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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
|
<?php
use PHPUnit\Framework\TestCase;
class MarkdownTestHelper
{
/**
* Takes an input directory containing .text and .(x)html files, and returns an array
* of .text files and the corresponding output xhtml or html file. Can be used in a unit test data provider.
*
* @param string $directory Input directory
*
* @return array
*/
public static function getInputOutputPaths($directory) {
$iterator = new RecursiveIteratorIterator(new RecursiveDirectoryIterator($directory));
$regexIterator = new RegexIterator(
$iterator,
'/^.+\.text$/',
RecursiveRegexIterator::GET_MATCH
);
$dataValues = array();
/** @var SplFileInfo $inputFile */
foreach ($regexIterator as $inputFiles) {
foreach ($inputFiles as $inputMarkdownPath) {
$xhtml = true;
$expectedHtmlPath = substr($inputMarkdownPath, 0, -4) . 'xhtml';
if (!file_exists($expectedHtmlPath)) {
$expectedHtmlPath = substr($inputMarkdownPath, 0, -4) . 'html';
$xhtml = false;
}
$dataValues[] = array($inputMarkdownPath, $expectedHtmlPath, $xhtml);
}
}
return $dataValues;
}
/**
* Applies PHPUnit's assertSame after normalizing both strings (e.g. ignoring whitespace differences).
* Uses logic found originally in MDTest.
*
* @param string $string1
* @param string $string2
* @param string $message Positive message to print when test fails (e.g. "String1 matches String2")
* @param bool $xhtml
*/
public static function assertSameNormalized($string1, $string2, $message, $xhtml = true) {
$t_result = $string1;
$t_output = $string2;
// DOMDocuments
if ($xhtml) {
$document = new DOMDocument();
$doc_result = $document->loadXML('<!DOCTYPE html>' .
"<html xmlns='http://www.w3.org/1999/xhtml'>" .
"<body>$t_result</body></html>");
$document2 = new DOMDocument();
$doc_output = $document2->loadXML('<!DOCTYPE html>' .
"<html xmlns='http://www.w3.org/1999/xhtml'>" .
"<body>$t_output</body></html>");
if ($doc_result) {
static::normalizeElementContent($document->documentElement, false);
$n_result = $document->saveXML();
} else {
$n_result = '--- Expected Result: XML Parse Error ---';
}
if ($doc_output) {
static::normalizeElementContent($document2->documentElement, false);
$n_output = $document2->saveXML();
} else {
$n_output = '--- Output: XML Parse Error ---';
}
} else {
// '@' suppressors used because some tests have invalid HTML (multiple elements with the same id attribute)
// Perhaps isolate to a separate test and remove this?
$document = new DOMDocument();
$doc_result = @$document->loadHTML($t_result);
$document2 = new DOMDocument();
$doc_output = @$document2->loadHTML($t_output);
if ($doc_result) {
static::normalizeElementContent($document->documentElement, false);
$n_result = $document->saveHTML();
} else {
$n_result = '--- Expected Result: HTML Parse Error ---';
}
if ($doc_output) {
static::normalizeElementContent($document2->documentElement, false);
$n_output = $document2->saveHTML();
} else {
$n_output = '--- Output: HTML Parse Error ---';
}
}
$n_result = preg_replace('{^.*?<body>|</body>.*?$}is', '', $n_result);
$n_output = preg_replace('{^.*?<body>|</body>.*?$}is', '', $n_output);
$c_result = $n_result;
$c_output = $n_output;
$c_result = trim($c_result) . "\n";
$c_output = trim($c_output) . "\n";
// This will throw a test exception if the strings don't exactly match
TestCase::assertSame($c_result, $c_output, $message);
}
/**
* @param DOMElement $element Modifies this element by reference
* @param bool $whitespace_preserve Preserve Whitespace
* @return void
*/
protected static function normalizeElementContent($element, $whitespace_preserve) {
#
# Normalize content of HTML DOM $element. The $whitespace_preserve
# argument indicates that whitespace is significant and shouldn't be
# normalized; it should be used for the content of certain elements like
# <pre> or <script>.
#
$node_list = $element->childNodes;
switch (strtolower($element->nodeName)) {
case 'body':
case 'div':
case 'blockquote':
case 'ul':
case 'ol':
case 'dl':
case 'h1':
case 'h2':
case 'h3':
case 'h4':
case 'h5':
case 'h6':
$whitespace = "\n\n";
break;
case 'table':
$whitespace = "\n";
break;
case 'pre':
case 'script':
case 'style':
case 'title':
$whitespace_preserve = true;
$whitespace = "";
break;
default:
$whitespace = "";
break;
}
foreach ($node_list as $node) {
switch ($node->nodeType) {
case XML_ELEMENT_NODE:
static::normalizeElementContent($node, $whitespace_preserve);
static::normalizeElementAttributes($node);
switch (strtolower($node->nodeName)) {
case 'p':
case 'div':
case 'hr':
case 'blockquote':
case 'ul':
case 'ol':
case 'dl':
case 'li':
case 'address':
case 'table':
case 'dd':
case 'pre':
case 'h1':
case 'h2':
case 'h3':
case 'h4':
case 'h5':
case 'h6':
$whitespace = "\n\n";
break;
case 'tr':
case 'td':
case 'dt':
$whitespace = "\n";
break;
default:
$whitespace = "";
break;
}
if (($whitespace === "\n\n" || $whitespace === "\n") &&
$node->nextSibling &&
$node->nextSibling->nodeType != XML_TEXT_NODE) {
$element->insertBefore(new DOMText($whitespace), $node->nextSibling);
}
break;
case XML_TEXT_NODE:
if (!$whitespace_preserve) {
if (trim($node->data) === "") {
$node->data = $whitespace;
}
else {
$node->data = preg_replace('{\s+}', ' ', $node->data);
}
}
break;
}
}
if (!$whitespace_preserve &&
($whitespace === "\n\n" || $whitespace === "\n")) {
if ($element->firstChild) {
if ($element->firstChild->nodeType == XML_TEXT_NODE) {
$element->firstChild->data =
preg_replace('{^\s+}', "\n", $element->firstChild->data);
}
else {
$element->insertBefore(new DOMText("\n"), $element->firstChild);
}
}
if ($element->lastChild) {
if ($element->lastChild->nodeType == XML_TEXT_NODE) {
$element->lastChild->data =
preg_replace('{\s+$}', "\n", $element->lastChild->data);
}
else {
$element->insertBefore(new DOMText("\n"), null);
}
}
}
}
/**
* @param DOMElement $element Modifies this element by reference
*/
protected static function normalizeElementAttributes (DOMElement $element)
{
#
# Sort attributes by name.
#
// Gather the list of attributes as an array.
$attr_list = array();
foreach ($element->attributes as $attr_node) {
$attr_list[$attr_node->name] = $attr_node;
}
// Sort attribute list by name.
ksort($attr_list);
// Remove then put back each attribute following sort order.
foreach ($attr_list as $attr_node) {
$element->removeAttributeNode($attr_node);
$element->setAttributeNode($attr_node);
}
}
}
|
