merge_request_diff.rb 6.23 KB
Newer Older
1
class MergeRequestDiff < ActiveRecord::Base
2
  include Sortable
3
  include Importable
James Lopez's avatar
James Lopez committed
4
  include EncodingHelper
5

6
  # Prevent store of diff if commits amount more then 500
7
  COMMITS_SAFE_SIZE = 100
8 9 10

  belongs_to :merge_request

11
  delegate :source_branch_sha, :target_branch_sha, :target_branch, :source_branch, to: :merge_request, prefix: nil
12 13 14

  state_machine :state, initial: :empty do
    state :collected
15 16 17
    state :overflow
    # Deprecated states: these are no longer used but these values may still occur
    # in the database.
18 19 20 21 22 23 24 25 26
    state :timeout
    state :overflow_commits_safe_size
    state :overflow_diff_files_limit
    state :overflow_diff_lines_limit
  end

  serialize :st_commits
  serialize :st_diffs

27
  after_create :reload_content, unless: :importing?
28
  after_save :keep_around_commits, unless: :importing?
29 30 31 32 33 34

  def reload_content
    reload_commits
    reload_diffs
  end

35 36
  def size
    real_size.presence || diffs.size
37 38
  end

39 40 41 42
  def diffs(options={})
    if options[:ignore_whitespace_change]
      @diffs_no_whitespace ||= begin
        compare = Gitlab::Git::Compare.new(
43
          repository.raw_repository,
44 45
          self.start_commit_sha || self.target_branch_sha,
          self.head_commit_sha || self.source_branch_sha,
46 47 48 49
        )
        compare.diffs(options)
      end
    else
50
      @diffs ||= {}
51
      @diffs[options] ||= load_diffs(st_diffs, options)
52
    end
53 54
  end

55 56 57 58 59 60 61 62
  def commits
    @commits ||= load_commits(st_commits || [])
  end

  def last_commit
    commits.first
  end

63 64 65 66
  def first_commit
    commits.last
  end

67
  def base_commit
68
    return unless self.base_commit_sha
69

70
    project.commit(self.base_commit_sha)
71 72
  end

73 74 75
  def start_commit
    return unless self.start_commit_sha

76
    project.commit(self.start_commit_sha)
77 78 79 80 81
  end

  def head_commit
    return last_commit unless self.head_commit_sha

82
    project.commit(self.head_commit_sha)
83 84
  end

85 86 87 88 89
  def compare
    @compare ||=
      begin
        # Update ref for merge request
        merge_request.fetch_ref
90

91
        Gitlab::Git::Compare.new(
92
          repository.raw_repository,
93 94 95 96
          self.target_branch_sha,
          self.source_branch_sha
        )
      end
97 98
  end

99
  private
100 101 102 103

  # Collect array of Git::Commit objects
  # between target and source branches
  def unmerged_commits
104
    commits = compare.commits
105 106

    if commits.present?
Sean McGivern's avatar
Sean McGivern committed
107
      commits = Commit.decorate(commits, merge_request.source_project).reverse
108 109 110 111 112
    end

    commits
  end

113 114 115 116 117 118 119 120
  def dump_commits(commits)
    commits.map(&:to_hash)
  end

  def load_commits(array)
    array.map { |hash| Commit.new(Gitlab::Git::Commit.new(hash), merge_request.source_project) }
  end

121 122 123
  # Reload all commits related to current merge request from repo
  # and save it as array of hashes in st_commits db field
  def reload_commits
124 125
    new_attributes = {}

126 127 128
    commit_objects = unmerged_commits

    if commit_objects.present?
129
      new_attributes[:st_commits] = dump_commits(commit_objects)
130 131
    end

132
    update_columns_serialized(new_attributes)
133 134
  end

135 136 137 138 139 140 141 142 143 144 145 146 147 148
  # Collect array of Git::Diff objects
  # between target and source branches
  def unmerged_diffs
    compare.diffs(Commit.max_diff_options)
  end

  def dump_diffs(diffs)
    if diffs.respond_to?(:map)
      diffs.map(&:to_hash)
    end
  end

  def load_diffs(raw, options)
    if raw.respond_to?(:each)
149
      if paths = options[:paths]
150
        raw = raw.select do |diff|
151
          paths.include?(diff[:old_path]) || paths.include?(diff[:new_path])
152 153 154
        end
      end

155 156 157 158 159 160
      Gitlab::Git::DiffCollection.new(raw, options)
    else
      Gitlab::Git::DiffCollection.new([])
    end
  end

161 162 163
  # Reload diffs between branches related to current merge request from repo
  # and save it as array of hashes in st_diffs db field
  def reload_diffs
164
    new_attributes = {}
165 166 167
    new_diffs = []

    if commits.size.zero?
168
      new_attributes[:state] = :empty
169
    else
170
      diff_collection = unmerged_diffs
171

172 173 174
      if diff_collection.overflow?
        # Set our state to 'overflow' to make the #empty? and #collected?
        # methods (generated by StateMachine) return false.
175
        new_attributes[:state] = :overflow
176 177
      end

178
      new_attributes[:real_size] = diff_collection.real_size
179

180 181
      if diff_collection.any?
        new_diffs = dump_diffs(diff_collection)
182
        new_attributes[:state] = :collected
183
      end
184
    end
185

186
    new_attributes[:st_diffs] = new_diffs
187

188 189 190
    new_attributes[:start_commit_sha] = self.target_branch_sha
    new_attributes[:head_commit_sha] = self.source_branch_sha
    new_attributes[:base_commit_sha] = branch_base_sha
191

192
    update_columns_serialized(new_attributes)
193 194

    keep_around_commits
195 196
  end

197 198
  def project
    merge_request.target_project
199 200 201
  end

  def repository
202
    project.repository
203
  end
204

205 206
  def branch_base_commit
    return unless self.source_branch_sha && self.target_branch_sha
207

208
    project.merge_base_commit(self.source_branch_sha, self.target_branch_sha)
209 210
  end

211 212
  def branch_base_sha
    branch_base_commit.try(:sha)
213 214
  end

James Lopez's avatar
James Lopez committed
215 216 217 218 219 220 221 222
  def utf8_st_diffs
    st_diffs.map do |diff|
      diff.each do |k, v|
        diff[k] = encode_utf8(v) if v.respond_to?(:encoding)
      end
    end
  end

223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
  #
  # #save or #update_attributes providing changes on serialized attributes do a lot of
  # serialization and deserialization calls resulting in bad performance.
  # Using #update_columns solves the problem with just one YAML.dump per serialized attribute that we provide.
  # As a tradeoff we need to reload the current instance to properly manage time objects on those serialized
  # attributes. So to keep the same behaviour as the attribute assignment we reload the instance.
  # The difference is in the usage of
  # #write_attribute= (#update_attributes) and #raw_write_attribute= (#update_columns)
  #
  # Ex:
  #
  #   new_attributes[:st_commits].first.slice(:committed_date)
  #   => {:committed_date=>2014-02-27 11:01:38 +0200}
  #   YAML.load(YAML.dump(new_attributes[:st_commits].first.slice(:committed_date)))
  #   => {:committed_date=>2014-02-27 10:01:38 +0100}
  #
  def update_columns_serialized(new_attributes)
    return unless new_attributes.any?

    update_columns(new_attributes.merge(updated_at: current_time_from_proper_timezone))
    reload
  end
245

246
  def keep_around_commits
247 248 249
    repository.keep_around(target_branch_sha)
    repository.keep_around(source_branch_sha)
    repository.keep_around(branch_base_sha)
250
  end
251
end