Example tutorial of using pinyin4j-javaTutorial-php.cn

Usage of pinyin4j

pinyin4j is a powerful Chinese pinyin toolkit. It mainly obtains pinyin in various formats and requirements from Chinese. It has powerful functions. Let’s see how to use it. 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 {

/**
* Get the first letter of the Chinese pinyin string, the English characters remain unchanged
*
* @param chinese Chinese character string
* @return The first letter of the Chinese pinyin
*/
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();
}

/**
* Get the pinyin of the Chinese character string, the English characters remain unchanged
*
* @param chinese Chinese character string
* @return Chinese pinyin
*/
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;

}
}
/**
* String set conversion string (comma separated)
* @author wyh
* @param stringSet
* @return
*/
public static String makeStringByStringSet(Set 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();
}

/* *
* Get the pinyin set
* @author wyh
* @param src
* @return Set
*/
public static Set getPinyin(String src){
if(src!=null && !src.trim().equalsIgnoreCase("")){
char[ ] srcChar ;
srcChar=src.toCharArray();
//Hanyu Pinyin format output class
HanyuPinyinOutputFormat hanYuPinOutputFormat = new HanyuPinyinOutputFormat();

//Output settings, upper and lower case, phonetic symbols Methods, etc.
hanYuPinOutputFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
hanYuPinOutputFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
hanYuPinOutputFormat.setVCharType(HanyuPinyinVCharType.WITH_V);
String[][] temp = new String[src.length()][];
for(int i=0;ichar c = srcChar[i];
//is Chinese Or convert pinyin from a-z or A-Z (my requirement is to keep Chinese or a-z or 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 pinyinSet = new HashSet();
for(int i=0;ipinyinSet. add(pingyinArray[i]);
}
return pinyinSet;
}
return null;
}

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

/* *
* Recursive
* @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;ifor(int j=0;jtemp[Index] = strJaggedArray[ 0][i] + strJaggedArray[1][j];
Index ++;
}
}
String[][] newArray = new String[len-1][];
for(int i=2;inewArray[i-1] = strJaggedArray[i]; (newArray);
}else{
return strJaggedArray;
}
}

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

// UPPERCASE: uppercase (ZHONG)
// LOWERCASE: lowercase ( zhong)
format.setCaseType(HanyuPinyinCaseType.LOWERCASE);

// WITHOUT_TONE: No phonetic symbols (zhong)
// WITH_TONE_NUMBER: 1-4 numbers represent British symbols (zhong4)
/ / WITH_TONE_MARK: Use phonetic symbols directly (must WITH_U_UNICODE otherwise exception) (zhòng)
format.setToneType(HanyuPinyinToneType.WITH_TONE_MARK);

// WITH_V: Use v to represent ü (nv)
// WITH_U_AND_COLON: Use "u:" to represent ü (nu:)
// WITH_U_UNICODE: Use ü (nü) directly
format.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);
String[] pinyin = PinyinHelper.toHanyuPinyinStringArray( 'heavy', format);
System.out.println(PinyinHelper.toHanyuPinyinStringArray('heavy', format)[1]);
System.out.println(PingYingChange.cnToSpell("Zhenjiang abc")) ;
System.out.println(PingYingChange.quanbianban('o'));
String x = "囧Who said bad students will send videos of their crotch";
System.out.println( cn2FirstSpell(x));
System.out.println(cn2Spell(x));
String str = "Shan Tianfang";
System.out.println(makeStringByStringSet(getPinyin(str))) ;
System.out.println("");
}
}

The above is the detailed content of Example tutorial of using pinyin4j. For more information, please follow other related articles on the PHP Chinese website!