summaryrefslogtreecommitdiffstats
path: root/parsers/DetectHTMLTag.java
blob: 45729278a96255ae76da9e205ffe176a45ce2c32 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
/*+
 *   Copyright 2012, 2013 rsiddharth <rsiddharth@ninthfloor.org>
 *
 *   This file is part of Scruf.
 *
 *   Scruf is free software: you can redistribute it and/or modify
 *   it under the terms of the GNU General Public License as published by
 *   the Free Software Foundation, either version 3 of the License, or
 *   (at your option) any later version.
 *
 *   This program is distributed in the hope that it will be useful,
 *   but WITHOUT ANY WARRANTY; without even the implied warranty of
 *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *   GNU General Public License for more details.
 *
 *   You should have received a copy of the GNU General Public License
 *   along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */


package scruf.parsers;

import java.util.*;
import java.util.regex.*;
import scruf.status.*;

public class DetectHTMLTag {
	private List<String> closingHtmlTags = new ArrayList<String>();
	private Pattern htmlTagPattern = Pattern.compile("^\\<((\\w+?).*?)\\>.*?(\\<\\/\\2\\>)",
													 Pattern.DOTALL);
	private String lastHtmlBlock = null;
	private boolean insideHtmlBlock = false;
	private boolean htmlInScruffy = false;
	public boolean isHtmlTag(String text) {
		Matcher htmlTagMatcher = htmlTagPattern.matcher(text);

		if(htmlTagMatcher.find()) {
			lastHtmlBlock = htmlTagMatcher.group();
			closingHtmlTags.add(htmlTagMatcher.group(3));
			insideHtmlBlock = true;
			return true;
		}else {
			return isClosingHtmlTag(text);
		}
	}

	private boolean isClosingHtmlTag(String text) {
		for(String closingTag: closingHtmlTags) {
			if(text.startsWith(closingTag)) {
				lastHtmlBlock = closingTag;
				closingHtmlTags.remove(closingTag);
				if(closingHtmlTags.isEmpty())
					insideHtmlBlock = false;
				return true;
			}
		}
		return false;
	}

	public boolean isHtmlInScruffy(String text) {
		Integer blankLineCounter;

		if(isHtmlTag(text)) {
			Pattern qText = Pattern.compile("\\Q"+lastHtmlBlock+"\\E");
			htmlInScruffy = qText.matcher(PresentFile.fileContent).find();

			Pattern pBlankLine = Pattern.compile("\\n\\n");
			Matcher mBlankLine = pBlankLine.matcher(lastHtmlBlock);
			blankLineCounter = 0;

			while(mBlankLine.find())
				++blankLineCounter;

			if(blankLineCounter == 0) {
				closingHtmlTags.clear();
				resetEverything();
			}
		}
		return insideHtmlBlock && htmlInScruffy;
	}

	public boolean insideHtmlBlock() {
		return insideHtmlBlock;
	}

	public void resetEverything() {
		insideHtmlBlock = false;
		htmlInScruffy = false;
		lastHtmlBlock = null;
	}
}