java 获取中文拼音首字母及全拼的实践
作者:Coder-CT
本文主要介绍了java 获取中文拼音首字母及全拼的实践,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学习学习吧
使用Hutool工具类 官网链接
以下为Hutool支持的拼音库的pom坐标,你可以选择任意一个引入项目中,如果引入多个,Hutool会按照以上顺序选择第一个使用。
<dependency> <groupId>io.github.biezhi</groupId> <artifactId>TinyPinyin</artifactId> <version>2.0.3.RELEASE</version> </dependency> <dependency> <groupId>com.belerweb</groupId> <artifactId>pinyin4j</artifactId> <version>2.5.1</version> </dependency> <dependency> <groupId>com.github.stuxuhai</groupId> <artifactId>jpinyin</artifactId> <version>1.1.8</version> </dependency>
<!--词库--> <dependency> <groupId>io.github.biezhi</groupId> <artifactId>TinyPinyin</artifactId> <version>2.0.3.RELEASE</version> </dependency> <!--Hutool工具类--> <dependency> <groupId>cn.hutool</groupId> <artifactId>hutool-all</artifactId> <version>5.8.4</version> </dependency>
import cn.hutool.extra.pinyin.PinyinUtil; public class Test { public static void main(String[] args) { // 获取全部汉字首字母,第二个参数为分隔符 String str1 = PinyinUtil.getFirstLetter("测试","-"); //c-s // 返回全部拼音 默认分隔符为空格,可以添加第二个参数分隔符 String str2 = PinyinUtil.getPinyin("测试"); // ce shi String str3 = PinyinUtil.getPinyin("测试","-");// ce-shi } }
判断字符串是否为中文
//判断是否为中文 private static Boolean isChinese(String str) { if (str.trim().matches("[\u4E00-\u9FA5]+")) { return true; } else return false; }
PS:其他实现方法
第一种:
直接上代码(有个别中文无法识别):
import java.io.UnsupportedEncodingException; /** * * @author yuki_ho * */ public class ChineseCharToEnUtil { private final static int[] li_SecPosValue = { 1601, 1637, 1833, 2078, 2274, 2302, 2433, 2594, 2787, 3106, 3212, 3472, 3635, 3722, 3730, 3858, 4027, 4086, 4390, 4558, 4684, 4925, 5249, 5590 }; private final static String[] lc_FirstLetter = { "a", "b", "c", "d", "e", "f", "g", "h", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "w", "x", "y", "z" }; /** * 取得给定汉字串的首字母串,即声母串 * @param str 给定汉字串 * @return 声母串 */ public String getAllFirstLetter(String str) { if (str == null || str.trim().length() == 0) { return ""; } String _str = ""; for (int i = 0; i < str.length(); i++) { _str = _str + this.getFirstLetter(str.substring(i, i + 1)); } return _str; } /** * 取得给定汉字的首字母,即声母 * @param chinese 给定的汉字 * @return 给定汉字的声母 */ public String getFirstLetter(String chinese) { if (chinese == null || chinese.trim().length() == 0) { return ""; } chinese = this.conversionStr(chinese, "GB2312", "ISO8859-1"); if (chinese.length() > 1) // 判断是不是汉字 { int li_SectorCode = (int) chinese.charAt(0); // 汉字区码 int li_PositionCode = (int) chinese.charAt(1); // 汉字位码 li_SectorCode = li_SectorCode - 160; li_PositionCode = li_PositionCode - 160; int li_SecPosCode = li_SectorCode * 100 + li_PositionCode; // 汉字区位码 if (li_SecPosCode > 1600 && li_SecPosCode < 5590) { for (int i = 0; i < 23; i++) { if (li_SecPosCode >= li_SecPosValue[i] && li_SecPosCode < li_SecPosValue[i + 1]) { chinese = lc_FirstLetter[i]; break; } } } else // 非汉字字符,如图形符号或ASCII码 { chinese = this.conversionStr(chinese, "ISO8859-1", "GB2312"); chinese = chinese.substring(0, 1); } } return chinese; } /** * 字符串编码转换 * @param str 要转换编码的字符串 * @param charsetName 原来的编码 * @param toCharsetName 转换后的编码 * @return 经过编码转换后的字符串 */ private String conversionStr(String str, String charsetName,String toCharsetName) { try { str = new String(str.getBytes(charsetName), toCharsetName); } catch (UnsupportedEncodingException ex) { System.out.println("字符串编码转换异常:" + ex.getMessage()); } return str; } public static void main(String[] args) { ChineseCharToEnUtil cte = new ChineseCharToEnUtil(); System.out.println("获取拼音首字母:"+ cte.getAllFirstLetter("广州")); } }
第二种:
所需包:net.sourceforge.pinyin4j
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; /** * * @author yuki_ho * @time 2017-07-25 */ public class ChineseCharToEnUtil { /** * 将字符串中的中文转化为拼音,其他字符不变 * * @param inputString * @return */ public static String getPingYin(String inputString) { HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat(); format.setCaseType(HanyuPinyinCaseType.LOWERCASE); format.setToneType(HanyuPinyinToneType.WITHOUT_TONE); format.setVCharType(HanyuPinyinVCharType.WITH_V); char[] input = inputString.trim().toCharArray(); String output = ""; try { for (int i = 0; i < input.length; i++) { if (java.lang.Character.toString(input[i]).matches("[\\u4E00-\\u9FA5]+")) { String[] temp = PinyinHelper.toHanyuPinyinStringArray(input[i], format); output += temp[0]; } else output += java.lang.Character.toString(input[i]); } } catch (BadHanyuPinyinOutputFormatCombination e) { e.printStackTrace(); } return output; } /** * 获取汉字串拼音首字母,英文字符不变 * @param chinese 汉字串 * @return 汉语拼音首字母 */ public static String getFirstSpell(String chinese) { StringBuffer pybf = new StringBuffer(); char[] arr = chinese.toCharArray(); HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat(); defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE); defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE); for (int i = 0; i < arr.length; i++) { if (arr[i] > 128) { try { String[] temp = PinyinHelper.toHanyuPinyinStringArray(arr[i], defaultFormat); if (temp != null) { pybf.append(temp[0].charAt(0)); } } catch (BadHanyuPinyinOutputFormatCombination e) { e.printStackTrace(); } } else { pybf.append(arr[i]); } } return pybf.toString().replaceAll("\\W", "").trim(); } /** * 获取汉字串拼音,英文字符不变 * @param chinese 汉字串 * @return 汉语拼音 */ public static String getFullSpell(String chinese) { StringBuffer pybf = new StringBuffer(); char[] arr = chinese.toCharArray(); HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat(); defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE); defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE); for (int i = 0; i < arr.length; i++) { if (arr[i] > 128) { try { pybf.append(PinyinHelper.toHanyuPinyinStringArray(arr[i], defaultFormat)[0]); } catch (BadHanyuPinyinOutputFormatCombination e) { e.printStackTrace(); } } else { pybf.append(arr[i]); } } return pybf.toString(); } public static void main(String[] args) { String cnStr = "讴萘"; System.out.println("讴萘-->" + getPingYin(cnStr)); String s = getFirstSpell("讴萘"); System.out.println("讴萘-->" + s); StringBuffer sb = new StringBuffer(s); if (sb.length() > 1) { String ss = sb.delete(1, sb.length()).toString(); System.out.println("讴萘-->" + Character.toUpperCase(ss.toCharArray()[0]) + ""); } } }
到此这篇关于java 获取中文拼音首字母及全拼的实践的文章就介绍到这了,更多相关java 获取中文拼音首字母及全拼内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家!