pubid 2.0.0.pre.alpha.40 → 2.0.0.pre.alpha.41

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c1e4c5a6889f61e535b4d05517aff5798eb5307c79bf7e318ab21822ebfe73ae
-  data.tar.gz: f129c70c4c9c646318c58e12d7a5e1097299c5698a083a0710e2866a2e7ad692
+  metadata.gz: 9b4cbb25ba50fae05ff215becf19f4edfe4b4cdea3d470e0ae1d7447d9e50c9d
+  data.tar.gz: 859a16d7d83590fc3a0ada0d7b0e78d631b3b923d7c85fbdc08bf1f170c78b98
 SHA512:
-  metadata.gz: d2e7e5cea5f0749a2aa5715521a2d6c192b43395bcb9f72470207629f6e7d1f0b9a7dbb089a1cc8e23c41a6ffc61a1e1424ce2546618249ed3eb074d611b3e4f
-  data.tar.gz: c4ee9f3166fa9caffb6f3b85d4684c11b6f08ac615ecf302af94831a9e7538a29264c2a862ffefa161fbeb4dbabc11b82405730c2435d5d666ab42c257fe2a61
+  metadata.gz: 7e6c74d29a9cb81d4e3cf829bfb707ce236e8e5f41af17cd5e6ac79ffe2712e7914c50c610be2f4ccb57534dc5ad3c1d087d71bb985500833780e01adf57b7b5
+  data.tar.gz: 3ded5e29bd316cdc19e52e380cc987446c2173c4d428e90084406aa224862e9c66df4c673d86b3f975d8bb6e60dabbb289896d8116ff4d95fc24bc6a8b967d46

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.40"
+  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.40
+  version: 2.0.0.pre.alpha.41
 platform: ruby
 authors:
 - Ribose Inc.