precedencequeryparser.java

lucene2.2.0版本

/* Generated By:JavaCC: Do not edit this line. PrecedenceQueryParser.java */
package org.apache.lucene.queryParser.precedence;

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;

/**
 * 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 ::= ["+", "-"] [&lt;TERM&gt; ":"] ( &lt;TERM&gt; | "(" Query ")" )
 * </pre>
 *
 * <p>
 * Examples of appropriately formatted queries can be found in the <a
 * href="http://jakarta.apache.org/lucene/docs/queryparsersyntax.html">query syntax
 * documentation</a>.
 * </p>
 *
 * @author Brian Goetz
 * @author Peter Halacsy
 * @author Tatu Saloranta
 */

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 final class Operator extends Parameter {
    private Operator(String name) {
      super(name);
    }
    static final Operator OR = new Operator("OR");
    static 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 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 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;
  }

  /**
   * 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(Vector 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 = (BooleanClause) clauses.elementAt(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 = (BooleanClause) clauses.elementAt(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.addElement(new BooleanClause(q, BooleanClause.Occur.MUST));
    else if (!required && !prohibited)
      clauses.addElement(new BooleanClause(q, BooleanClause.Occur.SHOULD));
    else if (!required && prohibited)
      clauses.addElement(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)  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));
    Vector v = new Vector();
    org.apache.lucene.analysis.Token t;
    int positionCount = 0;
    boolean severalTokensAtSamePosition = false;

    while (true) {
      try {
        t = source.next();
      }
      catch (IOException e) {
        t = null;
      }
      if (t == null)
        break;
      v.addElement(t);
      if (t.getPositionIncrement() == 1)
        positionCount++;
      else
        severalTokensAtSamePosition = true;
    }
    try {
      source.close();
    }
    catch (IOException e) {
      // ignore
    }

    if (v.size() == 0)
      return null;
    else if (v.size() == 1) {
      t = (org.apache.lucene.analysis.Token) v.elementAt(0);
      return new TermQuery(new Term(field, t.termText()));
    } else {
      if (severalTokensAtSamePosition) {
        if (positionCount == 1) {
          // no phrase query:
          BooleanQuery q = new BooleanQuery();
          for (int i = 0; i < v.size(); i++) {
            t = (org.apache.lucene.analysis.Token) v.elementAt(i);
            TermQuery currentQuery = new TermQuery(
                new Term(field, t.termText()));
            q.add(currentQuery, BooleanClause.Occur.SHOULD);
          }
          return q;
        }
        else {
          // phrase query:
          MultiPhraseQuery mpq = new MultiPhraseQuery();
          List multiTerms = new ArrayList();
          for (int i = 0; i < v.size(); i++) {
            t = (org.apache.lucene.analysis.Token) v.elementAt(i);
            if (t.getPositionIncrement() == 1 && multiTerms.size() > 0) {
              mpq.add((Term[])multiTerms.toArray(new Term[0]));
              multiTerms.clear();
            }
            multiTerms.add(new Term(field, t.termText()));
          }
          mpq.add((Term[])multiTerms.toArray(new Term[0]));
          return mpq;
        }
      }
      else {
        PhraseQuery q = new PhraseQuery();
        q.setSlop(phraseSlop);
        for (int i = 0; i < v.size(); i++) {
          q.add(new Term(field, ((org.apache.lucene.analysis.Token)
              v.elementAt(i)).termText()));

        }
        return q;
      }
    }
  }

  /**
   * Base implementation delegates to {@link #getFieldQuery(String,String)}.
   * 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);

    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 RangeQuery(new Term(field, part1),
                          new Term(field, part2),
                          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 Vector that contains {@link BooleanClause} instances
   *    to join.
   *
   * @return Resulting {@link Query} object.