pubid 2.0.20 → 2.0.22

data/data/parg/iso.parg

@@ -11,6 +11,20 @@
 # below, whose captures carry the idf_ prefix so they never collide
 # with the ISO ones and can bind as scalars.
 #
+# Historic TYPE-first ballot faces (decode-to-modern, owner ruling
+# 2026-11-12): the DAM-family token in TYPE position — "ISO/IEC FDAM 1
+# 14496-12:2004", "ISO/PDAM 19973-2" — and the space-attached ballot
+# face "ISO 15877-5:2009 FDAM 1". Both branches sit LAST in the
+# identifier alternation, so they are purely additive: every face an
+# earlier branch parses keeps its exact parse. The ballot token
+# captures as ballot_type_with_stage; a number on the TYPE token is
+# space-bounded (ballot_number) so "PDAM 19973-2" keeps 19973 in the
+# base; an on-base stamp's number/date capture as ballot_stamp_* (the
+# stamp token itself matches uncaptured — the ballot's stage comes
+# from the TYPE token and the decode keeps no spelling). The builder
+# folds the captures into ONE amendment layer over the whole base, the
+# number taken from the TYPE token, the stamp, or the implied 1.
+#
 # Edition 2 with typed model bindings: every capture the builder
 # consumes is bound. Supplement layers capture into position-scoped
 # names (supp_* on the first supplement, supp2_* on the second,
@@ -23,7 +37,7 @@
 
 use idf
 
-grammar PubidIso version "0.4.0" edition 2 {
+grammar PubidIso version "0.5.0" edition 2 {
 
   # ---- lexical (pubid/parser/common_parse_rules.rb + ISO override) ----
   digit = %x30-39
@@ -47,6 +61,7 @@ grammar PubidIso version "0.4.0" edition 2 {
   # inline the alt so the capture holds one scalar span) ----
   typed_stage_abbrev = alt from_table "typed_stages" column "abbr"
   supp_stage_abbrev = alt from_table "typed_stages_supplements" column "abbr"
+  ballot_stage_abbrev = alt from_table "typed_stages_ballots" column "abbr"
   directives_stage_abbrev = alt from_table "directives_typed_stages" column "abbr"
   directives_supp_stage_abbrev = alt from_table "directives_supplements_typed_stages" column "abbr"
   idf_stage_abbrev = alt from_table "idf_typed_stages" column "abbr"
@@ -395,6 +410,76 @@ grammar PubidIso version "0.4.0" edition 2 {
     )
   }
 
+  # ---- historic TYPE-first ballot faces (decode-to-modern) ----
+  ## The DAM-family ballot token in TYPE position. Captured under its
+  ## own name: the supplement tables' captures stay reserved for the
+  ## on-base layers, and the ballot's stage is the one the decode keeps.
+  ballot_type_with_stage = {
+    (
+      (alt from_table "typed_stages_ballots" column "abbr")
+    ) as ballot_type_with_stage
+  }
+  ## An on-base stamp riding a ballot face ("/Amd 9:2001", "/Amd.1",
+  ## "/Am1:2006"): it carries the amendment's number and ballot date
+  ## while its own token letters are decode-away (matched uncaptured —
+  ## the ballot's stage comes from the TYPE token). Mirrors the three
+  ## supplement tails: a (glued or spaced) number with an optional
+  ## date, or a dot number.
+  ballot_stamp = {
+    slash supp_stage_abbrev
+    (
+      (
+        [space]
+        ((1*5digit)) as ballot_stamp_number
+        [
+          [space]
+          (
+            (colon / dash) [
+              (("19" / "20") 2*digit !digit [(dash 2*digit)] [(dash 2*digit)]) as ballot_stamp_date
+              / (("--" / "—")) as ballot_stamp_undated_marker
+            ]
+          )
+        ]
+      )
+      / ( dot (1*digit) as ballot_stamp_dot_number )
+    )
+  }
+  ## "ISO/IEC FDAM 1 14496-12:2004", "ISO/PDAM 19973-2": the ballot
+  ## token first, then the base kept whole. The TYPE-token number is
+  ## space-bounded on both sides — mandatory trailing space — so
+  ## "PDAM 19973-2" cannot read 19973 as the ballot number: with no
+  ## second space the group backtracks and 19973 parses in second_part.
+  ballot_supplement_identifier = {
+    prefix_with_copublishers
+    [space]
+    [slash]
+    ballot_type_with_stage
+    [ space ((1*digit)) as ballot_number space ]
+    [space]
+    [type_with_stage]
+    [space]
+    second_part
+    [ ballot_stamp ]
+  }
+  ## The space-attached ballot face: "ISO 15877-5:2009 FDAM 1" — the
+  ## base designation first, then the ballot token attached by a space.
+  ## The base front is inlined (not supplement_base_no_third): that
+  ## rule ends in base_third_part_edition, whose own optional space
+  ## would consume the separator the ballot token needs. No base
+  ## edition is served here — none of the stored or owner-cited ballot
+  ## faces carries one.
+  ballot_space_supplement_identifier = {
+    [ (("Guide" / "GUIDE") as type_with_stage_fr) space ]
+    [prefix_with_copublishers]
+    [space]
+    [slash]
+    [type_with_stage]
+    [space]
+    second_part
+    space ballot_type_with_stage
+    [ space ((1*digit)) as ballot_number ]
+  }
+
   # ---- directives: "ISO/IEC DIR 1", "ISO/IEC JTC 1 DIR", supplements,
   # bundled "ISO/IEC DIR 1:2022 + IEC SUP:2022" ----
   directives_publisher_subgroup = ("JTC 1") as subgroup
@@ -609,7 +694,8 @@ grammar PubidIso version "0.4.0" edition 2 {
   }
 
   ## The ISO identifier root: common-text twin form first, then the
-  ## single spine.
+  ## single spine. The historic ballot faces go last — purely additive
+  ## branches (an input an earlier member parses keeps that parse).
   identifier = {
       bare_tc_document
     / nsb_iso_identifier
@@ -623,6 +709,8 @@ grammar PubidIso version "0.4.0" edition 2 {
     / supplement_identifier
     / joint_identifier
     / identifier_copublishers
+    / ballot_space_supplement_identifier
+    / ballot_supplement_identifier
   }
 
   entry identifier: identifier
@@ -712,6 +800,12 @@ bs3_undated_marker -> bs3_undated_marker (string)
     idf_supp_stage_iteration2 -> idf_supp_stage_iteration2 (string)
     idf_supp_date2 -> idf_supp_date2 (string)
     idf_supp_undated_marker -> idf_supp_undated_marker (string)
+    ballot_type_with_stage -> ballot_type_with_stage (string)
+    ballot_number -> ballot_number (string)
+    ballot_stamp_number -> ballot_stamp_number (string)
+    ballot_stamp_dot_number -> ballot_stamp_dot_number (string)
+    ballot_stamp_date -> ballot_stamp_date (string)
+    ballot_stamp_undated_marker -> ballot_stamp_undated_marker (string)
   }
 
   ## In-file grammar tests: run at compile time, embedded in the artifact,
@@ -728,9 +822,55 @@ bs3_undated_marker -> bs3_undated_marker (string)
     accept "ISO 5537|IDF 26"
     accept "ISO 4055/Amd 1:2021"
     accept "ISO/R 9:1962"
+    accept "ISO/IEC FDAM 1 14496-12:2004"
+    accept "ISO/PDAM 19973-2"
+    accept "ISO/IEC FPDAM 9075/1"
+    accept "ISO/IEC FPDAM 10373-6/Amd 9:2001"
+    accept "ISO/PDAM 19110:2005/Amd.1"
+    accept "ISO/IEC PDAM TR 9573-11/Amd.1"
+    accept "ISO/IEC PDAM 9541-1/Amd.4"
+    accept "ISO/IEC PDAM 2 10646:2012"
+    accept "ISO 15877-5:2009 FDAM 1"
+    accept "ISO 19776-2:2005/Am1:2006"
     reject "nonsense"
+    reject "ISO/PDAM"
+    reject "ISO/FDAM"
     example "ISO/IEC WD TS 25025" { publisher: "ISO" }
     example "JCGM 200:2008(F)" { publisher: "JCGM" }
+    example "ISO/IEC FDAM 1 14496-12:2004" {
+      ballot_type_with_stage: "FDAM"
+      ballot_number: "1"
+      number_with_part: "14496-12"
+      date: "2004"
+    }
+    example "ISO/PDAM 19973-2" {
+      ballot_type_with_stage: "PDAM"
+      number_with_part: "19973-2"
+    }
+    example "ISO/IEC FPDAM 10373-6/Amd 9:2001" {
+      ballot_type_with_stage: "FPDAM"
+      ballot_stamp_number: "9"
+      ballot_stamp_date: "2001"
+    }
+    example "ISO/PDAM 19110:2005/Amd.1" {
+      ballot_type_with_stage: "PDAM"
+      ballot_stamp_number: "1"
+    }
+    example "ISO/IEC FPDAM 9075/1" {
+      ballot_type_with_stage: "FPDAM"
+      number_with_part: "9075/1"
+    }
+    example "ISO 15877-5:2009 FDAM 1" {
+      ballot_type_with_stage: "FDAM"
+      ballot_number: "1"
+      number_with_part: "15877-5"
+      date: "2009"
+    }
+    example "ISO/IEC FDAM 19776-2:2005/Am1:2006" {
+      ballot_type_with_stage: "FDAM"
+      ballot_stamp_number: "1"
+      ballot_stamp_date: "2006"
+    }
   }
 }
 

data/data/parg/plateau.json

@@ -1 +1 @@
-{"bindings":null,"version":"0.1.0","grammar":"PubidPlateau","shape":"parsanol-tree/v2","binding_version":1,"entries":{"identifier":{"root":"identifier","grammar":{"atoms":[{"Entity":{"atom":69}},{"Entity":{"atom":49}},{"Str":{"pattern":"PLATEAU"}},{"Str":{"pattern":" "}},{"Entity":{"atom":8}},{"Str":{"pattern":"Handbook"}},{"Str":{"pattern":"Technical Report"}},{"Alternative":{"atoms":[5,6]}},{"Named":{"name":"type","atom":7}},{"Str":{"pattern":" "}},{"Entity":{"atom":15}},{"Str":{"pattern":"#"}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":12,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"number","atom":13}},{"Sequence":{"atoms":[11,14]}},{"Entity":{"atom":23}},{"Str":{"pattern":"-"}},{"Str":{"pattern":"_"}},{"Alternative":{"atoms":[17,18]}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":20,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"annex","atom":21}},{"Sequence":{"atoms":[19,22]}},{"Repetition":{"atom":16,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":47}},{"Str":{"pattern":" "}},{"Entity":{"atom":37}},{"Str":{"pattern":"第"}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":29,"min":1,"max":null,"tag":"Repetition"}},{"Str":{"pattern":"."}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":32,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[30,31,33]}},{"Named":{"name":"edition","atom":34}},{"Str":{"pattern":"版"}},{"Sequence":{"atoms":[28,35,36]}},{"Entity":{"atom":45}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":39,"min":1,"max":null,"tag":"Repetition"}},{"Str":{"pattern":"."}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":42,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[40,41,43]}},{"Named":{"name":"edition","atom":44}},{"Alternative":{"atoms":[27,38]}},{"Sequence":{"atoms":[26,46]}},{"Repetition":{"atom":25,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[2,3,4,9,10,24,48]}},{"Entity":{"atom":58}},{"Str":{"pattern":"PLATEAU"}},{"Str":{"pattern":" "}},{"Entity":{"atom":8}},{"Str":{"pattern":" "}},{"Entity":{"atom":15}},{"Entity":{"atom":23}},{"Repetition":{"atom":56,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[51,52,53,54,55,57]}},{"Alternative":{"atoms":[1,50]}},{"Named":{"name":"base","atom":59}},{"Entity":{"atom":68}},{"Str":{"pattern":" "}},{"Str":{"pattern":"Annex"}},{"Str":{"pattern":" "}},{"Entity":{"atom":67}},{"Re":{"pattern":"[\\x41-\\x5a]"}},{"Named":{"name":"annex_letter","atom":66}},{"Sequence":{"atoms":[62,63,64,65]}},{"Sequence":{"atoms":[60,61]}},{"Entity":{"atom":49}},{"Entity":{"atom":58}},{"Alternative":{"atoms":[0,70,71]}}],"root":72},"bindings":[{"capture":"base","path":"base","type":"raw","card":null,"preprocess":null},{"capture":"type","path":"type","type":"string","card":null,"preprocess":null},{"capture":"number","path":"number","type":"string","card":null,"preprocess":null},{"capture":"annex","path":"annex","type":"string","card":null,"preprocess":null},{"capture":"edition","path":"edition","type":"string","card":null,"preprocess":null},{"capture":"annex_letter","path":"annex_letter","type":"string","card":null,"preprocess":null}]}},"preprocess":{},"tables":{},"lint":{"order_warnings":["rule identifier: branches 1 and 2 are order-dependent (shared first bytes; ordered choice is decisive)","rule identifier: branches 1 and 3 are order-dependent (shared first bytes; ordered choice is decisive)","rule identifier: branches 2 and 3 are order-dependent (shared first bytes; ordered choice is decisive)"]},"default_entry":"identifier","render":{},"derive":{},"tests":[{"entry":"identifier","kind":"accept","input":"PLATEAU Handbook #3","expect":{}},{"entry":"identifier","kind":"accept","input":"PLATEAU Technical Report #1","expect":{}},{"entry":"identifier","kind":"reject","input":"nonsense","expect":{}}],"docs":{},"source":"# Port of lib/pubid/plateau/parser.rb: PLATEAU Handbook/Technical Report\n# #NN[-annex][ edition], plus Annex supplements. Japanese canonical\n# edition (第X.Y版) and legacy Latin X.Y both capture the same atom.\n#\n# Edition 2: every reference inside a captured body is inlined to raw\n# terms (a rule reference materializes as a named node in the edition-2\n# tree, so only a raw capture binds a scalar span). The base wrapper\n# keeps the v1 tree shape and the bindings name the scalar leaves.\n\ngrammar PubidPlateau version \"0.1.0\" edition 2 {\n  doc_type = (\"Handbook\" / \"Technical Report\") as type\n  number = \"#\" (1*%x30-39) as number\n  annex = (\"-\" / \"_\") (1*%x30-39) as annex\n  edition_part = \"第\" (1*%x30-39 \".\" 1*%x30-39) as edition \"版\"\n  edition_latin = (1*%x30-39 \".\" 1*%x30-39) as edition\n  edition = \" \" (edition_part / edition_latin)\n  annex_letter = (%x41-5A) as annex_letter\n  annex_supplement = \" \" \"Annex\" \" \" annex_letter\n  handbook = \"PLATEAU\" \" \" doc_type \" \" number [annex] [edition]\n  technical_report = \"PLATEAU\" \" \" doc_type \" \" number [annex]\n  annex_identifier = (handbook / technical_report) as base annex_supplement\n  identifier = annex_identifier / handbook / technical_report\n\n  entry identifier: identifier\n\n  test {\n    accept \"PLATEAU Handbook #3\"\n    accept \"PLATEAU Technical Report #1\"\n    reject \"nonsense\"\n  }\n\n  bindings identifier {\n    # The builder dispatches on base && annex_letter and RE-parses the base\n    # subtree recursively (build_annex calls build(parsed[:base])), so base\n    # binds uncast — the nested {type, number, annex, edition} hash.\n    base -> base (raw)\n    type -> type (string)\n    number -> number (string)\n    annex -> annex (string)\n    edition -> edition (string)\n    annex_letter -> annex_letter (string)\n  }\n}\n","source_hash":"c794ad3672c17b5cacdfa398ef912bc11fa61559a5dec42e38e83f85ea5a03ae","unicode_tables":"onigmo (Ruby 3.4.8)","compiler_version":"1.3.114","edition":2,"checksum":"sha256:18c528e9b4808183ec56567581aedff00d4e275644fe861b9db4a2dd2dbac3e8"}
+{"bindings":null,"version":"0.1.0","grammar":"PubidPlateau","shape":"parsanol-tree/v2","binding_version":1,"entries":{"identifier":{"root":"identifier","grammar":{"atoms":[{"Entity":{"atom":87}},{"Entity":{"atom":67}},{"Str":{"pattern":"PLATEAU"}},{"Str":{"pattern":" "}},{"Entity":{"atom":8}},{"Str":{"pattern":"Handbook"}},{"Str":{"pattern":"Technical Report"}},{"Alternative":{"atoms":[5,6]}},{"Named":{"name":"type","atom":7}},{"Str":{"pattern":" "}},{"Entity":{"atom":15}},{"Str":{"pattern":"#"}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":12,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"number","atom":13}},{"Sequence":{"atoms":[11,14]}},{"Entity":{"atom":23}},{"Str":{"pattern":"-"}},{"Str":{"pattern":"_"}},{"Alternative":{"atoms":[17,18]}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":20,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"annex","atom":21}},{"Sequence":{"atoms":[19,22]}},{"Repetition":{"atom":16,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":47}},{"Str":{"pattern":" "}},{"Entity":{"atom":37}},{"Str":{"pattern":"第"}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":29,"min":1,"max":null,"tag":"Repetition"}},{"Str":{"pattern":"."}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":32,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[30,31,33]}},{"Named":{"name":"edition","atom":34}},{"Str":{"pattern":"版"}},{"Sequence":{"atoms":[28,35,36]}},{"Entity":{"atom":45}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":39,"min":1,"max":null,"tag":"Repetition"}},{"Str":{"pattern":"."}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":42,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[40,41,43]}},{"Named":{"name":"edition","atom":44}},{"Alternative":{"atoms":[27,38]}},{"Sequence":{"atoms":[26,46]}},{"Entity":{"atom":63}},{"Entity":{"atom":52}},{"Str":{"pattern":" "}},{"Re":{"pattern":"[\\u3000]"}},{"Alternative":{"atoms":[50,51]}},{"Named":{"name":"volume_sep","atom":49}},{"Str":{"pattern":"本編"}},{"Str":{"pattern":"＋"}},{"Str":{"pattern":"+"}},{"Alternative":{"atoms":[55,56]}},{"Str":{"pattern":"付録"}},{"Sequence":{"atoms":[57,58]}},{"Repetition":{"atom":59,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[54,60]}},{"Named":{"name":"volume","atom":61}},{"Sequence":{"atoms":[53,62]}},{"Repetition":{"atom":48,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[25,64]}},{"Repetition":{"atom":65,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[2,3,4,9,10,24,66]}},{"Entity":{"atom":76}},{"Str":{"pattern":"PLATEAU"}},{"Str":{"pattern":" "}},{"Entity":{"atom":8}},{"Str":{"pattern":" "}},{"Entity":{"atom":15}},{"Entity":{"atom":23}},{"Repetition":{"atom":74,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[69,70,71,72,73,75]}},{"Alternative":{"atoms":[1,68]}},{"Named":{"name":"base","atom":77}},{"Entity":{"atom":86}},{"Str":{"pattern":" "}},{"Str":{"pattern":"Annex"}},{"Str":{"pattern":" "}},{"Entity":{"atom":85}},{"Re":{"pattern":"[\\x41-\\x5a]"}},{"Named":{"name":"annex_letter","atom":84}},{"Sequence":{"atoms":[80,81,82,83]}},{"Sequence":{"atoms":[78,79]}},{"Entity":{"atom":67}},{"Entity":{"atom":76}},{"Alternative":{"atoms":[0,88,89]}}],"root":90},"bindings":[{"capture":"base","path":"base","type":"raw","card":null,"preprocess":null},{"capture":"type","path":"type","type":"string","card":null,"preprocess":null},{"capture":"number","path":"number","type":"string","card":null,"preprocess":null},{"capture":"annex","path":"annex","type":"string","card":null,"preprocess":null},{"capture":"edition","path":"edition","type":"string","card":null,"preprocess":null},{"capture":"volume","path":"volume","type":"string","card":null,"preprocess":null},{"capture":"annex_letter","path":"annex_letter","type":"string","card":null,"preprocess":null}]}},"preprocess":{},"tables":{},"lint":{"order_warnings":["rule identifier: branches 1 and 2 are order-dependent (shared first bytes; ordered choice is decisive)","rule identifier: branches 1 and 3 are order-dependent (shared first bytes; ordered choice is decisive)","rule identifier: branches 2 and 3 are order-dependent (shared first bytes; ordered choice is decisive)"]},"default_entry":"identifier","render":{},"derive":{},"tests":[{"entry":"identifier","kind":"accept","input":"PLATEAU Handbook #3","expect":{}},{"entry":"identifier","kind":"accept","input":"PLATEAU Technical Report #1","expect":{}},{"entry":"identifier","kind":"accept","input":"PLATEAU Handbook #00 第5.0版 本編","expect":{}},{"entry":"identifier","kind":"accept","input":"PLATEAU Handbook #00 第5.0版　本編＋付録","expect":{}},{"entry":"identifier","kind":"accept","input":"PLATEAU Handbook #00 第5.0版 本編+付録","expect":{}},{"entry":"identifier","kind":"reject","input":"nonsense","expect":{}}],"docs":{},"source":"# Port of lib/pubid/plateau/parser.rb: PLATEAU Handbook/Technical Report\n# #NN[-annex][ edition], plus Annex supplements. Japanese canonical\n# edition (第X.Y版) and legacy Latin X.Y both capture the same atom.\n#\n# Edition 2: every reference inside a captured body is inlined to raw\n# terms (a rule reference materializes as a named node in the edition-2\n# tree, so only a raw capture binds a scalar span). The base wrapper\n# keeps the v1 tree shape and the bindings name the scalar leaves.\n\ngrammar PubidPlateau version \"0.1.0\" edition 2 {\n  doc_type = (\"Handbook\" / \"Technical Report\") as type\n  number = \"#\" (1*%x30-39) as number\n  annex = (\"-\" / \"_\") (1*%x30-39) as annex\n  edition_part = \"第\" (1*%x30-39 \".\" 1*%x30-39) as edition \"版\"\n  edition_latin = (1*%x30-39 \".\" 1*%x30-39) as edition\n  edition = \" \" (edition_part / edition_latin)\n  # MLIT's volume label after the edition: 本編 (main volume) or 本編＋付録\n  # (main volume with appendix). ASCII or full-width (U+3000) space; ASCII\n  # \"+\" or full-width \"＋\" (U+FF0B), which the builder normalizes to \"＋\".\n  volume_sep = \" \" / %x3000\n  volume = volume_sep (\"本編\" [(\"＋\" / \"+\") \"付録\"]) as volume\n  annex_letter = (%x41-5A) as annex_letter\n  annex_supplement = \" \" \"Annex\" \" \" annex_letter\n  handbook = \"PLATEAU\" \" \" doc_type \" \" number [annex] [edition [volume]]\n  technical_report = \"PLATEAU\" \" \" doc_type \" \" number [annex]\n  annex_identifier = (handbook / technical_report) as base annex_supplement\n  identifier = annex_identifier / handbook / technical_report\n\n  entry identifier: identifier\n\n  test {\n    accept \"PLATEAU Handbook #3\"\n    accept \"PLATEAU Technical Report #1\"\n    accept \"PLATEAU Handbook #00 第5.0版 本編\"\n    accept \"PLATEAU Handbook #00 第5.0版　本編＋付録\"\n    accept \"PLATEAU Handbook #00 第5.0版 本編+付録\"\n    reject \"nonsense\"\n  }\n\n  bindings identifier {\n    # The builder dispatches on base && annex_letter and RE-parses the base\n    # subtree recursively (build_annex calls build(parsed[:base])), so base\n    # binds uncast — the nested {type, number, annex, edition} hash.\n    base -> base (raw)\n    type -> type (string)\n    number -> number (string)\n    annex -> annex (string)\n    edition -> edition (string)\n    volume -> volume (string)\n    annex_letter -> annex_letter (string)\n  }\n}\n","source_hash":"f5a43fb4d638687462490f2b05b635501ac21375c917b10e28f2cad554985476","unicode_tables":"onigmo (Ruby 3.4.10)","compiler_version":"1.3.114","edition":2,"checksum":"sha256:e876e3871cd842ded4df7a9ad906a428fbf11ab466631f489f555dd9508bef8a"}

data/data/parg/tables/iec_typed_stages.yaml

@@ -4,8 +4,10 @@
 - abbr: "ANW Amd"
 - abbr: "WD Amd"
 - abbr: "CDAM"
+- abbr: "PDAM"
 - abbr: "DAM"
 - abbr: "FDAM"
+- abbr: "FPDAM"
 - abbr: "PRF Amd"
 - abbr: "Amd"
 - abbr: "AMD"
@@ -14,6 +16,7 @@
 - abbr: "ANW Cor"
 - abbr: "WDCor"
 - abbr: "CDCor"
+- abbr: "CDCOR"
 - abbr: "DCOR"
 - abbr: "FDCOR"
 - abbr: "PRF Cor"

data/data/parg/tables/typed_stages_ballots.yaml

@@ -0,0 +1,6 @@
+- abbr: "PDAM"
+- abbr: "DAM"
+- abbr: "DAmd"
+- abbr: "FDAM"
+- abbr: "FDAmd"
+- abbr: "FPDAM"

data/data/parg/tables/typed_stages_supplements.yaml

@@ -44,6 +44,7 @@
 - abbr: "Amd"
 - abbr: "AMD"
 - abbr: "Amd."
+- abbr: "Am"
 - abbr: "PWI Cor"
 - abbr: "NP Cor"
 - abbr: "AWI Cor"

data/lib/pubid/bipm/CLAUDE.md

@@ -12,7 +12,12 @@ These notes were part of the root `CLAUDE.md`. Read them before you change `lib/
 
 - **Routing reaches BIPM (`Pubid.parse`, pubid#644)**: the note above says "`Pubid.parse` auto-routing does not resolve **any** BIPM form today … so `PREFIXES` was left alone" — that is no longer true, in two halves. **(1) `PREFIXES` gained the two SI-family series tokens** `SI Brochure` and `SI MEP`: both lead real printed references on their own (`SI Brochure 9e v3.01 (2019/2024, E)` — the spelling relaton's `Bibliography#search` strips the `BIPM ` off, per the note above — and `SI MEP 10`), and before this both parsed **directly** but the router could not route them (no prefix owner ⇒ no non-exact fallback). "Rapport" stays excluded per the ambiguous-token policy (generic French word). **(2) The quoted-title form** `BIPM "The International System of Units"` — the brochure IS titled that — is mapped onto the parseable `BIPM SI Brochure` section form by **`data/bipm/update_codes.yaml`** (the CIPM-MRA precedent), so it parses as a **partial reference** that wildcards every edition, exactly like `SI Brochure Part 1`; the bare `"The International System of Units"` maps to `SI Brochure`. Both are normalizing parses and live with the loose-forms expectations, never in the byte-exact fixtures. The **French title is deliberately not mapped**: it names the F-language record specifically, and mapping it would silently drop typed language information (the loose-forms rule above). Also note the router's prefix-owner mechanism is what makes the normalizing parses routable: `Pubid::Bipm.parse("BIPM SI Brochure")` happens to round-trip exactly, but `SI Brochure 9e …` renders with the leading `BIPM ` the input lacked — without prefix-owner status the router would reject it. (hand-off: router-printed-forms-644.)
 
-- **Corpus-cited forms + guide printings (pubid#657)**: the metanorma-bipm fetch queue cites two spellings the grammar rejected, and the 2026-11 guide update adds printings of its own. All are **parse-in forms over the existing canonical identities** — the canonical render follows the guide, nothing that already parsed changed. **(1) The em-dash meeting variant** `CGPM -- Meeting 1 (1889)`: `meeting_en` gained `<group> -- Meeting <n>` and `<group> -- <n><ord> Meeting` branches (the corpus cites only the first; the second is the same reordering over the other word order). They build through the existing `Meeting` path, so the canonical render is `CGPM 1st Meeting (1889)`. **(2) The publisher-prefixed decision** `BIPM DECN CIPM/101-1 (2012, EN)` (and `, FR`): new `committee_prefixed` rule — a **literal `BIPM`** lead (the constant publisher, deliberately NOT the `group` table, which contains BIPM and would collide with the second `group` capture), `type_abbrev`, then the body-qualified id `{group}/{number}`. Builds through `build_committee` short-form, so it equals `CIPM DECN 101-1 (2012, E)` — verified against real `index-v2` rows in `loose_consumer_forms_spec` (the corpus's citeas comes out as the BIPM-long style, which is the consumer's rendering choice, not pubid's). **(3) The guide's French body-prefixed long form** `Décision CIPM/111-10 (2022)` / `Recommandation JCRB/43-1 (2021)`: an alternative inside `committee_long_fr` (same capture name, so the same builder path — long form, language F). **The canonical French long form stays the connective spelling** (`Décision 101-1 du CIPM (2012)`) even though the guide's language-independent example prefers the body-prefixed one — the corpus freezes the connective render for what already parsed, and flipping the canonical would move frozen cases; that flip is an owner decision if the guide is adopted wholesale. **(4) SI Brochure guide forms**: the language code and the version are now OPTIONAL (`SI Brochure 9e v3.01 (2019/2024)` language-independent, `SI Brochure 9e (2019, E)` version-less — both byte round-trips with the canonical `BIPM SI Brochure ` lead), and the guide's French lead `Brochure sur le SI 9e …` parses as an alias of the `BIPM SI Brochure sur le SI …` canonical (note the lead alternation is `"BIPM SI Brochure" / "SI Brochure" / "Brochure sur le SI"` with the `["sur le SI" space]` phrase still optional after the first two — it just fails cleanly after the third). **(5) The corpus-cited ordinal-edition spelling** `SI Brochure 9th edition (2019)`: its own `si_brochure_ordinal_edition` rule (a separate branch, because the `edition` capture would otherwise bind `"9th"`); the builder strips the ordinal and appends `e`, so it normalizes onto `BIPM SI Brochure 9e (2019)`. **(6) Part numbers** (the guide's resource-specific-id numbering, `partnumbers` proposal, bipm-si-brochure#301): parts/subparts are dash forms inside `number` (`CIPM DECN 111-10-2`) and always parsed; the appendix/annex complement `CIPM DECN 112 A3[.5]` is the new optional ` A<n>[.<m>]` tail on `committee_short`, stored in the shared `appendix`/`annex` attributes (the MEP/guide tail's home), printed back byte-exactly by `appendix_segment`, folded into the URN identifier segment as `-a<n>[.<m>]` (`urn:bipm:cipm:decn:112-a3.5:2022` — unambiguous, because a bare number never carries letters; `UrnParser#split_appendix` splits it back), and joined into the MR number segment (`mr_slug` collapses the annex dot). It requires a number before it (`CIPM DECN A3` still fails). **URN deviations from the guide, deliberate**: the guide's own committee-example URNs (`urn:bipm:v1:cipm:resolution:95-2006:1`) carry a `v1` version segment and venue-qualified shapes the flavor's URNs never adopted (`urn:bipm:cipm:res:101-1:2012`, no `v1`, no venue segments — green for years, kept byte-identical); the new forms emit URNs under the EXISTING shape for the same reason, and the same applies to the brochure (`urn:bipm:si-brochure:<lang>:<edition>:<version>:<years>` vs the guide's `urn:bipm:v1:bipm:si-brochure:9:3.01:2024` — the guide strips the `e`/`v` and drops the language segment; adopting that is an index-affecting owner decision, not taken here). **One Ruby trap the URN fold exposed**: `id.number.to_s` on a String **attribute** returns the attribute itself, so building the folded segment by `<<` mutated `number` in place — every later `to_s`/`to_hash` of the same object then carried `-a3`; the fold is now interpolation, and `urn_spec` pins that a URN emission leaves `number` untouched. **The unmerged `si-brochure-id` proposal** (`SI Brochure 9`, `SI Brochure 9 (E)`, `SI Brochure 9 (2024) (F)` — bare-number edition) is NOT implemented: it conflicts with the merged guide's `9e` spelling. (hand-off: bipm-657-corpus-forms.)
+- **Corpus-cited forms + guide printings (pubid#657)**: the metanorma-bipm fetch queue cites two spellings the grammar rejected, and the 2026-11 guide update adds printings of its own. All are **parse-in forms over the existing canonical identities** — the canonical render follows the guide, nothing that already parsed changed. **(1) The em-dash meeting variant** `CGPM -- Meeting 1 (1889)`: `meeting_en` gained `<group> -- Meeting <n>` and `<group> -- <n><ord> Meeting` branches (the corpus cites only the first; the second is the same reordering over the other word order). They build through the existing `Meeting` path, so the canonical render is `CGPM 1st Meeting (1889)`. **(2) The publisher-prefixed decision** `BIPM DECN CIPM/101-1 (2012, EN)` (and `, FR`): new `committee_prefixed` rule — a **literal `BIPM`** lead (the constant publisher, deliberately NOT the `group` table, which contains BIPM and would collide with the second `group` capture), `type_abbrev`, then the body-qualified id `{group}/{number}`. Builds through `build_committee` short-form, so it equals `CIPM DECN 101-1 (2012, E)` — verified against real `index-v2` rows in `loose_consumer_forms_spec` (the corpus's citeas comes out as the BIPM-long style, which is the consumer's rendering choice, not pubid's). **(3) The guide's French body-prefixed long form** `Décision CIPM/111-10 (2022)` / `Recommandation JCRB/43-1 (2021)`: an alternative inside `committee_long_fr` (same capture name, so the same builder path — long form, language F). **The canonical French long form stays the connective spelling** (`Décision 101-1 du CIPM (2012)`) even though the guide's language-independent example prefers the body-prefixed one — the corpus freezes the connective render for what already parsed, and flipping the canonical would move frozen cases; that flip is an owner decision if the guide is adopted wholesale. **(4) SI Brochure guide forms**: the language code and the version are now OPTIONAL (`SI Brochure 9e v3.01 (2019/2024)` language-independent, `SI Brochure 9e (2019, E)` version-less — both byte round-trips with the canonical `BIPM SI Brochure ` lead), and the guide's French lead `Brochure sur le SI 9e …` parses as an alias of the `BIPM SI Brochure sur le SI …` canonical (note the lead alternation is `"BIPM SI Brochure" / "SI Brochure" / "Brochure sur le SI"` with the `["sur le SI" space]` phrase still optional after the first two — it just fails cleanly after the third). **(5) The corpus-cited ordinal-edition spelling** `SI Brochure 9th edition (2019)`: its own `si_brochure_ordinal_edition` rule (a separate branch, because the `edition` capture would otherwise bind `"9th"`); the builder strips the ordinal and appends `e`, so it normalizes onto `BIPM SI Brochure 9e (2019)`. **(6) Part numbers** (the guide's resource-specific-id numbering, `partnumbers` proposal, bipm-si-brochure#301): parts/subparts are dash forms inside `number` (`CIPM DECN 111-10-2`) and always parsed; the appendix/annex complement `CIPM DECN 112 A3[.5]` is the new optional ` A<n>[.<m>]` tail on `committee_short`, stored in the shared `appendix`/`annex` attributes (the MEP/guide tail's home), printed back byte-exactly by `appendix_segment`, folded into the URN identifier segment as `-a<n>[.<m>]` (`urn:bipm:cipm:decn:112-a3.5:2022` — unambiguous, because a bare number never carries letters; `UrnParser#split_appendix` splits it back), and joined into the MR number segment (`mr_slug` collapses the annex dot). It requires a number before it (`CIPM DECN A3` still fails). **URN deviations from the guide, deliberate**: the guide's own committee-example URNs (`urn:bipm:v1:cipm:resolution:95-2006:1`) carry a `v1` version segment and venue-qualified shapes the flavor's URNs never adopted (`urn:bipm:cipm:res:101-1:2012`, no `v1`, no venue segments — green for years, kept byte-identical); the new forms emit URNs under the EXISTING shape for the same reason, and the same applies to the brochure (`urn:bipm:si-brochure:<lang>:<edition>:<version>:<years>` vs the guide's `urn:bipm:v1:bipm:si-brochure:9:3.01:2024` — the guide strips the `e`/`v` and drops the language segment; adopting that is an index-affecting owner decision, not taken here). *(Both halves superseded by the 2026-11-11 official-URN ruling, below.)* **One Ruby trap the URN fold exposed**: `id.number.to_s` on a String **attribute** returns the attribute itself, so building the folded segment by `<<` mutated `number` in place — every later `to_s`/`to_hash` of the same object then carried `-a3`; the fold is now interpolation, and `urn_spec` pins that a URN emission leaves `number` untouched. **The unmerged `si-brochure-id` proposal** (`SI Brochure 9`, `SI Brochure 9 (E)`, `SI Brochure 9 (2024) (F)` — bare-number edition) is NOT implemented: it conflicts with the merged guide's `9e` spelling. *(Superseded — adopted as parse-in aliases by the 2026-11-11 ruling, below.)* (hand-off: bipm-657-corpus-forms.)
+
+- **The three 2026-11-11 owner rulings (official URNs, bare-number brochure editions, French-long flip)**: the owner ratified the guide-of-record wholesale, moving the official `urn:bipm:` face for the first time (a relaton-data-bipm re-crawl follows, accepted) and flipping one canonical render.
+  **(R1 — the `si-brochure-id` proposal adopted as parse-in aliases.** `SI Brochure 9`, `SI Brochure 9 (E)` and `SI Brochure 9 (2024) (F)` now parse, via the `si_brochure_bare_edition` grammar rule (the `si_brochure_ordinal_edition` model: a separate branch because the `edition` capture would bind the bare digit without the canonical `e`; the year and the language may each sit in their own parentheses, exactly the proposal's spellings). The builder appends the `e` — `9` → `9e`, the same normalization the ordinal spelling takes — so all three land on `BIPM SI Brochure 9e …`. **Two grammar/render consequences worth recording**: the canonical render of a year-less alias (`BIPM SI Brochure 9e`) must re-parse, so the brochure parenthetical is now OPTIONAL and accepts a **language-only paren** (`(E)` with no year — the main `si_brochure` rule's second alternative); and the renderer's paren segment had to stop printing unconditionally, because a nil `years` beside a language rendered the garbage `(, E)` — a live bug the year-less ordinal spelling already had on main (`SI Brochure 9th edition` → `BIPM SI Brochure 9e ()`). The paren now carries the year, the language or both, and stays off entirely when neither is named. Alias expectations live ONLY in `loose_consumer_forms_spec` (the ruling restates the normalizing-parses-never-in-pass rule); the three canonical faces gained byte-exact fixture lines.
+  **(R2 — the guide's official-URN shapes adopted.** Every `to_urn` now emits the `v1` face: committee `urn:bipm:v1:{group}:{type-word}:{identifier}[:{year}]` (the guide's `urn:bipm:v1:cipm:decision:110-17:2021` verbatim; the type segment is the lowercase ENGLISH NAME — recommendation/resolution/decision/action/statement — never the REC/RES/DECN abbreviation), meeting `urn:bipm:v1:{group}:meeting:{n}[:{year}]` (venue-type + venue-id as separate segments per the guide's component list; the proceedings example glues them as `meeting-26` and carries a publication year the flavor does not model), metrologia unchanged-shape-plus-`v1` (the guide's metrologia URN section is empty — as are MEP/Guide, which still raise: no landed URN, nothing to move), brochure `urn:bipm:v1:bipm:si-brochure:{edition-no-e}:{version-no-v}:{latest-year}` (the guide's pattern verbatim: language segment dropped, `9e`→`9`, `v3.01`→`3.01`, `2019/2024`→`2024` — the guide's "latest year of publication at the version"; the version segment stays empty when absent, per the guide's `…si-brochure:9::2019`). **Two guide examples do not fit the guide's own stated pattern** and are documented, not reproduced: `urn:bipm:v1:cipm:resolution:95-2006:1` puts a venue-id and the outcome ordinal where the pattern's identifier/date slots sit (its own git history edited it there from `95-2006:resolution:1`, which fit), and `urn:bipm:v1:cgpm:26:2018:resolution:1` carries the CGPM meeting number in a venue-id slot the flavor has no attribute for — the venue qualification this flavor holds lives inside the document number (`110-17`), so CGPM resolutions emit `urn:bipm:v1:cgpm:resolution:1:2018`. **The legacy faces stay parseable as documented parse-in aliases** (`UrnParser` branches on the leading `v1`): `urn:bipm:cipm:res:101-1:2012`, `urn:bipm:si-brochure:e:9e:v3.01:2019/2024`, `urn:bipm:metrologia:51:1:128`, `urn:bipm:cgpm:meeting:17:1983` and the empty-segment forms all rebuild the same identity whose `to_urn` is now the v1 face — no stored row or consumer-held URN stops resolving while the crawl lags; the emitter never produces them. The brochure alias parser also tightened two segments through `presence` (the legacy face's empty edition/version/years segments now read nil, matching what `to_hash` stores). The **pubid-scheme URN (`urn:pubid:bipm:…`) is untouched** — schema, atoms and emission byte-identical (0-diff verified).
+  **(R3 — the French-long canonical flipped to the guide's body-prefixed form.** `render_committee_long`'s F branch now prints `{name} {group}/{number} (year)` — `Décision CIPM/111-10 (2022)` — for every group, wholesale (the owner overrode the guide's own mixed pattern, which keeps the connective for CGPM resolutions). A **number-less** document has no id to qualify, so it keeps the connective spelling (`Statement de la CGPM (1889)`) — the guide's general French pattern. The connective spellings (`Décision 101-1 du CIPM (2012)`) and the group-leading word order (`CIPM Décision 101-1 (2012)`) are now normalizing aliases onto the same identity; `language: "F"` semantics unchanged. **Six byte-exact fixture lines moved** to the new canonical (recorded in the PR): the four CCL/CGPM/JCRB/CIPM connective lines became their body-prefixed spellings, the two that would have duplicated existing lines were replaced (one by the guide's own `Décision CIPM/111-10 (2022)` example, one dropped as now-identical), and the partial `Recommandation 1 du CCL` became `Recommandation CCL/1`. `to_hash` is unchanged by all three rulings — the flips are render/emitter faces only; verified by a full corpus replay (0 `to_hash` diffs, `to_pubid_urn` 0-diff).
 
 ## pubid-scheme URN (issue #670)
 

data/lib/pubid/bipm/builder.rb

@@ -39,6 +39,8 @@ module Pubid
           build_si_brochure_section(data[:si_brochure_section])
         elsif data.key?(:si_brochure_ordinal_edition)
           build_si_brochure_ordinal_edition(data[:si_brochure_ordinal_edition])
+        elsif data.key?(:si_brochure_bare_edition)
+          build_si_brochure_bare_edition(data[:si_brochure_bare_edition])
         elsif data[:mep]
           build_mep(data[:mep])
         elsif data[:guide]
@@ -119,7 +121,7 @@ module Pubid
           number: node[:edition].to_s,
           edition: node[:edition].to_s,
           version: node[:version]&.to_s,
-          years: node[:years].to_s,
+          years: node[:years]&.to_s,
           language: Identifier.normalize_language(node[:language]),
         )
       end
@@ -153,6 +155,23 @@ module Pubid
         )
       end
 
+      # The unmerged si-brochure-id proposal spells the edition as a bare
+      # number ("SI Brochure 9 (2024) (F)"); the guide's canonical edition
+      # carries the trailing "e", so the bare number normalizes onto it the
+      # same way the corpus-cited ordinal spelling does. The proposal puts the
+      # year and the language in separate parentheses; they map onto the same
+      # attributes the canonical form prints, and an absent year stays nil (a
+      # partial reference, like "SI Brochure 9th edition" without a year).
+      def build_si_brochure_bare_edition(node)
+        edition = "#{node[:bare_edition]}e"
+        Identifiers::SiBrochure.new(
+          number: edition,
+          edition: edition,
+          years: node[:year]&.to_s,
+          language: Identifier.normalize_language(node[:language]),
+        )
+      end
+
       # The Appendix/Annex/Part tail is the full-content spelling of the SAME
       # document, so it stays out of the key.
       def build_mep(node)

data/lib/pubid/bipm/renderer.rb

@@ -57,6 +57,15 @@ module Pubid
       def render_committee_long(id)
         if id.language == "F"
           name = Identifier::TYPE_NAME_FR[id.type_code]
+          # The guide's body-prefixed French pattern ("Décision CIPM/111-10
+          # (2022)") is the canonical long face: the group qualifies the
+          # resource-specific id with a slash. A number-less document has no
+          # id to qualify, so it keeps the connective spelling the guide's
+          # general French pattern uses ("Statement de la CGPM (1889)").
+          if id.number
+            return "#{name} #{id.group}/#{id.number}#{year_segment(id)}"
+          end
+
           conn = Identifier.french_connective(id.group)
           "#{name}#{number_segment(id)} #{conn} #{id.group}#{year_segment(id)}"
         else
@@ -91,12 +100,15 @@ module Pubid
 
         # The version is optional (the guide's "SI Brochure 9e (2019, E)" form)
         # and the language code too (the language-independent form), so both
-        # segments are conditional.
+        # segments are conditional. The parens carry the year, the language or
+        # both, and stay off entirely when the reference names neither ("SI
+        # Brochure 9e", the bare-number alias without a year).
         phrase = id.language == "F" ? "sur le SI " : ""
         lang = id.language ? ", #{id.language}" : ""
+        tail = id.years ? "#{id.years}#{lang}" : id.language.to_s
         result = +"BIPM SI Brochure #{phrase}#{id.edition}"
         result << " #{id.version}" if id.version
-        result << " (#{id.years}#{lang})"
+        result << " (#{tail})" if id.years || id.language
         result
       end
 

data/lib/pubid/bipm/urn_generator.rb

@@ -3,12 +3,50 @@
 module Pubid
   module Bipm
     # Emits a URN carrying the canonical (language/form-neutral) document
-    # identity for each family:
-    #   committee:  urn:bipm:<group>:<type>:<number>:<year>   (empty number seg
-    #                                                          when number-less)
-    #   meeting:    urn:bipm:<group>:meeting:<number>:<year>
-    #   metrologia: urn:bipm:metrologia:<vol>[:<issue>[:<article>]]
-    #   brochure:   urn:bipm:si-brochure:<lang>:<edition>:<version>:<years>
+    # identity for each family, in the guide-of-record's official shapes
+    # (bipm-editor-guides, sources/bipm-references-en.adoc, "URN" clauses):
+    #
+    #   committee:  urn:bipm:v1:<group>:<type-word>:<identifier>[:<year>]
+    #   meeting:    urn:bipm:v1:<group>:meeting:<number>[:<year>]
+    #   metrologia: urn:bipm:v1:metrologia:<vol>[:<issue>[:<article>]]
+    #   brochure:   urn:bipm:v1:bipm:si-brochure:<edition>:[<version>]:<year>
+    #
+    # The guide's general pattern is
+    # `urn:bipm:{version}:{group}:{venue-type}:{venue-id}
+    #  :{type}:{identifier}:{date}` with the venue slots optional. The
+    # flavor holds no venue attribute — the venue qualification lives
+    # inside the document number itself ("110-17" is the 110th meeting's
+    # decision 17) — so the venue slots stay unfilled and one shape per
+    # family falls out:
+    #
+    #   * committee — the guide's `decision` example verbatim:
+    #     `urn:bipm:v1:cipm:decision:110-17:2021`. The type segment is the
+    #     English type name lowercased (resolution/recommendation/decision/
+    #     action/statement), not the REC/RES/DECN abbreviation the previous
+    #     face carried; the empty segment stays for the type-less bare MRA
+    #     form. The guide's second committee example
+    #     (`urn:bipm:v1:cipm:resolution:95-2006:1`) does not fit the stated
+    #     pattern — it puts a venue-id (meeting 95, year 2006) and the
+    #     outcome ordinal where the pattern's identifier/date slots sit
+    #     (its own git history edited it there from `95-2006:resolution:1`,
+    #     which DID fit). This flavor emits the pattern-conforming shape;
+    #     a venue-qualified number flows through the identifier slot
+    #     verbatim.
+    #   * meeting — the venue-type `meeting` plus the venue-id, as separate
+    #     segments per the guide's meeting-outcomes component list (its only
+    #     accepted venue-type value). The guide's proceedings example glues
+    #     them (`meeting-26`) and carries a proceedings type + publication
+    #     year this flavor does not model.
+    #   * metrologia — the guide defines no metrologia URN (its section is
+    #     empty), so only the mandatory `v1` convention applies; the series
+    #     shape is unchanged.
+    #   * brochure — the guide's pattern verbatim: the `bipm` group lead,
+    #     the edition without its `e` ("9e" → "9"), the version without its
+    #     `v` ("v3.01" → "3.01"), the language segment dropped (the guide's
+    #     URN is language-independent) and the year the latest the `years`
+    #     range names ("2019/2024" → "2024", the guide's "latest year of
+    #     publication at the version"). The version segment stays empty when
+    #     absent, per the guide's `urn:bipm:v1:bipm:si-brochure:9::2019`.
     class UrnGenerator < Pubid::UrnGenerator::Base
       def generate
         case identifier
@@ -23,18 +61,29 @@ module Pubid
 
       private
 
+      # The v1 version segment leads every family; the venue-type/venue-id
+      # slots of the guide's general pattern stay unfilled because the
+      # flavor carries no venue attribute (see the class comment).
       def committee
         id = identifier
-        # type_code is nil for the bare MRA form → empty type segment, mirroring
-        # the empty-number-segment convention for number-less documents.
-        parts = ["urn", "bipm", id.group.downcase,
-                 id.type_code.to_s.downcase, committee_number_segment(id)]
+        # type_code is nil for the bare MRA form → empty type segment,
+        # mirroring the empty-number-segment convention for number-less
+        # documents. The segment is the lowercase English type name the
+        # guide spells out ("decision"), never the REC/RES/DECN code.
+        parts = ["urn", "bipm", "v1", id.group.downcase,
+                 committee_type_segment(id), committee_number_segment(id)]
         # A partial (date-less) reference drops the trailing year segment; a
         # number-less-but-dated doc keeps its empty number segment.
         parts << id.year if id.year
         parts.join(":")
       end
 
+      def committee_type_segment(id)
+        return "" unless id.type_code
+
+        Identifier::TYPE_NAME_EN[id.type_code].downcase
+      end
+
       # The appendix/annex complement folds into the identifier segment as
       # "-a{appendix}[.{annex}]". A bare number is digits and dashes only, so
       # the letter-prefixed tail is unambiguous on the way back (UrnParser
@@ -50,21 +99,38 @@ module Pubid
 
       def meeting
         id = identifier
-        parts = ["urn", "bipm", id.group.downcase, "meeting", id.number.to_s]
+        parts = ["urn", "bipm", "v1", id.group.downcase, "meeting",
+                 id.number.to_s]
         parts << id.year if id.year
         parts.join(":")
       end
 
       def metrologia
-        parts = ["urn", "bipm", "metrologia", identifier.volume]
+        parts = ["urn", "bipm", "v1", "metrologia", identifier.volume]
         parts << identifier.issue if identifier.issue
         parts << identifier.article if identifier.article
         parts.join(":")
       end
 
       def si_brochure
-        ["urn", "bipm", "si-brochure", identifier.language.to_s.downcase,
-         identifier.edition, identifier.version, identifier.years].join(":")
+        id = identifier
+        ["urn", "bipm", "v1", "bipm", "si-brochure",
+         brochure_edition_segment(id), id.version.to_s.delete_prefix("v"),
+         brochure_year_segment(id)].join(":")
+      end
+
+      # The guide's edition-number carries no "e" ("Notice the absence of the
+      # letter e after the number"): "9e" emits "9". A variant (Appendix 3 /
+      # Concise / FAQ) or a bare section reference names no edition, so the
+      # segment is empty — the documented partial-reference bucket.
+      def brochure_edition_segment(id)
+        id.edition.to_s.delete_suffix("e")
+      end
+
+      # The guide's year is "the latest year of publication at the version":
+      # the "2019" of "2019", the "2024" of "2019/2024".
+      def brochure_year_segment(id)
+        id.years.to_s.split("/").last
       end
     end
   end