iev 0.3.6 → 0.3.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 42bd017437d3f78d461046e2cf5252eddb3d4b45988f1b885abe3eb4ddcf6999
-  data.tar.gz: 2c234ead4432ea4f469973997d7c7c0fa4ba90a03d9db9039477eec7cf77a84e
+  metadata.gz: 987335d7795e87ec798e7bba888b0e124a4695a341d180601de6c3035a408edc
+  data.tar.gz: 9948cb62807623d5413de5ba16d884d83585bf8bb96076edbe306c2a9dca06d0
 SHA512:
-  metadata.gz: 828c3d9eb81d35e71ef7b90b5abe6f39d9cdf3828db452092a60313e46bee8d2b1e7d6a44a4d6affe03e76e1f1ab90a7788959db9c0ff3d70a33624f748aafc0
-  data.tar.gz: 62a2f57172955b8375a3dba2f5e8a6d4ffe004498a6aa0ceb97c5ad5dffe8083ca9f791b2b25e3d9d15efa4094e4844652b05e335c4b8aaff674d948b6d0c239
+  metadata.gz: 3706dcd96d212daca67020bbb3be3f61ba6e05dceaaaac4dec5e5b1776c8f33e9e36ff7e25c36983e9504dab4049654e64ecd740464dee3ec27737e2e5972c07
+  data.tar.gz: 66eb1f2fe3025661478993451dce87541d1e3c0da1dbcc9c5656ccdc2e80059340b95b892a7557a498dbd02876e13c92ba076dd28030c17547c7d47266a8c99b

data/.github/workflows/rake.yml

@@ -1,10 +1,16 @@
 name: rake
 
+permissions:
+  contents: read
+  actions: write         # Add this if you need to approve or trigger workflows
+
+
 on:
   push:
     branches: [ master, main ]
     tags: [ v* ]
   pull_request:
+  workflow_dispatch:
 
 jobs:
   rake:

data/.github/workflows/release.yml

@@ -1,5 +1,8 @@
 name: release
 
+permissions:
+  contents: write
+
 on:
   workflow_dispatch:
     inputs:
@@ -19,4 +22,4 @@ jobs:
       next_version: ${{ github.event.inputs.next_version }}
     secrets:
       rubygems-api-key: ${{ secrets.GLOSSARIST_CI_RUBYGEMS_API_KEY }}
-
+      pat_token: ${{ secrets.GITHUB_TOKEN }}

data/.rubocop_todo.yml

@@ -1,33 +1,18 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2025-01-06 12:27:40 UTC using RuboCop version 1.69.2.
+# on 2025-11-14 11:14:05 UTC using RuboCop version 1.81.7.
 # 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
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle, IndentOneStep, IndentationWidth.
-# SupportedStyles: case, end
-Layout/CaseIndentation:
-  Exclude:
-    - 'lib/iev/iso_639_code.rb'
-
-# Offense count: 1
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyleAlignWith, Severity.
-# SupportedStylesAlignWith: keyword, variable, start_of_line
-Layout/EndAlignment:
-  Exclude:
-    - 'lib/iev/iso_639_code.rb'
-
-# Offense count: 45
+# Offense count: 43
 # This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: Max, AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, AllowedPatterns, SplitStrings.
+# Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, IgnoreCopDirectives, AllowedPatterns, SplitStrings.
 # URISchemes: http, https
 Layout/LineLength:
   Exclude:
+    - 'iev.gemspec'
     - 'lib/iev/cli/command.rb'
     - 'lib/iev/cli/command_helper.rb'
     - 'lib/iev/db_cache.rb'
@@ -36,6 +21,13 @@ Layout/LineLength:
     - 'spec/acceptance/xlsx2yaml_spec.rb'
     - 'spec/iev_spec.rb'
 
+# Offense count: 7
+# Configuration parameters: IgnoreLiteralBranches, IgnoreConstantBranches, IgnoreDuplicateElseBranch.
+Lint/DuplicateBranch:
+  Exclude:
+    - 'lib/iev/source_parser.rb'
+    - 'lib/iev/term_builder.rb'
+
 # Offense count: 1
 Lint/MixedRegexpCaptureTypes:
   Exclude:
@@ -59,7 +51,7 @@ Metrics/CyclomaticComplexity:
     - 'lib/iev/source_parser.rb'
     - 'lib/iev/term_builder.rb'
 
-# Offense count: 21
+# Offense count: 20
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Max: 74
@@ -71,11 +63,3 @@ Metrics/PerceivedComplexity:
     - 'lib/iev.rb'
     - 'lib/iev/converter/mathml_to_asciimath.rb'
     - 'lib/iev/term_builder.rb'
-
-# Offense count: 1
-# This cop supports unsafe autocorrection (--autocorrect-all).
-# Configuration parameters: EnforcedStyle.
-# SupportedStyles: literals, strict
-Style/MutableConstant:
-  Exclude:
-    - 'lib/iev/iso_639_code.rb'

data/Gemfile

@@ -2,13 +2,14 @@
 
 source "https://rubygems.org"
 
-# Specify your gem's dependencies in lutaml-model.gemspec
-gemspec
-
-gem "rake", "~> 13.0"
-gem "rspec", "~> 3.0"
-gem "rubocop", "~> 1.21"
-gem "rubocop-performance", require: false
-gem "rubocop-rake", require: false
-gem "rubocop-rspec", require: false
+gem "canon"
+gem "openssl"
+gem "rake"
+gem "rspec"
+gem "rubocop"
+gem "rubocop-performance"
+gem "rubocop-rake"
+gem "rubocop-rspec"
 gem "simplecov"
+
+gemspec

data/README.adoc

@@ -2,7 +2,7 @@
 
 image:https://img.shields.io/gem/v/iev.svg["Gem Version", link="https://rubygems.org/gems/iev"]
 image:https://github.com/glossarist/iev/workflows/rake/badge.svg["Build Status", link="https://github.com/glossarist/iev/actions?query=workflow%3Arake"]
-image:https://codeclimate.com/github/glossarist/iev/badges/gpa.svg["Code Climate", link="https://codeclimate.com/github/glossarist/iev"]
+// image:https://codeclimate.com/github/glossarist/iev/badges/gpa.svg["Code Climate", link="https://codeclimate.com/github/glossarist/iev"]
 image:https://img.shields.io/github/issues-pr-raw/glossarist/iev.svg["Pull Requests", link="https://github.com/glossarist/iev/pulls"]
 image:https://img.shields.io/github/commits-since/glossarist/iev/latest.svg["Commits since latest",link="https://github.com/glossarist/iev/releases"]
 

data/bin/console

@@ -2,7 +2,7 @@
 # frozen_string_literal: true
 
 require "bundler/setup"
-require "iev"
+require_relative "../lib/iev"
 
 # You can add fixtures and/or initialization code here to make experimenting
 # with your gem easier. You can also use a different console, if you like.

data/iev.gemspec

@@ -1,8 +1,6 @@
 # frozen_string_literal: true
 
-lib = File.expand_path("lib", __dir__)
-$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
-require "iev/version"
+require_relative "lib/iev/version"
 
 Gem::Specification.new do |spec|
   spec.name = "iev"
@@ -10,9 +8,9 @@ Gem::Specification.new do |spec|
   spec.authors = ["Ribose Inc."]
   spec.email = ["open.source@ribose.com"]
 
-  spec.summary = "Iev: Fetch and encode Iev term from Electropedia"
-  spec.description = "Iev: Fetch and encode Iev term from Electropedia"
-  spec.homepage = "https://github.com/metanorma/iev"
+  spec.summary = "Glossarist toolkit for working with IEV terms from Electropedia"
+  spec.description = "Glossarist toolkit for working with IEV terms from Electropedia"
+  spec.homepage = "https://github.com/glossarist/iev"
   spec.license = "BSD-2-Clause"
 
   spec.files = `git ls-files -z`.split("\x0").reject do |f|
@@ -23,14 +21,14 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
   spec.required_ruby_version = Gem::Requirement.new(">= 3.1.0")
 
-  spec.add_dependency "creek", "~> 2.5"
+  spec.add_dependency "creek", "~> 2.6"
   spec.add_dependency "glossarist", ">= 2.3.0"
-  spec.add_dependency "nokogiri", ">= 1.16.5"
+  spec.add_dependency "mechanize", "~> 2.10"
+  spec.add_dependency "nokogiri", "~> 1.17"
   spec.add_dependency "plurimath"
   spec.add_dependency "relaton", "~> 1.18"
   spec.add_dependency "sequel", "~> 5.40"
   spec.add_dependency "sqlite3", "~> 1.7.0"
   spec.add_dependency "thor", "~> 1.0"
   spec.add_dependency "unitsml"
-  spec.add_dependency "zeitwerk", "~> 2.4"
 end

data/lib/iev/cli/ui.rb

@@ -62,7 +62,7 @@ module Iev
         end
 
         def should_out?(level, topic)
-          topic.nil? || level == :warn || $IEV_DEBUG[topic]
+          topic.nil? || level == :warn || ($IEV_DEBUG && $IEV_DEBUG[topic])
         end
       end
     end

data/lib/iev/cli.rb

@@ -5,6 +5,10 @@
 
 module Iev
   module Cli
+    autoload :Command, "iev/cli/command"
+    autoload :CommandHelper, "iev/cli/command_helper"
+    autoload :Ui, "iev/cli/ui"
+
     def self.start(arguments)
       Signal.trap("INT") do
         Ui.info "Signal SIGINT received, quitting!"

data/lib/iev/converter.rb

@@ -2,6 +2,8 @@
 
 module Iev
   module Converter
+    autoload :MathmlToAsciimath, "iev/converter/mathml_to_asciimath"
+
     def self.mathml_to_asciimath(input)
       Iev::Converter::MathmlToAsciimath.convert(input)
     end

data/lib/iev/data_conversions.rb

@@ -3,6 +3,8 @@
 # (c) Copyright 2020 Ribose Inc.
 #
 
+require "htmlentities"
+
 module Iev
   module DataConversions
     refine String do

data/lib/iev/iso_639_code.rb

@@ -7,16 +7,18 @@ module Iev
   # @todo This needs to be rewritten.
   class Iso639Code
     COUNTRY_CODES = YAML.load(IO.read(File.join(__dir__, "iso_639_2.yaml")))
-    THREE_CHAR_MEMO = {}
+    # rubocop:disable Style/MutableConstant
+    THREE_CHAR_MEMO = {} # Memoization cache, must be mutable
+    # rubocop:enable Style/MutableConstant
 
     def initialize(two_char_code)
       @code = case two_char_code.length
-        when 2
-          two_char_code
-        else
-          # This is to handle code "nl BE" in the Iev sheet
-          two_char_code.split(" ").first
-        end
+              when 2
+                two_char_code
+              else
+                # This is to handle code "nl BE" in the Iev sheet
+                two_char_code.split.first
+              end
     end
 
     def find(code_type)

data/lib/iev/source_parser.rb

@@ -5,7 +5,6 @@
 
 # rubocop:todo Style/RedundantRegexpEscape
 
-require "English"
 module Iev
   # Parses information from the spreadsheet's SOURCE column.
   #

data/lib/iev/term_attrs_parser.rb

@@ -65,14 +65,22 @@ module Iev
     end
 
     def extract_gender(str)
-      gender_rx = /\b[mfn]\b/
-
-      @gender = remove_from_string(str, gender_rx)
+      # Match gender either:
+      # 1. Inside brackets/parentheses: (m), [f], (n)
+      # 2. As standalone word with boundaries: m, f, n
+      gender_rx = /(?:\(|\[)[mfn](?:\)|\])|\b[mfn]\b/
+
+      match = remove_from_string(str, gender_rx)
+      # Extract just the letter from the match (remove brackets if present)
+      @gender = match&.gsub(/[\[\]()]/, "")
     end
 
     # Must happen after #extract_gender
     def extract_plurality(str)
-      plural_rx = /\bpl\b/
+      # Match plurality either:
+      # 1. Inside brackets/parentheses: (pl), [pl]
+      # 2. As standalone word with boundaries: pl
+      plural_rx = /(?:\(|\[)pl(?:\)|\])|\bpl\b/
 
       if remove_from_string(str, plural_rx)
         @plurality = "plural"

data/lib/iev/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Iev
-  VERSION = "0.3.6"
+  VERSION = "0.3.8"
 end

data/lib/iev.rb

@@ -2,7 +2,7 @@
 
 require "iev/version"
 require "iev/db"
-require "open-uri"
+require "mechanize"
 require "nokogiri"
 
 require "benchmark"
@@ -15,26 +15,35 @@ require "relaton_bib"
 require "sequel"
 require "thor"
 require "yaml"
-require "zeitwerk"
-
-loader = Zeitwerk::Loader.for_gem
-loader.setup
 
 module Iev
+  autoload :Cli, "iev/cli"
+  autoload :Converter, "iev/converter"
+  autoload :DataConversions, "iev/data_conversions"
+  autoload :Db, "iev/db"
+  autoload :DbCache, "iev/db_cache"
+  autoload :DbWriter, "iev/db_writer"
+  autoload :Iso639Code, "iev/iso_639_code"
+  autoload :Profiler, "iev/profiler"
+  autoload :RelatonDb, "iev/relaton_db"
+  autoload :SourceParser, "iev/source_parser"
+  autoload :SupersessionParser, "iev/supersession_parser"
+  autoload :TermAttrsParser, "iev/term_attrs_parser"
+  autoload :TermBuilder, "iev/term_builder"
+  autoload :Utilities, "iev/utilities"
+
   #
   # Scrape Electropedia for term.
   #
   # @param [String] code for example "103-01-02"
-  # @param [String] lang language code, for examle "en"
+  # @param [String] lang language code, for example "en"
   #
   # @return [String, nil] if found than term,
   # if code not found then empty string,
   #   if language not found then nil.
   #
   def self.get(code, lang)
-    url = "http://www.electropedia.org/iev/iev.nsf/"\
-          "display?openform&ievref=#{code}"
-    doc = Nokogiri::HTML OpenURI.open_uri(url), nil, "UTF-8"
+    doc = get_doc(code)
     xpath = "//table/tr/td/div/font[.=\"#{lang}\"]/../../"\
             "following-sibling::td[2]"
     a = doc&.at(xpath)&.children&.to_xml
@@ -42,6 +51,18 @@ module Iev
       &.sub(/, <.*$/, "")
       &.gsub(/<[^<>]*>/, "")&.strip
   end
+
+  def self.get_doc(code)
+    url = "https://www.electropedia.org/iev/iev.nsf/"\
+         "display?openform&ievref=#{code}"
+
+    # Use Mechanize with User-Agent to avoid 403 Forbidden errors from bot detection
+    agent = Mechanize.new
+    agent.user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+
+    page = agent.get(url)
+    page.parser # Nokogiri document
+  end
 end
 
-require "iev/cli"
+require_relative "iev/cli"

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: iev
 version: !ruby/object:Gem::Version
-  version: 0.3.6
+  version: 0.3.8
 platform: ruby
 authors:
 - Ribose Inc.
-autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-05-12 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: creek
@@ -16,14 +15,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.5'
+        version: '2.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.5'
+        version: '2.6'
 - !ruby/object:Gem::Dependency
   name: glossarist
   requirement: !ruby/object:Gem::Requirement
@@ -38,20 +37,34 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 2.3.0
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.10'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.10'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.16.5
+        version: '1.17'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.16.5
+        version: '1.17'
 - !ruby/object:Gem::Dependency
   name: plurimath
   requirement: !ruby/object:Gem::Requirement
@@ -136,21 +149,7 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: zeitwerk
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.4'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.4'
-description: 'Iev: Fetch and encode Iev term from Electropedia'
+description: Glossarist toolkit for working with IEV terms from Electropedia
 email:
 - open.source@ribose.com
 executables:
@@ -161,7 +160,6 @@ files:
 - ".github/workflows/rake.yml"
 - ".github/workflows/release.yml"
 - ".gitignore"
-- ".hound.yml"
 - ".rspec"
 - ".rubocop.yml"
 - ".rubocop_todo.yml"
@@ -194,11 +192,10 @@ files:
 - lib/iev/term_builder.rb
 - lib/iev/utilities.rb
 - lib/iev/version.rb
-homepage: https://github.com/metanorma/iev
+homepage: https://github.com/glossarist/iev
 licenses:
 - BSD-2-Clause
 metadata: {}
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -213,8 +210,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.22
-signing_key:
+rubygems_version: 4.0.1
 specification_version: 4
-summary: 'Iev: Fetch and encode Iev term from Electropedia'
+summary: Glossarist toolkit for working with IEV terms from Electropedia
 test_files: []

data/.hound.yml

@@ -1,5 +0,0 @@
-# Auto-generated by Cimas: Do not edit it manually!
-# See https://github.com/metanorma/cimas
-ruby:
-  enabled: true
-  config_file: .rubocop.yml