Standardized rake tasks argument handling

.gitignore

@@ -43,7 +43,7 @@ ui-library/bower_components
 ui-library/css/vendor/
 ui-library/js/vendor/
 stash/stash_engine/ui-library/
-*.css.map                
+*.css.map
 
 # ######################################################
 
@@ -104,6 +104,7 @@ build-iPhoneSimulator/
 
 # unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
 .rvmrc
+.nvmrc
 
 #####=== Rails ===#####
 

documentation/external_services/salesforce.md

@@ -80,7 +80,7 @@ journal settings:
 rails journals:check_salesforce_sync
 ```
 
-To clean up metadata in Salesforce associated with journals, add `DRY_RUN=false`
+To clean up metadata in Salesforce associated with journals, add ` -- --dry_run false`
 to the end of the above command.
 
 

documentation/reports.md

@@ -18,7 +18,7 @@ tracking of payments.
 
 Run it with a command like:
 ```
-RAILS_ENV=v3_production bundle exec rails identifiers:shopping_cart_report YEAR_MONTH=2024-01
+RAILS_ENV=v3_production bundle exec rails identifiers:shopping_cart_report -- --year_month 2024-01
 ```
 
 Fields in the shopping cart report
@@ -37,7 +37,7 @@ To run the report and retrieve the files:
 ```
 # on v3-prod server
 cd ~/deploy/current
-RAILS_ENV=v3_production bundle exec rake identifiers:shopping_cart_report YEAR_MONTH=2024-01
+RAILS_ENV=v3_production bundle exec rake identifiers:shopping_cart_report -- --year_month 2024-01
 cp ~/deploy/current/shopping* ~/journal-payments/shoppingcart/
 cd ~/journal-payments/shoppingcart
 git pull
@@ -66,7 +66,7 @@ Run the deferred payment reports with a command like:
 ```
 cp ~/journal-payments/shoppingcart/shopping_cart_report_2023* /tmp
 # This command must be run on the v3-prod server, to access the production database
-RAILS_ENV=v3_production bundle exec rails identifiers:deferred_journal_reports SC_REPORT=/tmp/shopping_cart_report_2024-Q1.csv
+RAILS_ENV=v3_production bundle exec rails identifiers:deferred_journal_reports -- --sc_report /tmp/shopping_cart_report_2024-Q1.csv
 ```
 
 ### Tiered payment reports
@@ -83,7 +83,8 @@ Run the tiered journal payment reports with a command like:
 # This command must be run in a personal account with the journal-payments checked out
 cp ~/journal-payments/shoppingcart/shopping_cart_report_2023* /tmp
 # This command must be run on the production server, to access the production database
-RAILS_ENV=v3_production bundle exec rails identifiers:tiered_journal_reports SC_REPORT=/tmp/shopping_cart_report_2023-Q1.csv BASE_REPORT=/tmp/shopping_cart_report_2023.csv
+
+RAILS_ENV=v3_production bundle exec rails identifiers:tiered_journal_reports -- --sc_report /tmp/shopping_cart_report_2023-Q1.csv --base_report /tmp/shopping_cart_report_2023.csv
 ```
 
 For tenant institutions that have a tiered payment plan, a similar secondary task
@@ -96,7 +97,8 @@ Run the tiered institution payment reports with a command like:
 # This command must be run in a personal account with the journal-payments checked out
 cp ~/journal-payments/shoppingcart/shopping_cart_report_2023* /tmp
 # This command must be run on the production server, to access the production database
-RAILS_ENV=v3_production bundle exec rails identifiers:tiered_tenant_reports SC_REPORT=/tmp/shopping_cart_report_2023-Q1.csv BASE_REPORT=/tmp/shopping_cart_report_2023.csv
+
+RAILS_ENV=v3_production bundle exec rails identifiers:tiered_tenant_reports -- --sc_report tmp/shopping_cart_report_2023-Q1.csv --base_report /tmp/shopping_cart_report_2023.csv
 ```
 
 Dataset info report
@@ -205,7 +207,7 @@ This also gives institutions when people didn't autocomplete their ROR correctly
 Run like:
 
 ```
-bundle exec rails reports:from_text_institution name="Planck" RAILS_ENV=v3_production
+RAILS_ENV=v3_production bundle exec rails reports:from_text_institution -- --name="Planck"
 ```
 
 Put the string you want to detect in the `name` variable.  It shows the matches in `author_affiliations`

documentation/ror_transition.md

@@ -12,7 +12,7 @@ Truncate the table to remove all current entries.  The table is called `stash_en
 You can download the latest ROR exports at https://doi.org/10.5281/zenodo.6347574 .
 
 ```bash
-RAILS_ENV=development bundle exec rails affiliation_import:populate_funder_ror_mapping /path/to/file
+RAILS_ENV=development bundle exec rails affiliation_import:populate_funder_ror_mapping -- --path /path/to/file
 ```
 
 ## task to re-import latest ROR data
@@ -75,4 +75,4 @@ Update the DataCite records with updated metadata.
 
 ```bash
 RAILS_ENV=development bundle exec rails datacite_target:update_dryad
-```
+```

documentation/server_maintenance/troubleshooting.md

@@ -267,7 +267,7 @@ embargo date.  You can find the deposition_id in the stash_engine_zenodo_copies
 table. The zenodo_copy_id is the id from that same table.
 ```
 # the arguments are 1) resource_id, 2) deposition_id at zenodo, 3) date, 4) zenodo_copy_id
-RAILS_ENV=production bundle exec rake dev_ops:embargo_zenodo 97683 4407065 2021-12-31 12342
+RAILS_ENV=production bundle exec rake dev_ops:embargo_zenodo -- --resource_id 97683 --deposition_id 4407065 --date 2021-12-31 --zenodo_copy_id 12342
 ```
 
 **You must login to Zenodo and "publish" the new version of the dataset; otherwise the embargo
@@ -300,7 +300,8 @@ table. The zenodo_copy_id is the `stash_engine_zenodo_copies.id` from that same
 
 ```
 # the arguments are 1) resource_id, 2) deposition_id at zenodo, 3) date, 4) zenodo_copy_id
-RAILS_ENV=production bundle exec rake dev_ops:embargo_zenodo 97683 4407065 2023-07-25 1234
+RAILS_ENV=production bundle exec rake dev_ops:embargo_zenodo -- --resource_id 97683 --deposition_id 4407065 --date 2023-07-25 --zenodo_copy_id 1234
+
 ```
 **You must login to Zenodo and "publish" the new version of the dataset; otherwise the embargo
 will not take effect. This is probably something we can fix in the code, but it is waiting for us
@@ -386,13 +387,13 @@ it is harder to do after removal.
 
 ```
 # the parameters are 1) resource_id, 2) deposition_id (see in stash_engine_zenodo_copies), 3) date far in the future
-RAILS_ENV=production bundle exec rails dev_ops:embargo_zenodo <resource-id> <deposition-id> 2200-12-31
+RAILS_ENV=production bundle exec rails dev_ops:embargo_zenodo -- --resource_id <resource-id> --deposition_id <deposition-id> --date <YYYY-MM-DD> --zenodo_copy_id <zenodo_copy_id>
 ```
 
 
 If you need to completely remove a dataset from existence, you can run
 ```
-rails dev_ops:destroy_dataset 10.27837/dryad.catfood
+rails dev_ops:destroy_dataset -- --doi 10.27837/dryad.catfood
 ```
 
 This command will remove the dataset from Dryad, and give instructions to remove
@@ -484,7 +485,7 @@ end
 
 To update anything published between a set of dates using a task, you can use:
 ```
-RAILS_ENV=production bundle exec rails datacite_target:update_by_publication YYYY-MM-DD YYYY-MM-DD
+RAILS_ENV=production bundle exec rails datacite_target:update_by_publication -- --start YYYY-MM-DD --end YYYY-MM-DD
 ```
 
 If you need to update DataCite for *all* items in Dryad, you can use:

documentation/sql_queries/fundref_to_ror_comparisons.md

@@ -13,7 +13,7 @@ RAILS_ENV=production bundle exec rails affiliation_import:update_ror_orgs
 
 Download the zip and extract the json file from https://doi.org/10.5281/zenodo.6347574:
 ```bash
-RAILS_ENV=<environment> bundle exec rails affiliation_import:populate_funder_ror_mapping <path/to/ror/dump.json>
+RAILS_ENV=<environment> bundle exec rails affiliation_import:populate_funder_ror_mapping -- --path <path/to/ror/dump.json>
 ```
 
 After the imports you can run the following query to see how items in the database map and that
@@ -66,4 +66,4 @@ Items that are funders but don't match a fundref ID:
 SELECT DISTINCT contributor_name, contributor_type, identifier_type, name_identifier_id
   FROM dcs_contributors
  WHERE contributor_type = 'funder' AND name_identifier_id ='';
-```
+```

lib/tasks/affiliation_import.rake

@@ -22,21 +22,23 @@ namespace :affiliation_import do
     Stash::Organization::RorUpdater.perform
   end
 
+  # example: RAILS_ENV=development bundle exec rake affiliation_import:process_ror_csv -- --affiliation_mode true
   desc 'Process all of the CSV files'
   task process_ror_csv: :environment do
     start_time = Time.now
     @dois_to_skip = []
     @live_mode = false
     @last_resource = nil
+    args = Tasks::ArgsParser.parse(:affiliation_mode)
 
-    case ENV.fetch('AFFILIATION_MODE', nil)
+    case args.affiliation_mode
     when nil
-      puts 'Environment variable AFFILIATION_MODE is blank, assuming test mode.'
+      puts '--affiliation_mode argument is blank, assuming test mode.'
     when 'live'
-      puts 'Starting live processing due to environment variable AFFILIATION_MODE.'
+      puts 'Starting live processing due to --affiliation_mode argument.'
       @live_mode = true
     else
-      puts "Environment variable AFFILIATION_MODE is #{ENV.fetch('AFFILIATION_MODE', nil)}, entering test mode."
+      puts "--affiliation_mode argument is #{args.affiliation_mode}, entering test mode."
     end
 
     puts 'Loading affiliation info from CSV files in /tmp/dryad_affiliations*'
@@ -50,25 +52,28 @@ namespace :affiliation_import do
     end
 
     puts "DONE! Elapsed time: #{Time.at(Time.now - start_time).utc.strftime('%H:%M:%S')}"
+    exit
   end
 
+  # example: RAILS_ENV=development bundle exec rake affiliation_import:merge_duplicate_authors -- --author_merge_mode true --start 0
   desc 'Merge duplicate authors'
   task merge_duplicate_authors: :environment do
     start_time = Time.now
     @live_mode = false
+    args = Tasks::ArgsParser.parse(:author_merge_mode, :start)
 
-    case ENV.fetch('AUTHOR_MERGE_MODE', nil)
+    case args.author_merge_mode
     when nil
-      puts 'Environment variable AUTHOR_MERGE_MODE is blank, assuming test mode.'
+      puts '--author_merge_mode argument is blank, assuming test mode.'
     when 'live'
-      puts 'Starting live processing due to environment variable AUTHOR_MERGE_MODE.'
+      puts 'Starting live processing due to --author_merge_mode argument.'
       @live_mode = true
     else
-      puts "Environment variable AUTHOR_MERGE_MODE is #{ENV.fetch('AUTHOR_MERGE_MODE', nil)}, entering test mode."
+      puts "--author_merge_mode argument is #{args.author_merge_mode}, entering test mode."
     end
 
     start_from = 0
-    start_from = ENV['START'].to_i unless ENV['START'].blank?
+    start_from = args.start.to_i unless args.start.blank?
 
     stash_ids = StashEngine::Identifier.all.order('stash_engine_identifiers.id').distinct
     stash_ids.each_with_index do |i, idx|
@@ -94,35 +99,40 @@ namespace :affiliation_import do
       end
     end
     puts "DONE! Elapsed time: #{Time.at(Time.now - start_time).utc.strftime('%H:%M:%S')}"
+    exit
   end
 
+  # example: rake affiliation_import:populate_ror_db -- --path /path/to/json_file
   desc 'Populate our ROR database manually from the ROR dump json file because the Zenodo API not working'
   task populate_ror_db: :environment do
     $stdout.sync = true # keeps stdout from buffering which causes weird delays such as with tail -f
 
-    if ARGV.length != 1
+    args = Tasks::ArgsParser.parse(:path)
+    unless args.path
       puts 'Please enter the path to the ROR dump json file as an argument'
       puts 'You can get the latest dump from https://doi.org/10.5281/zenodo.6347574 (get json file for last version in zip)'
       exit
     end
 
-    ror_dump_file = ARGV[0]
+    ror_dump_file = args.path
     exit unless File.exist?(ror_dump_file)
 
     Stash::Organization::RorUpdater.process_ror_json(json_file_path: ror_dump_file)
   end
 
+  # example: rake affiliation_import:populate_funder_ror_mapping -- --path /path/to/json_file
   desc 'Populate fundref_id to ror_id mapping table'
   task populate_funder_ror_mapping: :environment do
     $stdout.sync = true # keeps stdout from buffering which causes weird delays such as with tail -f
 
-    if ARGV.length != 1
+    args = Tasks::ArgsParser.parse(:path)
+    unless args.path
       puts 'Please enter the path to the ROR dump json file as an argument'
       puts 'You can get the latest dump from https://doi.org/10.5281/zenodo.6347574 (get json file for last version in zip)'
       exit
     end
 
-    ror_dump_file = ARGV[0]
+    ror_dump_file = args.path
     exit unless File.exist?(ror_dump_file)
 
     ActiveRecord::Base.connection.truncate(StashEngine::XrefFunderToRor.table_name)

lib/tasks/args_parser.rb

@@ -0,0 +1,23 @@
+require 'optparse'
+# rubocop:disable Lint/EmptyBlock
+module Tasks
+  module ArgsParser
+
+    def self.parse(*attributes)
+      options = OpenStruct.new
+      return options if attributes.blank?
+
+      opts = OptionParser.new
+      opts.banner = 'Usage: rake add [options]'
+      attributes.each do |key|
+        opts.on('-o', "--#{key}=value", String) { |value| options[key] = value }
+      end
+
+      args = opts.order!(ARGV) {}
+      opts.parse!(args)
+
+      options
+    end
+  end
+end
+# rubocop:enable Lint/EmptyBlock

lib/tasks/compressed.rake

@@ -1,5 +1,7 @@
 # :nocov:
+
 namespace :compressed do
+  # example: rails/rake compressed:update_contents
   task update_contents: :environment do
     $stdout.sync = true # keeps stdout from buffering which causes weird delays such as with tail -f
 
@@ -52,15 +54,17 @@ namespace :compressed do
   end
 
   # a simplified version of the above task that only updates one resource for testing and doesn't catch errors
+  # example: rails/rake compressed:update_one -- --file_id 10
   task update_one: :environment do
     $stdout.sync = true # keeps stdout from buffering which causes weird delays such as with tail -f
+    args = Tasks::ArgsParser.parse(:file_id)
 
-    if ARGV.length != 1
+    unless args.file_id
       puts 'Please enter the file id as the only argument to this task'
       exit
     end
 
-    db_file = StashEngine::DataFile.find(ARGV[0])
+    db_file = StashEngine::DataFile.find(args.file_id)
 
     puts "Updating container_contents for #{db_file.upload_file_name} (id: #{db_file.id}, " \
          "resource_id: #{db_file.resource_id})"