queryparser.jj

Lucene a java open-source SearchEngine Framework

    if (fieldToDateResolution == null) {
      // lazily initialize HashMap
      fieldToDateResolution = new HashMap();
    }
    
    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 = (DateTools.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;
  }

  protected void addClause(Vector 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 = (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 = (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.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() != 0)
        positionCount += t.getPositionIncrement();
      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(true);
          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();
          mpq.setSlop(phraseSlop);          
          List multiTerms = new ArrayList();
          int position = -1;
          for (int i = 0; i < v.size(); i++) {
            t = (org.apache.lucene.analysis.Token) v.elementAt(i);
            if (t.getPositionIncrement() > 0 && multiTerms.size() > 0) {
              if (enablePositionIncrements) {
                mpq.add((Term[])multiTerms.toArray(new Term[0]),position);
              } else {
                mpq.add((Term[])multiTerms.toArray(new Term[0]));
              }
              multiTerms.clear();
            }
            position += t.getPositionIncrement();
            multiTerms.add(new Term(field, t.termText()));
          }
          if (enablePositionIncrements) {
            mpq.add((Term[])multiTerms.toArray(new Term[0]),position);
          } else {
            mpq.add((Term[])multiTerms.toArray(new Term[0]));
          }
          return mpq;
        }
      }
      else {
        PhraseQuery pq = new PhraseQuery();
        pq.setSlop(phraseSlop);
        int position = -1;
        for (int i = 0; i < v.size(); i++) {
          t = (org.apache.lucene.analysis.Token) v.elementAt(i);
          if (enablePositionIncrements) {
            position += t.getPositionIncrement();
            pq.add(new Term(field, t.termText()),position);
          } else {
            pq.add(new Term(field, t.termText()));
          }
        }
        return pq;
      }
    }
  }


  /**
   * 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);
      if (inclusive) {
        // 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();
      }
      DateTools.Resolution resolution = getDateResolution(field);
      if (resolution == null) {
        // no default or field specific date resolution has been set,
        // use deprecated DateField to maintain compatibilty with
        // pre-1.9 Lucene versions.
        part1 = DateField.dateToString(d1);
        part2 = DateField.dateToString(d2);
      } else {
        part1 = DateTools.dateToString(d1, resolution);
        part2 = DateTools.dateToString(d2, resolution);
      }
    }
    catch (Exception e) { }

    if(useOldRangeQuery)
    {
	    return new RangeQuery(new Term(field, part1),
                          new Term(field, part2),
                          inclusive);
    }
    else
    {
      return new ConstantScoreRangeQuery(field,part1,part2,inclusive,inclusive);
    }
  }

  /**
   * Factory method for generating query, given a set of clauses.
   * By default creates a boolean query composed of clauses passed in.
   *
   * Can be overridden by extending classes, to modify query being
   * returned.
   *
   * @param clauses Vector that contains {@link BooleanClause} instances
   *    to join.
   *
   * @return Resulting {@link Query} object.
   * @exception ParseException throw in overridden method to disallow
   */
  protected Query getBooleanQuery(Vector 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 Vector that contains {@link BooleanClause} instances
   *    to join.
   * @param disableCoord true if coord scoring should be disabled.
   *
   * @return Resulting {@link Query} object.
   * @exception ParseException throw in overridden method to disallow
   */
  protected Query getBooleanQuery(Vector clauses, boolean disableCoord)
    throws ParseException
  {
    if (clauses.size()==0) {
      return null; // all clause words were filtered away by the analyzer.
    }
    BooleanQuery query = new BooleanQuery(disableCoord);
    for (int i = 0; i < clauses.size(); i++) {
      query.add((BooleanClause)clauses.elementAt(i));
    }
    return query;
  }

  /**
   * Factory method for generating a query. Called when parser
   * parses an input term token that contains one or more wildcard
   * characters (? and *), but is not a prefix term token (one
   * that has just a single * character at the end)
   *<p>
   * Depending on settings, prefix term may be lower-cased
   * automatically. It will not go through the default Analyzer,
   * however, since normal Analyzers are unlikely to work properly
   * with wildcard templates.
   *<p>
   * Can be overridden by extending classes, to provide custom handling for
   * wildcard queries, which may be necessary due to missing analyzer calls.
   *
   * @param field Name of the field query will use.
   * @param termStr Term token that contains one or more wild card
   *   characters (? or *), but is not simple prefix term
   *
   * @return Resulting {@link Query} built for the term
   * @exception ParseException throw in overridden method to disallow
   */
  protected Query getWildcardQuery(String field, String termStr) throws ParseException
  {
    if ("*".equals(field)) {
      if ("*".equals(termStr)) return new MatchAllDocsQuery();
    }
    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 new WildcardQuery(t);
  }

  /**
   * Factory method for generating a query (similar to
   * {@link #getWildcardQuery}). Called when parser parses an input term
   * token that uses prefix notation; that is, contains a single '*' wildcard
   * character as its last character. Since this is a special case
   * of generic wildcard term, and such a query can be optimized easily,
   * this usually results in a different query object.
   *<p>
   * Depending on settings, a prefix term may be lower-cased
   * automatically. It will not go through the default Analyzer,
   * however, since normal Analyzers are unlikely to work properly
   * with wildcard templates.
   *<p>
   * Can be overridden by extending classes, to provide custom handling for
   * wild card queries, which may be necessary due to missing analyzer calls.
   *
   * @param field Name of the field query will use.
   * @param termStr Term token to use for building term for the query
   *    (<b>without</b> trailing '*' character!)
   *
   * @return Resulting {@link Query} built for the term
   * @exception ParseException throw in overridden method to disallow
   */
  protected Query getPrefixQuery(String field, String termStr) throws ParseException
  {
    if (!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 new PrefixQuery(t);
  }

  
   /**
   * Factory method for generating a query (similar to
   * {@link #getWildcardQuery}). Called when parser parses
   * an input term token that has the fuzzy suffix (~) appended.
   *
   * @param field Name of the field query will use.
   * @param termStr Term token to use for building term for the query
   *
   * @return Resulting {@link Query} built for the term
   * @exception ParseException throw in overridden method to disallow