Classes

Class	Line #	Total Statements	Complexity	TOTAL Coverage	Actions
ParseHtmlBodyAndLinks	36	42	22	0.00%	Show methods

Class ParseHtmlBodyAndLinks

Class ParseHtmlBodyAndLinks	Line # 36	Total Statements 42	Complexity 22	TOTAL Coverage 0.00%
getOrig() : String   getOrig() : String	4343	1.01	1.01	0.0 0.00%
isHtmlContent() : boolean   isHtmlContent() : boolean	5353	1.01	1.01	0.0 0.00%
getContent() : String   getContent() : String	6767	1.01	1.01	0.0 0.00%
getLinks() : List<String>   getLinks() : List<String>	7878	1.01	1.01	0.0 0.00%
ParseHtmlBodyAndLinks(String,boolean,String)   ParseHtmlBodyAndLinks(String,boolean,String)	9999	33.033	15.015	0.0 0.00%
translateEntities(String) : String   translateEntities(String) : String	164164	4.04	1.01	0.0 0.00%
getNonHtmlContent() : String   getNonHtmlContent() : String	178178	1.01	2.02	0.0 0.00%

 

Contributing tests

Source view

1		/*
2		* Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3		* Copyright (C) $$Year-Rel$$ The Jalview Authors
4		*
5		* This file is part of Jalview.
6		*
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
10		* of the License, or (at your option) any later version.
11		*
12		* Jalview is distributed in the hope that it will be useful, but
13		* WITHOUT ANY WARRANTY; without even the implied warranty
14		* of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15		* PURPOSE. See the GNU General Public License for more details.
16		*
17		* You should have received a copy of the GNU General Public License
18		* along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19		* The Jalview Authors are detailed in the 'AUTHORS' file.
20		*/
21		package jalview.util;
22
23		import java.util.Locale;
24
25		import java.util.ArrayList;
26		import java.util.List;
27		import java.util.StringTokenizer;
28		import java.util.regex.Pattern;
29
30		/**
31		* utility class for dealing with HTML link extraction
32		*
33		* @author jprocter
34		*
35		*/
		0% Uncovered Elements: 69 (69) Complexity: 22 Complexity Density: 0.52
36		public class ParseHtmlBodyAndLinks
37		{
38		private static final Pattern LEFT_ANGLE_BRACKET_PATTERN = Pattern
39		.compile("<");
40
41		String orig = null;
42
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
43	0	public String getOrig()...
44		{
45	0	return orig;
46		}
47
48		boolean htmlContent = true;
49
50		/**
51		* @return true if the content looked like HTML
52		*/
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
53	0	public boolean isHtmlContent()...
54		{
55	0	return htmlContent;
56		}
57
58		List<String> links = new ArrayList<String>();
59
60		String content;
61
62		/**
63		* result of parsing description - with or without HTML tags
64		*
65		* @return
66		*/
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
67	0	public String getContent()...
68		{
69
70	0	return content;
71		}
72
73		/**
74		* list of Label|Link encoded URL links extracted from HTML
75		*
76		* @return
77		*/
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
78	0	public List<String> getLinks()...
79		{
80	0	return links;
81		}
82
83		/**
84		* Parses the given html and
85		* <ul>
86		* <li>extracts any 'href' links to a list of "displayName|url" strings,
87		* retrievable by #getLinks</li>
88		* <li>extracts the remaining text (with %LINK% placeholders replacing hrefs),
89		* retrievable by #getContent</li>
90		* </ul>
91		*
92		* @param description
93		* - html or text content to be parsed
94		* @param removeHTML
95		* flag to indicate if HTML tags should be removed if they are
96		* present.
97		* @param newline
98		*/
		0% Uncovered Elements: 51 (51) Complexity: 15 Complexity Density: 0.45
99	0	public ParseHtmlBodyAndLinks(String description, boolean removeHTML,...
100		String newline)
101		{
102	0	if (description == null || description.length() == 0)
103		{
104	0	htmlContent = false;
105	0	return;
106		}
107	0	StringBuilder sb = new StringBuilder(description.length());
108	0	if (description.toUpperCase(Locale.ROOT).indexOf("<HTML>") == -1)
109		{
110	0	htmlContent = false;
111		}
112	0	orig = description;
113	0	StringTokenizer st = new StringTokenizer(description, "<");
114	0	String token, link;
115	0	int startTag;
116	0	String tag = null;
117	0	while (st.hasMoreElements())
118		{
119	0	token = st.nextToken(">");
120	0	if (token.equalsIgnoreCase("html") || token.startsWith("/"))
121		{
122	0	continue;
123		}
124
125	0	tag = null;
126	0	startTag = token.indexOf("<");
127
128	0	if (startTag > -1)
129		{
130	0	tag = token.substring(startTag + 1);
131	0	token = token.substring(0, startTag);
132		}
133
134	0	if (tag != null && tag.toUpperCase(Locale.ROOT).startsWith("A HREF="))
135		{
136	0	if (token.length() > 0)
137		{
138	0	sb.append(token);
139		}
140	0	link = tag.substring(tag.indexOf("\"") + 1, tag.length() - 1);
141	0	String label = st.nextToken("<>");
142	0	links.add(label + "|" + link);
143	0	sb.append(label + "%LINK%");
144		}
145	0	else if (tag != null && tag.equalsIgnoreCase("br"))
146		{
147	0	sb.append(newline);
148		}
149		else
150		{
151	0	sb.append(token);
152		}
153		}
154	0	if (removeHTML && !htmlContent)
155		{
156		// instead of parsing the html into plaintext
157		// clean the description ready for embedding in html
158	0	sb = new StringBuilder(LEFT_ANGLE_BRACKET_PATTERN.matcher(description)
159		.replaceAll("&lt;"));
160		}
161	0	content = translateEntities(sb.toString());
162		}
163
		0% Uncovered Elements: 4 (4) Complexity: 1 Complexity Density: 0.25
164	0	private String translateEntities(String s)...
165		{
166	0	s = s.replaceAll("&amp;", "&");
167	0	s = s.replaceAll("&lt;", "<");
168	0	s = s.replaceAll("&gt;", ">");
169	0	return s;
170		}
171
172		/**
173		* get either the parsed content or the original, depending on whether the
174		* original looked like html content or not.
175		*
176		* @return
177		*/
		0% Uncovered Elements: 3 (3) Complexity: 2 Complexity Density: 2
178	0	public String getNonHtmlContent()...
179		{
180	0	return isHtmlContent() ? content : orig;
181		}
182
183		}