进入了媒资行业,项目需求需要将片名生成拼音并支持多音字处理,主要使用pinyin4j库。结合业务跟网上的例子,整理了一个拼音处理工具类。
项目中需要引入jar包:
<dependency>
<groupId>com.belerweb</groupId>
<artifactId>pinyin4j</artifactId>
<version>2.5.1</version>
</dependency>
工具类代码如下:
package com.mgtv.media.vrs.util;
import lombok.extern.slf4j.Slf4j;
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;
import org.apache.commons.lang3.StringUtils;
import java.util.ArrayList;
import java.util.Hashtable;
import java.util.List;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* 拼音处理类
* <p>
* https://blog.51cto.com/273066044/1596126?source=dra
* https://blog.csdn.net/sunshine_YG/article/details/89642788
*
* @author :
* @date :Created in 2019/12/16 17:42
*/
@Slf4j
public class PinyinUtil {
/**
* 汉字转换位汉语拼音首字母,英文字符不变,特殊字符丢失 支持多音字,生成方式如(长沙市长:cssc,zssz,zssc,cssz)
*
* @param chines 汉字
* @return 拼音
*/
private 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(",");
}
}
}
} catch (BadHanyuPinyinOutputFormatCombination e) {
log.error("PinyinUtil报错", e);
}
} else {
pinyinName.append(nameChar[i]);
}
pinyinName.append(" ");
}
return parseTheChineseByObject(discountTheChinese(pinyinName.toString()));
}
/**
* 汉字转换位汉语全拼,英文字符不变,特殊字符丢失
* 支持多音字,生成方式如(重当参:zhongdangcen,zhongdangcan,chongdangcen
* ,chongdangshen,zhongdangshen,chongdangcan)
*
* @param chines 汉字
* @return 拼音
*/
private 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) {
log.error("拼音转换报错", e);
}
} else {
pinyinName.append(nameChar[i]);
}
pinyinName.append(" ");
}
// return pinyinName.toString();
return parseTheChineseByObject(discountTheChinese(pinyinName.toString()));
}
/**
* 去除多音字重复数据
*
* @param theStr
* @return
*/
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;
}
/**
* 解析并组合拼音,对象合并方案(推荐使用)
*
* @return
*/
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;
}
/**
* 将字符串中的中文转化为拼音,英文字符不变
* <p>
* 例: 举个栗子,abc123
* 返回值: JugeLiZiabc123
*/
private static String getPinYin(String inputString) {
inputString = cleanChar(inputString);
HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
format.setCaseType(HanyuPinyinCaseType.LOWERCASE);
format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
format.setVCharType(HanyuPinyinVCharType.WITH_V);
String output = "";
if (inputString != null && inputString.length() > 0 && !"null".equals(inputString)) {
char[] input = inputString.trim().toCharArray();
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);
String tmp = temp[0];
tmp = getFistCharToUpperCase(tmp);
output += tmp;
} else {
output += java.lang.Character.toString(input[i]);
}
}
} catch (BadHanyuPinyinOutputFormatCombination e) {
log.error("拼音转换报错", e);
}
} else {
return "*";
}
return output;
}
/**
* 将首字母变成大写
*
* @param str
* @return
*/
public static String getFistCharToUpperCase(String str) {
if (StringUtils.isEmpty(str)) {
return StringUtils.EMPTY;
}
char[] chars = str.toCharArray();
if (chars[0] >= 'a' && chars[0] <= 'z') {
chars[0] = (char) (chars[0] - 32);
}
return new String(chars);
}
/**
* 清理特殊字符以便得到
* <p>
* 例: 举个栗子,abc123
* 返回值: 举个栗子abc123
*/
public static String cleanChar(String chines) {
chines = chines.replaceAll("[\\p{Punct}\\p{Space}]+", ""); // 正则去掉所有字符操作
// 正则表达式去掉所有中文的特殊符号
String regEx = "[`~!@#$%^&*()+=|{}':;',\\[\\].<>/?~!@#¥%……&*()——+|{}<>《》【】‘;:”“’。,、?]";
Pattern pattern = Pattern.compile(regEx);
Matcher matcher = pattern.matcher(chines);
chines = matcher.replaceAll("").trim();
return chines;
}
/**
* 汉字转拼音缩写
*
* @param str
* @return 2007快乐男声 2007kyns|2007klns 多音字竖线分隔
*/
public static String getSimpleSpell(String str) {
if (StringUtils.isEmpty(str)) {
return StringUtils.EMPTY;
}
str = cleanChar(str);
return converterToFirstSpell(str).replaceAll(",", "|");
}
/**
* 汉字转换成全拼,不区分多音字
*
* @param str
* @return 2007快乐男声 2007KuaiLeNanSheng
*/
public static String getFullSpell(String str) {
if (StringUtils.isEmpty(str)) {
return StringUtils.EMPTY;
}
return getPinYin(str);
}
/**
* 取单个字符的拼音声母
*
* @param simpleSpell
* @return
*/
public static String getInital(String simpleSpell) {
if (StringUtils.isEmpty(simpleSpell))
return "";
simpleSpell = simpleSpell.trim().toLowerCase();
if (simpleSpell.length() == 0)
return "";
char[] clist = simpleSpell.toCharArray();
for (char c : clist) {
if ((c >= 'a' && c <= 'z') || (c >= '0' && c <= '9'))
return getFilter(java.lang.Character.toString(c));
}
return "";
}
/**
* 字符串过滤
*
* @param str
* @return
*/
private static String getFilter(String str) {
if (StringUtils.isEmpty(str))
return "";
str = str.replaceAll("[^a-zA-Z0-9]", "");
return str;
}
public static void main(String[] args) {
String s = "快乐大本营,abc123";
System.out.println(getSimpleSpell(s));
System.out.println(getFullSpell(s));
System.out.println(getFilter(s));
System.out.println(getInital(getSimpleSpell(s)));
}
}