Fix for two bugs related to Unicode translation support by Font objects

Symptom was that some documents' contents was rendering as a bunch of
control characters.  These are the untranslated strings.  This was
happening because for two different reasons, these strings weren't being
translated \Smalot\PdfParser\Font::decodeContent() in some circumstances.

First fix is to \Smalot\PdfParser\Font::loadTranslateTable():

  - Fixed bug where bfchar sections weren't loaded due to mistake in regexp.
  - It now uses `*` instead of `+` and thus supports translation tables with
    lines like `<0000><0000>`.  (Required `<0000> <0000>` before.)

Second fix is for documents that attach their Font objects to the Pages
object instead of each Page object:

  - \Smalot\PdfParser\Page now has a setFonts() method
  - \Smalot\PdfParser\Pages now declares its $fonts variable
  - \Smalot\PdfParser\Pages::getPages() now applies the object's fonts to each child Page
  - \Smalot\PdfParser\Pages::getFonts() copied from Page class

src/Smalot/PdfParser/Font.php

@@ -191,7 +191,7 @@ public function loadTranslateTable(): array
             // Support for multiple bfchar sections
             if (preg_match_all('/beginbfchar(?P<sections>.*?)endbfchar/s', $content, $matches)) {
                 foreach ($matches['sections'] as $section) {
-                    $regexp = '/<(?P<from>[0-9A-F]+)> +<(?P<to>[0-9A-F]+)>[ \r\n]+/is';
+                    $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)>[ \r\n]+/is';
 
                     preg_match_all($regexp, $section, $matches);
 

src/Smalot/PdfParser/Page.php

@@ -54,6 +54,13 @@ class Page extends PDFObject
      */
     protected $dataTm;
 
+    public function setFonts($fonts)
+    {
+        if (empty($this->fonts)) {
+            $this->fonts = $fonts;
+        }
+    }
+
     /**
      * @return Font[]
      */

src/Smalot/PdfParser/Pages.php

@@ -39,6 +39,11 @@
  */
 class Pages extends PDFObject
 {
+    /**
+     * @var Font[]
+     */
+    protected $fonts;
+
     /**
      * @todo Objects other than Pages or Page might need to be treated specifically in order to get Page objects out of them,
      *
@@ -57,17 +62,65 @@ public function getPages(bool $deep = false): array
             return $kidsElement->getContent();
         }
 
+        // Prepare to apply the Pages' object's fonts to each page
+        $fonts = $this->getFonts();
+
         $kids = $kidsElement->getContent();
         $pages = [];
 
         foreach ($kids as $kid) {
             if ($kid instanceof self) {
                 $pages = array_merge($pages, $kid->getPages(true));
             } elseif ($kid instanceof Page) {
+                if (!empty($this->fonts)) {
+                    $kid->setFonts($fonts);
+                }
                 $pages[] = $kid;
             }
         }
 
         return $pages;
     }
+
+    /**
+     * @return Font[]
+     */
+    public function getFonts()
+    {
+        if (null !== $this->fonts) {
+            return $this->fonts;
+        }
+
+        $resources = $this->get('Resources');
+
+        if (method_exists($resources, 'has') && $resources->has('Font')) {
+            if ($resources->get('Font') instanceof ElementMissing) {
+                return [];
+            }
+
+            if ($resources->get('Font') instanceof Header) {
+                $fonts = $resources->get('Font')->getElements();
+            } else {
+                $fonts = $resources->get('Font')->getHeader()->getElements();
+            }
+
+            $table = [];
+
+            foreach ($fonts as $id => $font) {
+                if ($font instanceof Font) {
+                    $table[$id] = $font;
+
+                    // Store too on cleaned id value (only numeric)
+                    $id = preg_replace('/[^0-9\.\-_]/', '', $id);
+                    if ('' != $id) {
+                        $table[$id] = $font;
+                    }
+                }
+            }
+
+            return $this->fonts = $table;
+        }
+
+        return [];
+    }
 }