Comment extraction on 598948.xlsx

package org.apache.poi.xssf.usermodel;

import java.io.File;

import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Comment;
import org.apache.poi.ss.usermodel.Row;
import org.junit.Test;

public class TikaTest {

    @Test
    public void testme() throws Exception {
        int comm_cnt = 0;
        int comm_char_cnt = 0;
        int auth_cnt = 0;
        int auth_char_cnt = 0;

        XSSFWorkbook wb = new XSSFWorkbook(new File("598948.xlsx"));
        for (XSSFSheet s : wb) {
            for (Row r : s) {
                for (Cell c : r) {
                    Comment cm = c.getCellComment();
                    if (cm != null) {
                        comm_cnt++;
                        comm_char_cnt += cm.getString().getString().length();
                        String author = cm.getAuthor();
                        if (author != null) {
                            auth_cnt++;
                            auth_char_cnt += author.length();
                        }
                    }
                }
            }
        }
        wb.close();
        System.out.println(comm_cnt+" "+comm_char_cnt+" "+auth_cnt+" "+auth_char_cnt);
        // prints 103 17281 103 192
    }
}