chemicalml 0.2.1 → 0.3.0

data/lib/tasks/scrape_fixtures.rake

@@ -1,21 +1,21 @@
 # frozen_string_literal: true
 
-require "net/http"
-require "uri"
-require "fileutils"
-require "cgi"
+require 'net/http'
+require 'uri'
+require 'fileutils'
+require 'cgi'
 
 # Idempotent scraper for xml-cml.org example CML files. Walks the
 # HTML index pages, extracts the embedded CML, and writes one `.cml`
 # file per example under `spec/fixtures/`.
 module FixturesScrape
-  BASE = "http://www.xml-cml.org".freeze
+  BASE = 'http://www.xml-cml.org'
 
   # Map of remote index URL => local target directory.
   INDEXES = {
-    "#{BASE}/examples/schema3/molecular/" => "spec/fixtures/schema3/molecular",
-    "#{BASE}/examples/schema3/compchem/"  => "spec/fixtures/schema3/compchem",
-    "#{BASE}/examples/schema24/"          => "spec/fixtures/schema24"
+    "#{BASE}/examples/schema3/molecular/" => 'spec/fixtures/schema3/molecular',
+    "#{BASE}/examples/schema3/compchem/" => 'spec/fixtures/schema3/compchem',
+    "#{BASE}/examples/schema24/" => 'spec/fixtures/schema24'
   }.freeze
 
   def self.scrape_all
@@ -41,7 +41,7 @@ module FixturesScrape
   end
 
   def self.extract_example_links(html, base_url)
-    hrefs = html.scan(/<a[^>]+href=["']([^"']+\.html?)["'][^>]*>([^<]+)<\/a>/i)
+    hrefs = html.scan(%r{<a[^>]+href=["']([^"']+\.html?)["'][^>]*>([^<]+)</a>}i)
     hrefs.map do |raw_href, raw_title|
       href = URI.join(base_url, raw_href).to_s
       title = CGI.unescapeHTML(raw_title.strip)
@@ -70,63 +70,62 @@ module FixturesScrape
 
     cml = extract_cml(body)
     unless cml
-      log_failure(url, target_dir, reason: "no <cml> block found")
+      log_failure(url, target_dir, reason: 'no <cml> block found')
       return
     end
 
-    File.write(path, cml.strip + "\n")
+    File.write(path, "#{cml.strip}\n")
     puts "  saved   #{slug}.cml"
   end
 
   def self.extract_cml(html)
-    match = html.match(/<cml[^>]*>.*<\/cml>/m)
+    match = html.match(%r{<cml[^>]*>.*</cml>}m)
     return match[0] if match
 
-    match = html.match(/<(?:cml|module|dictionary|molecule|reaction|unitList|unitTypeList)[^>]*>.*<\/(?:cml|module|dictionary|molecule|reaction|unitList|unitTypeList)>/m)
+    match = html.match(%r{<(?:cml|module|dictionary|molecule|reaction|unitList|unitTypeList)[^>]*>.*</(?:cml|module|dictionary|molecule|reaction|unitList|unitTypeList)>}m)
     match && match[0]
   end
 
   def self.slugify(title)
     title.downcase
-         .gsub(/[^a-z0-9]+/, "_")
-         .gsub(/^_+|_+$/, "")
+         .gsub(/[^a-z0-9]+/, '_')
+         .gsub(/^_+|_+$/, '')
   end
 
   def self.http_get(url, limit = 5)
-    raise "too many redirects" if limit.zero?
+    raise 'too many redirects' if limit.zero?
 
     uri = URI(url)
     http = Net::HTTP.new(uri.host, uri.port)
     http.use_ssl = true if uri.is_a?(URI::HTTPS)
     http.read_timeout = 30
-    req = Net::HTTP::Get.new(uri, "User-Agent" => "chemicalml-gem-fixtures-scrape")
+    req = Net::HTTP::Get.new(uri, 'User-Agent' => 'chemicalml-gem-fixtures-scrape')
     res = http.request(req)
 
     case res
     when Net::HTTPSuccess then res.body
-    when Net::HTTPRedirection then http_get(res["location"], limit - 1)
-    else nil
+    when Net::HTTPRedirection then http_get(res['location'], limit - 1)
     end
   rescue StandardError => e
     warn "  error fetching #{url}: #{e.message}"
     nil
   end
 
-  def self.log_failure(url, target_dir, reason: "fetch failed")
-    File.open(File.join(target_dir, ".scrape-log"), "a") do |f|
+  def self.log_failure(url, target_dir, reason: 'fetch failed')
+    File.open(File.join(target_dir, '.scrape-log'), 'a') do |f|
       f.puts "#{Time.now.utc.iso8601}\t#{url}\t#{reason}"
     end
   end
 
   def self.project_root
-    File.expand_path("../..", __dir__)
+    File.expand_path('../..', __dir__)
   end
 end
 
-require "time"
+require 'time'
 
 namespace :fixtures do
-  desc "Scrape every xml-cml.org example CML into spec/fixtures/. Idempotent."
+  desc 'Scrape every xml-cml.org example CML into spec/fixtures/. Idempotent.'
   task :scrape do
     FixturesScrape.scrape_all
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: chemicalml
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.3.0
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-07-15 00:00:00.000000000 Z
+date: 2026-07-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: lutaml-model
@@ -29,7 +29,8 @@ description: ChemML provides a lutaml-model-based Ruby object model for the Chem
   fidelity. Designed as a sibling model to other chemistry model layers (e.g. AsciiChem).
 email:
 - open.source@ribose.com
-executables: []
+executables:
+- chemicalml
 extensions: []
 extra_rdoc_files: []
 files:
@@ -108,6 +109,40 @@ files:
 - TODO.align/58-remaining-models.md
 - TODO.align/59-wire-new-models-translator.md
 - TODO.align/60-docs-and-final-verification.md
+- TODO.align/61-parallel-array-attrs.md
+- TODO.align/62-per-element-attribute-gaps.md
+- TODO.align/63-universal-children-mixin.md
+- TODO.align/64-per-element-child-gaps.md
+- TODO.align/65-simple-unit-convention.md
+- TODO.align/66-schema24-legacy-children.md
+- TODO.align/67-final-verification.md
+- TODO.align/68-detection-coverage.md
+- TODO.align/69-json-yaml-roundtrip.md
+- TODO.align/70-iterative-walker.md
+- TODO.align/71-violation-value.md
+- TODO.align/72-close-child-gaps.md
+- TODO.align/73-schema24-parse-limitation.md
+- TODO.align/74-final-verification-round18.md
+- TODO.align/75-key-value-mappings.md
+- TODO.align/76-schema24-workaround.md
+- TODO.align/77-convention-coverage-matrix.md
+- TODO.align/78-fixture-audit.md
+- TODO.align/79-final-verification-round19.md
+- TODO.align/80-xsd-enum-constants.md
+- TODO.align/81-enum-validation-constraints.md
+- TODO.align/82-reference-resolver.md
+- TODO.align/83-toml-roundtrip.md
+- TODO.align/84-final-verification-round21.md
+- TODO.align/85-bond-distinct-atoms.md
+- TODO.align/86-references-should-resolve.md
+- TODO.align/87-cli-utility.md
+- TODO.align/88-diverse-fixtures.md
+- TODO.align/89-final-verification-round22.md
+- TODO.align/90-bond-stereo-completeness.md
+- TODO.align/91-atomparity-distinct.md
+- TODO.align/92-unit-dictionary-completeness.md
+- TODO.align/93-yard-docs.md
+- TODO.align/94-final-verification-round23.md
 - TODO.align/README.md
 - TODO.align/README.round10.md
 - TODO.align/README.round11.md
@@ -116,8 +151,26 @@ files:
 - TODO.align/README.round14.md
 - TODO.align/README.round15.md
 - TODO.align/README.round16.md
+- TODO.align/README.round17.md
+- TODO.align/README.round18.md
+- TODO.align/README.round19.md
 - TODO.align/README.round2.md
+- TODO.align/README.round20.md
+- TODO.align/README.round21.md
+- TODO.align/README.round22.md
+- TODO.align/README.round23.md
+- TODO.align/README.round24.md
+- TODO.align/README.round25.md
+- TODO.align/README.round26.md
+- TODO.align/README.round27.md
+- TODO.align/README.round28.md
+- TODO.align/README.round29.md
 - TODO.align/README.round3.md
+- TODO.align/README.round30.md
+- TODO.align/README.round31.md
+- TODO.align/README.round32.md
+- TODO.align/README.round33.md
+- TODO.align/README.round34.md
 - TODO.align/README.round4.md
 - TODO.align/README.round5.md
 - TODO.align/README.round6.md
@@ -144,7 +197,21 @@ files:
 - data/dictionaries/unit_non_si.yaml
 - data/dictionaries/unit_si.yaml
 - data/dictionaries/unit_type.yaml
+- docs/constraints.md
+- docs/generate_constraint_docs.rb
+- exe/chemicalml
 - lib/chemicalml.rb
+- lib/chemicalml/cli.rb
+- lib/chemicalml/cli/base.rb
+- lib/chemicalml/cli/command.rb
+- lib/chemicalml/cli/constraints_command.rb
+- lib/chemicalml/cli/conventions_command.rb
+- lib/chemicalml/cli/dictionaries_command.rb
+- lib/chemicalml/cli/elements_command.rb
+- lib/chemicalml/cli/enums_command.rb
+- lib/chemicalml/cli/info_command.rb
+- lib/chemicalml/cli/inspect_command.rb
+- lib/chemicalml/cli/validate_command.rb
 - lib/chemicalml/cml.rb
 - lib/chemicalml/cml/aliases.rb
 - lib/chemicalml/cml/base.rb
@@ -178,6 +245,7 @@ files:
 - lib/chemicalml/cml/base/bond_type_list.rb
 - lib/chemicalml/cml/base/cell_parameter.rb
 - lib/chemicalml/cml/base/cml_module.rb
+- lib/chemicalml/cml/base/common_children.rb
 - lib/chemicalml/cml/base/complex_object.rb
 - lib/chemicalml/cml/base/condition_list.rb
 - lib/chemicalml/cml/base/crystal.rb
@@ -286,8 +354,12 @@ files:
 - lib/chemicalml/cml/base/xaxis.rb
 - lib/chemicalml/cml/base/yaxis.rb
 - lib/chemicalml/cml/base/z_matrix.rb
+- lib/chemicalml/cml/canonical_comparison.rb
 - lib/chemicalml/cml/elements.rb
+- lib/chemicalml/cml/enums.rb
 - lib/chemicalml/cml/namespace.rb
+- lib/chemicalml/cml/patterns.rb
+- lib/chemicalml/cml/reference_resolver.rb
 - lib/chemicalml/cml/role.rb
 - lib/chemicalml/cml/role/abundance.rb
 - lib/chemicalml/cml/role/action.rb
@@ -697,6 +769,12 @@ files:
 - lib/chemicalml/context_configuration.rb
 - lib/chemicalml/convention.rb
 - lib/chemicalml/convention/base.rb
+- lib/chemicalml/convention/cascade.rb
+- lib/chemicalml/convention/cascade/constraints.rb
+- lib/chemicalml/convention/cascade/constraints/reaction_scheme_must_have_content.rb
+- lib/chemicalml/convention/cascade/constraints/reaction_step_list_must_contain_steps.rb
+- lib/chemicalml/convention/cascade/constraints/reaction_step_must_have_reaction_or_lists.rb
+- lib/chemicalml/convention/cascade/constraints/reactive_centre_atom_refs_should_be_present.rb
 - lib/chemicalml/convention/compchem.rb
 - lib/chemicalml/convention/compchem/constraints.rb
 - lib/chemicalml/convention/compchem/constraints/array_rules.rb
@@ -706,9 +784,11 @@ files:
 - lib/chemicalml/convention/compchem/constraints/environment_must_not_contain_parameter.rb
 - lib/chemicalml/convention/compchem/constraints/finalization_at_most_one_molecule.rb
 - lib/chemicalml/convention/compchem/constraints/finalization_at_most_one_property_list.rb
+- lib/chemicalml/convention/compchem/constraints/finalization_must_have_content.rb
 - lib/chemicalml/convention/compchem/constraints/finalization_must_not_contain_parameter.rb
 - lib/chemicalml/convention/compchem/constraints/initialization_at_most_one_molecule.rb
 - lib/chemicalml/convention/compchem/constraints/initialization_at_most_one_parameter_list.rb
+- lib/chemicalml/convention/compchem/constraints/initialization_must_have_content.rb
 - lib/chemicalml/convention/compchem/constraints/initialization_must_not_contain_property.rb
 - lib/chemicalml/convention/compchem/constraints/job_list_module_must_have_id.rb
 - lib/chemicalml/convention/compchem/constraints/job_module_at_most_one_environment.rb
@@ -736,34 +816,64 @@ files:
 - lib/chemicalml/convention/molecular/constraints/atom_array_must_be_child_of_molecule_or_formula.rb
 - lib/chemicalml/convention/molecular/constraints/atom_array_must_contain_atoms.rb
 - lib/chemicalml/convention/molecular/constraints/atom_coordinates_must_be_paired.rb
+- lib/chemicalml/convention/molecular/constraints/atom_element_type_should_be_in_periodic_table.rb
 - lib/chemicalml/convention/molecular/constraints/atom_id_must_match_pattern.rb
 - lib/chemicalml/convention/molecular/constraints/atom_ids_unique_within_molecule.rb
 - lib/chemicalml/convention/molecular/constraints/atom_must_have_element_type.rb
 - lib/chemicalml/convention/molecular/constraints/atom_must_have_id.rb
+- lib/chemicalml/convention/molecular/constraints/atom_parity_atom_refs4_should_be_distinct.rb
+- lib/chemicalml/convention/molecular/constraints/atom_parity_should_include_parent_atom.rb
 - lib/chemicalml/convention/molecular/constraints/bond_array_must_be_child_of_molecule.rb
+- lib/chemicalml/convention/molecular/constraints/bond_atom_refs2_should_be_distinct.rb
+- lib/chemicalml/convention/molecular/constraints/bond_id_should_match_pattern.rb
 - lib/chemicalml/convention/molecular/constraints/bond_ids_unique_within_molecule.rb
 - lib/chemicalml/convention/molecular/constraints/bond_must_have_atom_refs2.rb
 - lib/chemicalml/convention/molecular/constraints/bond_must_have_order.rb
 - lib/chemicalml/convention/molecular/constraints/bond_must_reference_atoms_in_same_molecule.rb
 - lib/chemicalml/convention/molecular/constraints/bond_order_other_must_have_dict_ref.rb
+- lib/chemicalml/convention/molecular/constraints/bond_order_should_be_in_enum.rb
 - lib/chemicalml/convention/molecular/constraints/bond_order_should_not_be_numeric.rb
+- lib/chemicalml/convention/molecular/constraints/bond_stereo_atom_refs4_should_be_distinct.rb
 - lib/chemicalml/convention/molecular/constraints/bond_stereo_cis_trans_must_have_atom_refs4.rb
 - lib/chemicalml/convention/molecular/constraints/bond_stereo_other_must_have_dict_ref.rb
+- lib/chemicalml/convention/molecular/constraints/bond_stereo_should_be_in_enum.rb
 - lib/chemicalml/convention/molecular/constraints/bond_stereo_wedge_hash_must_have_atom_refs2.rb
+- lib/chemicalml/convention/molecular/constraints/dict_ref_should_resolve.rb
 - lib/chemicalml/convention/molecular/constraints/molecule_atom_array_mutually_exclusive_with_children.rb
 - lib/chemicalml/convention/molecular/constraints/molecule_bond_array_mutually_exclusive_with_children.rb
+- lib/chemicalml/convention/molecular/constraints/molecule_chirality_should_be_in_enum.rb
 - lib/chemicalml/convention/molecular/constraints/molecule_count_must_not_appear_on_top_level.rb
+- lib/chemicalml/convention/molecular/constraints/molecule_id_should_match_pattern.rb
 - lib/chemicalml/convention/molecular/constraints/molecule_must_have_id.rb
 - lib/chemicalml/convention/molecular/constraints/property_must_have_dict_ref.rb
+- lib/chemicalml/convention/molecular/constraints/property_scalar_data_type_matches_dictionary.rb
+- lib/chemicalml/convention/molecular/constraints/references_should_resolve.rb
 - lib/chemicalml/convention/molecular/constraints/scalar_must_have_data_type.rb
 - lib/chemicalml/convention/registry.rb
+- lib/chemicalml/convention/simple_unit.rb
+- lib/chemicalml/convention/simple_unit/constraints.rb
+- lib/chemicalml/convention/simple_unit/constraints/root_must_be_unit_list.rb
+- lib/chemicalml/convention/simple_unit/constraints/unit_must_have_power.rb
+- lib/chemicalml/convention/simple_unit/constraints/unit_must_have_symbol.rb
+- lib/chemicalml/convention/spectroscopy.rb
+- lib/chemicalml/convention/spectroscopy/constraints.rb
+- lib/chemicalml/convention/spectroscopy/constraints/peak_list_must_contain_peaks.rb
+- lib/chemicalml/convention/spectroscopy/constraints/peak_should_have_values.rb
+- lib/chemicalml/convention/spectroscopy/constraints/spectrum_must_have_content.rb
+- lib/chemicalml/convention/spectroscopy/constraints/spectrum_must_have_convention.rb
+- lib/chemicalml/convention/spectroscopy/constraints/spectrum_must_have_format.rb
 - lib/chemicalml/convention/unit_dictionary.rb
 - lib/chemicalml/convention/unit_dictionary/constraints.rb
 - lib/chemicalml/convention/unit_dictionary/constraints/unit_list_must_contain_at_least_one_unit.rb
 - lib/chemicalml/convention/unit_dictionary/constraints/unit_list_must_have_namespace.rb
 - lib/chemicalml/convention/unit_dictionary/constraints/unit_must_contain_definition.rb
 - lib/chemicalml/convention/unit_dictionary/constraints/unit_must_have_id.rb
+- lib/chemicalml/convention/unit_dictionary/constraints/unit_must_have_multiplier_or_constant_to_si.rb
+- lib/chemicalml/convention/unit_dictionary/constraints/unit_must_have_parent_si.rb
 - lib/chemicalml/convention/unit_dictionary/constraints/unit_must_have_symbol_and_unit_type.rb
+- lib/chemicalml/convention/unit_dictionary/constraints/unit_must_have_title.rb
+- lib/chemicalml/convention/unit_dictionary/constraints/unit_parent_si_should_resolve.rb
+- lib/chemicalml/convention/unit_dictionary/constraints/unit_unit_type_should_resolve.rb
 - lib/chemicalml/convention/unit_type_dictionary.rb
 - lib/chemicalml/convention/unit_type_dictionary/constraints.rb
 - lib/chemicalml/convention/unit_type_dictionary/constraints/unit_type_id_must_match_pattern.rb
@@ -781,6 +891,7 @@ files:
 - lib/chemicalml/dictionary/model.rb
 - lib/chemicalml/dictionary/registry.rb
 - lib/chemicalml/errors.rb
+- lib/chemicalml/logger.rb
 - lib/chemicalml/schema.rb
 - lib/chemicalml/schema/definition.rb
 - lib/chemicalml/schema/registry.rb