2018-11-09 13:39:43 -05:00
|
|
|
# frozen_string_literal: true
|
|
|
|
|
2017-01-04 13:43:06 -05:00
|
|
|
module Gitlab
|
|
|
|
module Git
|
|
|
|
class Blob
|
2018-08-03 09:24:26 -04:00
|
|
|
include Gitlab::BlobHelper
|
2017-06-01 17:21:14 -04:00
|
|
|
include Gitlab::EncodingHelper
|
2018-10-30 09:37:40 -04:00
|
|
|
extend Gitlab::Git::WrapsGitalyErrors
|
2017-01-04 13:43:06 -05:00
|
|
|
|
|
|
|
# This number is the maximum amount of data that we want to display to
|
2018-08-03 09:24:26 -04:00
|
|
|
# the user. We load as much as we can for encoding detection and LFS
|
|
|
|
# pointer parsing. All other cases where we need full blob data should
|
|
|
|
# use load_all_data!.
|
2017-04-13 12:49:24 -04:00
|
|
|
MAX_DATA_DISPLAY_SIZE = 10.megabytes
|
2017-01-04 13:43:06 -05:00
|
|
|
|
2017-08-24 21:30:12 -04:00
|
|
|
# These limits are used as a heuristic to ignore files which can't be LFS
|
|
|
|
# pointers. The format of these is described in
|
|
|
|
# https://github.com/git-lfs/git-lfs/blob/master/docs/spec.md#the-pointer
|
|
|
|
LFS_POINTER_MIN_SIZE = 120.bytes
|
|
|
|
LFS_POINTER_MAX_SIZE = 200.bytes
|
|
|
|
|
2017-01-04 13:43:06 -05:00
|
|
|
attr_accessor :name, :path, :size, :data, :mode, :id, :commit_id, :loaded_size, :binary
|
|
|
|
|
|
|
|
class << self
|
2018-06-22 07:58:06 -04:00
|
|
|
def find(repository, sha, path, limit: MAX_DATA_DISPLAY_SIZE)
|
2019-03-02 00:15:38 -05:00
|
|
|
tree_entry(repository, sha, path, limit)
|
|
|
|
end
|
|
|
|
|
|
|
|
def tree_entry(repository, sha, path, limit)
|
2018-06-22 07:58:06 -04:00
|
|
|
return unless path
|
|
|
|
|
|
|
|
path = path.sub(%r{\A/*}, '')
|
|
|
|
path = '/' if path.empty?
|
|
|
|
name = File.basename(path)
|
|
|
|
|
|
|
|
# Gitaly will think that setting the limit to 0 means unlimited, while
|
|
|
|
# the client might only need the metadata and thus set the limit to 0.
|
|
|
|
# In this method we'll then set the limit to 1, but clear the byte of data
|
|
|
|
# that we got back so for the outside world it looks like the limit was
|
|
|
|
# actually 0.
|
|
|
|
req_limit = limit == 0 ? 1 : limit
|
|
|
|
|
|
|
|
entry = Gitlab::GitalyClient::CommitService.new(repository).tree_entry(sha, path, req_limit)
|
|
|
|
return unless entry
|
|
|
|
|
|
|
|
entry.data = "" if limit == 0
|
|
|
|
|
|
|
|
case entry.type
|
|
|
|
when :COMMIT
|
|
|
|
new(id: entry.oid, name: name, size: 0, data: '', path: path, commit_id: sha)
|
|
|
|
when :BLOB
|
|
|
|
new(id: entry.oid, name: name, size: entry.size, data: entry.data.dup, mode: entry.mode.to_s(8),
|
|
|
|
path: path, commit_id: sha, binary: binary?(entry.data))
|
2017-01-04 13:43:06 -05:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
def raw(repository, sha)
|
2018-07-09 06:02:02 -04:00
|
|
|
repository.gitaly_blob_client.get_blob(oid: sha, limit: MAX_DATA_DISPLAY_SIZE)
|
2017-07-07 10:45:52 -04:00
|
|
|
end
|
2017-01-04 13:43:06 -05:00
|
|
|
|
2017-08-01 07:49:57 -04:00
|
|
|
# Returns an array of Blob instances, specified in blob_references as
|
2017-08-07 10:26:50 -04:00
|
|
|
# [[commit_sha, path], [commit_sha, path], ...]. If blob_size_limit < 0 then the
|
|
|
|
# full blob contents are returned. If blob_size_limit >= 0 then each blob will
|
2017-08-01 07:49:57 -04:00
|
|
|
# contain no more than limit bytes in its data attribute.
|
2017-08-15 13:44:37 -04:00
|
|
|
#
|
2017-08-01 07:49:57 -04:00
|
|
|
# Keep in mind that this method may allocate a lot of memory. It is up
|
2017-08-07 10:26:50 -04:00
|
|
|
# to the caller to limit the number of blobs and blob_size_limit.
|
2017-08-01 07:49:57 -04:00
|
|
|
#
|
2017-12-21 09:05:35 -05:00
|
|
|
def batch(repository, blob_references, blob_size_limit: MAX_DATA_DISPLAY_SIZE)
|
2018-07-11 06:59:15 -04:00
|
|
|
repository.gitaly_blob_client.get_blobs(blob_references, blob_size_limit).to_a
|
2017-08-01 07:49:57 -04:00
|
|
|
end
|
|
|
|
|
2018-05-09 14:20:28 -04:00
|
|
|
# Returns an array of Blob instances just with the metadata, that means
|
|
|
|
# the data attribute has no content.
|
|
|
|
def batch_metadata(repository, blob_references)
|
|
|
|
batch(repository, blob_references, blob_size_limit: 0)
|
|
|
|
end
|
|
|
|
|
2017-08-24 21:30:12 -04:00
|
|
|
# Find LFS blobs given an array of sha ids
|
|
|
|
# Returns array of Gitlab::Git::Blob
|
|
|
|
# Does not guarantee blob data will be set
|
|
|
|
def batch_lfs_pointers(repository, blob_ids)
|
2018-10-30 09:37:40 -04:00
|
|
|
wrapped_gitaly_errors do
|
2018-07-11 06:59:15 -04:00
|
|
|
repository.gitaly_blob_client.batch_lfs_pointers(blob_ids.to_a)
|
2018-01-17 08:21:46 -05:00
|
|
|
end
|
2017-08-24 21:30:12 -04:00
|
|
|
end
|
|
|
|
|
2017-09-04 15:32:57 -04:00
|
|
|
def binary?(data)
|
2017-09-05 13:16:08 -04:00
|
|
|
EncodingHelper.detect_libgit2_binary?(data)
|
2017-09-04 15:32:57 -04:00
|
|
|
end
|
|
|
|
|
2017-08-24 21:30:12 -04:00
|
|
|
def size_could_be_lfs?(size)
|
|
|
|
size.between?(LFS_POINTER_MIN_SIZE, LFS_POINTER_MAX_SIZE)
|
|
|
|
end
|
2017-01-04 13:43:06 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def initialize(options)
|
|
|
|
%w(id name path size data mode commit_id binary).each do |key|
|
2017-08-10 12:39:26 -04:00
|
|
|
self.__send__("#{key}=", options[key.to_sym]) # rubocop:disable GitlabSecurity/PublicSend
|
2017-01-04 13:43:06 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
# Retain the actual size before it is encoded
|
|
|
|
@loaded_size = @data.bytesize if @data
|
2018-02-28 17:22:44 -05:00
|
|
|
@loaded_all_data = @loaded_size == size
|
2017-01-04 13:43:06 -05:00
|
|
|
end
|
|
|
|
|
2018-12-13 12:49:05 -05:00
|
|
|
def binary_in_repo?
|
2017-01-04 13:43:06 -05:00
|
|
|
@binary.nil? ? super : @binary == true
|
|
|
|
end
|
|
|
|
|
|
|
|
def data
|
|
|
|
encode! @data
|
|
|
|
end
|
|
|
|
|
|
|
|
# Load all blob data (not just the first MAX_DATA_DISPLAY_SIZE bytes) into
|
|
|
|
# memory as a Ruby string.
|
|
|
|
def load_all_data!(repository)
|
|
|
|
return if @data == '' # don't mess with submodule blobs
|
|
|
|
|
2018-02-28 17:22:44 -05:00
|
|
|
# Even if we return early, recalculate wether this blob is binary in
|
|
|
|
# case a blob was initialized as text but the full data isn't
|
|
|
|
@binary = nil
|
|
|
|
|
|
|
|
return if @loaded_all_data
|
|
|
|
|
2018-07-09 06:02:02 -04:00
|
|
|
@data = repository.gitaly_blob_client.get_blob(oid: id, limit: -1).data
|
2017-01-04 13:43:06 -05:00
|
|
|
@loaded_all_data = true
|
|
|
|
@loaded_size = @data.bytesize
|
|
|
|
end
|
|
|
|
|
|
|
|
def name
|
|
|
|
encode! @name
|
|
|
|
end
|
|
|
|
|
2017-07-04 15:10:34 -04:00
|
|
|
def path
|
|
|
|
encode! @path
|
|
|
|
end
|
|
|
|
|
2017-05-02 18:45:50 -04:00
|
|
|
def truncated?
|
|
|
|
size && (size > loaded_size)
|
|
|
|
end
|
|
|
|
|
2017-01-04 13:43:06 -05:00
|
|
|
# Valid LFS object pointer is a text file consisting of
|
|
|
|
# version
|
|
|
|
# oid
|
|
|
|
# size
|
|
|
|
# see https://github.com/github/git-lfs/blob/v1.1.0/docs/spec.md#the-pointer
|
|
|
|
def lfs_pointer?
|
2017-08-24 21:30:12 -04:00
|
|
|
self.class.size_could_be_lfs?(size) && has_lfs_version_key? && lfs_oid.present? && lfs_size.present?
|
2017-01-04 13:43:06 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
def lfs_oid
|
|
|
|
if has_lfs_version_key?
|
|
|
|
oid = data.match(/(?<=sha256:)([0-9a-f]{64})/)
|
|
|
|
return oid[1] if oid
|
|
|
|
end
|
|
|
|
|
|
|
|
nil
|
|
|
|
end
|
|
|
|
|
|
|
|
def lfs_size
|
|
|
|
if has_lfs_version_key?
|
|
|
|
size = data.match(/(?<=size )([0-9]+)/)
|
2017-04-13 12:49:24 -04:00
|
|
|
return size[1].to_i if size
|
2017-01-04 13:43:06 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
nil
|
|
|
|
end
|
|
|
|
|
2017-05-02 18:45:50 -04:00
|
|
|
def external_storage
|
|
|
|
return unless lfs_pointer?
|
|
|
|
|
|
|
|
:lfs
|
2017-01-04 13:43:06 -05:00
|
|
|
end
|
|
|
|
|
2017-05-02 18:45:50 -04:00
|
|
|
alias_method :external_size, :lfs_size
|
|
|
|
|
2017-01-04 13:43:06 -05:00
|
|
|
private
|
|
|
|
|
|
|
|
def has_lfs_version_key?
|
2018-12-13 12:49:05 -05:00
|
|
|
!empty? && text_in_repo? && data.start_with?("version https://git-lfs.github.com/spec")
|
2017-01-04 13:43:06 -05:00
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
2019-03-02 00:15:38 -05:00
|
|
|
|
|
|
|
Gitlab::Git::Blob.singleton_class.prepend Gitlab::Git::RuggedImpl::Blob::ClassMethods
|