拼音工具类

import java.util.ArrayList;
import java.util.Hashtable;
import java.util.List;
import java.util.Map;

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.exception.BadHanyuPinyinOutputFormatCombination;

/**
* 拼音工具类
*
* @author: develp
* @version: 2.3
*/

public class PinYinUtils {

/**
* 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(重当参:cdc,zds,cds,zdc)
*
* @param chines
* 汉字
* @return 拼音
*/
private static final int ASCII_SPLIT_NUM = 128;

public 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] > ASCII_SPLIT_NUM) {
try {
String[] strs = PinyinHelper.toHanyuPinyinStringArray(
nameChar[i], defaultFormat);
if (strs != null) {
for (int j = 0; j < strs.length; j++) {
pinyinName.append(strs[j].charAt(0));
if (j != strs.length - 1) {
pinyinName.append(",");
}
}
}
} catch (BadHanyuPinyinOutputFormatCombination e) {
e.printStackTrace();
}
} else {
pinyinName.append(nameChar[i]);
}
pinyinName.append(" ");
}
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) {
List<Map<String, Integer>> mapList = new ArrayList<Map<String, Integer>>();
Map<String, Integer> onlyOne = null;
String[] firsts = theStr.split(" ");
for (String str : firsts) {
onlyOne = new Hashtable<String, Integer>();
String[] china = str.split(",");
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;

for (int i = 0; i < list.size(); i++) {

Map<String, Integer> temp = new Hashtable<String, Integer>();

if (first != null) {

for (String s : first.keySet()) {
for (String s1 : list.get(i).keySet()) {
String str = s + s1;
temp.put(str, 1);
}
}

if (temp != null && temp.size() > 0) {
first.clear();
}
} else {
for (String s : list.get(i).keySet()) {
String str = s;
temp.put(str, 1);
}
}

if (temp != null && temp.size() > 0) {
first = temp;
}
}
String returnStr = "";
if (first != null) {

for (String str : first.keySet()) {
returnStr += (str + ",");
}
}
if (returnStr.length() > 0) {
returnStr = returnStr.substring(0, returnStr.length() - 1);
}
return returnStr;
}
}

 

/pinyin4j-2.5.0.jar

posted on 2019-11-07 15:19  花非花-雾非雾  阅读(350)  评论(0编辑  收藏  举报