pubid 2.0.17 → 2.0.19

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0da3c4f8d7e991cfcee13325c148d4a58d3f9819521e24e96d6c9847dd0c49f1
-  data.tar.gz: 54c6aa151ee3c7ea3769b8ce83f153767ee48b804e967a02b805c097e71f8b31
+  metadata.gz: d2bbeed2065311312a5f62f6315be2f0d29cf03245755bf5a95b741567e08a96
+  data.tar.gz: cd32eefaf7a17f10fae7b4a78055e3f241758e544848d4b1dac239a0d1ff30c1
 SHA512:
-  metadata.gz: 80f63afedfd49021008da385957f9ea5c4dfb858e941467be476fb41027888a802c16c1c6542c86a0ef427cc507b9a419912bcb8529f3a2fe24dfd1939e0362a
-  data.tar.gz: a47f5d38518d79b0443f1cb9903f5b82d6875031be8f6b579f4b6b5fb0da7dab2e68f25c3ec4ecc008554a45dcacebc17c89d69edc606dcf34ec866c3c774bd3
+  metadata.gz: 9b543322085f97459a47b0ccd67541b9ae9106695e4779e4e385294460aa9c702f5247623d19762ee33c37810031c3d97e030d5d67e5859fde2e932b18f0e140
+  data.tar.gz: e147a8e6484951b7a31db7f013942aae7ebad11fe63b321c325fe71d72025e27415dce3cbcfa85f4159f6d2cedf2369da1a77dbce80702708333b7a4c2f62a0a

data/README.adoc

@@ -51,6 +51,141 @@ both humans and machines, in a round-trippable manner.
 
 See <<v2-migration-status>> for detailed status and <<v2-usage-examples>> for examples.
 
+== Documentation
+
+[cols="1,2", options="header"]
+|===
+|Document |Contents
+
+|link:docs/CONSTRUCTION.md[Constructing identifiers programmatically]
+|The v2 replacement for the v1 `Identifier.create`: `.new` keyword
+construction, `Pubid.from_hash`, supplement-with-base, copublishers, stages,
+and the cross-flavor keyword conventions (spec-tested by
+`spec/pubid/attribute_construction_spec.rb`).
+
+|link:docs/flavor-guides/iso.md[ISO: usage, rendering formats and stage mapping]
+|ISO rendering options (`lang_single`, `stage_format_long`, `with_date`,
+`with_edition`), the DAM/FDAM and DCor/FDCor supplement-stage abbreviations,
+the per-doctype harmonized-stage mapping tables, stage iteration, and typed
+stage queries. Ported from the archived pubid-iso README, restated for v2.
+
+|link:docs/flavor-guides/ieee.md[IEEE identifier patterns]
+|The Type I / Type II pattern series (with the full historic regexes), the
+filename generator (`to_mr_string`/`to_slug`), relationship clauses, and the
+AIEE/IRE predecessor-organization forms. Ported from the archived pubid-ieee
+README.
+
+|link:docs/flavor-guides/iec.md[IEC: TRF format grammars]
+|IECEE and IECEx Test Report Form patterns — the `&` part join, the
+`F_II`-style sub-versions, the `_EMC`/`_PS`/`_SOF` test-type suffixes, and the
+IECEx `_`/`v` separator. Ported from the archived pubid-iec README.
+
+|link:docs/flavor-guides/plateau.md[PLATEAU: the Handbook #11 edition split]
+|Why an edition-1–3 "Handbook #11" reference with a part suffix parses as
+Handbook #06 / #04 (the rule encoded in `data/plateau/update_codes.yaml`).
+Ported from the archived pubid-plateau README.
+
+|link:docs/RENDERING_GUIDE.md[Advanced Rendering Styles Guide]
+|ISO short/long supplement abbreviation preservation and IEC `AMD1` vs
+`Amd 1` spacing.
+
+|link:docs/identifier-patterns/README.md[Identifier pattern reference (generated)]
+|Per-flavor reference docs (`docs/identifier-patterns/<flavor>.md`) generated
+from the code by `rake docs:patterns` — identifier types, typed stages,
+harmonized codes.
+
+|link:docs/URN-GENERATION-GUIDE.adoc[URN Generation Guide]
+|`#to_urn` and `#to_pubid_urn`, RFC 5141-bis.
+|===
+
+=== Flavor index
+
+All flavors live in the one gem under `lib/pubid/<flavor>/`; each has a
+publisher page on https://pubid.github.io/publishers[pubid.github.io].
+
+// Compatibility aliases (:cen -> :cen_cenelec, :3gpp -> module Tgpp) are noted inline.
+|===
+|Flavor |Flavor |Flavor
+
+|link:https://pubid.github.io/publishers/iso[ISO]
+|link:https://pubid.github.io/publishers/iec[IEC]
+|link:https://pubid.github.io/publishers/ieee[IEEE]
+
+|link:https://pubid.github.io/publishers/nist[NIST]
+|link:https://pubid.github.io/publishers/itu[ITU]
+|link:https://pubid.github.io/publishers/bsi[BSI]
+
+|link:https://pubid.github.io/publishers/cen-cenelec[CEN/CENELEC]
+|link:https://pubid.github.io/publishers/etsi[ETSI]
+|link:https://pubid.github.io/publishers/jis[JIS]
+
+|link:https://pubid.github.io/publishers/tgpp[3GPP]
+|link:https://pubid.github.io/publishers/ansi[ANSI]
+|link:https://pubid.github.io/publishers/api[API]
+
+|link:https://pubid.github.io/publishers/astm[ASTM]
+|link:https://pubid.github.io/publishers/ashrae[ASHRAE]
+|link:https://pubid.github.io/publishers/asme[ASME]
+
+|link:https://pubid.github.io/publishers/bipm[BIPM]
+|link:https://pubid.github.io/publishers/ccsds[CCSDS]
+|link:https://pubid.github.io/publishers/cie[CIE]
+
+|link:https://pubid.github.io/publishers/csa[CSA]
+|link:https://pubid.github.io/publishers/doi[DOI]
+|link:https://pubid.github.io/publishers/easc[EASC]
+
+|link:https://pubid.github.io/publishers/ecma[ECMA]
+|link:https://pubid.github.io/publishers/evs[EVS]
+|link:https://pubid.github.io/publishers/gb[GB]
+
+|link:https://pubid.github.io/publishers/gost[GOST]
+|link:https://pubid.github.io/publishers/iala[IALA]
+|link:https://pubid.github.io/publishers/iana[IANA]
+
+|link:https://pubid.github.io/publishers/idf[IDF]
+|link:https://pubid.github.io/publishers/ietf[IETF]
+|link:https://pubid.github.io/publishers/iho[IHO]
+
+|link:https://pubid.github.io/publishers/isbn[ISBN]
+|link:https://pubid.github.io/publishers/jcgm[JCGM]
+|link:https://pubid.github.io/publishers/oasis[OASIS]
+
+|link:https://pubid.github.io/publishers/ogc[OGC]
+|link:https://pubid.github.io/publishers/oiml[OIML]
+|link:https://pubid.github.io/publishers/omg[OMG]
+
+|link:https://pubid.github.io/publishers/plateau[PLATEAU]
+|link:https://pubid.github.io/publishers/sae[SAE]
+|link:https://pubid.github.io/publishers/un[UN]
+
+|link:https://pubid.github.io/publishers/w3c[W3C]
+|link:https://pubid.github.io/publishers/xsf[XSF]
+|link:https://pubid.github.io/publishers/adobe[Adobe]
+
+|link:https://pubid.github.io/publishers/amca[AMCA]
+|link:https://pubid.github.io/publishers/calconnect[CalConnect]
+|
+|===
+
+(The gem's 3GPP flavor key is `3gpp`; its publisher page is `tgpp`. CEN and
+CENELEC share the `cen_cenelec` flavor, publisher page `cen-cenelec`.)
+
+=== Historic identifier patterns
+
+Some identifier eras predate the flavors and are not fully re-documented here;
+their pattern records live in the archived per-gem READMEs
+(`gh api repos/pubid/pubid-<flavor>/contents/README.adoc`):
+
+* *NBS-era NIST* — the National Bureau of Standards series (1920s–1988:
+  `NBS CIRC`, `NBS LCIRC`, `NBS CSM`, `FIPS` before the NIST rename) are
+  described in the archived link:https://github.com/pubid/pubid-nist#readme[pubid-nist README];
+  the v2 parser accepts them and preserves the NBS publisher.
+* *AIEE and IRE IEEE* — the predecessor organizations (1884–1963) are covered
+  in link:docs/flavor-guides/ieee.md[the IEEE patterns doc] and the archived
+  link:https://github.com/pubid/pubid-ieee#readme[pubid-ieee README].
+
+
 == URN Generation (RFC 5141-bis)
 
 PubID V2 implements RFC 5141-bis compliant URN generation for ISO and IEC identifiers with **full test coverage**.

data/lib/pubid/adobe/identifier.rb

@@ -27,6 +27,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         # R1 parser swap: the baked PG artifact is the parser of record.
         parsed = Pubid::Parg::Model.bound(:adobe, identifier.strip)
         Builder.build(parsed)

data/lib/pubid/amca/identifiers/base.rb

@@ -17,6 +17,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:amca, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/ansi/identifier.rb

@@ -23,6 +23,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        string = ::Pubid.utf8_input(string)
+
         parsed = Pubid::Parg::Model.bound(:ansi, string)
         Pubid::Ansi::Builder.new.build(parsed)
       end

data/lib/pubid/api/identifier.rb

@@ -28,6 +28,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        input = ::Pubid.utf8_input(input)
+
         # There used to be a `return nil if input.start_with?("#")` here, to
         # skip the comment lines of a fixture file. A comment is not an
         # identifier, so it must be rejected like any other unparseable string:

data/lib/pubid/ashrae/identifiers/base.rb

@@ -19,6 +19,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:ashrae, Parser.normalize_input(identifier))
         Builder.build(parsed)
       end

data/lib/pubid/ashrae.rb

@@ -30,6 +30,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       Identifier.parse(identifier)
     end
 

data/lib/pubid/asme/identifier.rb

@@ -13,6 +13,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        str = ::Pubid.utf8_input(str)
+
         builder = Builder.new
 
         parsed = Pubid::Parg::Model.bound(:asme, str)

data/lib/pubid/astm/identifier.rb

@@ -13,6 +13,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        str = ::Pubid.utf8_input(str)
+
         builder = Builder.new
 
         parsed = Pubid::Parg::Model.bound(:astm, str)

data/lib/pubid/bipm/identifier.rb

@@ -281,6 +281,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         # Normalize legacy/docnumber-style spellings before parsing
         # (data/bipm/update_codes.yaml), mirroring Pubid::Ccsds / Pubid::Plateau.
         normalized = Core::UpdateCodes.apply(identifier, :bipm)

data/lib/pubid/bipm.rb

@@ -44,6 +44,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       Identifier.parse(identifier)
     end
 

data/lib/pubid/bsi/single_identifier.rb

@@ -18,6 +18,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        string = ::Pubid.utf8_input(string)
+
         # Delegate to IEC for bare IEC identifiers. This handles IEC-specific
         # features like VAP suffixes (CSV, RLV, etc.) and consolidated
         # supplements (+AMD1:2001).

data/lib/pubid/bsi.rb

@@ -232,6 +232,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      string = ::Pubid.utf8_input(string)
+
       Identifier.parse(string)
     end
 

data/lib/pubid/calconnect/identifier.rb

@@ -118,6 +118,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         Pubid::Parg::Model.parse(:calconnect, Identifiers::Standard, identifier)
       end
     end

data/lib/pubid/calconnect.rb

@@ -35,6 +35,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       Identifier.parse(identifier)
     end
 

data/lib/pubid/ccsds/identifier.rb

@@ -75,6 +75,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         # Apply legacy update_codes normalization first
         normalized = Core::UpdateCodes.apply(identifier, :ccsds)
         parsed = Pubid::Parg::Model.bound(:ccsds, normalized)

data/lib/pubid/cen_cenelec/identifier.rb

@@ -119,6 +119,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         normalized = Parser.normalize_input(identifier)
         parsed = Pubid::Parg::Model.bound(:cen_cenelec, normalized)
         Builder.new.build(parsed)

data/lib/pubid/cen_cenelec.rb

@@ -166,6 +166,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       CenCenelec::Identifier.parse(identifier)
     end
 

data/lib/pubid/cie/identifier.rb

@@ -28,6 +28,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        input = ::Pubid.utf8_input(input)
+
         parsed = Pubid::Parg::Model.bound(:cie, Parser.normalize_input(input))
         builder = Builder.new
         builder.build(parsed, original_string: input)

data/lib/pubid/cie.rb

@@ -34,6 +34,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      input = ::Pubid.utf8_input(input)
+
       Identifier.parse(input)
     end
 

data/lib/pubid/components/typed_stage.rb

@@ -8,12 +8,7 @@ module Pubid
     # URN render: stage code (RFC 5141-bis: stage-XX.XX format handled by urn_generator).
     class TypedStage < Lutaml::Model::Serializable
       include ::Pubid::SubsetMatch
-
-      # `original_abbr` records the input spelling ("Amd" or "AMD"), not the
-      # stage, so a subset match skips it.
-      def self.subset_ignored_attributes
-        %i[original_abbr]
-      end
+      include ::Pubid::EqualityIgnored
 
       attribute :name, :string
       attribute :code, :string
@@ -25,6 +20,12 @@ module Pubid
       attribute :short_abbr, :string
       attribute :long_abbr, :string
 
+      # `original_abbr` records the input spelling ("Amd.", "AMD", "DAmd"),
+      # not the stage, so `==`, `hash` and `===` skip it (issue #656). It is
+      # not serialized: the parse path keeps the input spelling and
+      # `from_hash` rebuilds the canonical one, and the two ids must be ==.
+      equality_ignored :original_abbr
+
       def to_stage
         Stage.new(
           name: name,

data/lib/pubid/csa/identifier.rb

@@ -26,6 +26,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        input = ::Pubid.utf8_input(input)
+
         # Filter out comments
         if input.start_with?("#")
           raise Pubid::Errors::ParseError.new(

data/lib/pubid/csa.rb

@@ -31,6 +31,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier_string = ::Pubid.utf8_input(identifier_string)
+
       Identifier.parse(identifier_string)
     end
 

data/lib/pubid/doi/identifier.rb

@@ -41,6 +41,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:doi, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/easc/identifier.rb

@@ -37,6 +37,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:easc, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/ecma/identifier.rb

@@ -134,6 +134,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:ecma, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/etsi/identifiers/base.rb

@@ -18,6 +18,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:etsi, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/evs/identifier.rb

@@ -64,6 +64,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        string = ::Pubid.utf8_input(string)
+
         Pubid::Evs.parse(string)
       end
     end

data/lib/pubid/evs.rb

@@ -34,6 +34,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       # The trailing language code (" et" / " en" / " et-en") extracts
       # before the grammar runs — the CEN adopted_string is greedy over
       # plain text and would swallow it.

data/lib/pubid/gb/identifier.rb

@@ -86,6 +86,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:gb, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/gost/identifier.rb

@@ -23,6 +23,8 @@ module Pubid
                 ::Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:gost, Parser.normalize_input(identifier))
         Builder.build(parsed)
       end

data/lib/pubid/iala/identifier.rb

@@ -30,6 +30,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         if FormatDetector.detect(identifier) == :urn
           UrnParser.parse(identifier)
         else

data/lib/pubid/iana/identifier.rb

@@ -132,6 +132,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:iana, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/idf/identifier.rb

@@ -83,6 +83,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        string = ::Pubid.utf8_input(string)
+
         parsed = Pubid::Parg::Model.bound(:idf, string)
         Pubid::Idf::Builder.new.build(parsed)
       end

data/lib/pubid/idf.rb

@@ -29,6 +29,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       builder = Builder.new
 
       parsed = Pubid::Parg::Model.bound(:idf, identifier)

data/lib/pubid/iec/identifier.rb

@@ -316,6 +316,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        string = ::Pubid.utf8_input(string)
+
         # Route URN strings to the URN parser (mirrors Iso::Identifier.parse)
         if Pubid::FormatDetector.detect(string) == :urn
           return Pubid::Iec::UrnParser.parse(string)

data/lib/pubid/iec/urn_parser.rb

@@ -22,8 +22,12 @@ module Pubid
       # Parse IEC URN string
       # @param urn [String] URN string to parse
       # @return [Identifier] parsed identifier
+      # @raise [Pubid::Errors::InvalidInputError] for a non-String
+      # @raise [Pubid::Errors::UrnParseError] for a URN that does not parse
       def self.parse(urn)
-        new.parse_urn(urn)
+        ::Pubid::UrnParser::Base.guarded_parse(urn) do |utf8|
+          new.parse_urn(utf8)
+        end
       end
 
       # Parse URN string into identifier

data/lib/pubid/ieee/identifiers/base.rb

@@ -389,6 +389,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        input = ::Pubid.utf8_input(input)
+
         result = PreParser.preprocess(input)
 
         case result.dispatch

data/lib/pubid/ieee.rb

@@ -55,6 +55,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        input = ::Pubid.utf8_input(input)
+
         Identifier.parse(input)
       end
 

data/lib/pubid/ietf/identifiers/base.rb

@@ -64,6 +64,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:ietf, strip_prefix(identifier))
         Builder.build(parsed)
       end

data/lib/pubid/ietf.rb

@@ -41,6 +41,8 @@ module Pubid
               Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       Identifier.parse(identifier)
     end
 

data/lib/pubid/iho/identifiers/base.rb

@@ -32,6 +32,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:iho, identifier.strip)
         Builder.build(parsed)
       end

data/lib/pubid/isbn/identifier.rb

@@ -53,7 +53,9 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
-        # The two guards above must stay OUTSIDE build_identifier: this method
+        identifier = ::Pubid.utf8_input(identifier)
+
+        # The guards above must stay OUTSIDE build_identifier: this method
         # rescues ArgumentError to convert the Builder's check-digit and
         # length validation into a parse failure, and that rescue used to
         # swallow the guards' own ArgumentError and re-raise it as a

data/lib/pubid/iso/CLAUDE.md

@@ -143,3 +143,18 @@
     (`data/parg/iso.parg`) must move together — the twin is the embedded
     source's provenance copy.
 
+- **`typed_stage.original_abbr` is spelling, so `==` skips it (issue #656).**
+  The parse path stores the input token (`Amd.`, `COR`, `DAmd`, `pDCOR`) and
+  `stage_from_kv` stores the canonical one (`Amd`, `Cor`, `DAM`); the value is
+  not serialized. Before the fix, 90 pass ids (supplements, Directives,
+  Guides, `ISO/NWIP`) were not `==` after `from_hash(to_hash)`, so
+  `#matches?` against an index row returned false with no error. ISO cannot
+  delete the write as JCGM and IEC did, because `detect_stage_format_long`
+  reads it. `Components::TypedStage` now declares
+  `equality_ignored :original_abbr`. Since `to_s` reads the value, two `==`
+  ids may render differently, which the #656 rule allows. Locked by
+  `spec/pubid/iso/typed_stage_round_trip_spec.rb`.
+  **Still open, and not covered by that spec**: 14 pass ids stay unequal for
+  another reason — `DirectivesSupplement#supplement_publisher` is an
+  `Iso::Components::Publisher` after `parse` and a `Pubid::Components::Publisher`
+  after `from_hash` (11 supplements, 3 bundles).

data/lib/pubid/iso/identifier.rb

@@ -306,6 +306,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        string = ::Pubid.utf8_input(string)
+
         format = Pubid::FormatDetector.detect(string) if format == :auto
 
         case format

data/lib/pubid/iso/urn_parser.rb

@@ -64,8 +64,12 @@ module Pubid
       # Parse ISO URN string
       # @param urn [String] URN string to parse
       # @return [Identifier] parsed identifier
+      # @raise [Pubid::Errors::InvalidInputError] for a non-String
+      # @raise [Pubid::Errors::UrnParseError] for a URN that does not parse
       def self.parse(urn)
-        new.parse_urn(urn)
+        ::Pubid::UrnParser::Base.guarded_parse(urn) do |utf8|
+          new.parse_urn(utf8)
+        end
       end
 
       # Parse URN string into identifier
@@ -74,11 +78,17 @@ module Pubid
       def parse_urn(urn)
         # Remove urn:iso:std: prefix
         unless urn.start_with?("urn:iso:std:")
-          raise ArgumentError,
+          raise ::Pubid::Errors::UrnParseError,
                 "Invalid ISO URN: #{urn}"
         end
 
         parts = urn.sub("urn:iso:std:", "").split(":")
+        # "urn:iso:std:" has no originator; reading it as a publisher
+        # reached `split` on nil (issue #670).
+        if parts.empty?
+          raise ::Pubid::Errors::UrnParseError,
+                "missing originator: #{urn}"
+        end
 
         # Series suffix: a trailing "ser" marks an all-parts identifier. Strip
         # it before component parsing so it is not misread as a language or

data/lib/pubid/iso.rb

@@ -42,6 +42,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       format = Pubid::FormatDetector.detect(identifier) if format == :auto
 
       case format

data/lib/pubid/itu/identifiers/base.rb

@@ -19,6 +19,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:itu, normalize_whitespace(identifier))
         Builder.build(parsed)
       end

data/lib/pubid/jcgm.rb

@@ -33,6 +33,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       builder = Builder.new
 
       parsed = Pubid::Parg::Model.bound(:jcgm, identifier)

data/lib/pubid/jis/identifier.rb

@@ -184,6 +184,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:jis, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/nist.rb

@@ -78,6 +78,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       # Use the Parser class's preprocessing method
       # Note: We call the class method directly to ensure preprocessing is applied
       parsed = Parser.class_parse_with_preprocessing(identifier)

data/lib/pubid/oasis/identifier.rb

@@ -146,6 +146,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:oasis, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/oasis.rb

@@ -32,6 +32,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       Identifier.parse(identifier)
     end
 

data/lib/pubid/ogc/identifier.rb

@@ -96,6 +96,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         Builder.build(Pubid::Parg::Model.bound(:ogc, identifier))
       end
     end

data/lib/pubid/oiml.rb

@@ -30,6 +30,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       if identifier.include?("|")
         dual = Identifiers::DualPublished.build(identifier)
         return dual if dual

data/lib/pubid/omg/identifier.rb

@@ -58,6 +58,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:omg, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/plateau.rb

@@ -29,6 +29,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      input = ::Pubid.utf8_input(input)
+
       # Apply legacy update_codes normalization first
       normalized = Core::UpdateCodes.apply(input, :plateau)
       parsed = Pubid::Parg::Model.bound(:plateau, normalized)

data/lib/pubid/sae/identifiers/base.rb

@@ -16,6 +16,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        input = ::Pubid.utf8_input(input)
+
         parsed = Pubid::Parg::Model.bound(:sae, input)
         Builder.build(parsed)
       end

data/lib/pubid/subset_match.rb

@@ -169,9 +169,7 @@ module Pubid
     # Exactness composes rather than flattening: a nested value that
     # includes this module is matched in BOTH directions with its own
     # `===`, so the class that owns it keeps its rule. A plain `==` would
-    # override it — `Components::TypedStage` ignores `original_abbr`
-    # (the input spelling, `Amd` against `AMD`), and CEN/CENELEC declares
-    # `typed_stage` strict.
+    # override it — CEN/CENELEC declares `typed_stage` strict.
     # @return [Boolean]
     def self.exact_match?(mine, theirs)
       return true if blank?(mine) && blank?(theirs)

data/lib/pubid/tgpp/identifier.rb

@@ -113,6 +113,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:tgpp, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/tgpp.rb

@@ -47,6 +47,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       Identifier.parse(identifier)
     end
 

data/lib/pubid/un/identifier.rb

@@ -32,6 +32,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:un, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/urn_parser/base.rb

@@ -16,10 +16,50 @@ module Pubid
     # {number}:{year}` shape.
     class Base
       # Parse a URN string into an Identifier.
+      #
       # @param urn [String]
       # @return [Pubid::Identifier]
+      # @raise [Pubid::Errors::InvalidInputError] for a non-String
+      # @raise [Pubid::Errors::UrnParseError] for a URN that does not parse
       def self.parse(urn)
-        new.parse_urn(urn)
+        guarded_parse(urn) { |utf8| new.parse_urn(utf8) }
+      end
+
+      # Run a URN decode under the pubid error contract (issue #670). The
+      # input checks run first, before a parser reaches +downcase+ or a
+      # regex on the string. A decode then fails as a pubid error only:
+      # the raw classes a malformed body produced (+NoMethodError+ on a
+      # missing segment, +IndexError+ from +fetch+, +ArgumentError+) are
+      # wrapped as {Pubid::Errors::UrnParseError}, with the raw error kept
+      # as the cause so a parser defect stays visible. This is the same
+      # wrap +Pubid.parse_urn+ applies; here it also covers a direct call.
+      # ISO and IEC have their own parser classes and call this too.
+      #
+      # @param urn [Object]
+      # @yieldparam utf8 [String] the URN as a valid UTF-8 string
+      # @return [Pubid::Identifier] the block's result
+      def self.guarded_parse(urn)
+        yield validate_input!(urn)
+      rescue ::Pubid::Errors::Error
+        raise
+      rescue StandardError => e
+        raise ::Pubid::Errors::UrnParseError,
+              "#{name} cannot parse URN #{urn.inspect}: #{e.message}"
+      end
+
+      # The input checks every URN parser runs first.
+      # @param urn [Object]
+      # @return [String] the URN as a valid UTF-8 string (see
+      #   {Pubid.utf8_input})
+      # @raise [Pubid::Errors::InvalidInputError] for a non-String
+      # @raise [Pubid::Errors::UrnParseError] for invalid encoding bytes
+      def self.validate_input!(urn)
+        unless urn.is_a?(String)
+          raise ::Pubid::Errors::InvalidInputError,
+                ::Pubid::INPUT_NOT_A_STRING_MESSAGE
+        end
+
+        ::Pubid.utf8_input(urn, ::Pubid::Errors::UrnParseError)
       end
 
       # Subclasses override.

data/lib/pubid/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Pubid
-  VERSION = "2.0.17"
+  VERSION = "2.0.19"
 end

data/lib/pubid/w3c/identifier.rb

@@ -122,6 +122,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:w3c, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/xsf/identifier.rb

@@ -62,6 +62,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
+        identifier = ::Pubid.utf8_input(identifier)
+
         parsed = Pubid::Parg::Model.bound(:xsf, identifier)
         Builder.build(parsed)
       end

data/lib/pubid/xsf.rb

@@ -34,6 +34,8 @@ module Pubid
         raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
       end
 
+      identifier = ::Pubid.utf8_input(identifier)
+
       Identifier.parse(identifier)
     end
 

data/lib/pubid.rb

@@ -39,6 +39,57 @@ module Pubid
   # point rejects a non-String before it measures the length.
   INPUT_NOT_A_STRING_MESSAGE = "identifier must be a String"
 
+  # Raised when an input string cannot be read as UTF-8.
+  INPUT_INVALID_ENCODING_MESSAGE = "input string has invalid encoding"
+
+  # Encodings whose strings are read as raw bytes: their bytes are taken as
+  # UTF-8 without a conversion.
+  BYTE_ENCODINGS = [Encoding::UTF_8, Encoding::BINARY,
+                    Encoding::US_ASCII].freeze
+
+  # Return +string+ as a valid UTF-8 string, or raise a pubid error
+  # (issue #670). Invalid encoding is bad input, not a grammar failure:
+  # without this step the detectors, the normalization regexes and the
+  # parser raise raw `ArgumentError` (invalid byte sequence), `EncodingError`
+  # or `Encoding::CompatibilityError`, which are outside the {Errors::Error}
+  # marker.
+  #
+  # A UTF-8, binary or US-ASCII string is read as UTF-8 bytes, so ".b" of
+  # ASCII text passes and a stray high byte does not. A string labelled with
+  # another encoding (ISO-8859-1, Windows-1252, UTF-16LE …) is converted, so
+  # a valid "café" in Latin-1 parses as it does in UTF-8. A valid UTF-8
+  # string comes back as the same object.
+  #
+  # Every public +parse+ entry point assigns the result after its inline
+  # length guard. The length guard stays inline because it is the CodeQL
+  # barrier; this step is not one, so it can be a shared method.
+  #
+  # @param string [String]
+  # @param error_class [Class] the pubid error to raise
+  # @return [String] a valid UTF-8 string
+  # @raise [Errors::InvalidInputError] (or +error_class+) when the string
+  #   cannot be read as UTF-8
+  def self.utf8_input(string, error_class = Errors::InvalidInputError)
+    utf8 = if BYTE_ENCODINGS.include?(string.encoding)
+             utf8_bytes(string)
+           else
+             string.encode(Encoding::UTF_8)
+           end
+    return utf8 if utf8.valid_encoding?
+
+    raise error_class, INPUT_INVALID_ENCODING_MESSAGE
+  rescue EncodingError
+    raise error_class, INPUT_INVALID_ENCODING_MESSAGE
+  end
+
+  # The bytes of +string+ labelled UTF-8 (the same object when they are).
+  def self.utf8_bytes(string)
+    return string if string.encoding == Encoding::UTF_8
+
+    string.dup.force_encoding(Encoding::UTF_8)
+  end
+  private_class_method :utf8_bytes
+
   # Registry for tracking all loaded flavors
   class Registry
     @flavors = {}
@@ -252,15 +303,7 @@ module Pubid
       raise Pubid::Errors::InvalidInputError,
             Pubid::INPUT_TOO_LONG_MESSAGE
     end
-    # Invalid encoding is bad input, not a grammar failure: the detectors
-    # and normalization regexes raise raw `ArgumentError` (invalid byte
-    # sequence) or `Encoding::CompatibilityError` on it, which is the leak
-    # the contract closes (issue #670). The bytes are read as UTF-8 — a
-    # binary string of ASCII bytes (".b") is fine, high bytes are not.
-    unless string.dup.force_encoding(Encoding::UTF_8).valid_encoding?
-      raise Pubid::Errors::InvalidInputError,
-            "input string has invalid encoding"
-    end
+    string = utf8_input(string)
 
     format = FormatDetector.detect(string) if format == :auto
 
@@ -308,6 +351,7 @@ module Pubid
       raise Pubid::Errors::InvalidInputError,
             Pubid::INPUT_NOT_A_STRING_MESSAGE
     end
+    string = utf8_input(string, Errors::UrnParseError)
     eager_load_flavors!
     return PubidUrn.parse(string) if PubidUrn.pubid_urn?(string)
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pubid
 version: !ruby/object:Gem::Version
-  version: 2.0.17
+  version: 2.0.19
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-11-08 00:00:00.000000000 Z
+date: 2026-11-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: lutaml-model
@@ -1104,10 +1104,12 @@ files:
 - schema/iec.yaml
 - schema/iso.yaml
 - schema/schema.schema.yaml
-homepage: https://github.com/metanorma/pubid
+homepage: https://github.com/pubid/pubid
 licenses:
 - BSD-2-Clause
 metadata:
+  changelog_uri: https://github.com/pubid/pubid/releases
+  documentation_uri: https://rubydoc.info/gems/pubid
   rubygems_mfa_required: 'true'
 post_install_message:
 rdoc_options: []