Refactoring the thing:

inc/document-converter.php

@@ -0,0 +1,57 @@
+<?php
+/**
+ * Script to extract text from MS Word documents
+ *
+ * Based on a StackOverflow answer:
+ * @link https://stackoverflow.com/questions/19503653/how-to-extract-text-from-word-file-doc-docx-xlsx-pptx-php
+ */
+
+
+interface DocumentToText
+{
+	public static function getText(string $name): string;
+	public static function readDocument(string $name): string;
+	public static function formatText(string $text): string;
+}
+
+
+class DocxToHTML implements DocumentToText
+{
+	public static function getText(string $name): string
+	{
+		$content = DocxToHTML::readDocument($name);
+
+		return DocxToHTML::formatText($content);
+	}
+
+	public static function readDocument(string $name): string
+	{
+		try {
+			$zip = new ZipArchive;
+			$unzip = $zip->open($name, 16);
+
+			if ($unzip !== true) {
+				throw new Exception("Couldn't open file: $name", 1);
+			}
+
+			$content = $zip->getFromName('word/document.xml');
+			$zip->close();
+
+			return $content;
+		}
+		catch (Exception $exception) {
+			return $exception->getMessage();
+		}
+	}
+
+	public static function formatText(string $text): string
+	{
+		$formattedText = $text;
+		$formattedText = str_replace('</w:r></w:p></w:tc><w:tc>', ' ', $formattedText);
+		$formattedText = str_replace('</w:r></w:p>', '\r\n', $formattedText);
+		$formattedText = strip_tags($formattedText);
+		$formattedText = str_replace('\r\n', '<br>', $formattedText);
+
+		return $formattedText;
+	}
+}

index.php

@@ -5,14 +5,14 @@
  * plain text file.
  */
 
-include_once 'document-converter.php';
+include_once 'inc/document-converter.php';
 
 
 dir_digger(__DIR__ . '\documents\\', scandir(__DIR__ . '\documents\\')); // Windows path
 
 
 /**
- * Goes through all the nested directries
+ * Goes through all the nested directories
  *
  * @param string $dir_url
  * @param array $dir_cont
@@ -29,12 +29,12 @@ function dir_digger($dir_url, $dir_cont) {
 			dir_digger($nested_dir_url, $nested_dir_cont);
 		}
 		else {
-			$file_url		= $dir_url . $dir_cont[$i];
-			$file_obj		= new Docx_Conversion($file_url);
-			$file_cont	= $file_obj->convert_to_text();
+			// TODO: add the file check around here:
+			$fileName = $dir_url . $dir_cont[$i];
+			$fileContent = DocxToHTML::getText($fileName);
 
-			if ($file_cont !== 'Invalid file type') {
-				echo '<div style="padding: 1rem;">' . $file_cont . '</div>';
+			if ($fileContent !== 'Invalid file type') {
+				echo '<div style="padding: 1rem;">' . $fileContent . '</div>';
 			}
 		}
 	}

readme.md

@@ -3,17 +3,12 @@ The script in this repository crawls through directories, looks for MS Word docu
 Remember to change the Windows `\` with `/` in the paths if you're running the script on Linux.
 
 ## Requirements
-- folder named `/documetns` that will contain the documents in the root dir.
+- folder named `/documents` that will contain the documents in the root dir.
 
-## Known issues
-- in Windows, the script can't output `.doc` files properly, outputs a string of random characters (`Y, B8L 1(IzZYrH9pd4n(KgVB,lDAeX)Ly5otebW3gpj/gQjZTae9i5j5fE514g7vnO( ,jV9kvvadVoTAn7jahy@ARhW.GMuO /e5sZWfPtfkA0zUw@tAm4T2j 6Q`).
-
-## Resoruces
-- base on a [stackoverflow answer](https://stackoverflow.com/questions/19503653/how-to-extract-text-from-word-file-doc-docx-xlsx-pptx-php)
+## Resources
+- base on a [StackOverflow answer](https://stackoverflow.com/questions/19503653/how-to-extract-text-from-word-file-doc-docx-xlsx-pptx-php)
 
 ## TODO:
-- craete interface that allows the upload of multiple forms;
-- extract the recursive serach into it's own function;
-- refactor the main class to allow scaling;
-- add markup parser;
+- extract the recursive search into it's own function;
+- add markup parser; and
 - add more supported files.