Class: GithubRepoStatistics

Inherits:
Object
  • Object
show all
Defined in:
lib/github_repo_statistics.rb,
lib/github_repo_statistics/version.rb,
lib/github_repo_statistics/github_repo_statistics.rb

Defined Under Namespace

Classes: Error

Constant Summary collapse

VERSION = 
'2.3.26'

Instance Method Summary collapse

Constructor Details

#initialize(directory_path:, duration_in_days:, begin_time:, debug: nil, steps: 1) ⇒ GithubRepoStatistics

Returns a new instance of GithubRepoStatistics.



8
9
10
11
12
13
14
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 8

def initialize(directory_path:, duration_in_days:, begin_time:, debug: nil, steps: 1)
  @directory_path = directory_path
  @duration_in_days = duration_in_days
  @begin_time = begin_time
  @debug = debug
  @steps = steps
end

Instance Method Details

#analyze_changed_files(uniq_code_files_with_changes:, start_date:, end_date:, branch: DEFAULT_BRANCH) ⇒ Object 



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
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 202

def analyze_changed_files(uniq_code_files_with_changes:, start_date:, end_date:, branch: DEFAULT_BRANCH)
  all_teams = []
  cross_teams_count = 0
  single_ownership_teams_count = 0
  files_changed_by_many_teams = 0
  total_changes = 0
  file_team_map = {}
  uniq_code_files_with_changes.each do |file|
    filename = File.basename(file)
    commit_count = git_commit_count(file:, start_date:, end_date:, branch:).to_i
    git_log = git_commit_info(file:, start_date:, end_date:, branch:).split("\n")
    
    if EXCLUDED_PRS
      excluded_prs = EXCLUDED_PRS.split(',')
      git_log = git_log.reject { |c| excluded_prs.any? { |pr| c.include?(pr) } }
    end

    if EXCLUDED_CONTRIBUTOR_NAMES
      excluded_contributor_names = EXCLUDED_CONTRIBUTOR_NAMES.split(',')
      git_log = git_log.reject { |c| excluded_contributor_names.any? { |cr| c.include?(cr) } }
    end
    
    
    prs = git_log.map do |pr|
      match = pr.match(/#(\d+)/)
      match[0] if match
    end.uniq

    teams = git_log.map do |team|
      team.match(/#{TEAM_REGEX}/)[0].upcase
    end.reject { |e| EXCLUSIONS&.include?(e) }

    teams = calculate_percentile(teams, PERCENTILE.to_i)

    total_changes += commit_count
    all_teams << teams

    if teams.count > 1
      files_changed_by_many_teams += 1
      file_team_map.merge!(file.to_s => [teams, prs, commit_count])
      cross_teams_count += teams.count
    else
      single_ownership_teams_count += 1
    end

    puts "\n#{filename} [#{commit_count}]:#{teams}\n" if @debug
  end
  [all_teams, cross_teams_count, single_ownership_teams_count, files_changed_by_many_teams, total_changes,
   file_team_map]
end

#calculate_percentile(arr, percentile) ⇒ Object 



253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 253

def calculate_percentile(arr, percentile)
  # Count occurrences of each unique element
  counts = arr.each_with_object(Hash.new(0)) { |item, hash| hash[item] += 1 }

  # Sort elements by their counts in descending order
  sorted_counts = counts.sort_by { |_k, v| -v }.to_h

  # Calculate the cut-off for the percentile
  total_count = arr.size
  cutoff = total_count * (percentile / 100.0)

  # Select elements that meet the percentile criteria
  selected_elements = []
  cumulative_count = 0

  sorted_counts.each do |item, count|
    cumulative_count += count
    selected_elements << item
    break if cumulative_count >= cutoff
  end

  selected_elements
end

#contribution_message ⇒ Object 



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
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 286

def contribution_message
  duration_in_days = @duration_in_days.to_i
  start_date = @begin_time.to_time.to_i - duration_in_days * 86_400
  end_date = @begin_time.to_time.to_i
  git_ls = git_files(directory_path: @directory_path)
  file_count = filter_existing_code_files(git_ls.split, start_date, end_date).count
  all_files_with_changes = files_with_changes(directory_path: @directory_path, start_date:, end_date:).split.sort
  code_files_with_changes = filter_existing_code_files(all_files_with_changes, start_date, end_date)
  uniq_code_files_with_changes = code_files_with_changes.uniq

  all_teams, cross_teams_count, single_ownership_teams_count, files_changed_by_many_teams, total_changes, file_team_map = analyze_changed_files(
    uniq_code_files_with_changes:, start_date:, end_date:
  )
  occurrences = all_teams.flatten.compact.tally
  sorted_occurrences = occurrences.sort_by { |element, count| [-count, element] }
  contributors = Hash[sorted_occurrences]
  churn_count = file_team_map.values.map(&:last).sum
  hotspot_changes_percentage = ((churn_count.to_f / total_changes) * 100).round(2)
  # Filter files based on extension, existence and size
  filtered_files = filter_files(file_team_map:)
  filtered_top_touched_files = filtered_files.sort_by { |element, count| [-count.last, element] }

  files_with_single_contributor_percentage = (100 - ((files_changed_by_many_teams.to_f / file_count) * 100)).round(2)
  hotspot_lines = count_hotspot_lines(filtered_files.keys)
  big_files_count = count_big_files(@directory_path)

  # ENV['BQ_CREDENTIALS'] = `cat /Users/serghei.moret/.config/gcloud/application_default_credentials.json`

  if ENV['BQ_CREDENTIALS']
    require 'google/cloud/bigquery'
    require 'json'
    creds = JSON.parse(ENV['BQ_CREDENTIALS'])
    bigquery = Google::Cloud::Bigquery.new(
      project_id: 'hellofresh-android',
      credentials: creds
    )
    dataset = bigquery.dataset 'github_data'

    files_with_multiple_contributor = file_team_map.count
    big_files_with_multiple_contributors = filtered_top_touched_files.count
    total_files_changed = uniq_code_files_with_changes.count

    platform = if @directory_path == 'HelloFresh/HelloFresh/'
                 'ios'
               elsif @directory_path == 'features/legacy/'
                 'android'
               end

    query = <<~SQL
      INSERT INTO modularization (date, platform, single_contributor_percentage, files_changed_by_many_teams, file_count, cross_teams_count, single_ownership_teams_count, hotspot_changes_percentage, churn_count, total_changes, files_with_multiple_contributor, big_files_with_multiple_contributors, total_files_changed, hotspot_lines, big_files_count)
      VALUES ('#{@begin_time}', '#{platform}', #{files_with_single_contributor_percentage}, #{files_changed_by_many_teams}, #{file_count}, #{cross_teams_count}, #{single_ownership_teams_count}, #{hotspot_changes_percentage}, #{churn_count}, #{total_changes}, #{files_with_multiple_contributor}, #{big_files_with_multiple_contributors}, #{total_files_changed}, #{hotspot_lines}, #{big_files_count});
    SQL

    dataset.query(query)

    #       delete_query = <<~SQL
    # DELETE FROM modularization
    # WHERE CONCAT(DATE(date), ' ', TIME(date)) NOT IN (
    #     SELECT CONCAT(DATE(date), ' ', TIME(date))
    #     FROM modularization AS m1
    #     WHERE TIME(date) = (
    #         SELECT MAX(TIME(date))
    #         FROM modularization AS m2
    #         WHERE DATE(m1.date) = DATE(m2.date)
    #     )
    # );
    #       SQL

    # dataset.query(delete_query)
  end

  puts ''
  puts "*Timeframe:* #{(@begin_time - duration_in_days).strftime('%Y-%m-%d')} to #{@begin_time.strftime('%Y-%m-%d')}"
  puts "     *Code files with a single contributor:* #{files_with_single_contributor_percentage}%"
  puts "        *Existing files changed by many teams:* #{files_changed_by_many_teams}"
  puts "        *Current existing #{CODE_EXTENSIONS} files:* #{file_count}"
  puts '     *Cross-Squad Dependency:*'
  puts "        *Contributions by multiple squads to the same files:* #{cross_teams_count}"
  puts "        *Contributions by single squads contributing to single files:* #{single_ownership_teams_count}"
  puts "     *Hotspot Code Changes:* #{hotspot_changes_percentage}%"
  puts "        *Churn count(commits to files by multiple teams):* #{churn_count}"
  puts "        *Total amount of commits:* #{total_changes}"
  puts "     *Total lines of hotspot code:* #{hotspot_lines}"
  puts "     *#{CODE_EXTENSIONS} files with multiple contributors:* #{file_team_map.count}"
  puts "     *#{CODE_EXTENSIONS} files exceeding #{BIG_FILE_SIZE} lines with multiple contributors:* #{filtered_top_touched_files.count}"
  puts "     *Total amount of commits to #{CODE_EXTENSIONS} files:* #{total_changes}"
  puts "     *Total #{CODE_EXTENSIONS} files changed:* #{uniq_code_files_with_changes.count}"
  puts "     *Current total number of code files longer than #{BIG_FILE_SIZE} lines:* #{big_files_count}"
  puts "     *Current total of #{CODE_EXTENSIONS} files in the folder:* #{file_count}"
  puts "     *Contributors:* #{contributors}"

  if HOTSPOT
    hotspot_output = []

    filter_files(file_team_map:, size: 0).each do |line|
      file = line.first
      contributors = line.last.first
      lines_of_code = count_lines_of_code(file)
      commits = line.last.last
      owner = find_owner(file:)
      prs = line.last[1]
      new_change = new_changes?(file:)

      hotspot_output << [file.gsub(@directory_path, ''), new_change, contributors, lines_of_code, commits, owner, prs]
    end

    hotspot_output.sort_by! { |row| -row[3] }

    if FILE_OUTPUT
      CSV.open('hotspot.csv', 'w') do |csv|
        csv << ['File', 'Updated in the past week', 'Contributors', 'Lines', 'Commits', 'Owner', 'PRs']
        hotspot_output.each do |row|
          csv << row
        end
      end
    else
      puts "\n   *Hotspot files(#{filtered_top_touched_files.count}):*\n"
      hotspot_output.each do |row|
        puts "     #{row[0]} Contributors: #{row[1]} Updated in the past week: #{row[2]} Lines: #{row[3]} Commits: #{row[4]} Owner: #{row[5]} PRs: #{row[6]}"
      end
    end
  end

  handle_codeowners(file_team_map:) if CODEOWNERS

  @steps -= 1

  return unless @steps.positive?

  system("git checkout `git rev-list -1 --before='#{(@begin_time - duration_in_days).strftime('%B %d %Y')}' HEAD`",
         %i[out err] => File::NULL)
  @begin_time -= duration_in_days
  contribution_message
end

#count_big_files(directory_path, size: BIG_FILE_SIZE) ⇒ Object 



108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 108

def count_big_files(directory_path, size: BIG_FILE_SIZE)
  size = size.to_i
  # Get a list of all files in the specified directory
  files = Dir.glob(File.join(directory_path, '**', '*')).select { |file| File.file?(file) }

  code_files = files.select do |f|
    extension = File.extname(f)
    valid_extensions = CODE_EXTENSIONS
    valid_extensions.include?(extension)
  end

  # Initialize a counter for files that meet the criteria
  count = 0
  # Iterate through each file and check the line count
  code_files.each do |file|
    lines_count = File.foreach(file).reject { |line| line.match(%r{^\s*(//|/\*.*\*/|\s*$)}) }.count

    count += 1 if lines_count > size
  end

  count
end

#count_hotspot_lines(files) ⇒ Object 



131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 131

def count_hotspot_lines(files)
  code_files = files.select do |f|
    extension = File.extname(f)
    valid_extensions = CODE_EXTENSIONS
    valid_extensions.include?(extension)
  end

  count = 0

  code_files.each do |file|
    lines_count = File.foreach(file).reject { |line| line.match(%r{^\s*(//|/\*.*\*/|\s*$)}) }.count

    count += lines_count
  end

  count
end

#count_lines_of_code(file) ⇒ Object 



149
150
151
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 149

def count_lines_of_code(file)
  File.foreach(file).reject { |line| line.match(%r{^\s*(//|/\*.*\*/|\s*$)}) }.count
end

#files_with_changes(directory_path:, start_date:, end_date:, branch: DEFAULT_BRANCH) ⇒ Object 



186
187
188
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 186

def files_with_changes(directory_path:, start_date:, end_date:, branch: DEFAULT_BRANCH)
  `git log origin/#{branch} --name-only --pretty=format:"" --since="#{start_date}" --until="#{end_date}" "#{directory_path}"`
end

#filter_existing_code_files(files, start_date, end_date) ⇒ Object 



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
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 153

def filter_existing_code_files(files, start_date, end_date)
  files.select do |f|
    next unless File.exist?(f)

    git_log = git_commit_info(file: f, start_date:, end_date:).split("\n")

    teams = git_log.map do |team|
      team.match(/#{TEAM_REGEX}/)[0].upcase
    end.reject { |e| EXCLUSIONS&.include?(e) }

    if TEAM_TO_FOCUS && CODEOWNER_TO_FOCUS
      next if !teams.include?(TEAM_TO_FOCUS) && !find_owner(file: f).include?(CODEOWNER_TO_FOCUS)
    elsif TEAM_TO_FOCUS
      next unless teams.include?(TEAM_TO_FOCUS)
    elsif CODEOWNER_TO_FOCUS
      next unless find_owner(file: f).include?(CODEOWNER_TO_FOCUS)
    end

    if EXCLUDED_FILES
      excluded_patterns = EXCLUDED_FILES.split(',')
      next if excluded_patterns.any? { |pattern| f.include?(pattern) }
    end

    extension = File.extname(f)
    valid_extensions = CODE_EXTENSIONS
    valid_extensions.include?(extension)
  end
end

#filter_files(file_team_map:, size: BIG_FILE_SIZE) ⇒ Object 



277
278
279
280
281
282
283
284
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 277

def filter_files(file_team_map:, size: BIG_FILE_SIZE)
  file_team_map.select do |file_path|
    next unless File.exist?(file_path)

    # Check if the file size is more than BIG_FILE_SIZE lines (excluding empty and commented lines)
    File.foreach(file_path).reject { |line| line.match(%r{^\s*(//|/\*.*\*/|\s*$)}) }.count > size.to_i
  end
end

#find_owner(file:) ⇒ Object 



103
104
105
106
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 103

def find_owner(file:)
  codeowners = read_codeowners_file
  find_owners(file, codeowners)
end

#find_owners(file_path, codeowners) ⇒ Object 



35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 35

def find_owners(file_path, codeowners)
  matching_patterns = codeowners.keys.select do |pattern|
    pattern_regex = Regexp.new("^#{Regexp.escape(pattern.sub(%r{^/+}, '').chomp('/')).gsub('\*', '.*').gsub('**',
                                                                                                            '.*?')}")
    file_path =~ pattern_regex
  end

  return ['unknown'] if matching_patterns.empty?

  # Sort patterns by length in descending order
  sorted_patterns = matching_patterns.sort_by(&:length).reverse

  # Find the most specific matching pattern
  best_match = sorted_patterns.find do |pattern|
    pattern_regex = Regexp.new("^#{Regexp.escape(pattern.sub(%r{^/+}, '').chomp('/')).gsub('\*', '.*').gsub('**',
                                                                                                            '.*?')}")
    file_path =~ pattern_regex
  end

  codeowners[best_match].split(' ')
end

#git_commit_count(file:, start_date:, end_date:, branch: DEFAULT_BRANCH) ⇒ Object 



190
191
192
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 190

def git_commit_count(file:, start_date:, end_date:, branch: DEFAULT_BRANCH)
  `git log origin/#{branch} --since="#{start_date}" --until="#{end_date}" --follow -- "#{file}" | grep -c '^commit'`
end

#git_commit_info(file:, start_date:, end_date:, branch: DEFAULT_BRANCH) ⇒ Object 



194
195
196
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 194

def git_commit_info(file:, start_date:, end_date:, branch: DEFAULT_BRANCH)
  `git log origin/#{branch} --pretty=format:"%s : %an" --since="#{start_date}" --until="#{end_date}" -- "#{file}"`
end

#git_files(directory_path:) ⇒ Object 



182
183
184
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 182

def git_files(directory_path:)
  `git ls-tree -r --name-only $(git rev-list -1 HEAD) -- "#{directory_path}"`
end

#handle_codeowners(file_team_map:) ⇒ Object 



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
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 57

def handle_codeowners(file_team_map:)
  output = "\n   *Code ownership data:*\n"
  codeowners = read_codeowners_file

  owners_data = Hash.new do |hash, key|
    hash[key] = { directories: Hash.new do |h, k|
      h[k] = { files: [] }
    end, churn_count: 0 }
  end

  file_team_map.each do |file, count|
    owners = find_owners(file, codeowners)
    owners.each do |owner|
      owners_data[owner][:churn_count] += count.last

      dir_path = File.dirname(file)
      owners_data[owner][:directories][dir_path][:files] << { name: File.basename(file), count: }
    end
  end

  # Sort owners_data by total count in descending order
  sorted_owners_data = owners_data.sort_by { |_, data| -data[:churn_count] }
  converted_team_map = file_team_map.transform_keys { |key| File.basename(key) }

  sorted_owners_data.each do |owner, data|
    output += "\n      #{owner.split('/').last}:\n         Total Count: #{data[:churn_count]}\n"
    data[:directories].each do |dir, dir_data|
      output += "            Directory: #{dir}\n               Top files:\n"
      dir_data[:files].each do |file_data|
        next if converted_team_map[File.basename(file_data[:name])].nil?

        contributors = converted_team_map[file_data[:name]]&.first&.empty? ? ['Excluded contributor'] : converted_team_map[file_data[:name]].first
        output += "                  #{File.basename(file_data[:name])} - #{file_data[:count].last} #{contributors}}\n"
      end
    end
  end

  if FILE_OUTPUT
    File.open('codeowners.txt', 'w') do |f|
      f.puts output
    end
  else
    puts output
  end
end

#hotspot_check(files:, branch:) ⇒ Object 



421
422
423
424
425
426
427
428
429
430
431
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 421

def hotspot_check(files:, branch:)
  duration_in_days = @duration_in_days.to_i
  start_date = @begin_time.to_time.to_i - duration_in_days * 86_400
  end_date = @begin_time.to_time.to_i

  resulting_files = analyze_changed_files(
    uniq_code_files_with_changes: files, start_date:, end_date:, branch:
  ).last

  resulting_files.filter { |f| resulting_files[f].first.count > 1 }.keys
end

#new_changes?(file:) ⇒ Boolean

Returns:

  • (Boolean) 


198
199
200
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 198

def new_changes?(file:)
  git_commit_info(file:, start_date: DateTime.now - 7, end_date: DateTime.now) != ''
end

#read_codeowners_file ⇒ Object 



20
21
22
23
24
25
26
27
28
29
30
31
32
33
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 20

def read_codeowners_file
  raise "CODEOWNERS file does not exist under #{CODEOWNERS_PATH}" unless File.exist?(CODEOWNERS_PATH)

  codeowners = {}
  File.readlines(CODEOWNERS_PATH).each do |line|
    next if line.strip.empty? || line.start_with?('#') # Skip comments and empty lines

    parts = line.split(/\s+/)
    directory_pattern = parts[0]
    owner = parts[1..].map { |o| o.start_with?('@') ? o[1..] : o }.join(' ') # Remove leading '@' from team names
    codeowners[directory_pattern] = owner
  end
  codeowners
end

#true?(obj) ⇒ Boolean

Returns:

  • (Boolean) 


16
17
18
 
# File 'lib/github_repo_statistics/github_repo_statistics.rb', line 16

def true?(obj)
  obj.to_s.downcase == 'true'
end