001/* 002 * (C) Copyright 2012 Nuxeo SA (http://nuxeo.com/) and others. 003 * 004 * Licensed under the Apache License, Version 2.0 (the "License"); 005 * you may not use this file except in compliance with the License. 006 * You may obtain a copy of the License at 007 * 008 * http://www.apache.org/licenses/LICENSE-2.0 009 * 010 * Unless required by applicable law or agreed to in writing, software 011 * distributed under the License is distributed on an "AS IS" BASIS, 012 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 013 * See the License for the specific language governing permissions and 014 * limitations under the License. 015 * 016 * Contributors: 017 * Antoine Taillefer 018 */ 019package org.nuxeo.ecm.diff.content; 020 021import java.util.regex.Matcher; 022import java.util.regex.Pattern; 023 024/** 025 * Handles HTML detection in a string. 026 * 027 * @author <a href="mailto:[email protected]">Antoine Taillefer</a> 028 * @since 5.6 029 */ 030public final class HtmlGuesser { 031 032 public static final String HTML_TAG_REGEXP = "<.*?>.*?</.*?>"; 033 034 /** 035 * Checks if the specified text can be considered as HTML code. 036 * 037 * @param text the text 038 * @return true, if the specified text contains at least one HTML tag. 039 */ 040 public static boolean isHtml(String text) { 041 Pattern pattern = Pattern.compile(HTML_TAG_REGEXP); 042 Matcher matcher = pattern.matcher(text); 043 return matcher.find(); 044 } 045}