suma 0.1.16 → 0.1.18

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 955161f5bfcd18f46e1fcafafdc05bea5a7310eaa8899b03552e7d22f6f41795
-  data.tar.gz: ff06abeaf766ce76d814079ef718c6deb45e1dd0cae5d89e9d03d203e3a5635d
+  metadata.gz: 3fa571b528df159a9d83210a7f91f03cdb57cfa497dcaa312ad831392b4ab3ae
+  data.tar.gz: e536b9101471873b9ba3df2f422ec13221db3941e240c8731bcba1e79e361431
 SHA512:
-  metadata.gz: 2568587bc47fe2eb892fc7e9f8f4981aceaa06eef4b27ad54cb427e9082cc23571a2c26f8ae9380dfcd52fbb40f38a77ad0d2282e7ada54d8744e3e21edcd301
-  data.tar.gz: 4b8505d33b3eef150aeb76f23548f5983740d1940488a0ee1c7d6e515cd249e5fa74fbdadb72543a91104ca9ce609eb0f374dd01c033db8eee2bb7585525b09f
+  metadata.gz: 0a759070a8972bba5f92705f9abc5bc7e23038d1c92873b35457709dfeed1e3c5a03acfd426feca37760fe849e5d173faf742e84231d97544b13f38e91cba192
+  data.tar.gz: cca4eeff40165f757f60311ee9db9a33802cfb1733c5de09aba15f63dce4aca1d1d38c74af1701b8ce689fac41ee994fd6b6de90f231c6a3ce1b76a026b1fce1

data/.rubocop.yml

@@ -8,7 +8,7 @@ plugins:
 - rubocop-rspec
 
 AllCops:
-  TargetRubyVersion: 3.0
+  TargetRubyVersion: 3.1
   NewCops: enable
   Exclude:
     - 'vendor/**/*'

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2025-07-05 22:42:28 UTC using RuboCop version 1.77.0.
+# on 2025-07-17 08:10:53 UTC using RuboCop version 1.78.0.
 # 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
@@ -13,7 +13,30 @@ Gemspec/DuplicatedAssignment:
   Exclude:
     - 'suma.gemspec'
 
-# Offense count: 57
+# Offense count: 1
+# Configuration parameters: Severity, Include.
+# Include: **/*.gemspec
+Gemspec/RequiredRubyVersion:
+  Exclude:
+    - 'suma.gemspec'
+
+# Offense count: 17
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle, IndentationWidth.
+# SupportedStyles: with_first_argument, with_fixed_indentation
+Layout/ArgumentAlignment:
+  Exclude:
+    - 'lib/suma/cli/validate_ascii.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle.
+# SupportedStyles: normal, indented_internal_methods
+Layout/IndentationConsistency:
+  Exclude:
+    - 'lib/suma/glossarist_extensions.rb'
+
+# Offense count: 90
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, IgnoreCopDirectives, AllowedPatterns, SplitStrings.
 # URISchemes: http, https
@@ -21,10 +44,10 @@ Layout/LineLength:
   Exclude:
     - 'lib/suma/cli.rb'
     - 'lib/suma/cli/build.rb'
-    - 'lib/suma/cli/extract_terms.rb'
     - 'lib/suma/cli/validate.rb'
     - 'lib/suma/cli/validate_ascii.rb'
     - 'lib/suma/cli/validate_links.rb'
+    - 'lib/suma/glossarist_extensions.rb'
     - 'lib/suma/processor.rb'
     - 'lib/suma/schema_attachment.rb'
     - 'lib/suma/schema_collection.rb'
@@ -34,6 +57,13 @@ Layout/LineLength:
     - 'spec/suma/cli/validate_ascii_spec.rb'
     - 'suma.gemspec'
 
+# Offense count: 22
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AllowInHeredoc.
+Layout/TrailingWhitespace:
+  Exclude:
+    - 'lib/suma/cli/validate_ascii.rb'
+
 # Offense count: 1
 # Configuration parameters: IgnoreLiteralBranches, IgnoreConstantBranches, IgnoreDuplicateElseBranch.
 Lint/DuplicateBranch:
@@ -46,33 +76,48 @@ Lint/DuplicateMethods:
     - 'lib/suma/cli/validate_ascii.rb'
     - 'lib/suma/express_schema.rb'
 
-# Offense count: 20
+# Offense count: 2
+# This cop supports unsafe autocorrection (--autocorrect-all).
+Lint/NonAtomicFileOperation:
+  Exclude:
+    - 'lib/suma/glossarist_extensions.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AutoCorrect, IgnoreEmptyBlocks, AllowUnusedKeywordArguments.
+Lint/UnusedBlockArgument:
+  Exclude:
+    - 'lib/suma/glossarist_extensions.rb'
+
+# Offense count: 23
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Exclude:
     - 'lib/suma/cli/extract_terms.rb'
     - 'lib/suma/cli/validate_ascii.rb'
     - 'lib/suma/cli/validate_links.rb'
+    - 'lib/suma/glossarist_extensions.rb'
     - 'lib/suma/schema_attachment.rb'
     - 'lib/suma/schema_document.rb'
     - 'lib/suma/thor_ext.rb'
 
-# Offense count: 1
+# Offense count: 3
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns, inherit_mode.
 # AllowedMethods: refine
 Metrics/BlockLength:
   Max: 64
 
-# Offense count: 8
+# Offense count: 9
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/CyclomaticComplexity:
   Exclude:
     - 'lib/suma/cli/extract_terms.rb'
     - 'lib/suma/cli/validate_ascii.rb'
     - 'lib/suma/cli/validate_links.rb'
+    - 'lib/suma/glossarist_extensions.rb'
     - 'lib/suma/thor_ext.rb'
 
-# Offense count: 30
+# Offense count: 36
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Max: 107
@@ -82,13 +127,14 @@ Metrics/MethodLength:
 Metrics/ParameterLists:
   Max: 6
 
-# Offense count: 5
+# Offense count: 6
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/PerceivedComplexity:
   Exclude:
     - 'lib/suma/cli/extract_terms.rb'
     - 'lib/suma/cli/validate_ascii.rb'
     - 'lib/suma/cli/validate_links.rb'
+    - 'lib/suma/glossarist_extensions.rb'
 
 # Offense count: 5
 # Configuration parameters: EnforcedStyle, CheckMethodNames, CheckSymbols, AllowedIdentifiers, AllowedPatterns.
@@ -114,13 +160,14 @@ RSpec/ExampleLength:
 RSpec/MultipleExpectations:
   Max: 12
 
-# Offense count: 1
+# Offense count: 2
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: AutoCorrect, EnforcedStyle, AllowComments.
 # SupportedStyles: empty, nil, both
 Style/EmptyElse:
   Exclude:
     - 'lib/suma/cli/validate_links.rb'
+    - 'lib/suma/glossarist_extensions.rb'
 
 # Offense count: 4
 # This cop supports safe autocorrection (--autocorrect).
@@ -129,8 +176,37 @@ Style/EmptyElse:
 Style/FormatStringToken:
   EnforcedStyle: unannotated
 
+# Offense count: 2
+# This cop supports unsafe autocorrection (--autocorrect-all).
+# Configuration parameters: AllowedReceivers.
+# AllowedReceivers: Thread.current
+Style/HashEachMethods:
+  Exclude:
+    - 'lib/suma/glossarist_extensions.rb'
+
+# Offense count: 2
+# This cop supports unsafe autocorrection (--autocorrect-all).
+Style/IdenticalConditionalBranches:
+  Exclude:
+    - 'lib/suma/glossarist_extensions.rb'
+
+# Offense count: 3
+# This cop supports unsafe autocorrection (--autocorrect-all).
+# Configuration parameters: ConvertCodeThatCanStartToReturnNil, AllowedMethods, MaxChainLength.
+# AllowedMethods: present?, blank?, presence, try, try!
+Style/SafeNavigation:
+  Exclude:
+    - 'lib/suma/glossarist_extensions.rb'
+
 # Offense count: 1
 # Configuration parameters: Max.
 Style/SafeNavigationChainLength:
   Exclude:
     - 'lib/suma/cli/extract_terms.rb'
+
+# Offense count: 4
+# This cop supports unsafe autocorrection (--autocorrect-all).
+# Configuration parameters: Mode.
+Style/StringConcatenation:
+  Exclude:
+    - 'lib/suma/cli/validate_ascii.rb'

data/README.adoc

@@ -291,8 +291,9 @@ Replacement: AsciiMath: xx
 
 === Generate schemas command
 
-The `suma generate_schemas` command generates a schema manifest file containing
-all schemas defined in the Metanorma manifest file.
+The `suma generate_schemas` command generates an EXPRESS schema manifest file
+containing all schemas of documents referenced in the Metanorma manifest file,
+recursively.
 
 [source,sh]
 ----
@@ -331,6 +332,10 @@ out which schemas the document includes.
 
 === Extract terms command
 
+The "extract terms" command is implemented for ISO 10303-2, and could also be
+used for other EXPRESS schema collections that require term extraction for
+glossary or dictionary applications.
+
 The `suma extract_terms` command extracts terms from EXPRESS schemas and
 generates a Glossarist v2 dataset in the output directory. This command processes
 various types of STEP schemas and creates standardized terminology datasets
@@ -357,36 +362,35 @@ Options:
 
 The command supports extraction from the following EXPRESS schema types:
 
-* **ARM (Application Reference Model)** - Application module schemas ending with `_arm`
-* **MIM (Module Implementation Model)** - Application module schemas ending with `_mim`
+* **ARM (application reference model)** - application module schemas ending with `_arm`
+* **MIM (module implementation model)** - application module schemas ending with `_mim`
 * **Resource schemas** - General resource schemas
-* **BOM (Business Object Model)** - Business object model schemas ending with `_bom`
+* **BOM (business object model)** - business object model schemas ending with `_bom`
+
+NOTE: The "Long Form" EXPRESS schemas (ending with `_lf`) should be excluded
+from the manifest file as they do not contain definitions of `ENTITY` objects.
 
-==== Extracted terms
 
-The command extracts the following types of terms from EXPRESS schemas:
+==== Extracted concepts
 
-* **Entities** - EXPRESS entity definitions with their attributes and relationships
-* **Types** - EXPRESS type definitions including enumerations and select types
-* **Functions** - EXPRESS function definitions
-* **Procedures** - EXPRESS procedure definitions
-* **Constants** - EXPRESS constant definitions
+The command extracts `ENTITY` objects from EXPRESS schemas, with the following
+information:
 
-Each extracted term includes:
+. a unique identifier in form of `{schema_name}.{entity_name}` (where `entity_name` is a slug
+  derived from the `ENTITY` name);
+. a generated definition depending on the schema type and entity type;
+. a "Note to entry" from its first coherent textual element described in Annotated EXPRESS;
+. source information including: schema name and schema version;
+. domain in the pattern of: `{domain_type}: {schema_name}`, where `domain_type` is one of
+  `application module`, `resource`, or `business object model`.
 
-* Unique identifier based on schema and term name
-* Term definition and description
-* Source schema information
-* Appropriate domain classification (application module, resource, or business object model)
 
 ==== Output format
 
 The command generates a Glossarist v2 compliant dataset with:
 
-* `concept/` directory containing concept definition files
-* `localized_concept/` directory containing localized concept files
-* YAML format following Glossarist v2 schema specifications
-* Proper cross-references and citations to source schemas
+* `concept/` directory containing concept definition files in YAML
+* `localized_concept/` directory containing localized concept files in YAML
 
 .To extract terms from a schema manifest file
 [example]
@@ -394,7 +398,8 @@ The command generates a Glossarist v2 compliant dataset with:
 [source,sh]
 ----
 $ bundle exec suma extract_terms schemas-smrl-all.yml glossarist_output
-# => generates glossarist_output/concept/*.yaml and glossarist_output/localized_concept/*.yaml
+# => generates glossarist_output/concept/*.yaml and
+#      glossarist_output/localized_concept/*.yaml
 ----
 ====
 
@@ -408,7 +413,6 @@ $ bundle exec suma extract_terms schemas-activity-modules.yml terms_output
 ----
 ====
 
-The generated dataset is meant to be used for ISO 10303-2.
 
 
 == Usage: Ruby

data/lib/suma/cli/extract_terms.rb

@@ -103,6 +103,10 @@ module Suma
               language_code: language_code,
               source_ref: source_ref,
             )
+            localized_concept_id = get_localized_concept_identifier(
+              schema, entity, language_code
+            )
+            localized_concept.uuid = localized_concept_id
 
             managed_data = Glossarist::ManagedConceptData.new.tap do |data|
               data.id = get_entity_identifier(schema, entity)
@@ -111,9 +115,7 @@ module Suma
               data.localizations[language_code] = localized_concept
               # uuid is automatically set from the serialization of the object
               data.localized_concepts = {
-                language_code => get_localized_concept_identifier(
-                  schema, entity, language_code
-                ),
+                language_code => localized_concept_id,
               }
             end
 

data/lib/suma/cli/generate_schemas.rb

@@ -64,8 +64,6 @@ module Suma
       def load_yaml(file_path)
         YAML.safe_load(
           File.read(file_path, encoding: "UTF-8"),
-          permitted_classes: [Date, Time, Symbol],
-          permitted_symbols: [],
           aliases: true,
         )
       end

data/lib/suma/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Suma
-  VERSION = "0.1.16"
+  VERSION = "0.1.18"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: suma
 version: !ruby/object:Gem::Version
-  version: 0.1.16
+  version: 0.1.18
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-07-11 00:00:00.000000000 Z
+date: 2025-07-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: expressir