获取汉字的五笔,全拼和双拼的工具类
如题,项目需要,首先可用的自然是pinyin4j.
在不考虑多音字的情况下,全拼自然搞定.
双拼只是替换了全拼的声母和韵母,使用正则和对照也可以搞定.就是要注意声母中并没有y和w,但是常用拼音中却有,正则中要加入这两个.
五笔的话,参看我上一篇文章.
?
这里放出工具类,注意引入pinyin4j-2.5.jar包
?
public class StringUtil {/** * 匹配单个字符全拼的声母和韵母,声母可能不存在.注意y和w,虽然不在声母范围,但是居首也是有可能的 */private static final Pattern psp = Pattern.compile("^([bpmfdtnlgkhjqxrzcsyw]{0,2})([aeiouv][a-z]*)$");private static HanyuPinyinOutputFormat hpof;private static Properties wb86;private static Properties shuangPin;static {// 拼音格式hpof = new HanyuPinyinOutputFormat();hpof.setCaseType(HanyuPinyinCaseType.LOWERCASE);// 输出全小写hpof.setToneType(HanyuPinyinToneType.WITHOUT_TONE);// 不显示音调hpof.setVCharType(HanyuPinyinVCharType.WITH_V);// ü替换为v// 五笔数据wb86 = new Properties();try {wb86.load(new BufferedInputStream(StringUtil.class.getResourceAsStream("wb86.properties")));} catch (IOException e) {e.printStackTrace();}// 双拼shuangPin = new Properties();try {shuangPin.load(new BufferedInputStream(StringUtil.class.getResourceAsStream("sp.properties")));} catch (IOException e) {e.printStackTrace();}}/** * 字符转化为拼音.无法转换返回null,转换成功返回所有的发音 * * @param c * @return */public static String[] charToPinyin(char c) {if (c < 0x4E00 || c > 0x9FA5) {// GBK字库在unicode中的起始和结束位置if (c != 0x3007) {// 圆圈0比较特殊,需要处理一下return null;}}try {return PinyinHelper.toHanyuPinyinStringArray(c, hpof);} catch (BadHanyuPinyinOutputFormatCombination e) {return null;}}/** * 获取单个字符的双拼,顺序和全拼一致 * * @param c * @return */public static String[] charToShuangPin(char c) {String[] array = charToPinyin(c);if (array == null) {return array;}String[] result = new String[array.length];for (int i = 0; i < array.length; i++) {String s = array[i];Matcher m = psp.matcher(s);if (m.matches()) {String sm = m.group(1);String smdz = shuangPin.getProperty(sm);String ym = m.group(2);String ymdz = shuangPin.getProperty(ym);String r = "";if (smdz != null) {r = smdz;}if (ymdz != null) {r += ymdz;}result[i] = r;} else {System.err.println("分解" + c + "拼音的拼音时发生错误!无法拆分出声母和韵母.");}}return result;}/** * 返回字符串的拼音的首字母,每个多音字只取第一个发音. * * @param s * @return */public static String toPinyinShouZiMu(String s) {if (s == null || s.length() == 0) {return null;}StringBuilder sb = new StringBuilder();for (char c : s.toCharArray()) {String[] r = charToPinyin(c);if (r == null) {sb.append(c);} else {String py = r[0];if (py.length() > 0) {sb.append(py.charAt(0));}}}return sb.toString();}/** * 返回字符串的拼音,全拼,每个字的首字母大写,每个多音字只取第一个发音. * * @param s * @return */public static String toQuanPin(String s) {if (s == null || s.length() == 0) {return null;}StringBuilder sb = new StringBuilder();for (char c : s.toCharArray()) {String[] r = charToPinyin(c);if (r == null) {sb.append(c);} else {String py = r[0];if (py.length() > 0) {char f = Character.toUpperCase(py.charAt(0));// if ((f == 'A' || f == 'O' || f == 'E') && sb.length() >// 0) {// aoe 开头的音节连接在其它音节后面的时候，如果音节的界限发生混淆，用隔音符号（'）隔开，例如// pí'ǎo（皮袄）xī'ān（西安）。// py = "'" + f + py.substring(1);// } else {py = f + py.substring(1);// }}sb.append(py);}}return sb.toString();}/** * 返回字符串的双拼.多音字只取第一个发音.每个字的首字母大写 * * @param s * @return */public static String toShuangPin(String s) {if (s == null || s.length() == 0) {return null;}StringBuilder sb = new StringBuilder();for (char c : s.toCharArray()) {String[] r = charToShuangPin(c);if (r == null) {sb.append(c);} else {String py = r[0];if (py.length() > 0) {char f = Character.toUpperCase(py.charAt(0));py = f + py.substring(1);}sb.append(py);}}return sb.toString();}/** * 字符转化为五笔(86),无法转化返回null * * @param c * @return */public static String[] charToWubi(char c) {if (c < 0x4E00 || c > 0x9FA5) {// GBK字库在unicode中的起始和结束位置return null;}String result = wb86.getProperty(Integer.toHexString(c).toUpperCase());if (result == null) {return null;}if (result.contains(",")) {return result.split(",");} else {return new String[] { result };}}public static void main(String[] args) {System.out.println(toQuanPin("中华人民共和国--外交部"));System.out.println(toShuangPin("中华人民共和国--外交部"));System.out.println(toPinyinShouZiMu("中华人民共和国--外交部"));System.out.println(toShuangPin("壹仟贰佰叁拾肆亿伍仟陆佰柒拾捌万玖仟零壹拾贰元叁角肆分"));System.out.println(Arrays.deepToString(charToWubi('啊')));System.out.println(Arrays.deepToString(charToWubi('A')));System.out.println(Arrays.deepToString(charToWubi('工')));}}?
两个properties文件看附件,和工具类放在一个包下
?
输出结果:
ZhongHuaRenMinGongHeGuo--WaiJiaoBu
VsHwRfMnGsHeGo--WlJcBu
zhrmghg--wjb
YiQmRBlSjUiSiYiWuQmLuBlQiUiBaWjJqQmL;YiUiRYrSjJcSiFf
[kb, kbs, kbsk]
null
[a, aaa, aaaa]
?
?