[Data Liberation] Add HTML to Blocks converter

Adds a basic WP_HTML_To_Blocks class that accepts HTML and outputs block markup. It only considers the markup and won't consider any visual changes introduced via CSS or JavaScript. A part of #1894 ## Example ```html $html = <<<HTML <meta name="post_title" content="My first post"> <p>Hello <b>world</b>!</p> HTML; $converter = new WP_HTML_To_Blocks( $html ); $converter->convert(); var_dump( $converter->get_all_metadata() ); /* * array( 'post_title' => array( 'My first post' ) ) */ var_dump( $converter->get_block_markup() ); /* *  * <p>Hello <b>world</b>!</p> *  */ ``` ## Testing instructions This PR mostly adds new code. Just confirm the unit tests pass in CI.
WordPress · Dec 17, 2024 · 1c66dd0 · 1c66dd0
1 parent 869f6bd
commit 1c66dd0
Show file tree

Hide file tree

Showing 13 changed files with 10,336 additions and 3 deletions.
diff --git a/packages/playground/data-liberation/blueprints-library b/packages/playground/data-liberation/blueprints-library
diff --git a/packages/playground/data-liberation/bootstrap.php b/packages/playground/data-liberation/bootstrap.php
@@ -44,14 +44,17 @@
 	require_once __DIR__ . '/src/wordpress-core-html-api/html5-named-character-references.php';
 }
 
+require_once __DIR__ . '/src/block-markup/WP_Block_Markup_Converter.php';
 require_once __DIR__ . '/src/block-markup/WP_Block_Markup_Processor.php';
 require_once __DIR__ . '/src/block-markup/WP_Block_Markup_Url_Processor.php';
 require_once __DIR__ . '/src/block-markup/WP_URL_In_Text_Processor.php';
+require_once __DIR__ . '/src/block-markup/WP_HTML_To_Blocks.php';
 require_once __DIR__ . '/src/block-markup/WP_URL.php';
 
 require_once __DIR__ . '/src/xml-api/WP_XML_Decoder.php';
 require_once __DIR__ . '/src/xml-api/WP_XML_Processor.php';
 require_once __DIR__ . '/src/wxr/WP_WXR_Reader.php';
+require_once __DIR__ . '/src/import/WP_Import_Utils.php';
 require_once __DIR__ . '/src/import/WP_Block_Object.php';
 require_once __DIR__ . '/src/import/WP_Entity_Importer.php';
 require_once __DIR__ . '/src/import/WP_File_Visitor.php';
@@ -64,6 +67,8 @@
 require_once __DIR__ . '/src/import/WP_Entity_Iterator_Chain.php';
 require_once __DIR__ . '/src/import/WP_Retry_Frontloading_Iterator.php';
 require_once __DIR__ . '/src/import/WP_Markdown_Importer.php';
+require_once __DIR__ . '/src/entity-readers/WP_Entity_Reader.php';
+require_once __DIR__ . '/src/entity-readers/WP_HTML_Entity_Reader.php';
 
 require_once __DIR__ . '/src/utf8_decoder.php';
 

diff --git a/packages/playground/data-liberation/phpunit.xml b/packages/playground/data-liberation/phpunit.xml
@@ -2,6 +2,8 @@
 <phpunit xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" bootstrap="bootstrap.php" colors="true" xsi:noNamespaceSchemaLocation="https://schema.phpunit.de/10.0/phpunit.xsd" cacheDirectory=".phpunit.cache">
   <testsuites>
     <testsuite name="Application Test Suite">
+      <file>tests/WPHTMLEntityReaderTests.php</file>
+      <file>tests/WPHTMLToBlocksTests.php</file>
       <file>tests/WPWXRReaderTests.php</file>
       <file>tests/WPRewriteUrlsTests.php</file>
       <file>tests/WPURLInTextProcessorTests.php</file>

diff --git a/packages/playground/data-liberation/src/block-markup/WP_Block_Markup_Converter.php b/packages/playground/data-liberation/src/block-markup/WP_Block_Markup_Converter.php
@@ -0,0 +1,8 @@
+<?php
+
+interface WP_Block_Markup_Converter {
+	public function convert();
+	public function get_block_markup();
+	public function get_all_metadata();
+	public function get_meta_value( $key );
+}
+2 −2		README.md
+3 −0		composer.json
+1 −1		src/WordPress/AsyncHttp/Client.php
+0 −10		src/WordPress/AsyncHttp/Request.php