pinyin4j使用示例(支持多音字)
来源:互联网 发布:c 动漫网站源码 编辑:程序博客网 时间:2024/04/24 19:42
pinyin4j的主页:http://pinyin4j.sourceforge.net/
pinyin4j能够根据中文字符获取其对应的拼音,而且拼音的格式可以定制。
pinyin4j是一个支持将中文转换到拼音的Java开源类库。
- 支持简体中文和繁体中文字符;
- 支持转换到汉语拼音,通用拼音, 威妥玛拼音(威玛拼法), 注音符号第二式, 耶鲁拼法和国语罗马字;
- 支持多音字,即可以获取一个中文字符的多种发音;
- 支持多种字符串输出格式,比如支持Unicode格式的字符ü和声调符号(阴平 "ˉ",阳平"ˊ",上声"ˇ",去声"ˋ")的输出。
示例代码:
- public class Pinyin4jUtil {
-
-
-
-
-
-
-
-
- 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 {
-
- 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()));
- }
-
-
-
-
-
-
-
-
-
-
- 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 {
-
- 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 parseTheChineseByObject(discountTheChinese(pinyinName.toString()));
- }
-
-
-
-
-
-
-
- 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;
- }
-
-
-
-
-
-
- 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;
- }
-
- }
测试代码- <span style="white-space:pre"> </span> String str = "长沙市长";
-
- String pinyin = Pinyin4jUtil.converterToSpell(str);
- System.out.println(str+" pin yin :"+pinyin);
-
- pinyin = Pinyin4jUtil.converterToFirstSpell(str);
- System.out.println(str+" short pin yin :"+pinyin); <p style="margin-top:0px; margin-bottom:25px; line-height:28.8px; color:rgb(64,64,64); font-family:"Microsoft YaHei",Verdana,sans-serif,SimSun; font-size:16px"><span style="line-height:26px; font-family:Arial; font-size:14px">运行结果:</span></p><p style="margin-top:0px; margin-bottom:25px; line-height:28.8px; color:rgb(64,64,64); font-family:"Microsoft YaHei",Verdana,sans-serif,SimSun; font-size:16px"><span style="line-height:26px; font-family:Arial; font-size:14px">长沙市长 pin yin :zhangshashichang,changshashichang,zhangshashizhang,changshashizhang<br style="line-height:10px">长沙市长 short pin yin :cssc,zssz,zssc,cssz<br style="line-height:10px"></span></p><div><span style="line-height:26px; font-family:Arial; font-size:14px">
- </span></div>