unitsdb 2.1.0 → 2.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4b92f561a56f8cdd59a905cf7827c6ffda47acae64f1e31256f2c5efebfd81f2
-  data.tar.gz: 218a47cf5fb2c178f787f05e186c09f5b40d0f4914b81d6de5884759011621ef
+  metadata.gz: 3d26a180d24908f27758427140cfc5e01380afc6441ae2f96856523c2dc8f1d9
+  data.tar.gz: 3bc8f78dab0ed305d7f48bdcd07356b3914e87d9a096bdc5fb0cc177c1350d48
 SHA512:
-  metadata.gz: 82bd1ac58073379426b3378bda8b94e0bcdf46f954148d082b6008931d0c49c0c50d35b53ac64661a75e0f58bfedf46a5f53e0e948e5520584711a0260ebe638
-  data.tar.gz: ff4538f70410cc9572f7a7719bf32aa1324f6e2cdaf7fe95acbd6426b31168b9c4ba72271d81fe8a76dd1339aa0d3d3307424a878b4cb11e96be5af9897078b0
+  metadata.gz: 8601b692c2c4e0e6191e4e0c3f74a963325c63bd4a0830e20bf7ba1216f514557af8792c137acbd2f233919df6769d90604035f9bd4a8f99f872cb5959921a2e
+  data.tar.gz: 02f631a8c47820816d6415c30d78cb21d16eff2d00dc71ba652fd17a6b7f3e310e874ea1fa21fcb0a0ee71c65d2950dac07a3fde08cc34df8cf4e477550f5b4a

data/.rubocop_todo.yml

@@ -1,17 +1,56 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2025-05-20 11:22:36 UTC using RuboCop version 1.75.6.
+# on 2025-05-21 10:17:19 UTC using RuboCop version 1.75.6.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
 # versions of RuboCop, may require this file to be generated again.
 
 # Offense count: 1
-# Configuration parameters: Severity, Include.
-# Include: **/*.gemspec
-Gemspec/DuplicatedAssignment:
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle, IndentationWidth.
+# SupportedStyles: with_first_element, with_fixed_indentation
+Layout/ArrayAlignment:
+  Exclude:
+    - 'lib/unitsdb/commands/ucum/check.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AutoCorrect, AllowBorderComment, AllowMarginComment.
+Layout/EmptyComment:
+  Exclude:
+    - 'ucum-test.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+Layout/EmptyLineAfterMagicComment:
+  Exclude:
+    - 'ucum-test.rb'
+
+# Offense count: 4
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AllowMultipleStyles, EnforcedHashRocketStyle, EnforcedColonStyle, EnforcedLastArgumentHashStyle.
+# SupportedHashRocketStyles: key, separator, table
+# SupportedColonStyles: key, separator, table
+# SupportedLastArgumentHashStyles: always_inspect, always_ignore, ignore_implicit, ignore_explicit
+Layout/HashAlignment:
+  Exclude:
+    - 'spec/unitsdb/commands/ucum/update_spec.rb'
+
+# Offense count: 5
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AllowInHeredoc.
+Layout/TrailingWhitespace:
+  Exclude:
+    - 'lib/unitsdb/commands/ucum/check.rb'
+    - 'spec/unitsdb/commands/ucum/update_spec.rb'
+
+# Offense count: 1
+# This cop supports unsafe autocorrection (--autocorrect-all).
+# Configuration parameters: AllowSafeAssignment.
+Lint/AssignmentInCondition:
   Exclude:
-    - 'unitsdb.gemspec'
+    - 'lib/unitsdb/commands/ucum/updater.rb'
 
 # Offense count: 2
 Lint/ShadowingOuterLocalVariable:
@@ -19,12 +58,12 @@ Lint/ShadowingOuterLocalVariable:
     - 'lib/unitsdb/commands/search.rb'
     - 'lib/unitsdb/commands/validate/si_references.rb'
 
-# Offense count: 37
+# Offense count: 47
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes.
 Metrics/AbcSize:
   Max: 169
 
-# Offense count: 27
+# Offense count: 31
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 # AllowedMethods: refine
 Metrics/BlockLength:
@@ -33,19 +72,19 @@ Metrics/BlockLength:
 # Offense count: 3
 # Configuration parameters: CountComments, CountAsOne.
 Metrics/ClassLength:
-  Max: 441
+  Max: 442
 
-# Offense count: 38
+# Offense count: 45
 # Configuration parameters: AllowedMethods, AllowedPatterns.
 Metrics/CyclomaticComplexity:
   Max: 50
 
-# Offense count: 47
+# Offense count: 58
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Max: 169
 
-# Offense count: 3
+# Offense count: 5
 # Configuration parameters: CountComments, CountAsOne.
 Metrics/ModuleLength:
   Max: 369
@@ -55,7 +94,7 @@ Metrics/ModuleLength:
 Metrics/ParameterLists:
   Max: 6
 
-# Offense count: 33
+# Offense count: 39
 # Configuration parameters: AllowedMethods, AllowedPatterns.
 Metrics/PerceivedComplexity:
   Max: 56
@@ -73,17 +112,45 @@ Naming/MethodParameterName:
     - 'lib/unitsdb/commands/si_ttl_parser.rb'
     - 'lib/unitsdb/utils.rb'
 
+# Offense count: 1
+# Configuration parameters: NamePrefix, ForbiddenPrefixes, AllowedMethods, MethodDefinitionMacros, UseSorbetSigs.
+# NamePrefix: is_, has_, have_, does_
+# ForbiddenPrefixes: is_, has_, have_, does_
+# AllowedMethods: is_a?
+# MethodDefinitionMacros: define_method, define_singleton_method
+Naming/PredicateName:
+  Exclude:
+    - 'spec/**/*'
+    - 'lib/unitsdb/commands/ucum/matcher.rb'
+
 # Offense count: 1
 # This cop supports unsafe autocorrection (--autocorrect-all).
 Style/CombinableLoops:
   Exclude:
     - 'lib/unitsdb/commands/si_matcher.rb'
 
-# Offense count: 40
+# Offense count: 48
 # Configuration parameters: AllowedConstants.
 Style/Documentation:
   Enabled: false
 
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AutoCorrect, EnforcedStyle, AllowComments.
+# SupportedStyles: empty, nil, both
+Style/EmptyElse:
+  Exclude:
+    - 'lib/unitsdb/commands/ucum/updater.rb'
+
+# Offense count: 1
+# This cop supports unsafe autocorrection (--autocorrect-all).
+# Configuration parameters: EnforcedStyle.
+# SupportedStyles: always, always_true, never
+Style/FrozenStringLiteralComment:
+  Exclude:
+    - '**/*.arb'
+    - 'ucum-test.rb'
+
 # Offense count: 2
 # This cop supports unsafe autocorrection (--autocorrect-all).
 Style/IdenticalConditionalBranches:
@@ -95,15 +162,25 @@ Style/MultilineBlockChain:
   Exclude:
     - 'lib/unitsdb/commands/normalize.rb'
 
-# Offense count: 5
+# Offense count: 9
 # Configuration parameters: AllowedMethods.
 # AllowedMethods: respond_to_missing?
 Style/OptionalBooleanParameter:
   Exclude:
     - 'lib/unitsdb/commands/check_si.rb'
     - 'lib/unitsdb/commands/si_updater.rb'
+    - 'lib/unitsdb/commands/ucum/check.rb'
+    - 'lib/unitsdb/commands/ucum/updater.rb'
+
+# Offense count: 7
+# This cop supports unsafe autocorrection (--autocorrect-all).
+# Configuration parameters: ConvertCodeThatCanStartToReturnNil, AllowedMethods, MaxChainLength.
+# AllowedMethods: present?, blank?, presence, try, try!
+Style/SafeNavigation:
+  Exclude:
+    - 'lib/unitsdb/commands/ucum/matcher.rb'
 
-# Offense count: 6
+# Offense count: 12
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, AllowedPatterns, SplitStrings.
 # URISchemes: http, https

data/Gemfile

@@ -6,6 +6,7 @@ source "https://rubygems.org"
 gemspec
 
 gem "diffy"
+gem "nokogiri"
 gem "rake"
 gem "rspec"
 gem "rubocop"

data/README.adoc

@@ -101,6 +101,7 @@ Syntax:
 [source,yaml]
 ----
 schema_version: 2.0.0
+version: 1.0.0  # Release version (in semantic format x.y.z)
 dimensions:
   - identifiers: [...]
     length: {...}
@@ -269,7 +270,7 @@ Options:
 
 `--all`, `-a`:: Process all YAML files in the repository
 `--database`, `-d`:: Path to UnitsDB database (required)
-`--sort`:: Sort units by: 'short' (name, default), 'nist' (ID), 'unitsml' (ID), or 'none'
+`--sort`:: Sort units by: 'short' (name), 'nist' (ID, default), 'unitsml' (ID), or 'none'
 
 
 ==== Search
@@ -383,6 +384,108 @@ with added SI references
 `--include-potential-matches`, `-p`:: Include potential matches when updating
 references (default: false)
 
+
+==== Check references to UCUM
+
+Performs a comprehensive check of entities in the UCUM XML file against UnitsDB
+database entities and updates UnitsDB with UCUM references.
+
+UCUM supports the following entity types:
+
+* Base units
+* Units
+* Prefixes
+
+UCUM provides dimensions as part of their unit definitions but not as
+uniquely referencable entities.
+
+This combined command checks in both directions to ensure UnitsDB supports
+every UCUM entity:
+
+* From UCUM to UnitsDB: Ensures every UCUM entity is referenced by at least one
+UnitsDB entity
+
+* From UnitsDB to UCUM: Identifies UnitsDB entities that should reference UCUM
+entities
+
+There are two commands:
+
+* `ucum check`: Checks for matches between UnitsDB and UCUM entities and reports results
+
+* `ucum update`: Updates UnitsDB entities with references to matching UCUM entities
+
+[source,sh]
+----
+# Check all entity types and generate a report
+$ unitsdb ucum check --database=spec/fixtures/unitsdb --ucum-file=spec/fixtures/ucum/ucum-essence.xml
+
+# Check a specific entity type (units or prefixes)
+$ unitsdb ucum check --entity-type=units \
+  --database=spec/fixtures/unitsdb \
+  --ucum-file=spec/fixtures/ucum/ucum-essence.xml
+
+# Check in a specific direction only
+$ unitsdb ucum check --direction=from_ucum \
+  --database=spec/fixtures/unitsdb \
+  --ucum-file=spec/fixtures/ucum/ucum-essence.xml
+----
+
+Options:
+
+`--database`, `-d`:: Path to UnitsDB database (required)
+
+`--ucum-file`, `-u`:: Path to the UCUM essence XML file (required)
+
+`--entity-type`, `-e`:: Entity type to check (units or prefixes).
+If not specified, all types are checked.
+
+`--direction`, `-r`:: Direction to check: `to_ucum` (UnitsDB→UCUM), `from_ucum`
+(UCUM→UnitsDB), or `both` (default)
+
+`--output-updated-database`, `-o`:: Directory path to write updated YAML files
+with added UCUM references
+
+`--include-potential-matches`, `-p`:: Include potential matches when updating
+references (default: false)
+
+
+==== Update UCUM references
+
+[source,sh]
+----
+# Update all entity types with UCUM references
+$ unitsdb ucum update --database=spec/fixtures/unitsdb \
+  --ucum-file=spec/fixtures/ucum/ucum-essence.xml \
+  --output-dir=new_unitsdb
+
+# Update a specific entity type (units or prefixes)
+$ unitsdb ucum update --entity-type=units \
+  --database=spec/fixtures/unitsdb \
+  --ucum-file=spec/fixtures/ucum/ucum-essence.xml \
+  --output-dir=new_unitsdb
+
+# Include potential matches when updating references (default: false)
+$ unitsdb ucum update --include-potential-matches \
+  --database=spec/fixtures/unitsdb \
+  --ucum-file=spec/fixtures/ucum/ucum-essence.xml \
+  --output-dir=new_unitsdb
+----
+
+Options:
+
+`--database`, `-d`:: Path to UnitsDB database (required)
+
+`--ucum-file`, `-u`:: Path to the UCUM essence XML file (required)
+
+`--entity-type`, `-e`:: Entity type to update (units or prefixes).
+If not specified, all types are updated
+
+`--output-dir`, `-o`:: Directory path to write updated YAML files
+(defaults to database path)
+
+`--include-potential-matches`, `-p`:: Include potential matches when updating
+references (default: false)
+
 ==== Release
 
 Creates release files for UnitsDB in unified formats:
@@ -400,6 +503,9 @@ $ unitsdb release --format=zip --database=/path/to/unitsdb/data
 
 # Specify output directory
 $ unitsdb release --output-dir=/path/to/output --database=/path/to/unitsdb/data
+
+# Specify a version (required)
+$ unitsdb release --version=2.1.0 --database=/path/to/unitsdb/data
 ----
 
 This command creates release files for UnitsDB in two formats:
@@ -410,7 +516,7 @@ This command creates release files for UnitsDB in two formats:
 
 The command verifies that all files have the same schema version before creating
 the release files. The output files are named with the schema version (e.g.,
-`unitsdb-2.0.0.yaml` and `unitsdb-2.0.0.zip`).
+`unitsdb-2.1.0.yaml` and `unitsdb-2.1.0.zip`).
 
 Options:
 

data/lib/unitsdb/cli.rb

@@ -1,8 +1,10 @@
 # frozen_string_literal: true
 
 require "thor"
+require_relative "commands/base"
 require_relative "commands/validate"
 require_relative "commands/_modify"
+require_relative "commands/ucum"
 require "fileutils"
 
 module Unitsdb
@@ -12,6 +14,9 @@ module Unitsdb
       true
     end
 
+    desc "ucum SUBCOMMAND", "UCUM-related commands"
+    subcommand "ucum", Commands::UcumCommand
+
     desc "_modify SUBCOMMAND", "Commands that modify the database"
     subcommand "_modify", Commands::ModifyCommand
 
@@ -71,6 +76,8 @@ module Unitsdb
                     desc: "Output format: 'yaml' (single file), 'zip' (archive), or 'all' (both)"
     option :output_dir, type: :string, default: ".", aliases: "-o",
                         desc: "Directory to output release files"
+    option :version, type: :string, aliases: "-v", required: true,
+                     desc: "Version number for the release (x.y.z)"
     option :database, type: :string, required: true, aliases: "-d",
                       desc: "Path to UnitsDB database (required)"
     def release

data/lib/unitsdb/commands/_modify.rb

@@ -6,8 +6,8 @@ module Unitsdb
   module Commands
     class ModifyCommand < Thor
       desc "normalize [INPUT] [OUTPUT]", "Normalize a YAML file or all YAML files with --all"
-      method_option :sort, type: :string, default: "short",
-                           desc: "Sort units by: 'short' (name), 'nist' (ID), 'unitsml' (ID), or 'none'"
+      method_option :sort, type: :string, default: "nist",
+                           desc: "Sort units by: 'short' (name), 'nist' (ID, default), 'unitsml' (ID), or 'none'"
       method_option :database, type: :string, required: true, aliases: "-d",
                                desc: "Path to UnitsDB database (required)"
       method_option :all, type: :boolean, default: false, aliases: "-a",

data/lib/unitsdb/commands/base.rb

@@ -1,51 +1,25 @@
 # frozen_string_literal: true
 
-require "thor"
 require "yaml"
-require_relative "../utils"
-require_relative "../database"
+require "fileutils"
 
 module Unitsdb
   module Commands
     class Base
       def initialize(options = {})
         @options = options
+        puts "Database directory path: #{@options[:database]}" if @options[:database]
       end
 
       protected
 
-      def yaml_files(input = nil, opts = nil)
-        options_to_use = opts || @options
-
-        if options_to_use[:all]
-          Unitsdb::Utils::DEFAULT_YAML_FILES.map { |f| File.join(options_to_use[:database], f) }
-        elsif input
-          [input]
-        else
-          puts "Error: INPUT file is required when not using --all"
-          exit(1)
-        end
-      end
-
-      def load_database(database_path = nil)
-        path = database_path || @options[:database]
-
-        raise Unitsdb::Errors::DatabaseError, "Database path must be specified using the --database option" if path.nil?
+      def load_database(path = nil)
+        path ||= @options[:database]
+        raise Unitsdb::Errors::DatabaseError, "Database path not specified" unless path
 
         Unitsdb::Database.from_db(path)
-      rescue Unitsdb::Errors::DatabaseError => e
-        puts "Error: #{e.message}"
-        exit(1)
-      end
-
-      def load_yaml(file_path)
-        return nil unless File.exist?(file_path)
-
-        YAML.safe_load(File.read(file_path))
-      end
-
-      def file_type(file_path)
-        File.basename(file_path, ".yaml")
+      rescue StandardError => e
+        raise Unitsdb::Errors::DatabaseError, "Failed to load database: #{e.message}"
       end
     end
   end

data/lib/unitsdb/commands/normalize.rb

@@ -33,7 +33,7 @@ module Unitsdb
 
       def normalize_file(input, output)
         # Load the original YAML to work with
-        yaml = load_yaml(input)
+        yaml = YAML.safe_load(File.read(input))
 
         # For schema 2.0.0, we need to handle the schema_version and the main collection key
         if yaml.key?("schema_version") && yaml["schema_version"] == "2.0.0"

data/lib/unitsdb/commands/release.rb

@@ -1,111 +1,72 @@
 # frozen_string_literal: true
 
-require_relative "base"
 require "yaml"
 require "zip"
 require "fileutils"
 
 module Unitsdb
   module Commands
-    class Release < Base
+    class Release < ::Unitsdb::Commands::Base
       def run
-        # Verify all required files exist
-        yaml_files = Unitsdb::Utils::DEFAULT_YAML_FILES.map { |f| File.join(@options[:database], f) }
-        missing_files = yaml_files.reject { |f| File.exist?(f) }
-
-        if missing_files.any?
-          puts "Error: The following required files are missing:"
-          missing_files.each { |f| puts "  - #{f}" }
-          exit(1)
-        end
-
-        # Extract schema version from any file (they should all have the same version)
-        first_yaml = load_yaml(yaml_files.first)
-        schema_version = first_yaml["schema_version"]
-
-        unless schema_version
-          puts "Error: Could not determine schema version from #{yaml_files.first}"
-          exit(1)
-        end
-
-        # Verify all files have the same schema version
-        inconsistent_files = []
-        yaml_files.each do |file|
-          yaml = load_yaml(file)
-          next unless yaml["schema_version"] != schema_version
-
-          inconsistent_files << {
-            file: file,
-            version: yaml["schema_version"]
-          }
-        end
-
-        if inconsistent_files.any?
-          puts "Error: Inconsistent schema versions detected:"
-          puts "  Expected version: #{schema_version}"
-          inconsistent_files.each do |info|
-            puts "  - #{info[:file]}: #{info[:version]}"
-          end
-          exit(1)
-        end
+        # Load the database
+        db = load_database(@options[:database])
+        db.version = @options[:version]
 
         # Create output directory if it doesn't exist
-        output_dir = @options[:output_dir] || "."
-        FileUtils.mkdir_p(output_dir) unless Dir.exist?(output_dir)
-
-        # Generate outputs based on format option
-        format = @options[:format] || "all"
-
-        case format.downcase
-        when "yaml", "all"
-          create_unified_yaml(yaml_files, schema_version, output_dir)
-        end
-
-        case format.downcase
-        when "zip", "all"
-          create_zip_archive(yaml_files, schema_version, output_dir)
+        FileUtils.mkdir_p(@options[:output_dir])
+
+        # Generate release files based on format option
+        format = (@options[:format] || "all").downcase
+        case format
+        when "yaml"
+          create_unified_yaml(db)
+        when "zip"
+          create_zip_archive(db)
+        when "all"
+          create_unified_yaml(db)
+          create_zip_archive(db)
+        else
+          puts "Invalid format option: #{@options[:format]}"
+          puts "Valid options are: 'yaml', 'zip', or 'all'"
+          exit(1)
         end
 
-        puts "Release files created successfully in #{output_dir}"
+        puts "Release files created successfully in #{@options[:output_dir]}"
+      rescue Unitsdb::Errors::DatabaseError => e
+        puts "Error: #{e.message}"
+        exit(1)
       end
 
       private
 
-      def create_unified_yaml(yaml_files, schema_version, output_dir)
-        # Create a unified YAML structure
-        unified_yaml = { "schema_version" => schema_version }
-
-        # Load each YAML file and add its collection to the unified structure
-        yaml_files.each do |file|
-          yaml = load_yaml(file)
-          # Get the collection key (units, scales, etc.) - it's the key that's not schema_version
-          collection_key = (yaml.keys - ["schema_version"]).first
-          if collection_key
-            # Add the collection to the unified structure
-            unified_yaml[collection_key] = yaml[collection_key]
-          end
-        end
-
-        # Write the unified YAML to a file
-        output_file = File.join(output_dir, "unitsdb-#{schema_version}.yaml")
-        File.write(output_file, unified_yaml.to_yaml)
-        puts "Created unified YAML file: #{output_file}"
+      def create_unified_yaml(db)
+        # Create a unified YAML file with all database components
+        output_path = File.join(@options[:output_dir], "unitsdb-#{@options[:version]}.yaml")
+        File.write(output_path, db.to_yaml)
+        puts "Created unified YAML file: #{output_path}"
       end
 
-      def create_zip_archive(yaml_files, schema_version, output_dir)
-        # Create a ZIP archive containing all YAML files
-        output_file = File.join(output_dir, "unitsdb-#{schema_version}.zip")
-
-        Zip::File.open(output_file, Zip::File::CREATE) do |zipfile|
-          yaml_files.each do |file|
-            # Get the filename without the path
-            filename = File.basename(file)
-            # Add the file to the ZIP archive
-            zipfile.add(filename, file)
+      def create_zip_archive(db)
+        # Create a ZIP archive with individual YAML files
+        output_path = File.join(@options[:output_dir], "unitsdb-#{@options[:version]}.zip")
+
+        Zip::File.open(output_path, Zip::File::CREATE) do |zipfile|
+          {
+            dimensions: Unitsdb::Dimensions,
+            unit_systems: Unitsdb::UnitSystems,
+            units: Unitsdb::Units,
+            prefixes: Unitsdb::Prefixes,
+            quantities: Unitsdb::Quantities
+          }.each_pair do |access_method, collection_klass|
+            db.send(access_method).tap do |data|
+              collection = collection_klass.new(access_method => data)
+              collection.version = @options[:version]
+              zipfile.get_output_stream("#{access_method}.yaml") { |f| f.write(collection.to_yaml) }
+            end
           end
         end
 
-        puts "Created ZIP archive: #{output_file}"
+        puts "Created ZIP archive: #{output_path}"
       end
     end
   end