diff --git a/src/Controller/Tei2SolrController.php b/src/Controller/Tei2SolrController.php
index c3cb1c5c74943b181d869e9892531a74cf7c1788..c8ee39cbdc3f328c39ee10fcafaa7eb636b15cb3 100755
--- a/src/Controller/Tei2SolrController.php
+++ b/src/Controller/Tei2SolrController.php
@@ -2,8 +2,12 @@
 
 namespace App\Controller;
 
+use App\Service\PreProcessingService;
 use App\Model\SolrDocument;
+use App\Service\EditedTextService;
+use App\Service\TranscriptionService;
 use DOMDocument;
+use DOMElement;
 use DOMXPath;
 use League\Flysystem\Exception;
 use Symfony\Bundle\FrameworkBundle\Controller\AbstractController;
@@ -18,10 +22,21 @@ class Tei2SolrController extends AbstractController
     private Client $client;
 
     private ?string $teiDir = null;
-
-    public function __construct(Client $client)
+    private TranscriptionService $transcriptionService;
+    private EditedTextService $editedTextService;
+    private PreProcessingService $preProcessingService;
+
+    public function __construct(
+        Client $client,
+        PreProcessingService $preProcessingService,
+        TranscriptionService $transcriptionService,
+        EditedTextService $editedTextService
+    )
     {
         $this->client = $client;
+        $this->transcriptionService = $transcriptionService;
+        $this->editedTextService = $editedTextService;
+        $this->preProcessingService = $preProcessingService;
     }
 
     public function setConfigs(string $teiDir) {
@@ -628,9 +643,9 @@ class Tei2SolrController extends AbstractController
         $graphics = $this->getGraphics($imageIds, $imageUrls);
         $solrDocument = $this->getTextVersions($file, $graphics);
         $transcription = $solrDocument->getTranscriptedText();
-        $pagesTranscription = $solrDocument->getTranscriptedTextArr();
+        $pagesTranscription = $solrDocument->getPageLevelTranscriptedText();
         $editedText = $solrDocument->getEditedText();
-        $pagesEdited = $solrDocument->getEditedTextArr();
+        $pagesEdited = $solrDocument->getPageLevelEditedText();
         $pagesGndsUuids = $solrDocument->getPagesGndsUuids();
         $pagesNotesUuids = $solrDocument->getPagesNotesUuids();
         $pagesSegs = $solrDocument->getPagesSegs();
@@ -763,9 +778,10 @@ class Tei2SolrController extends AbstractController
                         $childDoc->edited_text = $pagesEdited[$i - 1];
                     }
 
-                    if (isset($pagesGndsUuids[$i - 1]) && !empty(($pagesGndsUuids[$i - 1]))) {
-                        $childDoc->entities = array_values($pagesGndsUuids[$i - 1]);
-                        $childDoc->annotation_ids = array_keys($pagesGndsUuids[$i - 1]);
+                    if (isset($pagesGndsUuids[$i]) && !empty(($pagesGndsUuids[$i]))) {
+//                    if (isset($pagesGndsUuids[$i - 1]) && !empty(($pagesGndsUuids[$i - 1]))) {
+                        $childDoc->entities = array_values($pagesGndsUuids[$i]);
+                        $childDoc->annotation_ids = array_keys($pagesGndsUuids[$i]);
                     }
 
                     if (isset($pagesNotesUuids[$i - 1]) && !empty(($pagesNotesUuids[$i - 1]))) {
@@ -920,355 +936,61 @@ class Tei2SolrController extends AbstractController
     public function getTextVersions(string $filePath = './../data/gitlab/Z_1822-02-20_k.xml', array $graphics = []): SolrDocument
     {
         $doc = new DOMDocument();
-        $doc->load($filePath);
+        $doc->load($filePath, LIBXML_NOBLANKS);
 
         $xpath = new DOMXPath($doc);
         $xpath->registerNamespace('tei', 'http://www.tei-c.org/ns/1.0');
         $pagesNodes = $xpath->query('//tei:body');
+        /** @var DOMElement $body */
+        $body = $pagesNodes[0];
+        $pages = $this->preProcessingService->splitByPages($body);
 
-        $allElements = [];
-        foreach ($pagesNodes as $pagesNode) {
-            $allElements = $this->getPagesNodes($pagesNode, $allElements);
-        }
+        $pageLevelEditedText = [];
+        $pageLevelTranscriptedText = [];
 
-        $editedTextArr = [];
-        $transcriptedTextArr = [];
-        $gndsUuids = [];
         $pagesGndsUuids = [];
         $pagesSegs = [];
         $pagesNotesUuids = [];
         $notesUuids = [];
         $pagesSics = [];
 
-        foreach ($allElements as $k => $elements) {
-            $renditions = [];
-            $myeditedText = '';
-            $mytranscriptedText = '';
-
-            foreach ($elements as $element) {
-                if (isset($element->nodeName) && (
-                        ($element->nodeName === 'p' && $element->firstChild->nodeName !== 'address') ||
-                        ($element->nodeName === 'dateline' && 'closer' !== $element->parentNode->nodeName) ||
-                        $element->nodeName === 'address' ||
-                        $element->nodeName === 'closer' ||
-                        $element->nodeName === 'list' ||
-                        ($element->nodeName === 'signed' && 'closer' !== $element->parentNode->nodeName)
-                    )) {
-
-                    $n = 0;
-                    $liNumber = 1;
-                    $tText = '';
-                    $eText = '';
-                    $childElementsArr = [];
-                    $childElements = $this->getNodeChilds($element, $childElementsArr);
-
-                    foreach ($childElements as $childElement) {
-                        if ($childElement->nodeName === '#text'
-                            && ($childElement->parentNode->nodeName !== 'abbr' && ($childElement->nodeName !== 'del' || $childElement->parentNode->nodeName !== 'add'))
-                            && $childElement->parentNode->nodeName !== 'note' && $childElement->parentNode->nodeName !== 'seg'
-                            && $childElement->parentNode->nodeName !== 'ref'
-                        ) {
-                            if (isset($add) && !empty($add)) {
-                                $tText .= ' ⟨' . $childElement->data . ' ' . $add;
-                                $eText .= ' ' . $childElement->data;
-                                $add = '';
-                            } elseif (isset($del) && !empty($del)) {
-                                $tText .= ' [' . $childElement->data . ' ' . $del;
-                                $del = '';
-                            } elseif (isset($li) && !empty($li) && !empty($childElement->data) && 'item' === $childElement->parentNode->nodeName) {
-                                if (isset($italic) && true === $italic) {
-                                    $tText .= $li . $childElement->data . '</li>';
-                                    $eText .= $li . $childElement->data . '</li>';
-                                    $italic = false;
-                                } else {
-                                    $tText .= $li . $childElement->data;
-                                    $eText .= $li . $childElement->data;
-                                }
-
-                                $li = '';
-                            } elseif ('supplied' === $childElement->parentNode->nodeName) {
-                                $tText .= $childElement->data;
-                                $eText .= '<i>' . $childElement->data . '</i>';
-                            } elseif ('hi' === $childElement->parentNode->nodeName && isset($childElement->parentNode->attributes[0])) {
-
-                                $hi = explode(':', $childElement->parentNode->attributes[0]->value);
-
-                                if (isset($hi[1]) && !empty($hi[1]) && 'superscript' === $hi[1]) {
-                                    $tText .= '<sup>' . $childElement->data . '</sup>';
-                                    $eText .= $childElement->data;
-                                } elseif (isset($hi[1]) && !empty($hi[1]) && 'italic' === $hi[1]) {
-                                    $tText .= '<i>' . $childElement->data . '</i>';
-                                    $eText .= $childElement->data;
-                                    $italic = true;
-                                }
-                            } elseif (isset($gnd) && true === $gnd) {
-                                $eText .= '</span>';
-                                $tText .= '';
-                                $gnd = false;
-                            } elseif (isset($note) && true === $note) {
-                                $eText .= ' </span>' . $childElement->data;
-                                $tText .= ' ' . $childElement->data;
-                                $note = false;
-                            } elseif (isset($sic) && true === $sic) {
-                                $eText .= ' </span>';
-                                $tText .= ' ';
-                                $sic = false;
-                            } elseif (isset($abbr) && !empty($abbr)) {
-                                $tText .= $abbr;
-                                $abbr = '';
-                            }
-                            elseif (isset($expan) && !empty($expan)) {
-                                $eText .= $expan;
-                                $expan = '';
-                            } else {
-                                $eText .= $childElement->data;
-                                if (isset($renditions) && !empty($renditions)) {
-                                    $classOpeningTag = '';
-                                    $classEndTag = '';
-
-                                    foreach ($renditions as $rendition) {
-                                        if ('italic' === $rendition) {
-                                            $class = 'i';
-                                        } elseif ('underline' === $rendition) {
-                                            $class = 'u';
-                                        }
-                                        if (isset($class) && !empty($class)) {
-                                            $classOpeningTag .= '<' . $class . '>';
-                                            $classEndTag .= '</' . $class . '>';
-                                        }
-
-                                        $renditions = [];
-                                    }
-                                }
-
-                                if (isset($classOpeningTag) && !empty($classOpeningTag)) {
-                                    $tText .= $classOpeningTag;
-                                    $classOpeningTag = '';
-                                }
-
-                                $tText .= $childElement->data;
-
-                                if (isset($classEndTag) && !empty($classEndTag)) {
-                                    $tText .= $classEndTag;
-                                    $classEndTag = '';
-                                }
-                            }
-                        } elseif ($childElement->nodeName === "seg") {
-                            $noteBibl = false;
-                            foreach ($childElement->childNodes as $childElementChildNode) {
-                                if ($childElementChildNode->nodeName === 'bibl') {
-                                    $noteBibl = true;
-                                    break;
-                                }
-                            }
-
-                            if (true === $noteBibl) {
-                                $segBiblTarget = $this->getSegBiblTarget($childElement);
-                                if (!empty($segBiblTarget)) {
-                                    $segBiblTargetArr = explode('#', $segBiblTarget);
-                                    $segTextBibl = str_replace('_', ' ', $segBiblTargetArr[1]);
-                                    $segBiblTargetlink = $segBiblTargetArr[0];
-                                    $segTextBibl = $segTextBibl.' ('.$segBiblTargetArr[0].')';
-                                    $segText = $this->getElementText($childElement);
-                                }
-                            } else {
-                                $segText = $this->getElementText($childElement);
-                            }
-
-                            $noteUuid = $this->getUuid();
-                            $eText .= '<span class="note" id="' . $noteUuid . '">'.$segText;
-                            $tText .= $segText;
-                            $note = true;
+        foreach ($pages as $key => $page) {
+            if ($key > 0) {
+                $transcriptedDoc = $this->transcriptionService->transformPage($page);
+                $pageLevelTranscriptedText[] = $transcriptedDoc->saveHTML();
 
-                            if (true === $noteBibl && !empty($segTextBibl)) {
-                                $pagesSegs[$k][$noteUuid] = trim($segTextBibl);
-                            } elseif ($noteBibl === false && !empty($segText)) {
-                                $pagesSegs[$k][$noteUuid] = trim($segText);
-                            }
-                        } elseif ($childElement->nodeName === "note") {
-                            $noteText = $this->getElementText($childElement);
-                            if ((isset($noteBibl) && false === $noteBibl) && (isset($noteUuid) && !empty($noteUuid)) && !empty($noteText)) {
-                                $notesUuids[$noteUuid] = trim($noteText);
-                                $pagesNotesUuids[$k][$noteUuid] = trim($noteText);
-                            } elseif ((isset($noteBibl) && true === $noteBibl) && (isset($noteUuid) && !empty($noteUuid)) && !empty($segBiblTargetlink)) {
-                                $notesUuids[$noteUuid] = trim($segBiblTargetlink);
-                                $pagesNotesUuids[$k][$noteUuid] = trim(' ');
-                            }
-                            unset($noteUuid);
-                        } elseif ('item' === $childElement->nodeName) {
-                            if ($liNumber++ === 1) {
-                                $li = '<ul><li>';
-                            } else {
-                                $li = '<li>';
-                            }
-                        } elseif ('add' === $childElement->nodeName) {
-                            if ('rdg' === $childElement->parentNode->nodeName) {
-                                if (!empty($childElement->attributes)) {
-                                    $pattern = '/^#[a-z_]*$/i';
-                                    foreach ($childElement->attributes as $attribute) {
-                                        if ('hand' === $attribute->nodeName) {
-                                            if (strpos($attribute->nodeValue, 'scrb') !== false) {
-                                                $add = $this->transformAddScrb($attribute->nodeValue);
-                                            } else {
-                                                $match = preg_match($pattern, $attribute->nodeValue, $matches);
-                                                if ($match) {
-                                                    $add = '<i>erg. ' . str_replace('_', ' ', trim($attribute->nodeValue, '#')) . '</i>';
-                                                }
-                                            }
-                                        }
-                                    }
-                                } else {
-                                    $add = '<i>erg.</i>';
-                                }
-
-                                if (!empty($add)) {
-                                    $add .= '&rang; ';
-                                }
-                            }
-                        } elseif ('del' === $childElement->nodeName) {
-                            if ('rdg' === $childElement->parentNode->nodeName) {
-                                if (!empty($childElement->attributes)) {
-                                    foreach ($childElement->attributes as $attribute) {
-                                        if ('hand' === $attribute->nodeName) {
-                                            if (strpos($attribute->nodeValue, 'scrb') !== false) {
-                                                $valueArr = explode('scrb', $attribute->nodeValue);
-                                                if (isset($valueArr[1])) {
-                                                    $valueArr = explode('_', ltrim($valueArr[1], '_'));
-                                                    if (count($valueArr) === 2) {
-                                                        $del = '<i>str Schrhd.' . $valueArr[0] . ' ' . $valueArr[1] . '</i>';
-                                                    }
-                                                }
-                                            } else {
-                                                $del = '<i>str. ' . str_replace('_', ' ', trim($attribute->nodeValue, '#')) . '</i>';
-                                            }
-                                        }
-                                    }
-                                } else {
-                                    $del = '<i>str.</i>';
-                                }
-
-                                if (!empty($del)) {
-                                    $del .= '&#x5D;';
-                                }
-                            }
-                        } elseif ('abbr' === $childElement->nodeName && 'choice' === $childElement->parentNode->nodeName) {
-                            if (isset($childElement->firstChild) && $childElement->firstChild->nodeName === '#text') {
-                                $abbr = $childElement->firstChild->data;;
-                            }
-                        } elseif ('expan' === $childElement->nodeName && 'choice' === $childElement->parentNode->nodeName) {
-                            if (isset($childElement->firstChild) && $childElement->firstChild->nodeName === '#text') {
-                                $expan = $childElement->firstChild->data;
-                            }
-                        } elseif ('handShift' === $childElement->nodeName && 'signed' === $childElement->parentNode->nodeName) {
-                            if (!empty($childElement->attributes)) {
-                                $pattern = '/^#[a-z_]*$/i';
-                                foreach ($childElement->attributes as $attribute) {
-                                    if ('scribeRef' === $attribute->nodeName) {
-                                        $match = preg_match($pattern, $attribute->nodeValue, $matches);
-                                        if ($match) {
-                                            $add = '<i>sign. ' . str_replace('_', ' ', trim($attribute->nodeValue, '#')) . '</i>&rang; ';
-                                        }
-                                    }
-                                }
-                            }
-                        } elseif ('lb' === $childElement->nodeName) {
-                            $tText .= '<br>';
-                            $eText .= ' ';
-                        } elseif ('addrLine' === $childElement->nodeName) {
-                            if ($n++ > 0) {
-                                $eText .= '<br>';
-                                $tText .= '<br>';
-                            }
-                        } elseif ('signed' === $childElement->nodeName) {
-                            $tText .= '<br><br>';
-                            $eText .= '<br><br>';
-                            $signedText = $this->getElementText($childElement);
-                            $tText .= $signedText;
-                            $eText .= $signedText;
-                        } elseif ('hi' === $childElement->nodeName) {
-                            foreach ($childElement->attributes as $attribute) {
-                                if (isset(explode(':', $attribute->value)[1])) {
-                                    $rend = explode(':', $attribute->value)[1];
-                                    if ('superscript' !== $rend && 'italic' !== $rend) {
-                                        $renditions[] = explode(':', $attribute->value)[1];
-                                    }
-                                }
-                            }
-                        } elseif ('name' === $childElement->nodeName && (isset($childElement->attributes[1]->value) && !empty($childElement->attributes[1]->value)) && (isset($childElement->attributes[0]->value) && !empty($childElement->attributes[0]->value))) {
-                            $entityName = $this->getEntityName($childElement);
-                            $uuid = $this->getUuid();
-                            if (str_contains($childElement->attributes[1]->value, 'gnd.')) {
-                                $gndsUuids[$uuid] = str_replace('gnd.', '', $childElement->attributes[1]->value);
-                                $pagesGndsUuids[$k][$uuid] = str_replace('gnd.', '', $childElement->attributes[1]->value);
-                            } elseif (str_contains($childElement->attributes[1]->value, 'gnd:')) {
-                                $gndsUuids[$uuid] = str_replace('gnd:', '', $childElement->attributes[1]->value);
-                                $pagesGndsUuids[$k][$uuid] = str_replace('gnd:', '', $childElement->attributes[1]->value);
-                            }
-                            if ('signed' === $childElement->parentNode->nodeName) {
-                                if (isset($childElement->parentNode->attributes[0])) {
-                                    $hand = explode('_', trim($childElement->parentNode->attributes[0]->value, '#'));
-                                }
-                                $eText .= '<span class="' . $childElement->attributes[0]->value . '" id="' . $uuid . '">'.$entityName;
-                                $tText .= '&lang;'.$entityName.' sign.';
-                                if (isset($hand[0]) && !empty($hand[0])) {
-                                    $tText .= ' '.$hand[0];
-                                }
-                                if (isset($hand[1]) && !empty($hand[1])) {
-                                    $tText .= ' '.$hand[1];
-                                }
-                                $tText .= ' &rang;';
-                            } else {
-                                $eText .= '<span class="' . $childElement->attributes[0]->value . '" id="' . $uuid . '">'.$entityName;
-                                $tText .= $entityName;
-                            }
-                            $gnd = true;
-                        } elseif ($childElement->nodeName === "sic") {
-                            $sicText = $this->getElementText($childElement);
-                            $sicUuid = $this->getUuid();
-                            $eText .= $this->createSpan($sicUuid, $sicText, $childElement->nodeName);
-                            $tText .= $sicText;
-                            $pagesSics[$k][$sicUuid] = trim($sicText);
-                            $sic = true;
-                        }
-                    }
+                $editedDoc = $this->editedTextService->transformPage($page);
+                $pagesGndsUuids[$key] = $this->editedTextService->getGndsUuids();
+                $pageLevelEditedText[] = $editedDoc->saveHTML();
 
-                    $eText = $this->convertSoftHyphenToHyphen($eText);
-                    $eText = $this->removeHyphen($eText);
-                    $myeditedText .= '<p>' . $eText . '</p>';
-                    $mytranscriptedText .= '<p>' . $tText . '</p>';
-                } elseif ('pb' === $element->nodeName) {
-                    $imageHref = $this->getImageHref($element, $graphics);
-                    $tText = $imageHref;
-                    $eText = $imageHref;
-                    $myeditedText .= '<p>' . $eText . '</p>';
-                    $mytranscriptedText .= '<p>' . $tText . '</p>';
-                }
+                $this->transcriptionService->clear();
+                $this->editedTextService->clear();
             }
-
-            $editedTextArr[] = $myeditedText;
-            $transcriptedTextArr[] = $mytranscriptedText;
         }
 
-        $transcriptedText = '';
-        foreach ($transcriptedTextArr as $mytranscriptedText) {
-            $transcriptedText .= $mytranscriptedText;
+        $this->preProcessingService->clear();
+
+        $gndsUuids = array_merge($pagesGndsUuids);
+
+        $documentLevelTranscriptedText = '';
+        foreach ($pageLevelTranscriptedText as $singlePageTranscriptedText) {
+            $documentLevelTranscriptedText .= $singlePageTranscriptedText;
         }
 
-        $editedText = '';
-        foreach ($editedTextArr as $myeditedText) {
-            $editedText .= $myeditedText;
+        $documentLevelEditedText = '';
+        foreach ($pageLevelEditedText as $singlePageEditedText) {
+            $documentLevelEditedText .= $singlePageEditedText;
         }
 
         $solrDocument = new SolrDocument();
-        $solrDocument->setTranscriptedText($transcriptedText);
-        $solrDocument->setTranscriptedTextArr($transcriptedTextArr);
-        $solrDocument->setEditedText($editedText);
-        $solrDocument->setEditedTextArr($editedTextArr);
+        $solrDocument->setTranscriptedText($documentLevelTranscriptedText);
+        $solrDocument->setPageLevelTranscriptedText($pageLevelTranscriptedText);
+        $solrDocument->setEditedText($documentLevelEditedText);
+        $solrDocument->setPageLevelEditedText($pageLevelEditedText);
         $solrDocument->setGndsUuids($gndsUuids);
         $solrDocument->setPagesGndsUuids($pagesGndsUuids);
         $solrDocument->setPagesNotesUuids($pagesNotesUuids);
         $solrDocument->setPagesSegs($pagesSegs);
-
         $solrDocument->setPagesSics($pagesSics);
 
         return $solrDocument;
@@ -1281,7 +1003,6 @@ class Tei2SolrController extends AbstractController
         return $span;
     }
 
-
     private function getSegBiblTarget(\DOMElement $childElement): ?string
     {
         $elementChildsArr = [];
diff --git a/src/Model/SolrDocument.php b/src/Model/SolrDocument.php
index 98fd842b7e869d54d6f571f9a71b3e5f732d393d..b5150d6c1878dcda1f2ddddb662fc79617ebccd7 100755
--- a/src/Model/SolrDocument.php
+++ b/src/Model/SolrDocument.php
@@ -5,9 +5,9 @@ namespace App\Model;
 class SolrDocument
 {
     private string $transcriptedText;
-    private array $transcriptedTextArr;
+    private array $pageLevelTranscriptedText;
     private string $editedText;
-    private array $editedTextArr;
+    private array $pageLevelEditedText;
     private array $gndsUuids;
     private array $pagesGndsUuids;
     private array $pagesNotesUuids;
@@ -26,14 +26,14 @@ class SolrDocument
         return $this;
     }
 
-    public function getTranscriptedTextArr(): array
+    public function getPageLevelTranscriptedText(): array
     {
-        return $this->transcriptedTextArr;
+        return $this->pageLevelTranscriptedText;
     }
 
-    public function setTranscriptedTextArr(array $transcriptedTextArr): SolrDocument
+    public function setPageLevelTranscriptedText(array $pageLevelTranscriptedText): SolrDocument
     {
-        $this->transcriptedTextArr = $transcriptedTextArr;
+        $this->pageLevelTranscriptedText = $pageLevelTranscriptedText;
 
         return $this;
     }
@@ -50,14 +50,14 @@ class SolrDocument
         return $this;
     }
 
-    public function getEditedTextArr(): array
+    public function getPageLevelEditedText(): array
     {
-        return $this->editedTextArr;
+        return $this->pageLevelEditedText;
     }
 
-    public function setEditedTextArr(array $editedTextArr): SolrDocument
+    public function setPageLevelEditedText(array $pageLevelEditedText): SolrDocument
     {
-        $this->editedTextArr = $editedTextArr;
+        $this->pageLevelEditedText = $pageLevelEditedText;
 
         return $this;
     }
diff --git a/src/Service/EditedTextService.php b/src/Service/EditedTextService.php
new file mode 100644
index 0000000000000000000000000000000000000000..b6c0fb8dc121b89dcf51207a075312202bb7ac63
--- /dev/null
+++ b/src/Service/EditedTextService.php
@@ -0,0 +1,90 @@
+<?php
+
+namespace App\Service;
+
+use DOMDocument;
+use DOMElement;
+use DOMNode;
+
+class EditedTextService extends HtmlService
+{
+    private array $gndsUuids = [];
+    private array $notesUuids = [];
+
+    public function transformPage(DOMDocument $page): DOMDocument
+    {
+        $this->setDoc(new DOMDocument());
+
+        /** @var DOMElement $element */
+        foreach ($page->childNodes as $element) {
+            $transformed = $this->transformElement($element);
+            if ($transformed) {
+                $this->appendChild($transformed);
+            }
+        }
+
+        // Later this should be packed in an object
+        return $this->getDoc();
+    }
+
+    public function getGndsUuids(): array
+    {
+        return $this->gndsUuids;
+    }
+
+    public function getNotesUuids(): array
+    {
+        return $this->notesUuids;
+    }
+
+    private function transformElement(DOMNode $el): ?DOMNode
+    {
+        $htmlEl = null;
+        $methodName = 'handle' . trim(ucfirst($el->nodeName), '#');
+        if (method_exists($this, $methodName)) {
+            $htmlEl = $this->{$methodName}($el);
+        } else {
+            $htmlEl = $this->span();
+        }
+
+        if ($el->hasChildNodes()) {
+            var_dump($el->nodeName);
+            foreach ($el->childNodes as $child) {
+                $transformed = $this->transformElement($child);
+                if ($transformed) {
+                    $htmlEl->appendChild($transformed);
+                }
+            }
+        }
+
+        return $htmlEl;
+    }
+
+    private function handleName(DOMNode $el): DOMNode
+    {
+        $htmlEl = $this->span();
+
+        if (isset($el->attributes[1]->value) && str_contains($el->attributes[1]->value, 'gnd:')) {
+            $uuid = $this->createUuid();
+            $this->gndsUuids[$uuid] = str_replace('gnd:', '', $el->attributes[1]->value);
+            $htmlEl->setAttribute('id', $uuid);
+            if (isset($el->attributes[0]->value)) {
+                $htmlEl->setAttribute('class', $el->attributes[0]->value);
+            }
+        }
+
+        return $htmlEl;
+    }
+
+    public function createUuid()
+    {
+        return uuid_create(UUID_TYPE_RANDOM);
+    }
+
+    public function clear()
+    {
+        parent::clear();
+        $this->gndsUuids = [];
+        $this->notesUuids = [];
+    }
+}
diff --git a/src/Service/HtmlService.php b/src/Service/HtmlService.php
new file mode 100644
index 0000000000000000000000000000000000000000..f07b4929b6505fa93aca9c26a4b7589d92da02bc
--- /dev/null
+++ b/src/Service/HtmlService.php
@@ -0,0 +1,61 @@
+<?php
+
+namespace App\Service;
+
+use DOMDocument;
+use DOMElement;
+use DOMNode;
+use DOMText;
+
+class HtmlService
+{
+    private ?DOMDocument $doc = null;
+
+    public function getDoc(): DOMDocument
+    {
+        return $this->doc;
+    }
+
+    public function setDoc(DOMDocument $doc): void
+    {
+        $this->doc = $doc;
+    }
+
+    public function appendChild(DOMNode $el): DOMNode
+    {
+        return $this->doc->appendChild($el);
+    }
+
+    public function p(): DOMElement
+    {
+        return $this->doc->createElement('p');
+    }
+
+    public function div():DOMElement
+    {
+        return $this->doc->createElement('div');
+    }
+
+    public function span(): DOMElement
+    {
+        return $this->doc->createElement('span');
+    }
+
+    public function br(): DOMElement
+    {
+        return $this->doc->createElement('br');
+    }
+
+    public function clear()
+    {
+        $this->doc = null;
+    }
+
+    public function handleText(DOMNode $el): DOMNode {
+        $text = new DOMText();
+        if ($el->nodeName === '#text') {
+            $text->data = $el->textContent;
+        }
+        return $text;
+    }
+}
diff --git a/src/Service/PreProcessingService.php b/src/Service/PreProcessingService.php
new file mode 100644
index 0000000000000000000000000000000000000000..ffa82f12848453dc8e4c302300721448f48b4d48
--- /dev/null
+++ b/src/Service/PreProcessingService.php
@@ -0,0 +1,126 @@
+<?php
+
+namespace App\Service;
+
+use DOMDocument;
+use DOMElement;
+use DOMNode;
+
+class PreProcessingService
+{
+    private array $pages = [];
+    private DOMNode $lastParent;
+
+    public function getPages(): array
+    {
+        return $this->pages;
+    }
+
+    public function splitByPages(DOMELement $body)
+    {
+        $this->pages[] = new DOMDocument();
+
+        // To start out we set our empty page as last parent to append other elements to
+        $this->lastParent = $this->getLastPage();
+
+        // Start recursion
+        $this->checkPb($body);
+
+        return $this->pages;
+    }
+
+    private function checkPb(DOMNode $el)  {
+        if ($el->nodeName === '#comment') {
+            return;
+        }
+
+        $lastPage = $this->getLastPage();
+
+        if ($el->nodeName === '#text') {
+            $clone = $lastPage->createTextNode($el->textContent);
+        } else {
+            $clone = $lastPage->createElement($el->nodeName);
+            $clone = $this->cloneAttributes($el->attributes, $clone);
+        }
+
+        // Always append the current element clone to last parent
+        $this->lastParent->appendChild($clone);
+
+        if ($el->hasChildNodes()) {
+
+            // If there are children then we want to append their clones to the current element
+            // so we have to move lastParent
+            $this->lastParent = $clone;
+
+            /** @var DOMElement $child */
+            foreach ($el->childNodes as $child) {
+                if ($child->nodeName === 'pb') {
+                    $this->pages[] = $this->createNewPage($child);
+                } else {
+                    $this->checkPb($child);
+                }
+            }
+
+            // After we finished iterating (recursively) over all children
+            // we are done here and want move on with our next sibling
+            // so we have to set lastParent to it's parent
+            if ($this->lastParent->parentNode) {
+                $this->lastParent = $this->lastParent->parentNode;
+            }
+        }
+    }
+
+    private function createNewPage(DOMElement $pbEl): DOMDocument
+    {
+        // Creates a new DOMDocument and replicates every parent node of pb element
+        // up to the <body>
+        $newPage = new DOMDocument();
+        $parent = $pbEl->parentNode;
+
+        $parents = [];
+        while ($parent->parentNode) {
+            // Collect all parents until <body>
+
+            $parents[] = $parent;
+
+            if ($parent->nodeName === 'body') break;
+            $parent = $parent->parentNode;
+        }
+
+        // Reverse them to append them from document root
+        $parentsReversed = array_reverse($parents);
+
+        $lastNode = $newPage;
+        foreach ($parentsReversed as $parent) {
+            $node = $newPage->createElement($parent->nodeName);
+            $node = $this->cloneAttributes($parent->attributes, $node);
+            $node = $lastNode->appendChild($node);
+
+            // Result will be the deepest parent node so we can continue cloning the TEI
+            // in further checkPb calls
+            $this->lastParent = $node;
+            $lastNode = $node;
+        }
+
+        return $newPage;
+    }
+
+    private function getLastPage(): ?DOMDocument
+    {
+        return (!empty($this->pages)) ? $this->pages[count($this->pages) - 1] : null;
+    }
+
+    public function clear()
+    {
+        $this->pages = [];
+    }
+
+    private function cloneAttributes($attributes, $clone)
+    {
+        foreach ($attributes as $attr) {
+            $clone->setAttribute($attr->name, $attr->value);
+        }
+
+        return $clone;
+    }
+}
diff --git a/src/Service/TranscriptionService.php b/src/Service/TranscriptionService.php
new file mode 100644
index 0000000000000000000000000000000000000000..a4aa4fbf8c729c6efaa7c35b34bcd9068a14723d
--- /dev/null
+++ b/src/Service/TranscriptionService.php
@@ -0,0 +1,66 @@
+<?php
+
+namespace App\Service;
+
+use DOMDocument;
+use DOMElement;
+use DOMNode;
+use App\Service\HtmlService;
+
+class TranscriptionService extends HtmlService
+{
+    public function transformPage(DOMDocument $page): DOMDocument
+    {
+        $this->setDoc(new DOMDocument());
+
+        /** @var DOMElement $element */
+        foreach ($page->childNodes as $element) {
+            $this->appendChild($this->transformElement($element));
+        }
+
+        return $this->getDoc();
+    }
+
+    private function transformElement(DOMNode $el): DOMNode
+    {
+        $methodName = 'handle' . trim(ucfirst($el->nodeName), '#');
+        if (method_exists($this, $methodName)) {
+            $htmlEl = $this->{$methodName}($el);
+        } else {
+            $htmlEl = $this->p();
+        }
+
+        if ($el->hasChildNodes()) {
+            foreach ($el->childNodes as $child) {
+                $htmlEl->appendChild($this->transformElement($child));
+            }
+        }
+
+        return $htmlEl;
+    }
+
+    private function handleLb(DOMElement $el): DOMNode
+    {
+        return $this->br();
+    }
+
+    private function handlePb(DOMElement $el): DOMNode
+    {
+        return $this->div();
+    }
+
+    private function handleP(DOMElement $el): DOMNode
+    {
+        return $this->p();
+    }
+
+    private function handleDiv(DOMElement $el): DOMNode
+    {
+        return $this->div();
+    }
+
+    private function handleSpan(DOMElement $el): DOMNode
+    {
+        return $this->span();
+    }
+}