pinyin4j的使用

Posted 2020-09-21 苗士军

pinyin4j的使用

 

pinyin4j是一个功能强悍的汉语拼音工具包，主要是从汉语获取各种格式和需求的拼音，功能强悍，下面看看如何使用pinyin4j。

 

import java.util.HashSet;
import java.util.Set;

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 PingYingChange {

/**
* 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 cn2FirstSpell(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[] _t = PinyinHelper.toHanyuPinyinStringArray(arr[i], defaultFormat);
if (_t != null) {
pybf.append(_t[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 cn2Spell(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 String cnToSpell(String chines) {

String pinyinName = "";
StringBuffer strbuf = 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++) {
char name = quanbianban(nameChar[i]);
nameChar[i] = name;
if (128 < nameChar[i]) {
try {
strbuf.append(PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat)[0].charAt(0));
} catch (BadHanyuPinyinOutputFormatCombination e) {
e.printStackTrace();
}
} else {
strbuf.append(nameChar[i]);
}
}

pinyinName = strbuf.toString();

return pinyinName;
}

public static char quanbianban(char quan) {
switch (quan) {

case \'０\':
return \'0\';

case \'１\':
return \'1\';

case \'２\':
return \'2\';

case \'３\':
return \'3\';

case \'４\':
return \'4\';

case \'５\':
return \'5\';

case \'６\':
return \'6\';

case \'７\':
return \'7\';

case \'８\':
return \'8\';

case \'９\':
return \'9\';

default:
return quan;

}
}
/**
* 字符串集合转换字符串(逗号分隔)
* @author wyh
* @param stringSet
* @return
*/
public static String makeStringByStringSet(Set<String> stringSet){
StringBuilder str = new StringBuilder();
int i=0;
for(String s : stringSet){
if(i == stringSet.size() - 1){
str.append(s);
}else{
str.append(s + ",");
}
i++;
}
return str.toString().toLowerCase();
}

/**
* 获取拼音集合
* @author wyh
* @param src
* @return Set<String>
*/
public static Set<String> getPinyin(String src){
if(src!=null && !src.trim().equalsIgnoreCase("")){
char[] srcChar ;
srcChar=src.toCharArray();
//汉语拼音格式输出类
HanyuPinyinOutputFormat hanYuPinOutputFormat = new HanyuPinyinOutputFormat();

//输出设置，大小写，音标方式等
hanYuPinOutputFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
hanYuPinOutputFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
hanYuPinOutputFormat.setVCharType(HanyuPinyinVCharType.WITH_V);

String[][] temp = new String[src.length()][];
for(int i=0;i<srcChar.length;i++){
char c = srcChar[i];
//是中文或者a-z或者A-Z转换拼音(我的需求，是保留中文或者a-z或者A-Z)
if(String.valueOf(c).matches("[\\\\u4E00-\\\\u9FA5]+")){
try{
temp[i] = PinyinHelper.toHanyuPinyinStringArray(srcChar[i], hanYuPinOutputFormat);
}catch(BadHanyuPinyinOutputFormatCombination e) {
e.printStackTrace();
}
}else if(((int)c>=65 && (int)c<=90) || ((int)c>=97 && (int)c<=122)){
temp[i] = new String[]{String.valueOf(srcChar[i])};
}else{
temp[i] = new String[]{""};
}
}
String[] pingyinArray = Exchange(temp);
Set<String> pinyinSet = new HashSet<String>();
for(int i=0;i<pingyinArray.length;i++){
pinyinSet.add(pingyinArray[i]);
}
return pinyinSet;
}
return null;
}

/**
* 递归
* @author wyh
* @param strJaggedArray
* @return
*/
public static String[] Exchange(String[][] strJaggedArray){
String[][] temp = DoExchange(strJaggedArray);
return temp[0];
}

/**
* 递归
* @author wyh
* @param strJaggedArray
* @return
*/
private static String[][] DoExchange(String[][] strJaggedArray){
int len = strJaggedArray.length;
if(len >= 2){
int len1 = strJaggedArray[0].length;
int len2 = strJaggedArray[1].length;
int newlen = len1*len2;
String[] temp = new String[newlen];
int Index = 0;
for(int i=0;i<len1;i++){
for(int j=0;j<len2;j++){
temp[Index] = strJaggedArray[0][i] + strJaggedArray[1][j];
Index ++;
}
}
String[][] newArray = new String[len-1][];
for(int i=2;i<len;i++){
newArray[i-1] = strJaggedArray[i];
}
newArray[0] = temp;
return DoExchange(newArray);
}else{
return strJaggedArray;
}
}

public static void main(String[] args) throws Exception {
HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();

// UPPERCASE：大写 (ZHONG)
// LOWERCASE：小写 (zhong)
format.setCaseType(HanyuPinyinCaseType.LOWERCASE);

// WITHOUT_TONE：无音标 (zhong)
// WITH_TONE_NUMBER：1-4数字表示英标 (zhong4)
// WITH_TONE_MARK：直接用音标符（必须WITH_U_UNICODE否则异常） (zhòng)
format.setToneType(HanyuPinyinToneType.WITH_TONE_MARK);

// WITH_V：用v表示ü (nv)
// WITH_U_AND_COLON：用"u:"表示ü (nu:)
// WITH_U_UNICODE：直接用ü (nü)
format.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);
String[] pinyin = PinyinHelper.toHanyuPinyinStringArray(\'重\', format);
System.out.println(PinyinHelper.toHanyuPinyinStringArray(\'重\', format)[1]);
System.out.println(PingYingChange.cnToSpell("镇江abc"));
System.out.println(PingYingChange.quanbianban(\'o\'));
String x = "嘅囧誰說壞學生來勼髮視頻裆児";
System.out.println(cn2FirstSpell(x));
System.out.println(cn2Spell(x));
String str = "单田芳";
System.out.println(makeStringByStringSet(getPinyin(str)));
System.out.println("");
}
}