admin/brew
1
0
Fork 0
Code Issues Packages Projects Releases 6 Wiki Activity

utils/curl: get encoding from header

Browse Source
This commit is contained in:
Alexander Bayandin 2022-05-04 00:13:56 +01:00
parent 4575ddf909
commit 6643f58b49
No known key found for this signature in database
GPG Key ID: DB8BA841834EF987
1 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
Library/Homebrew/utils/curl.rb
View File

@ -296,8 +296,8 @@ module Utils
return unless check_content
no_protocol_file_contents = %r{https?:\\?/\\?/}
http_content = details[:file]&.gsub(no_protocol_file_contents, "/")
https_content = secure_details[:file]&.gsub(no_protocol_file_contents, "/")
http_content = details[:file]&.scrub&.gsub(no_protocol_file_contents, "/")
https_content = secure_details[:file]&.scrub&.gsub(no_protocol_file_contents, "/")
# Check for the same content after removing all protocols
if (http_content && https_content) && (http_content == https_content) && http_with_https_available
@ -358,8 +358,19 @@ module Utils
content_length = headers["content-length"]
if status.success?
file_contents = File.read(file.path)
file_contents.encode!(Encoding::UTF_8, invalid: :replace) if headers["content-type"]&.start_with?("text/")
open_args = {}
# Try to get encoding from Content-Type header
# TODO: add guessing encoding by <meta http-equiv="Content-Type" ...> tag
if (content_type = headers["content-type"]) &&
(match = content_type.match(/;\s*charset\s*=\s*([^\s]+)/)) &&
(charset = match[1])
begin
open_args[:encoding] = Encoding.find(charset)
rescue ArgumentError
# Unknown charset in Content-Type header
end
end
file_contents = File.read(file.path, open_args)
file_hash = Digest::SHA2.hexdigest(file_contents) if hash_needed
end