Merge pull request #115 from froschdesign/feature/markdown-parser

Updates Markdown parser to use existing extensions for parsing front matter and table of contents

composer.json

@@ -37,7 +37,7 @@
         "forum": "https://discourse.laminas.dev"
     },
     "require": {
-        "php": "~8.1.12",
+        "php": "~8.1.0",
         "ext-pdo": "*",
         "dflydev/fig-cookies": "^3.0",
         "laminas/laminas-cli": "^1.7",

psalm-baseline.xml

@@ -1,5 +1,5 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<files psalm-version="4.28.0@52e96bea381e6cb07a672aefec791a5817694a26">
+<files psalm-version="4.29.0@7ec5ffbd5f68ae03782d7fd33fff0c45a69f95b3">
   <file src="bin/clear-config-cache.php">
     <MixedArgument occurrences="5">
       <code>$config['config_cache_path']</code>
@@ -64,13 +64,11 @@
       <code>static::FOLDER_COLLECTION</code>
     </MixedOperand>
   </file>
-  <file src="src/App/FrontMatter/Document.php">
-    <MixedInferredReturnType occurrences="1">
+  <file src="src/App/ContentParser/Document.php">
+    <MixedReturnTypeCoercion occurrences="2">
+      <code>(array) $this-&gt;renderedContent-&gt;getFrontMatter()</code>
       <code>array</code>
-    </MixedInferredReturnType>
-    <MixedReturnStatement occurrences="1">
-      <code>$this-&gt;document-&gt;matter()</code>
-    </MixedReturnStatement>
+    </MixedReturnTypeCoercion>
   </file>
   <file src="src/App/Handler/StaticPageHandler.php">
     <PossiblyFalseArgument occurrences="1">
@@ -142,16 +140,14 @@
     </RedundantConditionGivenDocblockType>
   </file>
   <file src="src/Blog/CreateBlogPostFromDataArray.php">
-    <MixedArgument occurrences="9">
+    <DocblockTypeContradiction occurrences="1">
+      <code>explode('|', trim((string) $post['tags'], '|'))</code>
+    </DocblockTypeContradiction>
+    <MixedArgument occurrences="4">
       <code>$metadata['email'] ?? ''</code>
       <code>$metadata['name'] ?? '[email protected]'</code>
       <code>$metadata['uri'] ?? ''</code>
-      <code>$post['author']</code>
-      <code>$post['created']</code>
-      <code>$post['id']</code>
       <code>$post['path']</code>
-      <code>$post['title']</code>
-      <code>$post['updated']</code>
     </MixedArgument>
     <MixedArrayAccess occurrences="3">
       <code>$metadata['email']</code>
@@ -161,6 +157,13 @@
     <MixedAssignment occurrences="1">
       <code>$metadata</code>
     </MixedAssignment>
+    <RedundantCastGivenDocblockType occurrences="2">
+      <code>(bool) $post['draft']</code>
+      <code>(bool) $post['public']</code>
+    </RedundantCastGivenDocblockType>
+    <RedundantConditionGivenDocblockType occurrences="1">
+      <code>is_array($post['tags'])</code>
+    </RedundantConditionGivenDocblockType>
   </file>
   <file src="src/Blog/Handler/DisplayPostHandler.php">
     <MixedArgument occurrences="1">

src/App/AbstractCollection.php

@@ -4,7 +4,7 @@
 
 namespace App;
 
-use App\FrontMatter\ParserInterface;
+use App\ContentParser\ParserInterface;
 use RuntimeException;
 
 use function file_exists;
@@ -25,7 +25,7 @@ abstract class AbstractCollection
 
     protected array $collection = [];
 
-    public function __construct(protected ParserInterface $frontMatterParser)
+    public function __construct(protected ParserInterface $contentParser)
     {
         if (empty(static::CACHE_FILE)) {
             throw new RuntimeException('The cache file path is not defined!');
@@ -48,8 +48,8 @@ public function getFromFile(string $file): array
     {
         $result = [];
         if (file_exists($file)) {
-            $doc            = $this->frontMatterParser->parse($file);
-            $result         = $doc->getYAML();
+            $doc            = $this->contentParser->parse($file);
+            $result         = $doc->getFrontMatter();
             $result['body'] = $doc->getContent();
         }
         return $result;
@@ -62,8 +62,8 @@ protected function buildCache(): void
         }
 
         foreach (glob(static::FOLDER_COLLECTION . '/*.md') as $file) {
-            $doc                     = $this->frontMatterParser->parse($file);
-            $fields                  = $doc->getYAML();
+            $doc                     = $this->contentParser->parse($file);
+            $fields                  = $doc->getFrontMatter();
             $this->collection[$file] = $fields;
         }
 

src/App/ContentParser/Document.php

@@ -0,0 +1,31 @@
+<?php
+
+declare(strict_types=1);
+
+namespace App\ContentParser;
+
+use League\CommonMark\Extension\FrontMatter\Output\RenderedContentWithFrontMatter;
+
+final class Document implements DocumentInterface
+{
+    public function __construct(
+        private readonly RenderedContentWithFrontMatter $renderedContent,
+        private readonly ?string $tableOfContents
+    ) {
+    }
+
+    public function getFrontMatter(): array
+    {
+        return (array) $this->renderedContent->getFrontMatter();
+    }
+
+    public function getTableOfContents(): ?string
+    {
+        return $this->tableOfContents;
+    }
+
+    public function getContent(): string
+    {
+        return $this->renderedContent->getContent();
+    }
+}

src/App/ContentParser/DocumentInterface.php

@@ -0,0 +1,26 @@
+<?php
+
+declare(strict_types=1);
+
+namespace App\ContentParser;
+
+interface DocumentInterface
+{
+    /**
+     * @return array{
+     *     id: string,
+     *     author: string,
+     *     title: string,
+     *     draft: bool,
+     *     public: bool,
+     *     created: string,
+     *     updated: string,
+     *     tags: list<string>
+     * }
+     */
+    public function getFrontMatter(): array;
+
+    public function getTableOfContents(): ?string;
+
+    public function getContent(): string;
+}

src/App/ContentParser/Parser.php

@@ -0,0 +1,96 @@
+<?php
+
+declare(strict_types=1);
+
+namespace App\ContentParser;
+
+use League\CommonMark\Environment\Environment;
+use League\CommonMark\Extension\CommonMark\CommonMarkCoreExtension;
+use League\CommonMark\Extension\DefaultAttributes\DefaultAttributesExtension;
+use League\CommonMark\Extension\FrontMatter\FrontMatterExtension;
+use League\CommonMark\Extension\FrontMatter\Output\RenderedContentWithFrontMatter;
+use League\CommonMark\Extension\HeadingPermalink\HeadingPermalinkExtension;
+use League\CommonMark\Extension\Table\Table;
+use League\CommonMark\Extension\Table\TableExtension;
+use League\CommonMark\Extension\TableOfContents\Node\TableOfContents;
+use League\CommonMark\Extension\TableOfContents\TableOfContentsExtension;
+use League\CommonMark\MarkdownConverter;
+use League\CommonMark\Node\Query;
+use League\CommonMark\Parser\MarkdownParser;
+use League\CommonMark\Renderer\HtmlRenderer;
+
+use function file_get_contents;
+
+final class Parser implements ParserInterface
+{
+    private readonly MarkdownConverter $converter;
+
+    private readonly MarkdownParser $parser;
+
+    private readonly HtmlRenderer $renderer;
+
+    public function __construct()
+    {
+        // Create default converter
+        $environment = new Environment(
+            [
+                'default_attributes' => [
+                    Table::class => [
+                        'class' => 'table table-striped table-bordered table-hover',
+                    ],
+                ],
+                'heading_permalink'  => [
+                    'insert'            => 'after',
+                    'min_heading_level' => 1,
+                    'max_heading_level' => 2,
+                ],
+            ]
+        );
+        $environment->addExtension(new CommonMarkCoreExtension());
+        $environment->addExtension(new DefaultAttributesExtension());
+        $environment->addExtension(new FrontMatterExtension());
+        $environment->addExtension(new HeadingPermalinkExtension());
+        $environment->addExtension(new TableExtension());
+
+        $this->converter = new MarkdownConverter($environment);
+
+        // Create parser and renderer for table of contents
+        $environment = new Environment(
+            [
+                'table_of_contents' => [
+                    'min_heading_level' => 2,
+                    'max_heading_level' => 2,
+                ],
+            ]
+        );
+        $environment->addExtension(new CommonMarkCoreExtension());
+        $environment->addExtension(new FrontMatterExtension());
+        $environment->addExtension(new HeadingPermalinkExtension());
+        $environment->addExtension(new TableOfContentsExtension());
+
+        $this->parser   = new MarkdownParser($environment);
+        $this->renderer = new HtmlRenderer($environment);
+    }
+
+    public function parse(string $file): DocumentInterface
+    {
+        $markdown = file_get_contents($file);
+
+        // Render markdown content
+        /** @var RenderedContentWithFrontMatter $renderedContent */
+        $renderedContent = $this->converter->convert($markdown);
+
+        // Extract table of contents
+        $document = $this->parser->parse($markdown);
+        $node     = (new Query())
+            ->where(Query::type(TableOfContents::class))
+            ->findOne($document);
+
+        $tableOfContents = null;
+        if ($node) {
+            $tableOfContents = $this->renderer->renderNodes([$node]);
+        }
+
+        return new Document($renderedContent, $tableOfContents);
+    }
+}

src/App/FrontMatter/ParserInterface.php → src/App/ContentParser/ParserInterface.php

@@ -2,7 +2,7 @@
 
 declare(strict_types=1);
 
-namespace App\FrontMatter;
+namespace App\ContentParser;
 
 interface ParserInterface
 {