基于ansj_seg和nlp-lang的简单nlp工具类
1、首先在pom中引入ansj_seg和nlp-lang的依赖包，
ansj_seg包的作用：
这是一个基于n-Gram+CRF+HMM的中文分词的java实现；
分词速度达到每秒钟大约200万字左右（mac air下测试），准确率能达到96%以上;
目前实现了.中文分词. 中文姓名识别 . 用户自定义词典,关键字提取，自动摘要，关键字标记等功能;
可以应用到自然语言处理等方面,适用于对分词效果要求高的各种项目;
nlp-lang包的作用(nlp常用工具和组件)：
工具：词语标准化、tire树结构、双数组tire树、文本断句、html标签清理、Viterbi算法增加；
组件：汉字转拼音、简繁体转换、bloomfilter、指纹去重、SimHash文章相似度计算、词贡献统计、基于内存的搜索提示、WordWeight词频统计,词idf统计,词类别相关度统计；
如下：
<!-- nlp-lang -->
<dependency>
<groupId>org.nlpcn</groupId>
<artifactId>nlp-lang</artifactId>
<version>1.7.2</version>
</dependency>
<!-- ansj_seg -->
<dependency>
<groupId>org.ansj</groupId>
<artifactId>ansj_seg</artifactId>
<version>5.1.2</version>
</dependency>
2、创建WordUtil类，如下：
package com.mengyao.nlp.util; import java.util.ArrayList; import java.util.Collection; import java.util.List; import java.util.Map; import java.util.Map.Entry; import org.ansj.app.keyword.KeyWordComputer; import org.ansj.app.keyword.Keyword; import org.ansj.app.summary.SummaryComputer; import org.ansj.app.summary.pojo.Summary; import org.ansj.domain.Result; import org.ansj.domain.Term; import org.ansj.splitWord.analysis.IndexAnalysis; import org.ansj.splitWord.analysis.NlpAnalysis; import org.ansj.splitWord.analysis.ToAnalysis; import org.apache.commons.lang3.StringUtils; import org.nlpcn.commons.lang.jianfan.JianFan; import org.nlpcn.commons.lang.pinyin.Pinyin; import org.nlpcn.commons.lang.util.WordAlert; import org.nlpcn.commons.lang.util.WordWeight;
/**
*
* @author mengyao
*
*/ public class WordUtil { public static void main(String[] args) { System.out.println("2016/06/25".matches("^\\d{4}(\\-|\\/|\\.)\\d{1,2}\\1\\d{1,2}$")); System.out.println("20160625".matches("^\\d{8}$")); } /** * 文章摘要 * @param title * @param content * @return */ public static String getSummary(String title, String content) { SummaryComputer summaryComputer = new SummaryComputer(title, content); Summary summary = summaryComputer.toSummary(); return summary.getSummary(); } /** * 带标题的文章关键词提取 * @param title * @param content * @return */ public static List<Keyword> getKeyWord(String title, String content) { List<Keyword> keyWords = new ArrayList<Keyword>(); KeyWordComputer<NlpAnalysis> kwc = new KeyWordComputer<NlpAnalysis>(20); Collection<Keyword> result = kwc.computeArticleTfidf(title, content); for (Keyword keyword : result) { keyWords.add(keyword); } return keyWords; } /** * 不带标题的文章关键词提取 * @param content * @return */ public static List<Keyword> getKeyWord2(String content) { List<Keyword> keyWords = new ArrayList<Keyword>(); KeyWordComputer<NlpAnalysis> kwc = new KeyWordComputer<NlpAnalysis>(20); Collection<Keyword> result = kwc.computeArticleTfidf(content); for (Keyword keyword : result) { keyWords.add(keyword); } return keyWords; } /** * 标准分词 * @param text * @return */ public static List<Term> getToSeg(String text) { List<Term> words = new ArrayList<Term>(); Result parse = ToAnalysis.parse(text); for (Term term : parse) { if (null!=term.getName()&&!term.getName().trim().isEmpty()) { words.add(term); } } return words; } /** * NLP分词 * @param text * @return */ public static List<Term> getNlpSeg(String text) { List<Term> words = new ArrayList<Term>(); Result parse = NlpAnalysis.parse(text); for (Term term : parse) { if (null!=term.getName()&&!term.getName().trim().isEmpty()) { words.add(term); } } return words; } /** * Index分词 * @param text * @return */ public static List<Term> getIndexSeg(String text) { List<Term> words = new ArrayList<Term>(); Result parse = IndexAnalysis.parse(text); for (Term term : parse) { if (null!=term.getName()&&!term.getName().trim().isEmpty()) { words.add(term); } } return words; } /** * 简体转繁体 * @param word * @return */ public static String jian2fan(String text) { return JianFan.j2f(text); } /** * 繁体转简体 * @param word * @return */ public static String fan2jian(String text) { return JianFan.f2j(text); } /** * 拼音(不带音标) * @param word * @return */ public static String pinyin(String text) { StringBuilder builder = new StringBuilder(); List<String> pinyins = Pinyin.pinyin(text); for (String pinyin : pinyins) { if (null != pinyin) { builder.append(pinyin+" "); } } return builder.toString(); } /** * 拼音(不带音标，首字母大写) * @param word * @return */ public static String pinyinUp(String text) { StringBuilder builder = new StringBuilder(); List<String> pinyins = Pinyin.pinyin(text); for (String pinyin : pinyins) { if (StringUtils.isEmpty(pinyin)) { continue; } builder.append(pinyin.substring(0,1).toUpperCase()+pinyin.substring(1)); } return builder.toString(); } /** * 拼音(带数字音标) * @param word * @return */ public static String tonePinyin(String text) { StringBuilder builder = new StringBuilder(); List<String> pinyins = Pinyin.tonePinyin(text); for (String pinyin : pinyins) { if (null != pinyin) { builder.append(pinyin+" "); } } return builder.toString(); } /** * 拼音(带符号音标) * @param word * @return */ public static String unicodePinyin(String text) { StringBuilder builder = new StringBuilder(); List<String> pinyins = Pinyin.unicodePinyin(text); for (String pinyin : pinyins) { if (null != pinyin) { builder.append(pinyin+" "); } } return builder.toString(); } /** * 词频统计 * @param words * @return */ public static Map<String, Double> wordCount(List<String> words) { WordWeight ww = new WordWeight(); for (String word : words) { ww.add(word); } return ww.export(); } /** * 词频统计 * @param words * @return */ public static List<String> wordCount1(List<String> words) { List<String> wcs = new ArrayList<String>(); WordWeight ww = new WordWeight(); for (String word : words) { ww.add(word); } Map<String, Double> export = ww.export(); for (Entry<String, Double> entry : export.entrySet()) { wcs.add(entry.getKey()+":"+entry.getValue()); } return wcs; } /** * 语种识别:1英文；0中文 * @param words * @return */ public static int language(String word) { return WordAlert.isEnglish(word)?1:0; } }
