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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
|
require_relative 'encoding_helper'
require_relative 'path_helper'
module Gitlab
module Git
class Blob
include Linguist::BlobHelper
include Gitlab::Git::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 = 10485760
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
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)
Blob.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)
Blob.new(
id: blob_entry[:oid],
name: blob_entry[:name],
data: '',
path: path,
commit_id: sha,
)
end
# Commit file in repository and return commit sha
#
# options should contain next structure:
# file: {
# content: 'Lorem ipsum...',
# path: 'documents/story.txt',
# update: true
# },
# author: {
# email: 'user@example.com',
# name: 'Test User',
# time: Time.now
# },
# committer: {
# email: 'user@example.com',
# name: 'Test User',
# time: Time.now
# },
# commit: {
# message: 'Wow such commit',
# branch: 'master',
# update_ref: false
# }
#
# rubocop:disable Metrics/AbcSize
# rubocop:disable Metrics/CyclomaticComplexity
# rubocop:disable Metrics/PerceivedComplexity
def commit(repository, options, action = :add)
file = options[:file]
update = file[:update].nil? ? true : file[:update]
author = options[:author]
committer = options[:committer]
commit = options[:commit]
repo = repository.rugged
ref = commit[:branch]
update_ref = commit[:update_ref].nil? ? true : commit[:update_ref]
parents = []
mode = 0o100644
unless ref.start_with?('refs/')
ref = 'refs/heads/' + ref
end
path_name = PathHelper.normalize_path(file[:path])
# Abort if any invalid characters remain (e.g. ../foo)
raise Repository::InvalidBlobName.new("Invalid path") if path_name.each_filename.to_a.include?('..')
filename = path_name.to_s
index = repo.index
unless repo.empty?
rugged_ref = repo.references[ref]
raise Repository::InvalidRef.new("Invalid branch name") unless rugged_ref
last_commit = rugged_ref.target
index.read_tree(last_commit.tree)
parents = [last_commit]
end
if action == :remove
index.remove(filename)
else
file_entry = index.get(filename)
if action == :rename
old_path_name = PathHelper.normalize_path(file[:previous_path])
old_filename = old_path_name.to_s
file_entry = index.get(old_filename)
index.remove(old_filename) unless file_entry.blank?
end
if file_entry
raise Repository::InvalidBlobName.new("Filename already exists; update not allowed") unless update
# Preserve the current file mode if one is available
mode = file_entry[:mode] if file_entry[:mode]
end
content = file[:content]
detect = CharlockHolmes::EncodingDetector.new.detect(content) if content
unless detect && detect[:type] == :binary
# When writing to the repo directly as we are doing here,
# the `core.autocrlf` config isn't taken into account.
content.gsub!("\r\n", "\n") if repository.autocrlf
end
oid = repo.write(content, :blob)
index.add(path: filename, oid: oid, mode: mode)
end
opts = {}
opts[:tree] = index.write_tree(repo)
opts[:author] = author
opts[:committer] = committer
opts[:message] = commit[:message]
opts[:parents] = parents
opts[:update_ref] = ref if update_ref
Rugged::Commit.create(repo, opts)
end
# rubocop:enable Metrics/AbcSize
# rubocop:enable Metrics/CyclomaticComplexity
# rubocop:enable Metrics/PerceivedComplexity
# Remove file from repository and return commit sha
#
# options should contain next structure:
# file: {
# path: 'documents/story.txt'
# },
# author: {
# email: 'user@example.com',
# name: 'Test User',
# time: Time.now
# },
# committer: {
# email: 'user@example.com',
# name: 'Test User',
# time: Time.now
# },
# commit: {
# message: 'Remove FILENAME',
# branch: 'master'
# }
#
def remove(repository, options)
commit(repository, options, :remove)
end
# Rename file from repository and return commit sha
#
# options should contain next structure:
# file: {
# previous_path: 'documents/old_story.txt'
# path: 'documents/story.txt'
# content: 'Lorem ipsum...',
# update: true
# },
# author: {
# email: 'user@example.com',
# name: 'Test User',
# time: Time.now
# },
# committer: {
# email: 'user@example.com',
# name: 'Test User',
# time: Time.now
# },
# commit: {
# message: 'Rename FILENAME',
# branch: 'master'
# }
#
def rename(repository, options)
commit(repository, options, :rename)
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 empty?
!data || data == ''
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
end
def name
encode! @name
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] if size
end
nil
end
def truncated?
size && (size > loaded_size)
end
private
def has_lfs_version_key?
!empty? && text? && data.start_with?("version https://git-lfs.github.com/spec")
end
end
end
end
|