pubid 2.0.0.pre.alpha.39 → 2.0.0.pre.alpha.41

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e53b03c87c2a04f877d8eba11d5689984de9c0af641258c68c8c03377d762f12
-  data.tar.gz: 5bdad1686cf8cd3709ea1494eef8c78dd7c6974bae2802ccc669db939f788731
+  metadata.gz: 9b4cbb25ba50fae05ff215becf19f4edfe4b4cdea3d470e0ae1d7447d9e50c9d
+  data.tar.gz: 859a16d7d83590fc3a0ada0d7b0e78d631b3b923d7c85fbdc08bf1f170c78b98
 SHA512:
-  metadata.gz: 822faa7030a35d1e87901785b0d22bb0716c1b997985c6b9d616c1eb75f3e7fe3436ca61c427c4d8abd44d14fe2e173b7a8c5ab3bc26941bb68e75f308862965
-  data.tar.gz: e636567ecb22497f4cf0c0cafdfe68d06f83e593bc15483c168cbc25053a61221d6738ac16730f2bbe0e05c88ce6d91bb3166da7386ac1ca4004363fea390a5a
+  metadata.gz: 7e6c74d29a9cb81d4e3cf829bfb707ce236e8e5f41af17cd5e6ac79ffe2712e7914c50c610be2f4ccb57534dc5ad3c1d087d71bb985500833780e01adf57b7b5
+  data.tar.gz: 3ded5e29bd316cdc19e52e380cc987446c2173c4d428e90084406aa224862e9c66df4c673d86b3f975d8bb6e60dabbb289896d8116ff4d95fc24bc6a8b967d46

data/lib/pubid/ieee/builder.rb

@@ -1762,6 +1762,7 @@ module Pubid
         end
 
         # Check for specific draft notation (D1, D2, etc.)
+        draft_version_present = false
         if parsed[:draft]
           draft_data = parsed[:draft]
           if draft_data.is_a?(Array)
@@ -1769,8 +1770,12 @@ module Pubid
               r.merge(e)
             end
           end
+          # A verbatim draft designator ("/D2.1.1") is a version in itself;
+          # only an attribute-less date hash ("{month:, year:}") lacks one.
+          draft_version_present = true unless draft_data.is_a?(Hash)
 
           if draft_data.is_a?(Hash) && draft_data[:draft_version]
+            draft_version_present = true
             dv = draft_data[:draft_version]
             version = if dv.is_a?(Array)
                         dv.map do |v|
@@ -1781,6 +1786,21 @@ module Pubid
                       end
 
             if version
+              # A draft version that IS an ISO stage token ("/DCD1" and
+              # "/CD1" both capture version "CD1") takes that stage on a
+              # PLAIN IEEE document: the stage token outranks the ordinal
+              # ladder (docs/IEEE-DRAFT-STAGES.md §1.3, "DDIS" = DIS), so
+              # the render drops the Draft word. A joint ISO-led
+              # stage-word draft keeps its generic project stage — its
+              # publishers block composes the same face through the
+              # typed-stage project branch.
+              copubs = parsed[:publishers].is_a?(Hash) ? parsed[:publishers][:copublishers] : nil
+              joint = copubs && !(copubs.respond_to?(:empty?) ? copubs.empty? : copubs.nil?)
+              if !joint &&
+                  (m = version.to_s.match(/\A(FDIS|FCD|CDV|DIS|CD|WD|PWI|NP)\d*\z/))
+                return m[1]
+              end
+
               # relaton's hyphenated "/D-2" spelling captures the dash inside
               # draft_version; the stage registry keys on "D2". A date-embedded
               # version ("3-2017-07") keys on its leading ordinal.
@@ -1802,13 +1822,17 @@ module Pubid
             return "P"
           elsif type_value == "Std"
             return "Std"
-          elsif type_value == "Draft Std" && parsed[:draft].nil? && parsed[:digit_draft].nil?
+          elsif type_value == "Draft Std" && !draft_version_present && parsed[:digit_draft].nil?
             # A version-less "Draft Std" fabricates /D1 (issue #205);
             # deriving the stage from that fabricated version renders the
             # same P-prefixed form as an explicit "/D1" spelling, so the
             # render reaches its fixed point in one round (pubid#318).
-            # Gated on no-draft: a dotted version ("D2.0") fails the registry
-            # lookup above and must fall through, keeping "Draft Std".
+            # Gated on no captured VERSION: a dotted version ("D2.0")
+            # fails the registry lookup above and must fall through,
+            # keeping "Draft Std". A draft-version-less tree that carries
+            # only a date ("IEEE Draft Std P754/D1.2.6 Nov 2006") takes
+            # the same fabricated D1, the version the render already
+            # implies.
             return "D1"
           elsif type_value.match?(/^No\.?$/)
             return type_value

data/lib/pubid/nist/CLAUDE.md

@@ -54,3 +54,21 @@ Read this before you change `lib/pubid/nist/` or `spec/pubid/nist/`. The root
   `update`/`update_component` and cleared to `nil` before the object is
   returned. Neither carries live information `edition`/`update` doesn't
   already cover. Locked by `spec/pubid/all_parts_edition_keys_audit_spec.rb`.
+
+- **The URN parser must rebuild the human face the generator started from,
+  field for field.** `UrnGenerator` dot-joins identity fields after the
+  number (`urn:nist:sp:304.e2017.A.supp`), and `UrnParser#parse_payload`
+  splits them back: the edition/volume/revision glue onto the number, a
+  single capital-letter token is a **part** glued to the code
+  (`304A`), an edition's additional text keeps its dot (`13e2.June1908` —
+  the token after `eN`), `insert`/`errata`/`add` markers glue verbatim,
+  the bare `.supp` is supplementability (non-identity) and a valued
+  `.supp-<v>` is `sup<v>`. The rebuild is only correct if the flavor's own
+  grammar accepts it, so every branch is measured against the corpus —
+  before this, the five rows with a part letter, an edition additional
+  text, or an addendum marker failed to re-parse and the reference's own
+  `parse_urn` raised on its own output. The ts mirror must reproduce
+  Ruby's `String#split` behaviour and drop **trailing** empty fields
+  (`"800-38.A.supp.add."` splits with a trailing `""` in JS but not in
+  Ruby; keeping it appends a stray `.`). Locked by
+  `spec/pubid/nist/urn_parser_spec.rb`.

data/lib/pubid/nist/urn_parser.rb

@@ -40,10 +40,10 @@ module Pubid
         parts = split_parts(body)
 
         type_token, payload = parts
-        code, revision = parse_payload(payload)
+        code, suffix = parse_payload(payload)
 
         text = "#{publisher_for(type_token)} #{type_label(type_token)} #{code}"
-        text += revision if revision
+        text += suffix
         flavor_parse(text)
       end
 
@@ -58,14 +58,42 @@ module Pubid
         NBS_SERIES.include?(type_token.downcase) ? "NBS" : "NIST"
       end
 
+      # The generator dot-joins the identity's fields after the number
+      # ("urn:nist:circ:25.e1924.supp", "urn:nist:circ:539.v10.supp",
+      # "urn:nist:circ:24.supp-1"). Reassemble the human spelling the
+      # flavor parser reads: the edition and volume glue onto the number,
+      # a revision glues after them, the bare ".supp" marks
+      # supplementability (non-identity) and a valued ".supp-<v>" is the
+      # supplement's "sup<v>" face.
       def parse_payload(payload)
-        # Strip the trailing ".supp" supplement marker.
-        stripped = payload.sub(/\.supp\z/, "")
-        # Split revision suffix from code (e.g., "800-53.r5" → ["800-53", "r5"]).
-        match = stripped.match(/^(.*)\.(r\d+)$/i)
-        return [stripped, nil] unless match
+        tokens = payload.split(".")
+        code = tokens.shift.to_s
+        suffix = +""
+        part = nil
+        edition = nil
+        volume = nil
+        revision = nil
+        supplement = nil
 
-        [match[1], match[2]]
+        tokens.each do |token|
+          case token
+          when /\Ar\d+\z/i then revision = token
+          when /\Ae[\w]+\z/i then edition = token
+          when /\Av\d+\z/i then volume = token
+          when /\Asupp-(.+)\z/im then supplement = Regexp.last_match(1)
+          when "supp" then next # supplementability marker, not identity
+          when "insert", "errata" then suffix << token # glued in the human
+          when /\A[A-Z]\z/ then part = token # part letter, glued to the code
+          when /\A[A-Z][a-z]+\d{4}\z/ # edition's additional text ("13e2.June1908")
+            edition = "#{edition}.#{token}" if edition
+          else suffix << ".#{token}" # unknown marker: keep verbatim
+          end
+        end
+
+        code << part.to_s
+        suffix << edition.to_s << volume.to_s << revision.to_s
+        suffix << "sup#{supplement}" if supplement
+        [code, suffix]
       end
 
       def type_label(token)

data/lib/pubid/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Pubid
-  VERSION = "2.0.0.pre.alpha.39"
+  VERSION = "2.0.0.pre.alpha.41"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pubid
 version: !ruby/object:Gem::Version
-  version: 2.0.0.pre.alpha.39
+  version: 2.0.0.pre.alpha.41
 platform: ruby
 authors:
 - Ribose Inc.