precedencequeryparser.java

lucene2.2.0版本

   * @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 == null || clauses.size() == 0)
      return null;

    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 (lowercaseExpandedTerms) {
      termStr = termStr.toLowerCase();
    }
    Term t = new Term(field, termStr);
    return new WildcardQuery(t);
  }

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

   /**
   * Factory method for generating a query (similar to
   * {@link #getWildcardQuery}). Called when parser parses
   * an input term token that has the fuzzy suffix (~) appended.
   *
   * @param field Name of the field query will use.
   * @param termStr Term token to use for building term for the query
   *
   * @return Resulting {@link Query} built for the term
   * @exception ParseException throw in overridden method to disallow
   */
  protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws ParseException
  {
    if (lowercaseExpandedTerms) {
      termStr = termStr.toLowerCase();
    }
    Term t = new Term(field, termStr);
    return new FuzzyQuery(t, minSimilarity, fuzzyPrefixLength);
  }

  /**
   * Returns a String where the escape char has been
   * removed, or kept only once if there was a double escape.
   */
  private String discardEscapeChar(String input) {
    char[] caSource = input.toCharArray();
    char[] caDest = new char[caSource.length];
    int j = 0;
    for (int i = 0; i < caSource.length; i++) {
      if ((caSource[i] != '\\') || (i > 0 && caSource[i-1] == '\\')) {
        caDest[j++]=caSource[i];
      }
    }
    return new String(caDest, 0, j);
  }

  /**
   * 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) {
    StringBuffer sb = new StringBuffer();
    for (int i = 0; i < s.length(); i++) {
      char c = s.charAt(i);
      // NOTE: keep this in sync with _ESCAPED_CHAR below!
      if (c == '\\' || c == '+' || c == '-' || c == '!' || c == '(' || c == ')' || c == ':'
        || c == '^' || c == '[' || c == ']' || c == '\"' || c == '{' || c == '}' || c == '~'
        || c == '*' || c == '?') {
        sb.append('\\');
      }
      sb.append(c);
    }
    return sb.toString();
  }

  /**
   * Command line tool to test QueryParser, using {@link org.apache.lucene.analysis.SimpleAnalyzer}.
   * Usage:<br>
   * <code>java org.apache.lucene.queryParser.QueryParser &lt;input&gt;</code>
   */
  public static void main(String[] args) throws Exception {
    if (args.length == 0) {
      System.out.println("Usage: java org.apache.lucene.queryParser.QueryParser <input>");
      System.exit(0);
    }
    PrecedenceQueryParser qp = new PrecedenceQueryParser("field",
                           new org.apache.lucene.analysis.SimpleAnalyzer());
    Query q = qp.parse(args[0]);
    System.out.println(q.toString("field"));
  }

// *   Query  ::= ( Clause )*
// *   Clause ::= ["+", "-"] [<TERM> ":"] ( <TERM> | "(" Query ")" )
  final public int Conjunction() throws ParseException {
  int ret = CONJ_NONE;
    switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
    case AND:
    case OR:
      switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
      case AND:
        jj_consume_token(AND);
            ret = CONJ_AND;
        break;
      case OR:
        jj_consume_token(OR);
              ret = CONJ_OR;
        break;
      default:
        jj_la1[0] = jj_gen;
        jj_consume_token(-1);
        throw new ParseException();
      }
      break;
    default:
      jj_la1[1] = jj_gen;
      ;
    }
    {if (true) return ret;}
    throw new Error("Missing return statement in function");
  }

  final public int Modifier() throws ParseException {
  int ret = MOD_NONE;
    switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
    case NOT:
    case PLUS:
    case MINUS:
      switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
      case PLUS:
        jj_consume_token(PLUS);
              ret = MOD_REQ;
        break;
      case MINUS:
        jj_consume_token(MINUS);
                 ret = MOD_NOT;
        break;
      case NOT:
        jj_consume_token(NOT);
               ret = MOD_NOT;
        break;
      default:
        jj_la1[2] = jj_gen;
        jj_consume_token(-1);
        throw new ParseException();
      }
      break;
    default:
      jj_la1[3] = jj_gen;
      ;
    }
    {if (true) return ret;}
    throw new Error("Missing return statement in function");
  }

  final public Query Query(String field) throws ParseException {
  Vector clauses = new Vector();
  Query q, firstQuery=null;
  boolean orPresent = false;
  int modifier;
    modifier = Modifier();
    q = andExpression(field);
    addClause(clauses, CONJ_NONE, modifier, q);
    if (modifier == MOD_NONE)
      firstQuery = q;
    label_1:
    while (true) {
      switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
      case OR:
      case NOT:
      case PLUS:
      case MINUS:
      case LPAREN:
      case QUOTED:
      case TERM:
      case PREFIXTERM:
      case WILDTERM:
      case RANGEIN_START:
      case RANGEEX_START:
      case NUMBER:
        ;
        break;
      default:
        jj_la1[4] = jj_gen;
        break label_1;
      }
      switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
      case OR:
        jj_consume_token(OR);
            orPresent=true;
        break;
      default:
        jj_la1[5] = jj_gen;
        ;
      }
      modifier = Modifier();
      q = andExpression(field);
      addClause(clauses, orPresent ? CONJ_OR : CONJ_NONE, modifier, q);
    }
      if (clauses.size() == 1 && firstQuery != null)
        {if (true) return firstQuery;}
      else {
        {if (true) return getBooleanQuery(clauses);}
      }
    throw new Error("Missing return statement in function");
  }

  final public Query andExpression(String field) throws ParseException {
  Vector clauses = new Vector();
  Query q, firstQuery=null;
  int modifier;
    q = Clause(field);
    addClause(clauses, CONJ_NONE, MOD_NONE, q);
    firstQuery = q;
    label_2:
    while (true) {
      switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
      case AND:
        ;
        break;
      default:
        jj_la1[6] = jj_gen;
        break label_2;
      }
      jj_consume_token(AND);
      modifier = Modifier();
      q = Clause(field);
      addClause(clauses, CONJ_AND, modifier, q);
    }
      if (clauses.size() == 1 && firstQuery != null)
        {if (true) return firstQuery;}
      else {
        {if (true) return getBooleanQuery(clauses);}
      }
    throw new Error("Missing return statement in function");
  }

  final public Query Clause(String field) throws ParseException {
  Query q;
  Token fieldToken=null, boost=null;
    if (jj_2_1(2)) {
      fieldToken = jj_consume_token(TERM);
      jj_consume_token(COLON);
      field=discardEscapeChar(fieldToken.image);
    } else {
      ;
    }
    switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
    case QUOTED:
    case TERM:
    case PREFIXTERM:
    case WILDTERM:
    case RANGEIN_START:
    case RANGEEX_START:
    case NUMBER:
      q = Term(field);
      break;
    case LPAREN:
      jj_consume_token(LPAREN);
      q = Query(field);
      jj_consume_token(RPAREN);
      switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
      case CARAT:
        jj_consume_token(CARAT);
        boost = jj_consume_token(NUMBER);
        break;
      default:
        jj_la1[7] = jj_gen;
        ;
      }
      break;
    default:
      jj_la1[8] = jj_gen;
      jj_consume_token(-1);
      throw new ParseException();
    }
      if (boost != null) {
        float f = (float)1.0;
  try {
    f = Float.valueOf(boost.image).floatValue();
          q.setBoost(f);
  } catch (Exception ignored) { }
      }
      {if (true) return q;}
    throw new Error("Missing return statement in function");
  }

  final public Query Term(String field) throws ParseException {
  Token term, boost=null, fuzzySlop=null, goop1, goop2;
  boolean prefix = false;
  boolean wildcard = false;
  boolean fuzzy = false;
  Query q;
    switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
    case TERM:
    case PREFIXTERM:
    case WILDTERM:
    case NUMBER:
      switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
      case TERM:
        term = jj_consume_token(TERM);
        break;
      case PREFIXTERM:
        term = jj_consume_token(PREFIXTERM);
                             prefix=true;
        break;
      case WILDTERM:
        term = jj_consume_token(WILDTERM);
                           wildcard=true;
        break;
      case NUMBER:
        term = jj_consume_token(NUMBER);
        break;
      default:
        jj_la1[9] = jj_gen;
        jj_consume_token(-1);
        throw new ParseException();
      }
      switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
      case FUZZY_SLOP:
        fuzzySlop = jj_consume_token(FUZZY_SLOP);
                                fuzzy=true;
        break;
      default:
        jj_la1[10] = jj_gen;
        ;
      }
      switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
      case CARAT:
        jj_consume_token(CARAT);
        boost = jj_consume_token(NUMBER);
        switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {
        case FUZZY_SLOP:
          fuzzySlop = jj_consume_token(FUZZY_SLOP);
                                                         fuzzy=true;
          break;
        default:
          jj_la1[11] = jj_gen;
          ;
        }
        break;
      default:
        jj_la1[12] = jj_gen;
        ;
      }
       String termImage=discardEscapeChar(term.image);
       if (wildcard) {
       q = getWildcardQuery(field, termImage);
       } else if (prefix) {
         q = getPrefixQuery(field,
           discardEscapeChar(term.image.substring
          (0, term.image.length()-1)));
       } else if (fuzzy) {
          float fms = fuzzyMinSim;
          try {