关键字的首字母拼音和全拼搜索

/*** @author ChineseSpelling*        所有全拼集合 汉字转拼音 使用工具类*/
public class ChineseSpelling {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 };private 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 ChineseSpelling chineseSpelling = new ChineseSpelling();public static ChineseSpelling getInstance() {return chineseSpelling;}public String getResource() {return resource;}public void setResource(String resource) {this.resource = resource;}private int getChsAscii(String chs) {int asc = 0;try {byte[] bytes = chs.getBytes("gb2312");if (bytes == null || bytes.length > 2 || bytes.length <= 0) { // 错误// logthrow new RuntimeException("illegal resource string");// System.out.println("error");}if (bytes.length == 1) { // 英文字符asc = bytes[0];}if (bytes.length == 2) { // 中文字符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);// e.printStackTrace();}return asc;}public String convert(String str) {String result = null;int ascii = getChsAscii(str);// System.out.println(ascii);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;}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());}
}

/***  * @Description:  首字母拼音*  * @Author:       lp*  * @CreateDate:   2021/4/21 15:43*/
public class FirstLetterUtil {private static int BEGIN = 45217;private static int END = 63486;// 按照声母表示，这个表是在GB2312中的出现的第一个汉字，也就是说“啊”是代表首字母a的第一个汉字。// i, u, v都不做声母, 自定规则跟随前面的字母private static char[] chartable = { '啊', '芭', '擦', '搭', '蛾', '发', '噶', '哈','哈', '击', '喀', '垃', '妈', '拿', '哦', '啪', '期', '然', '撒', '塌', '塌','塌', '挖', '昔', '压', '匝', };// 二十六个字母区间对应二十七个端点// GB2312码汉字区间十进制表示private static int[] table = new int[27];// 对应首字母区间表private static char[] initialtable = { 'a', 'b', 'c', 'd', 'e', 'f', 'g','h', 'h', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't','t', 't', 'w', 'x', 'y', 'z', };// 初始化static {for (int i = 0; i < 26; i++) {table[i] = gbValue(chartable[i]);// 得到GB2312码的首字母区间端点表，十进制。}table[26] = END;// 区间表结尾}/*** 根据一个包含汉字的字符串返回一个汉字拼音首字母的字符串 最重要的一个方法，思路如下：一个个字符读入、判断、输出*/public static String getFirstLetter(String sourceStr) {String result = "";String str = sourceStr.toLowerCase();int StrLength = str.length();int i;try {for (i = 0; i < StrLength; i++) {result += Char2Initial(str.charAt(i));}} catch (Exception e) {result = "";}return result;}/*** 输入字符,得到他的声母,英文字母返回对应的大写字母,其他非简体汉字返回 '0'*/private static char Char2Initial(char ch) {// 对英文字母的处理：小写字母转换为大写，大写的直接返回if (ch >= 'a' && ch <= 'z') {return ch;}if (ch >= 'A' && ch <= 'Z') {return ch;}// 对非英文字母的处理：转化为首字母，然后判断是否在码表范围内，// 若不是，则直接返回。// 若是，则在码表内的进行判断。int gb = gbValue(ch);// 汉字转换首字母if ((gb < BEGIN) || (gb > END))// 在码表区间之前，直接返回{return ch;}int i;for (i = 0; i < 26; i++) {// 判断匹配码表区间，匹配到就break,判断区间形如“[,)”if ((gb >= table[i]) && (gb < table[i + 1])) {break;}}if (gb == END) {// 补上GB2312区间最右端i = 25;}return initialtable[i]; // 在码表区间中，返回首字母}/*** 取出汉字的编码 cn 汉字*/private static int gbValue(char ch) {// 将一个汉字（GB2312）转换为十进制表示。String str = new String();str += ch;try {byte[] bytes = str.getBytes("GB2312");if (bytes.length < 2) {return 0;}return (bytes[0] << 8 & 0xff00) + (bytes[1] & 0xff);} catch (Exception e) {return 0;}}}


/*** @author lp* @time 2021/3/23 11:37* @classDescribe 模糊搜索，支持简拼，全拼*/
public class LocalSearch {/*** 拼音搜索* @param sequence*/public static ArrayList<AbsFile> search(String sequence, int type,List<AbsFile> list) {ArrayList<AbsFile> strList = new ArrayList<>();if(TextUtils.isEmpty(sequence)) return strList;ChineseSpelling finder = ChineseSpelling.getInstance();String result = "";for (AbsFile absFile : list) {// 先将输入的字符串转换为拼音finder.setResource(sequence);result = finder.getSpelling();//根据输入sequence，与歌曲名称，歌手名称进行匹配if (type == 0){if (contains(absFile.getName(), result)|| contains(((AudioFile)absFile).getArtist(),result)||contains(((AudioFile)absFile).getAlbum(),result)) {strList.add(absFile);}}else if(type == 1){if (contains(absFile.getName(), result)) {strList.add(absFile);}}else if(type == 2){if (contains(((AudioFile)absFile).getAlbum(),result)) {strList.add(absFile);}}else if(type == 3){if (contains(((AudioFile)absFile).getArtist(),result)) {strList.add(absFile);}}}return strList;}/*** 根据拼音搜索** @param** @param*** @return*/private static boolean contains(String str, String search) {if (TextUtils.isEmpty(str)) {return false;}boolean flag = false;// 简拼匹配,如果输入在字符串长度大于6就不按首字母匹配了if (search.length() < 6) {String firstLetters = FirstLetterUtil.getFirstLetter(str);// 不区分大小写Pattern firstLetterMatcher = Pattern.compile(search,Pattern.CASE_INSENSITIVE);flag = firstLetterMatcher.matcher(firstLetters).find();}if (!flag) { // 如果简拼已经找到了，就不使用全拼了// 全拼匹配ChineseSpelling finder = ChineseSpelling.getInstance();finder.setResource(str);// 不区分大小写Pattern pattern2 = Pattern.compile(search, Pattern.CASE_INSENSITIVE);Matcher matcher2 = pattern2.matcher(finder.getSpelling());flag = matcher2.find();}return flag;}//    private static String getGroupName(Group group) {
//        String strName = null;
//        if (!TextUtils.isEmpty(group.getNaturalName())) {
//            strName = group.getNaturalName();
//        } else if (!TextUtils.isEmpty(group.getRoomName())) {
//            strName = group.getRoomName();
//        } else {
//            strName = "";
//        }
//
//        return strName;
//    }
}

list = LocalSearch.search(key,type,absFiles);

key：关键字

type：搜索分类

absFiles：要被搜索的list

关键字的首字母拼音和全拼搜索相关推荐

C# 根据汉字获取首字母拼音或全拼
第一种方法.简单快速若是求快,可以用下面这个方法,不需要什么库,直接写就完事调用GetPYstring ,传入"世界和平",返回"SJHP" public ...
实现下拉框的汉字、拼音、首字母大小写，全拼检索选项
调用这个工具类,可以实现下拉框的汉字.拼音.首字母大小写,全拼检索选项 import java.util.Arrays;import net.sourceforge.pinyin4j.PinyinHe ...
JS实现获取汉字首字母拼音、全拼音及混拼音的方法
本文实例讲述了JS实现获取汉字首字母拼音.全拼音及混拼音的方法.分享给大家供大家参考,具体如下: 这里需要用到一个js获取汉字拼音的插件,可点击此处本站下载. 运行效果如下: 完整示例代码: ? 1 ...
JAVA获取字符串首字拼音和全拼
JAVA获取字符串首字拼音或者全部拼音,用的是pinyin4j. import java.util.ArrayList; import java.util.Hashtable; import java ...
Python3操作EXCEL，取汉字首字母，拼接全拼
开发需求: 将EXCEL中某列特殊字符之前的汉字取首字母,特殊字符之后的汉字取全拼,然后用下划线"_"相连,写入下一列把*******.xls中的汉字人名转成用户名,写到后面的单 ...
oracle汉字转拼音(获得全拼/拼音首字母/拼音截取等)
oracle汉字转拼音(获得全拼/拼音首字母/拼音截取等) oracle 字符集 GBK 没有问题 , UTF -8 需要修改一下 1.获得全拼 SELECT GETHZPY.GETHZFULLPY( ...
Java汉字转拼音（全拼、首字母拼）
Java汉字转拼音(全拼.首字母拼) public class ChineseToEnglish { /*** 汉字转拼音* @param src* @return*/public static St ...
最强汉字得到首字母拼音java版
网上有很多汉字得到首字母拼音的代码,基本都出自一种方式,通过对private static final char[] chartable = { '啊', * '芭', '擦', '搭', '蛾', ...
java实现汉字文字转换拼音（全拼和简拼）工具包
java实现汉字文字转换拼音(全拼和简拼)工具包话不多说,直接上代码,调用即可 /** * 得到全拼 * @param str * @return */public static String g ...

关键字的首字母拼音和全拼搜索

关键字的首字母拼音和全拼搜索相关推荐

最新文章

热门文章