提取灵格斯里ld2格式词典的内容

• 作为一个NLPer，拥有越多文本相关的资源当然越好，词典资源就是其中之一，面对灵格斯里面那么多的词典，怎么提取出其中的内容是个问题，之前在网上搜了一些相关的信息，最终找到一个java代码通过该代码可以直接将灵格斯里.ld2格式的词典内容提取出来，具体的做法应该是根据.ld2的词典格式进行分析，从而得到其中的内容，
• 感谢“Copyright (c) 2010 Xiaoyun Zhu”和“@author keke”，提供了这么方便的接口！
• 使用中，我们需要更改final String ld2File = "D:\\kr.ld2";这一条，就可以变为处理自己希望的词典。

/*  Copyright (c) 2010 Xiaoyun Zhu
 * 
 *  Permission is hereby granted, free of charge, to any person obtaining a copy  
 *  of this software and associated documentation files (the "Software"), to deal  
 *  in the Software without restriction, including without limitation the rights  
 *  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell  
 *  copies of the Software, and to permit persons to whom the Software is  
 *  furnished to do so, subject to the following conditions:
 *  
 *  The above copyright notice and this permission notice shall be included in  
 *  all copies or substantial portions of the Software.
 *  
 *  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR  
 *  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,  
 *  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE  
 *  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER  
 *  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,  
 *  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN  
 *  THE SOFTWARE.  
 */

import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.io.RandomAccessFile;
import java.io.UnsupportedEncodingException;
import java.nio.ByteBuffer;
import java.nio.ByteOrder;
import java.nio.CharBuffer;
import java.nio.channels.FileChannel;
import java.nio.charset.CharacterCodingException;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CoderResult;
import java.nio.charset.CodingErrorAction;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.zip.Inflater;
import java.util.zip.InflaterInputStream;

/**
 * Lingoes LD2/LDF File Reader
 * 
 * <pre>
 * Lingoes Format overview:
 * 
 * General Information:
 * - Dictionary data are stored in deflate streams.
 * - Index group information is stored in an index array in the LD2 file itself.
 * - Numbers are using little endian byte order.
 * - Definitions and xml data have UTF-8 or UTF-16LE encodings.
 * 
 * LD2 file schema:
 * - File Header
 * - File Description
 * - Additional Information (optional)
 * - Index Group (corresponds to definitions in dictionary) 
 * - Deflated Dictionary Streams
 * -- Index Data
 * --- Offsets of definitions
 * --- Offsets of translations
 * --- Flags
 * --- References to other translations
 * -- Definitions
 * -- Translations (xml)
 * 
 * TODO: find encoding / language fields to replace auto-detect of encodings
 * 
 * </pre>
 * 
 * @author keke
 * 
 */
public class LingoesLd2Reader {
   
  private static final SensitiveStringDecoder[] AVAIL_ENCODINGS = { new SensitiveStringDecoder(Charset.forName("UTF-8")),
      new SensitiveStringDecoder(Charset.forName("UTF-16LE")), new SensitiveStringDecoder(Charset.forName("UTF-16BE")),
      new SensitiveStringDecoder(Charset.forName("EUC-JP"))    };

  public static void main(final String[] args) throws IOException {
    // download from
    // https://skydrive.live.com/?cid=a10100d37adc7ad3&sc=documents&id=A10100D37ADC7AD3%211172#cid=A10100D37ADC7AD3&sc=documents
    // String ld2File = Helper.DIR_IN_DICTS+"\\lingoes\\Prodic English-Vietnamese Business.ld2";
    final String ld2File = "D:\\kr.ld2";

    // read lingoes ld2 into byte array
    final ByteBuffer dataRawBytes;
    try (RandomAccessFile file = new RandomAccessFile(ld2File, "r"); final FileChannel fChannel = file.getChannel();) {
      dataRawBytes = ByteBuffer.allocate((int) fChannel.size());
      fChannel.read(dataRawBytes);
    }
    dataRawBytes.order(ByteOrder.LITTLE_ENDIAN);
    dataRawBytes.rewind();

    System.out.println("文件：" + ld2File);
    System.out.println("类型：" + new String(dataRawBytes.array(), 0, 4, "ASCII"));
    System.out.println("版本：" + dataRawBytes.getShort(0x18) + "." + dataRawBytes.getShort(0x1A));
    System.out.println("ID: 0x" + Long.toHexString(dataRawBytes.getLong(0x1C)));

    final int offsetData = dataRawBytes.getInt(0x5C) + 0x60;
    if (dataRawBytes.limit() > offsetData) {
      System.out.println("简介地址：0x" + Integer.toHexString(offsetData));
      fi