1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
|
module Gitlab
module Git
class Blob
include Linguist::BlobHelper
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
# (Linguist) and LFS pointer parsing. All other cases where we need full
# blob data should use load_all_data!.
MAX_DATA_DISPLAY_SIZE = 10.megabytes
attr_accessor :name, :path, :size, :data, :mode, :id, :commit_id, :loaded_size, :binary
class << self
def find(repository, sha, path)
commit = repository.lookup(sha)
root_tree = commit.tree
blob_entry = find_entry_by_path(repository, root_tree.oid, path)
return nil unless blob_entry
if blob_entry[:type] == :commit
submodule_blob(blob_entry, path, sha)
else
blob = repository.lookup(blob_entry[:oid])
if blob
new(
id: blob.oid,
name: blob_entry[:name],
size: blob.size,
data: blob.content(MAX_DATA_DISPLAY_SIZE),
mode: blob_entry[:filemode].to_s(8),
path: path,
commit_id: sha,
binary: blob.binary?
)
end
end
end
def raw(repository, sha)
blob = repository.lookup(sha)
new(
id: blob.oid,
size: blob.size,
data: blob.content(MAX_DATA_DISPLAY_SIZE),
binary: blob.binary?
)
end
# Recursive search of blob id by path
#
# Ex.
# blog/ # oid: 1a
# app/ # oid: 2a
# models/ # oid: 3a
# file.rb # oid: 4a
#
#
# Blob.find_entry_by_path(repo, '1a', 'app/file.rb') # => '4a'
#
def find_entry_by_path(repository, root_id, path)
root_tree = repository.lookup(root_id)
# Strip leading slashes
path[/^\/*/] = ''
path_arr = path.split('/')
entry = root_tree.find do |entry|
entry[:name] == path_arr[0]
end
return nil unless entry
if path_arr.size > 1
return nil unless entry[:type] == :tree
path_arr.shift
find_entry_by_path(repository, entry[:oid], path_arr.join('/'))
else
[:blob, :commit].include?(entry[:type]) ? entry : nil
end
end
def submodule_blob(blob_entry, path, sha)
new(
id: blob_entry[:oid],
name: blob_entry[:name],
size: 0,
data: '',
path: path,
commit_id: sha
)
end
end
def initialize(options)
%w(id name path size data mode commit_id binary).each do |key|
self.send("#{key}=", options[key.to_sym])
end
@loaded_all_data = false
# Retain the actual size before it is encoded
@loaded_size = @data.bytesize if @data
end
def binary?
@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
return @data if @loaded_all_data
@loaded_all_data = true
@data = repository.lookup(id).content
@loaded_size = @data.bytesize
@binary = nil
end
def name
encode! @name
end
def truncated?
size && (size > loaded_size)
end
# 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?
has_lfs_version_key? && lfs_oid.present? && lfs_size.present?
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]+)/)
return size[1].to_i if size
end
nil
end
def external_storage
return unless lfs_pointer?
:lfs
end
alias_method :external_size, :lfs_size
private
def has_lfs_version_key?
!empty? && text? && data.start_with?("version https://git-lfs.github.com/spec")
end
end
end
end
|
