java的中文转拼音组件---pinyin4j

Pinyin4j是sourceforge.net上的一个开源项目，支持同一汉字有多个发音，还支持拼音的格式化输出，比如第几声之类的，同时支持简体中文、繁体中文转换为拼音。下面是其官方网址，其中提供了下载：

http://pinyin4j.sourceforge.net/

通常情况下，只需要用到其中的PinyinHelper类中的静态方法toHanyuPinyinStringArray就可以了，比如：

String[] pinyinArray =PinyinHelper.toHanyuPinyinStringArray('单');

for(int i = 0; i < pinyinArray.length; ++i)

{

         System.out.println(pinyinArray[i]);

}

就会输出：

dan1

chan2

shan4

这三种发音，后面的数字代表第几声。可以看到静态方法toHanyuPinyinStringArray返回的数据类型是一个String数组，它用来接收一个汉字的多个发音，如果toHanyuPinyinStringArray中的参数不是汉字，那么它会返回null

 

 

 

 

例子：

package com.ice.core.util;

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 PinyinUtil {
	/**
	 * 获取汉字串拼音首字母，英文字符不变 （没有处理多音字）
	 * 
	 * @param chinese
	 *            汉字串
	 * @return 汉语拼音首字母
	 */
	public static String cn2FirstSpell(String chinese) {
		StringBuffer pybf = new StringBuffer();
		char[] arr = chinese.toCharArray();
		HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat();
		defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
		defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
		for (int i = 0; i < arr.length; i++) {
			if (arr[i] > 128) {
				try {
					String[] _t = PinyinHelper.toHanyuPinyinStringArray(arr[i],
							defaultFormat);
					if (_t != null) {
						pybf.append(_t[0].charAt(0));
					}
				} catch (BadHanyuPinyinOutputFormatCombination e) {
					e.printStackTrace();
				}
			} else {
				pybf.append(arr[i]);
			}
		}
		return pybf.toString().replaceAll("\\W", "").trim();
	}

	/**
	 * 获取汉字串拼音，英文字符不变 （没有处理多音字）
	 * 
	 * @param chinese
	 *            汉字串
	 * @return 汉语拼音
	 */
	public static String cn2Spell(String chinese) {
		StringBuffer pybf = new StringBuffer();
		char[] arr = chinese.toCharArray();
		HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat();
		defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
		defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
		for (int i = 0; i < arr.length; i++) {
			if (arr[i] > 128) {
				try {
					pybf.append(PinyinHelper.toHanyuPinyinStringArray(arr[i],
							defaultFormat)[0]);
				} catch (BadHanyuPinyinOutputFormatCombination e) {
					e.printStackTrace();
				}
			} else {
				pybf.append(arr[i]);
			}
		}
		return pybf.toString();
	}

	/**
	 * 获取拼音集合(处理多音字)
	 * 
	 * @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[src.length()][];
			for (int i = 0; i < srcChar.length; i++) {
				char c = srcChar[i];
				// 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[i] = PinyinHelper.toHanyuPinyinStringArray(
								srcChar[i], hanYuPinOutputFormat);
					} catch (BadHanyuPinyinOutputFormatCombination e) {
						e.printStackTrace();
					}
				} else if (((int) c >= 65 && (int) c <= 90)
						|| ((int) c >= 97 && (int) c <= 122)) {
					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;
	}

	/**
	 * 递归
	 * 
	 * @author wyh
	 * @param strJaggedArray
	 * @return
	 */
	public static String[] Exchange(String[][] strJaggedArray) {
		String[][] temp = DoExchange(strJaggedArray);
		return temp[0];
	}

	/**
	 * 递归
	 * 
	 * @author wyh
	 * @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;
		}
	}

	/**
	 * 字符串集合转换字符串(逗号分隔)
	 * 
	 * @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();
	}

	public static void main(String[] args) {
		String str = "单田芳";

		// System.out.println(makeStringByStringSet(getPinyin(str)));
		System.out.println(cn2FirstSpell(str));
		System.out.println(cn2Spell(str));

	}
}

 

 

package com.ice;

import java.util.Arrays;
import java.util.Comparator;
import java.util.List;

import net.sourceforge.pinyin4j.PinyinHelper;

public class PinyinComparator implements Comparator<Object> {

	private 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]);
			}
		}
		String outputString = pinyinStrBuf.toString();
		return outputString;
	}

	public int compare(Object o1, Object o2) {

		int length1 = ((String) o1).length();
		int length2 = ((String) o2).length();

		int length = length1 - length2 > 0 ? length2 : length1;

		for (int i = 0; i < length; i++) {
			char c1 = ((String) o1).charAt(i);
			char c2 = ((String) o2).charAt(i);

			String c1topinyin = concatPinyinStringArray(PinyinHelper
					.toHanyuPinyinStringArray(c1));
			String c2topinyin = concatPinyinStringArray(PinyinHelper
					.toHanyuPinyinStringArray(c2));

			if ("".equals(c1topinyin) && "".equals(c2topinyin)) {
				if (c1 - c2 == 0) {
					continue;
				} else {
					return c1 - c2;
				}

			} else if ("".equals(c1topinyin) && !"".equals(c2topinyin)) {
				return -1;
			} else if (!"".equals(c1topinyin) && "".equals(c2topinyin)) {
				return 1;
			} else {
				int pinyinCompareValue = c1topinyin.compareTo(c2topinyin);
				if (pinyinCompareValue == 0) {
					if (c1 - c2 == 0) {
						continue;
					} else {
						// 同音字按笔画比较 先不实现
						return c1 - c2;
					}

				}
				return pinyinCompareValue;
			}
		}

		return length1 - length2;
	}

	public static void main(String[] args) {
		String[] data = { "13", "12", "123a", "1234", "123", "张a", "李四", "张a1",
				"章a", "9", "7", "镕", "C", "H", "张A", "重申", "重量" };
		List list = Arrays.asList(data);
		Arrays.sort(data, new PinyinComparator());
		System.out.println(list);
	}

}