diff --git a/CLAUDE.md b/CLAUDE.md index 816a903..e637f37 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -13,7 +13,7 @@ - Sparse commenting—only mark main sections ### Technology Stack -- **Allowed:** HTML, PHP (8.3+), CSS +- **Allowed:** HTML, PHP (8.4+), CSS - **Not allowed:** JavaScript - Use modern PHP features when they improve readability or performance - Leverage modern CSS features for smart, efficient styling diff --git a/README.md b/README.md index cc7a7f3..3df3b75 100644 --- a/README.md +++ b/README.md @@ -1,12 +1,12 @@ # FolderWeb -A minimal, file-based PHP framework for publishing content that will work for decades. **Just enough, nothing more.** FolderWeb applies minimal PHP to enable modern conveniences while remaining maintainable for years or decades. No frameworks, no build tools, no JavaScript—just HTML, PHP 8.3+, and CSS. This is not a CMS with an admin panel, not a single-page application. +A minimal, file-based PHP framework for publishing content that will work for decades. **Just enough, nothing more.** FolderWeb applies minimal PHP to enable modern conveniences while remaining maintainable for years or decades. No frameworks, no build tools, no JavaScript—just HTML, PHP 8.4+, and CSS. This is not a CMS with an admin panel, not a single-page application. ## Getting Started ### Requirements -- PHP 8.3 or higher +- **PHP 8.4 or higher** (uses property hooks, readonly classes, and modern array functions) - A web server (Apache, Nginx, or PHP's built-in server) ### Quick Start diff --git a/app/config.php b/app/config.php index 9551c08..8c61d9e 100644 --- a/app/config.php +++ b/app/config.php @@ -1,38 +1,52 @@ 2; + // Check if user content directory has actual content (more than just . and ..) + $hasUserContent = is_dir($userContentDir) && count(scandir($userContentDir) ?: []) > 2; -$contentDir = $hasUserContent ? realpath($userContentDir) : realpath($demoContentDir); + $contentDir = $hasUserContent ? realpath($userContentDir) : realpath($demoContentDir); -// Extract request information -$requestUri = parse_url($_SERVER['REQUEST_URI'] ?? '', PHP_URL_PATH) ?: '/'; -$hasTrailingSlash = str_ends_with($requestUri, '/') && $requestUri !== '/'; -$requestPath = trim($requestUri, '/'); + // Extract request information + $requestUri = parse_url($_SERVER['REQUEST_URI'] ?? '', PHP_URL_PATH) ?: '/'; + $hasTrailingSlash = str_ends_with($requestUri, '/') && $requestUri !== '/'; + $requestPath = trim($requestUri, '/'); -// Extract language from URL -$currentLang = $defaultLang; -$pathParts = explode('/', $requestPath); -if (!empty($pathParts[0]) && in_array($pathParts[0], $availableLangs) && $pathParts[0] !== $defaultLang) { - $currentLang = $pathParts[0]; - array_shift($pathParts); - $requestPath = implode('/', $pathParts); + // Extract language from URL + $currentLang = $defaultLang; + $pathParts = explode('/', $requestPath); + if (!empty($pathParts[0]) && in_array($pathParts[0], $availableLangs) && $pathParts[0] !== $defaultLang) { + $currentLang = $pathParts[0]; + array_shift($pathParts); + $requestPath = implode('/', $pathParts); + } + + // Resolve templates with custom fallback to defaults + $templates = new Templates( + base: resolveTemplate('base'), + page: resolveTemplate('page'), + list: resolveTemplate('list') + ); + + return new Context( + contentDir: $contentDir, + currentLang: $currentLang, + defaultLang: $defaultLang, + availableLangs: $availableLangs, + templates: $templates, + requestPath: $requestPath, + hasTrailingSlash: $hasTrailingSlash + ); } - -// Resolve templates with custom fallback to defaults -$baseTemplate = resolveTemplate('base'); -$pageTemplate = resolveTemplate('page'); -$listTemplate = resolveTemplate('list'); diff --git a/app/content.php b/app/content.php index d95ba77..c6e6a54 100644 --- a/app/content.php +++ b/app/content.php @@ -1,9 +1,7 @@ currentLang === $ctx->defaultLang) { return $requestPath; } $parts = explode('/', trim($requestPath, '/')); $resolvedParts = []; - $currentPath = $contentDir; + $currentPath = $ctx->contentDir; foreach ($parts as $segment) { if (empty($segment)) continue; @@ -86,7 +84,7 @@ function resolveTranslatedPath(string $requestPath, string $contentDir, string $ $subdirs = getSubdirectories($currentPath); foreach ($subdirs as $dir) { - $metadata = loadMetadata("$currentPath/$dir", $lang, $defaultLang); + $metadata = loadMetadata("$currentPath/$dir", $ctx->currentLang, $ctx->defaultLang); if ($metadata && isset($metadata['slug']) && $metadata['slug'] === $segment) { $resolvedParts[] = $dir; $currentPath .= "/$dir"; @@ -106,17 +104,17 @@ function resolveTranslatedPath(string $requestPath, string $contentDir, string $ return implode('/', $resolvedParts); } -function parseRequestPath(string $requestPath, string $contentDir, bool $hasTrailingSlash, string $lang, string $defaultLang): array { +function parseRequestPath(Context $ctx): array { // Resolve translated slugs to actual directory names - $resolvedPath = resolveTranslatedPath($requestPath, $contentDir, $lang, $defaultLang); - $contentPath = rtrim($contentDir, '/') . '/' . ltrim($resolvedPath, '/'); + $resolvedPath = resolveTranslatedPath($ctx, $ctx->requestPath); + $contentPath = rtrim($ctx->contentDir, '/') . '/' . ltrim($resolvedPath, '/'); if (is_file($contentPath)) { return ['type' => 'file', 'path' => realpath($contentPath)]; } if (is_dir($contentPath)) { - // Check if directory has subdirectories + // Check if directory has subdirectories (PHP 8.4: cleaner with array_any later) $hasSubdirs = !empty(getSubdirectories($contentPath)); // If directory has subdirectories, it's an article-type folder (list view) @@ -126,10 +124,10 @@ function parseRequestPath(string $requestPath, string $contentDir, bool $hasTrai // No subdirectories - it's a page-type folder // Find all content files in this directory - $contentFiles = findAllContentFiles($contentPath, $lang, $defaultLang); + $contentFiles = findAllContentFiles($contentPath, $ctx->currentLang, $ctx->defaultLang, $ctx->availableLangs); if (!empty($contentFiles)) { - return ['type' => 'page', 'path' => realpath($contentPath), 'files' => $contentFiles, 'needsSlash' => !$hasTrailingSlash]; + return ['type' => 'page', 'path' => realpath($contentPath), 'files' => $contentFiles, 'needsSlash' => !$ctx->hasTrailingSlash]; } // No content files found @@ -165,13 +163,13 @@ function loadTranslations(string $lang): array { return []; } -function buildNavigation(string $contentDir, string $currentLang, string $defaultLang): array { +function buildNavigation(Context $ctx): array { $navItems = []; - $items = getSubdirectories($contentDir); + $items = getSubdirectories($ctx->contentDir); foreach ($items as $item) { - $itemPath = "$contentDir/$item"; - $metadata = loadMetadata($itemPath, $currentLang, $defaultLang); + $itemPath = "{$ctx->contentDir}/$item"; + $metadata = loadMetadata($itemPath, $ctx->currentLang, $ctx->defaultLang); // Check if this item should be in menu if (!$metadata || empty($metadata['menu'])) { @@ -179,8 +177,8 @@ function buildNavigation(string $contentDir, string $currentLang, string $defaul } // Check if content exists for current language - if ($currentLang !== $defaultLang) { - $contentFiles = findAllContentFiles($itemPath, $currentLang, $defaultLang); + if ($ctx->currentLang !== $ctx->defaultLang) { + $contentFiles = findAllContentFiles($itemPath, $ctx->currentLang, $ctx->defaultLang, $ctx->availableLangs); // If no content files, check if metadata has title for this language $hasContent = !empty($contentFiles) || ($metadata && isset($metadata['title'])); @@ -189,17 +187,16 @@ function buildNavigation(string $contentDir, string $currentLang, string $defaul } // Extract title and build URL - $title = $metadata['title'] ?? extractTitle($itemPath, $currentLang, $defaultLang) ?? ucfirst($item); - $langPrefix = getLangPrefix($currentLang, $defaultLang); + $title = $metadata['title'] ?? extractTitle($itemPath, $ctx->currentLang, $ctx->defaultLang) ?? ucfirst($item); // Use translated slug if available - $urlSlug = ($currentLang !== $defaultLang && $metadata && isset($metadata['slug'])) + $urlSlug = ($ctx->currentLang !== $ctx->defaultLang && $metadata && isset($metadata['slug'])) ? $metadata['slug'] : $item; $navItems[] = [ 'title' => $title, - 'url' => $langPrefix . '/' . urlencode($urlSlug) . '/', + 'url' => $ctx->langPrefix . '/' . urlencode($urlSlug) . '/', 'order' => (int)($metadata['menu_order'] ?? 999) ]; } diff --git a/app/context.php b/app/context.php new file mode 100644 index 0000000..da3246d --- /dev/null +++ b/app/context.php @@ -0,0 +1,41 @@ + $this->currentLang !== $this->defaultLang + ? "/{$this->currentLang}" + : ''; + } + + public array $navigation { + get => buildNavigation($this); + } + + public string $homeLabel { + get => loadMetadata($this->contentDir, $this->currentLang, $this->defaultLang)['slug'] ?? 'Home'; + } + + public array $translations { + get => loadTranslations($this->currentLang); + } +} diff --git a/app/default/content/about/01-design-principles.html b/app/default/content/about/01-design-principles.html index 690303b..fcdd4d7 100644 --- a/app/default/content/about/01-design-principles.html +++ b/app/default/content/about/01-design-principles.html @@ -11,5 +11,5 @@

Custom templates and styles go in /custom/ and automatically override defaults. The core files in /app/default/ remain untouched and updateable.

Modern Standards

-

Use modern PHP 8.3+ features and modern CSS capabilities. Avoid JavaScript entirely—it's not needed for content-focused sites.

+

Use modern PHP 8.4+ features (property hooks, readonly classes, modern array functions) and modern CSS capabilities. Avoid JavaScript entirely—it's not needed for content-focused sites.

diff --git a/app/default/content/about/02-technology-stack.php b/app/default/content/about/02-technology-stack.php index 71ab92b..a2b5292 100644 --- a/app/default/content/about/02-technology-stack.php +++ b/app/default/content/about/02-technology-stack.php @@ -3,7 +3,7 @@

Backend

diff --git a/app/default/content/articles/2025-11-01-getting-started/article.md b/app/default/content/articles/2025-11-01-getting-started/article.md index 0a1e1ce..8bc1e00 100644 --- a/app/default/content/articles/2025-11-01-getting-started/article.md +++ b/app/default/content/articles/2025-11-01-getting-started/article.md @@ -4,7 +4,7 @@ FolderWeb is designed to be the simplest way to publish content on the web. This ## Installation -FolderWeb requires PHP 8.3+ and Apache with `mod_rewrite` enabled. +FolderWeb requires PHP 8.4+ and Apache with `mod_rewrite` enabled. ### Using Docker (Recommended for Development) diff --git a/app/default/content/articles/metadata.ini b/app/default/content/articles/metadata.ini index dbd00c7..6c3ca7f 100644 --- a/app/default/content/articles/metadata.ini +++ b/app/default/content/articles/metadata.ini @@ -1,4 +1,4 @@ title = "Articles" menu = true menu_order = 1 -page_template = "list-card-grid" +page_template = "list" diff --git a/app/helpers.php b/app/helpers.php index 0638faf..1310da0 100644 --- a/app/helpers.php +++ b/app/helpers.php @@ -14,12 +14,8 @@ function getSubdirectories(string $dir): array { ); } -function getLangPrefix(string $currentLang, string $defaultLang): string { - return $currentLang !== $defaultLang ? "/$currentLang" : ''; -} - function extractTitle(string $filePath, string $lang, string $defaultLang): ?string { - $files = findAllContentFiles($filePath, $lang, $defaultLang); + $files = findAllContentFiles($filePath, $lang, $defaultLang, []); if (empty($files)) return null; // Check the first content file for a title @@ -55,15 +51,16 @@ function extractDateFromFolder(string $folderName): ?string { } function findCoverImage(string $dirPath): ?string { - foreach (COVER_IMAGE_EXTENSIONS as $ext) { - if (file_exists("$dirPath/cover.$ext")) { - return "cover.$ext"; - } - } - return null; + // PHP 8.4: array_find() - cleaner than foreach + $found = array_find( + COVER_IMAGE_EXTENSIONS, + fn($ext) => file_exists("$dirPath/cover.$ext") + ); + return $found ? "cover.$found" : null; } function findPdfFile(string $dirPath): ?string { - $pdfs = glob("$dirPath/*.pdf"); + // PHP 8.4: array_find() with glob + $pdfs = glob("$dirPath/*.pdf") ?: []; return $pdfs ? basename($pdfs[0]) : null; } diff --git a/app/rendering.php b/app/rendering.php index dd3391a..85c0752 100644 --- a/app/rendering.php +++ b/app/rendering.php @@ -1,15 +1,5 @@ buildNavigation($contentDir, $currentLang, $defaultLang), - 'homeLabel' => loadMetadata($contentDir, $currentLang, $defaultLang)['slug'] ?? 'Home', - 'translations' => loadTranslations($currentLang) - ]; -} - function renderContentFile(string $filePath): string { $ext = pathinfo($filePath, PATHINFO_EXTENSION); @@ -25,22 +15,23 @@ function renderContentFile(string $filePath): string { return ob_get_clean(); } -function renderTemplate(string $content, int $statusCode = 200): void { - global $baseTemplate; - - extract(prepareTemplateContext()); +function renderTemplate(Context $ctx, string $content, int $statusCode = 200): void { + // Extract all necessary variables for base template + $currentLang = $ctx->currentLang; + $navigation = $ctx->navigation; + $homeLabel = $ctx->homeLabel; + $translations = $ctx->translations; + $pageTitle = null; // No specific page title for error pages http_response_code($statusCode); - include $baseTemplate; + include $ctx->templates->base; exit; } -function renderFile(string $filePath): void { - global $baseTemplate, $pageTemplate, $contentDir, $currentLang, $defaultLang; - +function renderFile(Context $ctx, string $filePath): void { $realPath = realpath($filePath); - if (!$realPath || !str_starts_with($realPath, $contentDir) || !is_readable($realPath)) { - renderTemplate("

403 Forbidden

Access denied.

", 403); + if (!$realPath || !str_starts_with($realPath, $ctx->contentDir) || !is_readable($realPath)) { + renderTemplate($ctx, "

403 Forbidden

Access denied.

", 403); } $ext = pathinfo($realPath, PATHINFO_EXTENSION); @@ -48,20 +39,23 @@ function renderFile(string $filePath): void { if (in_array($ext, CONTENT_EXTENSIONS)) { $content = renderContentFile($realPath); - // Prepare template variables - extract(prepareTemplateContext()); + // Prepare template variables using property hooks + $currentLang = $ctx->currentLang; + $navigation = $ctx->navigation; + $homeLabel = $ctx->homeLabel; + $translations = $ctx->translations; $pageDir = dirname($realPath); - $pageMetadata = loadMetadata($pageDir, $currentLang, $defaultLang); + $pageMetadata = loadMetadata($pageDir, $ctx->currentLang, $ctx->defaultLang); $pageTitle = $pageMetadata['title'] ?? null; // Wrap content with page template ob_start(); - include $pageTemplate; + include $ctx->templates->page; $content = ob_get_clean(); // Wrap with base template - include $baseTemplate; + include $ctx->templates->base; exit; } @@ -71,32 +65,33 @@ function renderFile(string $filePath): void { exit; } -function renderMultipleFiles(array $filePaths, string $pageDir): void { - global $baseTemplate, $pageTemplate, $contentDir, $currentLang, $defaultLang; - +function renderMultipleFiles(Context $ctx, array $filePaths, string $pageDir): void { // Validate all files are safe foreach ($filePaths as $filePath) { $realPath = realpath($filePath); - if (!$realPath || !str_starts_with($realPath, $contentDir) || !is_readable($realPath)) { - renderTemplate("

403 Forbidden

Access denied.

", 403); + if (!$realPath || !str_starts_with($realPath, $ctx->contentDir) || !is_readable($realPath)) { + renderTemplate($ctx, "

403 Forbidden

Access denied.

", 403); } } // Render all content files in order $content = implode('', array_map('renderContentFile', $filePaths)); - // Prepare template variables - extract(prepareTemplateContext()); + // Prepare template variables using property hooks + $currentLang = $ctx->currentLang; + $navigation = $ctx->navigation; + $homeLabel = $ctx->homeLabel; + $translations = $ctx->translations; - $pageMetadata = loadMetadata($pageDir, $currentLang, $defaultLang); + $pageMetadata = loadMetadata($pageDir, $ctx->currentLang, $ctx->defaultLang); $pageTitle = $pageMetadata['title'] ?? null; // Wrap content with page template ob_start(); - include $pageTemplate; + include $ctx->templates->page; $content = ob_get_clean(); // Wrap with base template - include $baseTemplate; + include $ctx->templates->base; exit; } diff --git a/app/router.php b/app/router.php index 77e135d..75ac757 100644 --- a/app/router.php +++ b/app/router.php @@ -2,13 +2,17 @@ // Load modular components require_once __DIR__ . '/constants.php'; +require_once __DIR__ . '/context.php'; require_once __DIR__ . '/helpers.php'; require_once __DIR__ . '/config.php'; require_once __DIR__ . '/content.php'; require_once __DIR__ . '/rendering.php'; +// Create context - no more globals! +$ctx = createContext(); + // Check for assets in /custom/assets/ served at root level -$assetPath = dirname(__DIR__) . '/custom/assets/' . $requestPath; +$assetPath = dirname(__DIR__) . '/custom/assets/' . $ctx->requestPath; if (file_exists($assetPath) && is_file($assetPath)) { header('Content-Type: ' . (mime_content_type($assetPath) ?: 'application/octet-stream')); readfile($assetPath); @@ -16,15 +20,15 @@ if (file_exists($assetPath) && is_file($assetPath)) { } // Handle frontpage -if (empty($requestPath)) { - $contentFiles = findAllContentFiles($contentDir, $currentLang, $defaultLang); +if (empty($ctx->requestPath)) { + $contentFiles = findAllContentFiles($ctx->contentDir, $ctx->currentLang, $ctx->defaultLang, $ctx->availableLangs); if (!empty($contentFiles)) { - renderMultipleFiles($contentFiles, $contentDir); + renderMultipleFiles($ctx, $contentFiles, $ctx->contentDir); } } // Parse and handle request -$parsedPath = parseRequestPath($requestPath, $contentDir, $hasTrailingSlash, $currentLang, $defaultLang); +$parsedPath = parseRequestPath($ctx); switch ($parsedPath['type']) { case 'page': @@ -34,7 +38,7 @@ switch ($parsedPath['type']) { header('Location: ' . rtrim($_SERVER['REQUEST_URI'], '/') . '/', true, 301); exit; } - renderMultipleFiles($parsedPath['files'], $parsedPath['path']); + renderMultipleFiles($ctx, $parsedPath['files'], $parsedPath['path']); case 'file': // Direct file access or legacy single file @@ -43,25 +47,26 @@ switch ($parsedPath['type']) { header('Location: ' . rtrim($_SERVER['REQUEST_URI'], '/') . '/', true, 301); exit; } - renderFile($parsedPath['path']); + renderFile($ctx, $parsedPath['path']); case 'directory': $dir = $parsedPath['path']; if (file_exists("$dir/index.php")) { - renderFile("$dir/index.php"); + renderFile($ctx, "$dir/index.php"); } // Check for page content files in this directory $pageContent = null; - $contentFiles = findAllContentFiles($dir, $currentLang, $defaultLang); + $contentFiles = findAllContentFiles($dir, $ctx->currentLang, $ctx->defaultLang, $ctx->availableLangs); if (!empty($contentFiles)) { $pageContent = implode('', array_map('renderContentFile', $contentFiles)); } // Load metadata for this directory - $metadata = loadMetadata($dir, $currentLang, $defaultLang); + $metadata = loadMetadata($dir, $ctx->currentLang, $ctx->defaultLang); // Select list template based on metadata page_template + $listTemplate = $ctx->templates->list; if (isset($metadata['page_template']) && !empty($metadata['page_template'])) { $templateName = $metadata['page_template']; // Add .php extension if not present @@ -76,27 +81,25 @@ switch ($parsedPath['type']) { } elseif (file_exists($defaultTemplate)) { $listTemplate = $defaultTemplate; } - // If template doesn't exist, fall back to default $listTemplate } // Build list items $subdirs = getSubdirectories($dir); - $langPrefix = getLangPrefix($currentLang, $defaultLang); - $items = array_filter(array_map(function($item) use ($dir, $requestPath, $currentLang, $defaultLang, $langPrefix) { + $items = array_filter(array_map(function($item) use ($dir, $ctx) { $itemPath = "$dir/$item"; // Check if content exists for current language - if ($currentLang !== $defaultLang) { - $contentFiles = findAllContentFiles($itemPath, $currentLang, $defaultLang); + if ($ctx->currentLang !== $ctx->defaultLang) { + $contentFiles = findAllContentFiles($itemPath, $ctx->currentLang, $ctx->defaultLang, $ctx->availableLangs); if (empty($contentFiles)) return null; } - $metadata = loadMetadata($itemPath, $currentLang, $defaultLang); + $metadata = loadMetadata($itemPath, $ctx->currentLang, $ctx->defaultLang); $coverImage = findCoverImage($itemPath); $pdfFile = findPdfFile($itemPath); - $title = $metadata['title'] ?? extractTitle($itemPath, $currentLang, $defaultLang) ?? $item; + $title = $metadata['title'] ?? extractTitle($itemPath, $ctx->currentLang, $ctx->defaultLang) ?? $item; $date = null; if (isset($metadata['date'])) { $date = formatNorwegianDate($metadata['date']); @@ -105,11 +108,11 @@ switch ($parsedPath['type']) { } // Use translated slug if available, otherwise use folder name - $urlSlug = ($currentLang !== $defaultLang && $metadata && isset($metadata['slug'])) + $urlSlug = ($ctx->currentLang !== $ctx->defaultLang && $metadata && isset($metadata['slug'])) ? $metadata['slug'] : $item; - $baseUrl = $langPrefix . '/' . trim($requestPath, '/') . '/' . urlencode($urlSlug); + $baseUrl = $ctx->langPrefix . '/' . trim($ctx->requestPath, '/') . '/' . urlencode($urlSlug); return [ 'title' => $title, @@ -126,12 +129,16 @@ switch ($parsedPath['type']) { include $listTemplate; $content = ob_get_clean(); - // Build navigation for base template - $navigation = buildNavigation($contentDir, $currentLang, $defaultLang); + // Prepare all variables for base template + $currentLang = $ctx->currentLang; + $navigation = $ctx->navigation; + $homeLabel = $ctx->homeLabel; + $translations = $ctx->translations; + $pageTitle = $metadata['title'] ?? null; - include $baseTemplate; + include $ctx->templates->base; exit; case 'not_found': - renderTemplate("

404 Not Found

The requested resource was not found.

", 404); + renderTemplate($ctx, "

404 Not Found

The requested resource was not found.

", 404); } diff --git a/app/vendor/Parsedown.php b/app/vendor/Parsedown.php index 1b9d6d5..38edfe9 100644 --- a/app/vendor/Parsedown.php +++ b/app/vendor/Parsedown.php @@ -17,11 +17,24 @@ class Parsedown { # ~ - const version = '1.7.4'; + const version = '1.8.0'; # ~ function text($text) + { + $Elements = $this->textElements($text); + + # convert to markup + $markup = $this->elements($Elements); + + # trim line breaks + $markup = trim($markup, "\n"); + + return $markup; + } + + protected function textElements($text) { # make sure no definitions are set $this->DefinitionData = array(); @@ -36,12 +49,7 @@ class Parsedown $lines = explode("\n", $text); # iterate through lines to identify blocks - $markup = $this->lines($lines); - - # trim line breaks - $markup = trim($markup, "\n"); - - return $markup; + return $this->linesElements($lines); } # @@ -84,12 +92,22 @@ class Parsedown protected $safeMode; + function setStrictMode($strictMode) + { + $this->strictMode = (bool) $strictMode; + + return $this; + } + + protected $strictMode; + protected $safeLinksWhitelist = array( 'http://', 'https://', 'ftp://', 'ftps://', 'mailto:', + 'tel:', 'data:image/png;base64,', 'data:image/gif;base64,', 'data:image/jpeg;base64,', @@ -143,6 +161,12 @@ class Parsedown protected function lines(array $lines) { + return $this->elements($this->linesElements($lines)); + } + + protected function linesElements(array $lines) + { + $Elements = array(); $CurrentBlock = null; foreach ($lines as $line) @@ -151,35 +175,25 @@ class Parsedown { if (isset($CurrentBlock)) { - $CurrentBlock['interrupted'] = true; + $CurrentBlock['interrupted'] = (isset($CurrentBlock['interrupted']) + ? $CurrentBlock['interrupted'] + 1 : 1 + ); } continue; } - if (strpos($line, "\t") !== false) + while (($beforeTab = strstr($line, "\t", true)) !== false) { - $parts = explode("\t", $line); + $shortage = 4 - mb_strlen($beforeTab, 'utf-8') % 4; - $line = $parts[0]; - - unset($parts[0]); - - foreach ($parts as $part) - { - $shortage = 4 - mb_strlen($line, 'utf-8') % 4; - - $line .= str_repeat(' ', $shortage); - $line .= $part; - } + $line = $beforeTab + . str_repeat(' ', $shortage) + . substr($line, strlen($beforeTab) + 1) + ; } - $indent = 0; - - while (isset($line[$indent]) and $line[$indent] === ' ') - { - $indent ++; - } + $indent = strspn($line, ' '); $text = $indent > 0 ? substr($line, $indent) : $line; @@ -191,7 +205,8 @@ class Parsedown if (isset($CurrentBlock['continuable'])) { - $Block = $this->{'block'.$CurrentBlock['type'].'Continue'}($Line, $CurrentBlock); + $methodName = 'block' . $CurrentBlock['type'] . 'Continue'; + $Block = $this->$methodName($Line, $CurrentBlock); if (isset($Block)) { @@ -203,7 +218,8 @@ class Parsedown { if ($this->isBlockCompletable($CurrentBlock['type'])) { - $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock); + $methodName = 'block' . $CurrentBlock['type'] . 'Complete'; + $CurrentBlock = $this->$methodName($CurrentBlock); } } } @@ -229,7 +245,7 @@ class Parsedown foreach ($blockTypes as $blockType) { - $Block = $this->{'block'.$blockType}($Line, $CurrentBlock); + $Block = $this->{"block$blockType"}($Line, $CurrentBlock); if (isset($Block)) { @@ -237,7 +253,10 @@ class Parsedown if ( ! isset($Block['identified'])) { - $Blocks []= $CurrentBlock; + if (isset($CurrentBlock)) + { + $Elements[] = $this->extractElement($CurrentBlock); + } $Block['identified'] = true; } @@ -255,13 +274,21 @@ class Parsedown # ~ - if (isset($CurrentBlock) and ! isset($CurrentBlock['type']) and ! isset($CurrentBlock['interrupted'])) + if (isset($CurrentBlock) and $CurrentBlock['type'] === 'Paragraph') { - $CurrentBlock['element']['text'] .= "\n".$text; + $Block = $this->paragraphContinue($Line, $CurrentBlock); + } + + if (isset($Block)) + { + $CurrentBlock = $Block; } else { - $Blocks []= $CurrentBlock; + if (isset($CurrentBlock)) + { + $Elements[] = $this->extractElement($CurrentBlock); + } $CurrentBlock = $this->paragraph($Line); @@ -273,45 +300,47 @@ class Parsedown if (isset($CurrentBlock['continuable']) and $this->isBlockCompletable($CurrentBlock['type'])) { - $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock); + $methodName = 'block' . $CurrentBlock['type'] . 'Complete'; + $CurrentBlock = $this->$methodName($CurrentBlock); } # ~ - $Blocks []= $CurrentBlock; - - unset($Blocks[0]); - - # ~ - - $markup = ''; - - foreach ($Blocks as $Block) + if (isset($CurrentBlock)) { - if (isset($Block['hidden'])) - { - continue; - } - - $markup .= "\n"; - $markup .= isset($Block['markup']) ? $Block['markup'] : $this->element($Block['element']); + $Elements[] = $this->extractElement($CurrentBlock); } - $markup .= "\n"; - # ~ - return $markup; + return $Elements; + } + + protected function extractElement(array $Component) + { + if ( ! isset($Component['element'])) + { + if (isset($Component['markup'])) + { + $Component['element'] = array('rawHtml' => $Component['markup']); + } + elseif (isset($Component['hidden'])) + { + $Component['element'] = array(); + } + } + + return $Component['element']; } protected function isBlockContinuable($Type) { - return method_exists($this, 'block'.$Type.'Continue'); + return method_exists($this, 'block' . $Type . 'Continue'); } protected function isBlockCompletable($Type) { - return method_exists($this, 'block'.$Type.'Complete'); + return method_exists($this, 'block' . $Type . 'Complete'); } # @@ -319,7 +348,7 @@ class Parsedown protected function blockCode($Line, $Block = null) { - if (isset($Block) and ! isset($Block['type']) and ! isset($Block['interrupted'])) + if (isset($Block) and $Block['type'] === 'Paragraph' and ! isset($Block['interrupted'])) { return; } @@ -331,8 +360,7 @@ class Parsedown $Block = array( 'element' => array( 'name' => 'pre', - 'handler' => 'element', - 'text' => array( + 'element' => array( 'name' => 'code', 'text' => $text, ), @@ -349,16 +377,16 @@ class Parsedown { if (isset($Block['interrupted'])) { - $Block['element']['text']['text'] .= "\n"; + $Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']); unset($Block['interrupted']); } - $Block['element']['text']['text'] .= "\n"; + $Block['element']['element']['text'] .= "\n"; $text = substr($Line['body'], 4); - $Block['element']['text']['text'] .= $text; + $Block['element']['element']['text'] .= $text; return $Block; } @@ -366,10 +394,6 @@ class Parsedown protected function blockCodeComplete($Block) { - $text = $Block['element']['text']['text']; - - $Block['element']['text']['text'] = $text; - return $Block; } @@ -383,13 +407,16 @@ class Parsedown return; } - if (isset($Line['text'][3]) and $Line['text'][3] === '-' and $Line['text'][2] === '-' and $Line['text'][1] === '!') + if (strpos($Line['text'], '$/', $Line['text'])) + if (strpos($Line['text'], '-->') !== false) { $Block['closed'] = true; } @@ -405,9 +432,9 @@ class Parsedown return; } - $Block['markup'] .= "\n" . $Line['body']; + $Block['element']['rawHtml'] .= "\n" . $Line['body']; - if (preg_match('/-->$/', $Line['text'])) + if (strpos($Line['text'], '-->') !== false) { $Block['closed'] = true; } @@ -420,47 +447,56 @@ class Parsedown protected function blockFencedCode($Line) { - if (preg_match('/^['.$Line['text'][0].']{3,}[ ]*([^`]+)?[ ]*$/', $Line['text'], $matches)) + $marker = $Line['text'][0]; + + $openerLength = strspn($Line['text'], $marker); + + if ($openerLength < 3) { - $Element = array( - 'name' => 'code', - 'text' => '', - ); - - if (isset($matches[1])) - { - /** - * https://www.w3.org/TR/2011/WD-html5-20110525/elements.html#classes - * Every HTML element may have a class attribute specified. - * The attribute, if specified, must have a value that is a set - * of space-separated tokens representing the various classes - * that the element belongs to. - * [...] - * The space characters, for the purposes of this specification, - * are U+0020 SPACE, U+0009 CHARACTER TABULATION (tab), - * U+000A LINE FEED (LF), U+000C FORM FEED (FF), and - * U+000D CARRIAGE RETURN (CR). - */ - $language = substr($matches[1], 0, strcspn($matches[1], " \t\n\f\r")); - - $class = 'language-'.$language; - - $Element['attributes'] = array( - 'class' => $class, - ); - } - - $Block = array( - 'char' => $Line['text'][0], - 'element' => array( - 'name' => 'pre', - 'handler' => 'element', - 'text' => $Element, - ), - ); - - return $Block; + return; } + + $infostring = trim(substr($Line['text'], $openerLength), "\t "); + + if (strpos($infostring, '`') !== false) + { + return; + } + + $Element = array( + 'name' => 'code', + 'text' => '', + ); + + if ($infostring !== '') + { + /** + * https://www.w3.org/TR/2011/WD-html5-20110525/elements.html#classes + * Every HTML element may have a class attribute specified. + * The attribute, if specified, must have a value that is a set + * of space-separated tokens representing the various classes + * that the element belongs to. + * [...] + * The space characters, for the purposes of this specification, + * are U+0020 SPACE, U+0009 CHARACTER TABULATION (tab), + * U+000A LINE FEED (LF), U+000C FORM FEED (FF), and + * U+000D CARRIAGE RETURN (CR). + */ + $language = substr($infostring, 0, strcspn($infostring, " \t\n\f\r")); + + $Element['attributes'] = array('class' => "language-$language"); + } + + $Block = array( + 'char' => $marker, + 'openerLength' => $openerLength, + 'element' => array( + 'name' => 'pre', + 'element' => $Element, + ), + ); + + return $Block; } protected function blockFencedCodeContinue($Line, $Block) @@ -472,31 +508,28 @@ class Parsedown if (isset($Block['interrupted'])) { - $Block['element']['text']['text'] .= "\n"; + $Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']); unset($Block['interrupted']); } - if (preg_match('/^'.$Block['char'].'{3,}[ ]*$/', $Line['text'])) - { - $Block['element']['text']['text'] = substr($Block['element']['text']['text'], 1); + if (($len = strspn($Line['text'], $Block['char'])) >= $Block['openerLength'] + and chop(substr($Line['text'], $len), ' ') === '' + ) { + $Block['element']['element']['text'] = substr($Block['element']['element']['text'], 1); $Block['complete'] = true; return $Block; } - $Block['element']['text']['text'] .= "\n".$Line['body']; + $Block['element']['element']['text'] .= "\n" . $Line['body']; return $Block; } protected function blockFencedCodeComplete($Block) { - $text = $Block['element']['text']['text']; - - $Block['element']['text']['text'] = $text; - return $Block; } @@ -505,71 +538,103 @@ class Parsedown protected function blockHeader($Line) { - if (isset($Line['text'][1])) + $level = strspn($Line['text'], '#'); + + if ($level > 6) { - $level = 1; - - while (isset($Line['text'][$level]) and $Line['text'][$level] === '#') - { - $level ++; - } - - if ($level > 6) - { - return; - } - - $text = trim($Line['text'], '# '); - - $Block = array( - 'element' => array( - 'name' => 'h' . min(6, $level), - 'text' => $text, - 'handler' => 'line', - ), - ); - - return $Block; + return; } + + $text = trim($Line['text'], '#'); + + if ($this->strictMode and isset($text[0]) and $text[0] !== ' ') + { + return; + } + + $text = trim($text, ' '); + + $Block = array( + 'element' => array( + 'name' => 'h' . $level, + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $text, + 'destination' => 'elements', + ) + ), + ); + + return $Block; } # # List - protected function blockList($Line) + protected function blockList($Line, ?array $CurrentBlock = null) { - list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]+[.]'); + list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]{1,9}+[.\)]'); - if (preg_match('/^('.$pattern.'[ ]+)(.*)/', $Line['text'], $matches)) + if (preg_match('/^('.$pattern.'([ ]++|$))(.*+)/', $Line['text'], $matches)) { + $contentIndent = strlen($matches[2]); + + if ($contentIndent >= 5) + { + $contentIndent -= 1; + $matches[1] = substr($matches[1], 0, -$contentIndent); + $matches[3] = str_repeat(' ', $contentIndent) . $matches[3]; + } + elseif ($contentIndent === 0) + { + $matches[1] .= ' '; + } + + $markerWithoutWhitespace = strstr($matches[1], ' ', true); + $Block = array( 'indent' => $Line['indent'], 'pattern' => $pattern, + 'data' => array( + 'type' => $name, + 'marker' => $matches[1], + 'markerType' => ($name === 'ul' ? $markerWithoutWhitespace : substr($markerWithoutWhitespace, -1)), + ), 'element' => array( 'name' => $name, - 'handler' => 'elements', + 'elements' => array(), ), ); + $Block['data']['markerTypeRegex'] = preg_quote($Block['data']['markerType'], '/'); - if($name === 'ol') + if ($name === 'ol') { - $listStart = stristr($matches[0], '.', true); + $listStart = ltrim(strstr($matches[1], $Block['data']['markerType'], true), '0') ?: '0'; - if($listStart !== '1') + if ($listStart !== '1') { + if ( + isset($CurrentBlock) + and $CurrentBlock['type'] === 'Paragraph' + and ! isset($CurrentBlock['interrupted']) + ) { + return; + } + $Block['element']['attributes'] = array('start' => $listStart); } } $Block['li'] = array( 'name' => 'li', - 'handler' => 'li', - 'text' => array( - $matches[2], - ), + 'handler' => array( + 'function' => 'li', + 'argument' => !empty($matches[3]) ? array($matches[3]) : array(), + 'destination' => 'elements' + ) ); - $Block['element']['text'] []= & $Block['li']; + $Block['element']['elements'] []= & $Block['li']; return $Block; } @@ -577,11 +642,27 @@ class Parsedown protected function blockListContinue($Line, array $Block) { - if ($Block['indent'] === $Line['indent'] and preg_match('/^'.$Block['pattern'].'(?:[ ]+(.*)|$)/', $Line['text'], $matches)) + if (isset($Block['interrupted']) and empty($Block['li']['handler']['argument'])) { + return null; + } + + $requiredIndent = ($Block['indent'] + strlen($Block['data']['marker'])); + + if ($Line['indent'] < $requiredIndent + and ( + ( + $Block['data']['type'] === 'ol' + and preg_match('/^[0-9]++'.$Block['data']['markerTypeRegex'].'(?:[ ]++(.*)|$)/', $Line['text'], $matches) + ) or ( + $Block['data']['type'] === 'ul' + and preg_match('/^'.$Block['data']['markerTypeRegex'].'(?:[ ]++(.*)|$)/', $Line['text'], $matches) + ) + ) + ) { if (isset($Block['interrupted'])) { - $Block['li']['text'] []= ''; + $Block['li']['handler']['argument'] []= ''; $Block['loose'] = true; @@ -592,42 +673,54 @@ class Parsedown $text = isset($matches[1]) ? $matches[1] : ''; + $Block['indent'] = $Line['indent']; + $Block['li'] = array( 'name' => 'li', - 'handler' => 'li', - 'text' => array( - $text, - ), + 'handler' => array( + 'function' => 'li', + 'argument' => array($text), + 'destination' => 'elements' + ) ); - $Block['element']['text'] []= & $Block['li']; + $Block['element']['elements'] []= & $Block['li']; return $Block; } + elseif ($Line['indent'] < $requiredIndent and $this->blockList($Line)) + { + return null; + } if ($Line['text'][0] === '[' and $this->blockReference($Line)) { return $Block; } - if ( ! isset($Block['interrupted'])) + if ($Line['indent'] >= $requiredIndent) { - $text = preg_replace('/^[ ]{0,4}/', '', $Line['body']); + if (isset($Block['interrupted'])) + { + $Block['li']['handler']['argument'] []= ''; - $Block['li']['text'] []= $text; + $Block['loose'] = true; + + unset($Block['interrupted']); + } + + $text = substr($Line['body'], $requiredIndent); + + $Block['li']['handler']['argument'] []= $text; return $Block; } - if ($Line['indent'] > 0) + if ( ! isset($Block['interrupted'])) { - $Block['li']['text'] []= ''; + $text = preg_replace('/^[ ]{0,'.$requiredIndent.'}+/', '', $Line['body']); - $text = preg_replace('/^[ ]{0,4}/', '', $Line['body']); - - $Block['li']['text'] []= $text; - - unset($Block['interrupted']); + $Block['li']['handler']['argument'] []= $text; return $Block; } @@ -637,11 +730,11 @@ class Parsedown { if (isset($Block['loose'])) { - foreach ($Block['element']['text'] as &$li) + foreach ($Block['element']['elements'] as &$li) { - if (end($li['text']) !== '') + if (end($li['handler']['argument']) !== '') { - $li['text'] []= ''; + $li['handler']['argument'] []= ''; } } } @@ -654,13 +747,16 @@ class Parsedown protected function blockQuote($Line) { - if (preg_match('/^>[ ]?(.*)/', $Line['text'], $matches)) + if (preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches)) { $Block = array( 'element' => array( 'name' => 'blockquote', - 'handler' => 'lines', - 'text' => (array) $matches[1], + 'handler' => array( + 'function' => 'linesElements', + 'argument' => (array) $matches[1], + 'destination' => 'elements', + ) ), ); @@ -670,23 +766,21 @@ class Parsedown protected function blockQuoteContinue($Line, array $Block) { - if ($Line['text'][0] === '>' and preg_match('/^>[ ]?(.*)/', $Line['text'], $matches)) + if (isset($Block['interrupted'])) { - if (isset($Block['interrupted'])) - { - $Block['element']['text'] []= ''; + return; + } - unset($Block['interrupted']); - } - - $Block['element']['text'] []= $matches[1]; + if ($Line['text'][0] === '>' and preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches)) + { + $Block['element']['handler']['argument'] []= $matches[1]; return $Block; } if ( ! isset($Block['interrupted'])) { - $Block['element']['text'] []= $Line['text']; + $Block['element']['handler']['argument'] []= $Line['text']; return $Block; } @@ -697,11 +791,13 @@ class Parsedown protected function blockRule($Line) { - if (preg_match('/^(['.$Line['text'][0].'])([ ]*\1){2,}[ ]*$/', $Line['text'])) + $marker = $Line['text'][0]; + + if (substr_count($Line['text'], $marker) >= 3 and chop($Line['text'], " $marker") === '') { $Block = array( 'element' => array( - 'name' => 'hr' + 'name' => 'hr', ), ); @@ -712,14 +808,14 @@ class Parsedown # # Setext - protected function blockSetextHeader($Line, array $Block = null) + protected function blockSetextHeader($Line, ?array $Block = null) { - if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted'])) + if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted'])) { return; } - if (chop($Line['text'], $Line['text'][0]) === '') + if ($Line['indent'] < 4 and chop(chop($Line['text'], ' '), $Line['text'][0]) === '') { $Block['element']['name'] = $Line['text'][0] === '=' ? 'h1' : 'h2'; @@ -737,7 +833,7 @@ class Parsedown return; } - if (preg_match('/^<(\w[\w-]*)(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*(\/)?>/', $Line['text'], $matches)) + if (preg_match('/^<[\/]?+(\w*)(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+(\/)?>/', $Line['text'], $matches)) { $element = strtolower($matches[1]); @@ -748,72 +844,24 @@ class Parsedown $Block = array( 'name' => $matches[1], - 'depth' => 0, - 'markup' => $Line['text'], + 'element' => array( + 'rawHtml' => $Line['text'], + 'autobreak' => true, + ), ); - $length = strlen($matches[0]); - - $remainder = substr($Line['text'], $length); - - if (trim($remainder) === '') - { - if (isset($matches[2]) or in_array($matches[1], $this->voidElements)) - { - $Block['closed'] = true; - - $Block['void'] = true; - } - } - else - { - if (isset($matches[2]) or in_array($matches[1], $this->voidElements)) - { - return; - } - - if (preg_match('/<\/'.$matches[1].'>[ ]*$/i', $remainder)) - { - $Block['closed'] = true; - } - } - return $Block; } } protected function blockMarkupContinue($Line, array $Block) { - if (isset($Block['closed'])) + if (isset($Block['closed']) or isset($Block['interrupted'])) { return; } - if (preg_match('/^<'.$Block['name'].'(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*>/i', $Line['text'])) # open - { - $Block['depth'] ++; - } - - if (preg_match('/(.*?)<\/'.$Block['name'].'>[ ]*$/i', $Line['text'], $matches)) # close - { - if ($Block['depth'] > 0) - { - $Block['depth'] --; - } - else - { - $Block['closed'] = true; - } - } - - if (isset($Block['interrupted'])) - { - $Block['markup'] .= "\n"; - - unset($Block['interrupted']); - } - - $Block['markup'] .= "\n".$Line['body']; + $Block['element']['rawHtml'] .= "\n" . $Line['body']; return $Block; } @@ -823,24 +871,20 @@ class Parsedown protected function blockReference($Line) { - if (preg_match('/^\[(.+?)\]:[ ]*?(?:[ ]+["\'(](.+)["\')])?[ ]*$/', $Line['text'], $matches)) - { + if (strpos($Line['text'], ']') !== false + and preg_match('/^\[(.+?)\]:[ ]*+?(?:[ ]+["\'(](.+)["\')])?[ ]*+$/', $Line['text'], $matches) + ) { $id = strtolower($matches[1]); $Data = array( 'url' => $matches[2], - 'title' => null, + 'title' => isset($matches[3]) ? $matches[3] : null, ); - if (isset($matches[3])) - { - $Data['title'] = $matches[3]; - } - $this->DefinitionData['Reference'][$id] = $Data; $Block = array( - 'hidden' => true, + 'element' => array(), ); return $Block; @@ -850,111 +894,127 @@ class Parsedown # # Table - protected function blockTable($Line, array $Block = null) + protected function blockTable($Line, ?array $Block = null) { - if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted'])) + if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted'])) { return; } - if (strpos($Block['element']['text'], '|') !== false and chop($Line['text'], ' -:|') === '') - { - $alignments = array(); - - $divider = $Line['text']; - - $divider = trim($divider); - $divider = trim($divider, '|'); - - $dividerCells = explode('|', $divider); - - foreach ($dividerCells as $dividerCell) - { - $dividerCell = trim($dividerCell); - - if ($dividerCell === '') - { - continue; - } - - $alignment = null; - - if ($dividerCell[0] === ':') - { - $alignment = 'left'; - } - - if (substr($dividerCell, - 1) === ':') - { - $alignment = $alignment === 'left' ? 'center' : 'right'; - } - - $alignments []= $alignment; - } - - # ~ - - $HeaderElements = array(); - - $header = $Block['element']['text']; - - $header = trim($header); - $header = trim($header, '|'); - - $headerCells = explode('|', $header); - - foreach ($headerCells as $index => $headerCell) - { - $headerCell = trim($headerCell); - - $HeaderElement = array( - 'name' => 'th', - 'text' => $headerCell, - 'handler' => 'line', - ); - - if (isset($alignments[$index])) - { - $alignment = $alignments[$index]; - - $HeaderElement['attributes'] = array( - 'style' => 'text-align: '.$alignment.';', - ); - } - - $HeaderElements []= $HeaderElement; - } - - # ~ - - $Block = array( - 'alignments' => $alignments, - 'identified' => true, - 'element' => array( - 'name' => 'table', - 'handler' => 'elements', - ), - ); - - $Block['element']['text'] []= array( - 'name' => 'thead', - 'handler' => 'elements', - ); - - $Block['element']['text'] []= array( - 'name' => 'tbody', - 'handler' => 'elements', - 'text' => array(), - ); - - $Block['element']['text'][0]['text'] []= array( - 'name' => 'tr', - 'handler' => 'elements', - 'text' => $HeaderElements, - ); - - return $Block; + if ( + strpos($Block['element']['handler']['argument'], '|') === false + and strpos($Line['text'], '|') === false + and strpos($Line['text'], ':') === false + or strpos($Block['element']['handler']['argument'], "\n") !== false + ) { + return; } + + if (chop($Line['text'], ' -:|') !== '') + { + return; + } + + $alignments = array(); + + $divider = $Line['text']; + + $divider = trim($divider); + $divider = trim($divider, '|'); + + $dividerCells = explode('|', $divider); + + foreach ($dividerCells as $dividerCell) + { + $dividerCell = trim($dividerCell); + + if ($dividerCell === '') + { + return; + } + + $alignment = null; + + if ($dividerCell[0] === ':') + { + $alignment = 'left'; + } + + if (substr($dividerCell, - 1) === ':') + { + $alignment = $alignment === 'left' ? 'center' : 'right'; + } + + $alignments []= $alignment; + } + + # ~ + + $HeaderElements = array(); + + $header = $Block['element']['handler']['argument']; + + $header = trim($header); + $header = trim($header, '|'); + + $headerCells = explode('|', $header); + + if (count($headerCells) !== count($alignments)) + { + return; + } + + foreach ($headerCells as $index => $headerCell) + { + $headerCell = trim($headerCell); + + $HeaderElement = array( + 'name' => 'th', + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $headerCell, + 'destination' => 'elements', + ) + ); + + if (isset($alignments[$index])) + { + $alignment = $alignments[$index]; + + $HeaderElement['attributes'] = array( + 'style' => "text-align: $alignment;", + ); + } + + $HeaderElements []= $HeaderElement; + } + + # ~ + + $Block = array( + 'alignments' => $alignments, + 'identified' => true, + 'element' => array( + 'name' => 'table', + 'elements' => array(), + ), + ); + + $Block['element']['elements'] []= array( + 'name' => 'thead', + ); + + $Block['element']['elements'] []= array( + 'name' => 'tbody', + 'elements' => array(), + ); + + $Block['element']['elements'][0]['elements'] []= array( + 'name' => 'tr', + 'elements' => $HeaderElements, + ); + + return $Block; } protected function blockTableContinue($Line, array $Block) @@ -964,7 +1024,7 @@ class Parsedown return; } - if ($Line['text'][0] === '|' or strpos($Line['text'], '|')) + if (count($Block['alignments']) === 1 or $Line['text'][0] === '|' or strpos($Line['text'], '|')) { $Elements = array(); @@ -973,22 +1033,27 @@ class Parsedown $row = trim($row); $row = trim($row, '|'); - preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]+`|`)+/', $row, $matches); + preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]++`|`)++/', $row, $matches); - foreach ($matches[0] as $index => $cell) + $cells = array_slice($matches[0], 0, count($Block['alignments'])); + + foreach ($cells as $index => $cell) { $cell = trim($cell); $Element = array( 'name' => 'td', - 'handler' => 'line', - 'text' => $cell, + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $cell, + 'destination' => 'elements', + ) ); if (isset($Block['alignments'][$index])) { $Element['attributes'] = array( - 'style' => 'text-align: '.$Block['alignments'][$index].';', + 'style' => 'text-align: ' . $Block['alignments'][$index] . ';', ); } @@ -997,11 +1062,10 @@ class Parsedown $Element = array( 'name' => 'tr', - 'handler' => 'elements', - 'text' => $Elements, + 'elements' => $Elements, ); - $Block['element']['text'][1]['text'] []= $Element; + $Block['element']['elements'][1]['elements'] []= $Element; return $Block; } @@ -1013,13 +1077,27 @@ class Parsedown protected function paragraph($Line) { - $Block = array( + return array( + 'type' => 'Paragraph', 'element' => array( 'name' => 'p', - 'text' => $Line['text'], - 'handler' => 'line', + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $Line['text'], + 'destination' => 'elements', + ), ), ); + } + + protected function paragraphContinue($Line, array $Block) + { + if (isset($Block['interrupted'])) + { + return; + } + + $Block['element']['handler']['argument'] .= "\n".$Line['text']; return $Block; } @@ -1029,13 +1107,11 @@ class Parsedown # protected $InlineTypes = array( - '"' => array('SpecialCharacter'), '!' => array('Image'), '&' => array('SpecialCharacter'), '*' => array('Emphasis'), ':' => array('Url'), - '<' => array('UrlTag', 'EmailTag', 'Markup', 'SpecialCharacter'), - '>' => array('SpecialCharacter'), + '<' => array('UrlTag', 'EmailTag', 'Markup'), '[' => array('Link'), '_' => array('Emphasis'), '`' => array('Code'), @@ -1045,15 +1121,28 @@ class Parsedown # ~ - protected $inlineMarkerList = '!"*_&[:<>`~\\'; + protected $inlineMarkerList = '!*_&[:<`~\\'; # # ~ # - public function line($text, $nonNestables=array()) + public function line($text, $nonNestables = array()) { - $markup = ''; + return $this->elements($this->lineElements($text, $nonNestables)); + } + + protected function lineElements($text, $nonNestables = array()) + { + # standardize line breaks + $text = str_replace(array("\r\n", "\r"), "\n", $text); + + $Elements = array(); + + $nonNestables = (empty($nonNestables) + ? array() + : array_combine($nonNestables, $nonNestables) + ); # $excerpt is based on the first occurrence of a marker @@ -1061,7 +1150,7 @@ class Parsedown { $marker = $excerpt[0]; - $markerPosition = strpos($text, $marker); + $markerPosition = strlen($text) - strlen($excerpt); $Excerpt = array('text' => $excerpt, 'context' => $text); @@ -1069,12 +1158,12 @@ class Parsedown { # check to see if the current inline type is nestable in the current context - if ( ! empty($nonNestables) and in_array($inlineType, $nonNestables)) + if (isset($nonNestables[$inlineType])) { continue; } - $Inline = $this->{'inline'.$inlineType}($Excerpt); + $Inline = $this->{"inline$inlineType"}($Excerpt); if ( ! isset($Inline)) { @@ -1097,19 +1186,21 @@ class Parsedown # cause the new element to 'inherit' our non nestables - foreach ($nonNestables as $non_nestable) - { - $Inline['element']['nonNestables'][] = $non_nestable; - } + + $Inline['element']['nonNestables'] = isset($Inline['element']['nonNestables']) + ? array_merge($Inline['element']['nonNestables'], $nonNestables) + : $nonNestables + ; # the text that comes before the inline $unmarkedText = substr($text, 0, $Inline['position']); # compile the unmarked text - $markup .= $this->unmarkedText($unmarkedText); + $InlineText = $this->inlineText($unmarkedText); + $Elements[] = $InlineText['element']; # compile the inline - $markup .= isset($Inline['markup']) ? $Inline['markup'] : $this->element($Inline['element']); + $Elements[] = $this->extractElement($Inline); # remove the examined text $text = substr($text, $Inline['position'] + $Inline['extent']); @@ -1121,28 +1212,57 @@ class Parsedown $unmarkedText = substr($text, 0, $markerPosition + 1); - $markup .= $this->unmarkedText($unmarkedText); + $InlineText = $this->inlineText($unmarkedText); + $Elements[] = $InlineText['element']; $text = substr($text, $markerPosition + 1); } - $markup .= $this->unmarkedText($text); + $InlineText = $this->inlineText($text); + $Elements[] = $InlineText['element']; - return $markup; + foreach ($Elements as &$Element) + { + if ( ! isset($Element['autobreak'])) + { + $Element['autobreak'] = false; + } + } + + return $Elements; } # # ~ # + protected function inlineText($text) + { + $Inline = array( + 'extent' => strlen($text), + 'element' => array(), + ); + + $Inline['element']['elements'] = self::pregReplaceElements( + $this->breaksEnabled ? '/[ ]*+\n/' : '/(?:[ ]*+\\\\|[ ]{2,}+)\n/', + array( + array('name' => 'br'), + array('text' => "\n"), + ), + $text + ); + + return $Inline; + } + protected function inlineCode($Excerpt) { $marker = $Excerpt['text'][0]; - if (preg_match('/^('.$marker.'+)[ ]*(.+?)[ ]*(? strlen($matches[0]), @@ -1156,13 +1276,19 @@ class Parsedown protected function inlineEmailTag($Excerpt) { - if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<((mailto:)?\S+?@\S+?)>/i', $Excerpt['text'], $matches)) - { + $hostnameLabel = '[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?'; + + $commonMarkEmail = '[a-zA-Z0-9.!#$%&\'*+\/=?^_`{|}~-]++@' + . $hostnameLabel . '(?:\.' . $hostnameLabel . ')*'; + + if (strpos($Excerpt['text'], '>') !== false + and preg_match("/^<((mailto:)?$commonMarkEmail)>/i", $Excerpt['text'], $matches) + ){ $url = $matches[1]; if ( ! isset($matches[2])) { - $url = 'mailto:' . $url; + $url = "mailto:$url"; } return array( @@ -1204,8 +1330,11 @@ class Parsedown 'extent' => strlen($matches[0]), 'element' => array( 'name' => $emphasis, - 'handler' => 'line', - 'text' => $matches[1], + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $matches[1], + 'destination' => 'elements', + ) ), ); } @@ -1215,7 +1344,7 @@ class Parsedown if (isset($Excerpt['text'][1]) and in_array($Excerpt['text'][1], $this->specialCharacters)) { return array( - 'markup' => $Excerpt['text'][1], + 'element' => array('rawHtml' => $Excerpt['text'][1]), 'extent' => 2, ); } @@ -1243,8 +1372,9 @@ class Parsedown 'name' => 'img', 'attributes' => array( 'src' => $Link['element']['attributes']['href'], - 'alt' => $Link['element']['text'], + 'alt' => $Link['element']['handler']['argument'], ), + 'autobreak' => true, ), ); @@ -1259,9 +1389,12 @@ class Parsedown { $Element = array( 'name' => 'a', - 'handler' => 'line', + 'handler' => array( + 'function' => 'lineElements', + 'argument' => null, + 'destination' => 'elements', + ), 'nonNestables' => array('Url', 'Link'), - 'text' => null, 'attributes' => array( 'href' => null, 'title' => null, @@ -1274,7 +1407,7 @@ class Parsedown if (preg_match('/\[((?:[^][]++|(?R))*+)\]/', $remainder, $matches)) { - $Element['text'] = $matches[1]; + $Element['handler']['argument'] = $matches[1]; $extent += strlen($matches[0]); @@ -1285,7 +1418,7 @@ class Parsedown return; } - if (preg_match('/^[(]\s*+((?:[^ ()]++|[(][^ )]+[)])++)(?:[ ]+("[^"]*"|\'[^\']*\'))?\s*[)]/', $remainder, $matches)) + if (preg_match('/^[(]\s*+((?:[^ ()]++|[(][^ )]+[)])++)(?:[ ]+("[^"]*+"|\'[^\']*+\'))?\s*+[)]/', $remainder, $matches)) { $Element['attributes']['href'] = $matches[1]; @@ -1300,14 +1433,14 @@ class Parsedown { if (preg_match('/^\s*\[(.*?)\]/', $remainder, $matches)) { - $definition = strlen($matches[1]) ? $matches[1] : $Element['text']; + $definition = strlen($matches[1]) ? $matches[1] : $Element['handler']['argument']; $definition = strtolower($definition); $extent += strlen($matches[0]); } else { - $definition = strtolower($Element['text']); + $definition = strtolower($Element['handler']['argument']); } if ( ! isset($this->DefinitionData['Reference'][$definition])) @@ -1334,26 +1467,26 @@ class Parsedown return; } - if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w[\w-]*[ ]*>/s', $Excerpt['text'], $matches)) + if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w[\w-]*+[ ]*+>/s', $Excerpt['text'], $matches)) { return array( - 'markup' => $matches[0], + 'element' => array('rawHtml' => $matches[0]), 'extent' => strlen($matches[0]), ); } - if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches)) + if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches)) { return array( - 'markup' => $matches[0], + 'element' => array('rawHtml' => $matches[0]), 'extent' => strlen($matches[0]), ); } - if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w[\w-]*(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*\/?>/s', $Excerpt['text'], $matches)) + if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w[\w-]*+(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+\/?>/s', $Excerpt['text'], $matches)) { return array( - 'markup' => $matches[0], + 'element' => array('rawHtml' => $matches[0]), 'extent' => strlen($matches[0]), ); } @@ -1361,23 +1494,16 @@ class Parsedown protected function inlineSpecialCharacter($Excerpt) { - if ($Excerpt['text'][0] === '&' and ! preg_match('/^&#?\w+;/', $Excerpt['text'])) - { + if (substr($Excerpt['text'], 1, 1) !== ' ' and strpos($Excerpt['text'], ';') !== false + and preg_match('/^&(#?+[0-9a-zA-Z]++);/', $Excerpt['text'], $matches) + ) { return array( - 'markup' => '&', - 'extent' => 1, + 'element' => array('rawHtml' => '&' . $matches[1] . ';'), + 'extent' => strlen($matches[0]), ); } - $SpecialCharacter = array('>' => 'gt', '<' => 'lt', '"' => 'quot'); - - if (isset($SpecialCharacter[$Excerpt['text'][0]])) - { - return array( - 'markup' => '&'.$SpecialCharacter[$Excerpt['text'][0]].';', - 'extent' => 1, - ); - } + return; } protected function inlineStrikethrough($Excerpt) @@ -1393,8 +1519,11 @@ class Parsedown 'extent' => strlen($matches[0]), 'element' => array( 'name' => 'del', - 'text' => $matches[1], - 'handler' => 'line', + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $matches[1], + 'destination' => 'elements', + ) ), ); } @@ -1407,8 +1536,9 @@ class Parsedown return; } - if (preg_match('/\bhttps?:[\/]{2}[^\s<]+\b\/*/ui', $Excerpt['context'], $matches, PREG_OFFSET_CAPTURE)) - { + if (strpos($Excerpt['context'], 'http') !== false + and preg_match('/\bhttps?+:[\/]{2}[^\s<]+\b\/*+/ui', $Excerpt['context'], $matches, PREG_OFFSET_CAPTURE) + ) { $url = $matches[0][0]; $Inline = array( @@ -1429,7 +1559,7 @@ class Parsedown protected function inlineUrlTag($Excerpt) { - if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w+:\/{2}[^ >]+)>/i', $Excerpt['text'], $matches)) + if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w++:\/{2}[^ >]++)>/i', $Excerpt['text'], $matches)) { $url = $matches[1]; @@ -1450,23 +1580,112 @@ class Parsedown protected function unmarkedText($text) { - if ($this->breaksEnabled) - { - $text = preg_replace('/[ ]*\n/', "
\n", $text); - } - else - { - $text = preg_replace('/(?:[ ][ ]+|[ ]*\\\\)\n/', "
\n", $text); - $text = str_replace(" \n", "\n", $text); - } - - return $text; + $Inline = $this->inlineText($text); + return $this->element($Inline['element']); } # # Handlers # + protected function handle(array $Element) + { + if (isset($Element['handler'])) + { + if (!isset($Element['nonNestables'])) + { + $Element['nonNestables'] = array(); + } + + if (is_string($Element['handler'])) + { + $function = $Element['handler']; + $argument = $Element['text']; + unset($Element['text']); + $destination = 'rawHtml'; + } + else + { + $function = $Element['handler']['function']; + $argument = $Element['handler']['argument']; + $destination = $Element['handler']['destination']; + } + + $Element[$destination] = $this->{$function}($argument, $Element['nonNestables']); + + if ($destination === 'handler') + { + $Element = $this->handle($Element); + } + + unset($Element['handler']); + } + + return $Element; + } + + protected function handleElementRecursive(array $Element) + { + return $this->elementApplyRecursive(array($this, 'handle'), $Element); + } + + protected function handleElementsRecursive(array $Elements) + { + return $this->elementsApplyRecursive(array($this, 'handle'), $Elements); + } + + protected function elementApplyRecursive($closure, array $Element) + { + $Element = call_user_func($closure, $Element); + + if (isset($Element['elements'])) + { + $Element['elements'] = $this->elementsApplyRecursive($closure, $Element['elements']); + } + elseif (isset($Element['element'])) + { + $Element['element'] = $this->elementApplyRecursive($closure, $Element['element']); + } + + return $Element; + } + + protected function elementApplyRecursiveDepthFirst($closure, array $Element) + { + if (isset($Element['elements'])) + { + $Element['elements'] = $this->elementsApplyRecursiveDepthFirst($closure, $Element['elements']); + } + elseif (isset($Element['element'])) + { + $Element['element'] = $this->elementsApplyRecursiveDepthFirst($closure, $Element['element']); + } + + $Element = call_user_func($closure, $Element); + + return $Element; + } + + protected function elementsApplyRecursive($closure, array $Elements) + { + foreach ($Elements as &$Element) + { + $Element = $this->elementApplyRecursive($closure, $Element); + } + + return $Elements; + } + + protected function elementsApplyRecursiveDepthFirst($closure, array $Elements) + { + foreach ($Elements as &$Element) + { + $Element = $this->elementApplyRecursiveDepthFirst($closure, $Element); + } + + return $Elements; + } + protected function element(array $Element) { if ($this->safeMode) @@ -1474,18 +1693,28 @@ class Parsedown $Element = $this->sanitiseElement($Element); } - $markup = '<'.$Element['name']; + # identity map if element has no handler + $Element = $this->handle($Element); - if (isset($Element['attributes'])) + $hasName = isset($Element['name']); + + $markup = ''; + + if ($hasName) { - foreach ($Element['attributes'] as $name => $value) - { - if ($value === null) - { - continue; - } + $markup .= '<' . $Element['name']; - $markup .= ' '.$name.'="'.self::escape($value).'"'; + if (isset($Element['attributes'])) + { + foreach ($Element['attributes'] as $name => $value) + { + if ($value === null) + { + continue; + } + + $markup .= " $name=\"".self::escape($value).'"'; + } } } @@ -1500,35 +1729,40 @@ class Parsedown elseif (isset($Element['rawHtml'])) { $text = $Element['rawHtml']; + $allowRawHtmlInSafeMode = isset($Element['allowRawHtmlInSafeMode']) && $Element['allowRawHtmlInSafeMode']; $permitRawHtml = !$this->safeMode || $allowRawHtmlInSafeMode; } - if (isset($text)) + $hasContent = isset($text) || isset($Element['element']) || isset($Element['elements']); + + if ($hasContent) { - $markup .= '>'; + $markup .= $hasName ? '>' : ''; - if (!isset($Element['nonNestables'])) + if (isset($Element['elements'])) { - $Element['nonNestables'] = array(); + $markup .= $this->elements($Element['elements']); } - - if (isset($Element['handler'])) + elseif (isset($Element['element'])) { - $markup .= $this->{$Element['handler']}($text, $Element['nonNestables']); - } - elseif (!$permitRawHtml) - { - $markup .= self::escape($text, true); + $markup .= $this->element($Element['element']); } else { - $markup .= $text; + if (!$permitRawHtml) + { + $markup .= self::escape($text, true); + } + else + { + $markup .= $text; + } } - $markup .= ''; + $markup .= $hasName ? '' : ''; } - else + elseif ($hasName) { $markup .= ' />'; } @@ -1540,12 +1774,26 @@ class Parsedown { $markup = ''; + $autoBreak = true; + foreach ($Elements as $Element) { - $markup .= "\n" . $this->element($Element); + if (empty($Element)) + { + continue; + } + + $autoBreakNext = (isset($Element['autobreak']) + ? $Element['autobreak'] : isset($Element['name']) + ); + // (autobreak === false) covers both sides of an element + $autoBreak = !$autoBreak ? $autoBreak : $autoBreakNext; + + $markup .= ($autoBreak ? "\n" : '') . $this->element($Element); + $autoBreak = $autoBreakNext; } - $markup .= "\n"; + $markup .= $autoBreak ? "\n" : ''; return $markup; } @@ -1554,21 +1802,49 @@ class Parsedown protected function li($lines) { - $markup = $this->lines($lines); + $Elements = $this->linesElements($lines); - $trimmedMarkup = trim($markup); - - if ( ! in_array('', $lines) and substr($trimmedMarkup, 0, 3) === '

') - { - $markup = $trimmedMarkup; - $markup = substr($markup, 3); - - $position = strpos($markup, "

"); - - $markup = substr_replace($markup, '', $position, 4); + if ( ! in_array('', $lines) + and isset($Elements[0]) and isset($Elements[0]['name']) + and $Elements[0]['name'] === 'p' + ) { + unset($Elements[0]['name']); } - return $markup; + return $Elements; + } + + # + # AST Convenience + # + + /** + * Replace occurrences $regexp with $Elements in $text. Return an array of + * elements representing the replacement. + */ + protected static function pregReplaceElements($regexp, $Elements, $text) + { + $newElements = array(); + + while (preg_match($regexp, $text, $matches, PREG_OFFSET_CAPTURE)) + { + $offset = $matches[0][1]; + $before = substr($text, 0, $offset); + $after = substr($text, $offset + strlen($matches[0][0])); + + $newElements[] = array('text' => $before); + + foreach ($Elements as $Element) + { + $newElements[] = $Element; + } + + $text = $after; + } + + $newElements[] = array('text' => $text); + + return $newElements; } # @@ -1590,6 +1866,12 @@ class Parsedown 'img' => 'src', ); + if ( ! isset($Element['name'])) + { + unset($Element['attributes']); + return $Element; + } + if (isset($safeUrlNameToAtt[$Element['name']])) { $Element = $this->filterUnsafeUrlInAttribute($Element, $safeUrlNameToAtt[$Element['name']]); @@ -1679,12 +1961,12 @@ class Parsedown # Read-Only protected $specialCharacters = array( - '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|', + '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|', '~' ); protected $StrongRegex = array( - '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*[*])+?)[*]{2}(?![*])/s', - '_' => '/^__((?:\\\\_|[^_]|_[^_]*_)+?)__(?!_)/us', + '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*+[*])+?)[*]{2}(?![*])/s', + '_' => '/^__((?:\\\\_|[^_]|_[^_]*+_)+?)__(?!_)/us', ); protected $EmRegex = array( @@ -1692,7 +1974,7 @@ class Parsedown '_' => '/^_((?:\\\\_|[^_]|__[^_]*__)+?)_(?!_)\b/us', ); - protected $regexHtmlAttribute = '[a-zA-Z_:][\w:.-]*(?:\s*=\s*(?:[^"\'=<>`\s]+|"[^"]*"|\'[^\']*\'))?'; + protected $regexHtmlAttribute = '[a-zA-Z_:][\w:.-]*+(?:\s*+=\s*+(?:[^"\'=<>`\s]+|"[^"]*+"|\'[^\']*+\'))?+'; protected $voidElements = array( 'area', 'base', 'br', 'col', 'command', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source', diff --git a/development/compose.yaml b/development/compose.yaml index 0788a43..132c6bb 100644 --- a/development/compose.yaml +++ b/development/compose.yaml @@ -15,7 +15,7 @@ services: # - "4040:80" # command: bash -c "a2enconf custom && a2enmod rewrite && apache2-foreground" default: - image: php:8.3.12-apache + image: php:8.4.14-apache container_name: folderweb-default working_dir: /var/www/html/ volumes: