gitlab_git 10.0.0 → 10.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 31c6a37123aa6b3d2a4e5a51508fd0bb46f3fa65
-  data.tar.gz: 1f9dd6e2548aca96d1b367435e131c78b1c12679
+  metadata.gz: a2d857c8e1f6c851a7fa699ef3279d936c999c27
+  data.tar.gz: ec384017aa519ce625cc9b05f13725450dd2dabb
 SHA512:
-  metadata.gz: 1852e5944d7ec3a02a0c745aa09d381f72cd9233b7bbb92d1ab38582e346ba900b75faea720aa0cdf51c3b8c86e7b1b94c5a8d69e52f105cd1e2ec35de51d7c4
-  data.tar.gz: 9ea1b801930d276a3de2cbf0ff3ad7e425a333d744c6d18ff34f769d00ff8c4d63a7916feef21632f45a87f2678e3c59c2d1539de79afc7edd64a1c7ccb35441
+  metadata.gz: 38cba0dc0b5db525ac2967133ed0ec439f41d10d153e3dc5608e6d796a4c955d173db00b63e2907e0fcc5620eaeedbef2dabd48a29af506c06090c54b22c9001
+  data.tar.gz: 9aff7f02f2ccf1cf4df3ca23c31ae5b55de7ef204c82ec075087420f7cdeae7924f4d88b89c19a10433fa69339557620e67cb42305b76dec2efb2e8eff49ae5e

data/VERSION

@@ -1 +1 @@
-10.0.0
+10.0.1

data/lib/gitlab_git/encoding_helper.rb

@@ -1,6 +1,17 @@
 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
 
@@ -12,8 +23,8 @@ module EncodingHelper
     detect = CharlockHolmes::EncodingDetector.detect(message)
     return message.force_encoding("BINARY") if detect && detect[:type] == :binary
 
-    # encoding message to detect encoding
-    if detect && detect[:encoding]
+    # force detected encoding if we have sufficient confidence.
+    if detect && detect[:encoding] && detect[:confidence] > ENCODING_CONFIDENCE_THRESHOLD
       message.force_encoding(detect[:encoding])
     end
 

data/lib/gitlab_git/repository.rb

@@ -7,6 +7,7 @@ require "rubygems/package"
 module Gitlab
   module Git
     class Repository
+      extend Forwardable
       include Gitlab::Git::Popen
 
       SEARCH_CONTEXT_LINES = 3
@@ -24,6 +25,9 @@ module Gitlab
       # Rugged repo object
       attr_reader :rugged
 
+      # Define a delegator for the rugged attributes
+      def_delegator :rugged, :attributes
+
       # 'path' must be the path to a _bare_ git repository, e.g.
       # /path/to/my-repo.git
       def initialize(path)
@@ -948,6 +952,12 @@ module Gitlab
         File.write(info_attributes_path, gitattributes_content)
       end
 
+      # Checks if the blob should be diffable according to its attributes
+      def diffable?(blob)
+        blob_attributes = attributes(blob.path).to_h
+        blob_attributes.fetch('diff', blob.text?)
+      end
+
       private
 
       # Get the content of a blob for a given commit.  If the blob is a commit

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gitlab_git
 version: !ruby/object:Gem::Version
-  version: 10.0.0
+  version: 10.0.1
 platform: ruby
 authors:
 - Dmitriy Zaporozhets
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-03-17 00:00:00.000000000 Z
+date: 2016-04-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: github-linguist
@@ -111,9 +111,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 2.4.8
 signing_key: 
 specification_version: 4
 summary: Gitlab::Git library
 test_files: []
-has_rdoc: