記錄一個獲取漢字的方法
使用的jar包
<!-- https://mvnrepository.com/artifact/com.github.liuzhuoming23/pinyin4j-spring-boot-starter -->
<dependency>
<groupId>com.github.liuzhuoming23</groupId>
<artifactId>pinyin4j-spring-boot-starter</artifactId>
<version>0.0.4</version>
</dependency>
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.HanyuPinyinVCharType;
import net.sourceforge.pinyin4j.format.exception.BadHanyuPinyinOutputFormatCombination;
public class Pinyin4jUtil {
/**
* 提取首個字符的首字母婉烟,其他返回*
*
* @param str
* @return String
*/
public static String getFirstPinYinHeadChar(String str) {
StringBuffer pybf = new StringBuffer();
char word = str.charAt(0);
// 提取漢字的首字母
String[] pinyinArray;
// 是否是因為字母
if (word > 128) {
pinyinArray = PinyinHelper.toHanyuPinyinStringArray(word);
// 如果不是漢字浮还,就返回*
if (pinyinArray != null) {
pybf.append(pinyinArray[0].charAt(0));
} else {
pybf.append("*");
}
} else {
// 是字母直接返回,不是返回*
if (Character.isLetter(word)) {
pybf.append(word);
} else {
pybf.append("*");
}
}
// 全部返回大寫
return pybf.toString().toUpperCase();
}
/**
* 將漢字轉(zhuǎn)換為全拼
*
* @param src
* @return String
*/
public static String getPinYin(String src) {
char[] t1 = null;
t1 = src.toCharArray();
// System.out.println(t1.length);
String[] t2 = new String[t1.length];
// System.out.println(t2.length);
// 設(shè)置漢字拼音輸出的格式
HanyuPinyinOutputFormat t3 = new HanyuPinyinOutputFormat();
t3.setCaseType(HanyuPinyinCaseType.LOWERCASE);
t3.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
t3.setVCharType(HanyuPinyinVCharType.WITH_V);
String t4 = "";
int t0 = t1.length;
try {
for (int i = 0; i < t0; i++) {
// 判斷是否為漢字字符
// System.out.println(t1[i]);
if (Character.toString(t1[i]).matches("[\\u4E00-\\u9FA5]+")) {
t2 = PinyinHelper.toHanyuPinyinStringArray(t1[i], t3);// 將漢字的幾種全拼都存到t2數(shù)組中
t4 += t2[0];// 取出該漢字全拼的第一種讀音并連接到字符串t4后
} else {
// 如果不是漢字字符浙炼,直接取出字符并連接到字符串t4后
t4 += Character.toString(t1[i]);
}
}
} catch (BadHanyuPinyinOutputFormatCombination e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return t4;
}
/**
* 提取每個漢字的首字母
*
* @param str
* @return String
*/
public static String getPinYinHeadChar(String str) {
String convert = "";
for (int j = 0; j < str.length(); j++) {
char word = str.charAt(j);
// 提取漢字的首字母
String[] pinyinArray = PinyinHelper.toHanyuPinyinStringArray(word);
if (pinyinArray != null) {
convert += pinyinArray[0].charAt(0);
} else {
convert += word;
}
}
return convert;
}
/**
* 將字符串轉(zhuǎn)換成ASCII碼
*
* @param cnStr
* @return String
*/
public static String getCnASCII(String cnStr) {
StringBuffer strBuf = new StringBuffer();
// 將字符串轉(zhuǎn)換成字節(jié)序列
byte[] bGBK = cnStr.getBytes();
for (int i = 0; i < bGBK.length; i++) {
// System.out.println(Integer.toHexString(bGBK[i] & 0xff));
// 將每個字符轉(zhuǎn)換成ASCII碼
strBuf.append(Integer.toHexString(bGBK[i] & 0xff) + " ");
}
return strBuf.toString();
}
/**
* 漢字轉(zhuǎn)換位漢語拼音首字母是尖,英文字符不變,特殊字符丟失 支持多音字,生成方式如(長沙市長:cssc,zssz,zssc,cssz)
*
* @param chines
* 漢字
* @return 拼音
*/
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] > 128) {
try {
// 取得當(dāng)前漢字的所有全拼
String[] strs = PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat);
if (strs != null) {
for (int j = 0; j < strs.length; j++) {
// 取首字母
pinyinName.append(strs[j].charAt(0));
if (j != strs.length - 1) {
pinyinName.append(",");
}
}
}
// else {
// pinyinName.append(nameChar[i]);
// }
} catch (BadHanyuPinyinOutputFormatCombination e) {
e.printStackTrace();
}
} else {
pinyinName.append(nameChar[i]);
}
pinyinName.append(" ");
}
// return pinyinName.toString();
return parseTheChineseByObject(discountTheChinese(pinyinName.toString()));
}
/**
* 漢字轉(zhuǎn)換位漢語全拼,英文字符不變,特殊字符丟失
* 支持多音字季眷,生成方式如(重當(dāng)參:zhongdangcen,zhongdangcan,chongdangcen
* ,chongdangshen,zhongdangshen,chongdangcan)
*
* @param chines
* 漢字
* @return 拼音
*/
public static String converterToSpell(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] > 128) {
try {
// 取得當(dāng)前漢字的所有全拼
String[] strs = PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat);
if (strs != null) {
for (int j = 0; j < strs.length; j++) {
pinyinName.append(strs[j]);
if (j != strs.length - 1) {
pinyinName.append(",");
}
}
}
} catch (BadHanyuPinyinOutputFormatCombination e) {
e.printStackTrace();
}
} else {
pinyinName.append(nameChar[i]);
}
pinyinName.append(" ");
}
// return pinyinName.toString();
return parseTheChineseByObject(discountTheChinese(pinyinName.toString()));
}
/**
* 去除多音字重復(fù)數(shù)據(jù)
*
* @param theStr
* @return
*/
private static List<Map<String, Integer>> discountTheChinese(String theStr) {
// 去除重復(fù)拼音后的拼音列表
List<Map<String, Integer>> mapList = new ArrayList<Map<String, Integer>>();
// 用于處理每個字的多音字,去掉重復(fù)
Map<String, Integer> onlyOne = null;
String[] firsts = theStr.split(" ");
// 讀出每個漢字的拼音
for (String str : firsts) {
onlyOne = new Hashtable<String, Integer>();
String[] china = str.split(",");
// 多音字處理
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;
}
/**
* 解析并組合拼音卷胯,對象合并方案(推薦使用)
*
* @return
*/
private static String parseTheChineseByObject(List<Map<String, Integer>> list) {
Map<String, Integer> first = null; // 用于統(tǒng)計每一次,集合組合數(shù)據(jù)
// 遍歷每一組集合
for (int i = 0; i < list.size(); i++) {
// 每一組集合與上一次組合的Map
Map<String, Integer> temp = new Hashtable<String, Integer>();
// 第一次循環(huán)子刮,first為空
if (first != null) {
// 取出上次組合與此次集合的字符,并保存
for (String s : first.keySet()) {
for (String s1 : list.get(i).keySet()) {
String str = s + s1;
temp.put(str, 1);
}
}
// 清理上一次組合數(shù)據(jù)
if (temp != null && temp.size() > 0) {
first.clear();
}
} else {
for (String s : list.get(i).keySet()) {
String str = s;
temp.put(str, 1);
}
}
// 保存組合數(shù)據(jù)以便下次循環(huán)使用
if (temp != null && temp.size() > 0) {
first = temp;
}
}
String returnStr = "";
if (first != null) {
// 遍歷取出組合字符串
for (String str : first.keySet()) {
returnStr += (str + ",");
}
}
if (returnStr.length() > 0) {
returnStr = returnStr.substring(0, returnStr.length() - 1);
}
return returnStr;
}