Added plaintext & basic PDF page Export

[bookstack] / app / Services / ExportService.php

diff --git a/app/Services/ExportService.php b/app/Services/ExportService.php
index 05ba85dd1143f7a9c2aafdfcba28c1ff6feb0af2..0497681e9ac695204ea7952af02b2ae5e81958fa 100644 (file)
--- a/app/Services/ExportService.php
+++ b/app/Services/ExportService.php
@@ -6,7 +6,6 @@ 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.
@@ -14,12 +13,35 @@ class ExportService
      * @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", $pageHtml, $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) {
@@ -34,12 +56,12 @@ class ExportService
                 $imageContent = file_get_contents($pathString);
                 $imageEncoded = 'data:image/' . pathinfo($pathString, PATHINFO_EXTENSION) . ';base64,' . base64_encode($imageContent);
                 $newImageString = str_replace($srcString, $imageEncoded, $oldImgString);
-                $pageHtml = str_replace($oldImgString, $newImageString, $pageHtml);
+                $htmlContent = str_replace($oldImgString, $newImageString, $htmlContent);
             }
         }
 
         $linksOutput = [];
-        preg_match_all("/\<a.*href\=(\'|\")(.*?)(\'|\").*?\>/i", $pageHtml, $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) {
@@ -49,13 +71,45 @@ class ExportService
                 if (strpos(trim($srcString), 'http') !== 0) {
                     $newSrcString = url($srcString);
                     $newLinkString = str_replace($srcString, $newSrcString, $oldLinkString);
-                    $pageHtml = str_replace($oldLinkString, $newLinkString, $pageHtml);
+                    $htmlContent = str_replace($oldLinkString, $newLinkString, $htmlContent);
                 }
             }
         }
 
         // Replace any relative links with system domain
-        return $pageHtml;
+        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;
     }
 
-}
\ No newline at end of file
+}
+
+
+
+
+
+
+
+
+
+
+
+