利用hanlp比较文本相似度_hanlp 文本相似度

import com.hankcs.hanlp.seg.common.Term;
import com.hankcs.hanlp.tokenizer.StandardTokenizer;

import org.apache.commons.lang3.StringUtils;
import org.jsoup.Jsoup;
import org.jsoup.safety.Whitelist;

import java.math.BigInteger;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import static com.hankcs.hanlp.dictionary.stopword.CoreStopWordDictionary.*;
import static java.lang.Math.log;

public class MySimHash {
    private String tokens; //字符串
    private BigInteger strSimHash;//字符产的hash值
    private int hashbits = 64; // 分词后的hash数;
    public MySimHash(){

    }

    public MySimHash(String tokens) {
        this.tokens = tokens;
        this.strSimHash = this.simHash();
    }

    private MySimHash(String tokens, int hashbits) {
        this.tokens = tokens;
        this.hashbits = hashbits;
        this.strSimHash = this.simHash();
    }


    /**
     * 清除html标签
     * @param content
     * @return
     */
    private String cleanResume(String content) {
        // 若输入为HTML,下面会过滤掉所有的HTML的tag
        content = Jsoup.clean(content, Whitelist.none());
        content = StringUtils.lowerCase(content);
        String[] strings = {" ", "\n", "\r", "\t", "\\r", "\\n", "\\t", " "};
        for (String s : strings) {
            content = content.replaceAll(s, "");
        }
        return content;
    }


    /**
     * 这个是对整个字符串进行hash计算
     * @return
     */
    private BigInteger simHash() {

        tokens = cleanResume(tokens); // cleanResume 删除一些特殊字符

        int[] v = new int[this.hashbits];

        List<Term> termList = StandardTokenizer.segment(this.tokens); // 对字符串进行分词

        //对分词的一些特殊处理 : 比如: 根据词性添加权重 , 过滤掉标点符号 , 过滤超频词汇等;
        Map<String, Integer> weightOfNature = new HashMap<String, Integer>(); // 词性的权重
        weightOfNature.put("n", 2); //给名词的权重是2;
        Map<String, String> stopNatures = new HashMap<String, String>();//停用的词性 如一些标点符号之类的;
        stopNatures.put("w", ""); //
        int overCount = 5; //设定超频词汇的界限 ;
        Map<String, Integer> wordCount = new HashMap<String, Integer>();

        for (Term term : termList) {
            String word = term.word; //分词字符串

            String nature = term.nature.toString(); // 分词属性;
            //  过滤超频词
            if (wordCount.containsKey(word)) {
                int count = wordCount.get(word);
                if (count > overCount) {
                    continue;
                }
                wordCount.put(word, count + 1);
            } else {
                wordCount.put(word, 1);
            }

            // 过滤停用词性
            if (stopNatures.containsKey(nature)) {
                continue;
            }

            // 2、将每一个分词hash为一组固定长度的数列.比如 64bit 的一个整数.
            BigInteger t = this.hash(word);
            for (int i = 0; i < this.hashbits; i++) {
                BigInteger bitmask = new BigInteger("1").shiftLeft(i);
                // 3、建立一个长度为64的整数数组(假设要生成64位的数字指纹,也可以是其它数字),
                // 对每一个分词hash后的数列进行判断,如果是1000...1,那么数组的第一位和末尾一位加1,
                // 中间的62位减一,也就是说,逢1加1,逢0减1.一直到把所有的分词hash数列全部判断完毕.
                int weight = 1;  //添加权重
                if (weightOfNature.containsKey(nature)) {
                    weight = weightOfNature.get(nature);
                }
                if (t.and(bitmask).signum() != 0) {
                    // 这里是计算整个文档的所有特征的向量和
                    v[i] += weight;
                } else {
                    v[i] -= weight;
                }
            }
        }
        BigInteger fingerprint = new BigInteger("0");
        for (int i = 0; i < this.hashbits; i++) {
            if (v[i] >= 0) {
                fingerprint = fingerprint.add(new BigInteger("1").shiftLeft(i));
            }
        }
        return fingerprint;
    }


    /**
     * 对单个的分词进行hash计算;
     * @param source
     * @return
     */
    private BigInteger hash(String source) {
        if (source == null || source.length() == 0) {
            return new BigInteger("0");
        } else {
            /**
             * 当sourece 的长度过短，会导致hash算法失效，因此需要对过短的词补偿
             */
            while (source.length() < 3) {
                source = source + source.charAt(0);
            }
            char[] sourceArray = source.toCharArray();
            BigInteger x = BigInteger.valueOf(((long) sourceArray[0]) << 7);
            BigInteger m = new BigInteger("1000003");
            BigInteger mask = new BigInteger("2").pow(this.hashbits).subtract(new BigInteger("1"));
            for (char item : sourceArray) {
                BigInteger temp = BigInteger.valueOf((long) item);
                x = x.multiply(m).xor(temp).and(mask);
            }
            x = x.xor(new BigInteger(String.valueOf(source.length())));
            if (x.equals(new BigInteger("-1"))) {
                x = new BigInteger("-2");
            }
            return x;
        }
    }

    /**
     * 计算海明距离,海明距离越小说明越相似;
     * @param other
     * @return
     */
    private int hammingDistance(MySimHash other) {
        BigInteger m = new BigInteger("1").shiftLeft(this.hashbits).subtract(
                new BigInteger("1"));
        BigInteger x = this.strSimHash.xor(other.strSimHash).and(m);
        int tot = 0;
        while (x.signum() != 0) {
            tot += 1;
            x = x.and(x.subtract(new BigInteger("1")));
        }
        return tot;
    }


    public double getSemblance(MySimHash s2 ){
        double i = (double) this.hammingDistance(s2);
        return 1 - i/this.hashbits ;
    }

    public List<Term> getSegList(String sen){
        List<Term> termList = StandardTokenizer.segment(sen);
        return termList;
    }
    public double getSimiliarity(String s1,String s2){
//        for (String retval: s1.split("，")){
//            System.out.println(retval);
//            s1 = retval;
//            break;
//        }
//        for (String retval: s2.split("、")){
//            System.out.println(retval);
//            s2 = retval;
//            break;
//        }
        System.out.println(s1);
        System.out.println(s2);
        List ls1 = getSegList(s1);
        List ls2 = getSegList(s2);

        double count =0;
        double similarity;
        for(int i=0;i<ls1.size();i++){
            List ls3 = ls2.subList(0,ls1.size());
//            System.out.println("ls3:"+ls3);
           if (ls3.contains(ls1.get(i))){
               count +=1;
            }
        }
        System.out.println("count:"+count);
        System.out.println("length:"+ls1.size()+"+"+ls2.size());
//        similarity= count/(Math.log(ls1.size())+Math.log(ls2.size()));
        similarity = count/(ls1.size());
        return similarity;
    }

    public static void main(String[] args) {
        String s1 = "风电装机大幅下降";
        String s2 = "产品价格竞争加剧";
        String s3 = "下游需求不及预期，产能进度不及预期";
        String s4 = "下游需求低于预期，价格战恶化，核心器件自产率提升进度不及预期";
        long l1 = System.currentTimeMillis();

        MySimHash test = new MySimHash();
        System.out.println(test.getSimiliarity(s3,s4));

        long l2 = System.currentTimeMillis();
        System.out.println(l2-l1);
        System.out.println("======================================");





    }
}
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232

import com.hankcs.hanlp.HanLP;
import com.hankcs.hanlp.dictionary.CustomDictionary;
import org.jsoup.Jsoup;

import java.util.ArrayList;
import java.util.Calendar;
import java.util.Collections;
import java.util.List;
import java.util.stream.Collectors;

public class SimilarityUtil {
    static {
        CustomDictionary.add("子类");
        CustomDictionary.add("父类");
    }

    private SimilarityUtil() {
    }

    /**
     * 获得两个句子的相似度
     *
     * @param sentence1
     * @param sentence2
     * @return
     */
    public static double getSimilarity(String sentence1, String sentence2) {
        List<String> sent1Words = getSplitWords(sentence1);
        System.out.println(sent1Words);
        List<String> sent2Words = getSplitWords(sentence2);
        System.out.println(sent2Words);
        List<String> allWords = mergeList(sent1Words, sent2Words);

        int[] statistic1 = statistic(allWords, sent1Words);
        int[] statistic2 = statistic(allWords, sent2Words);

        double dividend = 0;
        double divisor1 = 0;
        double divisor2 = 0;
        for (int i = 0; i < statistic1.length; i++) {
            dividend += statistic1[i] * statistic2[i];
            divisor1 += Math.pow(statistic1[i], 2);
            divisor2 += Math.pow(statistic2[i], 2);
        }

        return dividend / (Math.sqrt(divisor1) * Math.sqrt(divisor2));
    }

    private static int[] statistic(List<String> allWords, List<String> sentWords) {
        int[] result = new int[allWords.size()];
        for (int i = 0; i < allWords.size(); i++) {
            result[i] = Collections.frequency(sentWords, allWords.get(i));
        }
        return result;
    }

    private static List<String> mergeList(List<String> list1, List<String> list2) {
        List<String> result = new ArrayList<>();
        result.addAll(list1);
        result.addAll(list2);
        return result.stream().distinct().collect(Collectors.toList());
    }

    private static List<String> getSplitWords(String sentence) {
        // 去除掉html标签
        sentence = Jsoup.parse(sentence.replace("&nbsp;","")).body().text();
        // 标点符号会被单独分为一个Term，去除之
        return HanLP.segment(sentence).stream().map(a -> a.word).filter(s -> !"`~!@#$^&*()=|{}':;',\\[\\].<>/?~！@#￥……&*（）——|{}【】‘；：”“'。，、？ ".contains(s)).collect(Collectors.toList());
    }
}
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70