1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
namespace Mfonte\Sitemap\Renderer; |
4
|
|
|
|
5
|
|
|
use \DateTime; |
|
|
|
|
6
|
|
|
|
7
|
|
|
use Mfonte\Sitemap\Tags\Sitemap; |
8
|
|
|
use Mfonte\Sitemap\Tags\Url; |
9
|
|
|
|
10
|
|
|
class NativeRenderer |
11
|
|
|
{ |
12
|
|
|
/** |
13
|
|
|
* Params Array. Should be injected into current instance with a compact() call, for example: compact('tags', 'hasImages', 'hasNews') |
14
|
|
|
* |
15
|
|
|
* @var array |
16
|
|
|
*/ |
17
|
|
|
private array $params; |
18
|
|
|
private string $tempFile; |
19
|
|
|
|
20
|
|
|
public static function instance(array $params) : self |
21
|
|
|
{ |
22
|
|
|
return new self($params); |
23
|
|
|
} |
24
|
|
|
|
25
|
|
|
public function __construct(array $params) |
26
|
|
|
{ |
27
|
|
|
$this->params = $params; |
28
|
|
|
$this->tempFile = tempnam(sys_get_temp_dir(), 'mfonte_sitemap_nativerenderer_' . sha1(uniqid())); |
29
|
|
|
} |
30
|
|
|
|
31
|
|
|
/** |
32
|
|
|
* Renders the sitemap or sitemap index |
33
|
|
|
* |
34
|
|
|
* @param string $type - sitemap or sitemapIndex |
35
|
|
|
* |
36
|
|
|
* @return string |
37
|
|
|
*/ |
38
|
|
|
public function render(string $type) : string |
39
|
|
|
{ |
40
|
|
|
try { |
41
|
|
|
switch($type) { |
42
|
|
|
case 'sitemap': |
43
|
|
|
$this->renderSitemap(); |
44
|
|
|
|
45
|
|
|
break; |
46
|
|
|
case 'sitemapIndex': |
47
|
|
|
$this->renderSitemapIndex(); |
48
|
|
|
|
49
|
|
|
break; |
50
|
|
|
default: |
51
|
|
|
throw new \Exception('Invalid Render Type', 999); |
52
|
|
|
} |
53
|
|
|
} catch(\Exception $e) { |
54
|
|
|
if ($e->getCode() === 999) { |
55
|
|
|
throw new \Exception('The render type must be "sitemap" or "sitemapIndex"'); |
56
|
|
|
} |
57
|
|
|
|
58
|
|
|
throw new \Exception('Error while rendering the xml: ' . $e->getMessage()); |
59
|
|
|
} |
60
|
|
|
|
61
|
|
|
// if the tidy extension is not available, return the xml as it was rendered natively. |
62
|
|
|
if (! function_exists('tidy_parse_file')) { |
63
|
|
|
return $this->asString(); |
64
|
|
|
} |
65
|
|
|
|
66
|
|
|
// if the tidy extension is available, format the xml with tidy |
67
|
|
|
$tidyInstance = tidy_parse_file($this->tempFile, [ |
68
|
|
|
'indent' => true, |
69
|
|
|
'output-xml' => true, |
70
|
|
|
'input-xml' => true, |
71
|
|
|
'wrap' => 0, |
72
|
|
|
'indent-spaces' => 2, |
73
|
|
|
'newline' => 'LF', |
74
|
|
|
]); |
75
|
|
|
|
76
|
|
|
if ($tidyInstance === false) { |
77
|
|
|
throw new \Exception('Tidy: Error while loading the Sitemap xml with tidy_parse_file()'); |
78
|
|
|
} |
79
|
|
|
|
80
|
|
|
if ($tidyInstance->errorBuffer) { |
81
|
|
|
throw new \Exception('Tidy: Errors while loading the Sitemap xml with tidy_parse_file(): ' . "\n" . $tidyInstance->errorBuffer); |
82
|
|
|
} |
83
|
|
|
|
84
|
|
|
$formatted = tidy_clean_repair($tidyInstance); |
85
|
|
|
if ($formatted === false) { |
86
|
|
|
throw new \Exception('Tidy: Error while cleaning the Sitemap xml'); |
87
|
|
|
} |
88
|
|
|
|
89
|
|
|
// save the formatted xml back to the temporary file |
90
|
|
|
file_put_contents($this->tempFile, (string) $tidyInstance); |
91
|
|
|
|
92
|
|
|
return $this->asString(); |
93
|
|
|
} |
94
|
|
|
|
95
|
|
|
/** |
96
|
|
|
* Renders the sitemap index |
97
|
|
|
*/ |
98
|
|
|
private function renderSitemapIndex() |
99
|
|
|
{ |
100
|
|
|
$this->append('<?xml version="1.0" encoding="UTF-8"?>'); |
101
|
|
|
$this->append('<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">'); |
102
|
|
|
|
103
|
|
|
foreach ($this->params['tags'] as $tag) { |
104
|
|
|
/** @var Sitemap $tag */ |
105
|
|
|
|
106
|
|
|
$this->append('<sitemap>', 1); |
107
|
|
|
if (! empty($tag->url)) { |
108
|
|
|
$this->append('<loc>' . $this->format(url($tag->url)) . '</loc>', 2); |
109
|
|
|
} |
110
|
|
|
|
111
|
|
|
if (! empty($tag->lastModificationDate)) { |
112
|
|
|
$this->append('<lastmod>' . $tag->lastModificationDate->format(DateTime::ATOM) . '</lastmod>', 2); |
113
|
|
|
} |
114
|
|
|
|
115
|
|
|
$this->append('</sitemap>', 1); |
116
|
|
|
} |
117
|
|
|
|
118
|
|
|
$this->append('</sitemapindex>'); |
119
|
|
|
} |
120
|
|
|
|
121
|
|
|
/** |
122
|
|
|
* Renders the sitemap |
123
|
|
|
*/ |
124
|
|
|
private function renderSitemap() |
125
|
|
|
{ |
126
|
|
|
$this->append('<?xml version="1.0" encoding="UTF-8"?>'); |
127
|
|
|
$this->append('<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml"', 0, false); |
128
|
|
|
if ($this->params['hasImages']) { |
129
|
|
|
$this->append(' xmlns:image="http://www.google.com/schemas/sitemap-image/1.1"', 0, false); |
130
|
|
|
} |
131
|
|
|
if ($this->params['hasNews']) { |
132
|
|
|
$this->append(' xmlns:news="http://www.google.com/schemas/sitemap-news/0.9"', 0, false); |
133
|
|
|
} |
134
|
|
|
$this->append('>', 0); |
135
|
|
|
|
136
|
|
|
foreach ($this->params['tags'] as $tag) { |
137
|
|
|
$this->renderUrl($tag); |
138
|
|
|
} |
139
|
|
|
|
140
|
|
|
$this->append('</urlset>', 0, false); |
141
|
|
|
} |
142
|
|
|
|
143
|
|
|
/** |
144
|
|
|
* Renders a Url tag |
145
|
|
|
* |
146
|
|
|
* @param Url $tag |
147
|
|
|
*/ |
148
|
|
|
private function renderUrl(Url $tag) |
149
|
|
|
{ |
150
|
|
|
$this->append('<url>', 1); |
151
|
|
|
if (! empty($tag->url)) { |
152
|
|
|
$this->append('<loc>' . $this->format(url($tag->url)) . '</loc>', 2); |
153
|
|
|
} |
154
|
|
|
if (count($tag->alternates)) { |
155
|
|
|
foreach ($tag->alternates as $alternate) { |
156
|
|
|
$this->append('<xhtml:link rel="alternate" hreflang="' . $this->format($alternate->locale) . '" href="' . $this->format(url($alternate->url)) . '" />', 2); |
157
|
|
|
} |
158
|
|
|
} |
159
|
|
|
if (! empty($tag->lastModificationDate)) { |
160
|
|
|
$this->append('<lastmod>' . $tag->lastModificationDate->format(DateTime::ATOM) . '</lastmod>', 2); |
161
|
|
|
} |
162
|
|
|
if (! empty($tag->changeFrequency)) { |
163
|
|
|
$this->append('<changefreq>' . $this->format($tag->changeFrequency) . '</changefreq>', 2); |
164
|
|
|
} |
165
|
|
|
if (! empty($tag->priority)) { |
166
|
|
|
$this->append('<priority>' . number_format($tag->priority, 1) . '</priority>', 2); |
167
|
|
|
} |
168
|
|
|
if (count($tag->images)) { |
169
|
|
|
foreach ($tag->images as $image) { |
170
|
|
|
if (! empty($image->url)) { |
171
|
|
|
$this->append('<image:image>', 2); |
172
|
|
|
$this->append('<image:loc>' . url($image->url) . '</image:loc>', 3); |
173
|
|
|
if (! empty($image->caption)) { |
174
|
|
|
$this->append('<image:caption>' . $this->format($image->caption) . '</image:caption>', 3); |
175
|
|
|
} |
176
|
|
|
if (! empty($image->geo_location)) { |
177
|
|
|
$this->append('<image:geo_location>' . $this->format($image->geo_location) . '</image:geo_location>', 3); |
178
|
|
|
} |
179
|
|
|
if (! empty($image->title)) { |
180
|
|
|
$this->append('<image:title>' . $this->format($image->title) . '</image:title>', 3); |
181
|
|
|
} |
182
|
|
|
if (! empty($image->license)) { |
183
|
|
|
$this->append('<image:license>' . $this->format($image->license) . '</image:license>', 3); |
184
|
|
|
} |
185
|
|
|
$this->append('</image:image>', 2); |
186
|
|
|
} |
187
|
|
|
} |
188
|
|
|
} |
189
|
|
|
if (count($tag->news)) { |
190
|
|
|
foreach ($tag->news as $new) { |
191
|
|
|
$this->append('<news:news>', 2); |
192
|
|
|
if (! empty($new->publication_date)) { |
193
|
|
|
$this->append('<news:publication_date>' . $new->publication_date->format('Y-m-d') . '</news:publication_date>', 3); |
194
|
|
|
} |
195
|
|
|
if (! empty($new->title)) { |
196
|
|
|
$this->append('<news:title>' . $this->format($new->title) . '</news:title>', 3); |
197
|
|
|
} |
198
|
|
|
if (! empty($new->name) || ! empty($new->language)) { |
199
|
|
|
$this->append('<news:publication>', 3); |
200
|
|
|
if (! empty($new->name)) { |
201
|
|
|
$this->append('<news:name>' . $this->format($new->name) . '</news:name>', 4); |
202
|
|
|
} |
203
|
|
|
|
204
|
|
|
if (! empty($new->language)) { |
205
|
|
|
$this->append('<news:language>' . $this->format($new->language) . '</news:language>', 4); |
206
|
|
|
} |
207
|
|
|
$this->append('</news:publication>', 3); |
208
|
|
|
} |
209
|
|
|
$this->append('</news:news>', 2); |
210
|
|
|
} |
211
|
|
|
} |
212
|
|
|
|
213
|
|
|
$this->append('</url>', 1); |
214
|
|
|
} |
215
|
|
|
|
216
|
|
|
/** |
217
|
|
|
* Returns the contents of the temporary file as a string |
218
|
|
|
* |
219
|
|
|
* @return string |
220
|
|
|
*/ |
221
|
|
|
private function asString() : string |
222
|
|
|
{ |
223
|
|
|
if (!is_file($this->tempFile)) { |
224
|
|
|
throw new \Exception('The generated Sitemap temporary file does not exist'); |
225
|
|
|
} |
226
|
|
|
|
227
|
|
|
if (!is_readable($this->tempFile)) { |
228
|
|
|
throw new \Exception('The generated Sitemap temporary file is not readable'); |
229
|
|
|
} |
230
|
|
|
|
231
|
|
|
$contents = file_get_contents($this->tempFile); |
232
|
|
|
unlink($this->tempFile); |
233
|
|
|
|
234
|
|
|
if ($contents === false) { |
235
|
|
|
throw new \Exception('Error while reading the generated Sitemap temporary file'); |
236
|
|
|
} |
237
|
|
|
if (empty($contents)) { |
238
|
|
|
throw new \Exception('The generated Sitemap temporary file is empty'); |
239
|
|
|
} |
240
|
|
|
|
241
|
|
|
return $contents; |
242
|
|
|
} |
243
|
|
|
|
244
|
|
|
/** |
245
|
|
|
* Appends content to the temporary file |
246
|
|
|
* |
247
|
|
|
* @param string $content |
248
|
|
|
* @param string $indentLevel |
249
|
|
|
* @param string $newline |
250
|
|
|
*/ |
251
|
|
|
private function append(string $content, int $indentLevel = 0, bool $newline = true) |
252
|
|
|
{ |
253
|
|
|
if (!is_file($this->tempFile)) { |
254
|
|
|
@touch($this->tempFile); |
|
|
|
|
255
|
|
|
} |
256
|
|
|
|
257
|
|
|
if (!is_file($this->tempFile)) { |
258
|
|
|
throw new \Exception('The temporary file does not exist'); |
259
|
|
|
} |
260
|
|
|
|
261
|
|
|
if (!is_writable($this->tempFile)) { |
262
|
|
|
throw new \Exception('The temporary file is not writable'); |
263
|
|
|
} |
264
|
|
|
|
265
|
|
|
$content = ($indentLevel) ? str_repeat(' ', $indentLevel * 2) . $content : $content; |
266
|
|
|
$content = ($newline) ? $content . "\n" : $content; |
267
|
|
|
$result = file_put_contents($this->tempFile, $content, FILE_APPEND); |
268
|
|
|
|
269
|
|
|
if ($result === false) { |
270
|
|
|
throw new \Exception('Error while writing to the temporary file'); |
271
|
|
|
} |
272
|
|
|
} |
273
|
|
|
|
274
|
|
|
/** |
275
|
|
|
* Formats a tag text so that it does not contain invalid characters for the XML format. |
276
|
|
|
* |
277
|
|
|
* @param string|null $text |
278
|
|
|
* |
279
|
|
|
* @return string |
280
|
|
|
*/ |
281
|
|
|
private function format(?string $text = null) : string |
282
|
|
|
{ |
283
|
|
|
$text = html_entity_decode($text ?? '', ENT_QUOTES | ENT_IGNORE, 'UTF-8'); |
284
|
|
|
|
285
|
|
|
// remove any occurrence of UTF-8 encoding of a NO-BREAK SPACE codepoint, that we have decoded above |
286
|
|
|
$text = str_replace(chr(194).chr(160), ' ', $text); |
287
|
|
|
$text = trim(preg_replace('/\s\s+/', ' ', $text)); |
288
|
|
|
|
289
|
|
|
return trim(htmlspecialchars($text, ENT_QUOTES | ENT_IGNORE, 'UTF-8')); |
290
|
|
|
} |
291
|
|
|
} |
292
|
|
|
|
The issue could also be caused by a filter entry in the build configuration. If the path has been excluded in your configuration, e.g.
excluded_paths: ["lib/*"]
, you can move it to the dependency path list as follows:For further information see https://scrutinizer-ci.com/docs/tools/php/php-scrutinizer/#list-dependency-paths