1.x dev (#12)

* Updated

* OCR Fixing work

1. OCR error fixing work
2. Laravel 10 support

* Laravel 10 support & Bug fixing

- Laravel 10 support added
- Bug fixing on OCR
- EPUB support removed due to security issue. We will try to add it again later.

* PPT Support added

- PPT support now added (.ppt and .pptx) type files are now supported.

* Updated

- Updated and fixing work for PPTX.

* Update README.md

Author: NilGems

README.md

@@ -25,6 +25,7 @@ check file content MIME type before execute.
 - **ODT**
 - **ODS**
 - **RTF**
+- **PPTX** (NEW)
 
 **We are working hard to make this laravel plugin useful. If you found any issue please add a post on discussion.**
 

composer.json

@@ -39,7 +39,8 @@
         "phpoffice/phpword": "^0.18",
         "laravel/framework": "^10.0",
         "thiagoalessio/tesseract_ocr": "^2.12",
-        "html2text/html2text": "^4.3"
+        "html2text/html2text": "^4.3",
+        "phpoffice/phppresentation": "^1.0"
     },
     "require-dev": {
         "phpunit/phpunit": "^9.5"

composer.lock

@@ -0,0 +1,63 @@
+<?php
+
+namespace Nilgems\PhpTextract\ExtractorService\ExtractorCommonProcessors;
+
+use Nilgems\PhpTextract\Exceptions\TextractException;
+use Nilgems\PhpTextract\ExtractorService\Contracts\AbstractTextExtractor;
+use PhpOffice\PhpPresentation\IOFactory;
+use PhpOffice\PhpPresentation\Shape;
+
+/**
+ * PHP PowerPointProcessor
+ * Read the document: https://phpoffice.github.io/PHPPresentation/usage/readers.html
+ */
+class PhpPowerPointProcessor extends AbstractTextExtractor
+{
+    protected string $readerType = "PowerPoint2007";
+    private function hasReadable(): bool
+    {
+        $file_path = $this->utilsService->getFilePath();
+        $reader = IOFactory::createReader($this->readerType);
+        try {
+            $presentation = $reader->load($file_path);
+            return count($presentation->getAllSlides()) > 0;
+        } catch (\Exception $exception) {
+            throw $exception;
+            report($exception);
+            throw new TextractException(trans('textract::processor.error_unable_to_read', [
+                'path' => $this->utilsService->getFilePath()
+            ]));
+        }
+
+    }
+
+    /**
+     * @throws TextractException
+     * @throws \PhpOffice\PhpSpreadsheet\Reader\Exception
+     */
+    protected function getExtractedText(): string
+    {
+        if ($this->hasReadable()) {
+            $data_iterable = [];
+            $reader = IOFactory::createReader($this->readerType);
+            $presentation = $reader->load($this->utilsService->getFilePath());
+            foreach ($presentation->getAllSlides() as $slide) {
+                $shapes = $slide->getShapeCollection();
+                foreach ($shapes as $shape_k => $shape_v) {
+                    $shape = $shapes[$shape_k];
+                    if($shape instanceof Shape\RichText){
+                        $paragraphs = $shapes[$shape_k]->getParagraphs();
+                        foreach ($paragraphs as $paragraph_k => $paragraph_v) {
+                            $text_elements = $paragraph_v->getRichTextElements();
+                            foreach ($text_elements as $text_element_k => $text_element_v) {
+                                $data_iterable[] = $text_element_v->getText();
+                            }
+                        }
+                    }
+                }
+            }
+            return implode("\n", $data_iterable);
+        }
+        return "";
+    }
+}

src/ExtractorService/ExtractorCommonProcessors/PhpPowerPointProcessor.php

@@ -0,0 +1,18 @@
+<?php
+
+namespace Nilgems\PhpTextract\ExtractorService\Extractors;
+
+use Nilgems\PhpTextract\ExtractorService\ExtractorCommonProcessors\PhpPowerPointProcessor;
+
+class MsOfficePptxExtractor extends PhpPowerPointProcessor
+{
+    protected string $readerType = "PowerPoint2007";
+
+    protected array $supported_mime_types = [
+        'application/vnd.openxmlformats-officedocument.presentationml.presentation'
+    ];
+
+    public array $supported_extension = ['pptx'];
+
+    protected string $reader_name = 'MsPresentation';
+}

src/ExtractorService/Extractors/MsOfficePptxExtractor.php

@@ -7,6 +7,7 @@
 use Nilgems\PhpTextract\ExtractorService\Extractors\ImageExtractor;
 use Nilgems\PhpTextract\ExtractorService\Extractors\MsOfficeDocExtractor;
 use Nilgems\PhpTextract\ExtractorService\Extractors\MsOfficeDocxExtractor;
+use Nilgems\PhpTextract\ExtractorService\Extractors\MsOfficePptxExtractor;
 use Nilgems\PhpTextract\ExtractorService\Extractors\OpenOfficeDocument;
 use Nilgems\PhpTextract\ExtractorService\Extractors\OpenOfficeSpreadSheet;
 use Nilgems\PhpTextract\ExtractorService\Extractors\PdfExtractor;
@@ -52,6 +53,7 @@ protected function registerExtractors(): void
             ImageExtractor::class,
             MsOfficeDocExtractor::class,
             MsOfficeDocxExtractor::class,
+            MsOfficePptxExtractor::class,
             OpenOfficeDocument::class,
             OpenOfficeSpreadSheet::class,
             PdfExtractor::class,