Android通訊錄模糊匹配搜索實現(號碼、首字母、簡拼、全拼)

Android通訊錄模糊匹配搜索實現(號碼、首字母、簡拼、全拼)

2013年12月10日
工作記錄
小巫在工作中碰到一個需求,要求實現通訊錄聯系人的搜索,獲取聯系人的方式有好幾種,我都有點混亂瞭,下面提供我最近用的一種,看起來還算比較簡潔的,它是根據mimetypes表來查的。

	// 查詢所有聯系人的姓名,電話,郵箱

	public ArrayList loadContacts() throws Exception {

		Uri uri = Uri.parse("content://com.android.contacts/contacts");

		ContentResolver resolver = this.getContentResolver();

		Cursor cursor = resolver.query(uri, new String[] { "_id" }, null, null,
				null);
		ArrayList contacts = new ArrayList();
		while (cursor.moveToNext()) {

			Contact contact = new Contact();
			int contractID = cursor.getInt(0);

			StringBuilder sb = new StringBuilder("contractID=");

			contact.setId(String.valueOf(contractID));
			sb.append(contractID);

			uri = Uri.parse("content://com.android.contacts/contacts/"
					+ contractID + "/data");

			Cursor cursor1 = resolver.query(uri, new String[] { "mimetype",
					"data1", "data2" }, null, null, null);

			while (cursor1.moveToNext()) {

				String data1 = cursor1.getString(cursor1
						.getColumnIndex("data1"));

				String mimeType = cursor1.getString(cursor1
						.getColumnIndex("mimetype"));

				if ("vnd.android.cursor.item/name".equals(mimeType)) { // 是姓名
					contact.setName(data1);
					sb.append(",name=" + data1);

				} else if ("vnd.android.cursor.item/email_v2".equals(mimeType)) { // 郵箱
					if (!TextUtils.isEmpty(data1)) {
						contact.setEmail(data1);
					}
					contacts.add(contact);
					sb.append(",email=" + data1);

				} else if ("vnd.android.cursor.item/phone_v2".equals(mimeType)) { // 手機
					contact.setNumber(data1.replaceAll("-", ""));
					sb.append(",phone=" + data1);
				}

			}
			contacts.add(contact);
			cursor1.close();

			Log.i("wwj", sb.toString());

		}

		cursor.close();
		return contacts;

	}

關於模糊匹配,我真的有點頭大,我想到的是用正則表達式來做,但需要用到第三方類庫pinyin4j.jar,我試瞭一下,效率都點低,明顯感覺有點慢瞭,假如你的通訊錄的量比較大,用這個來做確實不合時宜,或許可以進行優化的地方。

定義一個工具類

package com.search;

import net.sourceforge.pinyin4j.PinyinHelper;
import net.sourceforge.pinyin4j.format.HanyuPinyinCaseType;
import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat;
import net.sourceforge.pinyin4j.format.HanyuPinyinToneType;
import net.sourceforge.pinyin4j.format.HanyuPinyinVCharType;
import android.provider.ContactsContract.CommonDataKinds.Phone;
import android.text.TextUtils;

public class BaseUtil {

	public final static String[] PHONES_PROJECTION = new String[] {
			Phone.DISPLAY_NAME, Phone.NUMBER };

	public static String STRS[] = { "", "", "[abc]", "[def]", "[ghi]", "[jkl]",
			"[mno]", "[pqrs]", "[tuv]", "[wxyz]" };

	/**
	 * 將字符串中的中文轉化為拼音,其他字符不變
	 * 
	 * @param inputString
	 * @return
	 */
	public static String getPingYin(String inputString) {
		if (TextUtils.isEmpty(inputString)) {
			return "";
		}
		HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
		format.setCaseType(HanyuPinyinCaseType.LOWERCASE);
		format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
		format.setVCharType(HanyuPinyinVCharType.WITH_V);

		char[] input = inputString.trim().toCharArray();
		String output = "";

		try {
			for (int i = 0; i < input.length; i++) {
				if (java.lang.Character.toString(input[i]).matches(
						"[\u4E00-\u9FA5]+")) {
					String[] temp = PinyinHelper.toHanyuPinyinStringArray(
							input[i], format);
					if (temp == null || TextUtils.isEmpty(temp[0])) {
						continue;
					}
					output += temp[0].replaceFirst(temp[0].substring(0, 1),
							temp[0].substring(0, 1).toUpperCase());
				} else
					output += java.lang.Character.toString(input[i]);
			}
		} catch (Exception e) {
			e.printStackTrace();
		}
		return output;
	}

}

	/**
	 * 按號碼-拼音搜索聯系人
	 * @param str
	 */
	public void search(String str){
		contactList.clear();
		//如果搜索條件以0 1 +開頭則按號碼搜索
		if(str.toString().startsWith("0") || str.toString().startsWith("1")
				 || str.toString().startsWith("+")){
			for(Model model : allContactList){
				if(model.telnum.contains(str)){
					model.group = str;
					contactList.add(model);
				}
			}
			adapter.refresh(contactList, false);
			return;
		}
		StringBuffer sb = new StringBuffer();
		//獲取每一個數字對應的字母列表並以'-'隔開
		for(int i = 0; i < str.length(); i++){
			sb.append((str.charAt(i) = '0')
					? BaseUtil.STRS[str.charAt(i) - '0'] : str.charAt(i));
			if(i != str.length() - 1){
				sb.append("-");
			}
		}
		
		for(Model model : allContactList){
			if(contains(sb.toString(), model, str)){
				contactList.add(model);
			} else if(model.telnum.contains(str)){
				model.group = str;
				contactList.add(model);
			}
		}
		adapter.refresh(contactList, false);
    }
	
	/**
	 * 根據拼音搜索
	 * @param str			正則表達式
	 * @param pyName		拼音
	 * @param isIncludsive	搜索條件是否大於6個字符
	 * @return
	 */
	public boolean contains(String str, Model model, String search){
		if(TextUtils.isEmpty(model.pyname)){
			return false;
		}
		model.group = "";
		//搜索條件大於6個字符將不按拼音首字母查詢
		if(search.length() < 6){
			//根據首字母進行模糊查詢
			Pattern pattern = Pattern.compile("^" + str.toUpperCase().replace("-", "[*+#a-z]*"));
			Matcher matcher = pattern.matcher(model.pyname);
			
			if(matcher.find()){
				String tempStr = matcher.group();
				for(int i = 0; i = 'A' && tempStr.charAt(i) <= 'Z'){
						model.group += tempStr.charAt(i);
					}
				}
				return true;
			}
		}
		
		//根據全拼查詢
		Pattern pattern = Pattern.compile(str.replace("-", ""), Pattern.CASE_INSENSITIVE);
		Matcher matcher = pattern.matcher(model.pyname);
		boolean flag = matcher.find();
		if(flag){
			model.group = matcher.group();
		}
		return flag;
	}

上面的代碼是我從網上搜瞭很久才搜到的一個demo裡面的代碼,我整合到項目當中去,發現使用pinyin4j.jar類庫效率實在有點低,所以我自己想瞭其他辦法,不用第三方類庫來實現。

下面是小巫的實現:


我找到一篇關於,中文字符轉換為拼音的實現類,很有用

package com.suntek.mobilemeeting.utils;

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 && ascii = 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 = 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());
	}
}

不過我也發現瞭一問題,關於一個中文字符的字節數的問題,不同的編碼可能會存在中文的字節數不同的情況,比如GBK編碼的中文是2,而UTF-8的編碼是3。其實我發現這個問題也挺驚奇的,這個問題可能是我們以後編碼的時候會遇到的,一個編碼就可能把你搞死。

英文字母和中文漢字在不同字符集編碼下的字節數

英文字母:

字節數 : 1;編碼:GB2312

字節數 : 1;編碼:GBK

字節數 : 1;編碼:GB18030

字節數 : 1;編碼:ISO-8859-1

字節數 : 1;編碼:UTF-8

字節數 : 4;編碼:UTF-16

字節數 : 2;編碼:UTF-16BE

字節數 : 2;編碼:UTF-16LE

中文漢字:

字節數 : 2;編碼:GB2312

字節數 : 2;編碼:GBK

字節數 : 2;編碼:GB18030

字節數 : 1;編碼:ISO-8859-1

字節數 : 3;編碼:UTF-8

字節數 : 4;編碼:UTF-16

字節數 : 2;編碼:UTF-16BE

字節數 : 2;編碼:UTF-16LE

/**
	 * 按號碼-拼音搜索聯系人
	 * 
	 * @param str
	 */
	public void search(String str) {
		contactList.clear();
		// 如果搜索條件以0 1 +開頭則按號碼搜索
		if (str.startsWith("0") || str.startsWith("1") || str.startsWith("+")) {
			for (Contact contact : allContacts) {
				if (contact.getNumber().contains(str)) {
					contact.setGroup(str);
					contactList.add(contact);
				}
			}
			refreshList();
			return;
		}

		boolean isChinese = false;
		Pattern pattern = Pattern.compile("[\u4E00-\u9FA5]");
		Matcher matcher = pattern.matcher(str);
		if (matcher.find()) { // 如果是中文
			isChinese = true;
		}

		for (Contact contact : allContacts) {
			if (contains(contact, str, isChinese)) {
				contactList.add(contact);
			} else if (contact.getNumber().contains(str)) {
				contact.setGroup(str);
				contactList.add(contact);
			}

		}
		refreshList();
	}

	/**
	 * 根據拼音搜索
	 * 
	 * @param str
	 *            正則表達式
	 * @param pyName
	 *            拼音
	 * @param isIncludsive
	 *            搜索條件是否大於6個字符
	 * @return
	 */
	public boolean contains(Contact contact, String search, boolean isChinese) {
		if (TextUtils.isEmpty(contact.getName())) {
			return false;
		}

		boolean flag = false;
		if (isChinese) {
			// 根據全拼中文查詢
			Pattern pattern = Pattern.compile(search.replace("-", ""),
					Pattern.CASE_INSENSITIVE);
			Matcher matcher = pattern.matcher(contact.getName());
			if (flag) {
				contact.setGroup(matcher.group());
			}
			return matcher.find();
		}

		// 簡拼匹配
		ChineseSpelling finder = ChineseSpelling.getInstance();
		finder.setResource(contact.getName());
		Pattern pattern2 = Pattern.compile(search.toUpperCase(),
				Pattern.CASE_INSENSITIVE);
		Matcher matcher2 = pattern2.matcher(finder.getSpelling());
		flag = matcher2.find();

		return flag;
	}

我發現自己換瞭這種方法之後,速度一下子提升瞭很多,滿足瞭自己的需求,用第三方類庫雖好,但涉及到用戶體驗這一塊,你不得不低頭,小巫總結在此,這篇博客我相信總會有人需要的,如果有幫助到你,不要忘記好評哈,你的支持將是我無限的動力。

發佈留言