unitsml 0.6.5 → 0.6.7

data/lib/unitsml/utility.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require "htmlentities"
+
 module Unitsml
   module Utility
     # Unit to dimension
@@ -109,8 +111,7 @@ module Unitsml
             prefix = if k.prefix_reference.nil?
                        u.prefix
                      else
-                       combine_prefixes(prefix_object(k.prefix_reference),
-                                        u.prefix)
+                       combine_prefixes(k.prefix_reference, u.prefix)
                      end
             unit_name = Unitsdb.units.find_by_id(k.unit_reference.id).symbols.first.id
             exponent = (k.power&.to_i || 1) * (u.power_numerator&.to_f || 1)
@@ -127,8 +128,7 @@ module Unitsml
           else
             m[-1][:unit]&.power_numerator = Number.new(numerator_value(k, m))
             m[-1] = {
-              prefix: combine_prefixes(prefix_object(m[-1][:prefix]),
-                                       prefix_object(k[:prefix])),
+              prefix: combine_prefixes(m[-1][:prefix], k[:prefix]),
               unit: m[-1][:unit],
             }
           end
@@ -144,72 +144,23 @@ module Unitsml
         object_hash[:unit]&.power_numerator&.to_f || 1
       end
 
-      def prefix_object(prefix)
-        return nil if prefix.nil?
-        return prefix if prefix_like?(prefix)
-
-        if prefix.is_a?(String)
-          return nil unless Unitsdb.prefixes_array.any?(prefix)
-
-          return Prefix.new(prefix)
-        end
-
-        return Unitsdb.prefixes.find_by_id(prefix.id) if prefix.respond_to?(:id)
-
-        prefix
-      end
-
       def combine_prefixes(p1, p2)
-        p1 = prefix_object(p1)
-        p2 = prefix_object(p2)
-        return nil if p1.nil? && p2.nil?
-        return prefix_symbolid(p1) if p2.nil?
-        return prefix_symbolid(p2) if p1.nil?
-        return UNKNOWN if prefix_base(p1) != prefix_base(p2)
+        a1 = PrefixAdapter.wrap(p1)
+        a2 = PrefixAdapter.wrap(p2)
+        return nil if a1.null? && a2.null?
+        return a1.symbolid if a2.null?
+        return a2.symbolid if a1.null?
+        return UNKNOWN if a1.base != a2.base
 
         Unitsdb.prefixes_array.each do |prefix_name|
-          p = prefix_object(prefix_name)
-          return p if prefix_base(p) == prefix_base(p1) &&
-            prefix_power(p) == prefix_power(p1) + prefix_power(p2)
+          candidate = PrefixAdapter.from_name(prefix_name)
+          return candidate.raw if candidate.base == a1.base &&
+            candidate.power == a1.power + a2.power
         end
 
         UNKNOWN
       end
 
-      def prefix_like?(prefix)
-        prefix.respond_to?(:base) && prefix.respond_to?(:power) &&
-          (prefix.respond_to?(:symbolid) || prefix.respond_to?(:symbols))
-      end
-
-      def prefix_symbolid(prefix)
-        return prefix.symbolid if prefix.respond_to?(:symbolid)
-
-        prefix_record = resolved_prefix(prefix)
-        return unless prefix_record
-
-        prefix_record.symbols&.first&.ascii
-      end
-
-      def prefix_base(prefix)
-        return prefix.base if prefix.respond_to?(:base)
-
-        resolved_prefix(prefix)&.base
-      end
-
-      def prefix_power(prefix)
-        return prefix.power if prefix.respond_to?(:power)
-
-        resolved_prefix(prefix)&.power
-      end
-
-      def resolved_prefix(prefix)
-        return prefix if prefix.nil?
-        return prefix if prefix.respond_to?(:symbols) && prefix.respond_to?(:base) && prefix.respond_to?(:power)
-        return Unitsdb.prefixes.find_by_id(prefix.id) if prefix.respond_to?(:id)
-
-        prefix
-      end
-
       def unit(units, formula, dims, norm_text, name, options)
         attributes = {
           id: unit_id(norm_text),
@@ -219,13 +170,11 @@ module Unitsml
           root_units: rootunits(units),
         }
         attributes[:dimension_url] = "##{dim_id(dims)}" if dims
-        Model::Unit.new(**attributes, lutaml_register: Configuration.context.id).to_xml
-          .force_encoding("UTF-8")
-          .gsub("&lt;", "<")
-          .gsub("&gt;", ">")
-          .gsub("&amp;", "&")
-          .gsub(/−/, "&#x2212;")
-          .gsub(/⋅/, "&#x22c5;")
+        xml = Model::Unit.new(
+          **attributes,
+          lutaml_register: Configuration.context.id,
+        ).to_xml
+        Xml::Formatter.format_unit(xml)
       end
 
       def unitname(text, name)
@@ -275,10 +224,11 @@ module Unitsml
 
         dim_attrs = { id: dim_id }
         dimid2dimensions(dim_id)&.compact&.each { |u| dimension1(u, dim_attrs) }
-        Model::Dimension.new(
+        xml = Model::Dimension.new(
           dim_attrs,
           lutaml_register: Configuration.context.id,
-        ).to_xml.force_encoding("UTF-8")
+        ).to_xml
+        xml.force_encoding("UTF-8")
       end
 
       def dimension1(dim, dims_hash)
@@ -323,34 +273,52 @@ module Unitsml
       end
 
       def prefix_xml(prefix, options)
-        Model::Prefix.new(
+        xml = Model::Prefix.new(
           prefix_attributes(prefix, options),
           lutaml_register: Configuration.context.id,
-        ).to_xml.force_encoding("UTF-8").gsub("&amp;", "&")
+        ).to_xml
+        Xml::Formatter.format_prefix(xml)
       end
 
       def prefix_attributes(prefix, options)
+        adapter = PrefixAdapter.wrap(prefix)
         {
-          prefix_base: prefix&.base,
-          prefix_power: prefix&.power,
-          id: prefix&.id,
-          name: prefix_name(prefix),
+          prefix_base: adapter.base,
+          prefix_power: adapter.power,
+          id: prefix_id(prefix, adapter),
+          name: prefix_name(prefix, adapter),
           symbol: prefix_symbols(prefix, options),
         }
       end
 
-      def prefix_name(prefix)
+      def prefix_id(prefix, adapter)
+        if prefix.is_a?(Unitsml::Prefix)
+          prefix.id
+        else
+          adapter.raw&.identifiers&.find do |i|
+            i.type == "nist"
+          end&.id
+        end
+      end
+
+      def prefix_name(prefix, adapter)
+        name_value = if prefix.is_a?(Unitsml::Prefix)
+                       prefix.name
+                     elsif adapter.raw.is_a?(::Unitsdb::Prefix)
+                       adapter.raw.names.find { |n| n.lang == "en" }&.value
+                     end
         Model::Prefixes::Name.new(
-          content: prefix&.name,
+          content: name_value,
           lutaml_register: Configuration.context.id,
         )
       end
 
       def prefix_symbols(prefix, options)
+        adapter = PrefixAdapter.wrap(prefix)
         PREFIX_SYMBOL_METHODS.map do |type, method_name|
           Model::Prefixes::Symbol.new(
             type: type,
-            content: prefix&.public_send(method_name, options),
+            content: adapter.raw&.public_send(method_name, options),
             lutaml_register: Configuration.context.id,
           )
         end
@@ -393,10 +361,11 @@ module Unitsml
 
         dim_attrs = { id: dim_id(dims) }
         dims.map { |u| dimension1(u, dim_attrs) }
-        Model::Dimension.new(
+        xml = Model::Dimension.new(
           **dim_attrs,
           lutaml_register: Configuration.context.id,
-        ).to_xml.force_encoding("UTF-8")
+        ).to_xml
+        xml.force_encoding("UTF-8")
       end
 
       def quantity(normtext, instance)
@@ -411,21 +380,21 @@ module Unitsml
 
       def unit_nist_id(unit)
         return unless unit
-        return unit.nist_id if unit.respond_to?(:nist_id)
+        return unit.nist_id if unit.is_a?(Unitsml::Unitsdb::Unit)
 
         unit.identifiers&.find { |identifier| identifier.type == "nist" }&.id
       end
 
       def unit_en_name(unit)
         return unless unit
-        return unit.en_name if unit.respond_to?(:en_name)
+        return unit.en_name if unit.is_a?(Unitsml::Unitsdb::Unit)
 
         unit.names&.find { |name| name.lang == "en" }&.value
       end
 
       def unit_dimension_id(unit)
         return unless unit
-        return unit.dimension_url if unit.respond_to?(:dimension_url)
+        return unit.dimension_url if unit.is_a?(Unitsml::Unitsdb::Unit)
 
         unit.dimension_reference&.id ||
           quantity_dimension_id(quantity_instance(unit.quantity_references&.first&.id))
@@ -441,19 +410,21 @@ module Unitsml
       end
 
       def model_quantity_xml(id, url)
-        Model::Quantity.new(
+        xml = Model::Quantity.new(
           id: id,
           name: quantity_name(id),
           dimension_url: url,
           lutaml_register: Configuration.context.id,
-        ).to_xml.force_encoding("UTF-8")
+        ).to_xml
+        xml.force_encoding("UTF-8")
       end
 
       def quantity_name(id)
         quantity_instance(id)&.names&.filter_map do |name|
           next unless name.lang == "en"
 
-          Model::Quantities::Name.new(content: name.value, lutaml_register: Configuration.context.id)
+          Model::Quantities::Name.new(content: name.value,
+                                      lutaml_register: Configuration.context.id)
         end
       end
 

data/lib/unitsml/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Unitsml
-  VERSION = "0.6.5"
+  VERSION = "0.6.7"
 end

data/lib/unitsml/xml/formatter.rb

@@ -0,0 +1,63 @@
+# frozen_string_literal: true
+
+module Unitsml
+  module Xml
+    # Owns the canonical post-processing applied to XML emitted by
+    # Unitsml::Model::* before it is returned to callers. Previously
+    # inlined as repeated `.gsub` chains at six call sites in
+    # Unitsml::Utility — this module is the single source of truth.
+    #
+    # The chain has two logical phases:
+    #   1. Decode XML entities that lutaml-model emitted but UnitsML
+    #      consumers expect as raw characters (`&lt;` → `<`, etc.).
+    #   2. Re-encode Unicode mathematical symbols (minus, dot operator)
+    #      as numeric character references for downstream XML consumers
+    #      that aren't guaranteed UTF-8 clean transport.
+    module Formatter
+      ENTITY_DECODINGS = {
+        "&lt;" => "<",
+        "&gt;" => ">",
+        "&amp;" => "&",
+      }.freeze
+
+      UNIT_SYMBOL_ENCODINGS = {
+        "−" => "&#x2212;",
+        "⋅" => "&#x22c5;",
+      }.freeze
+
+      module_function
+
+      # Full post-processing for UnitsML <Unit> XML: entity decode
+      # followed by Unicode → numeric-reference encoding.
+      def format_unit(xml)
+        decoded = decode_entities(xml)
+        encode_unit_symbols(decoded)
+      end
+
+      # Minimal post-processing for <Prefix> XML: only the ampersand
+      # decode is needed (UnitsML prefix symbols never contain the
+      # other reserved characters or Unicode math symbols).
+      def format_prefix(xml)
+        unfrozen(xml).force_encoding("UTF-8").gsub("&amp;", "&")
+      end
+
+      def decode_entities(xml)
+        buffer = unfrozen(xml).force_encoding("UTF-8")
+        ENTITY_DECODINGS.reduce(buffer) do |acc, (from, to)|
+          acc.gsub(from, to)
+        end
+      end
+
+      def encode_unit_symbols(xml)
+        UNIT_SYMBOL_ENCODINGS.reduce(xml) do |buffer, (from, to)|
+          buffer.gsub(from, to)
+        end
+      end
+
+      def unfrozen(xml)
+        xml.frozen? ? xml.dup : xml
+      end
+      private_class_method :unfrozen
+    end
+  end
+end

data/lib/unitsml/xml.rb

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+module Unitsml
+  module Xml
+    autoload :Formatter, "unitsml/xml/formatter"
+  end
+end

data/lib/unitsml.rb

@@ -21,12 +21,14 @@ module Unitsml
   autoload :Parse, "unitsml/parse"
   autoload :Parser, "unitsml/parser"
   autoload :Prefix, "unitsml/prefix"
+  autoload :PrefixAdapter, "unitsml/prefix_adapter"
   autoload :Sqrt, "unitsml/sqrt"
   autoload :Transform, "unitsml/transform"
   autoload :Unit, "unitsml/unit"
   autoload :Unitsdb, "unitsml/unitsdb"
   autoload :Utility, "unitsml/utility"
   autoload :VERSION, "unitsml/version"
+  autoload :Xml, "unitsml/xml"
 
   def parse(string)
     Unitsml::Parser.new(string).parse

data/unitsml.gemspec

@@ -33,9 +33,9 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_dependency "htmlentities"
-  spec.add_dependency "ox"
   spec.add_dependency "lutaml-model", "~> 0.8.0"
   spec.add_dependency "mml", "~> 2.3.6"
+  spec.add_dependency "ox"
   spec.add_dependency "parslet"
-  spec.add_dependency "unitsdb", "~> 2.2.2"
+  spec.add_dependency "unitsdb", "~> 2.2.4"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unitsml
 version: !ruby/object:Gem::Version
-  version: 0.6.5
+  version: 0.6.7
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-05 00:00:00.000000000 Z
+date: 2026-06-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities
@@ -25,47 +25,47 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: ox
+  name: lutaml-model
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.8.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.8.0
 - !ruby/object:Gem::Dependency
-  name: lutaml-model
+  name: mml
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.8.0
+        version: 2.3.6
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.8.0
+        version: 2.3.6
 - !ruby/object:Gem::Dependency
-  name: mml
+  name: ox
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.3.6
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.3.6
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: parslet
   requirement: !ruby/object:Gem::Requirement
@@ -86,14 +86,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.2.2
+        version: 2.2.4
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.2.2
+        version: 2.2.4
 description: Library to work with UnitsML in Ruby
 email:
 - open.source@ribose.com
@@ -103,6 +103,7 @@ extra_rdoc_files: []
 files:
 - ".github/workflows/dependent-repos.json"
 - ".github/workflows/depenedent-gems.yml"
+- ".github/workflows/opal.yml"
 - ".github/workflows/rake.yml"
 - ".github/workflows/release.yml"
 - ".gitignore"
@@ -123,8 +124,10 @@ files:
 - lib/unitsml/dimension.rb
 - lib/unitsml/errors.rb
 - lib/unitsml/errors/base_error.rb
+- lib/unitsml/errors/invalid_model_error.rb
 - lib/unitsml/errors/opal_payload_not_bundled_error.rb
 - lib/unitsml/errors/plurimath_load_error.rb
+- lib/unitsml/errors/unsupported_payload_type_error.rb
 - lib/unitsml/extender.rb
 - lib/unitsml/fenced.rb
 - lib/unitsml/fenced_numeric.rb
@@ -159,9 +162,13 @@ files:
 - lib/unitsml/model/units/system.rb
 - lib/unitsml/namespace.rb
 - lib/unitsml/number.rb
+- lib/unitsml/opal.rb
+- lib/unitsml/opal/database_payload.rb
+- lib/unitsml/opal/payload_generator.rb
 - lib/unitsml/parse.rb
 - lib/unitsml/parser.rb
 - lib/unitsml/prefix.rb
+- lib/unitsml/prefix_adapter.rb
 - lib/unitsml/sqrt.rb
 - lib/unitsml/transform.rb
 - lib/unitsml/unit.rb
@@ -170,6 +177,7 @@ files:
 - lib/unitsml/unitsdb/dimension.rb
 - lib/unitsml/unitsdb/dimension_details.rb
 - lib/unitsml/unitsdb/dimensions.rb
+- lib/unitsml/unitsdb/finders.rb
 - lib/unitsml/unitsdb/prefix_reference.rb
 - lib/unitsml/unitsdb/prefixes.rb
 - lib/unitsml/unitsdb/quantities.rb
@@ -177,6 +185,8 @@ files:
 - lib/unitsml/unitsdb/units.rb
 - lib/unitsml/utility.rb
 - lib/unitsml/version.rb
+- lib/unitsml/xml.rb
+- lib/unitsml/xml/formatter.rb
 - unitsml.gemspec
 homepage: https://github.com/unitsml/unitsml-ruby
 licenses: