umer936 · May 19, 2025 17:13
diff --git a/HTMLtoPHPWord.php b/HTMLtoPHPWord.php
 <?php
 declare(strict_types=1);

 /**
 * Writes a Word document of abstracts
 *
 * @param string $path The path to the Word document
 * @param int|null $conference_id
 * @return bool Whether the write was successful
 * @throws \PhpOffice\PhpWord\Exception\Exception
 */
 public function writeDocument(string $path, int|null $conference_id = null): bool
 {
    $word = new PhpWord();
    $word->addTitleStyle(1, ['bold' => true, 'size' => 16]);
    $word->addParagraphStyle('abstract', ['indentation' => ['left' => 240]]);

    // Add Conference Title as a header
    $section = $word->addSection();
    $headerText = $section->addTextRun(['alignment' => 'center']);
    $headerText->addText(CONFERENCE_TITLE, ['bold' => true, 'size' => 18]);
    $section->addText("\n\n");

    // Maybe have a logo and the text: "Book of Abstracts"
    // Can be added with: $section->addImage('path_to_logo');

    // Loop through each track and add its abstracts
    $tracks = $this->Tracks->find();
    foreach ($tracks as $track) {
        if ($abstracts->count()) {
            $section = $word->addSection();
            $section->addTitle(h($track->description));

            foreach ($abstracts as $abstract) {
                $section->addTextRun()->addText(h($abstract->registrant->full_name), ['bold' => true]);

                // Clean and process the abstract HTML
                $cleanedAbstract = $this->sanitizeHtml($abstract->abstract);

                // Add the processed HTML content to the section
                $this->addHtmlContentToSection($section, $cleanedAbstract);
            }
        }
    }

    // Save the document
    $writer = IOFactory::createWriter($word);
    $writer->save($path);

    // Return whether the file exists after saving
    return file_exists($path);
 }

 /**
 * Sanitize the HTML content before adding it to the Word document.
 *
 * @param string $html The HTML content to sanitize.
 * @return string The sanitized HTML.
 */
 private function sanitizeHtml(string $html): string
 {
    // Decode HTML entities
    $html = html_entity_decode($html, ENT_QUOTES | ENT_HTML5, 'UTF-8');

    // Allow only safe HTML tags (this list can be adjusted as needed)
    $allowedTags = '<p><br><b><i><u><em><strong><ul><ol><li><a>';

    // Remove any tags not in the allowed list
    $html = strip_tags($html, $allowedTags);

    // You can also perform additional sanitization like removing harmful attributes (e.g., on <a> tags)
    $html = preg_replace('/<a\s+([^>]+)>/', '<a>', $html);  // Strips out attributes from <a> tags, like href

    return $html;
 }

 /**
 * Adds the sanitized HTML content to the PhpWord section.
 *
 * @param \PhpOffice\PhpWord\Element\Section $section The PhpWord section where the content will be added.
 * @param string $html The HTML content to add.
 */
 private function addHtmlContentToSection(\PhpOffice\PhpWord\Element\Section $section, string $html)
 {
    // Check if the HTML content is just a single paragraph without complex tags
    if (preg_match('/^<p>.*<\/p>$/', $html)) {
        // If it's a single <p>, treat it as a simple block of text
        $section->addText(strip_tags($html), null, 'abstract');
    } else {
        // Load the HTML content into a DOMDocument for more complex HTML
        $dom = new \DOMDocument();
        libxml_use_internal_errors(true); // Disable warnings for malformed HTML
        $dom->loadHTML('<html><body>' . $html . '</body></html>'); // Wrap HTML in a body tag to make it valid
        libxml_clear_errors();

        // Process each child element of the body
        $body = $dom->getElementsByTagName('body')->item(0);
        foreach ($body->childNodes as $node) {
            if ($node->nodeName === 'p') {
                // Handle paragraphs (<p>)
                $section->addTextBreak(1);
                $this->addTextNodeToSection($section, $node);
            } elseif ($node->nodeName === 'br') {
                // Handle line breaks (<br>)
                $section->addTextBreak(1);
            } else {
                // Handle other text nodes
                $this->addTextNodeToSection($section, $node);
            }
        }
    }
 }

 /**
 * Adds a text node to the PhpWord section, handling basic formatting.
 *
 * @param \PhpOffice\PhpWord\Element\Section $section The PhpWord section.
 * @param \DOMNode $node The DOMNode containing the text.
 */
 private function addTextNodeToSection(\PhpOffice\PhpWord\Element\Section $section, \DOMNode $node)
 {
    match ($node->nodeName) {
        'b', 'strong' => $section->addText($node->nodeValue, ['bold' => true], 'abstract'),
        'i', 'em' => $section->addText($node->nodeValue, ['italic' => true], 'abstract'),
        'u' => $section->addText($node->nodeValue, ['underline' => true], 'abstract'),
        default => $section->addText($node->nodeValue, null, 'abstract'),
    };
 }
	<?php
	declare(strict_types=1);

	/**
	* Writes a Word document of abstracts
	*
	* @param string $path The path to the Word document
	* @param int\|null $conference_id
	* @return bool Whether the write was successful
	* @throws \PhpOffice\PhpWord\Exception\Exception
	*/
	public function writeDocument(string $path, int\|null $conference_id = null): bool
	{
	$word = new PhpWord();
	$word->addTitleStyle(1, ['bold' => true, 'size' => 16]);
	$word->addParagraphStyle('abstract', ['indentation' => ['left' => 240]]);

	// Add Conference Title as a header
	$section = $word->addSection();
	$headerText = $section->addTextRun(['alignment' => 'center']);
	$headerText->addText(CONFERENCE_TITLE, ['bold' => true, 'size' => 18]);
	$section->addText("\n\n");

	// Maybe have a logo and the text: "Book of Abstracts"
	// Can be added with: $section->addImage('path_to_logo');

	// Loop through each track and add its abstracts
	$tracks = $this->Tracks->find();
	foreach ($tracks as $track) {
	if ($abstracts->count()) {
	$section = $word->addSection();
	$section->addTitle(h($track->description));

	foreach ($abstracts as $abstract) {
	$section->addTextRun()->addText(h($abstract->registrant->full_name), ['bold' => true]);

	// Clean and process the abstract HTML
	$cleanedAbstract = $this->sanitizeHtml($abstract->abstract);

	// Add the processed HTML content to the section
	$this->addHtmlContentToSection($section, $cleanedAbstract);
	}
	}
	}

	// Save the document
	$writer = IOFactory::createWriter($word);
	$writer->save($path);

	// Return whether the file exists after saving
	return file_exists($path);
	}

	/**
	* Sanitize the HTML content before adding it to the Word document.
	*
	* @param string $html The HTML content to sanitize.
	* @return string The sanitized HTML.
	*/
	private function sanitizeHtml(string $html): string
	{
	// Decode HTML entities
	$html = html_entity_decode($html, ENT_QUOTES \| ENT_HTML5, 'UTF-8');

	// Allow only safe HTML tags (this list can be adjusted as needed)
	$allowedTags = '<p><br><b><i><u><em><strong><ul><ol><li><a>';

	// Remove any tags not in the allowed list
	$html = strip_tags($html, $allowedTags);

	// You can also perform additional sanitization like removing harmful attributes (e.g., on <a> tags)
	$html = preg_replace('/<a\s+([^>]+)>/', '<a>', $html); // Strips out attributes from <a> tags, like href

	return $html;
	}

	/**
	* Adds the sanitized HTML content to the PhpWord section.
	*
	* @param \PhpOffice\PhpWord\Element\Section $section The PhpWord section where the content will be added.
	* @param string $html The HTML content to add.
	*/
	private function addHtmlContentToSection(\PhpOffice\PhpWord\Element\Section $section, string $html)
	{
	// Check if the HTML content is just a single paragraph without complex tags
	if (preg_match('/^<p>.*<\/p>$/', $html)) {
	// If it's a single <p>, treat it as a simple block of text
	$section->addText(strip_tags($html), null, 'abstract');
	} else {
	// Load the HTML content into a DOMDocument for more complex HTML
	$dom = new \DOMDocument();
	libxml_use_internal_errors(true); // Disable warnings for malformed HTML
	$dom->loadHTML('<html><body>' . $html . '</body></html>'); // Wrap HTML in a body tag to make it valid
	libxml_clear_errors();

	// Process each child element of the body
	$body = $dom->getElementsByTagName('body')->item(0);
	foreach ($body->childNodes as $node) {
	if ($node->nodeName === 'p') {
	// Handle paragraphs (<p>)
	$section->addTextBreak(1);
	$this->addTextNodeToSection($section, $node);
	} elseif ($node->nodeName === 'br') {
	// Handle line breaks (<br>)
	$section->addTextBreak(1);
	} else {
	// Handle other text nodes
	$this->addTextNodeToSection($section, $node);
	}
	}
	}
	}

	/**
	* Adds a text node to the PhpWord section, handling basic formatting.
	*
	* @param \PhpOffice\PhpWord\Element\Section $section The PhpWord section.
	* @param \DOMNode $node The DOMNode containing the text.
	*/
	private function addTextNodeToSection(\PhpOffice\PhpWord\Element\Section $section, \DOMNode $node)
	{
	match ($node->nodeName) {
	'b', 'strong' => $section->addText($node->nodeValue, ['bold' => true], 'abstract'),
	'i', 'em' => $section->addText($node->nodeValue, ['italic' => true], 'abstract'),
	'u' => $section->addText($node->nodeValue, ['underline' => true], 'abstract'),
	default => $section->addText($node->nodeValue, null, 'abstract'),
	};
	}