Improve PHP parser compatibility with different server configurations

bin/create-php-parser.js

@@ -14,6 +14,7 @@ const parser = pegjs.generate(
 		phpegjs: {
 			parserNamespace: null,
 			parserGlobalNamePrefix: 'Gutenberg_PEG_',
+			mbstringAllowed: false,
 		},
 	}
 );

docs/faq.md

@@ -119,14 +119,13 @@ This also <a href="https://github.com/WordPress/gutenberg/issues/1516">gives us
 In JS:
 
 ```js
-wp.blocks.parse( postContent );
+var blocks = wp.blocks.parse( postContent );
 ```
 
 In PHP:
 
 ```php
-$parser = new Gutenberg_PEG_Parser;
-$blocks = $parser->parse( $post_content );
+$blocks = gutenberg_parse_blocks( $post_content );
 ```
 ## Why should I start using this once released?
 Blocks are likely to become the main way users interact with content. Users are going to be discovering functionality in the new universal inserter tool, with a richer block interface that provides more layout opportunities.

gutenberg.php

@@ -18,6 +18,7 @@
 	// Load API functions, register scripts and actions, etc.
 	require_once dirname( __FILE__ ) . '/lib/blocks.php';
 	require_once dirname( __FILE__ ) . '/lib/client-assets.php';
+	require_once dirname( __FILE__ ) . '/lib/compat.php';
 	require_once dirname( __FILE__ ) . '/lib/i18n.php';
 	require_once dirname( __FILE__ ) . '/lib/parser.php';
 	require_once dirname( __FILE__ ) . '/lib/register.php';

lib/blocks.php

@@ -70,25 +70,30 @@ function unregister_block_type( $name ) {
 }
 
 /**
- * Renders the dynamic blocks into the post content
+ * Parses blocks out of a content string.
  *
- * @since 0.1.0
+ * @since 0.5.0
  *
  * @param  string $content Post content.
+ * @return array  Array of parsedblock objects.
+ */
+function gutenberg_parse_blocks( $content ) {
+	$parser = new Gutenberg_PEG_Parser;
+	return $parser->parse( _gutenberg_utf8_split( $content ) );
+}
+
+/**
+ * Parses dynamic blocks out of `post_content` and re-renders them.
  *
+ * @since 0.1.0
+ *
+ * @param  string $content Post content.
  * @return string          Updated post content.
  */
 function do_blocks( $content ) {
 	global $wp_registered_blocks;
 
-	if ( ! extension_loaded( 'mbstring' ) ) {
-		// Skip server-side rendering of blocks until WordPress/gutenberg#1611
-		// is properly fixed.
-		return $content;
-	}
-
-	$parser = new Gutenberg_PEG_Parser;
-	$blocks = $parser->parse( $content );
+	$blocks = gutenberg_parse_blocks( $content );
 
 	$content_after_blocks = '';
 

lib/compat.php

@@ -0,0 +1,69 @@
+<?php
+/**
+ * PHP configuration compatibility functions for the Gutenberg editor plugin.
+ *
+ * @package gutenberg
+ */
+
+if ( ! defined( 'ABSPATH' ) ) {
+	die( 'Silence is golden.' );
+}
+
+/**
+ * Splits a UTF-8 string into an array of UTF-8-encoded codepoints.
+ *
+ * @since 0.5.0
+ *
+ * Based on WordPress' _mb_substr() compat function.
+ *
+ * @param string $str        The string to split.
+ * @return array
+ */
+function _gutenberg_utf8_split( $str ) {
+	if ( _wp_can_use_pcre_u() ) {
+		// Use the regex unicode support to separate the UTF-8 characters into
+		// an array.
+		preg_match_all( '/./us', $str, $match );
+		return $match[0];
+	}
+
+	$regex = '/(
+		  [\x00-\x7F]                  # single-byte sequences   0xxxxxxx
+		| [\xC2-\xDF][\x80-\xBF]       # double-byte sequences   110xxxxx 10xxxxxx
+		| \xE0[\xA0-\xBF][\x80-\xBF]   # triple-byte sequences   1110xxxx 10xxxxxx * 2
+		| [\xE1-\xEC][\x80-\xBF]{2}
+		| \xED[\x80-\x9F][\x80-\xBF]
+		| [\xEE-\xEF][\x80-\xBF]{2}
+		| \xF0[\x90-\xBF][\x80-\xBF]{2} # four-byte sequences   11110xxx 10xxxxxx * 3
+		| [\xF1-\xF3][\x80-\xBF]{3}
+		| \xF4[\x80-\x8F][\x80-\xBF]{2}
+	)/x';
+
+	// Start with 1 element instead of 0 since the first thing we do is pop.
+	$chars = array( '' );
+	do {
+		// We had some string left over from the last round, but we counted it
+		// in that last round.
+		array_pop( $chars );
+
+		// Split by UTF-8 character, limit to 1000 characters (last array
+		// element will contain the rest of the string).
+		$pieces = preg_split(
+			$regex,
+			$str,
+			1000,
+			PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY
+		);
+
+		$chars = array_merge( $chars, $pieces );
+
+		// If there's anything left over, repeat the loop.
+		if ( count( $pieces ) > 1 ) {
+			$str = array_pop( $pieces );
+		} else {
+			break;
+		}
+	} while ( $str );
+
+	return $chars;
+}