diff --git a/composer.json b/composer.json
index 7d89ffa..0681584 100644
--- a/composer.json
+++ b/composer.json
@@ -27,7 +27,9 @@
         "symfony/serializer": "^7.1",
         "symfony/property-access": "^7.1",
         "webmozart/assert": "^1.11",
-        "league/commonmark": "^2.4"
+        "league/commonmark": "^2.4",
+        "smalot/pdfparser": "^2.10",
+        "symfony/filesystem": "^7.1"
     },
     "require-dev": {
         "phpunit/phpunit": "^11.1",
diff --git a/composer.lock b/composer.lock
index 5fcee88..610d91e 100644
--- a/composer.lock
+++ b/composer.lock
@@ -4,7 +4,7 @@
         "Read more about it at https://getcomposer.org/doc/01-basic-usage.md#installing-dependencies",
         "This file is @generated automatically"
     ],
-    "content-hash": "1a1fc0bc0e899a1c9197cbd2c6d17d37",
+    "content-hash": "0cab03fcceac267b78fa89ff1ea15a6a",
     "packages": [
         {
             "name": "dflydev/dot-access-data",
@@ -570,6 +570,57 @@
             },
             "time": "2021-07-14T16:46:02+00:00"
         },
+        {
+            "name": "smalot/pdfparser",
+            "version": "v2.10.0",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/smalot/pdfparser.git",
+                "reference": "14adf318f8620a6195c0b00d51c6a507837b9ff4"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/smalot/pdfparser/zipball/14adf318f8620a6195c0b00d51c6a507837b9ff4",
+                "reference": "14adf318f8620a6195c0b00d51c6a507837b9ff4",
+                "shasum": ""
+            },
+            "require": {
+                "ext-iconv": "*",
+                "ext-zlib": "*",
+                "php": ">=7.1",
+                "symfony/polyfill-mbstring": "^1.18"
+            },
+            "type": "library",
+            "autoload": {
+                "psr-0": {
+                    "Smalot\\PdfParser\\": "src/"
+                }
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "LGPL-3.0"
+            ],
+            "authors": [
+                {
+                    "name": "Sebastien MALOT",
+                    "email": "sebastien@malot.fr"
+                }
+            ],
+            "description": "Pdf parser library. Can read and extract information from pdf file.",
+            "homepage": "https://www.pdfparser.org",
+            "keywords": [
+                "extract",
+                "parse",
+                "parser",
+                "pdf",
+                "text"
+            ],
+            "support": {
+                "issues": "https://github.com/smalot/pdfparser/issues",
+                "source": "https://github.com/smalot/pdfparser/tree/v2.10.0"
+            },
+            "time": "2024-04-29T06:36:50+00:00"
+        },
         {
             "name": "symfony/deprecation-contracts",
             "version": "v3.5.0",
@@ -637,6 +688,72 @@
             ],
             "time": "2024-04-18T09:32:20+00:00"
         },
+        {
+            "name": "symfony/filesystem",
+            "version": "v7.1.2",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/symfony/filesystem.git",
+                "reference": "92a91985250c251de9b947a14bb2c9390b1a562c"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/symfony/filesystem/zipball/92a91985250c251de9b947a14bb2c9390b1a562c",
+                "reference": "92a91985250c251de9b947a14bb2c9390b1a562c",
+                "shasum": ""
+            },
+            "require": {
+                "php": ">=8.2",
+                "symfony/polyfill-ctype": "~1.8",
+                "symfony/polyfill-mbstring": "~1.8"
+            },
+            "require-dev": {
+                "symfony/process": "^6.4|^7.0"
+            },
+            "type": "library",
+            "autoload": {
+                "psr-4": {
+                    "Symfony\\Component\\Filesystem\\": ""
+                },
+                "exclude-from-classmap": [
+                    "/Tests/"
+                ]
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "MIT"
+            ],
+            "authors": [
+                {
+                    "name": "Fabien Potencier",
+                    "email": "fabien@symfony.com"
+                },
+                {
+                    "name": "Symfony Community",
+                    "homepage": "https://symfony.com/contributors"
+                }
+            ],
+            "description": "Provides basic utilities for the filesystem",
+            "homepage": "https://symfony.com",
+            "support": {
+                "source": "https://github.com/symfony/filesystem/tree/v7.1.2"
+            },
+            "funding": [
+                {
+                    "url": "https://symfony.com/sponsor",
+                    "type": "custom"
+                },
+                {
+                    "url": "https://github.com/fabpot",
+                    "type": "github"
+                },
+                {
+                    "url": "https://tidelift.com/funding/github/packagist/symfony/symfony",
+                    "type": "tidelift"
+                }
+            ],
+            "time": "2024-06-28T10:03:55+00:00"
+        },
         {
             "name": "symfony/http-client",
             "version": "v7.1.1",
diff --git a/src/Retrieval/Loader/DirectoryLoader.php b/src/Retrieval/Loader/Directory/DirectoryLoader.php
similarity index 50%
rename from src/Retrieval/Loader/DirectoryLoader.php
rename to src/Retrieval/Loader/Directory/DirectoryLoader.php
index ddad6fa..734ba28 100644
--- a/src/Retrieval/Loader/DirectoryLoader.php
+++ b/src/Retrieval/Loader/Directory/DirectoryLoader.php
@@ -11,9 +11,11 @@
 
 declare(strict_types=1);
 
-namespace Devscast\Lugha\Retrieval\Loader;
+namespace Devscast\Lugha\Retrieval\Loader\Directory;
 
 use Devscast\Lugha\Retrieval\Document;
+use Devscast\Lugha\Retrieval\Loader\LoaderInterface;
+use Devscast\Lugha\Retrieval\Metadata;
 use Devscast\Lugha\Retrieval\Splitter\SplitterInterface;
 
 /**
@@ -25,24 +27,38 @@
 readonly class DirectoryLoader implements LoaderInterface
 {
     public function __construct(
-        public string $directory,
-        public ?string $glob = null
+        public string $path
     ) {
     }
 
     /**
      * @return iterable<Document>
      */
+    #[\Override]
     public function load(): iterable
     {
-        return [];
+        /** @var RecursiveDirectoryIterator|\DirectoryIterator $file */
+        foreach (new WildcardDirectoryIterator($this->path) as $file) {
+            if ($file->isFile()) {
+                yield new Document(
+                    content: (string) file_get_contents($file->getPathname()),
+                    metadata: new Metadata(
+                        sourceType: 'file',
+                        sourceName: $file->getFilename(),
+                    ),
+                );
+            }
+        }
     }
 
     /**
      * @return iterable<Document>
      */
+    #[\Override]
     public function loadAndSplit(SplitterInterface $splitter): iterable
     {
-        return [];
+        foreach ($this->load() as $document) {
+            yield from $splitter->createDocuments($document);
+        }
     }
 }
diff --git a/src/Retrieval/Loader/Directory/RecursiveDirectoryIterator.php b/src/Retrieval/Loader/Directory/RecursiveDirectoryIterator.php
new file mode 100644
index 0000000..2114bf7
--- /dev/null
+++ b/src/Retrieval/Loader/Directory/RecursiveDirectoryIterator.php
@@ -0,0 +1,33 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Retrieval\Loader\Directory;
+
+use RecursiveDirectoryIterator as NativeRecursiveDirectoryIterator;
+use RecursiveIteratorIterator;
+
+/**
+ * Class RealRecursiveDirectoryIterator.
+ *
+ * @extends RecursiveIteratorIterator<NativeRecursiveDirectoryIterator>
+ * @see https://www.php.net/manual/en/class.recursivedirectoryiterator.php
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final class RecursiveDirectoryIterator extends RecursiveIteratorIterator
+{
+    public function __construct(string $path)
+    {
+        parent::__construct(new NativeRecursiveDirectoryIterator($path));
+    }
+}
diff --git a/src/Retrieval/Loader/Directory/WildcardDirectoryIterator.php b/src/Retrieval/Loader/Directory/WildcardDirectoryIterator.php
new file mode 100644
index 0000000..69b0b6d
--- /dev/null
+++ b/src/Retrieval/Loader/Directory/WildcardDirectoryIterator.php
@@ -0,0 +1,62 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Retrieval\Loader\Directory;
+
+use DirectoryIterator;
+use FilterIterator;
+
+/**
+ * Class WildcardDirectoryIterator.
+ *
+ * @extends FilterIterator<int, string, RecursiveDirectoryIterator|DirectoryIterator>
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final class WildcardDirectoryIterator extends FilterIterator
+{
+    private string $regex;
+
+    public function __construct(string $path)
+    {
+        $recursive = false;
+
+        if (str_starts_with($path, '-R ')) {
+            $recursive = true;
+            $path = substr($path, 3);
+        }
+
+        if (preg_match('~/?([^/]*\*[^/]*)$~', $path, $matches)) { // matched wildcards in filename
+            $path = substr($path, 0, -strlen($matches[1]) - 1); // strip wildcards part from path
+            $this->regex = '~^' . str_replace('*', '.*', str_replace('.', '\.', $matches[1])) . '$~'; // convert wildcards to regex
+
+            if (! $path) {
+                $path = '.'; // if no path given, we assume CWD;
+            }
+        }
+
+        parent::__construct($recursive ? new RecursiveDirectoryIterator($path) : new DirectoryIterator($path));
+    }
+
+    /**
+     * Checks for regex in current filename, or matches all if no regex specified
+     */
+    #[\Override]
+    public function accept(): bool
+    {
+        /** @var RecursiveDirectoryIterator|DirectoryIterator $iterator */
+        $iterator = $this->getInnerIterator();
+
+        return (bool) preg_match($this->regex, $iterator->getFilename());
+    }
+}
diff --git a/src/Retrieval/Loader/Reader/AbstractReader.php b/src/Retrieval/Loader/Reader/AbstractReader.php
new file mode 100644
index 0000000..223a241
--- /dev/null
+++ b/src/Retrieval/Loader/Reader/AbstractReader.php
@@ -0,0 +1,64 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Retrieval\Loader\Reader;
+
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\FileNotFoundException;
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\UnreadableFileException;
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\UnsupportedFileException;
+use Symfony\Component\Filesystem\Path;
+
+/**
+ * Interface AbstractReader.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+abstract readonly class AbstractReader
+{
+    /**
+     * Supported extensions regex pattern
+     */
+    public const string SUPPORTED_EXTENSIONS_PATTERN = '';
+
+    /**
+     * @throws UnsupportedFileException If the file extension is not supported and the check is not skipped.
+     * @throws UnreadableFileException When the content cannot be read for any other reason
+     * @throws FileNotFoundException When the given file does not exist
+     */
+    abstract public function readContent(string $path, bool $skipExtensionCheck = false): string;
+
+    final public function supports(string $path): bool
+    {
+        $extension = Path::getExtension($path, forceLowerCase: true);
+        return (bool) preg_match(static::SUPPORTED_EXTENSIONS_PATTERN, $extension);
+    }
+
+    final public function ensureSupported(string $path): void
+    {
+        $extension = Path::getExtension($path, forceLowerCase: true);
+        if ($this->supports($path) === false) {
+            throw new UnsupportedFileException([$extension, static::SUPPORTED_EXTENSIONS_PATTERN]);
+        }
+    }
+
+    final public function ensureFileExists(string $path): void
+    {
+        if (file_exists($path) === false) {
+            throw new FileNotFoundException($path);
+        }
+
+        if (is_readable($path) === false) {
+            throw new UnreadableFileException($path);
+        }
+    }
+}
diff --git a/src/Retrieval/Loader/Reader/DocReader.php b/src/Retrieval/Loader/Reader/DocReader.php
new file mode 100644
index 0000000..785e38a
--- /dev/null
+++ b/src/Retrieval/Loader/Reader/DocReader.php
@@ -0,0 +1,35 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Retrieval\Loader\Reader;
+
+/**
+ * Class DocReader.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final readonly class DocReader extends AbstractReader
+{
+    public const string SUPPORTED_EXTENSIONS_PATTERN = '/docx?/';
+
+    #[\Override]
+    public function readContent(string $path, bool $skipExtensionCheck = false): string
+    {
+        if ($skipExtensionCheck === false) {
+            $this->ensureSupported($path);
+            $this->ensureFileExists($path);
+        }
+
+        return '';
+    }
+}
diff --git a/src/Retrieval/Loader/Reader/Exception/FileNotFoundException.php b/src/Retrieval/Loader/Reader/Exception/FileNotFoundException.php
new file mode 100644
index 0000000..b2c2a49
--- /dev/null
+++ b/src/Retrieval/Loader/Reader/Exception/FileNotFoundException.php
@@ -0,0 +1,28 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Retrieval\Loader\Reader\Exception;
+
+/**
+ * Class UnsupportedFileException.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final class FileNotFoundException extends \RuntimeException
+{
+    public function __construct(string $file, int $code = 0, \Throwable $previous = null)
+    {
+        $message = sprintf('Failed to open stream: No such file %s', $file);
+        parent::__construct($message, $code, $previous);
+    }
+}
diff --git a/src/Retrieval/Loader/Reader/Exception/UnreadableFileException.php b/src/Retrieval/Loader/Reader/Exception/UnreadableFileException.php
new file mode 100644
index 0000000..4889cd5
--- /dev/null
+++ b/src/Retrieval/Loader/Reader/Exception/UnreadableFileException.php
@@ -0,0 +1,28 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Retrieval\Loader\Reader\Exception;
+
+/**
+ * Class UnsupportedFileException.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final class UnreadableFileException extends \RuntimeException
+{
+    public function __construct(string $file, int $code = 0, \Throwable $previous = null)
+    {
+        $message = sprintf('Unable to read the content of %s', $file);
+        parent::__construct($message, $code, $previous);
+    }
+}
diff --git a/src/Retrieval/Loader/Reader/Exception/UnsupportedFileException.php b/src/Retrieval/Loader/Reader/Exception/UnsupportedFileException.php
new file mode 100644
index 0000000..170c5b7
--- /dev/null
+++ b/src/Retrieval/Loader/Reader/Exception/UnsupportedFileException.php
@@ -0,0 +1,31 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Retrieval\Loader\Reader\Exception;
+
+/**
+ * Class UnsupportedFileException.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final class UnsupportedFileException extends \RuntimeException
+{
+    public function __construct(
+        array $extensions = [],
+        int $code = 0,
+        \Throwable $previous = null
+    ) {
+        $message = vsprintf('The given %s file is not supported, this reader supports %s files', $extensions);
+        parent::__construct($message, $code, $previous);
+    }
+}
diff --git a/src/Retrieval/Loader/Reader/FileReader.php b/src/Retrieval/Loader/Reader/FileReader.php
new file mode 100644
index 0000000..5441dc3
--- /dev/null
+++ b/src/Retrieval/Loader/Reader/FileReader.php
@@ -0,0 +1,52 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Retrieval\Loader\Reader;
+
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\UnsupportedFileException;
+use Symfony\Component\Filesystem\Path;
+
+/**
+ * Class FileReader.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final readonly class FileReader extends AbstractReader
+{
+    public const string SUPPORTED_EXTENSIONS_PATTERN = '/txt|pdf|docx?/';
+
+    #[\Override]
+    public function readContent(string $path, bool $skipExtensionCheck = false): string
+    {
+        foreach ($this->getSupportedReaders() as $reader) {
+            if ($reader->supports($path)) {
+                $this->ensureFileExists($path);
+                return $reader->readContent($path, skipExtensionCheck: true);
+            }
+        }
+
+        $extension = Path::getExtension($path, forceLowerCase: true);
+        throw new UnsupportedFileException([$extension, self::SUPPORTED_EXTENSIONS_PATTERN]);
+    }
+
+    /**
+     * @return array<int, AbstractReader>
+     */
+    private function getSupportedReaders(): array
+    {
+        return [
+            new TxtReader(),
+            new PdfReader(),
+        ];
+    }
+}
diff --git a/src/Retrieval/Loader/Reader/PdfReader.php b/src/Retrieval/Loader/Reader/PdfReader.php
new file mode 100644
index 0000000..d8e4175
--- /dev/null
+++ b/src/Retrieval/Loader/Reader/PdfReader.php
@@ -0,0 +1,57 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Retrieval\Loader\Reader;
+
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\UnreadableFileException;
+use Smalot\PdfParser\{Config, Parser};
+
+/**
+ * Class PdfReader.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final readonly class PdfReader extends AbstractReader
+{
+    public const string SUPPORTED_EXTENSIONS_PATTERN = '/pdf/';
+
+    private Config $config;
+
+    private Parser $parser;
+
+    public function __construct()
+    {
+        $this->config = new Config();
+
+        // It won't retain image content anymore, but will use less memory too.
+        $this->config->setRetainImageContent(false);
+        $this->parser = new Parser(config: $this->config);
+    }
+
+    #[\Override]
+    public function readContent(string $path, bool $skipExtensionCheck = false): string
+    {
+        if ($skipExtensionCheck === false) {
+            $this->ensureSupported($path);
+            $this->ensureFileExists($path);
+        }
+
+        try {
+            $pdf = $this->parser->parseFile($path);
+        } catch (\Exception $e) {
+            throw new UnreadableFileException($path, previous: $e);
+        }
+
+        return $pdf->getText();
+    }
+}
diff --git a/src/Retrieval/Loader/Reader/TxtReader.php b/src/Retrieval/Loader/Reader/TxtReader.php
new file mode 100644
index 0000000..7a50239
--- /dev/null
+++ b/src/Retrieval/Loader/Reader/TxtReader.php
@@ -0,0 +1,43 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Retrieval\Loader\Reader;
+
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\UnreadableFileException;
+
+/**
+ * Class TxtReader.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final readonly class TxtReader extends AbstractReader
+{
+    public const string SUPPORTED_EXTENSIONS_PATTERN = '/txt/';
+
+    #[\Override]
+    public function readContent(string $path, bool $skipExtensionCheck = false): string
+    {
+        if ($skipExtensionCheck === false) {
+            $this->ensureSupported($path);
+            $this->ensureFileExists($path);
+        }
+
+        $content = file_get_contents($path);
+
+        if ($content === false) {
+            throw new UnreadableFileException($path);
+        }
+
+        return $content;
+    }
+}
diff --git a/src/Retrieval/Metadata.php b/src/Retrieval/Metadata.php
index 1341aae..baa0d1e 100644
--- a/src/Retrieval/Metadata.php
+++ b/src/Retrieval/Metadata.php
@@ -33,6 +33,7 @@ public function __construct(
     /**
      * @throws \JsonException
      */
+    #[\Override]
     public function __toString(): string
     {
         return json_encode([
diff --git a/src/Retrieval/Splitter/SplitterInterface.php b/src/Retrieval/Splitter/SplitterInterface.php
index 3f5c12b..55ede0d 100644
--- a/src/Retrieval/Splitter/SplitterInterface.php
+++ b/src/Retrieval/Splitter/SplitterInterface.php
@@ -30,5 +30,5 @@ public function splitText(string $text): iterable;
     /**
      * @return iterable<Document>
      */
-    public function createDocuments(string $text): iterable;
+    public function createDocuments(Document|string $text): iterable;
 }
diff --git a/src/Retrieval/Splitter/TextSplitter.php b/src/Retrieval/Splitter/TextSplitter.php
index e91bf5e..10a1561 100644
--- a/src/Retrieval/Splitter/TextSplitter.php
+++ b/src/Retrieval/Splitter/TextSplitter.php
@@ -72,8 +72,12 @@ public function splitText(string $text): iterable
     }
 
     #[\Override]
-    public function createDocuments(string $text): iterable
+    public function createDocuments(Document|string $text): iterable
     {
+        if ($text instanceof Document) {
+            $text = $text->content;
+        }
+
         /**
          * @var int $index
          */
diff --git a/tests/Retrieval/Loader/Reader/FileReaderTest.php b/tests/Retrieval/Loader/Reader/FileReaderTest.php
new file mode 100644
index 0000000..787bd4a
--- /dev/null
+++ b/tests/Retrieval/Loader/Reader/FileReaderTest.php
@@ -0,0 +1,56 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Tests\Retrieval\Loader\Reader;
+
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\FileNotFoundException;
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\UnsupportedFileException;
+use Devscast\Lugha\Retrieval\Loader\Reader\FileReader;
+use PHPUnit\Framework\TestCase;
+
+/**
+ * Class FileReaderTest.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final class FileReaderTest extends TestCase
+{
+    private FileReader $reader;
+
+    protected function setUp(): void
+    {
+        $this->reader = new FileReader();
+        parent::setUp();
+    }
+
+    public function testReadContentWithTheBestReader(): void
+    {
+        $text = $this->reader->readContent(__DIR__ . '/../../../fixtures/document.txt');
+        $pdf = $this->reader->readContent(__DIR__ . '/../../../fixtures/document.pdf');
+
+        $this->assertSame('hello world', $text);
+        $this->assertSame('helloworld', $pdf);
+    }
+
+    public function testCannotReadUnsupportedFile(): void
+    {
+        $this->expectException(UnsupportedFileException::class);
+        $content = $this->reader->readContent(__DIR__ . '/../../../fixtures/document.docx');
+    }
+
+    public function testCannotReadNonExistingFile(): void
+    {
+        $this->expectException(FileNotFoundException::class);
+        $content = $this->reader->readContent(__DIR__ . '/../../../fixtures/does-not-exist.pdf');
+    }
+}
diff --git a/tests/Retrieval/Loader/Reader/PdfReaderTest.php b/tests/Retrieval/Loader/Reader/PdfReaderTest.php
new file mode 100644
index 0000000..7e13e36
--- /dev/null
+++ b/tests/Retrieval/Loader/Reader/PdfReaderTest.php
@@ -0,0 +1,63 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Tests\Retrieval\Loader\Reader;
+
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\FileNotFoundException;
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\UnreadableFileException;
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\UnsupportedFileException;
+use Devscast\Lugha\Retrieval\Loader\Reader\PdfReader;
+use PHPUnit\Framework\TestCase;
+
+/**
+ * Class PdfReaderTest.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final class PdfReaderTest extends TestCase
+{
+    private PdfReader $reader;
+
+    protected function setUp(): void
+    {
+        $this->reader = new PdfReader();
+        parent::setUp();
+    }
+
+    public function testReadContent(): void
+    {
+        $content = $this->reader->readContent(__DIR__ . '/../../../fixtures/document.pdf');
+        $this->assertSame('helloworld', $content); // TODO: try to understand why whitespace is not taken into account
+    }
+
+    public function testCannotReadNonExistingFile(): void
+    {
+        $this->expectException(FileNotFoundException::class);
+        $content = $this->reader->readContent(__DIR__ . '/../../../fixtures/does-not-exist.pdf');
+    }
+
+    public function testCannotReadFileWithoutReadPermission(): void
+    {
+        touch('/tmp/test.pdf');
+        chmod('/tmp/test.pdf', 000);
+
+        $this->expectException(UnreadableFileException::class);
+        $content = $this->reader->readContent('/tmp/test.pdf');
+    }
+
+    public function testReadContentOnUnsupportedFile(): void
+    {
+        $this->expectException(UnsupportedFileException::class);
+        $content = $this->reader->readContent(__DIR__ . '/../../../fixtures/document.txt');
+    }
+}
diff --git a/tests/Retrieval/Loader/Reader/TxtReaderTest.php b/tests/Retrieval/Loader/Reader/TxtReaderTest.php
new file mode 100644
index 0000000..af1afa4
--- /dev/null
+++ b/tests/Retrieval/Loader/Reader/TxtReaderTest.php
@@ -0,0 +1,63 @@
+<?php
+
+/*
+ * This file is part of the Lugha package.
+ *
+ * (c) Bernard Ngandu <bernard@devscast.tech>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
+
+declare(strict_types=1);
+
+namespace Devscast\Lugha\Tests\Retrieval\Loader\Reader;
+
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\FileNotFoundException;
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\UnreadableFileException;
+use Devscast\Lugha\Retrieval\Loader\Reader\Exception\UnsupportedFileException;
+use Devscast\Lugha\Retrieval\Loader\Reader\TxtReader;
+use PHPUnit\Framework\TestCase;
+
+/**
+ * Class TxtReaderTest.
+ *
+ * @author bernard-ng <bernard@devscast.tech>
+ */
+final class TxtReaderTest extends TestCase
+{
+    private TxtReader $reader;
+
+    protected function setUp(): void
+    {
+        $this->reader = new TxtReader();
+        parent::setUp();
+    }
+
+    public function testReadContent(): void
+    {
+        $content = $this->reader->readContent(__DIR__ . '/../../../fixtures/document.txt');
+        $this->assertSame('hello world', $content);
+    }
+
+    public function testCannotReadNonExistingFile(): void
+    {
+        $this->expectException(FileNotFoundException::class);
+        $content = $this->reader->readContent(__DIR__ . '/../../../fixtures/does-not-exist.txt');
+    }
+
+    public function testCannotReadFileWithoutReadPermission(): void
+    {
+        touch('/tmp/test.txt');
+        chmod('/tmp/test.txt', 000);
+
+        $this->expectException(UnreadableFileException::class);
+        $content = $this->reader->readContent('/tmp/test.txt');
+    }
+
+    public function testReadContentOnUnsupportedFile(): void
+    {
+        $this->expectException(UnsupportedFileException::class);
+        $content = $this->reader->readContent(__DIR__ . '/../../../fixtures/document.pdf');
+    }
+}
diff --git a/tests/fixtures/document.docx b/tests/fixtures/document.docx
new file mode 100644
index 0000000..0696fb8
Binary files /dev/null and b/tests/fixtures/document.docx differ
diff --git a/tests/fixtures/document.pdf b/tests/fixtures/document.pdf
new file mode 100644
index 0000000..0908db2
Binary files /dev/null and b/tests/fixtures/document.pdf differ
diff --git a/tests/fixtures/document.txt b/tests/fixtures/document.txt
new file mode 100644
index 0000000..95d09f2
--- /dev/null
+++ b/tests/fixtures/document.txt
@@ -0,0 +1 @@
+hello world
\ No newline at end of file