汉字转拼音

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;

/**
 * @Description :
 * @Author : zhangyan
 * @Date: 2020/6/3 16:03
 */
public class Pinyin4jUtil {

    /**
     * getFirstSpellPinYin:(多音字的时候获取第一个). <br/>
     * @param src  传入的拼音字符串，以逗号隔开
     * @param isFullSpell 是否全拼，true:全拼，false:第一个汉字全拼(其它汉字取首字母)
     * @return 第一个拼音
     */
    public static String getFirstSpellPinYin(String src , boolean isFullSpell) {
        String targetStr = Pinyin4jUtil.makeStringByStringSet(Pinyin4jUtil.getPinyin(src, isFullSpell));
        String[] split = targetStr.split(",");
        if (split.length > 1) {
            targetStr = split[0];
        }
        return targetStr;
    }

    /**
     * makeStringByStringSet:(拼音字符串集合转换字符串(逗号分隔)). <br/>
     * @param stringSet  拼音集合
     * @return  带逗号字符串
     */
    public static String makeStringByStringSet(Set<String> stringSet) {
        StringBuilder str = new StringBuilder();
        int i = 0;
        if (stringSet.size() > 0) {
            for (String s : stringSet) {
                if (i == stringSet.size() - 1) {
                    str.append(s);
                } else {
                    str.append(s + ",");
                }
                i++;
            }
        }
        return str.toString().toLowerCase();
    }

    /**
     * getPinyin:(获取汉字拼音). <br/>
     * @param src   汉字
     * @param isFullPin  是否全拼,如果为true：全拼，false:首字全拼
     * @return
     */
    public static Set<String> getPinyin(String src, boolean isFullSpell) {
        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[src.length()][];
            for (int i = 0; i < srcChar.length; i++) {
                char c = srcChar[i];
                if (String.valueOf(c).matches("[\\u4E00-\\u9FA5]+")) {//中文
                    try {
                        temp[i] = PinyinHelper.toHanyuPinyinStringArray(
                                srcChar[i], hanYuPinOutputFormat);
                        if (!isFullSpell) {
                            if (i == 0) {
                                temp[i] = temp[i];
                            } else {
                                String[] tTemps = new String[temp[i].length];
                                for (int j = 0; j < temp[i].length; j++) {
                                    char t = temp[i][j].charAt(0);
                                    tTemps[j] = Character.toString(t);
                                }
                                temp[i] = tTemps;
                            }
                        }
                    } catch (BadHanyuPinyinOutputFormatCombination e) {
                        e.printStackTrace();
                    }
                } else if (((int) c >= 65 && (int) c <= 90)
                        || ((int) c >= 97 && (int) c <= 122)) {//英文
                    temp[i] = new String[] { String.valueOf(srcChar[i]) };
                } else {
                    temp[i] = new String[] { "" };
                }
            }
            String[] pingyinArray = exchange(temp);
            Set<String> pinyinSet = new HashSet<String>();
            for (int i = 0; i < pingyinArray.length; i++) {
                pinyinSet.add(pingyinArray[i]);
            }
            return pinyinSet;
        }
        return null;
    }

    public static String getFirstPinYin(String hanyu) {
        HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
        format.setCaseType(HanyuPinyinCaseType.UPPERCASE);
        format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
        /*
         * 输出大小写设置
         * LOWERCASE:输出小写
         * UPPERCASE:输出大写
         */
        format.setCaseType(HanyuPinyinCaseType.LOWERCASE);

        StringBuilder firstPinyin = new StringBuilder();
        char[] hanyuArr = hanyu.trim().toCharArray();
        try {
            for (int i = 0, len = hanyuArr.length; i < len; i++) {
                if(Character.toString(hanyuArr[i]).matches("[\\u4E00-\\u9FA5]+")){
                    String[] pys = PinyinHelper.toHanyuPinyinStringArray(hanyuArr[i],format);
                    firstPinyin.append(pys[0].charAt(0));
                }else {
                    firstPinyin.append(hanyuArr[i]);
                }
            }
        } catch (BadHanyuPinyinOutputFormatCombination badHanyuPinyinOutputFormatCombination) {
            badHanyuPinyinOutputFormatCombination.printStackTrace();
        }
        return firstPinyin.toString();
    }

    public static String getAllPinyin(String hanzi) {
        //输出格式设置
        HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
        /**
         * 输出大小写设置
         * LOWERCASE:输出小写
         * UPPERCASE:输出大写
         */
        format.setCaseType(HanyuPinyinCaseType.LOWERCASE);

        /**
         * 输出音标设置
         * WITH_TONE_MARK:直接用音标符（必须设置WITH_U_UNICODE，否则会抛出异常）
         * WITH_TONE_NUMBER：1-4数字表示音标
         * WITHOUT_TONE：没有音标
         */
        format.setToneType(HanyuPinyinToneType.WITH_TONE_MARK);

        /**
         * 特殊音标ü设置
         * WITH_V：用v表示ü
         * WITH_U_AND_COLON：用"u:"表示ü
         * WITH_U_UNICODE：直接用ü
         */
        format.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);

        char[] hanYuArr = hanzi.trim().toCharArray();
        StringBuilder pinYin = new StringBuilder();

        try {
            for (int i = 0, len = hanYuArr.length; i < len; i++) {
                //匹配是否是汉字
                if (Character.toString(hanYuArr[i]).matches("[\\u4E00-\\u9FA5]+")) {
                    //如果是多音字，返回多个拼音，这里只取第一个
                    String[] pys = PinyinHelper.toHanyuPinyinStringArray(hanYuArr[i], format);
                    pinYin.append(pys[0]).append(" ");
                } else {
                    pinYin.append(hanYuArr[i]).append(" ");
                }
            }
        } catch (BadHanyuPinyinOutputFormatCombination badHanyuPinyinOutputFormatCombination) {
            badHanyuPinyinOutputFormatCombination.printStackTrace();
        }
        return pinYin.toString();
    }

    /**
     * 递归
     * @param strJaggedArray
     * @return
     */
    public static String[] exchange(String[][] strJaggedArray) {
        String[][] temp = doExchange(strJaggedArray);
        return temp[0];
    }

    /**
     * 递归
     * @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; i < len1; i++) {
                for (int j = 0; j < len2; j++) {
                    temp[Index] = strJaggedArray[0][i] + strJaggedArray[1][j];
                    Index++;
                }
            }
            String[][] newArray = new String[len - 1][];
            for (int i = 2; i < len; i++) {
                newArray[i - 1] = strJaggedArray[i];
            }
            newArray[0] = temp;
            return doExchange(newArray);
        } else {
            return strJaggedArray;
        }
    }


}