !autoGeneratePhraseQueries)) {
- // no phrase query:
- BooleanQuery q = newBooleanQuery(positionCount == 1);
-
- BooleanClause.Occur occur = positionCount > 1 && operator == AND_OPERATOR ?
- BooleanClause.Occur.MUST : BooleanClause.Occur.SHOULD;
-
- for (int i = 0; i < numTokens; i++) {
- BytesRef term = new BytesRef();
- try {
- boolean hasNext = buffer.incrementToken();
- assert hasNext == true;
- termAtt.toBytesRef(term);
- } catch (IOException e) {
- // safe to ignore, because we know the number of tokens
- }
-
- Query currentQuery = newTermQuery(
- new Term(field, term));
- q.add(currentQuery, occur);
- }
- return q;
- }
- else {
- // phrase query:
- MultiPhraseQuery mpq = newMultiPhraseQuery();
- mpq.setSlop(phraseSlop);
- List<Term> multiTerms = new ArrayList<Term>();
- int position = -1;
- for (int i = 0; i < numTokens; i++) {
- BytesRef term = new BytesRef();
- int positionIncrement = 1;
- try {
- boolean hasNext = buffer.incrementToken();
- assert hasNext == true;
- termAtt.toBytesRef(term);
- if (posIncrAtt != null) {
- positionIncrement = posIncrAtt.getPositionIncrement();
- }
- } catch (IOException e) {
- // safe to ignore, because we know the number of tokens
- }
-
- if (positionIncrement > 0 && multiTerms.size() > 0) {
- if (enablePositionIncrements) {
- mpq.add(multiTerms.toArray(new Term[0]),position);
- } else {
- mpq.add(multiTerms.toArray(new Term[0]));
- }
- multiTerms.clear();
- }
- position += positionIncrement;
- multiTerms.add(new Term(field, term));
- }
- if (enablePositionIncrements) {
- mpq.add(multiTerms.toArray(new Term[0]),position);
- } else {
- mpq.add(multiTerms.toArray(new Term[0]));
- }
- return mpq;
- }
- }
- else {
- PhraseQuery pq = newPhraseQuery();
- pq.setSlop(phraseSlop);
- int position = -1;
-
-
- for (int i = 0; i < numTokens; i++) {
- BytesRef term = new BytesRef();
- int positionIncrement = 1;
-
- try {
- boolean hasNext = buffer.incrementToken();
- assert hasNext == true;
- termAtt.toBytesRef(term);
- if (posIncrAtt != null) {
- positionIncrement = posIncrAtt.getPositionIncrement();
- }
- } catch (IOException e) {
- // safe to ignore, because we know the number of tokens
- }
-
- if (enablePositionIncrements) {
- position += positionIncrement;
- pq.add(new Term(field, term),position);
- } else {
- pq.add(new Term(field, term));
- }
- }
- return pq;
- }
- }
- }
-
-
-
- /**
- * 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 org.apache.lucene.queryParser.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 org.apache.lucene.queryParser.ParseException
- */
- protected Query getRangeQuery(String field,
- String part1,
- String part2,
- boolean startInclusive,
- boolean endInclusive) throws ParseException
- {
- if (lowercaseExpandedTerms) {
- part1 = part1==null ? null : part1.toLowerCase();
- part2 = part2==null ? null : part2.toLowerCase();
- }
-
-
- DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT, locale);
- df.setLenient(true);
- DateTools.Resolution resolution = getDateResolution(field);
-
- try {
- part1 = DateTools.dateToString(df.parse(part1), resolution);
- } catch (Exception e) { }
-
- try {
- Date d2 = df.parse(part2);
- if (endInclusive) {
- // The user can only specify the date, not the time, so make sure
- // the time is set to the latest possible time of that date to really
- // include all documents:
- Calendar cal = Calendar.getInstance(locale);
- cal.setTime(d2);
- cal.set(Calendar.HOUR_OF_DAY, 23);
- cal.set(Calendar.MINUTE, 59);
- cal.set(Calendar.SECOND, 59);
- cal.set(Calendar.MILLISECOND, 999);
- d2 = cal.getTime();
- }
- part2 = DateTools.dateToString(d2, resolution);
- } catch (Exception e) { }
-
- return newRangeQuery(field, part1, part2, startInclusive, endInclusive);
- }
-
- /**
- * Builds a new BooleanQuery instance
- * @param disableCoord disable coord
- * @return new BooleanQuery instance
- */
- protected BooleanQuery newBooleanQuery(boolean disableCoord) {
- return new BooleanQuery(disableCoord);
- }
-
- /**
- * Builds a new BooleanClause instance
- * @param q sub query
- * @param occur how this clause should occur when matching documents
- * @return new BooleanClause instance
- */
- protected BooleanClause newBooleanClause(Query q, BooleanClause.Occur occur) {
- return new BooleanClause(q, occur);
- }
-
- /**
- * Builds a new TermQuery instance
- * @param term term
- * @return new TermQuery instance
- */
- protected Query newTermQuery(Term term){
- return new TermQuery(term);
- }
-
- /**
- * Builds a new PhraseQuery instance
- * @return new PhraseQuery instance
- */
- protected PhraseQuery newPhraseQuery(){
- return new PhraseQuery();
- }
-
- /**
- * Builds a new MultiPhraseQuery instance
- * @return new MultiPhraseQuery instance
- */
- protected MultiPhraseQuery newMultiPhraseQuery(){
- return new MultiPhraseQuery();
- }
-
- /**
- * Builds a new PrefixQuery instance
- * @param prefix Prefix term
- * @return new PrefixQuery instance
- */
- protected Query newPrefixQuery(Term prefix){
- PrefixQuery query = new PrefixQuery(prefix);
- query.setRewriteMethod(multiTermRewriteMethod);
- return query;
- }
-
- /**
- * Builds a new RegexpQuery instance
- * @param regexp Regexp term
- * @return new RegexpQuery instance
- */
- protected Query newRegexpQuery(Term regexp) {
- RegexpQuery query = new RegexpQuery(regexp);
- query.setRewriteMethod(multiTermRewriteMethod);
- return query;
- }
-
- /**
- * Builds a new FuzzyQuery instance
- * @param term Term
- * @param minimumSimilarity minimum similarity
- * @param prefixLength prefix length
- * @return new FuzzyQuery Instance
- */
- protected Query newFuzzyQuery(Term term, float minimumSimilarity, int prefixLength) {
- // FuzzyQuery doesn't yet allow constant score rewrite
- return new FuzzyQuery(term,minimumSimilarity,prefixLength);
- }
-
- /**
- * Builds a new TermRangeQuery instance
- * @param field Field
- * @param part1 min
- * @param part2 max
- * @param startInclusive true if the start of the range is inclusive
- * @param endInclusive true if the end of the range is inclusive
- * @return new TermRangeQuery instance
- */
- protected Query newRangeQuery(String field, String part1, String part2, boolean startInclusive, boolean endInclusive) {
- final TermRangeQuery query = new TermRangeQuery(field, part1, part2, startInclusive, endInclusive, rangeCollator);
- query.setRewriteMethod(multiTermRewriteMethod);
- return query;
- }
-
- /**
- * Builds a new MatchAllDocsQuery instance
- * @return new MatchAllDocsQuery instance
- */
- protected Query newMatchAllDocsQuery() {
- return new MatchAllDocsQuery();
- }
-
- /**
- * Builds a new WildcardQuery instance
- * @param t wildcard term
- * @return new WildcardQuery instance
- */
- protected Query newWildcardQuery(Term t) {
- WildcardQuery query = new WildcardQuery(t);
- query.setRewriteMethod(multiTermRewriteMethod);
- return query;
- }
-
- /**
- * 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 org.apache.lucene.search.BooleanClause} instances
- * to join.
- *
- * @return Resulting {@link org.apache.lucene.search.Query} object.
- * @exception org.apache.lucene.queryParser.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 org.apache.lucene.search.BooleanClause} instances
- * to join.
- * @param disableCoord true if coord scoring should be disabled.
- *
- * @return Resulting {@link org.apache.lucene.search.Query} object.
- * @exception org.apache.lucene.queryParser.ParseException throw in overridden method to disallow
- */
- protected Query getBooleanQuery(List<BooleanClause> clauses, boolean disableCoord)
- throws ParseException
- {
- if (clauses.size()==0) {
- return null; // all clause words were filtered away by the analyzer.
- }
- BooleanQuery query = newBooleanQuery(disableCoord);
- for(final BooleanClause clause: clauses) {
- query.add(clause);
- }
- 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 org.apache.lucene.search.Query} built for the term
- * @exception org.apache.lucene.queryParser.ParseException throw in overridden method to disallow
- */
- protected Query getWildcardQuery(String field, String termStr) throws ParseException
- {
- if ("*".equals(field)) {
- if ("*".equals(termStr)) return newMatchAllDocsQuery();
- }
- if (!allowLeadingWildcard && (termStr.startsWith("*") || termStr.startsWith("?")))
- throw new ParseException("'*' or '?' not allowed as first character in WildcardQuery");
- if (lowercaseExpandedTerms) {
- termStr = termStr.toLowerCase();
- }
- Term t = new Term(field, termStr);
- return newWildcardQuery(t);
- }
-
- /**
- * Factory method for generating a query. Called when parser
- * parses an input term token that contains a regular expression
- * query.
- *<p>
- * Depending on settings, pattern term may be lower-cased
- * automatically. It will not go through the default Analyzer,
- * however, since normal Analyzers are unlikely to work properly
- * with regular expression templates.
- *<p>
- * Can be overridden by extending classes, to provide custom handling for
- * regular expression 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 a regular expression
- *
- * @return Resulting {@link org.apache.lucene.search.Query} built for the term
- * @exception org.apache.lucene.queryParser.ParseException throw in overridden method to disallow
- */
- protected Query getRegexpQuery(String field, String termStr) throws ParseException
- {
- if (lowercaseExpandedTerms) {
- termStr = termStr.toLowerCase();
- }
- Term t = new Term(field, termStr);
- return newRegexpQuery(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 org.apache.lucene.search.Query} built for the term
- * @exception org.apache.lucene.queryParser.ParseException throw in overridden method to disallow
- */
- protected Query getPrefixQuery(String field, String termStr) throws ParseException
- {
- if (!allowLeadingWildcard && termStr.startsWith("*"))
- throw new ParseException("'*' not allowed as first character in PrefixQuery");
- if (lowercaseExpandedTerms) {
- termStr = termStr.toLowerCase();
- }
- Term t = new Term(field, termStr);
- return newPrefixQuery(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 org.apache.lucene.search.Query} built for the term
- * @exception org.apache.lucene.queryParser.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 newFuzzyQuery(t, minSimilarity, fuzzyPrefixLength);
- }
-
-
- // extracted from the .jj grammar
- Query handleBareTokenQuery(String qfield, Token term, Token fuzzySlop, boolean prefix, boolean wildcard, boolean fuzzy, boolean regexp) throws ParseException {
- Query q;
-
- String termImage=discardEscapeChar(term.image);
- if (wildcard) {
- q = getWildcardQuery(qfield, term.image);
- } else if (prefix) {
- q = getPrefixQuery(qfield,
- discardEscapeChar(term.image.substring
- (0, term.image.length()-1)));
- } else if (regexp) {
- q = getRegexpQuery(qfield, term.image.substring(1, 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){
- throw new ParseException("Minimum similarity for a FuzzyQuery has to be between 0.0f and 1.0f !");
- } else if (fms >= 1.0f && fms != (int) fms) {
- throw new ParseException("Fractional edit distances are not allowed!");
- }
- q = getFuzzyQuery(qfield, termImage, fms);
- } else {
- q = getFieldQuery(qfield, termImage, false);
- }
- return q;
- }
-
- // extracted from the .jj grammar
- Query handleQuotedTerm(String qfield, Token term, Token fuzzySlop) throws ParseException {
- int s = phraseSlop; // default
- if (fuzzySlop != null) {
- try {
- s = Float.valueOf(fuzzySlop.image.substring(1)).intValue();
- }
- catch (Exception ignored) { }
- }
- return getFieldQuery(qfield, discardEscapeChar(term.image.substring(1, term.image.length()-1)), s);
- }
-
- // extracted from the .jj grammar
- Query handleBoost(Query q, Token boost) throws 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);
- }
- }
- return q;
- }
-
-
-
- /**
- * Returns a String where the escape char has been
- * removed, or kept only once if there was a double escape.
- *
- * Supports escaped unicode characters, e. g. translates
- * <code>\\u0041</code> to <code>A</code>.
- *
- */
- String discardEscapeChar(String input) throws ParseException {
- // Create char array to hold unescaped char sequence
- char[] output = new char[input.length()];
-
- // The length of the output can be less than the input
- // due to discarded escape chars. This variable holds
- // the actual length of the output
- int length = 0;
-
- // We remember whether the last processed character was
- // an escape character
- boolean lastCharWasEscapeChar = false;
-
- // The multiplier the current unicode digit must be multiplied with.
- // E. g. the first digit must be multiplied with 16^3, the second with 16^2...
- int codePointMultiplier = 0;
-
- // Used to calculate the codepoint of the escaped unicode character
- int codePoint = 0;
-
- for (int i = 0; i < input.length(); i++) {
- char curChar = input.charAt(i);
- if (codePointMultiplier > 0) {
- codePoint += hexToInt(curChar) * codePointMultiplier;
- codePointMultiplier >>>= 4;
- if (codePointMultiplier == 0) {
- output[length++] = (char)codePoint;
- codePoint = 0;
- }
- } else if (lastCharWasEscapeChar) {
- if (curChar == 'u') {
- // found an escaped unicode character
- codePointMultiplier = 16 * 16 * 16;
- } else {
- // this character was escaped
- output[length] = curChar;
- length++;
- }
- lastCharWasEscapeChar = false;
- } else {
- if (curChar == '\\') {
- lastCharWasEscapeChar = true;
- } else {
- output[length] = curChar;
- length++;
- }
- }
- }
-
- if (codePointMultiplier > 0) {
- throw new ParseException("Truncated unicode escape sequence.");
- }
-
- if (lastCharWasEscapeChar) {
- throw new ParseException("Term can not end with escape character.");
- }
-
- return new String(output, 0, length);
- }
-
- /** Returns the numeric value of the hexadecimal character */
- static final int hexToInt(char c) throws ParseException {
- if ('0' <= c && c <= '9') {
- return c - '0';
- } else if ('a' <= c && c <= 'f'){
- return c - 'a' + 10;
- } else if ('A' <= c && c <= 'F') {
- return c - 'A' + 10;
- } else {
- throw new ParseException("None-hex character in unicode escape sequence: " + c);
- }
- }
-
- /**
- * Returns a String where those characters that QueryParser
- * expects to be escaped are escaped by a preceding <code>\</code>.
- */
- public static String escape(String s) {
- StringBuilder sb = new StringBuilder();
- for (int i = 0; i < s.length(); i++) {
- char c = s.charAt(i);
- // These characters are part of the query syntax and must be escaped
- if (c == '\\' || c == '+' || c == '-' || c == '!' || c == '(' || c == ')' || c == ':'
- || c == '^' || c == '[' || c == ']' || c == '\"' || c == '{' || c == '}' || c == '~'
- || c == '*' || c == '?' || c == '|' || c == '&') {
- sb.append('\\');
- }
- sb.append(c);
- }
- return sb.toString();
- }
-
-}
+/**
+ * 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.
+ */
+
+package org.apache.lucene.queryParser;
+
+import java.io.IOException;
+import java.io.StringReader;
+import java.text.Collator;
+import java.text.DateFormat;
+import java.util.*;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.CachingTokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
+import org.apache.lucene.analysis.tokenattributes.TermToBytesRefAttribute;
+import org.apache.lucene.document.DateTools;
+import org.apache.lucene.index.Term;
+import org.apache.lucene.queryParser.QueryParser.Operator;
+import org.apache.lucene.search.*;
+import org.apache.lucene.util.BytesRef;
+import org.apache.lucene.util.Version;
+
+/** This class is overridden by QueryParser in QueryParser.jj
+ * and acts to separate the majority of the Java code from the .jj grammar file.
+ */
+public abstract class QueryParserBase {
+
+ /** Do not catch this exception in your code, it means you are using methods that you should no longer use. */
+ public static class MethodRemovedUseAnother extends Throwable {}
+
+ static final int CONJ_NONE = 0;
+ static final int CONJ_AND = 1;
+ static final int CONJ_OR = 2;
+
+ static final int MOD_NONE = 0;
+ static final int MOD_NOT = 10;
+ static final int MOD_REQ = 11;
+
+ // make it possible to call setDefaultOperator() without accessing
+ // the nested class:
+ /** Alternative form of QueryParser.Operator.AND */
+ public static final Operator AND_OPERATOR = Operator.AND;
+ /** Alternative form of QueryParser.Operator.OR */
+ public static final Operator OR_OPERATOR = Operator.OR;
+
+ /** The actual operator that parser uses to combine query terms */
+ Operator operator = OR_OPERATOR;
+
+ boolean lowercaseExpandedTerms = true;
+ MultiTermQuery.RewriteMethod multiTermRewriteMethod = MultiTermQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT;
+ boolean allowLeadingWildcard = false;
+ boolean enablePositionIncrements = true;
+
+ Analyzer analyzer;
+ String field;
+ int phraseSlop = 0;
+ float fuzzyMinSim = FuzzyQuery.defaultMinSimilarity;
+ int fuzzyPrefixLength = FuzzyQuery.defaultPrefixLength;
+ Locale locale = Locale.getDefault();
+
+ // the default date resolution
+ DateTools.Resolution dateResolution = null;
+ // maps field names to date resolutions
+ Map<String,DateTools.Resolution> fieldToDateResolution = null;
+
+ // The collator to use when determining range inclusion,
+ // for use when constructing RangeQuerys.
+ Collator rangeCollator = null;
+
+ boolean autoGeneratePhraseQueries;
+
+ // So the generated QueryParser(CharStream) won't error out
+ protected QueryParserBase() {
+ }
+
+ /** Initializes a query parser. Called by the QueryParser constructor
+ * @param matchVersion Lucene version to match. See <a href="#version">above</a>.
+ * @param f the default field for query terms.
+ * @param a used to find terms in the query text.
+ */
+ public void init(Version matchVersion, String f, Analyzer a) {
+ analyzer = a;
+ field = f;
+ if (matchVersion.onOrAfter(Version.LUCENE_31)) {
+ setAutoGeneratePhraseQueries(false);
+ } else {
+ setAutoGeneratePhraseQueries(true);
+ }
+ }
+
+ // the generated parser will create these in QueryParser
+ public abstract void ReInit(CharStream stream);
+ public abstract Query TopLevelQuery(String field) throws ParseException;
+
+
+ /** Parses a query string, returning a {@link org.apache.lucene.search.Query}.
+ * @param query the query string to be parsed.
+ * @throws ParseException if the parsing fails
+ */
+ public Query parse(String query) throws ParseException {
+ ReInit(new FastCharStream(new StringReader(query)));
+ try {
+ // TopLevelQuery is a Query followed by the end-of-input (EOF)
+ Query res = TopLevelQuery(field);
+ return res!=null ? res : newBooleanQuery(false);
+ }
+ catch (ParseException tme) {
+ // rethrow to include the original query:
+ ParseException e = new ParseException("Cannot parse '" +query+ "': " + tme.getMessage());
+ e.initCause(tme);
+ throw e;
+ }
+ catch (TokenMgrError tme) {
+ ParseException e = new ParseException("Cannot parse '" +query+ "': " + tme.getMessage());
+ e.initCause(tme);
+ throw e;
+ }
+ catch (BooleanQuery.TooManyClauses tmc) {
+ ParseException e = new ParseException("Cannot parse '" +query+ "': too many boolean clauses");
+ e.initCause(tmc);
+ throw e;
+ }
+ }
+
+
+ /**
+ * @return Returns the analyzer.
+ */
+ public Analyzer getAnalyzer() {
+ return analyzer;
+ }
+
+ /**
+ * @return Returns the default field.
+ */
+ public String getField() {
+ return field;
+ }
+
+ /**
+ * @see #setAutoGeneratePhraseQueries(boolean)
+ */
+ public final boolean getAutoGeneratePhraseQueries() {
+ return autoGeneratePhraseQueries;
+ }
+
+ /**
+ * Set to true if phrase queries will be automatically generated
+ * when the analyzer returns more than one term from whitespace
+ * delimited text.
+ * NOTE: this behavior may not be suitable for all languages.
+ * <p>
+ * Set to false if phrase queries should only be generated when
+ * surrounded by double quotes.
+ */
+ public final void setAutoGeneratePhraseQueries(boolean value) {
+ this.autoGeneratePhraseQueries = value;
+ }
+
+ /**
+ * Get the minimal similarity for fuzzy queries.
+ */
+ public float getFuzzyMinSim() {
+ return fuzzyMinSim;
+ }
+
+ /**
+ * Set the minimum similarity for fuzzy queries.
+ * Default is 2f.
+ */
+ 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;
+ }
+
+
+ /**
+ * Set to <code>true</code> to allow leading wildcard characters.
+ * <p>
+ * When set, <code>*</code> or <code>?</code> are allowed as
+ * the first character of a PrefixQuery and WildcardQuery.
+ * Note that this can produce very slow
+ * queries on big indexes.
+ * <p>
+ * Default: false.
+ */
+ public void setAllowLeadingWildcard(boolean allowLeadingWildcard) {
+ this.allowLeadingWildcard = allowLeadingWildcard;
+ }
+
+ /**
+ * @see #setAllowLeadingWildcard(boolean)
+ */
+ public boolean getAllowLeadingWildcard() {
+ return allowLeadingWildcard;
+ }
+
+ /**
+ * Set to <code>true</code> to enable position increments in result query.
+ * <p>
+ * When set, result phrase and multi-phrase queries will
+ * be aware of position increments.
+ * Useful when e.g. a StopFilter increases the position increment of
+ * the token that follows an omitted token.
+ * <p>
+ * Default: true.
+ */
+ public void setEnablePositionIncrements(boolean enable) {
+ this.enablePositionIncrements = enable;
+ }
+
+ /**
+ * @see #setEnablePositionIncrements(boolean)
+ */
+ public boolean getEnablePositionIncrements() {
+ return enablePositionIncrements;
+ }
+
+ /**
+ * 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;
+ }
+
+ /**
+ * By default QueryParser uses {@link org.apache.lucene.search.MultiTermQuery#CONSTANT_SCORE_AUTO_REWRITE_DEFAULT}
+ * when creating a PrefixQuery, WildcardQuery or RangeQuery. This implementation is generally preferable because it
+ * a) Runs faster b) Does not have the scarcity of terms unduly influence score
+ * c) avoids any "TooManyBooleanClauses" exception.
+ * However, if your application really needs to use the
+ * old-fashioned BooleanQuery expansion rewriting and the above
+ * points are not relevant then use this to change
+ * the rewrite method.
+ */
+ public void setMultiTermRewriteMethod(MultiTermQuery.RewriteMethod method) {
+ multiTermRewriteMethod = method;
+ }
+
+
+ /**
+ * @see #setMultiTermRewriteMethod
+ */
+ public MultiTermQuery.RewriteMethod getMultiTermRewriteMethod() {
+ return multiTermRewriteMethod;
+ }
+
+ /**
+ * 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;
+ }
+
+ /**
+ * Sets the default date resolution used by RangeQueries for fields for which no
+ * specific date resolutions has been set. Field specific resolutions can be set
+ * with {@link #setDateResolution(String, org.apache.lucene.document.DateTools.Resolution)}.
+ *
+ * @param dateResolution the default date resolution to set
+ */
+ public void setDateResolution(DateTools.Resolution dateResolution) {
+ this.dateResolution = dateResolution;
+ }
+
+ /**
+ * Sets the date resolution used by RangeQueries for a specific field.
+ *
+ * @param fieldName field for which the date resolution is to be set
+ * @param dateResolution date resolution to set
+ */
+ public void setDateResolution(String fieldName, DateTools.Resolution dateResolution) {
+ if (fieldName == null) {
+ throw new IllegalArgumentException("Field cannot be null.");
+ }
+
+ if (fieldToDateResolution == null) {
+ // lazily initialize HashMap
+ fieldToDateResolution = new HashMap<String,DateTools.Resolution>();
+ }
+
+ fieldToDateResolution.put(fieldName, dateResolution);
+ }
+
+ /**
+ * Returns the date resolution that is used by RangeQueries for the given field.
+ * Returns null, if no default or field specific date resolution has been set
+ * for the given field.
+ *
+ */
+ public DateTools.Resolution getDateResolution(String fieldName) {
+ if (fieldName == null) {
+ throw new IllegalArgumentException("Field cannot be null.");
+ }
+
+ if (fieldToDateResolution == null) {
+ // no field specific date resolutions set; return default date resolution instead
+ return this.dateResolution;
+ }
+
+ DateTools.Resolution resolution = fieldToDateResolution.get(fieldName);
+ if (resolution == null) {
+ // no date resolutions set for the given field; return default date resolution instead
+ resolution = this.dateResolution;
+ }
+
+ return resolution;
+ }
+
+ /**
+ * Sets the collator used to determine index term inclusion in ranges
+ * for RangeQuerys.
+ * <p/>
+ * <strong>WARNING:</strong> Setting the rangeCollator to a non-null
+ * collator using this method will cause every single index Term in the
+ * Field referenced by lowerTerm and/or upperTerm to be examined.
+ * Depending on the number of index Terms in this Field, the operation could
+ * be very slow.
+ *
+ * @param rc the collator to use when constructing RangeQuerys
+ */
+ public void setRangeCollator(Collator rc) {
+ rangeCollator = rc;
+ }
+
+ /**
+ * @return the collator used to determine index term inclusion in ranges
+ * for RangeQuerys.
+ */
+ public Collator getRangeCollator() {
+ return rangeCollator;
+ }
+
+ protected void addClause(List<BooleanClause> clauses, int conj, int mods, 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 = (mods == MOD_NOT);
+ required = (mods == 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 = (mods == MOD_NOT);
+ required = (!prohibited && conj != CONJ_OR);
+ }
+ if (required && !prohibited)
+ clauses.add(newBooleanClause(q, BooleanClause.Occur.MUST));
+ else if (!required && !prohibited)
+ clauses.add(newBooleanClause(q, BooleanClause.Occur.SHOULD));
+ else if (!required && prohibited)
+ clauses.add(newBooleanClause(q, BooleanClause.Occur.MUST_NOT));
+ else
+ throw new RuntimeException("Clause cannot be both required and prohibited");
+ }
+
+ /**
+ * @exception org.apache.lucene.queryParser.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;
+ try {
+ source = analyzer.reusableTokenStream(field, new StringReader(queryText));
+ source.reset();
+ } catch (IOException e) {
+ source = analyzer.tokenStream(field, new StringReader(queryText));
+ }
+ CachingTokenFilter buffer = new CachingTokenFilter(source);
+ TermToBytesRefAttribute termAtt = null;
+ PositionIncrementAttribute posIncrAtt = null;
+ int numTokens = 0;
+
+ boolean success = false;
+ try {
+ buffer.reset();
+ success = true;
+ } catch (IOException e) {
+ // success==false if we hit an exception
+ }
+ if (success) {
+ if (buffer.hasAttribute(TermToBytesRefAttribute.class)) {
+ termAtt = buffer.getAttribute(TermToBytesRefAttribute.class);
+ }
+ if (buffer.hasAttribute(PositionIncrementAttribute.class)) {
+ posIncrAtt = buffer.getAttribute(PositionIncrementAttribute.class);
+ }
+ }
+
+ int positionCount = 0;
+ boolean severalTokensAtSamePosition = false;
+
+ boolean hasMoreTokens = false;
+ if (termAtt != null) {
+ try {
+ hasMoreTokens = buffer.incrementToken();
+ while (hasMoreTokens) {
+ numTokens++;
+ int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() : 1;
+ if (positionIncrement != 0) {
+ positionCount += positionIncrement;
+ } else {
+ severalTokensAtSamePosition = true;
+ }
+ hasMoreTokens = buffer.incrementToken();
+ }
+ } catch (IOException e) {
+ // ignore
+ }
+ }
+ try {
+ // rewind the buffer stream
+ buffer.reset();
+
+ // close original stream - all tokens buffered
+ source.close();
+ }
+ catch (IOException e) {
+ // ignore
+ }
+
+ if (numTokens == 0)
+ return null;
+ else if (numTokens == 1) {
+ BytesRef term = new BytesRef();
+ try {
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ termAtt.toBytesRef(term);
+ } catch (IOException e) {
+ // safe to ignore, because we know the number of tokens
+ }
+ return newTermQuery(new Term(field, term));
+ } else {
+ if (severalTokensAtSamePosition || (!quoted && !autoGeneratePhraseQueries)) {
+ if (positionCount == 1 || (!quoted && !autoGeneratePhraseQueries)) {
+ // no phrase query:
+ BooleanQuery q = newBooleanQuery(positionCount == 1);
+
+ BooleanClause.Occur occur = positionCount > 1 && operator == AND_OPERATOR ?
+ BooleanClause.Occur.MUST : BooleanClause.Occur.SHOULD;
+
+ for (int i = 0; i < numTokens; i++) {
+ BytesRef term = new BytesRef();
+ try {
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ termAtt.toBytesRef(term);
+ } catch (IOException e) {
+ // safe to ignore, because we know the number of tokens
+ }
+
+ Query currentQuery = newTermQuery(
+ new Term(field, term));
+ q.add(currentQuery, occur);
+ }
+ return q;
+ }
+ else {
+ // phrase query:
+ MultiPhraseQuery mpq = newMultiPhraseQuery();
+ mpq.setSlop(phraseSlop);
+ List<Term> multiTerms = new ArrayList<Term>();
+ int position = -1;
+ for (int i = 0; i < numTokens; i++) {
+ BytesRef term = new BytesRef();
+ int positionIncrement = 1;
+ try {
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ termAtt.toBytesRef(term);
+ if (posIncrAtt != null) {
+ positionIncrement = posIncrAtt.getPositionIncrement();
+ }
+ } catch (IOException e) {
+ // safe to ignore, because we know the number of tokens
+ }
+
+ if (positionIncrement > 0 && multiTerms.size() > 0) {
+ if (enablePositionIncrements) {
+ mpq.add(multiTerms.toArray(new Term[0]),position);
+ } else {
+ mpq.add(multiTerms.toArray(new Term[0]));
+ }
+ multiTerms.clear();
+ }
+ position += positionIncrement;
+ multiTerms.add(new Term(field, term));
+ }
+ if (enablePositionIncrements) {
+ mpq.add(multiTerms.toArray(new Term[0]),position);
+ } else {
+ mpq.add(multiTerms.toArray(new Term[0]));
+ }
+ return mpq;
+ }
+ }
+ else {
+ PhraseQuery pq = newPhraseQuery();
+ pq.setSlop(phraseSlop);
+ int position = -1;
+
+
+ for (int i = 0; i < numTokens; i++) {
+ BytesRef term = new BytesRef();
+ int positionIncrement = 1;
+
+ try {
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ termAtt.toBytesRef(term);
+ if (posIncrAtt != null) {
+ positionIncrement = posIncrAtt.getPositionIncrement();
+ }
+ } catch (IOException e) {
+ // safe to ignore, because we know the number of tokens
+ }
+
+ if (enablePositionIncrements) {
+ position += positionIncrement;
+ pq.add(new Term(field, term),position);
+ } else {
+ pq.add(new Term(field, term));
+ }
+ }
+ return pq;
+ }
+ }
+ }
+
+
+
+ /**
+ * 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 org.apache.lucene.queryParser.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 org.apache.lucene.queryParser.ParseException
+ */
+ protected Query getRangeQuery(String field,
+ String part1,
+ String part2,
+ boolean startInclusive,
+ boolean endInclusive) throws ParseException
+ {
+ if (lowercaseExpandedTerms) {
+ part1 = part1==null ? null : part1.toLowerCase();
+ part2 = part2==null ? null : part2.toLowerCase();
+ }
+
+
+ DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT, locale);
+ df.setLenient(true);
+ DateTools.Resolution resolution = getDateResolution(field);
+
+ try {
+ part1 = DateTools.dateToString(df.parse(part1), resolution);
+ } catch (Exception e) { }
+
+ try {
+ Date d2 = df.parse(part2);
+ if (endInclusive) {
+ // The user can only specify the date, not the time, so make sure
+ // the time is set to the latest possible time of that date to really
+ // include all documents:
+ Calendar cal = Calendar.getInstance(locale);
+ cal.setTime(d2);
+ cal.set(Calendar.HOUR_OF_DAY, 23);
+ cal.set(Calendar.MINUTE, 59);
+ cal.set(Calendar.SECOND, 59);
+ cal.set(Calendar.MILLISECOND, 999);
+ d2 = cal.getTime();
+ }
+ part2 = DateTools.dateToString(d2, resolution);
+ } catch (Exception e) { }
+
+ return newRangeQuery(field, part1, part2, startInclusive, endInclusive);
+ }
+
+ /**
+ * Builds a new BooleanQuery instance
+ * @param disableCoord disable coord
+ * @return new BooleanQuery instance
+ */
+ protected BooleanQuery newBooleanQuery(boolean disableCoord) {
+ return new BooleanQuery(disableCoord);
+ }
+
+ /**
+ * Builds a new BooleanClause instance
+ * @param q sub query
+ * @param occur how this clause should occur when matching documents
+ * @return new BooleanClause instance
+ */
+ protected BooleanClause newBooleanClause(Query q, BooleanClause.Occur occur) {
+ return new BooleanClause(q, occur);
+ }
+
+ /**
+ * Builds a new TermQuery instance
+ * @param term term
+ * @return new TermQuery instance
+ */
+ protected Query newTermQuery(Term term){
+ return new TermQuery(term);
+ }
+
+ /**
+ * Builds a new PhraseQuery instance
+ * @return new PhraseQuery instance
+ */
+ protected PhraseQuery newPhraseQuery(){
+ return new PhraseQuery();
+ }
+
+ /**
+ * Builds a new MultiPhraseQuery instance
+ * @return new MultiPhraseQuery instance
+ */
+ protected MultiPhraseQuery newMultiPhraseQuery(){
+ return new MultiPhraseQuery();
+ }
+
+ /**
+ * Builds a new PrefixQuery instance
+ * @param prefix Prefix term
+ * @return new PrefixQuery instance
+ */
+ protected Query newPrefixQuery(Term prefix){
+ PrefixQuery query = new PrefixQuery(prefix);
+ query.setRewriteMethod(multiTermRewriteMethod);
+ return query;
+ }
+
+ /**
+ * Builds a new RegexpQuery instance
+ * @param regexp Regexp term
+ * @return new RegexpQuery instance
+ */
+ protected Query newRegexpQuery(Term regexp) {
+ RegexpQuery query = new RegexpQuery(regexp);
+ query.setRewriteMethod(multiTermRewriteMethod);
+ return query;
+ }
+
+ /**
+ * Builds a new FuzzyQuery instance
+ * @param term Term
+ * @param minimumSimilarity minimum similarity
+ * @param prefixLength prefix length
+ * @return new FuzzyQuery Instance
+ */
+ protected Query newFuzzyQuery(Term term, float minimumSimilarity, int prefixLength) {
+ // FuzzyQuery doesn't yet allow constant score rewrite
+ return new FuzzyQuery(term,minimumSimilarity,prefixLength);
+ }
+
+ /**
+ * Builds a new TermRangeQuery instance
+ * @param field Field
+ * @param part1 min
+ * @param part2 max
+ * @param startInclusive true if the start of the range is inclusive
+ * @param endInclusive true if the end of the range is inclusive
+ * @return new TermRangeQuery instance
+ */
+ protected Query newRangeQuery(String field, String part1, String part2, boolean startInclusive, boolean endInclusive) {
+ final TermRangeQuery query = new TermRangeQuery(field, part1, part2, startInclusive, endInclusive, rangeCollator);
+ query.setRewriteMethod(multiTermRewriteMethod);
+ return query;
+ }
+
+ /**
+ * Builds a new MatchAllDocsQuery instance
+ * @return new MatchAllDocsQuery instance
+ */
+ protected Query newMatchAllDocsQuery() {
+ return new MatchAllDocsQuery();
+ }
+
+ /**
+ * Builds a new WildcardQuery instance
+ * @param t wildcard term
+ * @return new WildcardQuery instance
+ */
+ protected Query newWildcardQuery(Term t) {
+ WildcardQuery query = new WildcardQuery(t);
+ query.setRewriteMethod(multiTermRewriteMethod);
+ return query;
+ }
+
+ /**
+ * 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 org.apache.lucene.search.BooleanClause} instances
+ * to join.
+ *
+ * @return Resulting {@link org.apache.lucene.search.Query} object.
+ * @exception org.apache.lucene.queryParser.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 org.apache.lucene.search.BooleanClause} instances
+ * to join.
+ * @param disableCoord true if coord scoring should be disabled.
+ *
+ * @return Resulting {@link org.apache.lucene.search.Query} object.
+ * @exception org.apache.lucene.queryParser.ParseException throw in overridden method to disallow
+ */
+ protected Query getBooleanQuery(List<BooleanClause> clauses, boolean disableCoord)
+ throws ParseException
+ {
+ if (clauses.size()==0) {
+ return null; // all clause words were filtered away by the analyzer.
+ }
+ BooleanQuery query = newBooleanQuery(disableCoord);
+ for(final BooleanClause clause: clauses) {
+ query.add(clause);
+ }
+ 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 org.apache.lucene.search.Query} built for the term
+ * @exception org.apache.lucene.queryParser.ParseException throw in overridden method to disallow
+ */
+ protected Query getWildcardQuery(String field, String termStr) throws ParseException
+ {
+ if ("*".equals(field)) {
+ if ("*".equals(termStr)) return newMatchAllDocsQuery();
+ }
+ if (!allowLeadingWildcard && (termStr.startsWith("*") || termStr.startsWith("?")))
+ throw new ParseException("'*' or '?' not allowed as first character in WildcardQuery");
+ if (lowercaseExpandedTerms) {
+ termStr = termStr.toLowerCase();
+ }
+ Term t = new Term(field, termStr);
+ return newWildcardQuery(t);
+ }
+
+ /**
+ * Factory method for generating a query. Called when parser
+ * parses an input term token that contains a regular expression
+ * query.
+ *<p>
+ * Depending on settings, pattern term may be lower-cased
+ * automatically. It will not go through the default Analyzer,
+ * however, since normal Analyzers are unlikely to work properly
+ * with regular expression templates.
+ *<p>
+ * Can be overridden by extending classes, to provide custom handling for
+ * regular expression 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 a regular expression
+ *
+ * @return Resulting {@link org.apache.lucene.search.Query} built for the term
+ * @exception org.apache.lucene.queryParser.ParseException throw in overridden method to disallow
+ */
+ protected Query getRegexpQuery(String field, String termStr) throws ParseException
+ {
+ if (lowercaseExpandedTerms) {
+ termStr = termStr.toLowerCase();
+ }
+ Term t = new Term(field, termStr);
+ return newRegexpQuery(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 org.apache.lucene.search.Query} built for the term
+ * @exception org.apache.lucene.queryParser.ParseException throw in overridden method to disallow
+ */
+ protected Query getPrefixQuery(String field, String termStr) throws ParseException
+ {
+ if (!allowLeadingWildcard && termStr.startsWith("*"))
+ throw new ParseException("'*' not allowed as first character in PrefixQuery");
+ if (lowercaseExpandedTerms) {
+ termStr = termStr.toLowerCase();
+ }
+ Term t = new Term(field, termStr);
+ return newPrefixQuery(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 org.apache.lucene.search.Query} built for the term
+ * @exception org.apache.lucene.queryParser.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 newFuzzyQuery(t, minSimilarity, fuzzyPrefixLength);
+ }
+
+
+ // extracted from the .jj grammar
+ Query handleBareTokenQuery(String qfield, Token term, Token fuzzySlop, boolean prefix, boolean wildcard, boolean fuzzy, boolean regexp) throws ParseException {
+ Query q;
+
+ String termImage=discardEscapeChar(term.image);
+ if (wildcard) {
+ q = getWildcardQuery(qfield, term.image);
+ } else if (prefix) {
+ q = getPrefixQuery(qfield,
+ discardEscapeChar(term.image.substring
+ (0, term.image.length()-1)));
+ } else if (regexp) {
+ q = getRegexpQuery(qfield, term.image.substring(1, 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){
+ throw new ParseException("Minimum similarity for a FuzzyQuery has to be between 0.0f and 1.0f !");
+ } else if (fms >= 1.0f && fms != (int) fms) {
+ throw new ParseException("Fractional edit distances are not allowed!");
+ }
+ q = getFuzzyQuery(qfield, termImage, fms);
+ } else {
+ q = getFieldQuery(qfield, termImage, false);
+ }
+ return q;
+ }
+
+ // extracted from the .jj grammar
+ Query handleQuotedTerm(String qfield, Token term, Token fuzzySlop) throws ParseException {
+ int s = phraseSlop; // default
+ if (fuzzySlop != null) {
+ try {
+ s = Float.valueOf(fuzzySlop.image.substring(1)).intValue();
+ }
+ catch (Exception ignored) { }
+ }
+ return getFieldQuery(qfield, discardEscapeChar(term.image.substring(1, term.image.length()-1)), s);
+ }
+
+ // extracted from the .jj grammar
+ Query handleBoost(Query q, Token boost) throws 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);
+ }
+ }
+ return q;
+ }
+
+
+
+ /**
+ * Returns a String where the escape char has been
+ * removed, or kept only once if there was a double escape.
+ *
+ * Supports escaped unicode characters, e. g. translates
+ * <code>\\u0041</code> to <code>A</code>.
+ *
+ */
+ String discardEscapeChar(String input) throws ParseException {
+ // Create char array to hold unescaped char sequence
+ char[] output = new char[input.length()];
+
+ // The length of the output can be less than the input
+ // due to discarded escape chars. This variable holds
+ // the actual length of the output
+ int length = 0;
+
+ // We remember whether the last processed character was
+ // an escape character
+ boolean lastCharWasEscapeChar = false;
+
+ // The multiplier the current unicode digit must be multiplied with.
+ // E. g. the first digit must be multiplied with 16^3, the second with 16^2...
+ int codePointMultiplier = 0;
+
+ // Used to calculate the codepoint of the escaped unicode character
+ int codePoint = 0;
+
+ for (int i = 0; i < input.length(); i++) {
+ char curChar = input.charAt(i);
+ if (codePointMultiplier > 0) {
+ codePoint += hexToInt(curChar) * codePointMultiplier;
+ codePointMultiplier >>>= 4;
+ if (codePointMultiplier == 0) {
+ output[length++] = (char)codePoint;
+ codePoint = 0;
+ }
+ } else if (lastCharWasEscapeChar) {
+ if (curChar == 'u') {
+ // found an escaped unicode character
+ codePointMultiplier = 16 * 16 * 16;
+ } else {
+ // this character was escaped
+ output[length] = curChar;
+ length++;
+ }
+ lastCharWasEscapeChar = false;
+ } else {
+ if (curChar == '\\') {
+ lastCharWasEscapeChar = true;
+ } else {
+ output[length] = curChar;
+ length++;
+ }
+ }
+ }
+
+ if (codePointMultiplier > 0) {
+ throw new ParseException("Truncated unicode escape sequence.");
+ }
+
+ if (lastCharWasEscapeChar) {
+ throw new ParseException("Term can not end with escape character.");
+ }
+
+ return new String(output, 0, length);
+ }
+
+ /** Returns the numeric value of the hexadecimal character */
+ static final int hexToInt(char c) throws ParseException {
+ if ('0' <= c && c <= '9') {
+ return c - '0';
+ } else if ('a' <= c && c <= 'f'){
+ return c - 'a' + 10;
+ } else if ('A' <= c && c <= 'F') {
+ return c - 'A' + 10;
+ } else {
+ throw new ParseException("None-hex character in unicode escape sequence: " + c);
+ }
+ }
+
+ /**
+ * Returns a String where those characters that QueryParser
+ * expects to be escaped are escaped by a preceding <code>\</code>.
+ */
+ public static String escape(String s) {
+ StringBuilder sb = new StringBuilder();
+ for (int i = 0; i < s.length(); i++) {
+ char c = s.charAt(i);
+ // These characters are part of the query syntax and must be escaped
+ if (c == '\\' || c == '+' || c == '-' || c == '!' || c == '(' || c == ')' || c == ':'
+ || c == '^' || c == '[' || c == ']' || c == '\"' || c == '{' || c == '}' || c == '~'
+ || c == '*' || c == '?' || c == '|' || c == '&') {
+ sb.append('\\');
+ }
+ sb.append(c);
+ }
+ return sb.toString();
+ }
+
+}
Modified: lucene/dev/branches/bulkpostings/lucene/src/java/org/apache/lucene/search/AutomatonQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/bulkpostings/lucene/src/java/org/apache/lucene/search/AutomatonQuery.java?rev=1068718&r1=1068717&r2=1068718&view=diff
==============================================================================
--- lucene/dev/branches/bulkpostings/lucene/src/java/org/apache/lucene/search/AutomatonQuery.java (original)
+++ lucene/dev/branches/bulkpostings/lucene/src/java/org/apache/lucene/search/AutomatonQuery.java Wed Feb 9 01:03:49 2011
@@ -22,11 +22,10 @@ import java.io.IOException;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.Terms;
import org.apache.lucene.index.TermsEnum;
+import org.apache.lucene.search.AutomatonTermsEnum.CompiledAutomaton;
import org.apache.lucene.util.ToStringUtils;
import org.apache.lucene.util.AttributeSource;
-import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.automaton.Automaton;
-import org.apache.lucene.util.automaton.ByteRunAutomaton;
import org.apache.lucene.util.automaton.BasicAutomata;
import org.apache.lucene.util.automaton.BasicOperations;
import org.apache.lucene.util.automaton.MinimizationOperations;
@@ -56,9 +55,16 @@ public class AutomatonQuery extends Mult
/** term containing the field, and possibly some pattern structure */
protected final Term term;
- transient ByteRunAutomaton runAutomaton;
- transient boolean isFinite;
- transient BytesRef commonSuffixRef;
+ /**
+ * abstraction for returning a termsenum:
+ * in the ctor the query computes one of these, the actual
+ * implementation depends upon the automaton's structure.
+ */
+ private abstract class TermsEnumFactory {
+ protected abstract TermsEnum getTermsEnum(Terms terms, AttributeSource atts) throws IOException;
+ }
+
+ private final TermsEnumFactory factory;
/**
* Create a new AutomatonQuery from an {@link Automaton}.
@@ -68,60 +74,77 @@ public class AutomatonQuery extends Mult
* @param automaton Automaton to run, terms that are accepted are considered a
* match.
*/
- public AutomatonQuery(Term term, Automaton automaton) {
+ public AutomatonQuery(final Term term, Automaton automaton) {
super(term.field());
this.term = term;
this.automaton = automaton;
MinimizationOperations.minimize(automaton);
- }
-
- private synchronized void compileAutomaton() {
- // this method must be synchronized, as setting the three transient fields is not atomic:
- if (runAutomaton == null) {
- runAutomaton = new ByteRunAutomaton(automaton);
- isFinite = SpecialOperations.isFinite(automaton);
- commonSuffixRef = isFinite ? null : SpecialOperations.getCommonSuffixBytesRef(runAutomaton.getAutomaton());
- }
- }
-
- @Override
- protected TermsEnum getTermsEnum(Terms terms, AttributeSource atts) throws IOException {
- // matches nothing
- if (BasicOperations.isEmpty(automaton)) {
- return TermsEnum.EMPTY;
- }
-
- TermsEnum tenum = terms.iterator();
- // matches all possible strings
- if (BasicOperations.isTotal(automaton)) {
- return tenum;
- }
-
- // matches a fixed string in singleton representation
- String singleton = automaton.getSingleton();
- if (singleton != null)
- return new SingleTermsEnum(tenum, term.createTerm(singleton));
-
- // matches a fixed string in expanded representation
- final String commonPrefix = SpecialOperations.getCommonPrefix(automaton);
-
- if (commonPrefix.length() > 0) {
- if (BasicOperations.sameLanguage(automaton, BasicAutomata.makeString(commonPrefix))) {
- return new SingleTermsEnum(tenum, term.createTerm(commonPrefix));
+ if (BasicOperations.isEmpty(automaton)) {
+ // matches nothing
+ factory = new TermsEnumFactory() {
+ @Override
+ protected TermsEnum getTermsEnum(Terms terms, AttributeSource atts) throws IOException {
+ return TermsEnum.EMPTY;
+ }
+ };
+ } else if (BasicOperations.isTotal(automaton)) {
+ // matches all possible strings
+ factory = new TermsEnumFactory() {
+ @Override
+ protected TermsEnum getTermsEnum(Terms terms, AttributeSource atts) throws IOException {
+ return terms.iterator();
+ }
+ };
+ } else {
+ final String singleton;
+ final String commonPrefix;
+
+ if (automaton.getSingleton() == null) {
+ commonPrefix = SpecialOperations.getCommonPrefix(automaton);
+ if (commonPrefix.length() > 0 && BasicOperations.sameLanguage(automaton, BasicAutomata.makeString(commonPrefix))) {
+ singleton = commonPrefix;
+ } else {
+ singleton = null;
+ }
+ } else {
+ commonPrefix = null;
+ singleton = automaton.getSingleton();
}
-
- // matches a constant prefix
- Automaton prefixAutomaton = BasicOperations.concatenate(BasicAutomata
- .makeString(commonPrefix), BasicAutomata.makeAnyString());
- if (BasicOperations.sameLanguage(automaton, prefixAutomaton)) {
- return new PrefixTermsEnum(tenum, term.createTerm(commonPrefix));
+
+ if (singleton != null) {
+ // matches a fixed string in singleton or expanded representation
+ factory = new TermsEnumFactory() {
+ @Override
+ protected TermsEnum getTermsEnum(Terms terms, AttributeSource atts) throws IOException {
+ return new SingleTermsEnum(terms.iterator(), term.createTerm(singleton));
+ }
+ };
+ } else if (BasicOperations.sameLanguage(automaton, BasicOperations.concatenate(
+ BasicAutomata.makeString(commonPrefix), BasicAutomata.makeAnyString()))) {
+ // matches a constant prefix
+ factory = new TermsEnumFactory() {
+ @Override
+ protected TermsEnum getTermsEnum(Terms terms, AttributeSource atts) throws IOException {
+ return new PrefixTermsEnum(terms.iterator(), term.createTerm(commonPrefix));
+ }
+ };
+ } else {
+ final AutomatonTermsEnum.CompiledAutomaton compiled =
+ new CompiledAutomaton(automaton, SpecialOperations.isFinite(automaton));
+ factory = new TermsEnumFactory() {
+ @Override
+ protected TermsEnum getTermsEnum(Terms terms, AttributeSource atts) throws IOException {
+ return new AutomatonTermsEnum(terms.iterator(), compiled);
+ }
+ };
}
}
+ }
- compileAutomaton();
-
- return new AutomatonTermsEnum(runAutomaton, tenum, isFinite, commonSuffixRef);
+ @Override
+ protected TermsEnum getTermsEnum(Terms terms, AttributeSource atts) throws IOException {
+ return factory.getTermsEnum(terms, atts);
}
@Override