From e564fe971f3dacb1a2a38ad984b865ae23e54400 Mon Sep 17 00:00:00 2001 From: Bob Van Landuyt Date: Thu, 1 Jun 2017 21:21:14 +0000 Subject: [PATCH] Rename `Gitlab::Git::EncodingHelper` to `Gitlab::EncodingHelper` --- app/models/merge_request_diff.rb | 2 +- app/validators/dynamic_path_validator.rb | 2 +- lib/gitlab/encoding_helper.rb | 62 ++++++++++++++++++ lib/gitlab/git/blame.rb | 2 +- lib/gitlab/git/blob.rb | 2 +- lib/gitlab/git/commit.rb | 2 +- lib/gitlab/git/diff.rb | 2 +- lib/gitlab/git/encoding_helper.rb | 64 ------------------- lib/gitlab/git/ref.rb | 2 +- lib/gitlab/git/tree.rb | 2 +- .../gitlab/{git => }/encoding_helper_spec.rb | 4 +- spec/lib/gitlab/git/repository_spec.rb | 2 +- 12 files changed, 73 insertions(+), 75 deletions(-) create mode 100644 lib/gitlab/encoding_helper.rb delete mode 100644 lib/gitlab/git/encoding_helper.rb rename spec/lib/gitlab/{git => }/encoding_helper_spec.rb (97%) diff --git a/app/models/merge_request_diff.rb b/app/models/merge_request_diff.rb index 1c2f335f95e..99dd2130188 100644 --- a/app/models/merge_request_diff.rb +++ b/app/models/merge_request_diff.rb @@ -1,7 +1,7 @@ class MergeRequestDiff < ActiveRecord::Base include Sortable include Importable - include Gitlab::Git::EncodingHelper + include Gitlab::EncodingHelper # Prevent store of diff if commits amount more then 500 COMMITS_SAFE_SIZE = 100 diff --git a/app/validators/dynamic_path_validator.rb b/app/validators/dynamic_path_validator.rb index a9b76c7c960..27ac60637fd 100644 --- a/app/validators/dynamic_path_validator.rb +++ b/app/validators/dynamic_path_validator.rb @@ -6,7 +6,7 @@ # Values are checked for formatting and exclusion from a list of illegal path # names. class DynamicPathValidator < ActiveModel::EachValidator - extend Gitlab::Git::EncodingHelper + extend Gitlab::EncodingHelper class << self def valid_user_path?(path) diff --git a/lib/gitlab/encoding_helper.rb b/lib/gitlab/encoding_helper.rb new file mode 100644 index 00000000000..dbe28e6bb93 --- /dev/null +++ b/lib/gitlab/encoding_helper.rb @@ -0,0 +1,62 @@ +module Gitlab + module EncodingHelper + extend self + + # This threshold is carefully tweaked to prevent usage of encodings detected + # by CharlockHolmes with low confidence. If CharlockHolmes confidence is low, + # we're better off sticking with utf8 encoding. + # Reason: git diff can return strings with invalid utf8 byte sequences if it + # truncates a diff in the middle of a multibyte character. In this case + # CharlockHolmes will try to guess the encoding and will likely suggest an + # obscure encoding with low confidence. + # There is a lot more info with this merge request: + # https://gitlab.com/gitlab-org/gitlab_git/merge_requests/77#note_4754193 + ENCODING_CONFIDENCE_THRESHOLD = 40 + + def encode!(message) + return nil unless message.respond_to? :force_encoding + + # if message is utf-8 encoding, just return it + message.force_encoding("UTF-8") + return message if message.valid_encoding? + + # return message if message type is binary + detect = CharlockHolmes::EncodingDetector.detect(message) + return message.force_encoding("BINARY") if detect && detect[:type] == :binary + + # force detected encoding if we have sufficient confidence. + if detect && detect[:encoding] && detect[:confidence] > ENCODING_CONFIDENCE_THRESHOLD + message.force_encoding(detect[:encoding]) + end + + # encode and clean the bad chars + message.replace clean(message) + rescue + encoding = detect ? detect[:encoding] : "unknown" + "--broken encoding: #{encoding}" + end + + def encode_utf8(message) + detect = CharlockHolmes::EncodingDetector.detect(message) + if detect + begin + CharlockHolmes::Converter.convert(message, detect[:encoding], 'UTF-8') + rescue ArgumentError => e + Rails.logger.warn("Ignoring error converting #{detect[:encoding]} into UTF8: #{e.message}") + + '' + end + else + clean(message) + end + end + + private + + def clean(message) + message.encode("UTF-16BE", undef: :replace, invalid: :replace, replace: "") + .encode("UTF-8") + .gsub("\0".encode("UTF-8"), "") + end + end +end diff --git a/lib/gitlab/git/blame.rb b/lib/gitlab/git/blame.rb index 58193391926..66829a03c2e 100644 --- a/lib/gitlab/git/blame.rb +++ b/lib/gitlab/git/blame.rb @@ -1,7 +1,7 @@ module Gitlab module Git class Blame - include Gitlab::Git::EncodingHelper + include Gitlab::EncodingHelper attr_reader :lines, :blames diff --git a/lib/gitlab/git/blob.rb b/lib/gitlab/git/blob.rb index 6b0a66365a7..d60e607b02b 100644 --- a/lib/gitlab/git/blob.rb +++ b/lib/gitlab/git/blob.rb @@ -2,7 +2,7 @@ module Gitlab module Git class Blob include Linguist::BlobHelper - include Gitlab::Git::EncodingHelper + include Gitlab::EncodingHelper # This number is the maximum amount of data that we want to display to # the user. We load as much as we can for encoding detection diff --git a/lib/gitlab/git/commit.rb b/lib/gitlab/git/commit.rb index 297531db4cc..bb04731f08c 100644 --- a/lib/gitlab/git/commit.rb +++ b/lib/gitlab/git/commit.rb @@ -2,7 +2,7 @@ module Gitlab module Git class Commit - include Gitlab::Git::EncodingHelper + include Gitlab::EncodingHelper attr_accessor :raw_commit, :head, :refs diff --git a/lib/gitlab/git/diff.rb b/lib/gitlab/git/diff.rb index ccccca96595..0594ac8e213 100644 --- a/lib/gitlab/git/diff.rb +++ b/lib/gitlab/git/diff.rb @@ -3,7 +3,7 @@ module Gitlab module Git class Diff TimeoutError = Class.new(StandardError) - include Gitlab::Git::EncodingHelper + include Gitlab::EncodingHelper # Diff properties attr_accessor :old_path, :new_path, :a_mode, :b_mode, :diff diff --git a/lib/gitlab/git/encoding_helper.rb b/lib/gitlab/git/encoding_helper.rb deleted file mode 100644 index f918074cb14..00000000000 --- a/lib/gitlab/git/encoding_helper.rb +++ /dev/null @@ -1,64 +0,0 @@ -module Gitlab - module Git - module EncodingHelper - extend self - - # This threshold is carefully tweaked to prevent usage of encodings detected - # by CharlockHolmes with low confidence. If CharlockHolmes confidence is low, - # we're better off sticking with utf8 encoding. - # Reason: git diff can return strings with invalid utf8 byte sequences if it - # truncates a diff in the middle of a multibyte character. In this case - # CharlockHolmes will try to guess the encoding and will likely suggest an - # obscure encoding with low confidence. - # There is a lot more info with this merge request: - # https://gitlab.com/gitlab-org/gitlab_git/merge_requests/77#note_4754193 - ENCODING_CONFIDENCE_THRESHOLD = 40 - - def encode!(message) - return nil unless message.respond_to? :force_encoding - - # if message is utf-8 encoding, just return it - message.force_encoding("UTF-8") - return message if message.valid_encoding? - - # return message if message type is binary - detect = CharlockHolmes::EncodingDetector.detect(message) - return message.force_encoding("BINARY") if detect && detect[:type] == :binary - - # force detected encoding if we have sufficient confidence. - if detect && detect[:encoding] && detect[:confidence] > ENCODING_CONFIDENCE_THRESHOLD - message.force_encoding(detect[:encoding]) - end - - # encode and clean the bad chars - message.replace clean(message) - rescue - encoding = detect ? detect[:encoding] : "unknown" - "--broken encoding: #{encoding}" - end - - def encode_utf8(message) - detect = CharlockHolmes::EncodingDetector.detect(message) - if detect - begin - CharlockHolmes::Converter.convert(message, detect[:encoding], 'UTF-8') - rescue ArgumentError => e - Rails.logger.warn("Ignoring error converting #{detect[:encoding]} into UTF8: #{e.message}") - - '' - end - else - clean(message) - end - end - - private - - def clean(message) - message.encode("UTF-16BE", undef: :replace, invalid: :replace, replace: "") - .encode("UTF-8") - .gsub("\0".encode("UTF-8"), "") - end - end - end -end diff --git a/lib/gitlab/git/ref.rb b/lib/gitlab/git/ref.rb index 37ef6836742..ebf7393dc61 100644 --- a/lib/gitlab/git/ref.rb +++ b/lib/gitlab/git/ref.rb @@ -1,7 +1,7 @@ module Gitlab module Git class Ref - include Gitlab::Git::EncodingHelper + include Gitlab::EncodingHelper # Branch or tag name # without "refs/tags|heads" prefix diff --git a/lib/gitlab/git/tree.rb b/lib/gitlab/git/tree.rb index d41256d9a84..b9afa05c819 100644 --- a/lib/gitlab/git/tree.rb +++ b/lib/gitlab/git/tree.rb @@ -1,7 +1,7 @@ module Gitlab module Git class Tree - include Gitlab::Git::EncodingHelper + include Gitlab::EncodingHelper attr_accessor :id, :root_id, :name, :path, :type, :mode, :commit_id, :submodule_url diff --git a/spec/lib/gitlab/git/encoding_helper_spec.rb b/spec/lib/gitlab/encoding_helper_spec.rb similarity index 97% rename from spec/lib/gitlab/git/encoding_helper_spec.rb rename to spec/lib/gitlab/encoding_helper_spec.rb index 48fc817d857..1482ef7132d 100644 --- a/spec/lib/gitlab/git/encoding_helper_spec.rb +++ b/spec/lib/gitlab/encoding_helper_spec.rb @@ -1,7 +1,7 @@ require "spec_helper" -describe Gitlab::Git::EncodingHelper do - let(:ext_class) { Class.new { extend Gitlab::Git::EncodingHelper } } +describe Gitlab::EncodingHelper do + let(:ext_class) { Class.new { extend Gitlab::EncodingHelper } } let(:binary_string) { File.read(Rails.root + "spec/fixtures/dk.png") } describe '#encode!' do diff --git a/spec/lib/gitlab/git/repository_spec.rb b/spec/lib/gitlab/git/repository_spec.rb index 9d0e95d5b19..26215381cc4 100644 --- a/spec/lib/gitlab/git/repository_spec.rb +++ b/spec/lib/gitlab/git/repository_spec.rb @@ -1,7 +1,7 @@ require "spec_helper" describe Gitlab::Git::Repository, seed_helper: true do - include Gitlab::Git::EncodingHelper + include Gitlab::EncodingHelper let(:repository) { Gitlab::Git::Repository.new('default', TEST_REPO_PATH) }