Package nl.siegmann.epublib.html.htmlcleaner

Source Code of nl.siegmann.epublib.html.htmlcleaner.HtmlCleanerBookProcessorTest

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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
package nl.siegmann.epublib.html.htmlcleaner;

import java.io.IOException;

import junit.framework.TestCase;
import nl.siegmann.epublib.Constants;
import nl.siegmann.epublib.bookprocessor.HtmlCleanerBookProcessor;
import nl.siegmann.epublib.domain.Book;
import nl.siegmann.epublib.domain.Resource;
import nl.siegmann.epublib.service.MediatypeService;

public class HtmlCleanerBookProcessorTest extends TestCase {

  public void testSimpleDocument1() {
    Book book = new Book();
    String testInput = "<html><head><title>title</title></head><body>Hello, world!</html>";
    String expectedResult = Constants.DOCTYPE_XHTML + "\n<html xmlns=\"http://www.w3.org/1999/xhtml\"><head><title>title</title></head><body>Hello, world!</body></html>";
    try {
      Resource resource = new Resource(testInput.getBytes(Constants.CHARACTER_ENCODING), "test.html");
      book.getResources().add(resource);
      HtmlCleanerBookProcessor htmlCleanerBookProcessor = new HtmlCleanerBookProcessor();
      byte[] processedHtml = htmlCleanerBookProcessor.processHtml(resource, book, Constants.CHARACTER_ENCODING);
      String actualResult = new String(processedHtml, Constants.CHARACTER_ENCODING);
      assertEquals(expectedResult, actualResult);
    } catch (IOException e) {
      assertTrue(e.getMessage(), false);
    }
  }
 
  public void testSimpleDocument2() {
    Book book = new Book();
    String testInput = "<html xmlns=\"http://www.w3.org/1999/xhtml\"><head><title>test page</title><link foo=\"bar\" /></head><body background=\"red\">Hello, world!</body></html>";
    try {
      Resource resource = new Resource(testInput.getBytes(Constants.CHARACTER_ENCODING), "test.html");
      book.getResources().add(resource);
      HtmlCleanerBookProcessor htmlCleanerBookProcessor = new HtmlCleanerBookProcessor();
      byte[] processedHtml = htmlCleanerBookProcessor.processHtml(resource, book, Constants.CHARACTER_ENCODING);
      String result = new String(processedHtml, Constants.CHARACTER_ENCODING);
      assertEquals(Constants.DOCTYPE_XHTML + "\n" + testInput, result);
    } catch (IOException e) {
      assertTrue(e.getMessage(), false);
    }
  }
 
  public void testSimpleDocument3() {
    Book book = new Book();
    String testInput = "<html xmlns=\"http://www.w3.org/1999/xhtml\"><head><title>test page</title></head><body>Hello, world! ß</body></html>";
    try {
      Resource resource = new Resource(null, testInput.getBytes(Constants.CHARACTER_ENCODING), "test.html", MediatypeService.XHTML, Constants.CHARACTER_ENCODING);
      book.getResources().add(resource);
      HtmlCleanerBookProcessor htmlCleanerBookProcessor = new HtmlCleanerBookProcessor();
      byte[] processedHtml = htmlCleanerBookProcessor.processHtml(resource, book, Constants.CHARACTER_ENCODING);
      String result = new String(processedHtml, Constants.CHARACTER_ENCODING);
      assertEquals(Constants.DOCTYPE_XHTML + "\n" + testInput, result);
    } catch (IOException e) {
      assertTrue(e.getMessage(), false);
    }
  }
 
  public void testSimpleDocument4() {
    Book book = new Book();
    String testInput = "<html><head><title>title</title></head><body>Hello, world!\nHow are you ?</html>";
    String expectedResult = Constants.DOCTYPE_XHTML + "\n<html xmlns=\"http://www.w3.org/1999/xhtml\"><head><title>title</title></head><body>Hello, world!\nHow are you ?</body></html>";
    try {
      Resource resource = new Resource(testInput.getBytes(Constants.CHARACTER_ENCODING), "test.html");
      book.getResources().add(resource);
      HtmlCleanerBookProcessor htmlCleanerBookProcessor = new HtmlCleanerBookProcessor();
      byte[] processedHtml = htmlCleanerBookProcessor.processHtml(resource, book, Constants.CHARACTER_ENCODING);
      String actualResult = new String(processedHtml, Constants.CHARACTER_ENCODING);
      assertEquals(expectedResult, actualResult);
    } catch (IOException e) {
      assertTrue(e.getMessage(), false);
    }
  }


  public void testMetaContentType() {
    Book book = new Book();
    String testInput = "<html><head><title>title</title><meta http-equiv=\"Content-Type\" content=\"text/html; charset=iso-8859-1\"/></head><body>Hello, world!</html>";
    String expectedResult = Constants.DOCTYPE_XHTML + "\n<html xmlns=\"http://www.w3.org/1999/xhtml\"><head><title>title</title><meta http-equiv=\"Content-Type\" content=\"text/html; charset=" + Constants.CHARACTER_ENCODING + "\" /></head><body>Hello, world!</body></html>";
    try {
      Resource resource = new Resource(testInput.getBytes(Constants.CHARACTER_ENCODING), "test.html");
      book.getResources().add(resource);
      HtmlCleanerBookProcessor htmlCleanerBookProcessor = new HtmlCleanerBookProcessor();
      byte[] processedHtml = htmlCleanerBookProcessor.processHtml(resource, book, Constants.CHARACTER_ENCODING);
      String actualResult = new String(processedHtml, Constants.CHARACTER_ENCODING);
      assertEquals(expectedResult, actualResult);
    } catch (IOException e) {
      assertTrue(e.getMessage(), false);
    }
  }
 
  public void testDocType1() {
    Book book = new Book();
    String testInput = "<html><head><title>title</title><meta http-equiv=\"Content-Type\" content=\"text/html; charset=iso-8859-1\"/></head><body>Hello, world!</html>";
    String expectedResult = Constants.DOCTYPE_XHTML + "\n<html xmlns=\"http://www.w3.org/1999/xhtml\"><head><title>title</title><meta http-equiv=\"Content-Type\" content=\"text/html; charset=" + Constants.CHARACTER_ENCODING + "\" /></head><body>Hello, world!</body></html>";
    try {
      Resource resource = new Resource(testInput.getBytes(Constants.CHARACTER_ENCODING), "test.html");
      book.getResources().add(resource);
      HtmlCleanerBookProcessor htmlCleanerBookProcessor = new HtmlCleanerBookProcessor();
      byte[] processedHtml = htmlCleanerBookProcessor.processHtml(resource, book, Constants.CHARACTER_ENCODING);
      String actualResult = new String(processedHtml, Constants.CHARACTER_ENCODING);
      assertEquals(expectedResult, actualResult);
    } catch (IOException e) {
      assertTrue(e.getMessage(), false);
    }
  }

  public void testDocType2() {
    Book book = new Book();
    String testInput = Constants.DOCTYPE_XHTML + "\n<html><head><title>title</title><meta http-equiv=\"Content-Type\" content=\"text/html; charset=iso-8859-1\"/></head><body>Hello, world!</html>";
    String expectedResult = Constants.DOCTYPE_XHTML + "\n<html xmlns=\"http://www.w3.org/1999/xhtml\"><head><title>title</title><meta http-equiv=\"Content-Type\" content=\"text/html; charset=" + Constants.CHARACTER_ENCODING + "\" /></head><body>Hello, world!</body></html>";
    try {
      Resource resource = new Resource(testInput.getBytes(Constants.CHARACTER_ENCODING), "test.html");
      book.getResources().add(resource);
      HtmlCleanerBookProcessor htmlCleanerBookProcessor = new HtmlCleanerBookProcessor();
      byte[] processedHtml = htmlCleanerBookProcessor.processHtml(resource, book, Constants.CHARACTER_ENCODING);
      String actualResult = new String(processedHtml, Constants.CHARACTER_ENCODING);
      assertEquals(expectedResult, actualResult);
    } catch (IOException e) {
      assertTrue(e.getMessage(), false);
    }
  }

  public void testXmlNS() {
    Book book = new Book();
    String testInput = "<html><head><title>title</title></head><body xmlns:xml=\"xml\">Hello, world!</html>";
    String expectedResult = Constants.DOCTYPE_XHTML + "\n<html xmlns=\"http://www.w3.org/1999/xhtml\"><head><title>title</title></head><body>Hello, world!</body></html>";
    try {
      Resource resource = new Resource(testInput.getBytes(Constants.CHARACTER_ENCODING), "test.html");
      book.getResources().add(resource);
      HtmlCleanerBookProcessor htmlCleanerBookProcessor = new HtmlCleanerBookProcessor();
      byte[] processedHtml = htmlCleanerBookProcessor.processHtml(resource, book, Constants.CHARACTER_ENCODING);
      String actualResult = new String(processedHtml, Constants.CHARACTER_ENCODING);
      assertEquals(expectedResult, actualResult);
    } catch (IOException e) {
      assertTrue(e.getMessage(), false);
    }
  }
  public void testApos() {
    Book book = new Book();
    String testInput = "<html xmlns=\"http://www.w3.org/1999/xhtml\"><head><title>test page</title></head><body>'hi'</body></html>";
    try {
      Resource resource = new Resource(null, testInput.getBytes(Constants.CHARACTER_ENCODING), "test.html", MediatypeService.XHTML, Constants.CHARACTER_ENCODING);
      book.getResources().add(resource);
      HtmlCleanerBookProcessor htmlCleanerBookProcessor = new HtmlCleanerBookProcessor();
      byte[] processedHtml = htmlCleanerBookProcessor.processHtml(resource, book, Constants.CHARACTER_ENCODING);
      String result = new String(processedHtml, Constants.CHARACTER_ENCODING);
      assertEquals(Constants.DOCTYPE_XHTML + "\n" + testInput, result);
    } catch (IOException e) {
      assertTrue(e.getMessage(), false);
    }
  }
}
TOP

Related Classes of nl.siegmann.epublib.html.htmlcleaner.HtmlCleanerBookProcessorTest

  • nl.siegmann.epublib.bookprocessor.HtmlCleanerBookProcessor
  • nl.siegmann.epublib.domain.Book
  • nl.siegmann.epublib.domain.Resource
    • TOP
    Copyright © 2018 www.massapi.com. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.