|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace SilverStripe\TextExtraction\Extension; |
|
4
|
|
|
|
|
5
|
|
|
use SilverStripe\Assets\File; |
|
6
|
|
|
use SilverStripe\ORM\DataExtension; |
|
7
|
|
|
use SilverStripe\TextExtraction\Cache\FileTextCache; |
|
8
|
|
|
use SilverStripe\TextExtraction\Extractor\FileTextExtractor; |
|
9
|
|
|
|
|
10
|
|
|
/** |
|
11
|
|
|
* Decorate File or a File derivative to enable text extraction from the file content. Uses a set of subclasses of |
|
12
|
|
|
* FileTextExtractor to do the extraction based on the content type of the file. |
|
13
|
|
|
* |
|
14
|
|
|
* Adds an additional property which is the cached contents, which is populated on demand. |
|
15
|
|
|
* |
|
16
|
|
|
* @author mstephens |
|
17
|
|
|
*/ |
|
18
|
|
|
class FileTextExtractable extends DataExtension |
|
19
|
|
|
{ |
|
20
|
|
|
/** |
|
21
|
|
|
* @var array |
|
22
|
|
|
* @config |
|
23
|
|
|
*/ |
|
24
|
|
|
private static $db = [ |
|
|
|
|
|
|
25
|
|
|
'FileContentCache' => 'Text' |
|
26
|
|
|
]; |
|
27
|
|
|
|
|
28
|
|
|
/** |
|
29
|
|
|
* @var array |
|
30
|
|
|
* @config |
|
31
|
|
|
*/ |
|
32
|
|
|
private static $casting = [ |
|
|
|
|
|
|
33
|
|
|
'FileContent' => 'Text' |
|
34
|
|
|
]; |
|
35
|
|
|
|
|
36
|
|
|
/** |
|
37
|
|
|
* @var array |
|
38
|
|
|
* @config |
|
39
|
|
|
*/ |
|
40
|
|
|
private static $dependencies = [ |
|
|
|
|
|
|
41
|
|
|
'TextCache' => '%$' . FileTextCache::class, |
|
42
|
|
|
]; |
|
43
|
|
|
|
|
44
|
|
|
/** |
|
45
|
|
|
* @var FileTextCache |
|
46
|
|
|
*/ |
|
47
|
|
|
protected $fileTextCache = null; |
|
48
|
|
|
|
|
49
|
|
|
/** |
|
50
|
|
|
* @param FileTextCache $cache |
|
51
|
|
|
* @return $this |
|
52
|
|
|
*/ |
|
53
|
|
|
public function setTextCache(FileTextCache $cache) |
|
54
|
|
|
{ |
|
55
|
|
|
$this->fileTextCache = $cache; |
|
56
|
|
|
return $this; |
|
57
|
|
|
} |
|
58
|
|
|
|
|
59
|
|
|
/** |
|
60
|
|
|
* @return FileTextCache |
|
61
|
|
|
*/ |
|
62
|
|
|
public function getTextCache() |
|
63
|
|
|
{ |
|
64
|
|
|
return $this->fileTextCache; |
|
65
|
|
|
} |
|
66
|
|
|
|
|
67
|
|
|
/** |
|
68
|
|
|
* Helper function for template |
|
69
|
|
|
* |
|
70
|
|
|
* @return string |
|
71
|
|
|
*/ |
|
72
|
|
|
public function getFileContent() |
|
73
|
|
|
{ |
|
74
|
|
|
return $this->extractFileAsText(); |
|
75
|
|
|
} |
|
76
|
|
|
|
|
77
|
|
|
/** |
|
78
|
|
|
* Tries to parse the file contents if a FileTextExtractor class exists to handle the file type, and |
|
79
|
|
|
* returns the text. The value is also cached into the File record itself. |
|
80
|
|
|
* |
|
81
|
|
|
* @param boolean $disableCache If false, the file content is only parsed on demand. |
|
82
|
|
|
* If true, the content parsing is forced, bypassing |
|
83
|
|
|
* the cached version |
|
84
|
|
|
* @return string|null |
|
85
|
|
|
*/ |
|
86
|
|
|
public function extractFileAsText($disableCache = false) |
|
87
|
|
|
{ |
|
88
|
|
|
/** @var File $file */ |
|
89
|
|
|
$file = $this->owner; |
|
90
|
|
|
if (!$disableCache) { |
|
91
|
|
|
$text = $this->getTextCache()->load($file); |
|
92
|
|
|
if ($text) { |
|
93
|
|
|
return $text; |
|
94
|
|
|
} |
|
95
|
|
|
} |
|
96
|
|
|
|
|
97
|
|
|
// Determine which extractor can process this file. |
|
98
|
|
|
$extractor = FileTextExtractor::for_file($file); |
|
99
|
|
|
if (!$extractor) { |
|
100
|
|
|
return null; |
|
101
|
|
|
} |
|
102
|
|
|
|
|
103
|
|
|
$text = $extractor->getContent($file); |
|
104
|
|
|
if (!$text) { |
|
105
|
|
|
return null; |
|
106
|
|
|
} |
|
107
|
|
|
|
|
108
|
|
|
if (!$disableCache) { |
|
109
|
|
|
$this->getTextCache()->save($file, $text); |
|
110
|
|
|
} |
|
111
|
|
|
|
|
112
|
|
|
return $text; |
|
113
|
|
|
} |
|
114
|
|
|
|
|
115
|
|
|
/** |
|
116
|
|
|
* @return void |
|
117
|
|
|
*/ |
|
118
|
|
|
public function onBeforeWrite() |
|
119
|
|
|
{ |
|
120
|
|
|
// Clear cache before changing file |
|
121
|
|
|
$this->getTextCache()->invalidate($this->owner); |
|
122
|
|
|
} |
|
123
|
|
|
} |
|
124
|
|
|
|