Nomad changes

docs/snippets/php/quickstart/basic_extraction_oop.php

@@ -0,0 +1,39 @@
+```php title="basic_extraction_oop.php"
+<?php
+
+declare(strict_types=1);
+
+/**
+ * Basic Document Extraction (OOP API)
+ *
+ * This example demonstrates the simplest way to extract text from a document
+ * using the object-oriented API.
+ */
+
+require_once __DIR__ . '/vendor/autoload.php';
+
+use Kreuzberg\Kreuzberg;
+
+$kreuzberg = new Kreuzberg();
+
+$result = $kreuzberg->extractFile('document.pdf');
+
+echo "Extracted Content:\n";
+echo "==================\n";
+echo $result->content . "\n\n";
+
+echo "Metadata:\n";
+echo "=========\n";
+echo "Title: " . ($result->metadata->title ?? 'N/A') . "\n";
+echo "Authors: " . (isset($result->metadata->authors) ? implode(', ', $result->metadata->authors) : 'N/A') . "\n";
+echo "Pages: " . ($result->metadata->pageCount ?? 'N/A') . "\n";
+echo "Format: " . $result->mimeType . "\n\n";
+
+if (count($result->tables) > 0) {
+    echo "Tables Found: " . count($result->tables) . "\n";
+    foreach ($result->tables as $index => $table) {
+        echo "\nTable " . ($index + 1) . " (Page {$table->pageNumber}):\n";
+        echo $table->markdown . "\n";
+    }
+}
+```

docs/snippets/php/quickstart/basic_extraction_procedural.php

@@ -0,0 +1,35 @@
+```php title="basic_extraction_procedural.php"
+<?php
+
+declare(strict_types=1);
+
+/**
+ * Basic Document Extraction (Procedural API)
+ *
+ * This example shows the procedural API for document extraction,
+ * which is more concise for simple use cases.
+ */
+
+require_once __DIR__ . '/vendor/autoload.php';
+
+use function Kreuzberg\extract_file;
+
+$result = extract_file('document.pdf');
+
+echo "Extracted Text:\n";
+echo str_repeat('=', 50) . "\n";
+echo $result->content . "\n\n";
+
+echo "Document Information:\n";
+echo str_repeat('=', 50) . "\n";
+printf("Title:   %s\n", $result->metadata->title ?? 'Unknown');
+printf("Authors: %s\n", isset($result->metadata->authors) ? implode(', ', $result->metadata->authors) : 'Unknown');
+printf("Pages:   %d\n", $result->metadata->pageCount ?? 0);
+printf("Format:  %s\n", $result->mimeType);
+
+$char_count = mb_strlen($result->content);
+$word_count = str_word_count($result->content);
+printf("\nStatistics:\n");
+printf("Characters: %d\n", $char_count);
+printf("Words:      %d\n", $word_count);
+```

docs/snippets/php/quickstart/extract_from_bytes.php

@@ -0,0 +1,44 @@
+```php title="extract_from_bytes.php"
+<?php
+
+declare(strict_types=1);
+
+/**
+ * Extracting from Bytes
+ *
+ * Extract content from file data in memory instead of from disk.
+ * Useful for processing uploaded files or data from remote sources.
+ */
+
+require_once __DIR__ . '/vendor/autoload.php';
+
+use Kreuzberg\Kreuzberg;
+use function Kreuzberg\extract_bytes;
+
+$fileData = file_get_contents('document.pdf');
+$mimeType = 'application/pdf';
+
+$result = extract_bytes($fileData, $mimeType);
+echo "Extracted using procedural API:\n";
+echo substr($result->content, 0, 200) . "...\n\n";
+
+$kreuzberg = new Kreuzberg();
+$result = $kreuzberg->extractBytes($fileData, $mimeType);
+echo "Extracted using OOP API:\n";
+echo substr($result->content, 0, 200) . "...\n\n";
+
+$uploadedFile = [
+    'tmp_name' => '/tmp/uploaded_document.pdf',
+    'type' => 'application/pdf',
+    'size' => 1024000,
+];
+
+if (file_exists($uploadedFile['tmp_name'])) {
+    $data = file_get_contents($uploadedFile['tmp_name']);
+    $result = extract_bytes($data, $uploadedFile['type']);
+
+    echo "Uploaded file processed:\n";
+    echo "Size: " . strlen($data) . " bytes\n";
+    echo "Content length: " . strlen($result->content) . " characters\n";
+}
+```

docs/snippets/php/quickstart/mime_type_detection.php

@@ -0,0 +1,53 @@
+```php title="mime_type_detection.php"
+<?php
+
+declare(strict_types=1);
+
+/**
+ * MIME Type Detection
+ *
+ * Kreuzberg can automatically detect MIME types from file content or paths.
+ * This is useful when the file extension is missing or unreliable.
+ */
+
+require_once __DIR__ . '/vendor/autoload.php';
+
+use function Kreuzberg\detect_mime_type;
+use function Kreuzberg\detect_mime_type_from_path;
+use function Kreuzberg\extract_file;
+
+$path = 'document.pdf';
+$mimeType = detect_mime_type_from_path($path);
+echo "Detected MIME type from path: $mimeType\n";
+
+$data = file_get_contents($path);
+$mimeType = detect_mime_type($data);
+echo "Detected MIME type from content: $mimeType\n\n";
+
+$unknownFile = 'file_without_extension';
+if (file_exists($unknownFile)) {
+    $detectedType = detect_mime_type_from_path($unknownFile);
+    echo "Unknown file detected as: $detectedType\n";
+
+    $result = extract_file($unknownFile, $detectedType);
+    echo "Successfully extracted " . strlen($result->content) . " characters\n";
+}
+
+$allowedTypes = [
+    'application/pdf',
+    'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
+    'text/plain',
+];
+
+$fileToCheck = 'user_upload.dat';
+if (file_exists($fileToCheck)) {
+    $type = detect_mime_type_from_path($fileToCheck);
+
+    if (in_array($type, $allowedTypes, true)) {
+        echo "File type $type is allowed, processing...\n";
+        $result = extract_file($fileToCheck);
+    } else {
+        echo "File type $type is not allowed\n";
+    }
+}
+```