relaton-index 0.2.21 → 2.2.0.pre.alpha.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f2e7462982813b35a76cc8549bad25b97ad125cf3b9986426889aecae65bb513
-  data.tar.gz: '0338bedb98265e0fbe2efac2db854b7105a3c281ee0275507ca80c35d71dbbc9'
+  metadata.gz: e05bc6da371d0f9f3346ed3df0fa82c69c13f6af75148b8a36e1992f82b34394
+  data.tar.gz: 457df757d72b7213e6ac726a7ced8a452b5341d6d9b8d52a52bdf34e717d5776
 SHA512:
-  metadata.gz: 754adaf38cb24cf06987a73b82c544aee61952cbd895cd2c5b2acba69544b5453264680f117d6788b9b3f4cdfab87d1a25c757e046947a4903bbe02be3b8a6bd
-  data.tar.gz: f0e5b98bd26b5ef53519167370c0a0a2754f4ea482ad7e0b77c52b23b5073c57649db0b158a7d482a6a78fb2ad11143be5278e4c5a13f9114d13e71d31dfcd2f
+  metadata.gz: efcc97baaa47640770274043611e99dc2f1b4442d0205da3c6a375b735e9ad67480112fc1063ef6f271e14110076a845b9072f4e53fc7745ef844122f6eb7841
+  data.tar.gz: b4793790e433dc5bac23a1f3a937abe3cc2168e57e6cbcefdabcf10748200776fbb2db96229517ee20a092da386dbf38532052474d66954c397cd839f7525e8b

data/Gemfile

@@ -5,6 +5,14 @@ source "https://rubygems.org"
 # Specify your gem's dependencies in relaton-index.gemspec
 gemspec
 
+# Use local monorepo sibling gems where available.
+Dir["../*/"].each do |dir|
+  name = File.basename(dir)
+  next if name == File.basename(__dir__)
+  next unless File.exist?(File.join(dir, "#{name}.gemspec"))
+  gem name, path: dir
+end
+
 gem "rake", "~> 13.0"
 
 gem "rspec", "~> 3.0"

data/lib/relaton/index/file_io.rb

@@ -6,6 +6,13 @@ module Relaton
     # In index mode url should be nil.
     #
     class FileIO
+      include IdNumber
+
+      # Raised internally when a deserialized id cannot be parsed or is not
+      # understood by the pubid class; `#load_index` rescues it to trigger the
+      # wrong-structure handling (re-download, or stop and log).
+      class InvalidIndexError < StandardError; end
+
       attr_reader :url, :pubid_class
       attr_accessor :sorted
 
@@ -21,13 +28,16 @@ module Relaton
       #     and save it to the storage (if not exists, or older than 24 hours)
       #   if true then the index is read from the storage (used to remove index file)
       #   if nil then the fiename is used to read and write file (used to create indes in GH actions)
-      # @param [Pubid::Core::Identifier::Base] pubid class for deserialization
+      # @param [Pubid::Identifier] pubid class for deserialization
       #
-      def initialize(dir, url, filename, id_keys, pubid_class = nil)
+      # `id_keys` is accepted for backward compatibility but no longer used: the
+      # index format is now validated by round-tripping a sample of ids through
+      # the pubid class (see #check_serialization), which understands the pubid
+      # v2 (lutaml) `_type` serialization that the old key-allowlist could not.
+      def initialize(dir, url, filename, _id_keys = nil, pubid_class = nil)
         @dir = dir
         @url = url
         @filename = filename
-        @id_keys = id_keys || []
         @pubid_class = pubid_class
         @sorted = false
       end
@@ -84,8 +94,12 @@ module Relaton
       #
       # @return [Boolean] <description>
       #
+      # Structural check only. Per-id serialization is validated during
+      # deserialization (see #deserialize_id), which reuses the `from_hash` the
+      # index load performs anyway, so every row is checked at no extra parse
+      # cost.
       def check_format(index)
-        check_basic_format(index) && check_id_format(index)
+        check_basic_format(index)
       end
 
       def check_basic_format(index)
@@ -95,13 +109,35 @@ module Relaton
         index.all? { |item| item.respond_to?(:keys) && item.keys.sort == keys }
       end
 
-      def check_id_format(index)
-        return true if @id_keys.empty?
+      # An id is supported when `from_hash` either resolves it to a concrete
+      # type (a subclass — the polymorphic `_type` matched) or round-trips
+      # losslessly through `to_hash`. The subclass clause covers valid entries
+      # pubid cannot fully rebuild on re-serialize (e.g. ISO directives drop a
+      # redundant subgroup number); the round-trip clause covers pubid classes
+      # without a subclass hierarchy. A wrong-format/garbled id satisfies
+      # neither: it falls back to the bare base class and fails to round-trip.
+      def id_supported?(obj, raw)
+        # A concrete subtype means pubid recognized the `_type`; accept without
+        # round-tripping. This both skips the false positive for valid-but-lossy
+        # types (e.g. ISO directives) and avoids the costly hash compare for the
+        # ~all rows that resolve to a subtype (it would otherwise add ~33%).
+        return true unless obj.instance_of?(@pubid_class)
 
-        keys = index.each_with_object(Set.new) do |item, acc|
-          acc.merge item[:id].keys if item[:id].is_a?(Hash)
+        normalize(obj.to_hash) == normalize(raw)
+      rescue StandardError
+        false
+      end
+
+      # Stringify hash keys and scalar values so the comparison ignores YAML
+      # scalar typing (e.g. 1 vs "1") and string/symbol key differences, while
+      # still detecting dropped/added keys or genuinely changed values.
+      def normalize(value)
+        case value
+        when Hash then value.to_h { |k, v| [k.to_s, normalize(v)] }
+        when Array then value.map { |v| normalize(v) }
+        when nil then nil
+        else value.to_s
         end
-        keys.none? { |k| !@id_keys.include? k }
       end
 
       #
@@ -116,17 +152,51 @@ module Relaton
         load_index(yaml) || []
       end
 
+      # Deserialize and sort by the same narrowing key Type#search bsearches
+      # on, so binary search always has a consistent total order. The published
+      # index is only approximately sorted (generated under pubid 1.x base
+      # semantics); merely detecting sortedness left bsearch disabled and every
+      # search a full O(n) scan. Sorting here is one-time per load.
       def deserialize_pubid(index)
         return index unless @pubid_class
 
+        deserialized = index.map do |r|
+          { id: deserialize_id(r[:id]), file: r[:file] }
+        end
+        warn_unless_sorted(deserialized)
+        deserialized.sort_by! { |r| get_id_number(r[:id]) }
         @sorted = true
-        prev_number = nil
-        index.map do |r|
-          id = @pubid_class.create(**(r[:id] || {}))
-          num = get_id_number id
-          @sorted = false if prev_number && prev_number > num
-          prev_number = num
-          { id: id, file: r[:file] }
+        deserialized
+      end
+
+      # Deserialize one id and verify pubid understands it. Reuses the
+      # `from_hash` deserialization the load performs anyway, so validating every
+      # row costs only the `to_hash`/compare for ids that need the round-trip
+      # clause. Raises InvalidIndexError when an id cannot be parsed or is
+      # unsupported, so `#load_index` rejects (and re-downloads) the whole index.
+      def deserialize_id(raw)
+        obj = @pubid_class.from_hash(raw)
+      rescue StandardError => e
+        raise InvalidIndexError, "cannot parse id #{raw.inspect}: #{e.message}"
+      else
+        return obj if id_supported?(obj, raw)
+
+        raise InvalidIndexError, "unsupported id #{raw.inspect}"
+      end
+
+      # Log when the loaded index is not already in get_id_number order, so the
+      # in-memory sort above (and the underlying not-sorted index file) is
+      # visible. Stops at the first out-of-order pair.
+      def warn_unless_sorted(index)
+        prev = nil
+        index.each do |r|
+          num = get_id_number(r[:id])
+          if prev && prev > num
+            Util.warn "Index file `#{file}` is not sorted by id number; " \
+                      "sorting #{index.size} entries in memory.", progname
+            return
+          end
+          prev = num
         end
       end
 
@@ -147,18 +217,20 @@ module Relaton
       def load_index(yaml, save = false)
         index = YAML.safe_load(yaml, permitted_classes: [Symbol])
         save index if save
-        return deserialize_pubid(index) if check_format index
+        return deserialize_pubid(index) if check_format(index)
 
-        if save
-          warn_remote_index_error "Wrong structure of"
-        else
-          warn_local_index_error "Wrong structure of"
-        end
+        report_invalid_index(save, "Wrong structure of")
       rescue Psych::SyntaxError
+        report_invalid_index(save, "YAML parsing error when reading")
+      rescue InvalidIndexError
+        report_invalid_index(save, "Wrong structure of")
+      end
+
+      def report_invalid_index(save, reason)
         if save
-          warn_remote_index_error "YAML parsing error when reading"
+          warn_remote_index_error reason
         else
-          warn_local_index_error "YAML parsing error when reading"
+          warn_local_index_error reason
         end
       end
 
@@ -194,23 +266,21 @@ module Relaton
       #
       def save(index)
         yaml = sort_structured_index(index).map do |item|
-          item.transform_values { |value| value.is_a?(Pubid::Core::Identifier::Base) ? value.to_h : value }
+          item.transform_values do |value|
+            @pubid_class && value.is_a?(@pubid_class) ? value.to_hash : value
+          end
         end.to_yaml
         Index.config.storage.write file, yaml
       end
 
       def sort_structured_index(index)
-        if @pubid_class && index.first&.dig(:id).is_a?(Pubid::Core::Identifier::Base)
+        if @pubid_class && index.first&.dig(:id).is_a?(@pubid_class)
           index.sort_by { |item| get_id_number item[:id] }
         else
           index
         end
       end
 
-      def get_id_number(id)
-        id.respond_to?(:base) && id.base ? id.base.number.to_s : id.number.to_s
-      end
-
       #
       # Remove index file from storage
       #

data/lib/relaton/index/id_number.rb

@@ -0,0 +1,30 @@
+module Relaton
+  module Index
+    # Shared narrowing/sort key for structured (pubid) index ids. Type uses it
+    # for binary-search narrowing; FileIO uses it to sort the index and detect
+    # sortedness. The two MUST agree, so the rule lives in one place.
+    module IdNumber
+      # One-level narrowing key: a supplement/amendment is filed under its
+      # immediate parent's number, everything else under its own number.
+      #
+      # Pubid 2.x exposes the parent via `.base_identifier` (the LutaML
+      # `Pubid::Iso::Identifiers::*` classes that relaton loads at runtime). A
+      # standalone `require "pubid-iso"` can instead surface the legacy
+      # `Pubid::Iso::Identifier::*` classes, which use `.base`; we accept either
+      # so the key is stable in both load orders. The wrong accessor silently
+      # falls through to the row's own number and breaks bsearch narrowing.
+      def get_id_number(id)
+        base = id_base(id)
+        ((base && base.number) || id.number).to_s
+      end
+
+      def id_base(id)
+        if id.respond_to?(:base_identifier) && id.base_identifier
+          id.base_identifier
+        elsif id.respond_to?(:base) && id.base
+          id.base
+        end
+      end
+    end
+  end
+end

data/lib/relaton/index/type.rb

@@ -4,6 +4,8 @@ module Relaton
     # Relaton::Index::Type is a class for indexing Relaton files.
     #
     class Type
+      include IdNumber
+
       #
       # Initialize a new Relaton::Index::Type object
       #
@@ -12,7 +14,7 @@ module Relaton
       # @param [String, nil] file output file name
       # @param [Array<Symbol>] id_keys keys of identifier to be used for sorting index
       #   format of index file is checked if id_keys all is provided at least in one of the IDs
-      # @param [Pubid::Core::Identifier::Base, nil] pubid class for deserialization
+      # @param [Pubid::Identifier, nil] pubid class for deserialization
       #
       def initialize(type, url = nil, file = nil, id_keys = nil, pubid_class = nil) # rubocop:disable Metrics/ParameterLists
         @file = file
@@ -41,7 +43,7 @@ module Relaton
       #
       # Add or update index item
       #
-      # @param [Pubid::Core::Identifier::Base] id document ID
+      # @param [Pubid::Identifier] id document ID
       # @param [String] file file name of the document
       #
       # @return [void]
@@ -62,7 +64,7 @@ module Relaton
       #
       # Search index for a given ID
       #
-      # @param [String, Pubid::Core::Identifier::Base] id ID to search for
+      # @param [String, Pubid::Identifier] id ID to search for
       #
       # @return [Array<Hash>] search results
       #
@@ -131,10 +133,6 @@ module Relaton
         index[left...right]
       end
 
-      def get_id_number(id)
-        id.respond_to?(:base) && id.base ? id.base.number.to_s : id.number.to_s
-      end
-
       def bsearch_left(target)
         index.bsearch_index do |item|
           get_id_number(item[:id]) >= target

data/lib/relaton/index/version.rb

@@ -2,6 +2,6 @@
 
 module Relaton
   module Index
-    VERSION = "0.2.21"
+    VERSION = "2.2.0.pre.alpha.1"
   end
 end

data/lib/relaton/index.rb

@@ -3,12 +3,12 @@
 require "yaml"
 require "zip"
 require "relaton/logger"
-require "pubid-core"
 
 require_relative "index/version"
 require_relative "index/file_storage"
 require_relative "index/config"
 require_relative "index/util"
+require_relative "index/id_number"
 require_relative "index/pool"
 require_relative "index/type"
 require_relative "index/file_io"

metadata

@@ -1,13 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-index
 version: !ruby/object:Gem::Version
-  version: 0.2.21
+  version: 2.2.0.pre.alpha.1
 platform: ruby
 authors:
 - Ribose Inc.
+autorequire:
 bindir: exe
 cert_chain: []
-date: 1980-01-02 00:00:00.000000000 Z
+date: 2026-06-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: openssl
@@ -23,34 +24,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 3.3.2
-- !ruby/object:Gem::Dependency
-  name: pubid-core
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 1.15.6
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 1.15.6
 - !ruby/object:Gem::Dependency
   name: relaton-logger
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.2.0
+        version: 2.2.0.pre.alpha.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.2.0
+        version: 2.2.0.pre.alpha.1
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
@@ -65,6 +52,7 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 2.3.0
+description:
 email:
 - open.source@ribose.com
 executables: []
@@ -72,7 +60,6 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".rspec"
-- ".rubocop.yml"
 - CLAUDE.md
 - Gemfile
 - LICENSE.txt
@@ -82,11 +69,11 @@ files:
 - lib/relaton/index/config.rb
 - lib/relaton/index/file_io.rb
 - lib/relaton/index/file_storage.rb
+- lib/relaton/index/id_number.rb
 - lib/relaton/index/pool.rb
 - lib/relaton/index/type.rb
 - lib/relaton/index/util.rb
 - lib/relaton/index/version.rb
-- relaton-index.gemspec
 - sig/relaton/index.rbs
 homepage: https://github.com/relaton/relaton-index
 licenses:
@@ -94,6 +81,7 @@ licenses:
 metadata:
   homepage_uri: https://github.com/relaton/relaton-index
   source_code_uri: https://github.com/relaton/relaton-index
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -101,14 +89,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 3.1.0
+      version: 3.3.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.9
+rubygems_version: 3.5.22
+signing_key:
 specification_version: 4
 summary: Relaton Index is a library for indexing Relaton files.
 test_files: []

data/.rubocop.yml

@@ -1,12 +0,0 @@
-# This project follows the Ribose OSS style guide.
-# https://github.com/riboseinc/oss-guides
-# All project-specific additions and overrides should be specified in this file.
-
-require: rubocop-rails
-
-inherit_from:
-  - https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
-AllCops:
-  TargetRubyVersion: 3.1
-Rails:
-  Enabled: false

data/relaton-index.gemspec

@@ -1,40 +0,0 @@
-# frozen_string_literal: true
-
-require_relative "lib/relaton/index/version"
-
-Gem::Specification.new do |spec|
-  spec.name = "relaton-index"
-  spec.version = Relaton::Index::VERSION
-  spec.authors = ["Ribose Inc."]
-  spec.email = ["open.source@ribose.com"]
-
-  spec.summary = "Relaton Index is a library for indexing Relaton files."
-  spec.homepage = "https://github.com/relaton/relaton-index"
-  spec.license = "MIT"
-  spec.required_ruby_version = ">= 3.1.0"
-
-  # 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"] = spec.homepage
-  # 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|
-      (f == __FILE__) || f.match(%r{\A(?:(?:bin|test|spec|features)/|\.(?:git|circleci)|appveyor)})
-    end
-  end
-  spec.bindir = "exe"
-  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
-  spec.require_paths = ["lib"]
-
-  spec.add_dependency "openssl", "~> 3.3.2"
-  spec.add_dependency "pubid-core", "~> 1.15.6"
-  spec.add_dependency "relaton-logger", "~> 0.2.0"
-  spec.add_dependency "rubyzip", "~> 2.3.0"
-
-  # For more information and examples about making a new gem, check out our
-  # guide at: https://bundler.io/guides/creating_gem.html
-end