From fcd3b60903c82ff4d6c48f956d92cd57b5598370 Mon Sep 17 00:00:00 2001
From: Shahyar <shahyar@gmail.com>
Date: Fri, 22 Aug 2014 15:07:49 -0700
Subject: [PATCH] Fix malformed UTF-8 going to query profiler

Bug: 69926
Change-Id: I1c2e3f22104792fbc59491b1c6a17f2a6a0dd0b6
---
 includes/debug/MWDebug.php | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/includes/debug/MWDebug.php b/includes/debug/MWDebug.php
index fb11f368ea..c2f22233bb 100644
--- a/includes/debug/MWDebug.php
+++ b/includes/debug/MWDebug.php
@@ -335,6 +335,28 @@ class MWDebug {
 			return -1;
 		}
 
+		// Replace invalid UTF-8 chars with a square UTF-8 character
+		// This prevents json_encode from erroring out due to binary SQL data
+		$sql = preg_replace(
+			'/(
+				[\xC0-\xC1] # Invalid UTF-8 Bytes
+				| [\xF5-\xFF] # Invalid UTF-8 Bytes
+				| \xE0[\x80-\x9F] # Overlong encoding of prior code point
+				| \xF0[\x80-\x8F] # Overlong encoding of prior code point
+				| [\xC2-\xDF](?![\x80-\xBF]) # Invalid UTF-8 Sequence Start
+				| [\xE0-\xEF](?![\x80-\xBF]{2}) # Invalid UTF-8 Sequence Start
+				| [\xF0-\xF4](?![\x80-\xBF]{3}) # Invalid UTF-8 Sequence Start
+				| (?<=[\x0-\x7F\xF5-\xFF])[\x80-\xBF] # Invalid UTF-8 Sequence Middle
+				| (?<![\xC2-\xDF]|[\xE0-\xEF]|[\xE0-\xEF][\x80-\xBF]|[\xF0-\xF4]
+				   |[\xF0-\xF4][\x80-\xBF]|[\xF0-\xF4][\x80-\xBF]{2})[\x80-\xBF] # Overlong Sequence
+				| (?<=[\xE0-\xEF])[\x80-\xBF](?![\x80-\xBF]) # Short 3 byte sequence
+				| (?<=[\xF0-\xF4])[\x80-\xBF](?![\x80-\xBF]{2}) # Short 4 byte sequence
+				| (?<=[\xF0-\xF4][\x80-\xBF])[\x80-\xBF](?![\x80-\xBF]) # Short 4 byte sequence (2)
+			)/x',
+			'■',
+			$sql
+		);
+
 		self::$query[] = array(
 			'sql' => $sql,
 			'function' => $function,
-- 
2.20.1