Android类似通讯录模糊匹配搜索实现（号码、首字母、简拼、全拼）

最近开发中有个需求类似qq搜索功能，根据数字，首字母，全拼，简拼实现数据检索。之前只是根据对象的属性来对比，后来发现有局限性，所以参考一篇博客自己动手修改了一下，实现的结果还比较不错的，在这里分享一下：

参考原文：点击打开链接

效果图1 简拼：

效果2 全拼：

效果3 根据数字搜索：

下面介绍关键的类：

一、中文字符转换为拼音的实现类

/**
 * Java汉字转换为拼音
 * 
 * @author zihao
 * 
 */
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 **/
	public String convert(String str) {
		String result = null;
		int ascii = getChsAscii(str);
		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());
	}

}

二、搜索的类

public class LocalGroupSearch {
	/**
	 * 按群号-群名拼音搜索
	 * 
	 * @param str
	 */
	public static ArrayList searchGroup(CharSequence str,
			ArrayList allContacts) {
		ArrayList groupList = new ArrayList();
		// 如果搜索条件以0 1 +开头则按号码搜索
		if (str.toString().startsWith("0") || str.toString().startsWith("1")
				|| str.toString().startsWith("+")) {
			for (Group group : allContacts) {
				if (getGroupName(group) != null
						&& group.getRoomid() + "" != null) {
					if ((group.getRoomid() + "").contains(str)
							|| group.getNaturalName().contains(str)) {
						groupList.add(group);
					}
				}
			}
			return groupList;
		}
		CharacterParser finder = CharacterParser.getInstance();

		String result = "";
		for (Group group : allContacts) {
			// 先将输入的字符串转换为拼音
			finder.setResource(str.toString());
			result = finder.getSpelling();
			if (contains(group, result)) {
				groupList.add(group);
			} else if ((group.getRoomid() + "").contains(str)) {
				groupList.add(group);
			}
		}
		return groupList;
	}

	/**
	 * 根据拼音搜索
	 * 
	 * @param str
	 *            正则表达式
	 * @param pyName
	 *            拼音
	 * @param isIncludsive
	 *            搜索条件是否大于6个字符
	 * @return
	 */
	private static boolean contains(Group group, String search) {
		if (TextUtils.isEmpty(group.getNaturalName())
				&& TextUtils.isEmpty(group.getRoomName())) {
			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(getGroupName(group));
			// 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
			CharacterParser finder = CharacterParser.getInstance();
			finder.setResource(getGroupName(group));
			// 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;
	}
}

三、调用

/**
	 * 搜索框监听
	 */
	TextWatcher textWatcher = new TextWatcher() {

		@Override
		public void onTextChanged(CharSequence s, int arg1, int arg2, int arg3) {
			// TODO Auto-generated method stub
			if (s != null && s.length() > 0) {
			        List listG = LocalGroupSearch.searchGroup(s, al);
				Logger.e(this, "local_group=" + listG.toString());
				TitledListView.FLAG_VIEW = true;
				FLAG_SHOW_TITLE = true;
				if (listG != null && listG.size() > 0) {
				} else {
					ToastUtil.show("搜索为空");
				}
				dAdapter.updateList(listG);
				searchUtils.showListView(dAdapter, null);
				Logger.e(this, "new_group=" + listG.toString());
			} else {
				FLAG_SHOW_TITLE = false;
				TitledListView.FLAG_VIEW = false;
				searchUtils.hideListView();
				dAdapter.updateList(al);
			}
		}

		@Override
		public void beforeTextChanged(CharSequence arg0, int arg1, int arg2,
				int arg3) {
		}

		@Override
		public void afterTextChanged(Editable arg0) {
		}
	};

搞定，代码量也不是很多，自己做个总结留个笔记，也希望可以帮助到朋友们。