example.pp


001A 02012:18-04-12
001B 02012:04-05-12t16:13:28.000
001D 02012:31-08-98
001U 0utf8
001X 00
002@ 0Tuv1
003@ 0034034986
003U ahttp://d-nb.info/gnd/4510065-2
004B awit
007K agnd04510065-2
007N aswd04510065-2vzg
008A as
022@ aPraelectio in priora Aristotelis analyticavNUC pre 56
022@ aPraelectio in priora Aristotelis analytica, titulus LamiavNUC pre 56
022@ aPraelectio in analytica Aristotelis quae dicitur Lamia
022@ aPraelectio in Aristotelem, cui titulus est Lamia
022@ aIn priora analytica praelectio cui titulus est Lamia
022A aLamia
028R 90793881328Politianus, Angelus ; ID: gnd/1185955124aut1
042A a12.2pa6.1p
042B aXA-IT
050E aLUI, -GBV-AK gegen NUC pre 56
050H aPhilosophische Vorlesung, gehalten im November 1492


001A 02012:18-04-12
001B 02012:04-05-12t16:13:29.000
001D 02012:03-08-98
001U 0utf8
001X 00
002@ 0Tuv1
003@ 0034041737
003U ahttp://d-nb.info/gnd/4509532-2
004B awit
007K agnd04509532-2
007N aswd04509532-2vzg
008A as
022@ aSpeyrer Zeitungv1814-1816
022A aNeue Speyerer Zeitung
041R 91061088328Zeitung ; ID: gnd/4067510-54obin
042A a2.3
042B aXA-DE
050E aZDB
050H a1816-1853
065R 91047048618Deutschland ; ID: gnd/4011882-44geoa

gistfile1.txt

/*
 * This file is part of de.hab.diglib.
 *
 * de.hab.diglib 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 3 of the License, or
 * (at your option) any later version.
 *
 * de.hab.diglib 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 de.hab.diglib.  If not, see <http://www.gnu.org/licenses/>.
 */

package de.hab.diglib.batch.reader;

import org.springframework.batch.item.ItemReader;

import java.io.Reader;
import java.io.IOException;
import java.io.BufferedReader;

/**
 * Read PICA+ records from a VZG export file.
 *
 * In contrast to the common dumpfile format the VZG's format uses one
 * line per field and indicates records with a preceeding sequence of
 * 0x0A 0x1D.
 *
 * @author David Maus <[email protected]>
 */
public class PicaVzgDumpReader implements ItemReader<String>
{
    /**
     * Reader
     */
    private BufferedReader reader;

    /**
     * Constructor.
     */
    public PicaVzgDumpReader (Reader reader)
    {
        this.reader = new BufferedReader(reader);
    }

    @Override
    public String read () throws IOException
    {
        if (this.next()) {
            String field;
            StringBuilder record = new StringBuilder();
            do {
                field = this.reader.readLine();
                if (field != null) {
                    record.append(field);
                }
            } while (field != null && !field.isEmpty());
            return record.toString();
        }
        return null;
    }

    /**
     * Advance reader to next record.
     *
     * Returns TRUE if there is a next record, otherwise FALSE.
     *
     * Moves cursor until the reader is exhausted or the record
     * separator character (ASCII 0x1D) is found.
     */
    private boolean next () throws IOException
    {
        int octet;
        do {
            octet = this.reader.read();
        } while (octet != -1 && octet != 29);
        if (octet == 29) {
            this.reader.skip(1);
            return true;
        }
        return false;
    }
}