简介:
pinyin4j是一个开源的流行java库(官网地址:http://pinyin4j./,在线文档:http://pinyin4j./pinyin4j-doc/ ),使用来处理中文转换成拼音(汉语拼音,罗马拼音等),功能强大。 有几个常用的类: net.sourceforge.pinyin4j.PinyinHelper; net.sourceforge.pinyin4j.format.HanyuPinyinCaseType; net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat; net.sourceforge.pinyin4j.format.HanyuPinyinToneType; net.sourceforge.pinyin4j.format.HanyuPinyinVCharType; PinyinHelper:提供了几个实用程序函数,用于将中文字符(简体和繁体)转换为各种中文罗马化表示。 HanyuPinyinOutputFormat:这个类定义了如何输出汉语拼音。 HanyuPinyinCaseType:为汉语拼音字符串的输出案例提供了几种选项。 HanyuPinyinToneType:该类提供了几种输出中文音调的选项。 HanyuPinyinVCharType:这个类为'ü'的输出提供了几个选项。
使用的时候需要下载pinyin4j.jar包,或者通过maven下载,依赖如下:
<dependency> <groupId>com.belerweb</groupId> <artifactId>pinyin4j</artifactId> <version>2.5.0</version> </dependency>
例子:
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.HanyuPinyinVCharType; import net.sourceforge.pinyin4j.format.exception.BadHanyuPinyinOutputFormatCombination; public class TestPinyin4jCsdn { public static String getAllPinyin(String hanzi) { HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat(); format.setCaseType(HanyuPinyinCaseType.LOWERCASE); * WITH_TONE_MARK:直接用音标符(必须设置WITH_U_UNICODE,否则会抛出异常) * WITH_TONE_NUMBER:1-4数字表示音标 format.setToneType(HanyuPinyinToneType.WITH_TONE_MARK); * WITH_U_AND_COLON:用"u:"表示ü format.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE); char[] hanYuArr = hanzi.trim().toCharArray(); StringBuilder pinYin = new StringBuilder(); for (int i = 0, len = hanYuArr.length; i < len; i++) { if (Character.toString(hanYuArr[i]).matches("[\\u4E00-\\u9FA5]+")) { String[] pys = PinyinHelper.toHanyuPinyinStringArray(hanYuArr[i], format); pinYin.append(pys[0]).append(" "); pinYin.append(hanYuArr[i]).append(" "); } catch (BadHanyuPinyinOutputFormatCombination badHanyuPinyinOutputFormatCombination) { badHanyuPinyinOutputFormatCombination.printStackTrace(); return pinYin.toString(); public static String getFirstPinYin(String hanyu) { HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat(); format.setCaseType(HanyuPinyinCaseType.UPPERCASE); format.setToneType(HanyuPinyinToneType.WITHOUT_TONE); StringBuilder firstPinyin = new StringBuilder(); char[] hanyuArr = hanyu.trim().toCharArray(); for (int i = 0, len = hanyuArr.length; i < len; i++) { if(Character.toString(hanyuArr[i]).matches("[\\u4E00-\\u9FA5]+")){ String[] pys = PinyinHelper.toHanyuPinyinStringArray(hanyuArr[i],format); firstPinyin.append(pys[0].charAt(0)); firstPinyin.append(hanyuArr[i]); } catch (BadHanyuPinyinOutputFormatCombination badHanyuPinyinOutputFormatCombination) { badHanyuPinyinOutputFormatCombination.printStackTrace(); return firstPinyin.toString(); public static void main(String[] args) { String pinYin = getAllPinyin("秋水共长天一色"); String firstPinYin = getFirstPinYin("秋水共长天一色"); System.out.println("秋水共长天一色全拼:"+pinYin); System.out.println("秋水共长天一色首字母:"+firstPinYin);
|