queryparser.jj

Lucene a java open-source SearchEngine Framework

/**
 * 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.
 */

options {
  STATIC=false;
  JAVA_UNICODE_ESCAPE=true;
  USER_CHAR_STREAM=true;
}

PARSER_BEGIN(QueryParser)

package org.apache.lucene.queryParser;

import java.util.Vector;
import java.io.*;
import java.text.*;
import java.util.*;
import org.apache.lucene.index.Term;
import org.apache.lucene.analysis.*;
import org.apache.lucene.document.*;
import org.apache.lucene.search.*;
import org.apache.lucene.util.Parameter;

/**
 * This class is generated by JavaCC.  The most important method 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 ::= ["+", "-"] [&lt;TERM&gt; ":"] ( &lt;TERM&gt; | "(" Query ")" )
 * </pre>
 *
 * <p>
 * Examples of appropriately formatted queries can be found in the <a
 * href="http://lucene.apache.org/java/docs/queryparsersyntax.html">query syntax
 * documentation</a>.
 * </p>
 *
 * <p>
 * In {@link RangeQuery}s, QueryParser tries to detect date values, e.g.
 * <tt>date:[6/1/2005 TO 6/4/2005]</tt> produces a range query that searches
 * for "date" fields between 2005-06-01 and 2005-06-04. Note that the format
 * of the accepted input depends on {@link #setLocale(Locale) the locale}.
 * By default a date is converted into a search term using the deprecated
 * {@link DateField} for compatibility reasons.
 * To use the new {@link DateTools} to convert dates, a
 * {@link org.apache.lucene.document.DateTools.Resolution} has to be set.
 * </p>
 * <p>
 * The date resolution that shall be used for RangeQueries can be set
 * using {@link #setDateResolution(DateTools.Resolution)}
 * or {@link #setDateResolution(String, DateTools.Resolution)}. The former
 * sets the default date resolution for all fields, whereas the latter can
 * be used to set field specific date resolutions. Field specific date
 * resolutions take, if set, precedence over the default date resolution.
 * </p>
 * <p>
 * If you use neither {@link DateField} nor {@link DateTools} in your
 * index, you can create your own
 * query parser that inherits QueryParser and overwrites
 * {@link #getRangeQuery(String, String, String, boolean)} to
 * use a different method for date conversion.
 * </p>
 *
 * <p>Note that QueryParser is <em>not</em> thread-safe.</p>
 *
 * @author Brian Goetz
 * @author Peter Halacsy
 * @author Tatu Saloranta
 */
public class QueryParser {

  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:
  /** 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 */
  private Operator operator = OR_OPERATOR;

  boolean lowercaseExpandedTerms = true;
  boolean useOldRangeQuery= false;  
  boolean allowLeadingWildcard = false;
  boolean enablePositionIncrements = false;

  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 fieldToDateResolution = null;

  /** The default operator for parsing queries. 
   * Use {@link QueryParser#setDefaultOperator} to change it.
   */
  static public final class Operator extends Parameter {
    private Operator(String name) {
      super(name);
    }
    static public final Operator OR = new Operator("OR");
    static public final Operator AND = new Operator("AND");
  }


  /** Constructs a query parser.
   *  @param f  the default field for query terms.
   *  @param a   used to find terms in the query text.
   */
  public QueryParser(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 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 : new BooleanQuery();
    }
    catch (ParseException tme) {
      // rethrow to include the original query:
      throw new ParseException("Cannot parse '" +query+ "': " + tme.getMessage());
    }
    catch (TokenMgrError tme) {
      throw new ParseException("Cannot parse '" +query+ "': " + tme.getMessage());
    }
    catch (BooleanQuery.TooManyClauses tmc) {
      throw new ParseException("Cannot parse '" +query+ "': 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;
  }


  /**
   * 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: false.
   */
  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 conjuction: 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 new ConstantScoreRangeQuery in preference to RangeQuery
   * for range queries. This implementation is generally preferable because it 
   * a) Runs faster b) Does not have the scarcity of range terms unduly influence score 
   * c) avoids any "TooManyBooleanClauses" exception.
   * However, if your application really needs to use the old-fashioned RangeQuery and the above
   * points are not required then set this option to <code>true</code>
   * Default is <code>false</code>.
   */
  public void setUseOldRangeQuery(boolean useOldRangeQuery) {
    this.useOldRangeQuery = useOldRangeQuery;
  }


  /**
   * @see #setUseOldRangeQuery(boolean)
   */
  public boolean getUseOldRangeQuery() {
    return useOldRangeQuery;
  }
  

  /**
   * 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, 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.");
    }