pubid 2.0.6 → 2.0.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a55050f14ad3cf19fd2e3d3a00faf0d2258cf761d71515716cdf61a172ce0484
-  data.tar.gz: 9c150c6b494788ad7b3f158ed0bd9132d8ae970089e182d9f5cef7885d22a7de
+  metadata.gz: 8013a826102b555c7067ce39bb01b1b3a4d43a6ec09ba6092ae4fe80ce364c8e
+  data.tar.gz: 9e7ebbfa50e70911201bc5800438ed661c1d03116c85e7f96f164bfc4089b615
 SHA512:
-  metadata.gz: 665bddc99ab7da91c7f67c045655b0b55ef86b500469efdca15a7215ec89479f1fa0c1046fbad88ea3683ed664a3c6d01d54a6fe4800d681ec1b758d73b5b01f
-  data.tar.gz: 6fada1851bb8adbbc936ca69167336f6ddd88dfcce72dbeeb9a73a035449547a8cd6324d5b1240ed3aaa71ddadceb9dff89d5efe22e9f62df0a775055f4110f0
+  metadata.gz: f3d0739c523091e44a03e9c4796696a046dbbad30b6681cc4d19e69df785fff10a8bfb83912bff0d3215def503a1d28d48e1f1ca5f76335424cf9f7782c672bd
+  data.tar.gz: ae1b998769f90c7ea9463cd11c66f0374bf4598d2c7a425bb2f615c5acf592652f2a98fba9bf3b8c1db5c10d4f7b24952c516ca994de58f2f8c55b17db42919b

data/README.adoc

@@ -88,6 +88,22 @@ id.to_urn  # => "urn:iso:std:iso:9001:amd:2020:v1"
 * ✅ Multi-level supplement support with correct nesting order
 * ✅ Round-trip parsing (parse_urn -> to_urn) for ISO and IEC
 
+=== The pubid-scheme URN
+
+`#to_urn` follows the registered grammar of the organization, which can
+drop values (RFC 5141 has no year). `#to_pubid_urn` is pubid's own URN: it
+carries every value, always round-trips through `Pubid.parse_urn`, and is
+safe to use as an HTTP path. ISO, IEEE, ANSI, ITU, NIST and ASTM support it now; the other flavors follow
+(link:docs/URN-SCHEMES.adoc[URN schemes]).
+
+[source,ruby]
+----
+id = Pubid::Iso.parse("ISO 9001:2015/Amd 1:2016")
+id.to_pubid_urn
+# => "urn:pubid:iso:is:9001:year-2015:amd:1:year-2016"
+Pubid.parse_urn(id.to_pubid_urn).to_s  # => "ISO 9001:2015/Amd 1:2016"
+----
+
 === Key Difference: ISO vs IEC Part Numbering
 
 ISO URNs (RFC 5141): part number is a separate colon-separated field:

data/lib/pubid/ansi/pubid_urn_schema.rb

@@ -0,0 +1,44 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Ansi
+    # The pubid-scheme URN of ANSI (issue #656; docs/URN-SCHEMES.adoc).
+    #
+    #   ANSI 802.3-2012
+    #   urn:pubid:ansi:std:802.3:pub-ANSI:part-2012
+    #
+    # Landed with the IEEE wave, which nests ANSI ids ("IEEE Std 144-1971
+    # (ANSI C37.24-1971)"). Note that ANSI stores the year of
+    # "ANSI 802.3-2012" in +part+ ("2012"); the URN keeps it as it is.
+    #
+    # A component attribute maps through its identifying field only
+    # (+type.abbr+, +stage.abbr+, +edition.number+ …). The registry fields of
+    # a stage or a type (+name+, +harmonized_stages+) are deliberately not
+    # placed, so a value there makes #to_pubid_urn raise rather than write
+    # registry data into the URN. The corpus sets none of them.
+    PubidUrnSchema = Pubid::PubidUrn.define("ansi") do
+      atom "publisher.body", "pub"
+      atom "copublishers.*.body", "co"
+      atom "type.abbr", "type"
+      atom "part", "part"
+      atom "subpart", "subpart"
+      atom "year", "year"
+      atom "date.year", "dateyear"
+      atom "date.month", "datemonth"
+      atom "date.day", "dateday"
+      atom "date.undated", "undated", kind: :bool
+      atom "edition.number", "ed"
+      atom "stage.abbr", "stage"
+      atom "stage_iteration.number", "iter"
+      atom "languages.*.code", "lang"
+      atom "locality.value", "loc"
+
+      facet "languages.*.original_code", "langsrc"
+      facet "edition.original_text", "edsrc"
+
+      type "pubid:ansi:standard", "std"
+      type "pubid:ansi:american-national-standard", "ans"
+      type "pubid:ansi:identifier", "id"
+    end
+  end
+end

data/lib/pubid/ansi.rb

@@ -14,6 +14,7 @@ module Pubid
     autoload :Identifier, "#{__dir__}/ansi/identifier"
     autoload :Identifiers, "#{__dir__}/ansi/identifiers"
     autoload :Parser, "#{__dir__}/ansi/parser"
+    autoload :PubidUrnSchema, "#{__dir__}/ansi/pubid_urn_schema"
     autoload :Renderer, "#{__dir__}/ansi/renderer"
     autoload :SingleIdentifier, "#{__dir__}/ansi/single_identifier"
     autoload :UrnGenerator, "#{__dir__}/ansi/urn_generator"

data/lib/pubid/api/pubid_urn_schema.rb

@@ -0,0 +1,29 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Api
+    # The pubid-scheme URN of API (issue #656; docs/URN-SCHEMES.adoc).
+    #
+    #   API MPMS Ch. 10.10  ->  urn:pubid:api:mpms:10.10:subsec-...
+    #
+    # The number is the core of every type; +part+, +section+ and
+    # +subsection+ are atoms, in the doc's canonical order.
+    PubidUrnSchema = Pubid::PubidUrn.define("api") do
+      atom "part", "part"
+      atom "section", "section"
+      atom "subsection", "subsection"
+
+      type "pubid:api:base", "base"
+      type "pubid:api:bulletin", "bulletin"
+      type "pubid:api:continuous-operations-standard", "cos"
+      type "pubid:api:identifier", "id"
+      type "pubid:api:mpms", "mpms"
+      type "pubid:api:publication", "pub"
+      type "pubid:api:recommended-practice", "rp"
+      type "pubid:api:specification", "spec"
+      type "pubid:api:standard", "std"
+      type "pubid:api:technical-report", "tr"
+      type "pubid:api:typeless-standard", "ts"
+    end
+  end
+end

data/lib/pubid/api.rb

@@ -16,6 +16,7 @@ module Pubid
     autoload :SingleIdentifier, "#{__dir__}/api/single_identifier"
     autoload :UrnGenerator, "#{__dir__}/api/urn_generator"
     autoload :UrnParser, "#{__dir__}/api/urn_parser"
+    autoload :PubidUrnSchema, "#{__dir__}/api/pubid_urn_schema"
 
     def self.parse(input)
       Identifier.parse(input)

data/lib/pubid/ashrae/pubid_urn_schema.rb

@@ -0,0 +1,37 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Ashrae
+    # The pubid-scheme URN of ASHRAE (issue #656; docs/URN-SCHEMES.adoc).
+    #
+    #   ASHRAE Standard 15-2007 (RA 2010)
+    #   urn:pubid:ashrae:std:15:year-2007:reaffirmed-2010
+    #
+    # The number is the core of every type (the base-anchored ones emit
+    # it as NULL when absent — the errata and the package carry their
+    # identity in the base chain). The atoms follow the doc's canonical
+    # order; the date internals stay placed until the Components::Code
+    # reduction lands (docs/URN-SCHEMES.adoc, ashrae finding).
+    PubidUrnSchema = Pubid::PubidUrn.define("ashrae") do
+      atom "copublisher", "co"
+      atom "year", "year"
+      atom "date.day", "dateday"
+      atom "date.month", "datemonth"
+      atom "date.year", "dateyear"
+      atom "addendum_code", "addendumcode"
+      atom "addendum_codes", "addendumcodes"
+      atom "package_description", "packagedescription"
+      atom "reaffirmed", "reaffirmed"
+      atom "suffix", "suffix"
+
+      type "pubid:ashrae:addenda-package", "ap"
+      type "pubid:ashrae:addendum", "add"
+      type "pubid:ashrae:combined-addenda", "ca"
+      type "pubid:ashrae:errata", "err"
+      type "pubid:ashrae:guideline", "g"
+      type "pubid:ashrae:identifier", "id"
+      type "pubid:ashrae:interpretation", "interp"
+      type "pubid:ashrae:standard", "std"
+    end
+  end
+end

data/lib/pubid/ashrae.rb

@@ -18,6 +18,7 @@ module Pubid
     autoload :SupplementIdentifier, "#{__dir__}/ashrae/supplement_identifier"
     autoload :UrnGenerator, "#{__dir__}/ashrae/urn_generator"
     autoload :UrnParser, "#{__dir__}/ashrae/urn_parser"
+    autoload :PubidUrnSchema, "#{__dir__}/ashrae/pubid_urn_schema"
 
     def self.parse(identifier)
       unless identifier.is_a?(String)

data/lib/pubid/asme/pubid_urn_schema.rb

@@ -0,0 +1,34 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Asme
+    # The pubid-scheme URN of ASME (issue #656; docs/URN-SCHEMES.adoc).
+    #
+    #   ASME B30.3-20XX (Revision of ASME B30.1-2020)
+    #   urn:pubid:asme:std:B30.3:pub-ASME:draftyear-20XX
+    #     :parentheticalrevision-...
+    #
+    # The number is the core; the atoms follow the doc's canonical order.
+    # +parenthetical_revision+ and +revision_note+ are the two verbatim
+    # bracket notes, case-kept.
+    PubidUrnSchema = Pubid::PubidUrn.define("asme") do
+      atom "publisher", "pub"
+      atom "year", "year"
+      atom "language", "lang"
+      atom "csa_number", "csanumber"
+      atom "draft_year", "draftyear"
+      atom "first_code", "firstcode"
+      atom "first_publisher", "firstpublisher"
+      atom "handbook", "handbook", kind: :bool
+      atom "joint_publisher", "jointpublisher"
+      atom "parenthetical_revision", "parentheticalrevision"
+      atom "ptc_suffix", "ptcsuffix"
+      atom "revision_note", "revisionnote"
+      atom "second_publisher", "secondpublisher"
+
+      type "pubid:asme:base", "base"
+      type "pubid:asme:identifier", "id"
+      type "pubid:asme:standard", "std"
+    end
+  end
+end

data/lib/pubid/asme.rb

@@ -17,6 +17,7 @@ module Pubid
     autoload :SingleIdentifier, "#{__dir__}/asme/single_identifier"
     autoload :UrnGenerator, "#{__dir__}/asme/urn_generator"
     autoload :UrnParser, "#{__dir__}/asme/urn_parser"
+    autoload :PubidUrnSchema, "#{__dir__}/asme/pubid_urn_schema"
 
     def self.parse(str)
       Identifier.parse(str)

data/lib/pubid/astm/CLAUDE.md

@@ -7,3 +7,11 @@ These notes were part of the root `CLAUDE.md`. Read them before you change `lib/
 ## From the root note "AMCA / ASME / ASTM index key (`root.number`): three flavors, three different shapes"
 
 **(3) ASTM — the mixin, on EVERY concrete class.** `Astm::Components::Code` is a five-field taxonomy (`letter`/`number`/`suffix`/`subseries`/`dual_m`) that the renderer reads field-by-field, so it keeps its structure: `Identifiers::CodeNumber` installs the five columns plus a derived `#code`. **It is included by `Standard` AND by `IsoDualPublished`, which inherits `Standard` — deliberately, not redundantly**: a class that is itself inherited from must still declare the columns so its subclass holds its own snapshot rather than relying on a parent table. `Adjunct` has no code at all, so its designation IS its number: the `designation` attribute was **removed** and the value stored in `number` directly, because keeping both made `to_hash` emit the same string twice and a `def number` shadowing the attribute is the construct CLAUDE.md forbids.
+
+## pubid-scheme URN (issue #656)
+
+`lib/pubid/astm/pubid_urn_schema.rb` covers all 12 types; rulings in
+`docs/URN-SCHEMES.adoc` (`[[urn-astm]]`). Every suffix marker (`-EB`, `-EA`,
+`DVD`, the metric `M`, `TP`) names a different catalogue record, so all are
+atoms and ASTM has no facet. A new marker attribute needs an atom there, or
+`#to_pubid_urn` raises for every id that sets it.

data/lib/pubid/astm/pubid_urn_schema.rb

@@ -0,0 +1,47 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Astm
+    # The pubid-scheme URN of ASTM (issue #656; docs/URN-SCHEMES.adoc).
+    #
+    #   ASTM E2938-15(2023)
+    #   urn:pubid:astm:std:2938:letter-E:year-2015:reapproval-2023
+    #
+    # The core is the document number; every other value is an optional
+    # prefixed atom. Each suffix marker ("-EB", "-EA", "DVD", the metric
+    # "M", the "TP" of a manual) names a different catalogue record, so all
+    # are atoms and none is a facet. The current urn:astm: form of #to_urn
+    # is pubid-invented and stays as it is.
+    PubidUrnSchema = Pubid::PubidUrn.define("astm") do
+      atom "publisher", "pub"
+      atom "committee", "committee"
+      atom "letter", "letter"
+      atom "subseries", "subseries"
+      atom "suffix", "suffix"
+      atom "dual_m", "metric", kind: :bool
+      atom "year", "year"
+      atom "sub_year", "subyear"
+      atom "reapproval", "reapproval"
+      atom "edition", "ed"
+      atom "supplement", "sup", kind: :bool
+      atom "tp_designation", "tp"
+      atom "format_suffix", "format"
+      atom "ea_suffix", "ea", kind: :bool
+      atom "dvd_suffix", "dvd", kind: :bool
+      atom "hol_suffix", "hol", kind: :bool
+
+      type "pubid:astm:identifier", "id"
+      type "pubid:astm:single-identifier", "single"
+      type "pubid:astm:base", "base"
+      type "pubid:astm:standard", "std"
+      type "pubid:astm:iso-dual-published", "isodual"
+      type "pubid:astm:adjunct", "adj"
+      type "pubid:astm:data-series", "ds"
+      type "pubid:astm:manual", "mnl"
+      type "pubid:astm:monograph", "mono"
+      type "pubid:astm:research-report", "rr"
+      type "pubid:astm:technical-report", "tr"
+      type "pubid:astm:work-in-progress", "wk"
+    end
+  end
+end

data/lib/pubid/astm.rb

@@ -13,6 +13,7 @@ module Pubid
     autoload :Identifiers, "#{__dir__}/astm/identifiers"
     autoload :SingleIdentifier, "#{__dir__}/astm/single_identifier"
     autoload :Parser, "#{__dir__}/astm/parser"
+    autoload :PubidUrnSchema, "#{__dir__}/astm/pubid_urn_schema"
     autoload :Builder, "#{__dir__}/astm/builder"
     autoload :Renderer, "#{__dir__}/astm/renderer"
     autoload :UrnGenerator, "#{__dir__}/astm/urn_generator"

data/lib/pubid/identifier.rb

@@ -1114,6 +1114,21 @@ module Pubid
       resolve_urn_generator.new(self).generate
     end
 
+    # The lossless pubid-scheme URN ("urn:pubid:…").
+    #
+    # It is in pubid's own namespace (issue #656), carries every value of
+    # #to_hash and always round-trips through Pubid.parse_urn. Not the
+    # same as #to_urn, the official, possibly lossy URN of the
+    # organization. Defined once, here, from #to_hash and the flavor's
+    # PubidUrnSchema; flavors do not override it.
+    #
+    # @return [String]
+    # @raise [Pubid::Errors::InvalidInputError] when the flavor has no
+    #   pubid-scheme schema yet
+    def to_pubid_urn
+      Pubid::PubidUrn.generate(self)
+    end
+
     def resolve_urn_generator
       flavor = self.class.name.split("::")[1]
       Object.const_get("Pubid::#{flavor}::UrnGenerator")

data/lib/pubid/iec/pubid_urn_schema.rb

@@ -0,0 +1,32 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Iec
+    # The pubid-scheme URN of IEC — PARTIAL (issue #656;
+    # docs/URN-SCHEMES.adoc).
+    #
+    # Only +pubid:iec:international-standard+ is declared, because IEEE
+    # identifiers nest it (IEC/IEEE co-publications). IEC's own wave declares
+    # the rest of the flavor; until then IEC stays pending in the contract
+    # spec. The official RFC 5141-style urn:iec:std: form stays on #to_urn.
+    PubidUrnSchema = Pubid::PubidUrn.define("iec") do
+      atom "publisher", "pub"
+      atom "copublishers", "co", kind: :list
+      atom "part", "part"
+      atom "subpart", "subpart"
+      atom "year", "year"
+      atom "month", "month"
+      atom "day", "day"
+      atom "undated", "undated", kind: :bool
+      atom "edition", "ed"
+      atom "stage", "stage"
+      atom "stage_iteration", "iter"
+      atom "database", "database"
+      atom "languages.*.code", "lang"
+
+      facet "languages.*.original_code", "langsrc"
+
+      type "pubid:iec:international-standard", "is"
+    end
+  end
+end

data/lib/pubid/iec.rb

@@ -17,6 +17,7 @@ module Pubid
     autoload :SingleIdentifier, "#{__dir__}/iec/single_identifier"
     autoload :SupplementIdentifier, "#{__dir__}/iec/supplement_identifier"
     autoload :Parser, "#{__dir__}/iec/parser"
+    autoload :PubidUrnSchema, "#{__dir__}/iec/pubid_urn_schema"
     autoload :Builder, "#{__dir__}/iec/builder"
     autoload :UrnParser, "#{__dir__}/iec/urn_parser"
     autoload :UrnGenerator, "#{__dir__}/iec/urn_generator"

data/lib/pubid/ieee/CLAUDE.md

@@ -99,3 +99,5 @@ The lesson BSI paid for: a wrapper's hand-written `#number` delegation makes the
 - **Joint stage-first forms are lead ISO, and the ISO face is lossless (pubid#477)**: a stage word printed in the ISO position (`IEEE FCD 15026.3:2010`, `IEEE/IEC CD2 P62582-2017-05`) parses as printed (#469): `Builder#build_joint_development` sets `lead_party "ISO"` whatever the publisher order, so `canonical_format` is `:iso`. PR #472 had made the lead the first printed publisher and rendered an IEEE-first form in the `D=` face — but the grammar artifact cannot parse most of those renders (`D=FCD`, `D=CD.2`, a non-P number, a month), and `D=CD-2020` parses into a *different* id (`ieee_draft`, no `iso_stage`), so 19 published `relaton-data-ieee` rows stopped matching themselves. The `D=` face now prints only for an id that carries a `D=` designator, or on an explicit `to_s(format: :ieee)`. `JointDevelopment#to_iso_format` prints `iso_stage` as stored (`DIS2`, `CD4` — #472's bare `CD` lost the iteration) and the date in the spelling that parses back (`#iso_date_suffix`: `:2018`, `-2018-05`, `, April 2019`). **The test is `parse(to_s) == id`, not a stable `to_s`**: a lossy render reaches a fixed point and round-trips its *hash* (`iso_stage_spellings_spec` held both while dropping `CD4`→`CD`), yet the reparse is a different identifier. Measured over the 118 joint stage rows of `relaton-data-ieee`: `to_s` stable 100 → 118, `==` 51 → 106; the other 12 carry an `ieee_draft` or an edition that the ISO face still drops. **PARG separator-in-capture, again (#471)**: the draft `revision` capture is `".12"`, and `Draft#to_s` adds its own dot, so `handle_draft` strips the leading dot (`D2022.10.12` rendered `D2022.10..12`). Check every capture a renderer re-joins with a separator. Locked by `spec/pubid/ieee/joint_stage_roundtrip_spec.rb` (stored index hashes → `parse(to_s) == row`).
 
 - **IEEE parses through the edition-2 artifact's typed model bindings (the last converter wave)**: the three `Backend.parse` sites (`identifiers/base.rb` `parse_single`, `Aiee::Identifier.parse`, `Ire::Identifier.parse`) route through `Pubid::Parg::Model.bound` — the grammar's `bindings` block produces the builder-ready hash at the engine, replacing the tree normalization. The grammar side (pubid-grammar `grammars/{ieee,nesc}.parg` edition 2 + bindings, plus a class-ref inlining pass over the merged `aiee.parg`/`ire.parg`) keeps every capture the builder reads: leaf scalars bind `(string)`; the branch/wrapper captures the builder dispatches on (`draft`, `parameters`, `publishers`, `base`, `relationship_type`, `related_ids`, the aiee/ire/nesc wrappers, …) bind `(raw)` — raw subtrees carry `Parsanol::Slice` leaves whose `to_s`/`==` behave like strings, so `extract_value` and the `.is_a?(Hash)` probes are unchanged. **Load-bearing grammar deviations** (documented in the `.parg` headers): the zero-width markers are re-spelled as real-token captures (`printed_dash_year`/`printed_month_year` capture their branch's leading separator, `iec_label_dash` the dash, `iso_published` the whole joint head choice — every read sits behind a nil-`iso_stage` gate, so the wider presence set is inert exactly where v1's was narrow); the `([dash]) as draft_dash` / `([rev_sep] as rev_sep)` capture-over-OPTIONAL landmines are `[ (x) as y ]` (parsanol-ruby#394); nested-only captures that collide with a top-level name rename with the builder (`draft_date_month/year/day`, `draft_version_dash_*`, `fdraft_month/year`, and `reaffirmed_year` — unbound, because binding it would have surfaced the reaffirmation year v1 kept absent). **Class RULE refs (`digit`/`lower`/`upper`, and multi-char ones like `alnum_char`/`identifier_string`'s `non_nl`) materialize per-token named nodes inside captures when the runtime recompiles the `use`-importing source — the vendored `data/parg/{aiee,ire,nesc}.parg` copies are the live import sources, so they must be re-vendored together with the artifacts** (a stale `.parg` beside a fresh `.json` silently parses through the old grammar). **Builder accommodations** (all dual-key with the v1 spellings as fallback, so HEAD trees and bound maps read alike): the renamed nested keys; and the multi-segment draft-version normalization at the top of `build_single_identifier` — edition-2 trees materialize a "D2.1.1" designator as per-token nodes with no `:draft_version`, where v1 degraded to a whole-clause leaf (reconstructed: the leaf string → `Draft.parse` inverse) or to a date-only hash when a draft date follows (no draft built). **Measured**: fixture-corpus parity (old artifact + tree backend + builder vs new artifact + bound + builder) over all 9,054 pass-fixture inputs → 1 diff, and standalone aiee/ire/nesc sweeps → 0 diffs each. **The one residue is an engine wall, documented not chased**: `IEC/IEEE PC37.60/P62271-111_D6.1` (testsuite case `ieee.project_draft_identifier.0946`, one corpus input, one `draft_compact_convergence` example) — v1's edition-1 tree degraded its whole draft clause ("DP62271-111_D6.1, Aug 2016", two P-numbers plus date) into a single leaf, and edition-2's fully-named trees cannot reproduce that collapse at any binding spelling (isolated rule probes + programmatic branch bisect); the row is one of the two-P-number joint one-offs already recorded as deferred above. The conversion also **fixed** two testsuite rows (`ieee.project_draft_identifier.9263` "ISO/IEC/IEEE P42010.2019/D4" / "P42010.WD4:2019(E)" — the lettered `draft_iso_iteration` capture now binds, so the D= face composes), at the cost of the 0946 residue above.
+
+- **The pubid-scheme URN (`#to_pubid_urn`, issue #656) — IEEE wave.** Schema: `lib/pubid/ieee/pubid_urn_schema.rb`; design and rulings: the `[[urn-ieee]]` section of `docs/URN-SCHEMES.adoc`. All 9,049 parseable pass ids emit, round-trip by `to_hash`, are path-safe and collision-free; the contract row is `spec/pubid/pubid_urn_contract_spec.rb`, the per-family examples `spec/pubid/ieee/pubid_urn_spec.rb`. **No `to_hash` change, so no `relaton-data-ieee` re-crawl.** Three things to know before editing: **(1)** the wrappers whose parent slot is not `base` (`ieee_identifier`, `first_identifier`, `primary_identifier` …, see "The parent slot is never called `base` in IEEE" above) write that document as a nested atom, so they do NOT share its slug prefix — renaming a slot to `base` moves every such URN; **(2)** IEEE nests ANSI and IEC ids, so ANSI landed whole with this wave and `lib/pubid/iec/pubid_urn_schema.rb` is a partial schema for the one IEC type the corpus nests — a new nested foreign type (an adopted `IEC TR`, `TS`, `AMD`, `CSV`) makes `#to_pubid_urn` raise until its flavor's schema declares it; **(3)** the schema must place every `to_hash` key, so a new IEEE attribute fails the contract row until its atom is declared — add it in the shared-vocabulary group it belongs to, never at the end out of habit, because atom order is part of every published slug. **The URN inherits two `to_hash` gaps, pinned rather than fixed**: `csa_identifier` is a plain accessor, so the CSA half of a `CsaDualPublished` is lost (4 corpus ids, and two such documents with the same IEEE half share a hash and a URN); and one `separator` serves every part, so `IEEE Std 7-4.3.2-2016` comes back as `7.4.3.2` (14 ids). A third: `SupplementIdentifier#to_hash` drops the delegated `publisher` only on a top-level wrapper, so for a non-IEEE supplement nested in an adoption (`IEEE Std 1234-2010 (ISO 1234/Amd 1:2001)`) `from_hash(to_hash)` is not idempotent and `parse_urn` refuses the emitted URN as not canonical (none in the corpus). Fixing any of the three changes `to_hash`. Separately, `IEC/IEEE P62582-6, FDIS May 2019` and `ISO/IEC/IEEE P21840, DIS-2019` raise `Parsanol::PARG::BindError` from `parse` — the parse-error contract expects `Pubid::Errors::ParseError`.

data/lib/pubid/ieee/pubid_urn_schema.rb

@@ -0,0 +1,150 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Ieee
+    # The pubid-scheme URN of IEEE (issue #656; docs/URN-SCHEMES.adoc).
+    #
+    #   IEEE Std 802.11-2016
+    #   urn:pubid:ieee:std:802:stage-Std:part-11:year-2016:f:0.sep-.
+    #
+    # The core is the document number. Every other value is an optional
+    # prefixed atom, in the order below: the shared vocabulary first (who,
+    # what, which part, when, which edition, which state), then the IEEE
+    # flags, then the identifiers an IEEE id nests.
+    #
+    # The wrappers that name their wrapped document something other than
+    # +base+ (+ieee_identifier+, +first_identifier+, +primary_identifier+ …)
+    # write it as a nested atom, not as a root-first chain node, so they do
+    # not share the slug prefix of that document. Renaming them to +base+
+    # would change #to_hash and needs a relaton-data-ieee re-crawl.
+    #
+    # The official urn:ieee:std: form (RFC 8069) stays on #to_urn.
+    PubidUrnSchema = Pubid::PubidUrn.define("ieee") do
+      # Who.
+      atom "publisher", "pub"
+      atom "publishers", "pubs", kind: :list
+      atom "lead_party", "lead"
+      atom "copublisher", "co", kind: :list
+      atom "copublishers.*.body", "copubs"
+      # What.
+      atom "prefix", "prefix"
+      atom "type", "type"
+      atom "variant", "variant"
+      # Which part.
+      atom "parts", "part", kind: :list
+      atom "part", "pt"
+      atom "subpart", "subpart"
+      # When.
+      atom "year", "year"
+      atom "month", "month"
+      atom "day", "day"
+      atom "date.year", "dateyear"
+      atom "date.month", "datemonth"
+      atom "date.day", "dateday"
+      atom "date.undated", "undated", kind: :bool
+      atom "date_info", "dateinfo"
+      atom "iec_year", "iecyear"
+      # Which edition or revision.
+      atom "edition", "ed"
+      atom "edition_month", "edmonth"
+      atom "revision", "rev"
+      atom "reaffirmed", "reaff"
+      # Which state.
+      atom "stage", "stage"
+      atom "stage_iteration", "iter"
+      atom "iso_stage", "isostage"
+      atom "ieee_draft", "ieeedraft"
+      atom "draft", "draft"
+      atom "draft_info", "draftinfo"
+      atom "draft_status", "draftstatus"
+      atom "typed_stage.abbr", "tsabbr", kind: :list
+      atom "typed_stage.stage_code", "tsstage"
+      atom "typed_stage.type_code", "tstype"
+      atom "typed_stage.iso_stage_equivalent", "tsiso"
+      atom "typed_stage.ieee_draft_equivalent", "tsieee"
+      atom "typed_stage.approval_status", "tsapproval"
+      atom "typed_stage.project_status", "tsproject", kind: :bool
+      # Which language and locality.
+      atom "languages.*.code", "lang"
+      atom "locality.value", "loc"
+      # IEEE flags and free-text designations.
+      atom "project_marker", "project", kind: :bool
+      atom "redline", "redline", kind: :bool
+      atom "interpretation", "interp", kind: :bool
+      atom "registered", "registered", kind: :bool
+      atom "abbr_suffix", "abbrsuffix", kind: :bool
+      atom "abbr_suffix_registered", "abbrsuffixreg", kind: :bool
+      atom "rev_bare", "revbare", kind: :bool
+      atom "space_before_draft", "spacedraft", kind: :bool
+      atom "month_glued", "monthglued", kind: :bool
+      atom "ashrae_number", "ashrae"
+      atom "ashrae_year", "ashraeyear"
+      atom "iso_identifier", "isoid"
+      atom "adoption", "adoption"
+      atom "amendment_to", "amendmentto"
+      atom "crossref", "crossref"
+      atom "nickname", "nick"
+      atom "note", "note"
+      atom "parenthetical_content", "paren"
+      atom "relationships.*.relationship_type", "rel"
+      # Identifiers an IEEE id nests.
+      atom "ieee_identifier", "ieeeid", kind: :id
+      atom "iec_identifier", "iecid", kind: :id
+      atom "first_identifier", "first", kind: :id
+      atom "second_identifier", "second", kind: :id
+      atom "primary_identifier", "primary", kind: :id
+      atom "secondary_identifier", "secondary", kind: :id
+      atom "parenthetical_identifier", "parenid", kind: :id
+      atom "adopted_identifiers", "adopted", kind: :ids
+      atom "revision_of", "revof", kind: :id
+      atom "supplement_to", "supto", kind: :id
+      atom "amendments", "amds", kind: :ids
+      atom "corrigenda", "cors", kind: :ids
+      atom "incorporates", "incl", kind: :ids
+      atom "supersedes", "supersedes", kind: :ids
+
+      # Spelling only.
+      facet "separator", "sep"
+      facet "separators.*", "seps"
+      facet "rev_sep", "revsep"
+      facet "year_sep", "yearsep"
+      facet "date_separator", "datesep"
+      facet "original_format", "format"
+      facet "languages.*.original_code", "langsrc"
+
+      type "pubid:ieee:standard", "std"
+      type "pubid:ieee:project-draft-identifier", "proj"
+      type "pubid:ieee:si-standard", "si"
+      type "pubid:ieee:redlined-standard", "redlined"
+      type "pubid:ieee:joint-development", "joint"
+      type "pubid:ieee:iec-ieee-copublished", "iecieee"
+      type "pubid:ieee:dual-identifier", "dual"
+      type "pubid:ieee:dual-published", "dualpub"
+      type "pubid:ieee:csa-dual-published", "csadual"
+      type "pubid:ieee:multi-numbered-identifier", "multi"
+      type "pubid:ieee:adopted-standard", "adopted"
+      type "pubid:ieee:parenthetical-identifier", "paren"
+
+      type "pubid:ieee:amendment", "amd"
+      type "pubid:ieee:corrigendum", "cor"
+      type "pubid:ieee:interpretation-identifier", "int"
+      type "pubid:ieee:conformance-identifier", "conf"
+      type "pubid:ieee:supplement-identifier", "sup"
+
+      type "pubid:ieee:aiee", "aiee"
+      type "pubid:ieee:ire", "ire"
+
+      type "pubid:ieee:nesc-standard", "nesc"
+      type "pubid:ieee:nesc-edition", "nescedition"
+      type "pubid:ieee:nesc-handbook", "nescbook"
+      type "pubid:ieee:nesc-draft", "nescdraft"
+      type "pubid:ieee:nesc-preprint", "nescpre"
+      type "pubid:ieee:nesc-redline", "nescredline"
+
+      # The base class. The builder makes one for a parenthetical inside a
+      # relationship, whose related ids #to_hash does not serialize today;
+      # declared so that one in any other slot still emits.
+      type "pubid:ieee:identifier", "id"
+    end
+  end
+end

data/lib/pubid/ieee.rb

@@ -18,6 +18,7 @@ module Pubid
     autoload :Ire, "#{__dir__}/ieee/ire"
     autoload :Nesc, "#{__dir__}/ieee/nesc"
     autoload :Parser, "#{__dir__}/ieee/parser"
+    autoload :PubidUrnSchema, "#{__dir__}/ieee/pubid_urn_schema"
     autoload :PreParser, "#{__dir__}/ieee/pre_parser"
     autoload :Compaction, "#{__dir__}/ieee/compaction"
     autoload :ProjectRenderer, "#{__dir__}/ieee/project_renderer"

data/lib/pubid/iso/pubid_urn_schema.rb

@@ -0,0 +1,61 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Iso
+    # The pubid-scheme URN of ISO (issue #656; docs/URN-SCHEMES.adoc).
+    #
+    #   ISO/IEC 13818-1:2015/Amd 3:2016
+    #   urn:pubid:iso:is:13818:co-IEC:part-1:year-2015:amd:3:co-IEC:year-2016
+    #
+    # The type tokens follow the RFC 5141 type codes where one exists. The
+    # core is the document number; every other value is an optional prefixed
+    # atom, in the order below. The official urn:iso:std: form stays on
+    # #to_urn (Pubid::Iso::UrnGenerator).
+    PubidUrnSchema = Pubid::PubidUrn.define("iso") do
+      atom "publisher", "pub"
+      atom "copublishers", "co", kind: :list
+      atom "part", "part"
+      atom "subpart", "subpart"
+      atom "year", "year"
+      atom "month", "month"
+      atom "day", "day"
+      atom "undated", "undated", kind: :bool
+      atom "edition.number", "ed"
+      atom "stage", "stage"
+      atom "stage_iteration", "iter"
+      atom "supplement_version", "v"
+      atom "languages.*.code", "lang"
+      atom "locality.value", "loc"
+
+      facet "languages.*.original_code", "langsrc"
+      facet "edition.original_text", "edsrc"
+
+      type "pubid:iso:international-standard", "is"
+      type "pubid:iso:technical-report", "tr"
+      type "pubid:iso:technical-specification", "ts"
+      type "pubid:iso:guide", "guide"
+      type "pubid:iso:pas", "pas"
+      type "pubid:iso:recommendation", "r"
+      type "pubid:iso:international-standardized-profile", "isp"
+      type "pubid:iso:international-workshop-agreement", "iwa"
+      type "pubid:iso:technology-trends-assessments", "tta"
+      type "pubid:iso:data", "data"
+      type "pubid:iso:tc-document", "tcdoc",
+           atoms: [%w[tc_type tctype], %w[tc_number tc],
+                   %w[sc_type sctype], %w[sc_number sc],
+                   %w[wg_type wgtype], %w[wg_number wg]]
+      type "pubid:iso:directives", "dir", atoms: [%w[subgroup subgroup]]
+      type "pubid:iso:directives-supplement", "dirsup"
+
+      type "pubid:iso:amendment", "amd"
+      type "pubid:iso:corrigendum", "cor"
+      type "pubid:iso:addendum", "add"
+      type "pubid:iso:extract", "ext"
+      type "pubid:iso:supplement", "sup"
+
+      type "pubid:iso:all-parts", "all", atoms: [["identifiers", "ids", :ids]]
+      type "pubid:iso:bundled-identifier", "bundle",
+           atoms: [["supplements", "sups", :ids]]
+    end
+  end
+end

data/lib/pubid/iso.rb

@@ -20,6 +20,7 @@ module Pubid
     autoload :Identifiers, "#{__dir__}/iso/identifiers"
     autoload :Normalizer, "#{__dir__}/iso/normalizer"
     autoload :Parser, "#{__dir__}/iso/parser"
+    autoload :PubidUrnSchema, "#{__dir__}/iso/pubid_urn_schema"
     autoload :RenderingStyle, "#{__dir__}/iso/rendering_style"
     autoload :SingleIdentifier, "#{__dir__}/iso/single_identifier"
     autoload :SupplementIdentifier, "#{__dir__}/iso/supplement_identifier"

data/lib/pubid/itu/CLAUDE.md

@@ -113,3 +113,18 @@ a replay of all 24,382 rows and every ITU pass fixture showed 0 changes.
   **Not done:** an RR supplement (`ITU-R RR (2020) Amd 1` fails; the
   base-less `ITU-R RR Amd 1` still builds an Amendment on series `RR`), and
   `ITU-R RR-E` is still a Recommendation numbered `E` — both as on `main`.
+
+## pubid-scheme URN (issue #656)
+
+`lib/pubid/itu/pubid_urn_schema.rb` covers all 17 types; design and rulings
+in `docs/URN-SCHEMES.adoc` (`[[urn-itu]]`). **A new rendering flag needs a
+place in that schema, or `#to_pubid_urn` raises for every id that sets it.**
+Declare it as a `:bool` *facet* when it is spelling only (the
+`number_glued`/`series_suffix_spaced` kind — "the same document") and as a
+`:bool` *atom* when it names a different document (`technical`,
+`attachment`, `series_word`). The facet/atom choice is what decides whether
+a slug without its `f` group keeps two ids apart. Not placed today:
+`combined.*.parts` (a list inside a list; no pass fixture has one).
+`imp_marker` (`G.Imp712`) and `common_text_twin` (`| ISO/IEC …`, an `:id`
+atom) are in no pass fixture either; the contract spec reads only `pass/`,
+so sweep `full/` and the spec literals as well after a schema change.