java开源类库pinyin4j的使用
最近CMS系统为了增加查询的匹配率，需要增加拼音检索字段,在网上找到了pinyin4j的java开源类库，提供中文转汉语拼音(并且支持多音字)，呵呵，看了看他的demo，决定就用它了，因为我在实际使用的时候，需要考虑多音字的不同排列组合，下面的代码就是支持多音字的.pinyin4j官方网址:http://pinyin4j.sourceforge.net/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 pinyin4j {
/**
* 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[];
for(int i=0;i<srcChar.length;i++){
char c = srcChar;
//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 = PinyinHelper.toHanyuPinyinStringArray(srcChar, hanYuPinOutputFormat);
}catch(BadHanyuPinyinOutputFormatCombination e) {
e.printStackTrace();
}
}else if(((int)c>=65 && (int)c<=90) || ((int)c>=97 && (int)c<=122)){
temp = new String[]{String.valueOf(srcChar)};
}else{
temp = new String[]{""};
}
}
String[] pingyinArray = Exchange(temp);
Set<String> pinyinSet = new HashSet<String>();
for(int i=0;i<pingyinArray.length;i++){
pinyinSet.add(pingyinArray);
}
return pinyinSet;
}
return null;
}
/**
* 递归
* @author wyh
* @param strJaggedArray
* @return
*/
public static String[] Exchange(String[][] strJaggedArray){
String[][] temp = DoExchange(strJaggedArray);
return temp;
}
/**
* 递归
* @author wyh
* @param strJaggedArray
* @return
*/
private static String[][] DoExchange(String[][] strJaggedArray){
int len = strJaggedArray.length;
if(len >= 2){
int len1 = strJaggedArray.length;
int len2 = strJaggedArray.length;
int newlen = len1*len2;
String[] temp = new String;
int Index = 0;
for(int i=0;i<len1;i++){
for(int j=0;j<len2;j++){
temp = strJaggedArray + strJaggedArray;
Index ++;
}
}
String[][] newArray = new String[];
for(int i=2;i<len;i++){
newArray = strJaggedArray;
}
newArray = temp;
return DoExchange(newArray);
}else{
return strJaggedArray;
}
}
/**
* @param args
*/
public static void main(String[] args) {
String str = "单田芳";
System.out.println(makeStringByStringSet(getPinyin(str)));
}
}
控制台输出：dantianfang,shantianfang,chantianfang
from:http://go.cxweb.com.cn/0ex2h
页:
[1]