Add descriptions to all rake tasks

Related #378

lib/tasks/backfill.rake

@@ -2,6 +2,7 @@ require 'open-uri'
 require 'zlib'
 
 namespace :backfill do
+  desc 'import event data for all non-internal repos with internal dependencies from gharchive'
   task all: :environment do
 
     repo_names = Repository.not_internal.with_internal_deps.pluck(:full_name)

lib/tasks/changelog.rake

@@ -1,4 +1,5 @@
 namespace :changelog do
+  desc 'list internal repos with no changelog or history file'
   task missing: :environment do
     release_events = Event.internal.event_type('ReleaseEvent').includes(:repository)
     repos = release_events.map(&:repository).uniq.reject(&:archived?)
@@ -15,6 +16,7 @@ namespace :changelog do
     end
   end
 
+  desc "generate a changelog file for a repository based on it's releases"
   task generate: :environment do
     full_name = 'ipfs-shipyard/ipld-explorer-components'
     repo = Repository.find_by_full_name(full_name)

lib/tasks/contributions.rake

@@ -1,6 +1,7 @@
 require 'csv'
 
 namespace :contributions do
+  desc "generate output a csv of avg first response time for each contributor"
   task research: :environment do
     counts = Issue.not_core.group(:user).count
 

lib/tasks/contributors.rake

@@ -1,10 +1,13 @@
 require 'csv'
 
 namespace :contributors do
+
+  desc "sync least recently updated contributors from discovered repositories"
   task sync: :environment do
     Repository.discovered_contributors.order('last_events_sync_at ASC nulls first').where(bot: false).limit(200).each(&:sync)
   end
 
+  desc "output a csv of top contributor data"
   task research: :environment do
     contributors = Issue.not_core.group(:user).count.sort_by{|u,c| -c}.select{|u,c| c > 10 }.reject{|u,c| u == 'ghost'}
 
@@ -14,7 +17,6 @@ namespace :contributors do
       collabs[username] = Issue.where(user: username).first.collabs
     end
 
-
     csv_string = CSV.generate do |csv|
       csv << [
         'Name',

lib/tasks/discovery.rake

@@ -1,6 +1,6 @@
 namespace :discovery do
+  desc "search libraries.io for packages mentioning ipfs"
   task packages: :environment do
-    # find all packages that mention ipfs
     platforms = ['npm', 'maven', 'rubygems', 'pypi', 'cargo', 'packagist', 'nuget', 'clojars', 'cocoapods', 'hackage', 'hex', 'meteor', 'carthage', 'pub']
 
     platforms.each do |platform|
@@ -23,6 +23,7 @@ namespace :discovery do
     end
   end
 
+  desc "find repositories for packages discovered in discovery:packages task"
   task package_repos: :environment do
     platforms = ['npm', 'maven', 'rubygems', 'pypi', 'cargo', 'packagist', 'nuget', 'clojars', 'cocoapods', 'hackage', 'hex', 'meteor', 'carthage', 'pub']
 
@@ -41,6 +42,7 @@ namespace :discovery do
     end
   end
 
+  desc "find dependent repositories for packages discovered in discovery:packages task"
   task package_dependents: :environment do
     platforms = ['npm', 'maven', 'rubygems', 'pypi', 'nuget']
 
@@ -81,19 +83,15 @@ namespace :discovery do
     end
   end
 
-  task local_repos: :environment do
-    # find collab repos that depend on ipfs packages
-
-  end
-
+  desc "find collab repos that depend on ipfs packages"
   task local_search: :environment do
-    # find collab repos that depend on ipfs packages
     search_repo_names = SearchResult.group(:repository_full_name).count.keys
     File.open("data/search_results.json","w") do |f|
       f.write(search_repo_names.to_json)
     end
   end
 
+  desc "list unique repo names from package_dependents, local_search and package_repos task outputs"
   task all_repos: :environment do
     search_results = JSON.load(File.open("data/search_results.json")).map{|name| "https://github.com/#{name}"}
     package_repos = JSON.load(File.open("data/package_repos.json"))
@@ -106,6 +104,7 @@ namespace :discovery do
     # puts names.length
   end
 
+  desc 'list github orgs/users with most repos not already in the database'
   task big_orgs: :environment do
     # rows = []
     orgs = {}
@@ -127,6 +126,7 @@ namespace :discovery do
     # p rows.length
   end
 
+  desc 'check repo repos listed in all_repos.csv still exist'
   task check_status: :environment do
     valid_rows = []
     CSV.foreach("data/all_repos.csv") do |row,i|
@@ -154,7 +154,7 @@ namespace :discovery do
     p valid_rows.uniq.length
   end
 
-  task ranking: :environment do
+  # task ranking: :environment do
     # Is it a fork?                         (fork)
     # Is it archived?                       (archived)
     # How many stars?                       (stargazers_count)
@@ -178,6 +178,5 @@ namespace :discovery do
     # Does it use go-ipfs as a library?
     # Does it use js-ipfs as a library?
     # Does it use go-ipfs via docker?
-
-  end
+  # end
 end

lib/tasks/docker.rake

@@ -1,6 +1,7 @@
 require 'csv'
 
 namespace :docker do
+  desc 'search github for repositories that have Dockerfile files containing "ipfs"'
   task search: :environment do
     client = Issue.github_client
     search = client.search_code("filename:Dockerfile ipfs")
@@ -26,6 +27,7 @@ namespace :docker do
     end
   end
 
+  desc 'load more data for repositories found in docker:search task'  
   task augment_docker: :environment do
     client = Issue.github_client
     repos = {}
@@ -69,6 +71,7 @@ namespace :docker do
     end
   end
 
+  desc 'search github for repositories that have docker-compose files containing "ipfs"'
   task search_compose: :environment do
     client = Issue.github_client
 
@@ -94,6 +97,7 @@ namespace :docker do
     end
   end
 
+  desc 'load more data for repositories found in docker:search_compose task'
   task augment_compose: :environment do
     client = Issue.github_client
     repos = {}

lib/tasks/graph.rake

@@ -1,4 +1,5 @@
 namespace :graph do
+  desc "generate graphviz file to graph links between contributors and internal repos"
   task generate: :environment do
     issues = Issue.internal.not_core.humans.order('repo_full_name').map{|i| [i.user, i.repo_full_name] }.uniq
 
@@ -28,6 +29,7 @@ namespace :graph do
     # rake graph:generate && dot -Tjpeg -Kneato test.gv > both.jpeg && open both.jpeg
   end
 
+  desc "generate graphviz file to graph links between collaborators and internal repos"
   task collabs: :environment do
     issues = Issue.internal.not_core.humans.all_collabs.order('repo_full_name').map{|i| [i.collabs.first, i.repo_full_name] }.uniq
 
@@ -56,6 +58,7 @@ namespace :graph do
     # rake graph:generate && dot -Tjpeg -Kneato test.gv > both.jpeg && open both.jpeg
   end
 
+  desc "generate graphviz file to graph links internal repos and javascript dependencies"
   task deps: :environment do
 
     @scope = Repository.internal

lib/tasks/issues.rake

@@ -1,8 +1,10 @@
 namespace :issues do
+  desc 'sync recently active repos from each collaborator org'
   task sync_collabs: :environment do
     Organization.collaborator.each(&:sync_recently_active_repos)
   end
 
+  desc 'sync issues from recently active repositories'
   task sync_recent: :environment do
     Repository.not_internal.triage.each(&:download_issues)
     Repository.not_internal.triage.each(&:sync_events)
@@ -13,6 +15,7 @@ namespace :issues do
     Organization.collaborator.each(&:update_counts)
   end
 
+  desc 'sync internal issues that have not been synced in over 24 hours'
   task sync_daily: :environment do
     ids = Issue.internal.state('open').where('issues.last_synced_at < ? or issues.last_synced_at is null', 1.day.ago).limit(1000).order('issues.last_synced_at asc nulls first, issues.updated_at asc').pluck(:id)
     Issue.where(id: ids).find_each(&:sync)

lib/tasks/orgs.rake

@@ -1,4 +1,5 @@
 namespace :orgs do
+  desc 'update count fields on collabortor organizations'
   task update_counts: :environment do
     Organization.collaborator.each(&:update_counts)
   end

lib/tasks/packages.rake

@@ -1,8 +1,10 @@
 namespace :packages do
+  desc "sync internal packages"
   task sync_internal: :environment do
     Package.internal_or_partner.maintained.find_each(&:sync)
   end
 
+  desc "find missing packages from npm, cargo, go and docker"
   task find_missing_npm_packages: :environment do
     Package.download_internal_dependent_packages
 
@@ -17,18 +19,22 @@ namespace :packages do
     Organization.where('docker_hub_org is not null').each(&:sync_docker_packages)
   end
 
+  desc 'sync 100 least recently updated packages'
   task sync: :environment do
     Package.order('last_synced_at ASC nulls first').limit(100).each(&:sync)
   end
 
+  desc "download repositories for packages with no repository"
   task find_missing_package_repos: :environment do
     Package.find_missing_package_repos
   end
 
+  desc "discover github repos that depend on internal packages"
   task find_dependent_github_repos: :environment do
     Package.find_dependent_github_repos
   end
 
+  desc 'list repositories that directly depend upon internal packages'
   task find_direct_dependent_repos: :environment do
     internal_package_ids = Package.internal.pluck(:id)
     direct_repo_ids = RepositoryDependency.where(package_id: internal_package_ids, direct: true).pluck(:repository_id).uniq
@@ -43,6 +49,7 @@ namespace :packages do
     puts "#{direct_repo_ids.length} direct dependent repos total"
   end
 
+  desc 'list repositories that indirectly depend upon internal packages'
   task find_indirect_dependent_repos: :environment do
     internal_package_ids = Package.internal.pluck(:id)
 
@@ -61,6 +68,7 @@ namespace :packages do
     puts "#{only_indirect_repo_ids.length} indirect dependent repos total"
   end
 
+  desc 'list packages that directly depend upon internal packages'
   task find_direct_dependent_packages: :environment do
     internal_package_ids = Package.internal.pluck(:id)
     direct_version_ids = Dependency.where(package_id: internal_package_ids).pluck(:version_id).uniq
@@ -78,6 +86,7 @@ namespace :packages do
     puts "#{direct_package_ids.length} direct dependent packages total"
   end
 
+  desc 'list packages that indirectly depend upon internal packages'
   task find_indirect_dependent_packages: :environment do
     internal_package_ids = Package.internal.pluck(:id)
 
@@ -100,6 +109,7 @@ namespace :packages do
     puts "#{all_indirect_dependent_ids.length} indirect dependent packages total"
   end
 
+  desc 'list repositories that indirectly depend upon internal packages via recursive method'  
   task find_indirect_dependent_recursive_repos: :environment do
     internal_package_ids = Package.internal.pluck(:id)
 
@@ -125,6 +135,7 @@ namespace :packages do
     puts "#{indirect_repo_ids.length} indirect dependent repos total"
   end
 
+  desc 'list the difference between find_indirect_dependent_recursive_repos and find_indirect_dependent_repos tasks'
   task indirect_diff: :environment do
     internal_package_ids = Package.internal.pluck(:id)
 

lib/tasks/pmf.rake

@@ -1,4 +1,5 @@
 namespace :pmf do
+  desc "list pmf states summary"
   task states: :environment do
     start_date = 6.week.ago
     end_date = 2.week.ago
@@ -16,6 +17,7 @@ namespace :pmf do
     end
   end
 
+  desc "list pmf transitions summary"
   task transitions: :environment do
     start_date = 6.week.ago
     end_date = 2.week.ago
@@ -33,6 +35,7 @@ namespace :pmf do
     end
   end
 
+  desc "calculate pmf windows for past year from yesterday"
   task warm_caches: :environment do
     # run this via cron just after midnight
     # calculate pmf windows for past year from yesterday

lib/tasks/repositories.rake

@@ -1,17 +1,21 @@
 namespace :repositories do
+  desc "import new repositories discovered searching github "
   task discover_from_search_results: :environment do
     Repository.discover_from_search_results
   end
 
+  desc "update ecosystem score for each repository"
   task recalculate_scores: :environment do
     Repository.recalculate_scores
   end
 
+  desc "update 1200 least recently synced repositories"
   task sync: :environment do
     Repository.order('last_events_sync_at ASC nulls first').limit(1000).each(&:sync_if_updates)
     Repository.order('last_sync_at ASC nulls first').limit(200).each(&:sync)
   end
 
+  desc "import 200 new repositories from discovered contributor events to other repos"
   task sync_discovered: :environment do
     all_names = Repository.discovered_related_repo_names
     existing_names = Repository.where(full_name: all_names).pluck(:full_name)

lib/tasks/research.rake

@@ -1,4 +1,5 @@
 namespace :research do
+  desc "download arweave org, repo and packages and output as csv"
   task arweave: :environment do
     # download all the repos
     o = Organization.find_or_create_by(name: 'ArweaveTeam')

lib/tasks/search.rake

@@ -1,4 +1,5 @@
 namespace :search do
+  desc 'peform all search queries'
   task run_all: :environment do
     SearchQuery.run_all
   end

lib/tasks/stewards.rake

@@ -1,8 +1,8 @@
 require 'csv'
 
 namespace :stewards do
+  desc 'export all internal repositories as csv'
   task export_repos: :environment do
-
     exclude_fields = ['topics', 'direct_internal_dependency_package_ids', 'indirect_internal_dependency_package_ids']
 
     scope = Repository.internal
@@ -16,8 +16,8 @@ namespace :stewards do
     puts csv_string
   end
 
+  desc 'export all internal events for the past 6 months as csv'
   task export_events: :environment do
-
     scope = Event.internal.this_period(180).humans
     csv_string = CSV.generate do |csv|
       csv << Event.attribute_names.excluding("payload")

lib/tasks/upgrades.rake

@@ -1,6 +1,7 @@
 require 'csv'
 
 namespace :upgrades do
+  desc 'discover and export a csv of issues and pull requests on github related to updating ipfs'
   task search: :environment do
     search_to_csv(["update ipfs is:issue", "update ipfs is:pr", "upgrade ipfs is:issue", "upgrade ipfs is:pr", "bump ipfs", "ipfs 0.5", "go-ipfs", "ipfs docker"], 'ipfs')
   end