Android汉字转拼音的完美解决方案
2024-04-21 12:37:51
前面的话：做一件事情前一定要先对比多种解决方案在开始写代码，如果一开始就知道某种方法的不合理，就不会浪费那么多时间在解决之前的错误上啦。这篇文章就是因为一开始没有认识到这个问题，付出的代价。以此为戒！
一开始，我使用ASCII码和拼音的映射对汉字和拼音间进行转换，相关类如下：
public class CharacterParser {private static int[] pyvalue = new int[]{-20319, -20317, -20304, -20295, -20292, -20283, -20265, -20257, -20242, -20230, -20051, -20036, -20032,-20026, -20002, -19990, -19986, -19982, -19976, -19805, -19784, -19775, -19774, -19763, -19756, -19751, -19746, -19741, -19739, -19728,-19725, -19715, -19540, -19531, -19525, -19515, -19500, -19484, -19479, -19467, -19289, -19288, -19281, -19275, -19270, -19263, -19261,-19249, -19243, -19242, -19238, -19235, -19227, -19224, -19218, -19212, -19038, -19023, -19018, -19006, -19003, -18996, -18977, -18961,-18952, -18783, -18774, -18773, -18763, -18756, -18741, -18735, -18731, -18722, -18710, -18697, -18696, -18526, -18518, -18501, -18490,-18478, -18463, -18448, -18447, -18446, -18239, -18237, -18231, -18220, -18211, -18201, -18184, -18183, -18181, -18012, -17997, -17988,-17970, -17964, -17961, -17950, -17947, -17931, -17928, -17922, -17759, -17752, -17733, -17730, -17721, -17703, -17701, -17697, -17692,-17683, -17676, -17496, -17487, -17482, -17468, -17454, -17433, -17427, -17417, -17202, -17185, -16983, -16970, -16942, -16915, -16733,-16708, -16706, -16689, -16664, -16657, -16647, -16474, -16470, -16465, -16459, -16452, -16448, -16433, -16429, -16427, -16423, -16419,-16412, -16407, -16403, -16401, -16393, -16220, -16216, -16212, -16205, -16202, -16187, -16180, -16171, -16169, -16158, -16155, -15959,-15958, -15944, -15933, -15920, -15915, -15903, -15889, -15878, -15707, -15701, -15681, -15667, -15661, -15659, -15652, -15640, -15631,-15625, -15454, -15448, -15436, -15435, -15419, -15416, -15408, -15394, -15385, -15377, -15375, -15369, -15363, -15362, -15183, -15180,-15165, -15158, -15153, -15150, -15149, -15144, -15143, -15141, -15140, -15139, -15128, -15121, -15119, -15117, -15110, -15109, -14941,-14937, -14933, -14930, -14929, -14928, -14926, -14922, -14921, -14914, -14908, -14902, -14894, -14889, -14882, -14873, -14871, -14857,-14678, -14674, -14670, -14668, -14663, -14654, -14645, -14630, -14594, -14429, -14407, -14399, -14384, -14379, -14368, -14355, -14353,-14345, -14170, -14159, -14151, -14149, -14145, -14140, -14137, -14135, -14125, -14123, -14122, -14112, -14109, -14099, -14097, -14094,-14092, -14090, -14087, -14083, -13917, -13914, -13910, -13907, -13906, -13905, -13896, -13894, -13878, -13870, -13859, -13847, -13831,-13658, -13611, -13601, -13406, -13404, -13400, -13398, -13395, -13391, -13387, -13383, -13367, -13359, -13356, -13343, -13340, -13329,-13326, -13318, -13147, -13138, -13120, -13107, -13096, -13095, -13091, -13076, -13068, -13063, -13060, -12888, -12875, -12871, -12860,-12858, -12852, -12849, -12838, -12831, -12829, -12812, -12802, -12607, -12597, -12594, -12585, -12556, -12359, -12346, -12320, -12300,-12120, -12099, -12089, -12074, -12067, -12058, -12039, -11867, -11861, -11847, -11831, -11798, -11781, -11604, -11589, -11536, -11358,-11340, -11339, -11324, -11303, -11097, -11077, -11067, -11055, -11052, -11045, -11041, -11038, -11024, -11020, -11019, -11018, -11014,-10838, -10832, -10815, -10800, -10790, -10780, -10764, -10587, -10544, -10533, -10519, -10331, -10329, -10328, -10322, -10315, -10309,-10307, -10296, -10281, -10274, -10270, -10262, -10260, -10256, -10254};public static String[] pystr = new String[]{"a", "ai", "an", "ang", "ao", "ba", "bai", "ban", "bang", "bao", "bei", "ben", "beng", "bi", "bian","biao", "bie", "bin", "bing", "bo", "bu", "ca", "cai", "can", "cang", "cao", "ce", "ceng", "cha", "chai", "chan", "chang", "chao", "che","chen", "cheng", "chi", "chong", "chou", "chu", "chuai", "chuan", "chuang", "chui", "chun", "chuo", "ci", "cong", "cou", "cu", "cuan","cui", "cun", "cuo", "da", "dai", "dan", "dang", "dao", "de", "deng", "di", "dian", "diao", "die", "ding", "diu", "dong", "dou", "du","duan", "dui", "dun", "duo", "e", "en", "er", "fa", "fan", "fang", "fei", "fen", "feng", "fo", "fou", "fu", "ga", "gai", "gan", "gang","gao", "ge", "gei", "gen", "geng", "gong", "gou", "gu", "gua", "guai", "guan", "guang", "gui", "gun", "guo", "ha", "hai", "han", "hang","hao", "he", "hei", "hen", "heng", "hong", "hou", "hu", "hua", "huai", "huan", "huang", "hui", "hun", "huo", "ji", "jia", "jian","jiang", "jiao", "jie", "jin", "jing", "jiong", "jiu", "ju", "juan", "jue", "jun", "ka", "kai", "kan", "kang", "kao", "ke", "ken","keng", "kong", "kou", "ku", "kua", "kuai", "kuan", "kuang", "kui", "kun", "kuo", "la", "lai", "lan", "lang", "lao", "le", "lei", "leng","li", "lia", "lian", "liang", "liao", "lie", "lin", "ling", "liu", "long", "lou", "lu", "lv", "luan", "lue", "lun", "luo", "ma", "mai","man", "mang", "mao", "me", "mei", "men", "meng", "mi", "mian", "miao", "mie", "min", "ming", "miu", "mo", "mou", "mu", "na", "nai","nan", "nang", "nao", "ne", "nei", "nen", "neng", "ni", "nian", "niang", "niao", "nie", "nin", "ning", "niu", "nong", "nu", "nv", "nuan","nue", "nuo", "o", "ou", "pa", "pai", "pan", "pang", "pao", "pei", "pen", "peng", "pi", "pian", "piao", "pie", "pin", "ping", "po", "pu","qi", "qia", "qian", "qiang", "qiao", "qie", "qin", "qing", "qiong", "qiu", "qu", "quan", "que", "qun", "ran", "rang", "rao", "re","ren", "reng", "ri", "rong", "rou", "ru", "ruan", "rui", "run", "ruo", "sa", "sai", "san", "sang", "sao", "se", "sen", "seng", "sha","shai", "shan", "shang", "shao", "she", "shen", "sheng", "shi", "shou", "shu", "shua", "shuai", "shuan", "shuang", "shui", "shun","shuo", "si", "song", "sou", "su", "suan", "sui", "sun", "suo", "ta", "tai", "tan", "tang", "tao", "te", "teng", "ti", "tian", "tiao","tie", "ting", "tong", "tou", "tu", "tuan", "tui", "tun", "tuo", "wa", "wai", "wan", "wang", "wei", "wen", "weng", "wo", "wu", "xi","xia", "xian", "xiang", "xiao", "xie", "xin", "xing", "xiong", "xiu", "xu", "xuan", "xue", "xun", "ya", "yan", "yang", "yao", "ye", "yi","yin", "ying", "yo", "yong", "you", "yu", "yuan", "yue", "yun", "za", "zai", "zan", "zang", "zao", "ze", "zei", "zen", "zeng", "zha","zhai", "zhan", "zhang", "zhao", "zhe", "zhen", "zheng", "zhi", "zhong", "zhou", "zhu", "zhua", "zhuai", "zhuan", "zhuang", "zhui","zhun", "zhuo", "zi", "zong", "zou", "zu", "zuan", "zui", "zun", "zuo"};private StringBuilder buffer;private String resource;private static CharacterParser characterParser = new CharacterParser();public static CharacterParser getInstance() {return characterParser;}public String getResource() {return resource;}public void setResource(String resource) {this.resource = resource;}/*** 汉字转成ASCII码 * * @param chs * @return*/private int getChsAscii(String chs) {int asc = 0;try {byte[] bytes = chs.getBytes("gb2312");if (bytes == null || bytes.length > 2 || bytes.length <= 0) {throw new RuntimeException("illegal resource string");}if (bytes.length == 1) {asc = bytes[0];}if (bytes.length == 2) {int hightByte = 256 + bytes[0];int lowByte = 256 + bytes[1];asc = (256 * hightByte + lowByte) - 256 * 256;}} catch (Exception e) {System.out.println("ERROR:ChineseSpelling.class-getChsAscii(String chs)" + e);}return asc;}/*** 单字解析 * * @param str * @return*/public String convert(String str) {String result = null;int ascii = getChsAscii(str);if (str.equals("梵")) {result = "fan";}else if(str.equals("诶")){result = "ei";L.i("ds>>>"," 单字解析 222222 result = "+result);}else if(str.equals("玥")){result="yue";L.i("ds>>>"," 单字解析 333 result = "+result);}else if (ascii > 0 && ascii < 160) {result = String.valueOf((char) ascii);} else {for (int i = (pyvalue.length - 1); i >= 0; i--) {if (pyvalue[i] <= ascii) {result = pystr[i];break;}}}return result;}/*** 词组解析 * * @param chs * @return*/public String getSelling(String chs) {String key, value;buffer = new StringBuilder();for (int i = 0; i < chs.length(); i++) {key = chs.substring(i, i + 1);if (key.getBytes().length >= 2) {value = (String) convert(key);if (value == null) {value = "unknown";}} else {value = key;}buffer.append(value);}return buffer.toString();}public String getSpelling() {return this.getSelling(this.getResource());}这个方式我使用了大半年，有一天测试突然告诉我，有问题。如图：
原来，这个方式虽然使用简单，但是它只能解析出一些常用的一级汉字，对于比如说玥，莉就不能成功解析。
然后，我只能舍弃这个类，换种方式。使用compile ‘com.belerweb:pinyin4j:2.5.0’，并写一个工具类（如下），便解决了这个问题。
public class PinyinTool {static HanyuPinyinOutputFormat format = null;public static enum Type {UPPERCASE, //全部大写LOWERCASE, //全部小写FIRSTUPPER //首字母大写}public PinyinTool(){format = new HanyuPinyinOutputFormat();format.setCaseType(HanyuPinyinCaseType.UPPERCASE);format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);}/*** 将str转换成拼音，如果不是汉字或者没有对应的拼音，则不作转换* 如： 明天 转换成 MINGTIAN* @param str* @param spera* @return* @throws BadHanyuPinyinOutputFormatCombination*/public static String toPinYin(String str, String spera, Type type) throws BadHanyuPinyinOutputFormatCombination {if(str == null || str.trim().length()==0)return "";if(type == Type.UPPERCASE)format.setCaseType(HanyuPinyinCaseType.UPPERCASE);elseformat.setCaseType(HanyuPinyinCaseType.LOWERCASE);String py = "";String temp = "";String[] t;for(int i=0,len=str.length();i<len;i++){char c = str.charAt(i);if((int)c <= 128)py += c;else{t = PinyinHelper.toHanyuPinyinStringArray(c, format);if(t == null)py += c;else{temp = t[0];if(type == Type.FIRSTUPPER)temp = t[0].toUpperCase().charAt(0)+temp.substring(1);py += temp+(i==str.length()-1?"":spera);}}}return py.trim();}
}Android汉字转拼音的完美解决方案相关推荐
- android 汉字转拼音pinyin4j包
android 汉字转拼音pinyin4j包 转载于:https://www.cnblogs.com/longhs/p/3148276.html
- Android 汉字转拼音工具
Android 汉字转拼音工具 前言 工具 使用 前言 没有.. 工具 pinyin4j - 下载1 pinyin4j - 下载2 使用 import net.sourceforge.pinyin4j ...
- Android绘制竖直虚线完美解决方案—自定义View
Android绘制竖直虚线完美解决方案-自定义View 开发中我们经常会遇到绘制虚线的需求,一般我们使用一个drawable文件即可实现,下面我会先列举常规drawable文件的实现方式. 使用dra ...
- Android汉字转拼音HanziToPinyin
Android系统本身自带有有将汉字转化为英文拼音的类和方法.具体的类就是HanziToPinyin.java.Android系统自身实现的通讯录中就使用了HanziToPinyin.java对中文通 ...
- Excel中汉字转拼音的完美方案
实现汉字转拼音的常见方案一般是通过ASCII编码表进行对照,或者通过字典库查询,这两个方案的优点是简单,不需要依赖外部程序,但缺点也很明显:无法识别多音字,且需要庞大的数据文件支撑,并不完美. 而利用 ...
- android汉字转拼音，不用第三方包
有时候我们的项目中需要用到汉字转拼音的功能,典型的比如通讯录,网上也有第三方包可以实现这个功能.现在这里提供一个比较轻巧的解决办法,这是google的通讯录里面使用的,代码路径packages/pro ...
- android 汉字转拼音
android源码有汉字转拼音的文件,路径:android_source/packages/providers/ContactsProvider/src/com/android/providers/c ...
- Android 汉字转换拼音之JPinyin
一.简介 项目地址:https://github.com/stuxuhai/jpinyin JPinyin是一个汉字转拼音的Java开源类库,在PinYin4j的功能基础上做了一些改进. [JPiny ...
- 强大的Android汉字转拼音开源库TinyPinyin
我们日常开发中遇到汉字转拼音的机会比较少,但是在做联系人相关的时候就会常常遇到,比如微信联系列表,手机联系人列表,张三的首字母排序是Z,王五的首字母排序是W. 今天给大家介绍一个汉字转拼音的库Tiny ...
最新文章
- 官宣！微软宣布桌面版 Edge将基于Chromium进行开发\n
- Open×××整合OpenLDAP
- Android中从assets资源中读取图片文件并保存到内部存储器并加载显示在ImageView中
- 《进化——我们在互联网上奋斗的故事》一一1.1 靠谱工程师向管理者的转变...
- No.1010_第七次团队会议
- webpack打包---报错内存溢出javaScript heap out of memory
- 学习 vuex 源码整体架构，打造属于自己的状态管理库
- 使用Python进行汽车黑客攻击：泄露GPS和OBDIICAN总线数据
- 2020统计局的行政划分表_国家统计局：月入2000-5000元并非“中等收入群体”
- OpenCV-基本图形绘制（圆、矩形、椭圆）
- respberry pi VNC 连接设置
- 魔兽世界国服服务器稳定,《魔兽世界》国服大服务器功能实装启动
- Sablog-X v2.x 任意变量覆盖漏洞
- 无缝衔接的人会遭报应吗_怎么看待分手后无缝衔接的人?
- Gameloft的移动游戏王者之路
- 判断设备是否是 iphone5
- “8421码 5421码 2421码 余3码”区别
- AI中的变形，扭曲和变化，栅格化命令，裁剪标记，路径，路径查找器，转化为形状
- android 新闻功能列表,Android中通过ListView的实现简单新闻列表
- “linux系统内网穿透、外网访问”教程