pubid 2.0.32 → 2.0.33

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cf1af3c60d0d620d92b5b8393d2c246628a8fc71c87484ad53a5d75335254644
-  data.tar.gz: 7da19312a43e892d150bc517dbc8dd9882174a3bae6e6284c10c5950b30b34f6
+  metadata.gz: 8aef45a3d166689b823ce4ab85ab8651e066838a49ddf5b7d23e40345c1a9e0c
+  data.tar.gz: 0d9e256b0cfcdb8ba4354b7e16836e1a0f236f14f5f682bce0850504e4af16ae
 SHA512:
-  metadata.gz: 8e7430bf08502334e07d742cbf529a2b2c9381d5f1f58dac93d70a822623cafe6f77caad2b3b2a17aafb7c18a8a55bf196dcf082cdd9024c82f722b0cbc014f2
-  data.tar.gz: e85be66ebca3178f9adc7514f477032e3551122de76c4e8055dc6b75e4cfbc684e61161ba9763eca454a36619dd75d98bdcf79e0cd06a30ac9b120de59e3305e
+  metadata.gz: 7cdbc8c5709b74a0a3298a56b79ea954a689a95f94868c2c3a0973ad5912c07581a03f797944caf5f62414ad71cb6c27f9a4b0243351b883962adc67a5b5b2ff
+  data.tar.gz: 00debefc3b8438a48a158c4a706817807f75e2489cc8a3f8ceb247ebd7598592aa4927c6a0942730db12dba5d7e9af0ae875d126f7d7a321732eb2d866e7388d

data/data/iso/update_codes.yaml

@@ -2,6 +2,11 @@ ISO/R 657/IV: ISO/R 657-4:1969
 ISO/IEC/IEEE 8802-22.2:2015/Amd.2:2017(E): ISO/IEC/IEEE 8802-22:2015/Amd.2:2017(E)
 ISO/TR 17716.2: ISO/TR 17716
 ISO/TR 17716.2(E): ISO/TR 17716(E)
+# Unassigned-part placeholder: ISO's open data writes `-_` where a
+# multipart project has no part number yet ("ISO/NP TS 6041-_", title
+# "… Part _: _No part"). It carries no identity, so drop it and leave the
+# part nil (relaton/relaton-data-iso#43).
+"/(\\d)-_(?=[\\s:\\/(]|$)/": '\1'
 # Long-form draft typed stages (DIS TR, FDIS PAS, ...) → canonical short
 # typed-stage abbrs (DTR, FDPAS, ...). DIS/FDIS are typed-stages of the
 # IS class only — for TR/TS/PAS/ISP they have dedicated D<type>/FD<type>

data/lib/pubid/iso/CLAUDE.md

@@ -207,3 +207,24 @@
     `spec/pubid/iso/ballot_face_decode_spec.rb` (all 13 SSOT anchors, the
     no-number rule, base-whole guards, Am alias, stored-twin agreement, and
     the website-face-vs-stored-face drift rows the SSOT §5 records).
+
+- **The unassigned-part placeholder `-_` is dropped before the parse
+  (relaton/relaton-data-iso#43).** ISO's open data
+  (`iso_deliverables_metadata.jsonl`) writes `-_` where a multipart project
+  has no part number yet — record 95616 is `ISO/NP TS 6041-_`, stage 10.20,
+  title "… Part _: _No part". The grammar's part body is word characters and
+  digits, so the id failed, and the relaton crawler left the file unindexed.
+  A `data/iso/update_codes.yaml` regex removes `-_` after a digit when a
+  separator (`:`, `/`, `(`, space) or the end follows, so the id parses as
+  `ISO/NP TS 6041` with a nil part. A nil part is the honest model (the part
+  is unknown), and `Pubid::Iso.parse` of the `-_` form (the call relaton's
+  crawler and lookup make) gives the same identifier as the index row. The
+  render is normalized, not byte-exact. No grammar or artifact change.
+  **Known gap:** the rule is ISO-only, and IEC's grammar accepts `_` as a
+  part, so `Pubid.parse("ISO 6041-_")` routes to IEC (an exact round trip
+  wins) with part `"_"`. The reported `ISO/NP TS 6041-_` still reaches ISO,
+  because IEC cannot read the NP stage. BSI and CSA delegate to ISO and get
+  the normalization. Over the whole open-data file (81,625
+  non-`Withdrawn` references, 2026-11-14) this was the only failure; the
+  `Withdrawn …` rows fail too, but the crawler skips them. Locked by
+  `spec/pubid/iso/update_codes_spec.rb`.

data/lib/pubid/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Pubid
-  VERSION = "2.0.32"
+  VERSION = "2.0.33"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pubid
 version: !ruby/object:Gem::Version
-  version: 2.0.32
+  version: 2.0.33
 platform: ruby
 authors:
 - Ribose Inc.