WordPress · adamziel · Jul 24, 2025 · Jul 24, 2025 · Jul 24, 2025 · Jul 26, 2025
diff --git a/bin/run-server-next-gen-importer.sh b/bin/run-server-next-gen-importer.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+
+# @TODO: Figure out how to set up the dev environment to be as similar to
+#        production as possible.
+npx @wp-playground/cli@latest \
+    server \
+    --php=8.2 \
+    --mount=`pwd`/plugins/next-gen-importer:/wordpress/wp-content/plugins/next-gen-importer \
+    --blueprint=./blueprint-next-gen-importer.json \
+    --mount=`pwd`:/wordpress/wp-content/data-liberation \
+    --mount=`pwd`/debug.log:/wordpress/wp-content/debug.log
+
diff --git a/blueprint-next-gen-importer.json b/blueprint-next-gen-importer.json
@@ -0,0 +1,16 @@
+{
+	"login": true,
+	"constants": {
+		"WP_DEBUG": true,
+		"WP_DEBUG_LOG": "/wordpress/wp-content/debug.log",
+		"WP_DEBUG_DISPLAY": true,
+		"DISABLE_WP_CRON": false
+	},
+	"plugins": ["wp-crontrol"],
+    "steps": [
+        {
+            "step": "activatePlugin",
+            "pluginPath": "next-gen-importer/plugin.php"
+        }
+    ]
+}
diff --git a/components/BlockParser/class-wp-block-parser-block.php b/components/BlockParser/class-wp-block-parser-block.php
@@ -1,4 +1,5 @@
 <?php
+namespace WordPress\BlockParser;
 /**
  * Block Serialization Parser
  *

diff --git a/components/BlockParser/class-wp-block-parser-error.php b/components/BlockParser/class-wp-block-parser-error.php
@@ -1,4 +1,7 @@
 <?php
+namespace WordPress\BlockParser;
+use Exception;
+
 /**
  * @package WordPress
  */

diff --git a/components/BlockParser/class-wp-block-parser-frame.php b/components/BlockParser/class-wp-block-parser-frame.php
@@ -1,4 +1,5 @@
 <?php
+namespace WordPress\BlockParser;
 /**
  * Block Serialization Parser
  *

diff --git a/components/BlockParser/class-wp-block-parser.php b/components/BlockParser/class-wp-block-parser.php
@@ -1,4 +1,6 @@
 <?php
+namespace WordPress\BlockParser;
+
 /**
  * Block Serialization Parser
  *

diff --git a/components/Blueprints/Steps/scripts/import-content.php b/components/Blueprints/Steps/scripts/import-content.php
@@ -19,6 +19,7 @@
 use WordPress\Zip\ZipFilesystem;
 
 use function WordPress\Filesystem\wp_join_unix_paths;
+use function WordPress\Filesystem\add_filter;
 
 require_once getenv('DOCROOT') . '/wp-load.php';
 require_once getenv('DOCROOT') . '/php-toolkit.phar';

diff --git a/components/ByteStream/ReadStream/BaseByteReadStream.php b/components/ByteStream/ReadStream/BaseByteReadStream.php
@@ -7,7 +7,7 @@
 
 abstract class BaseByteReadStream implements ByteReadStream {
 
-	const CHUNK_SIZE = 100;// 64 * 1024;
+	const CHUNK_SIZE = 64 * 1024;
 
 	protected $buffer_size = 2048;
 

diff --git a/components/DataLiberation/.DS_Store b/components/DataLiberation/.DS_Store
diff --git a/components/DataLiberation/BlockMarkup/BlockMarkupProcessor.php b/components/DataLiberation/BlockMarkup/BlockMarkupProcessor.php
@@ -2,8 +2,8 @@
 
 namespace WordPress\DataLiberation\BlockMarkup;
 
-use WP_Block_Parser_Error;
-use WP_HTML_Tag_Processor;
+use WordPress\BlockParser\WP_Block_Parser_Error;
+use WordPress\HTML\WP_HTML_Tag_Processor;
 
 /**
  * A processor class capable of reading and rewriting block markup.

diff --git a/components/DataLiberation/DataFormatConsumer/AnnotatedBlockMarkupConsumer.php b/components/DataLiberation/DataFormatConsumer/AnnotatedBlockMarkupConsumer.php
@@ -2,7 +2,9 @@
 
 namespace WordPress\DataLiberation\DataFormatConsumer;
 
-use WP_HTML_Processor;
+use WordPress\HTML\WP_HTML_Processor;
+use function WordPress\Polyfill\parse_blocks;
+use function WordPress\Polyfill\serialize_block;
 
 /**
  * Converts a metadata-annotated block markup into block markup+metadata pair.
@@ -48,7 +50,7 @@ public function consume() {
 			$metadata     = array();
 			foreach ( parse_blocks( $this->original_html ) as $block ) {
 				if ( $block['blockName'] === null ) {
-					$html_converter = new MarkupProcessorConsumer( WP_HTML_Processor::create_fragment( $block['innerHTML'] ) );
+					$html_converter = new MarkupProcessorConsumer( \WordPress\HTML\WP_HTML_Processor::create_fragment( $block['innerHTML'] ) );
 					$result         = $html_converter->consume();
 					$block_markup   .= $result->get_block_markup() . "\n";
 					$metadata       = array_merge( $metadata, $result->get_all_metadata() );

diff --git a/components/DataLiberation/DataFormatConsumer/MarkupProcessorConsumer.php b/components/DataLiberation/DataFormatConsumer/MarkupProcessorConsumer.php
@@ -6,8 +6,8 @@
 use WordPress\DataLiberation\DataLiberationException;
 use WordPress\DataLiberation\Importer\ImportUtils;
 use WordPress\XML\XMLProcessor;
-use WP_HTML_Processor;
-use WP_HTML_Tag_Processor;
+use WordPress\HTML\WP_HTML_Processor;
+use WordPress\HTML\WP_HTML_Tag_Processor;
 
 /**
  * Creates block markup from a WP_HTML_Processor or WP_XML_Processor instance.

diff --git a/components/DataLiberation/DataFormatProducer/AnnotatedBlockMarkupProducer.php b/components/DataLiberation/DataFormatProducer/AnnotatedBlockMarkupProducer.php
@@ -3,7 +3,7 @@
 namespace WordPress\DataLiberation\DataFormatProducer;
 
 use WordPress\DataLiberation\DataFormatConsumer\BlocksWithMetadata;
-use WP_HTML_Tag_Processor;
+use WordPress\HTML\WP_HTML_Tag_Processor;
 
 /**
  * Turns Block Markup + Metadata into a metadata-annotated Block Markup.

diff --git a/components/DataLiberation/DataLiberationHTMLProcessor.php b/components/DataLiberation/DataLiberationHTMLProcessor.php
@@ -2,8 +2,8 @@
 
 namespace WordPress\DataLiberation;
 
-use WP_HTML_Processor;
-use WP_HTML_Tag_Processor;
+use WordPress\HTML\WP_HTML_Processor;
+use WordPress\HTML\WP_HTML_Tag_Processor;
 
 class DataLiberationHTMLProcessor extends WP_HTML_Processor {
 

diff --git a/components/DataLiberation/EntityReader/EPubEntityReader.php b/components/DataLiberation/EntityReader/EPubEntityReader.php
@@ -8,6 +8,7 @@
 use WordPress\XML\XMLProcessor;
 
 use function WordPress\Filesystem\wp_join_unix_paths;
+use function WordPress\Polyfill\_doing_it_wrong;
 
 /**
  * https://www.w3.org/AudioVideo/ebook/

diff --git a/components/DataLiberation/EntityReader/FilesystemEntityReader.php b/components/DataLiberation/EntityReader/FilesystemEntityReader.php
@@ -12,7 +12,7 @@
 use WordPress\Filesystem\Visitor\FilesystemVisitor;
 use WordPress\Markdown\MarkdownConsumer;
 use WordPress\XML\XMLProcessor;
-use WP_HTML_Processor;
+use WordPress\HTML\WP_HTML_Processor;
 
 use function WordPress\Filesystem\wp_join_unix_paths;
 
@@ -277,7 +277,7 @@ public function next_entity(): bool {
 						$result    = $converter->consume();
 						break;
 					case 'html':
-						$converter = new MarkupProcessorConsumer( WP_HTML_Processor::create_fragment( $content ) );
+						$converter = new MarkupProcessorConsumer( \WordPress\HTML\WP_HTML_Processor::create_fragment( $content ) );
 						$result    = $converter->consume();
 						break;
 					default:

diff --git a/components/DataLiberation/EntityReader/WXREntityReader.php b/components/DataLiberation/EntityReader/WXREntityReader.php
@@ -6,6 +6,7 @@
 use WordPress\DataLiberation\ImportEntity;
 use WordPress\XML\XMLProcessor;
 use WordPress\XML\XMLUnsupportedException;
+use function WordPress\Polyfill\_doing_it_wrong;
 
 /**
  * Data Liberation API: WP_WXR_Entity_Reader class
@@ -819,7 +820,11 @@ private function read_next_entity() {
 				$this->entity_data['terms'][] = array(
 					'taxonomy'    => $this->last_opener_attributes['domain'],
 					'slug'        => $this->last_opener_attributes['nicename'],
-					'description' => $this->text_buffer,
+					/**
+					 * trim() – in XML, trailing whitespace in text nodes must be ignored.
+					 * @TODO: Only trim text nodes, not CDATA sections.
+					 */
+					'description' => trim( $this->text_buffer ),
 				);
 				$this->text_buffer            = '';
 				continue;
@@ -838,8 +843,12 @@ private function read_next_entity() {
 				continue;
 			}
 
-			$key                       = $this->KNOWN_ENITIES[ $this->entity_tag ]['fields'][ $tag_with_namespace ];
-			$this->entity_data[ $key ] = $this->text_buffer;
+			$key = $this->KNOWN_ENITIES[ $this->entity_tag ]['fields'][ $tag_with_namespace ];
+			/**
+			 * trim() – in XML, trailing whitespace in text nodes must be ignored.
+			 * @TODO: Only trim text nodes, not CDATA sections.
+			 */
+			$this->entity_data[ $key ] = trim( $this->text_buffer );
 			$this->text_buffer         = '';
 		} while ( $this->xml->next_token() );
 

diff --git a/components/DataLiberation/Importer/AttachmentDownloader.php b/components/DataLiberation/Importer/AttachmentDownloader.php
@@ -8,6 +8,7 @@
 use WordPress\HttpClient\Request;
 
 use function WordPress\Filesystem\wp_join_unix_paths;
+use function WordPress\Polyfill\_doing_it_wrong;
 
 class AttachmentDownloader {
 	private $client;