使用Pinyin4j怎么实现拼音分词？很多新手对此不是很清楚，为了帮助大家解决这个难题，下面小编将为大家详细讲解，有这方面需求的人可以来学习下，希望你能有所收获。
使用maven引入相关的jar
<dependency> <groupId>com.belerweb</groupId> <artifactId>pinyin4j</artifactId> <version>2.5.1</version></dependency>创建Pinyin4jUtil
package com.os.core.util.solr;import net.sourceforge.pinyin4j.PinyinHelper;import net.sourceforge.pinyin4j.format.HanyuPinyinCaseType;import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat;import net.sourceforge.pinyin4j.format.HanyuPinyinToneType;import net.sourceforge.pinyin4j.format.exception.BadHanyuPinyinOutputFormatCombination;import java.util.ArrayList;import java.util.Hashtable;import java.util.List;import java.util.Map;public class Pinyin4jUtil { public static void main(String[] args) { String str = "测试"; String pinyin = Pinyin4jUtil.converterToSpell(str); System.out.println(str + " pin yin ：" + pinyin); pinyin = Pinyin4jUtil.converterToFirstSpell(str); System.out.println(str + " short pin yin ：" + pinyin); } public static String converterToFirstSpell(String chines) { StringBuffer pinyinName = new StringBuffer(); char[] nameChar = chines.toCharArray(); HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat(); defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE); defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE); for (int i = 0; i < nameChar.length; i++) { if (nameChar[i] > 128) { try { // 取得当前汉字的所有全拼 String[] strs = PinyinHelper.toHanyuPinyinStringArray( nameChar[i], defaultFormat); if (strs != null) { for (int j = 0; j < strs.length; j++) { // 取首字母 pinyinName.append(strs[j].charAt(0)); if (j != strs.length - 1) { pinyinName.append(","); } } } // else { // pinyinName.append(nameChar[i]); // } } catch (BadHanyuPinyinOutputFormatCombination e) { e.printStackTrace(); } } else { pinyinName.append(nameChar[i]); } pinyinName.append(" "); } // return pinyinName.toString(); return parseTheChineseByObject(discountTheChinese(pinyinName.toString())); } public static String converterToSpell(String chines) { StringBuffer pinyinName = new StringBuffer(); char[] nameChar = chines.toCharArray(); HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat(); defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE); defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE); for (int i = 0; i < nameChar.length; i++) { if (nameChar[i] > 128) { try { // 取得当前汉字的所有全拼 String[] strs = PinyinHelper.toHanyuPinyinStringArray( nameChar[i], defaultFormat); if (strs != null) { for (int j = 0; j < strs.length; j++) { pinyinName.append(strs[j]); if (j != strs.length - 1) { pinyinName.append(","); } } } } catch (BadHanyuPinyinOutputFormatCombination e) { e.printStackTrace(); } } else { pinyinName.append(nameChar[i]); } pinyinName.append(" "); } // return pinyinName.toString(); return parseTheChineseByObject(discountTheChinese(pinyinName.toString())); } private static List<Map<String, Integer>> discountTheChinese(String theStr) { // 去除重复拼音后的拼音列表 List<Map<String, Integer>> mapList = new ArrayList<Map<String, Integer>>(); // 用于处理每个字的多音字，去掉重复 Map<String, Integer> onlyOne = null; String[] firsts = theStr.split(" "); // 读出每个汉字的拼音 for (String str : firsts) { onlyOne = new Hashtable<String, Integer>(); String[] china = str.split(","); // 多音字处理 for (String s : china) { Integer count = onlyOne.get(s); if (count == null) { onlyOne.put(s, new Integer(1)); } else { onlyOne.remove(s); count++; onlyOne.put(s, count); } } mapList.add(onlyOne); } return mapList; } private static String parseTheChineseByObject( List<Map<String, Integer>> list) { Map<String, Integer> first = null; // 用于统计每一次,集合组合数据 // 遍历每一组集合 for (int i = 0; i < list.size(); i++) { // 每一组集合与上一次组合的Map Map<String, Integer> temp = new Hashtable<String, Integer>(); // 第一次循环，first为空 if (first != null) { // 取出上次组合与此次集合的字符，并保存 for (String s : first.keySet()) { for (String s1 : list.get(i).keySet()) { String str = s + s1; temp.put(str, 1); } } // 清理上一次组合数据 if (temp != null && temp.size() > 0) { first.clear(); } } else { for (String s : list.get(i).keySet()) { String str = s; temp.put(str, 1); } } // 保存组合数据以便下次循环使用 if (temp != null && temp.size() > 0) { first = temp; } } String returnStr = ""; if (first != null) { // 遍历取出组合字符串 for (String str : first.keySet()) { returnStr += (str + ","); } } if (returnStr.length() > 0) { returnStr = returnStr.substring(0, returnStr.length() - 1); } return returnStr; }}看完上述内容是否对您有帮助呢？如果还想对相关知识有进一步的了解或阅读更多相关文章，请关注编程网行业资讯频道，感谢您对编程网的支持。
