2016-01-21 06:13:13 +08:00
|
|
|
<?php namespace BookStack\Services;
|
|
|
|
|
|
|
|
use BookStack\Page;
|
2017-01-21 21:53:00 +08:00
|
|
|
use BookStack\Repos\EntityRepo;
|
2016-01-21 06:13:13 +08:00
|
|
|
|
|
|
|
class ExportService
|
|
|
|
{
|
|
|
|
|
2017-01-21 21:53:00 +08:00
|
|
|
protected $entityRepo;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* ExportService constructor.
|
|
|
|
* @param $entityRepo
|
|
|
|
*/
|
|
|
|
public function __construct(EntityRepo $entityRepo)
|
|
|
|
{
|
|
|
|
$this->entityRepo = $entityRepo;
|
|
|
|
}
|
|
|
|
|
2016-01-21 06:13:13 +08:00
|
|
|
/**
|
|
|
|
* 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)
|
2016-02-01 01:53:30 +08:00
|
|
|
{
|
|
|
|
$cssContent = file_get_contents(public_path('/css/export-styles.css'));
|
2017-01-21 21:53:00 +08:00
|
|
|
$pageHtml = view('pages/export', ['page' => $page, 'pageContent' => $this->entityRepo->renderPage($page), 'css' => $cssContent])->render();
|
2016-02-01 01:53:30 +08:00
|
|
|
return $this->containHtml($pageHtml);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Convert a page to a pdf file.
|
|
|
|
* @param Page $page
|
|
|
|
* @return mixed|string
|
|
|
|
*/
|
|
|
|
public function pageToPdf(Page $page)
|
2016-01-21 06:13:13 +08:00
|
|
|
{
|
|
|
|
$cssContent = file_get_contents(public_path('/css/export-styles.css'));
|
2017-01-21 21:53:00 +08:00
|
|
|
$pageHtml = view('pages/pdf', ['page' => $page, 'pageContent' => $this->entityRepo->renderPage($page), 'css' => $cssContent])->render();
|
2017-01-01 20:20:30 +08:00
|
|
|
$useWKHTML = config('snappy.pdf.binary') !== false;
|
2016-02-01 01:53:30 +08:00
|
|
|
$containedHtml = $this->containHtml($pageHtml);
|
2017-01-01 20:20:30 +08:00
|
|
|
if ($useWKHTML) {
|
|
|
|
$pdf = \SnappyPDF::loadHTML($containedHtml);
|
|
|
|
} else {
|
|
|
|
$pdf = \PDF::loadHTML($containedHtml);
|
|
|
|
}
|
2016-02-01 01:53:30 +08:00
|
|
|
return $pdf->output();
|
|
|
|
}
|
2016-01-21 06:13:13 +08:00
|
|
|
|
2016-02-01 01:53:30 +08:00
|
|
|
/**
|
|
|
|
* Bundle of the contents of a html file to be self-contained.
|
|
|
|
* @param $htmlContent
|
|
|
|
* @return mixed|string
|
|
|
|
*/
|
|
|
|
protected function containHtml($htmlContent)
|
|
|
|
{
|
2016-01-21 06:13:13 +08:00
|
|
|
$imageTagsOutput = [];
|
2016-02-01 01:53:30 +08:00
|
|
|
preg_match_all("/\<img.*src\=(\'|\")(.*?)(\'|\").*?\>/i", $htmlContent, $imageTagsOutput);
|
2016-01-21 06:13:13 +08:00
|
|
|
|
|
|
|
// Replace image src with base64 encoded image strings
|
|
|
|
if (isset($imageTagsOutput[0]) && count($imageTagsOutput[0]) > 0) {
|
|
|
|
foreach ($imageTagsOutput[0] as $index => $imgMatch) {
|
|
|
|
$oldImgString = $imgMatch;
|
|
|
|
$srcString = $imageTagsOutput[2][$index];
|
2016-09-04 02:24:58 +08:00
|
|
|
$isLocal = strpos(trim($srcString), 'http') !== 0;
|
|
|
|
if ($isLocal) {
|
|
|
|
$pathString = public_path(trim($srcString, '/'));
|
2016-01-21 06:13:13 +08:00
|
|
|
} else {
|
|
|
|
$pathString = $srcString;
|
|
|
|
}
|
2016-09-04 02:24:58 +08:00
|
|
|
if ($isLocal && !file_exists($pathString)) continue;
|
2017-01-21 21:53:00 +08:00
|
|
|
try {
|
|
|
|
$imageContent = file_get_contents($pathString);
|
|
|
|
$imageEncoded = 'data:image/' . pathinfo($pathString, PATHINFO_EXTENSION) . ';base64,' . base64_encode($imageContent);
|
|
|
|
$newImageString = str_replace($srcString, $imageEncoded, $oldImgString);
|
|
|
|
} catch (\ErrorException $e) {
|
|
|
|
$newImageString = '';
|
|
|
|
}
|
2016-02-01 01:53:30 +08:00
|
|
|
$htmlContent = str_replace($oldImgString, $newImageString, $htmlContent);
|
2016-01-21 06:13:13 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
$linksOutput = [];
|
2016-02-01 01:53:30 +08:00
|
|
|
preg_match_all("/\<a.*href\=(\'|\")(.*?)(\'|\").*?\>/i", $htmlContent, $linksOutput);
|
2016-01-21 06:13:13 +08:00
|
|
|
|
|
|
|
// Replace image src with base64 encoded image strings
|
|
|
|
if (isset($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);
|
2016-02-01 01:53:30 +08:00
|
|
|
$htmlContent = str_replace($oldLinkString, $newLinkString, $htmlContent);
|
2016-01-21 06:13:13 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Replace any relative links with system domain
|
2016-02-01 01:53:30 +08:00
|
|
|
return $htmlContent;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Converts the page contents into simple plain text.
|
2017-01-21 21:53:00 +08:00
|
|
|
* This method filters any bad looking content to provide a nice final output.
|
2016-02-01 01:53:30 +08:00
|
|
|
* @param Page $page
|
|
|
|
* @return mixed
|
|
|
|
*/
|
|
|
|
public function pageToPlainText(Page $page)
|
|
|
|
{
|
2017-01-21 21:53:00 +08:00
|
|
|
$html = $this->entityRepo->renderPage($page);
|
|
|
|
$text = strip_tags($html);
|
2016-02-01 01:53:30 +08:00
|
|
|
// 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;
|
2016-01-21 06:13:13 +08:00
|
|
|
}
|
|
|
|
|
2016-02-01 01:53:30 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|