2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.0b1)
3 * Copyright (C) 2014 The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
11 * Jalview is distributed in the hope that it will be useful, but
12 * WITHOUT ANY WARRANTY; without even the implied warranty
13 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
14 * PURPOSE. See the GNU General Public License for more details.
16 * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
17 * The Jalview Authors are detailed in the 'AUTHORS' file.
21 import java.util.ArrayList;
22 import java.util.StringTokenizer;
23 import java.util.regex.Pattern;
26 * utility class for dealing with HTML link extraction
31 public class ParseHtmlBodyAndLinks
35 public String getOrig()
40 boolean htmlContent = true;
43 * @return true if the content looked like HTML
45 public boolean isHtmlContent()
50 ArrayList<String> links = new ArrayList<String>();
52 StringBuffer sb = new StringBuffer();
55 * result of parsing description - with or without HTML tags
59 public String getContent()
66 * list of Label|Link encoded URL links extracted from HTML
70 public ArrayList<String> getLinks()
78 * - html or text content to be parsed
80 * flag to indicate if HTML tags should be removed if they are
84 public ParseHtmlBodyAndLinks(String description, boolean removeHTML,
87 if (description == null || description.length() == 0)
92 if (description.toUpperCase().indexOf("<HTML>") == -1)
97 StringTokenizer st = new StringTokenizer(description, "<");
101 while (st.hasMoreElements())
103 token = st.nextToken("&>");
104 if (token.equalsIgnoreCase("html") || token.startsWith("/"))
110 startTag = token.indexOf("<");
114 tag = token.substring(startTag + 1);
115 token = token.substring(0, startTag);
118 if (tag != null && tag.toUpperCase().startsWith("A HREF="))
120 if (token.length() > 0)
124 link = tag.substring(tag.indexOf("\"") + 1, tag.length() - 1);
125 String label = st.nextToken("<>");
126 links.add(label + "|" + link);
127 sb.append(label + "%LINK%");
129 else if (tag != null && tag.equalsIgnoreCase("br"))
133 else if (token.startsWith("lt;"))
135 sb.append("<" + token.substring(3));
137 else if (token.startsWith("gt;"))
139 sb.append(">" + token.substring(3));
141 else if (token.startsWith("amp;"))
143 sb.append("&" + token.substring(4));
150 if (removeHTML && !htmlContent)
152 // instead of parsing the html into plaintext
153 // clean the description ready for embedding in html
154 sb = new StringBuffer(Pattern.compile("<").matcher(description)
155 .replaceAll("<"));
162 * get either the parsed content or the original, depending on whether the
163 * original looked like html content or not.
167 public String getNonHtmlContent()
169 return isHtmlContent() ? sb.toString() : orig;