analysis/java/JavaSymbolTokenizer.lex

	JavaSymbolTokenizer.lex revision 2b46c6c34fcb824c622e7da13c019de88e8474a7
/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * See LICENSE.txt included in this distribution for the specific
 * language governing permissions and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at LICENSE.txt.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */

/*
 * Copyright 2006 Sun Microsystems, Inc.  All rights reserved.
 * Use is subject to license terms.
 */

/*
 * Gets Java symbols - ignores comments, strings, keywords
 */

package org.opensolaris.opengrok.analysis.java;
import java.util.*;
import java.io.*;
import org.apache.lucene.analysis.*;

%%
%public
%class JavaSymbolTokenizer
%extends Tokenizer
%unicode
%function next
%type Token

%{
  public void close() {
  }

  public void reInit(char[] buf, int len) {
    yyreset((Reader) null);
    zzBuffer = buf;
    zzEndRead = len;
    zzAtEOF = true;
    zzStartRead = 0;
  }

  public static void main(String argv[]) {
    if (argv.length == 0) {
      System.out.println("Usage : java JavaSymbolTokenizer <inputfiles>");
    }
    else {
      Date start = new Date();
      for (String arg: argv) {
        JavaSymbolTokenizer scanner = null;
        try {
          scanner = new JavaSymbolTokenizer( new BufferedReader(new java.io.FileReader(arg)));
      Token t;
          while ((t = scanner.next()) != null) {
        System.out.println(t.termText() + " ["+t.startOffset()+"-"+ t.endOffset()+"]");
      }
        }
        catch (Exception e) {
          e.printStackTrace();
        }
    long span =  ((new Date()).getTime() - start.getTime());
    System.err.println("took: "+ span + " msec");
      }
    }
  }

%}
Identifier = [a-zA-Z_] [a-zA-Z0-9_]*

%state STRING COMMENT SCOMMENT QSTRING

%%

<YYINITIAL> {
{Identifier} {String id = yytext();
        if(!Consts.kwd.contains(id))
            return new Token(yytext(), zzStartRead, zzMarkedPos);}
 \" { yybegin(STRING); }
 \' { yybegin(QSTRING); }
 "/*"   { yybegin(COMMENT); }
 "//"   { yybegin(SCOMMENT); }
}

<STRING> {
 \" { yybegin(YYINITIAL); }
\\\\ | \\\" {}
}

<QSTRING> {
 \' { yybegin(YYINITIAL); }
}

<COMMENT> {
"*/"    { yybegin(YYINITIAL);}
}

<SCOMMENT> {
\n  { yybegin(YYINITIAL);}
}

<YYINITIAL, STRING, COMMENT, SCOMMENT, QSTRING> {
<<EOF>>   { return null;}
.|\n    {}
}