Pinyin4j的使用研究-开源JAVA中文字符和拼音之间的转换
Pinyin4j是一个流行的Java库，支持中文字符和拼音之间的转换。拼音输出格式可以定制。
代码实现如下：
1.带声调的方法
/**
* 汉字转换位汉语拼音，英文字符不变 带声调的方法
* @param chines 汉字
* @return 拼音
*/
public static String converterToSpellWithTONE(String chines) {
String pinyinName = "";
char[] nameChar = chines.toCharArray();
HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat();
defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
defaultFormat.setToneType(HanyuPinyinToneType.WITH_TONE_NUMBER);
defaultFormat.setVCharType(HanyuPinyinVCharType.WITH_V);
for (int i = 0; i < nameChar.length; i++) {
if (nameChar[i] > 128) {
try {
if (PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat) != null
&& PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat).length > 0) {
pinyinName += PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat)[0];
}
} catch (BadHanyuPinyinOutputFormatCombination e) {
e.printStackTrace();
}
} else {
pinyinName += nameChar[i];
}
}
return pinyinName;
}
2.不带声调的方法
/**
* 汉字转换位汉语拼音，英文字符不变
* @param chines 汉字
* @return 拼音
*/
public static String converterToSpell(String chines) {
String pinyinName = "";
char[] nameChar = chines.toCharArray();
HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat();
defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
defaultFormat.setVCharType(HanyuPinyinVCharType.WITH_V);
for (int i = 0; i < nameChar.length; i++) {
if (nameChar[i] > 128) {
try {
if (PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat) != null
&& PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat).length > 0) {
pinyinName += PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat)[0];
}
} catch (BadHanyuPinyinOutputFormatCombination e) {
e.printStackTrace();
}
} else {
pinyinName += nameChar[i];
}
}
return pinyinName;
}
3.
/**
* 汉字转换位汉语拼音首字母，英文字符不变
* @param chines 汉字
* @return 拼音
*/
public static String converterToFirstSpell(String chines) {
String pinyinName = "";
char[] nameChar = chines.toCharArray();
HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat();
defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
defaultFormat.setVCharType(HanyuPinyinVCharType.WITH_V);
for (int i = 0; i < nameChar.length; i++) {
if (nameChar[i] > 128) {
try {
if (PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat) != null
&& PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat).length > 0) {
pinyinName += PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat)[0].charAt(0);
}
} catch (BadHanyuPinyinOutputFormatCombination e) {
e.printStackTrace();
}
} else {
pinyinName += nameChar[i];
}
}
return pinyinName;
}
Part Two:详细实现类如下：
package test;
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;
/**
*
* pinyin4j使用
*
* @author
*
*/
public class PinYinTest {
public static HanyuPinyinToneType[] toneTypes = new HanyuPinyinToneType[] {
HanyuPinyinToneType.WITH_TONE_NUMBER,
HanyuPinyinToneType.WITHOUT_TONE,
HanyuPinyinToneType.WITH_TONE_MARK };
public static HanyuPinyinVCharType[] vCharTypes = new HanyuPinyinVCharType[] {
HanyuPinyinVCharType.WITH_U_AND_COLON, HanyuPinyinVCharType.WITH_V,
HanyuPinyinVCharType.WITH_U_UNICODE };
public static HanyuPinyinCaseType[] caseTypes = new HanyuPinyinCaseType[] {
HanyuPinyinCaseType.LOWERCASE, HanyuPinyinCaseType.UPPERCASE };
/**
* 将中文字符转换为相应的数组
*
* @param chineseCharacter
* @param toneSelection
* @param vcharSelection
* @param caseSelection
*/
private static void updateFormattedText(String chineseCharacter,
HanyuPinyinToneType toneSelection,
HanyuPinyinVCharType vcharSelection,
HanyuPinyinCaseType caseSelection) {
// 拼音格式化对象
HanyuPinyinOutputFormat outputFormat = new HanyuPinyinOutputFormat();
// 设置中文声调
if (toneSelection != null) {
if (toneTypes[0] == toneSelection) {
outputFormat.setToneType(HanyuPinyinToneType.WITH_TONE_NUMBER);
} else if (toneTypes[1] == toneSelection) {
outputFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
} else if (toneTypes[2] == toneSelection) {
outputFormat.setToneType(HanyuPinyinToneType.WITH_TONE_MARK);
}
}
// 设置特殊拼音的转换
if (vcharSelection != null) {
if (vCharTypes[0] == vcharSelection) {
outputFormat
.setVCharType(HanyuPinyinVCharType.WITH_U_AND_COLON);
} else if (vCharTypes[1] == vcharSelection) {
outputFormat.setVCharType(HanyuPinyinVCharType.WITH_V);
} else if (vCharTypes[2] == vcharSelection) {
outputFormat.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);
}
}
// 设置转换的拼音的大小写
if (caseSelection != null) {
if (caseTypes[0] == caseSelection) {
outputFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
} else if (caseTypes[1] == caseSelection) {
outputFormat.setCaseType(HanyuPinyinCaseType.UPPERCASE);
}
}
// 获取字符串
char[] cnStr = chineseCharacter.toCharArray();
String msg = "";
for (char chineseChar : cnStr) {
// 将字符转换为拼音数组
String[] pinyinArray = null;
String myenglish = "";
try {
myenglish = PinyinHelper.toHanyuPinyinStringArray(
chineseChar, outputFormat)[0];
} catch (BadHanyuPinyinOutputFormatCombination e1) {
e1.printStackTrace();
}
// String outputString = concatPinyinStringArray(pinyinArray);
System.out.println(myenglish);
msg += myenglish;
}
System.out.println("msg is====" + msg);
}
private static void updateFormattedText2(String chineseCharacter,
HanyuPinyinToneType toneSelection,
HanyuPinyinVCharType vcharSelection,
HanyuPinyinCaseType caseSelection) {
// 拼音格式化对象
HanyuPinyinOutputFormat outputFormat = new HanyuPinyinOutputFormat();
// 设置中文声调
if (toneSelection != null) {
if (toneTypes[0] == toneSelection) {
outputFormat.setToneType(HanyuPinyinToneType.WITH_TONE_NUMBER);
} else if (toneTypes[1] == toneSelection) {
outputFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
} else if (toneTypes[2] == toneSelection) {
outputFormat.setToneType(HanyuPinyinToneType.WITH_TONE_MARK);
}
}
// 设置特殊拼音的转换
if (vcharSelection != null) {
if (vCharTypes[0] == vcharSelection) {
outputFormat
.setVCharType(HanyuPinyinVCharType.WITH_U_AND_COLON);
} else if (vCharTypes[1] == vcharSelection) {
outputFormat.setVCharType(HanyuPinyinVCharType.WITH_V);
} else if (vCharTypes[2] == vcharSelection) {
outputFormat.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);
}
}
// 设置转换的拼音的大小写
if (caseSelection != null) {
if (caseTypes[0] == caseSelection) {
outputFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
} else if (caseTypes[1] == caseSelection) {
outputFormat.setCaseType(HanyuPinyinCaseType.UPPERCASE);
}
}
// 获取字符串
char[] cnStr = chineseCharacter.toCharArray();
for (char chineseChar : cnStr) {
// 将字符转换为拼音数组
String[] pinyinArray = null;
// String test = "";
try {
pinyinArray = PinyinHelper.toHanyuPinyinStringArray(
chineseChar, outputFormat);
} catch (BadHanyuPinyinOutputFormatCombination e1) {
e1.printStackTrace();
}
String outputString = concatPinyinStringArray(pinyinArray);
System.out.println(outputString);
}
}
/**
* 测试中文转换拼音方法
*
* @param args
*/
public static void main(String[] args) {
updateFormattedText("我是中国人", HanyuPinyinToneType.WITH_TONE_NUMBER,
HanyuPinyinVCharType.WITH_V,
HanyuPinyinCaseType.LOWERCASE);
System.out.println("===================");
updateFormattedText("握事种果任", HanyuPinyinToneType.WITH_TONE_NUMBER,
HanyuPinyinVCharType.WITH_U_AND_COLON,
HanyuPinyinCaseType.LOWERCASE);
System.out.println("========================");
updateFormattedText("握事种果任", HanyuPinyinToneType.WITHOUT_TONE,
HanyuPinyinVCharType.WITH_V,
HanyuPinyinCaseType.LOWERCASE);
}
/**
* 将转换的拼音数组转换为字符串
*
* @param pinyinArray
* @return
*/
private static String concatPinyinStringArray(String[] pinyinArray) {
StringBuffer pinyinStrBuf = new StringBuffer();
if ((null != pinyinArray) && (pinyinArray.length > 0)) {
for (int i = 0; i < pinyinArray.length; i++) {
pinyinStrBuf.append(pinyinArray[i]);
pinyinStrBuf.append(System.getProperty("line.separator"));
}
}
String outputString = pinyinStrBuf.toString();
return outputString;
}
}