queryparser.jjt

jsr170接口的java实现。是个apache的开源项目。

   * 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 (lowercaseWildcardTerms) {
  termStr = termStr.toLowerCase();
    }
    return new WildcardQuery(field, null, translateWildcards(termStr));
  }

  /**
   * 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
  {
    return getWildcardQuery(field, termStr + "*");
  }

  /**
   * 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) throws ParseException {
    return getFuzzyQuery(field, termStr, fuzzyMinSim);
  }

    /**
     * Translates unescaped wildcards '*' and '?' into '%' and '_'.
     *
     * @param input the input String.
     * @return the translated String.
     */
    private String translateWildcards(String input) {
        StringBuffer translated = new StringBuffer(input.length());
        boolean escaped = false;
        for (int i = 0; i < input.length(); i++) {
            if (input.charAt(i) == '\\') {
                if (escaped) {
                    translated.append("\\\\");
                    escaped = false;
                } else {
                    escaped = true;
                }
            } else if (input.charAt(i) == '*') {
                if (escaped) {
                    translated.append('*');
                    escaped = false;
                } else {
                    translated.append('%');
                }
            } else if (input.charAt(i) == '?') {
                if (escaped) {
                    translated.append('?');
                    escaped = false;
                } else {
                    translated.append('_');
                }
            } else if (input.charAt(i) == '%' || input.charAt(i) == '_') {
                // escape every occurrence of '%' and '_'
                escaped = false;
                translated.append('\\').append(input.charAt(i));
            } else {
                if (escaped) {
                    translated.append('\\');
                    escaped = false;
                }
                translated.append(input.charAt(i));
            }
        }
        return translated.toString();
    }

  /**
   * Factory method for generating a query (similar to
   * ({@link #getWildcardQuery}). Called when parser parses
   * an input term token that has the fuzzy suffix (~floatNumber) appended.
   *
   * @param field Name of the field query will use.
   * @param termStr Term token to use for building term for the query
   * @param minSimilarity the minimum similarity required for a fuzzy match
   *
   * @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
  {
    Term t = new Term(field, termStr);
    return new FuzzyQuery(t, minSimilarity);
  }

  /**
   * 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, i.e. preceded by a <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();
  }

  public static void main(String[] args) throws Exception {
    QueryParser qp = new QueryParser("field",
                           new org.apache.lucene.analysis.SimpleAnalyzer());
    Query q = qp.parse(args[0]);
    System.out.println(q.toString("field"));
  }
}

PARSER_END(QueryParser)

/* ***************** */
/* Token Definitions */
/* ***************** */

<*> TOKEN : {
  <#_NUM_CHAR:   ["0"-"9"] >
// NOTE: keep this in sync with escape(String) above!
| <#_ESCAPED_CHAR: "\\" [ "\\", "+", "-", "!", "(", ")", ":", "^",
                          "[", "]", "\"", "{", "}", "~", "*", "?" ] >
| <#_TERM_START_CHAR: ( ~[ " ", "\t", "\n", "\r", "+", "-", "!", "(", ")", ":", "^",
                           "[", "]", "\"", "{", "}", "~", "*", "?" ]
                       | <_ESCAPED_CHAR> ) >
| <#_TERM_CHAR: ( <_TERM_START_CHAR> | <_ESCAPED_CHAR> | "-" | "+" ) >
| <#_WHITESPACE: ( " " | "\t" | "\n" | "\r") >
}

<DEFAULT, RangeIn, RangeEx> SKIP : {
  < <_WHITESPACE>>
}

// OG: to support prefix queries:
// http://nagoya.apache.org/bugzilla/show_bug.cgi?id=12137
// Change from:
// | <WILDTERM:  <_TERM_START_CHAR>
//              (<_TERM_CHAR> | ( [ "*", "?" ] ))* >
// To:
//
// | <WILDTERM: (<_TERM_START_CHAR> | [ "*", "?" ]) (<_TERM_CHAR> | ( [ "*", "?" ] ))* >

<DEFAULT> TOKEN : {
  <AND:       ("AND" | "&&") >
| <OR:        ("OR" | "||") >
| <NOT:       ("NOT" | "!") >
| <PLUS:      "+" >
| <MINUS:     "-" >
| <LPAREN:    "(" >
| <RPAREN:    ")" >
| <COLON:     ":" >
| <CARAT:     "^" > : Boost
| <QUOTED:     "\"" (~["\""])+ "\"">
| <TERM:      <_TERM_START_CHAR> (<_TERM_CHAR>)*  >
| <FUZZY_SLOP:     "~" ( (<_NUM_CHAR>)+ ( "." (<_NUM_CHAR>)+ )? )? >
| <PREFIXTERM:  <_TERM_START_CHAR> (<_TERM_CHAR>)* "*" >
// support for prefix queries enabled!
| <WILDTERM: (<_TERM_START_CHAR> | [ "*", "?" ]) (<_TERM_CHAR> | ( [ "*", "?" ] ))* >
| <RANGEIN_START: "[" > : RangeIn
| <RANGEEX_START: "{" > : RangeEx
}

<Boost> TOKEN : {
<NUMBER:    (<_NUM_CHAR>)+ ( "." (<_NUM_CHAR>)+ )? > : DEFAULT
}

<RangeIn> TOKEN : {
<RANGEIN_TO: "TO">
| <RANGEIN_END: "]"> : DEFAULT
| <RANGEIN_QUOTED: "\"" (~["\""])+ "\"">
| <RANGEIN_GOOP: (~[ " ", "]" ])+ >
}

<RangeEx> TOKEN : {
<RANGEEX_TO: "TO">
| <RANGEEX_END: "}"> : DEFAULT
| <RANGEEX_QUOTED: "\"" (~["\""])+ "\"">
| <RANGEEX_GOOP: (~[ " ", "}" ])+ >
}

// *   Query  ::= ( Clause )*
// *   Clause ::= ["+", "-"] [<TERM> ":"] ( <TERM> | "(" Query ")" )

int Conjunction() : {
  int ret = CONJ_NONE;
}
{
  [
    <AND> { ret = CONJ_AND; }
    | <OR>  { ret = CONJ_OR; }
  ]
  { return ret; }
}

int Modifiers() : {
  int ret = MOD_NONE;
}
{
  [
     <PLUS> { ret = MOD_REQ; }
     | <MINUS> { ret = MOD_NOT; }
     | <NOT> { ret = MOD_NOT; }
  ]
  { return ret; }
}

Query Query(String field) :
{
  Vector clauses = new Vector();
  Query q, firstQuery=null;
  int conj, mods;
}
{
  mods=Modifiers() q=Clause(field)
  {
    addClause(clauses, CONJ_NONE, mods, q);
    if (mods == MOD_NONE)
        firstQuery=q;
  }
  (
    conj=Conjunction() mods=Modifiers() q=Clause(field)
    { addClause(clauses, conj, mods, q); }
  )*
    {
      if (clauses.size() == 1 && firstQuery != null)
        return firstQuery;
      else {
  return getBooleanQuery(clauses);
      }
    }
}

Query Clause(String field) : {
  Query q;
  Token fieldToken=null, boost=null;
}
{
  [
    LOOKAHEAD(2)
    fieldToken=<TERM> <COLON> {
      field=discardEscapeChar(fieldToken.image);
    }
  ]

  (
   q=Term(field)
   | <LPAREN> q=Query(field) <RPAREN> (<CARAT> boost=<NUMBER>)?

  )
    {
      if (boost != null) {
        float f = (float)1.0;
  try {
    f = Float.valueOf(boost.image).floatValue();
          q.setBoost(f);
  } catch (Exception ignored) { }
      }
      return q;
    }
}


Query Term(String field) : {
  Token term, boost=null, fuzzySlop=null, goop1, goop2;
  boolean prefix = false;
  boolean wildcard = false;
  boolean fuzzy = false;
  boolean rangein = false;
  Query q;
}
{
  (
     (
       term=<TERM>
       | term=<PREFIXTERM> { prefix=true; }
       | term=<WILDTERM> { wildcard=true; }
       | term=<NUMBER>
     )
     [ fuzzySlop=<FUZZY_SLOP> { fuzzy=true; } ]
     [ <CARAT> boost=<NUMBER> [ fuzzySlop=<FUZZY_SLOP> { fuzzy=true; } ] ]
     {
       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 {
            fms = Float.valueOf(fuzzySlop.image.substring(1)).floatValue();
       	  } catch (Exception ignored) { }
       	 if(fms < 0.0f || fms > 1.0f){
       	   throw new ParseException("Minimum similarity for a FuzzyQuery has to be between 0.0f and 1.0f !");
       	 }
       	 if(fms == fuzzyMinSim)
       	   q = getFuzzyQuery(field, termImage);
       	 else
           q = getFuzzyQuery(field, termImage, fms);
       } else {
         q = getFieldQuery(field, analyzer, termImage);
       }
     }
     | ( <RANGEIN_START> ( goop1=<RANGEIN_GOOP>|goop1=<RANGEIN_QUOTED> )
         [ <RANGEIN_TO> ] ( goop2=<RANGEIN_GOOP>|goop2=<RANGEIN_QUOTED> )
         <RANGEIN_END> )
       [ <CARAT> boost=<NUMBER> ]
        {
          if (goop1.kind == RANGEIN_QUOTED) {
            goop1.image = goop1.image.substring(1, goop1.image.length()-1);
          } else {
            goop1.image = discardEscapeChar(goop1.image);
          }
          if (goop2.kind == RANGEIN_QUOTED) {
            goop2.image = goop2.image.substring(1, goop2.image.length()-1);
      } else {
        goop2.image = discardEscapeChar(goop2.image);
      }
          q = getRangeQuery(field, analyzer, goop1.image, goop2.image, true);
        }
     | ( <RANGEEX_START> ( goop1=<RANGEEX_GOOP>|goop1=<RANGEEX_QUOTED> )
         [ <RANGEEX_TO> ] ( goop2=<RANGEEX_GOOP>|goop2=<RANGEEX_QUOTED> )
         <RANGEEX_END> )
       [ <CARAT> boost=<NUMBER> ]
        {
          if (goop1.kind == RANGEEX_QUOTED) {
            goop1.image = goop1.image.substring(1, goop1.image.length()-1);
          } else {
            goop1.image = discardEscapeChar(goop1.image);
          }
          if (goop2.kind == RANGEEX_QUOTED) {
            goop2.image = goop2.image.substring(1, goop2.image.length()-1);
      } else {
        goop2.image = discardEscapeChar(goop2.image);
      }

          q = getRangeQuery(field, analyzer, goop1.image, goop2.image, false);
        }
     | term=<QUOTED>
       [ fuzzySlop=<FUZZY_SLOP> ]
       [ <CARAT> boost=<NUMBER> ]
       {
         int s = phraseSlop;

         if (fuzzySlop != null) {
           try {
             s = Float.valueOf(fuzzySlop.image.substring(1)).intValue();
           }
           catch (Exception ignored) { }
         }
         q = getFieldQuery(field, analyzer, term.image.substring(1, term.image.length()-1), s);
       }
  )
  {
    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;
  }
}