标签:
今天在写一个项目的时候,需要能够识别网址的功能,首先想到的是正则表达式
但是网址的类型多种多样,网络上各种表达式也一搜一大把,很难知道哪一位大神写的靠谱
今天首先是发现Android自带的TextView功能里面有一个类似的功能
<TextView android:id="@+id/tv_scan_result" android:layout_width="match_parent" android:layout_height="wrap_content" android:autoLink="web|email|phone|map" android:visibility="gone" />
当设置了autoLink属性之后,TextView会根据列出的属性值显示内容的时候,对网址,邮箱,电话进行特殊显示,点击的时候也会有各自的事件处理
那么,TextView这里是怎么实现的呢
查看一点点源码发现,Android提供的SDK里面存在一个类:android.util.Patterns;
/** * Regular expression pattern to match most part of RFC 3987 * Internationalized URLs, aka IRIs. Commonly used Unicode characters are * added. */ public static final Pattern WEB_URL = Pattern.compile( "((?:(http|https|Http|Https|rtsp|Rtsp):\\/\\/(?:(?:[a-zA-Z0-9\\$\\-\\_\\.\\+\\!\\*\\‘\\(\\)" + "\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,64}(?:\\:(?:[a-zA-Z0-9\\$\\-\\_" + "\\.\\+\\!\\*\\‘\\(\\)\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,25})?\\@)?)?" + "(?:" + DOMAIN_NAME + ")" + "(?:\\:\\d{1,5})?)" // plus option port number + "(\\/(?:(?:[" + GOOD_IRI_CHAR + "\\;\\/\\?\\:\\@\\&\\=\\#\\~" // plus option query params + "\\-\\.\\+\\!\\*\\‘\\(\\)\\,\\_])|(?:\\%[a-fA-F0-9]{2}))*)?" + "(?:\\b|$)"); // and finally, a word boundary or end of // input. This is to stop foo.sure from // matching as foo.su
我自己这边的方法如下:
/** * 判断是否是一个合法的URL 网址 * @param url * @return */ private boolean isValidUrl(String url){ return TextUtils.isEmpty(url) == false && url.matches(Patterns.WEB_URL.pattern()); }
还有很多其他的Patterns,比如手机号码,邮件,IP地址。下面将整个类加进来
/* * Copyright (C) 2007 The Android Open Source Project * * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. * You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ package android.util; import java.util.regex.Matcher; import java.util.regex.Pattern; /** * Commonly used regular expression patterns. */ public class Patterns { /** * Regular expression to match all IANA top-level domains. * List accurate as of 2011/07/18. List taken from: * http://data.iana.org/TLD/tlds-alpha-by-domain.txt * This pattern is auto-generated by frameworks/ex/common/tools/make-iana-tld-pattern.py * * @deprecated Due to the recent profileration of gTLDs, this API is * expected to become out-of-date very quickly. Therefore it is now * deprecated. */ @Deprecated public static final String TOP_LEVEL_DOMAIN_STR = "((aero|arpa|asia|a[cdefgilmnoqrstuwxz])" + "|(biz|b[abdefghijmnorstvwyz])" + "|(cat|com|coop|c[acdfghiklmnoruvxyz])" + "|d[ejkmoz]" + "|(edu|e[cegrstu])" + "|f[ijkmor]" + "|(gov|g[abdefghilmnpqrstuwy])" + "|h[kmnrtu]" + "|(info|int|i[delmnoqrst])" + "|(jobs|j[emop])" + "|k[eghimnprwyz]" + "|l[abcikrstuvy]" + "|(mil|mobi|museum|m[acdeghklmnopqrstuvwxyz])" + "|(name|net|n[acefgilopruz])" + "|(org|om)" + "|(pro|p[aefghklmnrstwy])" + "|qa" + "|r[eosuw]" + "|s[abcdeghijklmnortuvyz]" + "|(tel|travel|t[cdfghjklmnoprtvwz])" + "|u[agksyz]" + "|v[aceginu]" + "|w[fs]" + "|(\u03b4\u03bf\u03ba\u03b9\u03bc\u03ae|\u0438\u0441\u043f\u044b\u0442\u0430\u043d\u0438\u0435|\u0440\u0444|\u0441\u0440\u0431|\u05d8\u05e2\u05e1\u05d8|\u0622\u0632\u0645\u0627\u06cc\u0634\u06cc|\u0625\u062e\u062a\u0628\u0627\u0631|\u0627\u0644\u0627\u0631\u062f\u0646|\u0627\u0644\u062c\u0632\u0627\u0626\u0631|\u0627\u0644\u0633\u0639\u0648\u062f\u064a\u0629|\u0627\u0644\u0645\u063a\u0631\u0628|\u0627\u0645\u0627\u0631\u0627\u062a|\u0628\u06be\u0627\u0631\u062a|\u062a\u0648\u0646\u0633|\u0633\u0648\u0631\u064a\u0629|\u0641\u0644\u0633\u0637\u064a\u0646|\u0642\u0637\u0631|\u0645\u0635\u0631|\u092a\u0930\u0940\u0915\u094d\u0937\u093e|\u092d\u093e\u0930\u0924|\u09ad\u09be\u09b0\u09a4|\u0a2d\u0a3e\u0a30\u0a24|\u0aad\u0abe\u0ab0\u0aa4|\u0b87\u0ba8\u0bcd\u0ba4\u0bbf\u0baf\u0bbe|\u0b87\u0bb2\u0b99\u0bcd\u0b95\u0bc8|\u0b9a\u0bbf\u0b99\u0bcd\u0b95\u0baa\u0bcd\u0baa\u0bc2\u0bb0\u0bcd|\u0baa\u0bb0\u0bbf\u0b9f\u0bcd\u0b9a\u0bc8|\u0c2d\u0c3e\u0c30\u0c24\u0c4d|\u0dbd\u0d82\u0d9a\u0dcf|\u0e44\u0e17\u0e22|\u30c6\u30b9\u30c8|\u4e2d\u56fd|\u4e2d\u570b|\u53f0\u6e7e|\u53f0\u7063|\u65b0\u52a0\u5761|\u6d4b\u8bd5|\u6e2c\u8a66|\u9999\u6e2f|\ud14c\uc2a4\ud2b8|\ud55c\uad6d|xn\\-\\-0zwm56d|xn\\-\\-11b5bs3a9aj6g|xn\\-\\-3e0b707e|xn\\-\\-45brj9c|xn\\-\\-80akhbyknj4f|xn\\-\\-90a3ac|xn\\-\\-9t4b11yi5a|xn\\-\\-clchc0ea0b2g2a9gcd|xn\\-\\-deba0ad|xn\\-\\-fiqs8s|xn\\-\\-fiqz9s|xn\\-\\-fpcrj9c3d|xn\\-\\-fzc2c9e2c|xn\\-\\-g6w251d|xn\\-\\-gecrj9c|xn\\-\\-h2brj9c|xn\\-\\-hgbk6aj7f53bba|xn\\-\\-hlcj6aya9esc7a|xn\\-\\-j6w193g|xn\\-\\-jxalpdlp|xn\\-\\-kgbechtv|xn\\-\\-kprw13d|xn\\-\\-kpry57d|xn\\-\\-lgbbat1ad8j|xn\\-\\-mgbaam7a8h|xn\\-\\-mgbayh7gpa|xn\\-\\-mgbbh1a71e|xn\\-\\-mgbc0a9azcg|xn\\-\\-mgberp4a5d4ar|xn\\-\\-o3cw4h|xn\\-\\-ogbpf8fl|xn\\-\\-p1ai|xn\\-\\-pgbs0dh|xn\\-\\-s9brj9c|xn\\-\\-wgbh1c|xn\\-\\-wgbl6a|xn\\-\\-xkc2al3hye2a|xn\\-\\-xkc2dl3a5ee0h|xn\\-\\-yfro4i67o|xn\\-\\-ygbi2ammx|xn\\-\\-zckzah|xxx)" + "|y[et]" + "|z[amw])"; /** * Regular expression pattern to match all IANA top-level domains. * @deprecated This API is deprecated. See {@link #TOP_LEVEL_DOMAIN_STR}. */ @Deprecated public static final Pattern TOP_LEVEL_DOMAIN = Pattern.compile(TOP_LEVEL_DOMAIN_STR); /** * Regular expression to match all IANA top-level domains for WEB_URL. * List accurate as of 2011/07/18. List taken from: * http://data.iana.org/TLD/tlds-alpha-by-domain.txt * This pattern is auto-generated by frameworks/ex/common/tools/make-iana-tld-pattern.py * * @deprecated This API is deprecated. See {@link #TOP_LEVEL_DOMAIN_STR}. */ @Deprecated public static final String TOP_LEVEL_DOMAIN_STR_FOR_WEB_URL = "(?:" + "(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])" + "|(?:biz|b[abdefghijmnorstvwyz])" + "|(?:cat|com|coop|c[acdfghiklmnoruvxyz])" + "|d[ejkmoz]" + "|(?:edu|e[cegrstu])" + "|f[ijkmor]" + "|(?:gov|g[abdefghilmnpqrstuwy])" + "|h[kmnrtu]" + "|(?:info|int|i[delmnoqrst])" + "|(?:jobs|j[emop])" + "|k[eghimnprwyz]" + "|l[abcikrstuvy]" + "|(?:mil|mobi|museum|m[acdeghklmnopqrstuvwxyz])" + "|(?:name|net|n[acefgilopruz])" + "|(?:org|om)" + "|(?:pro|p[aefghklmnrstwy])" + "|qa" + "|r[eosuw]" + "|s[abcdeghijklmnortuvyz]" + "|(?:tel|travel|t[cdfghjklmnoprtvwz])" + "|u[agksyz]" + "|v[aceginu]" + "|w[fs]" + "|(?:\u03b4\u03bf\u03ba\u03b9\u03bc\u03ae|\u0438\u0441\u043f\u044b\u0442\u0430\u043d\u0438\u0435|\u0440\u0444|\u0441\u0440\u0431|\u05d8\u05e2\u05e1\u05d8|\u0622\u0632\u0645\u0627\u06cc\u0634\u06cc|\u0625\u062e\u062a\u0628\u0627\u0631|\u0627\u0644\u0627\u0631\u062f\u0646|\u0627\u0644\u062c\u0632\u0627\u0626\u0631|\u0627\u0644\u0633\u0639\u0648\u062f\u064a\u0629|\u0627\u0644\u0645\u063a\u0631\u0628|\u0627\u0645\u0627\u0631\u0627\u062a|\u0628\u06be\u0627\u0631\u062a|\u062a\u0648\u0646\u0633|\u0633\u0648\u0631\u064a\u0629|\u0641\u0644\u0633\u0637\u064a\u0646|\u0642\u0637\u0631|\u0645\u0635\u0631|\u092a\u0930\u0940\u0915\u094d\u0937\u093e|\u092d\u093e\u0930\u0924|\u09ad\u09be\u09b0\u09a4|\u0a2d\u0a3e\u0a30\u0a24|\u0aad\u0abe\u0ab0\u0aa4|\u0b87\u0ba8\u0bcd\u0ba4\u0bbf\u0baf\u0bbe|\u0b87\u0bb2\u0b99\u0bcd\u0b95\u0bc8|\u0b9a\u0bbf\u0b99\u0bcd\u0b95\u0baa\u0bcd\u0baa\u0bc2\u0bb0\u0bcd|\u0baa\u0bb0\u0bbf\u0b9f\u0bcd\u0b9a\u0bc8|\u0c2d\u0c3e\u0c30\u0c24\u0c4d|\u0dbd\u0d82\u0d9a\u0dcf|\u0e44\u0e17\u0e22|\u30c6\u30b9\u30c8|\u4e2d\u56fd|\u4e2d\u570b|\u53f0\u6e7e|\u53f0\u7063|\u65b0\u52a0\u5761|\u6d4b\u8bd5|\u6e2c\u8a66|\u9999\u6e2f|\ud14c\uc2a4\ud2b8|\ud55c\uad6d|xn\\-\\-0zwm56d|xn\\-\\-11b5bs3a9aj6g|xn\\-\\-3e0b707e|xn\\-\\-45brj9c|xn\\-\\-80akhbyknj4f|xn\\-\\-90a3ac|xn\\-\\-9t4b11yi5a|xn\\-\\-clchc0ea0b2g2a9gcd|xn\\-\\-deba0ad|xn\\-\\-fiqs8s|xn\\-\\-fiqz9s|xn\\-\\-fpcrj9c3d|xn\\-\\-fzc2c9e2c|xn\\-\\-g6w251d|xn\\-\\-gecrj9c|xn\\-\\-h2brj9c|xn\\-\\-hgbk6aj7f53bba|xn\\-\\-hlcj6aya9esc7a|xn\\-\\-j6w193g|xn\\-\\-jxalpdlp|xn\\-\\-kgbechtv|xn\\-\\-kprw13d|xn\\-\\-kpry57d|xn\\-\\-lgbbat1ad8j|xn\\-\\-mgbaam7a8h|xn\\-\\-mgbayh7gpa|xn\\-\\-mgbbh1a71e|xn\\-\\-mgbc0a9azcg|xn\\-\\-mgberp4a5d4ar|xn\\-\\-o3cw4h|xn\\-\\-ogbpf8fl|xn\\-\\-p1ai|xn\\-\\-pgbs0dh|xn\\-\\-s9brj9c|xn\\-\\-wgbh1c|xn\\-\\-wgbl6a|xn\\-\\-xkc2al3hye2a|xn\\-\\-xkc2dl3a5ee0h|xn\\-\\-yfro4i67o|xn\\-\\-ygbi2ammx|xn\\-\\-zckzah|xxx)" + "|y[et]" + "|z[amw]))"; /** * Good characters for Internationalized Resource Identifiers (IRI). * This comprises most common used Unicode characters allowed in IRI * as detailed in RFC 3987. * Specifically, those two byte Unicode characters are not included. */ public static final String GOOD_IRI_CHAR = "a-zA-Z0-9\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF"; public static final Pattern IP_ADDRESS = Pattern.compile( "((25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(25[0-5]|2[0-4]" + "[0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(25[0-5]|2[0-4][0-9]|[0-1]" + "[0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}" + "|[1-9][0-9]|[0-9]))"); /** * RFC 1035 Section 2.3.4 limits the labels to a maximum 63 octets. */ private static final String IRI = "[" + GOOD_IRI_CHAR + "]([" + GOOD_IRI_CHAR + "\\-]{0,61}[" + GOOD_IRI_CHAR + "]){0,1}"; private static final String GOOD_GTLD_CHAR = "a-zA-Z\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF"; private static final String GTLD = "[" + GOOD_GTLD_CHAR + "]{2,63}"; private static final String HOST_NAME = "(" + IRI + "\\.)+" + GTLD; public static final Pattern DOMAIN_NAME = Pattern.compile("(" + HOST_NAME + "|" + IP_ADDRESS + ")"); /** * Regular expression pattern to match most part of RFC 3987 * Internationalized URLs, aka IRIs. Commonly used Unicode characters are * added. */ public static final Pattern WEB_URL = Pattern.compile( "((?:(http|https|Http|Https|rtsp|Rtsp):\\/\\/(?:(?:[a-zA-Z0-9\\$\\-\\_\\.\\+\\!\\*\\‘\\(\\)" + "\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,64}(?:\\:(?:[a-zA-Z0-9\\$\\-\\_" + "\\.\\+\\!\\*\\‘\\(\\)\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,25})?\\@)?)?" + "(?:" + DOMAIN_NAME + ")" + "(?:\\:\\d{1,5})?)" // plus option port number + "(\\/(?:(?:[" + GOOD_IRI_CHAR + "\\;\\/\\?\\:\\@\\&\\=\\#\\~" // plus option query params + "\\-\\.\\+\\!\\*\\‘\\(\\)\\,\\_])|(?:\\%[a-fA-F0-9]{2}))*)?" + "(?:\\b|$)"); // and finally, a word boundary or end of // input. This is to stop foo.sure from // matching as foo.su public static final Pattern EMAIL_ADDRESS = Pattern.compile( "[a-zA-Z0-9\\+\\.\\_\\%\\-\\+]{1,256}" + "\\@" + "[a-zA-Z0-9][a-zA-Z0-9\\-]{0,64}" + "(" + "\\." + "[a-zA-Z0-9][a-zA-Z0-9\\-]{0,25}" + ")+" ); /** * This pattern is intended for searching for things that look like they * might be phone numbers in arbitrary text, not for validating whether * something is in fact a phone number. It will miss many things that * are legitimate phone numbers. * * <p> The pattern matches the following: * <ul> * <li>Optionally, a + sign followed immediately by one or more digits. Spaces, dots, or dashes * may follow. * <li>Optionally, sets of digits in parentheses, separated by spaces, dots, or dashes. * <li>A string starting and ending with a digit, containing digits, spaces, dots, and/or dashes. * </ul> */ public static final Pattern PHONE = Pattern.compile( // sdd = space, dot, or dash "(\\+[0-9]+[\\- \\.]*)?" // +<digits><sdd>* + "(\\([0-9]+\\)[\\- \\.]*)?" // (<digits>)<sdd>* + "([0-9][0-9\\- \\.]+[0-9])"); // <digit><digit|sdd>+<digit> /** * Convenience method to take all of the non-null matching groups in a * regex Matcher and return them as a concatenated string. * * @param matcher The Matcher object from which grouped text will * be extracted * * @return A String comprising all of the non-null matched * groups concatenated together */ public static final String concatGroups(Matcher matcher) { StringBuilder b = new StringBuilder(); final int numGroups = matcher.groupCount(); for (int i = 1; i <= numGroups; i++) { String s = matcher.group(i); if (s != null) { b.append(s); } } return b.toString(); } /** * Convenience method to return only the digits and plus signs * in the matching string. * * @param matcher The Matcher object from which digits and plus will * be extracted * * @return A String comprising all of the digits and plus in * the match */ public static final String digitsAndPlusOnly(Matcher matcher) { StringBuilder buffer = new StringBuilder(); String matchingRegion = matcher.group(); for (int i = 0, size = matchingRegion.length(); i < size; i++) { char character = matchingRegion.charAt(i); if (character == ‘+‘ || Character.isDigit(character)) { buffer.append(character); } } return buffer.toString(); } /** * Do not create this static utility class. */ private Patterns() {} }
Android 关于网址,电话号码,邮箱的正则表达式-最权威
标签:
原文地址:http://www.cnblogs.com/zhou-guobao/p/5113849.html