24 lines
875 B
Diff
24 lines
875 B
Diff
From e444525ef1634b675cd1cf52d39f4320ef0aecfd Mon Sep 17 00:00:00 2001
|
|
From: Mike Dalessio <mike.dalessio@gmail.com>
|
|
Date: Sun, 10 Apr 2022 14:42:04 -0400
|
|
Subject: [PATCH] fix(perf): HTML4::EncodingReader detection
|
|
|
|
---
|
|
lib/nokogiri/html4/document.rb | 2 +-
|
|
test/html4/test_document_encoding.rb | 12 ++++++++++++
|
|
2 files changed, 13 insertions(+), 1 deletion(-)
|
|
|
|
diff --git a/lib/nokogiri/html4/document.rb b/lib/nokogiri/html4/document.rb
|
|
index 177efc04f..fbc22d207 100644
|
|
--- a/lib/nokogiri/html4/document.rb
|
|
+++ b/lib/nokogiri/html4/document.rb
|
|
@@ -268,7 +268,7 @@ def start_element(name, attrs = [])
|
|
end
|
|
|
|
def self.detect_encoding(chunk)
|
|
- (m = chunk.match(/\A(<\?xml[ \t\r\n]+[^>]*>)/)) &&
|
|
+ (m = chunk.match(/\A(<\?xml[ \t\r\n][^>]*>)/)) &&
|
|
(return Nokogiri.XML(m[1]).encoding)
|
|
|
|
if Nokogiri.jruby?
|