Android通讯录模糊匹配搜索实现（号码、首字母、简拼、全拼）

2013年12月10日 工作记录
小巫在工作中碰到一个需求，要求实现通讯录联系人的搜索，获取联系人的方式有好几种，我都有点混乱了，下面提供我最近用的一种，看起来还算比较简洁的，它是根据mimetypes表来查的。

[java] view
plaincopyprint?





// 查询所有联系人的姓名，电话，邮箱

public ArrayList<Contact> 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<Contact> contacts = new ArrayList<Contact>();

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)) { // 邮箱

if (!TextUtils.isEmpty(data1)) {

contact.setEmail(data1);

}

contacts.add(contact);

sb.append(",email=" + data1);

} else if ("vnd.android.cursor.item/phone_v2".equals(mimeType)) { // 手机

contact.setNumber(data1.replaceAll("-", ""));

sb.append(",phone=" + data1);

}

}

contacts.add(contact);

cursor1.close();

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

}

cursor.close();

return contacts;

}

关于模糊匹配，我真的有点头大，我想到的是用正则表达式来做，但需要用到第三方类库pinyin4j.jar，我试了一下，效率都点低，明显感觉有点慢了，假如你的通讯录的量比较大，用这个来做确实不合时宜，或许可以进行优化的地方。

定义一个工具类

[java] view
plaincopyprint?





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]" };

/**

* 将字符串中的中文转化为拼音,其他字符不变

*

* @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;

}

}

[java] view
plaincopyprint?





/**

* 按号码-拼音搜索联系人

* @param str

*/

public void search(String str){

contactList.clear();

//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(Model model : allContactList){

if(model.telnum.contains(str)){

model.group = str;

contactList.add(model);

}

}

adapter.refresh(contactList, false);

return;

}

StringBuffer sb = new StringBuffer();

//获取每一个数字对应的字母列表并以'-'隔开

for(int i = 0; i < str.length(); i++){

sb.append((str.charAt(i) <= '9' && 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

*/

public boolean contains(String str, Model model, String search){

if(TextUtils.isEmpty(model.pyname)){

return false;

}

model.group = "";

//搜索条件大于6个字符将不按拼音首字母查询

if(search.length() < 6){

//根据首字母进行模糊查询

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 < tempStr.length(); i++){

if(tempStr.charAt(i) >= 'A' && tempStr.charAt(i) <= 'Z'){

model.group += tempStr.charAt(i);

}

}

return true;

}

}

//根据全拼查询

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;

}

上面的代码是我从网上搜了很久才搜到的一个demo里面的代码，我整合到项目当中去，发现使用pinyin4j.jar类库效率实在有点低，所以我自己想了其他办法，不用第三方类库来实现。

下面是小巫的实现：

我找到一篇关于，中文字符转换为拼音的实现类，很有用

[java] view
plaincopyprint?





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) { // 错误

// log

throw 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());

}

}

不过我也发现了一问题，关于一个中文字符的字节数的问题，不同的编码可能会存在中文的字节数不同的情况，比如GBK编码的中文是2，而UTF-8的编码是3。其实我发现这个问题也挺惊奇的，这个问题可能是我们以后编码的时候会遇到的，一个编码就可能把你搞死。

英文字母和中文汉字在不同字符集编码下的字节数

英文字母：

字节数 : 1;编码：GB2312

字节数 : 1;编码：GBK

字节数 : 1;编码：GB18030

字节数 : 1;编码：ISO-8859-1

字节数 : 1;编码：UTF-8

字节数 : 4;编码：UTF-16

字节数 : 2;编码：UTF-16BE

字节数 : 2;编码：UTF-16LE

中文汉字：

字节数 : 2;编码：GB2312
字节数 : 2;编码：GBK

字节数 : 2;编码：GB18030

字节数 : 1;编码：ISO-8859-1
字节数 : 3;编码：UTF-8

字节数 : 4;编码：UTF-16

字节数 : 2;编码：UTF-16BE

字节数 : 2;编码：UTF-16LE

[java] view
plaincopyprint?





/**

* 按号码-拼音搜索联系人

*

* @param str

*/

public void search(String str) {

contactList.clear();

// 如果搜索条件以0 1 +开头则按号码搜索

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

*/

public boolean contains(Contact contact, String search, boolean isChinese) {

if (TextUtils.isEmpty(contact.getName())) {

return false;

}

boolean flag = false;

if (isChinese) {

// 根据全拼中文查询

Pattern pattern = Pattern.compile(search.replace("-", ""),

Pattern.CASE_INSENSITIVE);

Matcher matcher = pattern.matcher(contact.getName());

if (flag) {

contact.setGroup(matcher.group());

}

return matcher.find();

}

// 简拼匹配

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;

}

我发现自己换了这种方法之后，速度一下子提升了很多，满足了自己的需求，用第三方类库虽好，但涉及到用户体验这一块，你不得不低头，小巫总结在此，这篇博客我相信总会有人需要的，如果有帮助到你，不要忘记好评哈，你的支持将是我无限的动力。