relaton-iso 2.0.0.pre.alpha.2 → 2.0.0.pre.alpha.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 52a7ad701da999890a9e5947a408ed028c14a23c1beb268f2be990299f5c44c6
-  data.tar.gz: e80e496c6198a01d2ea9b5ed07a9511184adfc4ca6963d619af9e2de28a1a2e1
+  metadata.gz: a4e9325119df51d5aea288a6d612d7353107a25ac3030715dcf910ffaea13c26
+  data.tar.gz: e8167236cafc25b54a3a4d8d4bcee86dca7326103aec873e3534bf896e9c7498
 SHA512:
-  metadata.gz: 35a4b249729a7ff7f1df79088e4cb780f0dd86c25145bea9201a16f86f3fed88ca19f65eab16df7d47179382dc53d2c6b302136eb6c63015e6c485d8dea87c93
-  data.tar.gz: 54053f7fb0344f53c69679c5c14dd1fd2452fbbbf5c9d1b8b69ed8842222e50769f633107b3ffaef5a040d87a73e047a7edd948836a4a793cbfafd565db5ed13
+  metadata.gz: 9166abf7a46ec9604872543c9e572eebb03c34146635c156393cdd4e27c684a94e657daec4f55a889e928e38453fa1c690b6bc13549c7a67f80c6d7a9de447ae
+  data.tar.gz: 1a57e63a6faca62cf6ed1b6a6d0e346ae783f30d9d2bf48ef833cdeb6282f04b07e2af468183cedd0bf5367b12d71daeb9e5aad0574207c746d6c1cd6bcb0ca0

data/.github/workflows/rake.yml

@@ -7,8 +7,7 @@ on:
     branches: [ master, main ]
     tags: [ v* ]
   pull_request:
-  schedule:
-    - cron: '0 0 * * *'
+  workflow_dispatch:
 
 jobs:
   rake:

data/CLAUDE.md

@@ -0,0 +1,33 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Development
+
+- `bin/setup` — install dependencies
+- `rake spec` — run tests
+- `rspec spec/relaton/iso/bibliography_spec.rb` — run a single test file
+- `rspec spec/relaton/iso/bibliography_spec.rb -e "some description"` — run a specific example
+- `rake spec:update_index` — download latest ISO index fixture (`spec/fixtures/index-v1.zip`) from relaton-data-iso
+- `bin/console` — interactive prompt with the gem loaded
+- `rubocop` — lint (Ribose OSS style guide, Ruby 3.2 target)
+
+## Architecture
+
+relaton-iso retrieves ISO standard bibliographic data. The core retrieval flow:
+
+1. **Bibliography** (`lib/relaton/iso/bibliography.rb`) — entry point via `search(pubid)` and `get(ref, year, opts)`. Handles year filtering, part matching, and type/stage validation.
+2. **HitCollection** (`lib/relaton/iso/hit_collection.rb`) — searches a pre-built YAML index (`index-v1.zip` from relaton-data-iso) using `Relaton::Index`. Matches on `id_keys`: publisher, number, copublisher, part, year, edition, type, stage, iteration. Returns sorted Hit array.
+3. **Hit** (`lib/relaton/iso/hit.rb`) — wraps an index result. The `item` attribute lazy-loads the full document from GitHub raw content (relaton-data-iso repo). `sort_weight` prioritizes published over withdrawn/deleted.
+4. **ItemData** / **Model::Item** — ISO-specific bibliographic item extending `Relaton::Bib::ItemData`.
+5. **Scraper** (`lib/relaton/iso/scraper.rb`) — parses ISO website pages for metadata (used by DataFetcher for bulk operations, not the normal lookup path).
+6. **DataFetcher** (`lib/relaton/iso/data_fetcher.rb`) — bulk fetches from ISO.org ICS pages using 3 threads with a persistent queue for resumability.
+
+Key dependency: `pubid-iso` gem handles ISO publication identifier parsing and comparison.
+
+## Testing
+
+- **Framework:** RSpec with VCR cassettes and WebMock
+- **Network access:** fully blocked via `WebMock.disable_net_connect!`
+- **Index fixture:** `spec/fixtures/index-v1.zip` is served by WebMock stub (configured in `spec/support/webmock.rb`). Run `rake spec:update_index` to refresh when upstream data changes.
+- **VCR:** cassettes in `spec/vcr_cassettes/`, record mode `:once`, re-record interval 7 days. Index download requests are ignored by VCR (handled by WebMock stub instead).

data/README.adoc

@@ -360,6 +360,8 @@ RelatonIso uses the relaton-logger gem for logging. By default, it logs to STDOU
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
 
+To update the ISO index test fixture (used by WebMock in tests), run `rake spec:update_index`. This downloads the latest `index-v1.zip` from the https://github.com/relaton/relaton-data-iso[relaton-data-iso] repository.
+
 To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
 
 

data/Rakefile

@@ -4,3 +4,25 @@ require "rspec/core/rake_task"
 RSpec::Core::RakeTask.new(:spec)
 
 task :default => :spec
+
+namespace :spec do
+  desc "Download latest ISO index fixture from relaton-data-iso"
+  task :update_index do
+    require "net/http"
+    require "uri"
+
+    url = "https://raw.githubusercontent.com/relaton/relaton-data-iso/data-v2/index-v1.zip"
+    dest = File.join(__dir__, "spec", "fixtures", "index-v1.zip")
+
+    puts "Downloading #{url} ..."
+    uri = URI.parse(url)
+    response = Net::HTTP.get_response(uri)
+
+    if response.is_a?(Net::HTTPSuccess)
+      File.binwrite(dest, response.body)
+      puts "Updated #{dest} (#{response.body.bytesize} bytes)"
+    else
+      abort "Failed to download: HTTP #{response.code}"
+    end
+  end
+end

data/lib/relaton/iso/bibliography.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require "date"
+
 # require 'relaton_iso/iso_bibliographic_item'
 # require "relaton_iso/scrapper"
 # require "relaton_iso/hit_collection"
@@ -44,12 +46,19 @@ module Relaton
 
         hits, missed_year_ids = isobib_search_filter(query_pubid, opts)
         tip_ids = look_up_with_any_types_stages(hits, ref, opts)
-        ret = hits.fetch_doc
+
+        date_filter = opts[:publication_date_before] || opts[:publication_date_after]
+        if date_filter && !query_pubid.root.all_parts
+          ret = find_match_by_date(hits, query_pubid, opts)
+        else
+          ret = hits.fetch_doc(date_filter ? opts : {})
+        end
         return fetch_ref_err(query_pubid, missed_year_ids, tip_ids) unless ret
 
         response_pubid = ret.docidentifier.find(&:primary) # .sub(" (all parts)", "")
         Util.info "Found: `#{response_pubid}`", key: query_pubid.to_s
-        get_all = (query_pubid.root.year && opts[:keep_year].nil?) || opts[:keep_year] || opts[:all_parts]
+        get_all = (query_pubid.root.year && opts[:keep_year].nil?) || opts[:keep_year] || opts[:all_parts] ||
+          opts[:publication_date_before] || opts[:publication_date_after]
         return ret if get_all
 
         ret.to_most_recent_reference
@@ -109,6 +118,78 @@ module Relaton
 
       private
 
+      # Find the best match among hits using date filters.
+      # @param hits [Relaton::Iso::HitCollection]
+      # @param pubid [Pubid::Iso::Identifier]
+      # @param opts [Hash]
+      # @return [Relaton::Iso::ItemData, nil]
+      def find_match_by_date(hits, pubid, opts) # rubocop:disable Metrics/AbcSize
+        candidates = []
+        hits.each { |h| candidates << h if year_in_range?(hit_year(h), opts) }
+        candidates.sort_by { |h| -hit_year(h) }.each do |h|
+          ret = fetch_and_check_date(h, pubid, opts)
+          return ret if ret
+        end
+        nil
+      end
+
+      # Extract year from a hit as an integer.
+      # @param hit [Relaton::Iso::Hit]
+      # @return [Integer]
+      def hit_year(hit)
+        yr = hit.pubid&.year || hit.hit[:year]
+        yr.to_i
+      end
+
+      # Check if a year falls within the date filter range.
+      # @param year [Integer]
+      # @param opts [Hash]
+      # @return [Boolean]
+      def year_in_range?(year, opts)
+        return false if year.zero?
+
+        if opts[:publication_date_before]
+          return false if year > opts[:publication_date_before].year
+        end
+        if opts[:publication_date_after]
+          return false if year < opts[:publication_date_after].year
+        end
+        true
+      end
+
+      # Check if the item's published date falls within the filter range.
+      # @param item [Relaton::Iso::ItemData]
+      # @param opts [Hash]
+      # @return [Boolean]
+      def publication_date_in_range?(item, opts)
+        pub_date_entry = item.date.find { |d| d.type == "published" }
+        return true unless pub_date_entry&.at
+
+        pub_date = pub_date_entry.at.to_date
+        return true unless pub_date
+
+        if opts[:publication_date_before]
+          return false if pub_date >= opts[:publication_date_before]
+        end
+        if opts[:publication_date_after]
+          return false if pub_date < opts[:publication_date_after]
+        end
+        true
+      end
+
+      # Fetch the item for a hit and check if its publication date is in range.
+      # @param hit [Relaton::Iso::Hit]
+      # @param pubid [Pubid::Iso::Identifier]
+      # @param opts [Hash]
+      # @return [Relaton::Iso::ItemData, nil]
+      def fetch_and_check_date(hit, pubid, opts)
+        ret = hit.item
+        if publication_date_in_range?(ret, opts)
+          Util.info "Found: `#{ret.docidentifier.first.content}`", key: pubid.to_s
+          ret
+        end
+      end
+
       def check_year(year, hit) # rubocop:disable Metrics/AbcSize
         (hit.pubid.base.nil? && hit.pubid.year.to_s == year.to_s) ||
           (!hit.pubid.base.nil? && hit.pubid.base.year.to_s == year.to_s) ||

data/lib/relaton/iso/hit_collection.rb

@@ -31,7 +31,7 @@ module Relaton
       #
       def find # rubocop:disable Metrics/AbcSize
         @array = index.search do |row|
-          row[:id].is_a?(Hash) ? pubid_match?(row[:id]) : ref.to_s(with_prf: true) == row[:id]
+          row[:id].is_a?(Hash) || row[:id].is_a?(::Pubid::Core::Identifier::Base) ? pubid_match?(row[:id]) : ref.to_s(with_prf: true) == row[:id]
         end.map { |row| Hit.new row, self }
           .sort_by! { |h| h.pubid.to_s }
           .reverse!
@@ -49,6 +49,8 @@ module Relaton
       end
 
       def create_pubid(id)
+        return id if id.is_a?(::Pubid::Core::Identifier::Base)
+
         ::Pubid::Iso::Identifier.create(**id)
       rescue StandardError => e
         Util.warn e.message, key: ref.to_s
@@ -74,15 +76,24 @@ module Relaton
           excl_attrs << :iteration
         end
         # excl_parts << :edition if ref.root.edition.nil? || all_parts
-        @escludings = excl_attrs
+        @excludings = excl_attrs
       end
 
       def index
-        @index ||= Relaton::Index.find_or_create :iso, url: "#{ENDPOINT}#{INDEXFILE}.zip", file: "#{INDEXFILE}.yaml"
+        @index ||= Relaton::Index.find_or_create(
+          :iso,
+          url: "#{ENDPOINT}#{INDEXFILE}.zip",
+          file: "#{INDEXFILE}.yaml",
+          id_keys: %i[publisher number copublisher part year edition type stage
+                      iteration joint_document tctype sctype wgtype tcnumber
+                      scnumber wgnumber dirtype base supplements addendum
+                      jtc_dir month amendments corrigendums language],
+          pubid_class: ::Pubid::Iso::Identifier,
+        )
       end
 
       def fetch_doc(options = {})
-        @excludeingds = nil if options != opts
+        @excludings = nil if options != opts
         @opts = options
 
         if !ref.root.all_parts || size == 1
@@ -94,7 +105,11 @@ module Relaton
 
       # @return [RelatonIsoBib::IsoBibliographicItem, nil]
       def to_all_parts # rubocop:disable Metrics/AbcSize,Metrics/CyclomaticComplexity
-        hit = @array.select { |h| h.pubid.part }.min_by { |h| h.pubid.part.to_i }
+        parts = @array.select { |h| h.pubid.part }
+        if opts[:publication_date_before] || opts[:publication_date_after]
+          parts = parts.select { |h| Bibliography.send(:year_in_range?, (h.pubid.year || h.hit[:year]).to_i, opts) }
+        end
+        hit = parts.min_by { |h| h.pubid.part.to_i }
         return @array.first&.item unless hit
 
         bibitem = hit.item

data/lib/relaton/iso/version.rb

@@ -2,6 +2,6 @@
 
 module Relaton
   module Iso
-    VERSION = "2.0.0-alpha.2"
+    VERSION = "2.0.0-alpha.3"
   end
 end

data/relaton_iso.gemspec

@@ -28,7 +28,7 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency "isoics", "~> 0.1.6"
   spec.add_dependency "openssl", "~> 3.3.2" # 3.3.0 raised an error on Ruby 3.4.7
-  spec.add_dependency "pubid-iso", "~> 1.15.0"
+  spec.add_dependency "pubid-iso", "~> 1.15.8"
   spec.add_dependency "relaton-bib", "~> 2.0.0-alpha.4"
   spec.add_dependency "relaton-core", "~> 0.0.9"
   spec.add_dependency "relaton-index", "~> 0.2.12"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: relaton-iso
 version: !ruby/object:Gem::Version
-  version: 2.0.0.pre.alpha.2
+  version: 2.0.0.pre.alpha.3
 platform: ruby
 authors:
 - Ribose Inc.
@@ -43,14 +43,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.15.0
+        version: 1.15.8
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.15.0
+        version: 1.15.8
 - !ruby/object:Gem::Dependency
   name: relaton-bib
   requirement: !ruby/object:Gem::Requirement
@@ -107,6 +107,7 @@ files:
 - ".hound.yml"
 - ".rspec"
 - ".rubocop.yml"
+- CLAUDE.md
 - CODE_OF_CONDUCT.md
 - Gemfile
 - LICENSE.txt