relaton-etsi 2.1.1 → 2.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 83ff53d11a3552ae1912b417996db91727e92e8e3603db51e8cb7e952e1201b2
-  data.tar.gz: 325c2b01e11be54efaacb079750b09f28dc9111beb496fbacae85516943177b2
+  metadata.gz: abf8bf4e0aa5207f1a957ebca5b69ebd3a44857a4f8fbc0f17d9f3d9617bb174
+  data.tar.gz: f1ae62b230c9a6a32e4037b26690c2668890c9e8911d9665a7e46176628c3a98
 SHA512:
-  metadata.gz: 2cfa40bd4c74fb3f5ed33e89f8b334a02e27ceeddbdc6885f603b59cef183b7dd2d90ae768b11e2340bb4a02ec0ab25728f55df1471df260e7c19ff1c6b7f6dd
-  data.tar.gz: 3245710e0f9cdb786477c02b164b8e953ef2b9fedda33fa70604d464e26ad91c221c200290cf6ad2b07f504e47d66f3043c25e131b156c874f897c1123749399
+  metadata.gz: f7ee42ae9e44aa09dcc8c3e822eed2e1d5e78454a2faecc552060f61471fa3bc927edd92cdd5736403ef28fed9e3701413c902bb6e6a48fda8d2e10fc0a557ca
+  data.tar.gz: a0cc870769279fd8a0c0f2448cd107b22245fa43dffa133df7cc7ddd4fe711295fb51b981aa1b3389d0ca75f133f4c6b90f776fa7be51f03102d9a175a785d5d

data/CLAUDE.md

@@ -60,7 +60,7 @@ Uses Lutaml for serialization:
 
 ### Data Flow
 
-1. `Bibliography.get(ref)` searches the relaton-data-etsi index
+1. `Bibliography.get(ref)` searches the relaton-data-etsi index. `Bibliography#best_match` keeps the rows that match the whole document number, then picks the highest version, and among equal versions the latest date. The index matches a String query with `include?`, so this filter is what stops `ETSI TS 103 1` from matching `ETSI TS 103 104`.
 2. Fetches YAML from GitHub, converts to `Item` using `from_yaml`
 3. `DataFetcher.fetch` pulls CSV from etsi.org, parses with `DataParser`, saves to output folder
 

data/README.adoc

@@ -37,6 +37,24 @@ item = Relaton::Etsi::Bibliography.get("ETSI GS ZSM 012 V1.1.1")
 ...
 ----
 
+=== Reference matching
+
+A reference matches a whole ETSI document number. Neither `ETSI TS 103 1` nor
+`ETSI TS 103` matches `ETSI TS 103 104`. A reference without a part number
+matches every part of the document. The `ETSI` prefix is optional.
+
+A reference without a version returns the newest edition of the document. A
+reference with a version and a date returns that edition.
+
+[source,ruby]
+----
+Relaton::Etsi::Bibliography.get("ETSI EN 319 401")
+[relaton-etsi] INFO: (ETSI EN 319 401) Found: `ETSI EN 319 401 V3.2.1 (2026-01)`
+
+Relaton::Etsi::Bibliography.get("ETSI EN 319 401 V2.3.1 (2021-05)")
+[relaton-etsi] INFO: (ETSI EN 319 401 V2.3.1 (2021-05)) Found: `ETSI EN 319 401 V2.3.1 (2021-05)`
+----
+
 === XML serialization
 
 [source,ruby]

data/lib/relaton/etsi/bibliography.rb

@@ -6,11 +6,16 @@ module Relaton
     module Bibliography
       SOURCE = "https://raw.githubusercontent.com/relaton/relaton-data-etsi/refs/heads/v2/"
 
+      # What follows the document number in an index id: the part numbers, then
+      # the version. A reference matches a whole number only, so a part number
+      # is optional but a group of digits of the number is not.
+      SUFFIX = /\A(?:-\d+)*\s(?:V\d|ed\.\d)/
+
       # @param text [String]
       # @return [Relaton::Etsi::ItemData, nil]
       def search(text) # rubocop:disable Metrics/MethodLength, Metrics/AbcSize
         index = Relaton::Index.find_or_create :etsi, url: "#{SOURCE}index-v1.zip", file: INDEX_FILE
-        row = index.search(text).min_by { |r| r[:id] }
+        row = best_match(index, text)
         return unless row
 
         url = "#{SOURCE}#{row[:file]}"
@@ -40,6 +45,64 @@ module Relaton
         result
       end
 
+      # Match the reference against the index and return the newest edition.
+      #
+      # An index id renders as `ETSI <type> <number> <V1.2.3|ed.4> (<yyyy-mm>)`.
+      # The index matches a String query with `include?`, so a bare reference
+      # matches every edition of the document, but also longer numbers. The
+      # `matches?` filter drops the longer numbers, then `edition_key` picks the
+      # highest version, and among equal versions the latest date.
+      #
+      # @param index [Relaton::Index::Type]
+      # @param text [String] the reference
+      # @return [Hash, nil] the winning index row (`{ id:, file: }`)
+      def best_match(index, text)
+        ref = normalize(text)
+        index.search(ref)
+          .select { |row| matches? ref, row[:id] }
+          .max_by { |row| edition_key row[:id] }
+      end
+
+      private
+
+      # Every index id has the `ETSI` prefix. A reference can omit it.
+      #
+      # @param text [String] the reference
+      # @return [String]
+      def normalize(text)
+        ref = text.strip.squeeze(" ").sub(/\AETSI\s+/i, "")
+        "ETSI #{ref}"
+      end
+
+      # `ETSI EN 319 142` matches every part of the document. Neither
+      # `ETSI EN 319 14` nor `ETSI EN 319` matches anything: the first stops
+      # inside a group of digits, the second stops before the last group.
+      #
+      # @param ref [String] the normalized reference
+      # @param id [String] the index id
+      # @return [Boolean]
+      def matches?(ref, id)
+        return true if id == ref
+
+        rest = id[ref.length..]
+        !rest.nil? && rest.match?(SUFFIX)
+      end
+
+      # Sort key of one edition. The numbers keep `V19.0.0` above `V9.0.0` and
+      # `ed.11` above `ed.9`, which a comparison of the strings does not. The id
+      # is the last element to make the order of equal editions stable.
+      #
+      # A `V` version and an `ed.` edition give keys of a different length. No
+      # ETSI document has the two forms together, and `matches?` keeps the rows
+      # of one document number only, so the two forms do not meet here.
+      #
+      # @param id [String] the index id
+      # @return [Array]
+      def edition_key(id)
+        version = id[/\sV(\d+(?:\.\d+)*)/, 1] || id[/\sed\.(\d+)/, 1] || ""
+        [version.split(".").map(&:to_i), id[/\((\d{4}-\d{2})\)/, 1].to_s, id]
+      end
+
       extend Bibliography
     end
   end

data/lib/relaton/etsi/version.rb

@@ -2,6 +2,6 @@
 
 module Relaton
   module Etsi
-    VERSION = "2.1.1"
+    VERSION = "2.1.2"
   end
 end

data/relaton-etsi.gemspec

@@ -0,0 +1,44 @@
+# frozen_string_literal: true
+
+require_relative "lib/relaton/etsi/version"
+
+Gem::Specification.new do |spec| # rubocop:disable Metrics/BlockLength
+  spec.name = "relaton-etsi"
+  spec.version = Relaton::Etsi::VERSION
+  spec.authors = ["Ribose Inc."]
+  spec.email = ["open.source@ribose.com"]
+
+  spec.summary =  "Relaton::Etsi: retrieve ETSI Standards for bibliographic " \
+                  "using the BibliographicItem model"
+  spec.description = "Relaton::Etsi: retrieve ETSI Standards for bibliographic " \
+                  "using the BibliographicItem model"
+  spec.homepage = "https://github.com/relaton/relaton-etsi"
+  spec.license = "BSD-2-Clause"
+  spec.required_ruby_version = Gem::Requirement.new(">= 3.2.0")
+
+  # spec.metadata["allowed_push_host"] = "TODO: Set to your gem server 'https://example.com'"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  # spec.metadata["source_code_uri"] = "TODO: Put your gem's public repo URL here."
+  # spec.metadata["changelog_uri"] = "TODO: Put your gem's CHANGELOG.md URL here."
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files = Dir.chdir(__dir__) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      (File.expand_path(f) == __FILE__) ||
+        f.start_with?(*%w[bin/ test/ spec/ features/ .git .circleci appveyor Gemfile])
+    end
+  end
+  spec.bindir = "exe"
+  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "mechanize", "~> 2.8"
+  spec.add_dependency "relaton-bib", "~> 2.1.0"
+  spec.add_dependency "relaton-core", "~> 0.0.13"
+  spec.add_dependency "relaton-index", "~> 0.2.7"
+
+  # For more information and examples about making a new gem, check out our
+  # guide at: https://bundler.io/guides/creating_gem.html
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-etsi
 version: !ruby/object:Gem::Version
-  version: 2.1.1
+  version: 2.1.2
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-11 00:00:00.000000000 Z
+date: 2026-08-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mechanize
@@ -80,11 +80,6 @@ files:
 - LICENSE.txt
 - README.adoc
 - Rakefile
-- grammars/basicdoc.rng
-- grammars/biblio-standoc.rng
-- grammars/biblio.rng
-- grammars/relaton-etsi-compile.rng
-- grammars/relaton-etsi.rng
 - lib/relaton/etsi.rb
 - lib/relaton/etsi/bibdata.rb
 - lib/relaton/etsi/bibitem.rb
@@ -100,6 +95,7 @@ files:
 - lib/relaton/etsi/status.rb
 - lib/relaton/etsi/util.rb
 - lib/relaton/etsi/version.rb
+- relaton-etsi.gemspec
 - sig/relaton_etsi.rbs
 homepage: https://github.com/relaton/relaton-etsi
 licenses: