UrlMatcher.java

/*
 * The MIT License (MIT)
 *
 * Copyright (c) 2014-2015 Umeng, Inc
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 * 
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

package com.umeng.comm.ui.utils;

import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public final class UrlMatcher {
    // url必须以http、https、ftp或者www开头
    private static Pattern sPattern = Pattern
            .compile("(http://|ftp://|https://|www){1}[^\u4e00-\u9fa5\\s]*?\\.(com|net|cn|me|tw|fr)[^\u4e00-\u9fa5\\s]*");

    private UrlMatcher() {
    }

    public static List<String> recognizeUrls(String feedText) {
        List<String> urls = new ArrayList<String>();
        Matcher matcher = sPattern.matcher(feedText);
        while (matcher.find()) {
            urls.add(matcher.group(0));
        }
        return urls;
    }
}