Class: Downloader

Inherits:
Object
  • Object
show all
Defined in:
lib/jirametrics/downloader.rb

Direct Known Subclasses

DownloaderForCloud, DownloaderForDataCenter

Constant Summary collapse

CURRENT_METADATA_VERSION = 
5

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(download_config:, file_system:, jira_gateway:, github_pr_cache: {}) ⇒ Downloader

Returns a new instance of Downloader.



46
47
48
49
50
51
52
53
54
55
56
57
 
# File 'lib/jirametrics/downloader.rb', line 46

def initialize download_config:, file_system:, jira_gateway:, github_pr_cache: {}
  @metadata = {}
  @download_config = download_config
  @target_path = @download_config.project_config.target_path
  @file_system = file_system
  @jira_gateway = jira_gateway
  @github_pr_cache = github_pr_cache
  @board_id_to_filter_id = {}

  @issue_keys_downloaded_in_current_run = []
  @issue_keys_pending_download = []
end

Instance Attribute Details

#board_id_to_filter_id ⇒ Object (readonly)

For testing only



34
35
36
 
# File 'lib/jirametrics/downloader.rb', line 34

def board_id_to_filter_id
  @board_id_to_filter_id
end

#file_system ⇒ Object (readonly)

Returns the value of attribute file_system.



31
32
33
 
# File 'lib/jirametrics/downloader.rb', line 31

def file_system
  @file_system
end

#metadata ⇒ Object

Returns the value of attribute metadata.



30
31
32
 
# File 'lib/jirametrics/downloader.rb', line 30

def metadata
  @metadata
end

#start_date_in_query ⇒ Object (readonly)

For testing only



34
35
36
 
# File 'lib/jirametrics/downloader.rb', line 34

def start_date_in_query
  @start_date_in_query
end

Class Method Details

.create(download_config:, file_system:, jira_gateway:, github_pr_cache: {}) ⇒ Object 



36
37
38
39
40
41
42
43
44
 
# File 'lib/jirametrics/downloader.rb', line 36

def self.create download_config:, file_system:, jira_gateway:, github_pr_cache: {}
  is_cloud = jira_gateway.settings['jira_cloud'] || jira_gateway.cloud?
  (is_cloud ? DownloaderForCloud : DownloaderForDataCenter).new(
    download_config: download_config,
    file_system: file_system,
    jira_gateway: jira_gateway,
    github_pr_cache: github_pr_cache
  )
end

Instance Method Details

#download_board_configuration(board_id:) ⇒ Object 



176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
 
# File 'lib/jirametrics/downloader.rb', line 176

def download_board_configuration board_id:
  log "  Downloading board configuration for board #{board_id}", both: true
  json = @jira_gateway.call_url relative_url: "/rest/agile/1.0/board/#{board_id}/configuration"

  @file_system.save_json(
    json: json,
    filename: File.join(@target_path, "#{file_prefix}_board_#{board_id}_configuration.json")
  )

  # We have a reported bug that blew up on this line. Moved it after the save so we can
  # actually look at the returned json.
  @board_id_to_filter_id[board_id] = json['filter']['id'].to_i

  if json['type'] == 'simple'
    features_json = download_features board_id: board_id
    if BoardFeature.from_raw(features_json).any? { |f| f.name == 'jsw.agility.sprints' && f.enabled? }
      download_sprints board_id: board_id
    end
  end
  download_sprints board_id: board_id if json['type'] == 'scrum'
  # TODO: Should be passing actual statuses, not empty list
  Board.new raw: json, possible_statuses: StatusCollection.new
end

#download_features(board_id:) ⇒ Object 



200
201
202
203
204
205
206
207
208
209
 
# File 'lib/jirametrics/downloader.rb', line 200

def download_features board_id:
  log "  Downloading features for board #{board_id}", both: true
  json = @jira_gateway.call_url relative_url: "/rest/agile/1.0/board/#{board_id}/features"

  @file_system.save_json(
    json: json,
    filename: File.join(@target_path, "#{file_prefix}_board_#{board_id}_features.json")
  )
  json
end

#download_github_prs ⇒ Object 



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
 
# File 'lib/jirametrics/downloader.rb', line 336

def download_github_prs
  project_keys = extract_project_keys_from_downloaded_issues
  if project_keys.empty?
    log '  No project keys found in downloaded issues, skipping GitHub PR download', both: true
    return
  end

  prs = []
  any_repo_failed = false
  @download_config.github_repos.each do |repo|
    prs.concat(
      GithubGateway.new(
        repo: repo,
        project_keys: project_keys,
        file_system: @file_system,
        raw_pr_cache: @github_pr_cache
      ).fetch_pull_requests(since: @download_date_range&.begin)
    )
  rescue StandardError => e
    any_repo_failed = true
    warn_about_failed_pr_download(repo, e)
  end

  # A successful-but-empty fetch is a legitimate result and gets saved. But if any repo raised, we
  # can't produce a complete file, so we leave the previously downloaded data untouched.
  return if any_repo_failed

  @file_system.save_json(
    json: prs.map(&:raw),
    filename: File.join(@target_path, "#{file_prefix}_github_prs.json")
  )
end

#download_sprints(board_id:) ⇒ Object 



211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
 
# File 'lib/jirametrics/downloader.rb', line 211

def download_sprints board_id:
  log "  Downloading sprints for board #{board_id}", both: true
  max_results = 100
  start_at = 0
  is_last = false

  while is_last == false
    json = @jira_gateway.call_url relative_url: "/rest/agile/1.0/board/#{board_id}/sprint?" \
      "maxResults=#{max_results}&startAt=#{start_at}"

    @file_system.save_json(
      json: json,
      filename: File.join(@target_path, "#{file_prefix}_board_#{board_id}_sprints_#{start_at}.json")
    )
    is_last = json['isLast']
    max_results = json['maxResults']
    if json['values']
      start_at += json['values'].size
    else
      log "  No sprints found for board #{board_id}"
    end
  end
end

#download_statuses ⇒ Object 



128
129
130
131
132
133
134
135
136
 
# File 'lib/jirametrics/downloader.rb', line 128

def download_statuses
  log '  Downloading all statuses', both: true
  json = @jira_gateway.call_url relative_url: '/rest/api/2/status'

  @file_system.save_json(
    json: json,
    filename: File.join(@target_path, "#{file_prefix}_statuses.json")
  )
end

#download_users ⇒ Object 



138
139
140
141
142
143
144
145
146
147
148
 
# File 'lib/jirametrics/downloader.rb', line 138

def download_users
  return unless @jira_gateway.cloud?

  log '  Downloading all users', both: true
  json = @jira_gateway.call_url relative_url: '/rest/api/2/users'

  @file_system.save_json(
    json: json,
    filename: File.join(@target_path, "#{file_prefix}_users.json")
  )
end

#end_progress ⇒ Object 



103
104
105
 
# File 'lib/jirametrics/downloader.rb', line 103

def end_progress
  @file_system.end_progress
end

#extract_project_keys_from_downloaded_issues ⇒ Object 



382
383
384
385
386
387
388
389
390
391
 
# File 'lib/jirametrics/downloader.rb', line 382

def extract_project_keys_from_downloaded_issues
  path = File.join(@target_path, "#{file_prefix}_issues")
  return [] unless @file_system.dir_exist?(path)

  keys = []
  @file_system.foreach(path) do |filename|
    keys << filename.split('-').first if filename.match?(/^[A-Z][A-Z_0-9]+-\d+-\d+\.json$/)
  end
  keys.uniq
end

#file_prefix ⇒ Object 



393
394
395
 
# File 'lib/jirametrics/downloader.rb', line 393

def file_prefix
  @download_config.project_config.get_file_prefix
end

#find_board_ids ⇒ Object 



107
108
109
110
111
112
 
# File 'lib/jirametrics/downloader.rb', line 107

def find_board_ids
  ids = @download_config.project_config.board_configs.collect(&:id)
  raise 'Board ids must be specified' if ids.empty?

  ids
end

#identify_other_issues_to_be_downloaded(raw_issue:, board:) ⇒ Object 



114
115
116
117
118
119
120
121
122
123
124
125
126
 
# File 'lib/jirametrics/downloader.rb', line 114

def identify_other_issues_to_be_downloaded raw_issue:, board:
  issue = Issue.new raw: raw_issue, board: board
  @issue_keys_downloaded_in_current_run << issue.key

  # Parent
  parent_key = issue.parent_key(project_config: @download_config.project_config)
  @issue_keys_pending_download << parent_key if parent_key

  # Sub-tasks
  issue.raw['fields']['subtasks']&.each do |raw_subtask|
    @issue_keys_pending_download << raw_subtask['key']
  end
end

#load_cached_metadata(hash) ⇒ Object 



253
254
255
256
257
258
 
# File 'lib/jirametrics/downloader.rb', line 253

def load_cached_metadata hash
  hash.each do |key, value|
    value = Date.parse(value) if value.is_a?(String) && value =~ /^\d{4}-\d{2}-\d{2}$/
    @metadata[key] = value
  end
end

#load_metadata ⇒ Object 



239
240
241
242
243
244
245
246
247
248
249
250
251
 
# File 'lib/jirametrics/downloader.rb', line 239

def load_metadata
  # If we've never done a download before then this file won't be there. That's ok.
  hash = file_system.load_json(metadata_pathname, fail_on_error: false)
  return if hash.nil?

  # Only use the saved metadata if the version number is the same one that we're currently using.
  # If the cached data is in an older format then we're going to throw most of it away.
  @cached_data_format_is_current = (hash['version'] || 0) == CURRENT_METADATA_VERSION
  load_cached_metadata(hash) if @cached_data_format_is_current

  # Even if this is the old format, we want to obey this one tag
  @metadata['no-download'] = hash['no-download'] if hash['no-download']
end

#log(text, both: false) ⇒ Object 



86
87
88
 
# File 'lib/jirametrics/downloader.rb', line 86

def log text, both: false
  @file_system.log text, also_write_to_stderr: both
end

#log_start(text) ⇒ Object 



90
91
92
 
# File 'lib/jirametrics/downloader.rb', line 90

def log_start text
  @file_system.log_start text
end

#make_jql(filter_id:, today: nil) ⇒ Object 



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
 
# File 'lib/jirametrics/downloader.rb', line 310

def make_jql filter_id:, today: nil
  today ||= today_in_project_timezone
  segments = []
  segments << "filter=#{filter_id}"

  start_date = @download_config.start_date today: today

  if start_date
    @download_date_range = start_date..today.to_date
    @start_date_in_query = @download_date_range.begin

    # Catch-all to pick up anything that's been around since before the range started but hasn't
    # had an update during the range.
    catch_all = '((status changed OR Sprint is not EMPTY) AND statusCategory != Done)'

    # Pick up any issues that had a status change in the range
    start_date_text = @start_date_in_query.strftime '%Y-%m-%d'
    # find_in_range = %((status changed DURING ("#{start_date_text} 00:00","#{end_date_text} 23:59")))
    find_in_range = %(updated >= "#{start_date_text} 00:00")

    segments << "(#{find_in_range} OR #{catch_all})"
  end

  segments.join ' AND '
end

#metadata_pathname ⇒ Object 



235
236
237
 
# File 'lib/jirametrics/downloader.rb', line 235

def metadata_pathname
  File.join(@target_path, "#{file_prefix}_meta.json")
end

#progress_dot(message = nil) ⇒ Object 



98
99
100
101
 
# File 'lib/jirametrics/downloader.rb', line 98

def progress_dot message = nil
  @file_system.log message if message
  @file_system.progress_dot
end

#remove_old_files ⇒ Object 



289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
 
# File 'lib/jirametrics/downloader.rb', line 289

def remove_old_files
  Dir.foreach @target_path do |file|
    next unless file.match?(/^#{file_prefix}_\d+\.json$/)
    next if file == "#{file_prefix}_status_history.json"

    File.unlink File.join(@target_path, file)
  end

  return if @cached_data_format_is_current

  # Also throw away all the previously downloaded issues.
  path = File.join(@target_path, "#{file_prefix}_issues")
  return unless File.exist? path

  Dir.foreach path do |file|
    next unless file.match?(/\.json$/)

    File.unlink File.join(path, file)
  end
end

#run ⇒ Object 



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
 
# File 'lib/jirametrics/downloader.rb', line 59

def run
  log '', both: true
  log @download_config.project_config.name, both: true

  load_metadata

  if @metadata['no-download']
    log '  Skipping download. Found no-download in meta file', both: true
    return
  end

  # board_ids = @download_config.board_ids

  remove_old_files
  update_status_history_file
  download_statuses
  find_board_ids.each do |id|
    board = download_board_configuration board_id: id
    board.project_config = @download_config.project_config
    download_issues board: board
  end
  download_users

  save_metadata
  download_github_prs if @download_config.github_repos.any?
end

#save_metadata ⇒ Object 



268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
 
# File 'lib/jirametrics/downloader.rb', line 268

def save_metadata
  @metadata['version'] = CURRENT_METADATA_VERSION
  @metadata['rolling_date_count'] = @download_config.rolling_date_count
  @metadata['date_start_from_last_query'] = @start_date_in_query if @start_date_in_query

  if @download_date_range.nil?
    log "Making up a date range in meta since one wasn't specified. You'll want to change that.", both: true
    today = today_in_project_timezone
    @download_date_range = (today - 7)..today
  end

  @metadata['earliest_date_start'] = @download_date_range.begin if @metadata['earliest_date_start'].nil?

  @metadata['date_start'] = @download_date_range.begin
  @metadata['date_end'] = @download_date_range.end

  @metadata['jira_url'] = @jira_url

  @file_system.save_json json: @metadata, filename: metadata_pathname
end

#start_progress ⇒ Object 



94
95
96
 
# File 'lib/jirametrics/downloader.rb', line 94

def start_progress
  @file_system.start_progress
end

#timezone_offset ⇒ Object 



260
261
262
 
# File 'lib/jirametrics/downloader.rb', line 260

def timezone_offset
  @download_config.project_config.exporter.timezone_offset
end

#today_in_project_timezone ⇒ Object 



264
265
266
 
# File 'lib/jirametrics/downloader.rb', line 264

def today_in_project_timezone
  Time.now.getlocal(timezone_offset).to_date
end

#update_status_history_file ⇒ Object 



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
 
# File 'lib/jirametrics/downloader.rb', line 150

def update_status_history_file
  status_filename = File.join(@target_path, "#{file_prefix}_statuses.json")
  return unless file_system.file_exist? status_filename

  status_json = file_system.load_json(status_filename)

  history_filename = File.join(@target_path, "#{file_prefix}_status_history.json")
  history_json = file_system.load_json(history_filename) if file_system.file_exist? history_filename

  if history_json
    file_system.log '  Updating status history file', also_write_to_stderr: true
  else
    file_system.log '  Creating status history file', also_write_to_stderr: true
    history_json = []
  end

  status_json.each do |status_item|
    id = status_item['id']
    history_item = history_json.find { |s| s['id'] == id }
    history_json.delete(history_item) if history_item
    history_json << status_item
  end

  file_system.save_json(filename: history_filename, json: history_json)
end

#warn_about_failed_pr_download(repo, error) ⇒ Object

The same github_repos are downloaded for every project, so an unreachable repo would otherwise warn once per project (dozens of identical messages). The github_pr_cache is shared across all projects in a run, so we use it to warn about each repo at most once.



372
373
374
375
376
377
378
379
380
 
# File 'lib/jirametrics/downloader.rb', line 372

def warn_about_failed_pr_download repo, error
  warned_key = [repo, :download_failure_warned]
  return if @github_pr_cache[warned_key]

  @github_pr_cache[warned_key] = true
  @file_system.warning "Failed to download pull requests from #{repo}: #{error.message}. " \
    'Left the existing PR data in place rather than overwriting it with an incomplete set. ' \
    'Fix the access problem (often a `gh auth login` / repo-access issue) and re-run download to refresh it.'
end