├── README.md
├── pom.xml
└── src
    ├── main
        └── java
        │   └── cm
        │       └── eg
        │           ├── model
        │               ├── Article.java
        │               ├── CompareReport.java
        │               ├── CompareTask.java
        │               └── WordFreq.java
        │           └── util
        │               └── TextUtil.java
    └── test
        ├── java
            └── cm
            │   └── eg
            │       ├── DocTest.java
            │       ├── ProcessTest.java
            │       └── SegmentTest.java
        └── resource
            ├── doc
                ├── Li_info1.doc
                ├── Li_info2.doc
                ├── Li_info3.doc
                ├── Li_info4.doc
                ├── Wu_info1.doc
                ├── Wu_info2.doc
                ├── Wu_info3.doc
                └── Wu_info4.doc
            └── txt
                └── 小王子.txt


/README.md:
--------------------------------------------------------------------------------
1 | # HanLP-TextSimilarity
2 | 
3 | 中文分词、统计词频、比对文本相似度
4 | 
5 | 使用了汉语言处理包HanLP (https://github.com/hankcs/HanLP)
6 | 
7 | 2017.4.18
8 | 


--------------------------------------------------------------------------------
/pom.xml:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="UTF-8"?>
 2 | <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 3 | 	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
 4 | 	<modelVersion>4.0.0</modelVersion>
 5 | 
 6 | 	<groupId>cm.eg</groupId>
 7 | 	<artifactId>text-similarity</artifactId>
 8 | 	<version>0.0.2</version>
 9 | 
10 | 	<dependencies>
11 | 
12 | 		<dependency>
13 | 			<groupId>com.hankcs</groupId>
14 | 			<artifactId>hanlp</artifactId>
15 | 			<version>portable-1.7.3</version>
16 | 		</dependency>
17 | 
18 | 		<dependency>
19 | 			<groupId>com.google.guava</groupId>
20 | 			<artifactId>guava</artifactId>
21 | 			<version>27.1-jre</version>
22 | 		</dependency>
23 | 
24 | 		<dependency>
25 | 			<groupId>org.apache.tika</groupId>
26 | 			<artifactId>tika-core</artifactId>
27 | 			<version>1.20</version>
28 | 		</dependency>
29 | 
30 | 		<dependency>
31 | 			<groupId>org.apache.tika</groupId>
32 | 			<artifactId>tika-parsers</artifactId>
33 | 			<version>1.20</version>
34 | 			<exclusions>
35 | 				<exclusion>
36 | 					<groupId>org.apache.poi</groupId>
37 | 					<artifactId>poi-ooxml-schemas</artifactId>
38 | 				</exclusion>
39 | 			</exclusions>
40 | 		</dependency>
41 | 
42 | 		<dependency>
43 | 			<groupId>org.apache.poi</groupId>
44 | 			<artifactId>ooxml-schemas</artifactId>
45 | 			<version>1.3</version>
46 | 		</dependency>
47 | 
48 | 		<dependency>
49 | 			<groupId>org.apache.poi</groupId>
50 | 			<artifactId>ooxml-security</artifactId>
51 | 			<version>1.1</version>
52 | 		</dependency>
53 | 
54 | 		<dependency>
55 | 			<groupId>junit</groupId>
56 | 			<artifactId>junit</artifactId>
57 | 			<version>4.12</version>
58 | 		</dependency>
59 | 
60 | 	</dependencies>
61 | </project>


--------------------------------------------------------------------------------
/src/main/java/cm/eg/model/Article.java:
--------------------------------------------------------------------------------
 1 | package cm.eg.model;
 2 | 
 3 | import java.util.List;
 4 | 
 5 | import com.hankcs.hanlp.seg.common.Term;
 6 | 
 7 | public class Article {
 8 | 	private String name;
 9 | 
10 | 	private String text;
11 | 
12 | 	private List<Term> segmentList;
13 | 	private List<WordFreq> wordFreqList;
14 | 
15 | 	public List<Term> getSegmentList() {
16 | 		return segmentList;
17 | 	}
18 | 
19 | 	public void setSegmentList(List<Term> segmentList) {
20 | 		this.segmentList = segmentList;
21 | 	}
22 | 
23 | 	public String getName() {
24 | 		return name;
25 | 	}
26 | 
27 | 	public void setName(String name) {
28 | 		this.name = name;
29 | 	}
30 | 
31 | 	public String getText() {
32 | 		return text;
33 | 	}
34 | 
35 | 	public List<WordFreq> getWordFreqList() {
36 | 		return wordFreqList;
37 | 	}
38 | 
39 | 	public void setText(String text) {
40 | 		this.text = text;
41 | 	}
42 | 
43 | 	public void setWordFreqList(List<WordFreq> wordFreqList) {
44 | 		this.wordFreqList = wordFreqList;
45 | 	}
46 | 
47 | }
48 | 


--------------------------------------------------------------------------------
/src/main/java/cm/eg/model/CompareReport.java:
--------------------------------------------------------------------------------
 1 | package cm.eg.model;
 2 | 
 3 | /**
 4 |  * 文本相似度的对比报告。
 5 |  */
 6 | public class CompareReport {
 7 | 	private Article a1;
 8 | 	private Article a2;
 9 | 
10 | 	private int top;
11 | 
12 | 	private double similarity;
13 | 
14 | 	public CompareReport(Article a1, Article a2, int top, double similarity) {
15 | 		this.a1 = a1;
16 | 		this.a2 = a2;
17 | 		this.top = top;
18 | 		this.similarity = similarity;
19 | 	}
20 | 
21 | 	@Override
22 | 
23 | 	/**
24 | 	 * 返回比较结果的简单报告。
25 | 	 * 可调用getDetail()方法获得详细报告。
26 | 	 */
27 | 	public String toString() {
28 | 		return String.format("%s和%s 相似度：%.0f%%", a1.getName(), a2.getName(), similarity*100);
29 | 	}
30 | 
31 | 	public String getConsoleDetail() {
32 | 		StringBuilder sb = new StringBuilder();
33 | 		String ls = System.lineSeparator();
34 | 		sb.append(a1.getName() +" 长度："+a1.getText().length() +" 高频词：");
35 | 		sb.append(ls);
36 | 		sb.append(a1.getWordFreqList().subList(0, top));
37 | 		sb.append(ls);
38 | 		sb.append(a2.getName() +" 长度："+a2.getText().length() + " 高频词：");
39 | 		sb.append(ls);
40 | 		sb.append(a2.getWordFreqList().subList(0, top));
41 | 		sb.append(ls);
42 | 		sb.append("相似度：" + String.format("%.4f",similarity));
43 | 		return sb.toString();
44 | 	}
45 | }
46 | 


--------------------------------------------------------------------------------
/src/main/java/cm/eg/model/CompareTask.java:
--------------------------------------------------------------------------------
 1 | package cm.eg.model;
 2 | 
 3 | import java.util.ArrayList;
 4 | import java.util.Comparator;
 5 | import java.util.List;
 6 | 
 7 | /**
 8 |  * 用于表示比较两篇文章的任务。<br/>
 9 |  * 设置了任务状态；可查看比较的结果。
10 |  */
11 | public class CompareTask {
12 | 
13 | 	private Article a1;
14 | 	private Article a2;
15 | 
16 | 	private boolean isFinished;
17 | 
18 | 	private CompareReport compareReport;
19 | 
20 | 	// 取高频词前若干位
21 | 	private static final int TOP_MAX = 20;
22 | 
23 | 	public CompareTask(Article a1, Article a2) {
24 | 		this.a1 = a1;
25 | 		this.a2 = a2;
26 | 		this.isFinished = false;
27 | 	}
28 | 
29 | 	public void execute() {
30 | 		// 取高频词前若干位
31 | 		int top = TOP_MAX;
32 | 		List<WordFreq> freq1 = a1.getWordFreqList().subList(0, top);
33 | 		List<WordFreq> freq2 = a2.getWordFreqList().subList(0, top);
34 | 		// 获取高频词并集
35 | 		ArrayList<WordFreq> union = new ArrayList<>(freq1);
36 | 		union.addAll(freq2);
37 | 		// 生成向量
38 | 		ArrayList<WordFreq> v1 = new ArrayList<>(freq1);
39 | 		ArrayList<WordFreq> v2 = new ArrayList<>(freq2);
40 | 		for (WordFreq wf : union) {
41 | 			// 向量包含了高频词并集里的每个词，如果不包含则词频为0
42 | 			if (!v1.contains(wf)) {
43 | 				v1.add(new WordFreq(wf.getWord(), 0));
44 | 			}
45 | 			if (!v2.contains(wf)) {
46 | 				v2.add(new WordFreq(wf.getWord(), 0));
47 | 			}
48 | 		}
49 | 		// 根据词语排序以对齐向量，方便计算
50 | 		Comparator<WordFreq> strComp = Comparator.comparing(WordFreq::getWord);
51 | 		v1.sort(strComp);
52 | 		v2.sort(strComp);
53 | 		/**
54 | 		 * 代入公式
55 | 		 */
56 | 		double vProduct = 0;
57 | 		int sumSquare1 = 0;
58 | 		int sumSquare2 = 0;
59 | 		for (int i = 0; i < v1.size(); ++i) {
60 | 			int num1 = v1.get(i).getFreq();
61 | 			int num2 = v2.get(i).getFreq();
62 | 			// 向量点积
63 | 			vProduct += num1 * num2;
64 | 			// 求向量模的过程
65 | 			sumSquare1 += num1 * num1;
66 | 			sumSquare2 += num2 * num2;
67 | 		}
68 | 		// 两向量模的乘积
69 | 		double normProduct = Math.sqrt(sumSquare1 * sumSquare2);
70 | 		// 点积除以模乘积
71 | 		double similarity = vProduct / normProduct;
72 | 		// 标记完成状态
73 | 		isFinished = true;
74 | 		makeReport(a1, a2, similarity);
75 | 	}
76 | 
77 | 	private void makeReport(Article a1, Article a2, double similarity) {
78 | 		compareReport = new CompareReport(a1, a2, TOP_MAX, similarity);
79 | 
80 | 	}
81 | 
82 | 	public boolean isFinished() {
83 | 		return isFinished;
84 | 	}
85 | 
86 | 	public CompareReport getCompareReport() {
87 | 		return compareReport;
88 | 	}
89 | 
90 | }
91 | 


--------------------------------------------------------------------------------
/src/main/java/cm/eg/model/WordFreq.java:
--------------------------------------------------------------------------------
 1 | package cm.eg.model;
 2 | 
 3 | /**
 4 |  * 词频。
 5 |  */
 6 | public class WordFreq {
 7 | 
 8 | 	private String word;
 9 | 	private int freq;
10 | 
11 | 	public WordFreq(String word, int freq) {
12 | 		this.word = word;
13 | 		this.freq = freq;
14 | 	}
15 | 
16 | 	public String getWord() {
17 | 		return word;
18 | 	}
19 | 
20 | 	public int getFreq() {
21 | 		return freq;
22 | 	}
23 | 
24 | 	public void setWord(String word) {
25 | 		this.word = word;
26 | 	}
27 | 
28 | 	public void setFreq(int freq) {
29 | 		this.freq = freq;
30 | 	}
31 | 
32 | 	@Override
33 | 	public String toString() {
34 | 		return "[" + word + " : " + freq + "]";
35 | 	}
36 | 
37 | 	@Override
38 | 	public boolean equals(Object obj) {
39 | 		WordFreq wf = (WordFreq) obj;
40 | 		return this.getWord().equals(wf.getWord());
41 | 	}
42 | }
43 | 


--------------------------------------------------------------------------------
/src/main/java/cm/eg/util/TextUtil.java:
--------------------------------------------------------------------------------
  1 | package cm.eg.util;
  2 | 
  3 | import cm.eg.model.Article;
  4 | import cm.eg.model.WordFreq;
  5 | import com.google.common.collect.HashMultiset;
  6 | import com.google.common.collect.Multiset;
  7 | import com.google.common.collect.Multiset.Entry;
  8 | import com.hankcs.hanlp.HanLP;
  9 | import com.hankcs.hanlp.corpus.tag.Nature;
 10 | import com.hankcs.hanlp.seg.common.Term;
 11 | import org.apache.tika.Tika;
 12 | import org.apache.tika.exception.TikaException;
 13 | 
 14 | import java.io.File;
 15 | import java.io.IOException;
 16 | import java.util.ArrayList;
 17 | import java.util.List;
 18 | import java.util.function.Predicate;
 19 | 
 20 | public class TextUtil {
 21 | 
 22 | 	/**
 23 | 	 * 从文件中获取数据，封装成对象。会将词频排序，在多个任务的情况下性能得到优化
 24 | 	 * 
 25 | 	 * @param file
 26 | 	 */
 27 | 	public static Article getArticle(File file) throws IOException, TikaException {
 28 | 		String text = getString(file);
 29 | 		List<Term> segmentList = getSegmentList(text);
 30 | 		List<WordFreq> wordFreqList = getWordFrequency(segmentList);
 31 | 		// 词频从高到低排序
 32 | 		wordFreqList.sort((a, b) -> Integer.compare(b.getFreq(), a.getFreq()));
 33 | 
 34 | 		// 封装Article
 35 | 		Article article = new Article();
 36 | 		article.setName(file.getName());
 37 | 		article.setText(text);
 38 | 		article.setSegmentList(segmentList);
 39 | 		article.setWordFreqList(wordFreqList);
 40 | 		return article;
 41 | 	}
 42 | 
 43 | 	/**
 44 | 	 * 从指定文件读取一整个字符串
 45 | 	 * 
 46 | 	 * @param file
 47 | 	 */
 48 | 	private static String getString(File file) throws IOException, TikaException {
 49 | 		Tika tika = new Tika();
 50 | 		tika.setMaxStringLength((int) file.length());
 51 | 		String str = tika.parseToString(file);
 52 | 		return str;
 53 | 	}
 54 | 
 55 | 	/**
 56 | 	 * 将输入的字符串分词处理。
 57 | 	 * 
 58 | 	 * @param text 文本
 59 | 	 * @return 切分后的单词
 60 | 	 */
 61 | 	private static List<Term> getSegmentList(String text) {
 62 | 		List<Term> segmentList = HanLP.segment(text);
 63 | 		// 过滤器
 64 | 		segmentList.removeIf(new Predicate<Term>() {
 65 | 			/**
 66 | 			 * 过滤掉：长度为1的分词、标点符号
 67 | 			 */
 68 | 			public boolean test(Term term) {
 69 | 				boolean flag = false;
 70 | 				// 长度
 71 | 				String real = term.word.trim();
 72 | 				if (real.length() <= 1) {
 73 | 					flag = true;
 74 | 				}
 75 | 				// 类型
 76 | 				// 词性以w开头的，为各种标点符号
 77 | 				if (term.nature.startsWith('w')) {
 78 | 					flag = true;
 79 | 				}
 80 | 				// 过滤掉代码
 81 | 				if (term.nature.equals(Nature.nx)) {// 字母专名
 82 | 					flag = true;
 83 | 				}
 84 | 				return flag;
 85 | 			}
 86 | 		});
 87 | 		return segmentList;
 88 | 	}
 89 | 
 90 | 	/**
 91 | 	 * 根据分词集合统计词频
 92 | 	 * @param segmentList 词频集合
 93 | 	 */
 94 | 	public static List<WordFreq> getWordFrequency(List<Term> segmentList) {
 95 | 		// 统计词频
 96 | 		Multiset<String> wordSet = HashMultiset.create();
 97 | 		for (Term term : segmentList) {// 放入词汇集合
 98 | 			wordSet.add(term.word);
 99 | 		}
100 | 		// 从词汇集合取出单词和频次,放入词频集合
101 | 		List<WordFreq> wfList = new ArrayList<>();
102 | 		for (Entry<String> entry : wordSet.entrySet()) {
103 | 			wfList.add(new WordFreq(entry.getElement(), entry.getCount()));
104 | 		}
105 | 		return wfList;
106 | 	}
107 | 
108 | 	/**
109 | 	 * 最长公共子串。
110 | 	 */
111 | 	public static String getLCString(String string1, String string2) {
112 | 		int len1, len2;
113 | 		char[] str1 = string1.toCharArray();
114 | 		char[] str2 = string2.toCharArray();
115 | 
116 | 		len1 = str1.length;
117 | 		len2 = str2.length;
118 | 		int maxLen = len1 > len2 ? len1 : len2;
119 | 
120 | 		int[] max = new int[maxLen];// 保存最长子串长度的数组
121 | 		int[] maxIndex = new int[maxLen];// 保存最长子串长度最大索引的数组
122 | 		int[] c = new int[maxLen];
123 | 
124 | 		int i, j;
125 | 		for (i = 0; i < len2; i++) {
126 | 			for (j = len1 - 1; j >= 0; j--) {
127 | 				if (str2[i] == str1[j]) {
128 | 					if ((i == 0) || (j == 0))
129 | 						c[j] = 1;
130 | 					else
131 | 						c[j] = c[j - 1] + 1;// 此时C[j-1]还是上次循环中的值，因为还没被重新赋值
132 | 				} else {
133 | 					c[j] = 0;
134 | 				}
135 | 
136 | 				// 如果是大于那暂时只有一个是最长的,而且要把后面的清0
137 | 				if (c[j] > max[0]) {
138 | 					max[0] = c[j];
139 | 					maxIndex[0] = j;
140 | 
141 | 					for (int k = 1; k < maxLen; k++) {
142 | 						max[k] = 0;
143 | 						maxIndex[k] = 0;
144 | 					}
145 | 				}
146 | 				// 有多个是相同长度的子串
147 | 				else if (c[j] == max[0]) {
148 | 					for (int k = 1; k < maxLen; k++) {
149 | 						if (max[k] == 0) {
150 | 							max[k] = c[j];
151 | 							maxIndex[k] = j;
152 | 							break;
153 | 						}
154 | 					}
155 | 				}
156 | 			}
157 | 		}
158 | 		// 最长子字符串
159 | 		StringBuilder lcs = new StringBuilder();
160 | 		for (j = 0; j < maxLen; j++) {
161 | 			if (max[j] > 0) {
162 | 				for (i = maxIndex[j] - max[j] + 1; i <= maxIndex[j]; i++)
163 | 					lcs.append((str1[i]));
164 | 			}
165 | 		}
166 | 		return lcs.toString();
167 | 	}
168 | }
169 | 


--------------------------------------------------------------------------------
/src/test/java/cm/eg/DocTest.java:
--------------------------------------------------------------------------------
 1 | package cm.eg;
 2 | import java.io.File;
 3 | import java.io.IOException;
 4 | 
 5 | import org.apache.tika.Tika;
 6 | import org.apache.tika.exception.TikaException;
 7 | import org.junit.Test;
 8 | import org.xml.sax.SAXException;
 9 | 
10 | /**
11 |  * 处理文档测试。
12 |  */
13 | public class DocTest {
14 | 
15 | 	private static String docDir = "doc/";
16 | 
17 | 	@Test
18 | 	public void demo1() throws TikaException, IOException, SAXException {
19 | 		File file = new File(docDir + "Wu_info1.doc");
20 | 		System.out.println("length:" + file.length());
21 | 
22 | 		Tika tika = new Tika();
23 | 		System.out.println("tika detect():" + tika.detect(file));
24 | 		String text = tika.parseToString(file);
25 | 
26 | 		System.out.println("file string length:" + text.length());
27 | 	}
28 | 	
29 | }
30 | 


--------------------------------------------------------------------------------
/src/test/java/cm/eg/ProcessTest.java:
--------------------------------------------------------------------------------
  1 | package cm.eg;
  2 | 
  3 | import java.io.File;
  4 | import java.io.IOException;
  5 | import java.util.ArrayList;
  6 | import java.util.List;
  7 | 
  8 | import cm.eg.model.Article;
  9 | import cm.eg.model.CompareReport;
 10 | import cm.eg.model.CompareTask;
 11 | import cm.eg.model.WordFreq;
 12 | import cm.eg.util.TextUtil;
 13 | 
 14 | import org.apache.tika.exception.TikaException;
 15 | import org.junit.Test;
 16 | 
 17 | import com.hankcs.hanlp.seg.common.Term;
 18 | 
 19 | /**
 20 |  * 文本相似度处理测试。
 21 |  */
 22 | public class ProcessTest {
 23 | 
 24 | 	private static String docDir = "doc/";
 25 | 
 26 | 	private static String txtDir = "txt/";
 27 | 
 28 | 	/**
 29 | 	 * 显示词频最高的若干项
 30 | 	 */
 31 | 	@Test
 32 | 	public void demo1() throws IOException, TikaException {
 33 | 		Article article = TextUtil.getArticle(new File(txtDir + "小王子.txt"));
 34 | 		List<WordFreq> wfList = article.getWordFreqList();
 35 | 
 36 | 		System.out.println("高频词排名:");
 37 | 		for (int i = 0; i < 50; ++i) {
 38 | 			System.out.println(wfList.get(i));
 39 | 		}
 40 | 	}
 41 | 
 42 | 
 43 | 	/**
 44 | 	 * 向量相似度算法
 45 | 	 */
 46 | 	@Test
 47 | 	public void demo2() throws IOException, TikaException {
 48 | 		// TODO 涉及读写可用多线程FutureTask优化。
 49 | 		Article a1 = TextUtil.getArticle(new File(docDir + "Li_info2.doc"));
 50 | 		Article a2 = TextUtil.getArticle(new File(docDir + "Wu_info2.doc"));
 51 | 		CompareTask task = new CompareTask(a1, a2);
 52 | 		task.execute();
 53 | 		CompareReport report = task.getCompareReport();
 54 | 		System.out.println(report);
 55 | 	}
 56 | 
 57 | 
 58 | 	/**
 59 | 	 * 报告多个测试
 60 | 	 */
 61 | 	@Test
 62 | 	public void demo3() throws IOException, TikaException {
 63 | 		List<CompareTask> tasks = new ArrayList<CompareTask>();
 64 | 
 65 | 		Article a1 = TextUtil.getArticle(new File(docDir + "Wu_info1.doc"));
 66 | 		Article b1 = TextUtil.getArticle(new File(docDir + "Li_info1.doc"));
 67 | 		tasks.add(new CompareTask(a1, b1));
 68 | 		System.out.println("load 1");
 69 | 
 70 | 		Article a2 = TextUtil.getArticle(new File(docDir + "Wu_info2.doc"));
 71 | 		Article b2 = TextUtil.getArticle(new File(docDir + "Li_info2.doc"));
 72 | 		tasks.add(new CompareTask(a2, b2));
 73 | 		System.out.println("load 2");
 74 | 
 75 | 		Article a3 = TextUtil.getArticle(new File(docDir + "Wu_info3.doc"));
 76 | 		Article b3 = TextUtil.getArticle(new File(docDir + "Li_info3.doc"));
 77 | 		tasks.add(new CompareTask(a3, b3));
 78 | 		System.out.println("load 3");
 79 | 
 80 | 		Article a4 = TextUtil.getArticle(new File(docDir + "Wu_info4.doc"));
 81 | 		Article b4 = TextUtil.getArticle(new File(docDir + "Li_info4.doc"));
 82 | 		tasks.add(new CompareTask(a4, b4));
 83 | 		System.out.println("load 4");
 84 | 
 85 | 		for (CompareTask task : tasks) {
 86 | 			task.execute();
 87 | 			System.out.println(task.getCompareReport().getConsoleDetail());
 88 | 			System.out.println();
 89 | 		}
 90 | 	}
 91 | 
 92 | 
 93 | 	/**
 94 | 	 * 公共子序列
 95 | 	 */
 96 | 	@Test
 97 | 	public void demo4() throws IOException, TikaException {
 98 | 		// 获得分词后的一整串字符
 99 | 		Article a1 = TextUtil.getArticle(new File(docDir + "Wu_info3.doc"));
100 | 		Article a2 = TextUtil.getArticle(new File(docDir + "Li_info1.doc"));
101 | 		List<Term> termList1 = a1.getSegmentList();
102 | 		List<Term> termList2 = a2.getSegmentList();
103 | 		StringBuilder segStr1 = new StringBuilder();
104 | 		StringBuilder segStr2 = new StringBuilder();
105 | 
106 | 		for (Term term : termList1) {
107 | 			segStr1.append(term.word);
108 | 		}
109 | 		for (Term term : termList2) {
110 | 			segStr2.append(term.word);
111 | 		}
112 | 		// 最长公共子序列
113 | 		String lcs = "";
114 | 		String str1 = segStr1.toString();
115 | 		String str2 = segStr2.toString();
116 | 
117 | 		for (int i = 1; i <= 5; ++i) {
118 | 			if (i != 1) {
119 | 				str1 = str1.replaceAll(lcs, "");
120 | 				str2 = str2.replaceAll(lcs, "");
121 | 			}
122 | 			lcs = TextUtil.getLCString(str1, str2);
123 | 			System.out.println("第" + i + "个最长公共子序列（长度" + lcs.length() + "）：");
124 | 			System.out.println(lcs);
125 | 			System.out.println();
126 | 		}
127 | 	}
128 | 
129 | }
130 | 


--------------------------------------------------------------------------------
/src/test/java/cm/eg/SegmentTest.java:
--------------------------------------------------------------------------------
 1 | package cm.eg;
 2 | 
 3 | import com.hankcs.hanlp.HanLP;
 4 | import com.hankcs.hanlp.seg.common.Term;
 5 | import com.hankcs.hanlp.tokenizer.StandardTokenizer;
 6 | import org.junit.Test;
 7 | 
 8 | import java.util.List;
 9 | 
10 | /**
11 |  * 分词测试。
12 |  */
13 | public class SegmentTest {
14 | 
15 | 	/**
16 | 	 * 标准分词器。
17 | 	 * 推荐使用这种HanLP静态调用的方式。
18 | 	 */
19 | 	@Test
20 | 	public void demo1() {
21 | 		List<Term> list = HanLP.segment("你好，欢迎使用HanLP汉语处理包！");
22 | 		for (Term term : list) {
23 | 			System.out.println(term.word + " " + term.nature);
24 | 		}
25 | 	}
26 | 
27 | 	/**
28 | 	 * 标准分词
29 | 	 */
30 | 	@Test
31 | 	public void demo2() {
32 | 		List<Term> termList = StandardTokenizer.segment("商品和服务");
33 | 		System.out.println(termList);
34 | 	}
35 | 
36 | 
37 | }
38 | 


--------------------------------------------------------------------------------
/src/test/resource/doc/Li_info1.doc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/mokou591/HanLP-TextSimilarity/7a25b858124bca2accb19b5ab0e08428e29ee82c/src/test/resource/doc/Li_info1.doc


--------------------------------------------------------------------------------
/src/test/resource/doc/Li_info2.doc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/mokou591/HanLP-TextSimilarity/7a25b858124bca2accb19b5ab0e08428e29ee82c/src/test/resource/doc/Li_info2.doc


--------------------------------------------------------------------------------
/src/test/resource/doc/Li_info3.doc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/mokou591/HanLP-TextSimilarity/7a25b858124bca2accb19b5ab0e08428e29ee82c/src/test/resource/doc/Li_info3.doc


--------------------------------------------------------------------------------
/src/test/resource/doc/Li_info4.doc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/mokou591/HanLP-TextSimilarity/7a25b858124bca2accb19b5ab0e08428e29ee82c/src/test/resource/doc/Li_info4.doc


--------------------------------------------------------------------------------
/src/test/resource/doc/Wu_info1.doc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/mokou591/HanLP-TextSimilarity/7a25b858124bca2accb19b5ab0e08428e29ee82c/src/test/resource/doc/Wu_info1.doc


--------------------------------------------------------------------------------
/src/test/resource/doc/Wu_info2.doc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/mokou591/HanLP-TextSimilarity/7a25b858124bca2accb19b5ab0e08428e29ee82c/src/test/resource/doc/Wu_info2.doc


--------------------------------------------------------------------------------
/src/test/resource/doc/Wu_info3.doc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/mokou591/HanLP-TextSimilarity/7a25b858124bca2accb19b5ab0e08428e29ee82c/src/test/resource/doc/Wu_info3.doc


--------------------------------------------------------------------------------
/src/test/resource/doc/Wu_info4.doc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/mokou591/HanLP-TextSimilarity/7a25b858124bca2accb19b5ab0e08428e29ee82c/src/test/resource/doc/Wu_info4.doc


--------------------------------------------------------------------------------
/src/test/resource/txt/小王子.txt:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/mokou591/HanLP-TextSimilarity/7a25b858124bca2accb19b5ab0e08428e29ee82c/src/test/resource/txt/小王子.txt


--------------------------------------------------------------------------------