Class: Downloader

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

Direct Known Subclasses

DownloaderForCloud, DownloaderForDataCenter

Constant Summary collapse

CURRENT_METADATA_VERSION = 
4

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(download_config:, file_system:, jira_gateway:) ⇒ Downloader

Returns a new instance of Downloader.



52
53
54
55
56
57
58
59
60
61
62
 
# File 'lib/jirametrics/downloader.rb', line 52

def initialize download_config:, file_system:, jira_gateway:
  @metadata = {}
  @download_config = download_config
  @target_path = @download_config.project_config.target_path
  @file_system = file_system
  @jira_gateway = jira_gateway
  @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:) ⇒ Object 



36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
 
# File 'lib/jirametrics/downloader.rb', line 36

def self.create download_config:, file_system:, jira_gateway:
  if jira_gateway.cloud?
    DownloaderForCloud.new(
      download_config: download_config,
      file_system: file_system,
      jira_gateway: jira_gateway
    )
  else
    DownloaderForDataCenter.new(
      download_config: download_config,
      file_system: file_system,
      jira_gateway: jira_gateway
    )
  end
end

Instance Method Details

#bulk_fetch_issues(issue_datas:, board:, in_initial_query:) ⇒ Object 



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
 
# File 'lib/jirametrics/downloader.rb', line 360

def bulk_fetch_issues issue_datas:, board:, in_initial_query:
  log "  Downloading #{issue_datas.size} issues", both: true
  payload = {
    'expand' => [
      'changelog'
    ],
    'fields' => ['*all'],
    'issueIdsOrKeys' => issue_datas.collect(&:key)
  }
  response = @jira_gateway.post_request(
    relative_url: issue_bulk_fetch_api,
    payload: JSON.generate(payload)
  )
  response['issues'].each do |issue_json|
    issue_json['exporter'] = {
      'in_initial_query' => in_initial_query
    }
    issue = Issue.new(raw: issue_json, board: board)
    data = issue_datas.find { |d| d.key == issue.key }
    data.up_to_date = true
    data.last_modified = issue.updated
    data.issue = issue
  end
  issue_datas
end

#delete_issues_from_cache_that_are_not_in_server(issue_data_hash:, path:) ⇒ Object 



386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
 
# File 'lib/jirametrics/downloader.rb', line 386

def delete_issues_from_cache_that_are_not_in_server issue_data_hash:, path:
  # The gotcha with deleted issues is that they just stop being returned in queries
  # and we have no way to know that they should be removed from our local cache.
  # With the new approach, we ask for every issue that Jira knows about (within
  # the parameters of the query) and then delete anything that's in our local cache
  # but wasn't returned.
  @file_system.foreach path do |file|
    next if file.start_with? '.'
    raise "Unexpected filename in #{path}: #{file}" unless file =~ /^(\w+-\d+)-\d+\.json$/

    key = $1
    next if issue_data_hash[key] # Still in Jira

    file_to_delete = File.join(path, file)
    # log "  Issue #{key} appears to have been deleted from Jira. Removing local copy", both: true
    # file_system.unlink file_to_delete
    puts "Flagging #{key} for deletion"
  end
end

#download_board_configuration(board_id:) ⇒ Object 



160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
 
# File 'lib/jirametrics/downloader.rb', line 160

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

  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_issues(board:) ⇒ Object 



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
 
# File 'lib/jirametrics/downloader.rb', line 295

def download_issues board:
  log "  Downloading primary issues for board #{board.id} from #{jira_instance_type}", both: true
  path = File.join(@target_path, "#{file_prefix}_issues/")
  unless Dir.exist?(path)
    log "  Creating path #{path}"
    Dir.mkdir(path)
  end

  filter_id = @board_id_to_filter_id[board.id]
  jql = make_jql(filter_id: filter_id)
  intercept_jql = @download_config.project_config.settings['intercept_jql']
  jql = intercept_jql.call jql if intercept_jql

  issue_data_hash = search_for_issues jql: jql, board_id: board.id, path: path

  loop do
    related_issue_keys = Set.new
    issue_data_hash
      .values
      .reject { |data| data.up_to_date }
      .each_slice(100) do |slice|
        slice = bulk_fetch_issues(
          issue_datas: slice, board: board, in_initial_query: true
        )
        slice.each do |data|
          @file_system.save_json(
            json: data.issue.raw, filename: data.cache_path
          )
          # Set the timestamp on the file to match the updated one so that we don't have
          # to parse the file just to find the timestamp
          @file_system.utime time: data.issue.updated, file: data.cache_path

          issue = data.issue
          next unless issue

          parent_key = issue.parent_key(project_config: @download_config.project_config)
          related_issue_keys << parent_key if parent_key

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

    # Remove all the ones we already downloaded
    related_issue_keys.reject! { |key| issue_data_hash[key] }

    related_issue_keys.each do |key|
      data = DownloadIssueData.new key: key
      data.found_in_primary_query = false
      data.up_to_date = false
      data.cache_path = File.join(path, "#{key}-#{board.id}.json")
      issue_data_hash[key] = data
    end
    break if related_issue_keys.empty?

    log "  Downloading linked issues for board #{board.id}", both: true
  end

  delete_issues_from_cache_that_are_not_in_server(
    issue_data_hash: issue_data_hash, path: path
  )
end

#download_sprints(board_id:) ⇒ Object 



178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
 
# File 'lib/jirametrics/downloader.rb', line 178

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 



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

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 



124
125
126
127
128
129
130
131
132
 
# File 'lib/jirametrics/downloader.rb', line 124

def download_users
  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

#file_prefix ⇒ Object 



291
292
293
 
# File 'lib/jirametrics/downloader.rb', line 291

def file_prefix
  @download_config.project_config.get_file_prefix
end

#find_board_ids ⇒ Object 



93
94
95
96
97
98
 
# File 'lib/jirametrics/downloader.rb', line 93

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 



100
101
102
103
104
105
106
107
108
109
110
111
112
 
# File 'lib/jirametrics/downloader.rb', line 100

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

#last_modified(filename:) ⇒ Object 



406
407
408
 
# File 'lib/jirametrics/downloader.rb', line 406

def last_modified filename:
  File.mtime(filename) if File.exist?(filename)
end

#load_metadata ⇒ Object 



206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
 
# File 'lib/jirametrics/downloader.rb', line 206

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
  if @cached_data_format_is_current
    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

  # 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 



89
90
91
 
# File 'lib/jirametrics/downloader.rb', line 89

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

#make_jql(filter_id:, today: Date.today) ⇒ Object 



266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
 
# File 'lib/jirametrics/downloader.rb', line 266

def make_jql filter_id:, today: Date.today
  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 



202
203
204
 
# File 'lib/jirametrics/downloader.rb', line 202

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

#remove_old_files ⇒ Object 



245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
 
# File 'lib/jirametrics/downloader.rb', line 245

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 



64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
 
# File 'lib/jirametrics/downloader.rb', line 64

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
    download_issues board: board
  end
  download_users

  save_metadata
end

#save_metadata ⇒ Object 



225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
 
# File 'lib/jirametrics/downloader.rb', line 225

def save_metadata
  @metadata['version'] = CURRENT_METADATA_VERSION
  @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 = Date.today
    @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

#update_status_history_file ⇒ Object 



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
 
# File 'lib/jirametrics/downloader.rb', line 134

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