package com.xjt.nlp.word;/** * <p>Title: Java中文分詞組件</p> * <p>Description: 本組件以中科院ICTCLAS系統為基礎，在其基礎之上改編，本組件僅供學習和研究用途，任何商業用途將自行承擔法律后果，與組件編寫人無關。</p> * <p>Copyright: Copyright (c) 2004</p> * <p>Company: 北京師范大學</p> * @author 陳天 * @version 1.0 */import java.util.LinkedList;import java.util.List;import java.util.Iterator;public class Sentence {    private List sentence = new LinkedList();    public Sentence() {    }    /**     * 得到某個詞匯     * @param index 第幾個詞匯     * @return 詞匯對象     */    public Word getWord(int index){        return (Word)sentence.get(index);    }    /**     * 得到一句話的詞匯數量     * @return 詞匯數量     */    public int totalWords(){        return sentence.size();    }    /**     * 在一句話的最后增加一個詞     * @param word 詞對象     */    public void addWord(Word word){        sentence.add(word);    }    /**     * 從一句話中去掉某個詞     * @param word     */    public void removeWord(Word word){        sentence.remove(word);    }    /**     * 從一句話中去掉某個詞     * @param index     */    public void removeWord(int index){        sentence.remove(index);    }    /**     * 合成一個完整的句子，不帶任何詞性標注     * @return     */    public String toSentence(){        StringBuffer buffer = new StringBuffer();        for (int i=0;i<sentence.size();i++){            Word word = (Word)sentence.get(i);            buffer.append(word.getWord());        }        return buffer.toString();    }    /**     * 合成一個帶詞性標注的句子     * @return     */    public String toString(){        StringBuffer buffer = new StringBuffer();        for (int i=0;i<sentence.size();i++){            Word word = (Word)sentence.get(i);            buffer.append(word.toString());        }        return buffer.toString();    }    /**     * 將句子中的若干個單詞和并     * @param startIndex 開始要合并的單詞的位置     * @param endIndex 最后一個要合并的單詞的位置     * @param newAttr 合并后的新詞性     */    public void mergeWord(int startIndex, int endIndex, String newAttr){        if (startIndex<0 || endIndex>=sentence.size())            throw new IllegalArgumentException("詞匯合并的開始位置和結束位置不正確");        if (startIndex>=endIndex)            throw new IllegalArgumentException("詞匯合并的開始位置不能大于或者等于結束位置");        Word startWord=(Word)sentence.get(startIndex);        for (int i=startIndex+1;i<=endIndex;i++){            Word word = (Word) sentence.get(startIndex+1);            startWord.setWord(startWord.getWord()+word.getWord());            sentence.remove(startIndex+1);        }        startWord.setAttribute(newAttr);    }    public static void main(String[] args) {        Sentence sentence=new Sentence();        Word word1 = new Word("中華","n");        Word word2 = new Word("人民","nr");        Word word3 = new Word("共和國","n");        sentence.addWord(word1);        sentence.addWord(word2);        sentence.addWord(word3);        sentence.removeWord(word2);        System.out.println(sentence.toSentence());        sentence.mergeWord(0,1,"nz");        System.out.println(sentence.toString());    }}