ExportService.php
3.85 KB
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
<?php namespace BookStack\Services;
use BookStack\Page;
class ExportService
{
/**
* Convert a page to a self-contained HTML file.
* Includes required CSS & image content. Images are base64 encoded into the HTML.
* @param Page $page
* @return mixed|string
*/
public function pageToContainedHtml(Page $page)
{
$cssContent = file_get_contents(public_path('/css/export-styles.css'));
$pageHtml = view('pages/export', ['page' => $page, 'css' => $cssContent])->render();
return $this->containHtml($pageHtml);
}
/**
* Convert a page to a pdf file.
* @param Page $page
* @return mixed|string
*/
public function pageToPdf(Page $page)
{
$cssContent = file_get_contents(public_path('/css/export-styles.css'));
$pageHtml = view('pages/pdf', ['page' => $page, 'css' => $cssContent])->render();
$containedHtml = $this->containHtml($pageHtml);
$pdf = \PDF::loadHTML($containedHtml);
return $pdf->output();
}
/**
* Bundle of the contents of a html file to be self-contained.
* @param $htmlContent
* @return mixed|string
*/
protected function containHtml($htmlContent)
{
$imageTagsOutput = [];
preg_match_all("/\<img.*src\=(\'|\")(.*?)(\'|\").*?\>/i", $htmlContent, $imageTagsOutput);
// Replace image src with base64 encoded image strings
if (isset($imageTagsOutput[0]) && count($imageTagsOutput[0]) > 0) {
foreach ($imageTagsOutput[0] as $index => $imgMatch) {
$oldImgString = $imgMatch;
$srcString = $imageTagsOutput[2][$index];
$isLocal = strpos(trim($srcString), 'http') !== 0;
if ($isLocal) {
$pathString = public_path(trim($srcString, '/'));
} else {
$pathString = $srcString;
}
if ($isLocal && !file_exists($pathString)) continue;
$imageContent = file_get_contents($pathString);
$imageEncoded = 'data:image/' . pathinfo($pathString, PATHINFO_EXTENSION) . ';base64,' . base64_encode($imageContent);
$newImageString = str_replace($srcString, $imageEncoded, $oldImgString);
$htmlContent = str_replace($oldImgString, $newImageString, $htmlContent);
}
}
$linksOutput = [];
preg_match_all("/\<a.*href\=(\'|\")(.*?)(\'|\").*?\>/i", $htmlContent, $linksOutput);
// Replace image src with base64 encoded image strings
if (isset($linksOutput[0]) && count($linksOutput[0]) > 0) {
foreach ($linksOutput[0] as $index => $linkMatch) {
$oldLinkString = $linkMatch;
$srcString = $linksOutput[2][$index];
if (strpos(trim($srcString), 'http') !== 0) {
$newSrcString = url($srcString);
$newLinkString = str_replace($srcString, $newSrcString, $oldLinkString);
$htmlContent = str_replace($oldLinkString, $newLinkString, $htmlContent);
}
}
}
// Replace any relative links with system domain
return $htmlContent;
}
/**
* Converts the page contents into simple plain text.
* This method filters any bad looking content to
* provide a nice final output.
* @param Page $page
* @return mixed
*/
public function pageToPlainText(Page $page)
{
$text = $page->text;
// Replace multiple spaces with single spaces
$text = preg_replace('/\ {2,}/', ' ', $text);
// Reduce multiple horrid whitespace characters.
$text = preg_replace('/(\x0A|\xA0|\x0A|\r|\n){2,}/su', "\n\n", $text);
$text = html_entity_decode($text);
// Add title
$text = $page->name . "\n\n" . $text;
return $text;
}
}