Laboratoire ICAR » Plateforme TXM

// Copyright © 2010-2013 ENS de Lyon.

// Copyright © 2007-2010 ENS de Lyon, CNRS, INRP, University of

// Lyon 2, University of Franche-Comté, University of Nice

// Sophia Antipolis, University of Paris 3.

//

// The TXM platform is free software: you can redistribute it

// and/or modify it under the terms of the GNU General Public

// License as published by the Free Software Foundation,

// either version 2 of the License, or (at your option) any

// later version.

//

// The TXM platform is distributed in the hope that it will be

// useful, but WITHOUT ANY WARRANTY; without even the implied

// warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR

// PURPOSE. See the GNU General Public License for more

// details.

//

// You should have received a copy of the GNU General

// Public License along with the TXM platform. If not, see

// http://www.gnu.org/licenses.

//

//

//

// $LastChangedDate:$

// $LastChangedRevision:$

// $LastChangedBy:$

//

package org.txm.scripts.filters.OneTagPerLine;

//Pre-processing extra-word tags (1)

import org.txm.importer.scripts.filters.*;

import java.util.regex.*;

import org.txm.tokenizer.TokenizerClasses;

// TODO: Auto-generated Javadoc

/**

 * The Class OneTagPerLine.

 */

class OneTagPerLine extends Filter {

        /** The tag_all. */

        String tag_all = TokenizerClasses.tag_all;

        /** The counterreg1. */

        int counterreg1 = 0;

        /** The counterreg2. */

        int counterreg2 = 0;

        /* (non-Javadoc)

         * @see org.txm.importer.filters.Filter#SetUsedParam(java.lang.Object)

         */

        void SetUsedParam(Object args) {

        }

        /* (non-Javadoc)

         * @see org.txm.importer.filters.Filter#before()

         */

        boolean before() {

        }

        /* (non-Javadoc)

         * @see org.txm.importer.filters.Filter#after()

         */

        void after() {

        }

        /* (non-Javadoc)

         * @see org.txm.importer.filters.Filter#filter()

         */

        void filter()

        {

                def m;

                boolean firstTest = true;

                while(!(line ==~ /\A\s*\Z/))

                {

                        if (( m = line =~ /^([^<]+)(.*)$/) )// trucs(<balise>

                        {

                                if(firstTest)

                                {

                                        output.write(lineSeparator);

                                        firstTest=false;

                                }

                                output.write(m[0][1]);

                                line = m[0][2];

                        }

                        else if ((m = line =~ /^($tag_all)(.*)$/)) {//

                                firstTest=false;

                                output.write("\n"+m[0][1]);

                                line = m[0][2];

                        }

                        else

                        {

                                println "Error in "+ line;

                                line = " ";

                        }

                }

                // End

        }

}