pubid 2.0.4 → 2.0.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 84bd43c2b2468d0b30852e4d2d624a031d285deafe17e8e82d1dfa7c9d1b9b69
-  data.tar.gz: 1b38d8c8f8fa201e5af2a029ccd6ca64b99cd9b942211cf8d4819002e2ef220b
+  metadata.gz: bb0eb2441f1733fb2498a35955d3840cf1058c1cc2a0da5222633b80451258b2
+  data.tar.gz: 110f3275bbef45f8b5d956193ae4aee6647bb9ca57ff51b383451b1f575c964e
 SHA512:
-  metadata.gz: 01feda9bcfedabf22e2e759b19962b3defdc2c89149d3e25549520aac507d47e7ff1ae51662aa6c5126abb6a7d15e8a3859012383c6e6470251d34c2ca127d0f
-  data.tar.gz: 87106f99d5450648e77694567752fa6aa48918ce6d88544393c3baa04ccd5a71e46ba7eae25f76a0ce692db59c7d8095dc62c1a783dbc23de8ae59231822eb3b
+  metadata.gz: 270e7d940a329eeb409bd65dc14dd325318ab11b81f702fc45e3c5186fd6d39d40cae0f0c286ab454900928d009dcf8073ddfcb4a6d803181223f6608c5d85c2
+  data.tar.gz: fd28a2998a2bb92a7812b7a435d5965e95991ad5f666d5c6f2d13e1171b8d4edaa6905e32b2b15124052816d0ee2873446d73c125e1b3d6ef26ca6d6b3e851a2

data/data/bipm/update_codes.yaml

@@ -7,3 +7,17 @@
 # the docnumber and docidentifier spellings map onto the bare "CIPM 2005-06" form.
 "CIPM/2005-06(REV)": CIPM 2005-06
 "CIPM 2005-06(REV)": CIPM 2005-06
+
+# The SI Brochure cited by its title: the brochure IS "The International
+# System of Units", and external references cite it in quotes (pubid#644).
+# Map the quoted-title spelling onto the parseable "BIPM SI Brochure" section
+# form — a partial reference with no edition, so it wildcards every edition
+# under the matching primitives, exactly like "SI Brochure Part 1". A
+# normalizing parse like the CIPM MRA ones above: never a byte-exact fixture
+# (see spec/pubid/bipm/loose_consumer_forms_spec.rb).
+#
+# The French title is deliberately NOT mapped: it names the F-language record
+# specifically, and mapping it would silently drop language information the
+# user typed (the loose-forms rule). English is language-neutral, so it stays.
+/^BIPM "The International System of Units"$/: BIPM SI Brochure
+/^"The International System of Units"$/: SI Brochure

data/data/parg/iho.json

@@ -1 +1 @@
-{"bindings":null,"version":"0.1.0","grammar":"PubidIho","shape":"parsanol-tree/v2","binding_version":1,"entries":{"identifier":{"root":"identifier","grammar":{"atoms":[{"Str":{"pattern":"IHO"}},{"Entity":{"atom":2}},{"Str":{"pattern":" "}},{"Sequence":{"atoms":[0,1]}},{"Repetition":{"atom":3,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":12}},{"Str":{"pattern":"S"}},{"Str":{"pattern":"P"}},{"Str":{"pattern":"M"}},{"Str":{"pattern":"B"}},{"Str":{"pattern":"C"}},{"Alternative":{"atoms":[6,7,8,9,10]}},{"Named":{"name":"type","atom":11}},{"Entity":{"atom":14}},{"Str":{"pattern":"-"}},{"Entity":{"atom":37}},{"Entity":{"atom":17}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":16,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":34}},{"Str":{"pattern":":"}},{"Entity":{"atom":17}},{"Repetition":{"atom":21,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[20,22]}},{"Str":{"pattern":"/"}},{"Entity":{"atom":17}},{"Repetition":{"atom":25,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[24,26]}},{"Entity":{"atom":14}},{"Entity":{"atom":17}},{"Repetition":{"atom":29,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[28,30]}},{"Entity":{"atom":33}},{"Re":{"pattern":"[\\x41-\\x5a]"}},{"Alternative":{"atoms":[23,27,31,32]}},{"Repetition":{"atom":19,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[18,35]}},{"Named":{"name":"number","atom":36}},{"Entity":{"atom":54}},{"Entity":{"atom":2}},{"Str":{"pattern":"Appendix"}},{"Str":{"pattern":"Ap."}},{"Alternative":{"atoms":[40,41]}},{"Entity":{"atom":2}},{"Entity":{"atom":33}},{"Entity":{"atom":14}},{"Entity":{"atom":17}},{"Repetition":{"atom":46,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[44,45,47]}},{"Entity":{"atom":17}},{"Repetition":{"atom":49,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":33}},{"Alternative":{"atoms":[48,50,51]}},{"Named":{"name":"appendix","atom":52}},{"Sequence":{"atoms":[39,42,43,53]}},{"Repetition":{"atom":38,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":72}},{"Entity":{"atom":2}},{"Str":{"pattern":"Part"}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":60,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":66}},{"Entity":{"atom":33}},{"Entity":{"atom":65}},{"Re":{"pattern":"[\\x61-\\x7a]"}},{"Alternative":{"atoms":[63,64]}},{"Repetition":{"atom":62,"min":0,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[61,67]}},{"Entity":{"atom":33}},{"Alternative":{"atoms":[68,69]}},{"Named":{"name":"part","atom":70}},{"Sequence":{"atoms":[57,58,59,71]}},{"Repetition":{"atom":56,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":80}},{"Entity":{"atom":2}},{"Str":{"pattern":"Annex"}},{"Entity":{"atom":2}},{"Entity":{"atom":33}},{"Named":{"name":"annex","atom":78}},{"Sequence":{"atoms":[75,76,77,79]}},{"Repetition":{"atom":74,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":89}},{"Entity":{"atom":2}},{"Str":{"pattern":"Suppl"}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":86,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"supplement","atom":87}},{"Sequence":{"atoms":[83,84,85,88]}},{"Repetition":{"atom":82,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":135}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":93,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":96}},{"Str":{"pattern":"."}},{"Entity":{"atom":17}},{"Repetition":{"atom":97,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":96}},{"Entity":{"atom":17}},{"Repetition":{"atom":100,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[94,95,98,99,101]}},{"Named":{"name":"version","atom":102}},{"Str":{"pattern":"19"}},{"Str":{"pattern":"20"}},{"Alternative":{"atoms":[104,105]}},{"Entity":{"atom":17}},{"Repetition":{"atom":107,"min":2,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[106,108]}},{"Named":{"name":"year","atom":109}},{"Str":{"pattern":"Vol."}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":113,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"volume","atom":114}},{"Sequence":{"atoms":[111,112,115]}},{"Entity":{"atom":2}},{"Str":{"pattern":"Issue"}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":120,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"issue","atom":121}},{"Sequence":{"atoms":[117,118,119,122]}},{"Entity":{"atom":2}},{"Str":{"pattern":"("}},{"Entity":{"atom":17}},{"Repetition":{"atom":126,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"issue","atom":127}},{"Str":{"pattern":")"}},{"Sequence":{"atoms":[124,125,128,129]}},{"Alternative":{"atoms":[123,130]}},{"Repetition":{"atom":131,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[116,132]}},{"Alternative":{"atoms":[103,110,133]}},{"Sequence":{"atoms":[92,134]}},{"Repetition":{"atom":91,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[4,5,13,15,55,73,81,90,136]}}],"root":137},"bindings":[{"capture":"year","path":"year","type":"string","card":null,"preprocess":null},{"capture":"volume","path":"volume","type":"string","card":null,"preprocess":null},{"capture":"issue","path":"issue","type":"string","card":null,"preprocess":null}]}},"preprocess":{},"tables":{},"lint":{"order_warnings":[]},"default_entry":"identifier","render":{},"derive":{},"tests":[{"entry":"identifier","kind":"accept","input":"S-5","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-5 Appendix 2","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO B-12 3.0.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-5 2024","expect":{}},{"entry":"identifier","kind":"accept","input":"P-5 2024","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO B-7 2023","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-1 Vol. 30","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-1 Vol. 30 (2)","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-1 Vol. 30 Issue 2","expect":{}},{"entry":"identifier","kind":"reject","input":"nonsense","expect":{}},{"entry":"identifier","kind":"reject","input":"IHO B-12 3.0","expect":{}}],"docs":{},"source":"# Port of lib/pubid/iho/parser.rb — IHO identifiers: letter series\n# (S/P/M/B/C), a number with an optional suffix, and appendix, part,\n# annex, supplement and version tails.\n#\n# The trailing component of a series form is a discriminator chosen\n# from:\n#   - the dotted version a.b.c (unchanged — the historical placeholder\n#     and the real S/M/B/C editions, e.g. \"B-12 3.0.0\");\n#   - a 4-digit year 19xx/20xx (\"P-5 2024\", \"B-7 2023\") — the identity\n#     form for the year-identified series (relaton#407: B-7, P-5, P-6\n#     are identified by year, not by a placeholder edition);\n#   - a volume \"Vol. N\" with an optional issue (\"P-1 Vol. 30\",\n#     \"P-1 Vol. 30 (2)\"). The issue is captured as the bare number and\n#     prints in parentheses. The \"Issue N\" spelling is accepted as an\n#     input alias; the parenthesized form is the canonical print.\n#     DECISION FLAG for the IHO-agreement step: real IHR issue\n#     spellings vary (\"No. N\" is also seen) — only \"(N)\" and\n#     \"Issue N\" are accepted until the spelling is agreed.\n# A two-segment version (\"B-12 3.0\") is deliberately NOT supported:\n# no IHO series carries one in the corpus, and neither new rule\n# swallows it (a year needs all four digits of 19xx/20xx; a dotted\n# version needs all three segments).\n#\n# The grammar stays edition v1: the v1 tree inlines rule references\n# inside a captured body (the v2 tree materializes them as named\n# nodes), which the builder's string fold over :number/:type expects.\n# The tail rule uses only raw terms, so nothing in it needs v2.\n\ngrammar PubidIho version \"0.1.0\" edition 1 {\n  digit = %x30-39\n  upper = %x41-5A\n  lower = %x61-7A\n  letter = upper / lower\n  space = \" \"\n  dash = \"-\"\n  dot = \".\"\n\n  series = (\"S\" / \"P\" / \"M\" / \"B\" / \"C\") as type\n  number_suffix = ((\":\" 1*digit) / (\"/\" 1*digit) / (dash 1*digit) / upper)\n  number = (1*digit [number_suffix]) as number\n  appendix = {\n    space (\"Appendix\" / \"Ap.\") space\n    ((upper dash 1*digit) / (1*digit) / upper) as appendix\n  }\n  part = {\n    space \"Part\" space\n    ((1*digit *letter) / upper) as part\n  }\n  annex = space \"Annex\" space upper as annex\n  supplement = space \"Suppl\" space (1*digit) as supplement\n  tail = {\n    space\n    (\n      (1*digit dot 1*digit dot 1*digit) as version\n      / ((\"19\" / \"20\") 2*digit) as year\n      / (\n        (\"Vol.\" space (1*digit) as volume)\n        [\n          (space \"Issue\" space (1*digit) as issue)\n          / (space \"(\" (1*digit) as issue \")\")\n        ]\n      )\n    )\n  }\n\n  identifier = {\n    [(\"IHO\" space)]\n    series\n    dash\n    number\n    [appendix]\n    [part]\n    [annex]\n    [supplement]\n    [tail]\n  }\n\n  entry identifier: identifier\n\n  test {\n    accept \"S-5\"\n    accept \"IHO S-5 Appendix 2\"\n    accept \"IHO B-12 3.0.0\"\n    accept \"IHO P-5 2024\"\n    accept \"P-5 2024\"\n    accept \"IHO B-7 2023\"\n    accept \"IHO P-1 Vol. 30\"\n    accept \"IHO P-1 Vol. 30 (2)\"\n    accept \"IHO P-1 Vol. 30 Issue 2\"\n    reject \"nonsense\"\n    reject \"IHO B-12 3.0\"\n  }\n\n  bindings identifier {\n    year -> year (string)\n    volume -> volume (string)\n    issue -> issue (string)\n  }\n}\n","source_hash":"8d0d31907c36e5a398b7af8e11b434afb75588f6252e79cd975cb2c10a10ad8a","unicode_tables":"onigmo (Ruby 3.4.8)","compiler_version":"1.3.114","edition":1,"checksum":"sha256:52f91157a4d75ed1eef5cddd14789fcd907ec721384f88f5d3df77548dc307b9"}
+{"bindings":null,"version":"0.2.0","grammar":"PubidIho","shape":"parsanol-tree/v2","binding_version":1,"entries":{"identifier":{"root":"identifier","grammar":{"atoms":[{"Str":{"pattern":"IHO"}},{"Entity":{"atom":2}},{"Str":{"pattern":" "}},{"Sequence":{"atoms":[0,1]}},{"Repetition":{"atom":3,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":12}},{"Str":{"pattern":"S"}},{"Str":{"pattern":"P"}},{"Str":{"pattern":"M"}},{"Str":{"pattern":"B"}},{"Str":{"pattern":"C"}},{"Alternative":{"atoms":[6,7,8,9,10]}},{"Named":{"name":"type","atom":11}},{"Entity":{"atom":14}},{"Str":{"pattern":"-"}},{"Entity":{"atom":26}},{"Entity":{"atom":17}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":16,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":23}},{"Str":{"pattern":":"}},{"Entity":{"atom":17}},{"Repetition":{"atom":21,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[20,22]}},{"Repetition":{"atom":19,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[18,24]}},{"Named":{"name":"number","atom":25}},{"Entity":{"atom":53}},{"Str":{"pattern":"-"}},{"Str":{"pattern":"S"}},{"Str":{"pattern":"P"}},{"Str":{"pattern":"M"}},{"Str":{"pattern":"B"}},{"Str":{"pattern":"C"}},{"Alternative":{"atoms":[29,30,31,32,33]}},{"Entity":{"atom":14}},{"Entity":{"atom":17}},{"Repetition":{"atom":36,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[34,35,37]}},{"Entity":{"atom":17}},{"Repetition":{"atom":39,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":46}},{"Entity":{"atom":43}},{"Re":{"pattern":"[\\x41-\\x5a]"}},{"Entity":{"atom":45}},{"Re":{"pattern":"[\\x61-\\x7a]"}},{"Alternative":{"atoms":[42,44]}},{"Repetition":{"atom":41,"min":0,"max":null,"tag":"Repetition"}},{"Repetition":{"atom":47,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[40,48]}},{"Entity":{"atom":43}},{"Alternative":{"atoms":[38,49,50]}},{"Named":{"name":"part","atom":51}},{"Sequence":{"atoms":[28,52]}},{"Repetition":{"atom":27,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":57}},{"Entity":{"atom":43}},{"Named":{"name":"part","atom":56}},{"Repetition":{"atom":55,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":94}},{"Str":{"pattern":"/"}},{"Entity":{"atom":17}},{"Repetition":{"atom":61,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"volume","atom":62}},{"Entity":{"atom":92}},{"Entity":{"atom":78}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":67,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Str":{"pattern":"."}},{"Entity":{"atom":17}},{"Repetition":{"atom":71,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":74,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[68,69,72,73,75]}},{"Named":{"name":"volume_edition","atom":76}},{"Sequence":{"atoms":[66,77]}},{"Entity":{"atom":90}},{"Entity":{"atom":2}},{"Str":{"pattern":"("}},{"Str":{"pattern":"19"}},{"Str":{"pattern":"20"}},{"Alternative":{"atoms":[82,83]}},{"Entity":{"atom":17}},{"Repetition":{"atom":85,"min":2,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[84,86]}},{"Named":{"name":"volume_year","atom":87}},{"Str":{"pattern":")"}},{"Sequence":{"atoms":[80,81,88,89]}},{"Repetition":{"atom":79,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[65,91]}},{"Repetition":{"atom":64,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[60,63,93]}},{"Repetition":{"atom":59,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":137}},{"Entity":{"atom":109}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":99,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":102,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":105,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[100,101,103,104,106]}},{"Named":{"name":"edition","atom":107}},{"Sequence":{"atoms":[98,108]}},{"Entity":{"atom":122}},{"Entity":{"atom":2}},{"Str":{"pattern":"v"}},{"Entity":{"atom":17}},{"Repetition":{"atom":113,"min":1,"max":null,"tag":"Repetition"}},{"Str":{"pattern":"."}},{"Entity":{"atom":17}},{"Repetition":{"atom":116,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[115,117]}},{"Repetition":{"atom":118,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[114,119]}},{"Named":{"name":"edition_shorthand","atom":120}},{"Sequence":{"atoms":[111,112,121]}},{"Alternative":{"atoms":[97,110]}},{"Entity":{"atom":135}},{"Entity":{"atom":2}},{"Str":{"pattern":"("}},{"Str":{"pattern":"19"}},{"Str":{"pattern":"20"}},{"Alternative":{"atoms":[127,128]}},{"Entity":{"atom":17}},{"Repetition":{"atom":130,"min":2,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[129,131]}},{"Named":{"name":"year","atom":132}},{"Str":{"pattern":")"}},{"Sequence":{"atoms":[125,126,133,134]}},{"Repetition":{"atom":124,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[123,136]}},{"Repetition":{"atom":96,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":177}},{"Entity":{"atom":2}},{"Str":{"pattern":"Suppl"}},{"Str":{"pattern":"Sup"}},{"Alternative":{"atoms":[141,142]}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":145,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"supplement","atom":146}},{"Entity":{"atom":175}},{"Entity":{"atom":161}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":151,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":154,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":157,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[152,153,155,156,158]}},{"Named":{"name":"supplement_edition","atom":159}},{"Sequence":{"atoms":[150,160]}},{"Entity":{"atom":173}},{"Entity":{"atom":2}},{"Str":{"pattern":"("}},{"Str":{"pattern":"19"}},{"Str":{"pattern":"20"}},{"Alternative":{"atoms":[165,166]}},{"Entity":{"atom":17}},{"Repetition":{"atom":168,"min":2,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[167,169]}},{"Named":{"name":"supplement_year","atom":170}},{"Str":{"pattern":")"}},{"Sequence":{"atoms":[163,164,171,172]}},{"Repetition":{"atom":162,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[149,174]}},{"Repetition":{"atom":148,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[140,143,144,147,176]}},{"Repetition":{"atom":139,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":233}},{"Entity":{"atom":2}},{"Str":{"pattern":"Part"}},{"Entity":{"atom":2}},{"Entity":{"atom":203}},{"Entity":{"atom":194}},{"Str":{"pattern":"S"}},{"Str":{"pattern":"P"}},{"Str":{"pattern":"M"}},{"Str":{"pattern":"B"}},{"Str":{"pattern":"C"}},{"Alternative":{"atoms":[185,186,187,188,189]}},{"Entity":{"atom":14}},{"Entity":{"atom":17}},{"Repetition":{"atom":192,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[190,191,193]}},{"Entity":{"atom":17}},{"Repetition":{"atom":195,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":46}},{"Repetition":{"atom":197,"min":0,"max":null,"tag":"Repetition"}},{"Repetition":{"atom":198,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[196,199]}},{"Entity":{"atom":43}},{"Alternative":{"atoms":[184,200,201]}},{"Named":{"name":"part","atom":202}},{"Entity":{"atom":231}},{"Entity":{"atom":217}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":207,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":210,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":213,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[208,209,211,212,214]}},{"Named":{"name":"part_edition","atom":215}},{"Sequence":{"atoms":[206,216]}},{"Entity":{"atom":229}},{"Entity":{"atom":2}},{"Str":{"pattern":"("}},{"Str":{"pattern":"19"}},{"Str":{"pattern":"20"}},{"Alternative":{"atoms":[221,222]}},{"Entity":{"atom":17}},{"Repetition":{"atom":224,"min":2,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[223,225]}},{"Named":{"name":"part_year","atom":226}},{"Str":{"pattern":")"}},{"Sequence":{"atoms":[219,220,227,228]}},{"Repetition":{"atom":218,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[205,230]}},{"Repetition":{"atom":204,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[180,181,182,183,232]}},{"Repetition":{"atom":179,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":270}},{"Entity":{"atom":2}},{"Str":{"pattern":"Annex"}},{"Entity":{"atom":2}},{"Entity":{"atom":43}},{"Named":{"name":"annex","atom":239}},{"Entity":{"atom":268}},{"Entity":{"atom":254}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":244,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":247,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":250,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[245,246,248,249,251]}},{"Named":{"name":"annex_edition","atom":252}},{"Sequence":{"atoms":[243,253]}},{"Entity":{"atom":266}},{"Entity":{"atom":2}},{"Str":{"pattern":"("}},{"Str":{"pattern":"19"}},{"Str":{"pattern":"20"}},{"Alternative":{"atoms":[258,259]}},{"Entity":{"atom":17}},{"Repetition":{"atom":261,"min":2,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[260,262]}},{"Named":{"name":"annex_year","atom":263}},{"Str":{"pattern":")"}},{"Sequence":{"atoms":[256,257,264,265]}},{"Repetition":{"atom":255,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[242,267]}},{"Repetition":{"atom":241,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[236,237,238,240,269]}},{"Repetition":{"atom":235,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":321}},{"Entity":{"atom":2}},{"Str":{"pattern":"Appendix"}},{"Str":{"pattern":"App"}},{"Str":{"pattern":"Ap."}},{"Alternative":{"atoms":[274,275,276]}},{"Entity":{"atom":2}},{"Entity":{"atom":284}},{"Entity":{"atom":43}},{"Entity":{"atom":17}},{"Repetition":{"atom":281,"min":1,"max":null,"tag":"Repetition"}},{"Alternative":{"atoms":[280,282]}},{"Named":{"name":"appendix","atom":283}},{"Entity":{"atom":290}},{"Entity":{"atom":14}},{"Entity":{"atom":17}},{"Repetition":{"atom":287,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"appendix_subnumber","atom":288}},{"Sequence":{"atoms":[286,289]}},{"Repetition":{"atom":285,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":319}},{"Entity":{"atom":305}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":295,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":298,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":70}},{"Entity":{"atom":17}},{"Repetition":{"atom":301,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[296,297,299,300,302]}},{"Named":{"name":"appendix_edition","atom":303}},{"Sequence":{"atoms":[294,304]}},{"Entity":{"atom":317}},{"Entity":{"atom":2}},{"Str":{"pattern":"("}},{"Str":{"pattern":"19"}},{"Str":{"pattern":"20"}},{"Alternative":{"atoms":[309,310]}},{"Entity":{"atom":17}},{"Repetition":{"atom":312,"min":2,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[311,313]}},{"Named":{"name":"appendix_year","atom":314}},{"Str":{"pattern":")"}},{"Sequence":{"atoms":[307,308,315,316]}},{"Repetition":{"atom":306,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[293,318]}},{"Repetition":{"atom":292,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[273,277,278,279,291,320]}},{"Repetition":{"atom":272,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":362}},{"Entity":{"atom":348}},{"Entity":{"atom":2}},{"Str":{"pattern":"Vol."}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":328,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"volume","atom":329}},{"Entity":{"atom":346}},{"Entity":{"atom":2}},{"Str":{"pattern":"Issue"}},{"Entity":{"atom":2}},{"Entity":{"atom":17}},{"Repetition":{"atom":335,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"issue","atom":336}},{"Sequence":{"atoms":[332,333,334,337]}},{"Entity":{"atom":2}},{"Str":{"pattern":"("}},{"Entity":{"atom":17}},{"Repetition":{"atom":341,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"issue","atom":342}},{"Str":{"pattern":")"}},{"Sequence":{"atoms":[339,340,343,344]}},{"Alternative":{"atoms":[338,345]}},{"Repetition":{"atom":331,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[325,326,327,330,347]}},{"Entity":{"atom":358}},{"Entity":{"atom":2}},{"Str":{"pattern":"19"}},{"Str":{"pattern":"20"}},{"Alternative":{"atoms":[351,352]}},{"Entity":{"atom":17}},{"Repetition":{"atom":354,"min":2,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[353,355]}},{"Named":{"name":"volume","atom":356}},{"Sequence":{"atoms":[350,357]}},{"Alternative":{"atoms":[324,349]}},{"Entity":{"atom":92}},{"Repetition":{"atom":360,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[359,361]}},{"Repetition":{"atom":323,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":135}},{"Repetition":{"atom":364,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[4,5,13,15,54,58,95,138,178,234,271,322,363,365]}}],"root":366},"bindings":[{"capture":"type","path":"type","type":"string","card":null,"preprocess":null},{"capture":"number","path":"number","type":"string","card":null,"preprocess":null},{"capture":"part","path":"part","type":"string","card":null,"preprocess":null},{"capture":"part_edition","path":"part_edition","type":"string","card":null,"preprocess":null},{"capture":"part_year","path":"part_year","type":"string","card":null,"preprocess":null},{"capture":"annex","path":"annex","type":"string","card":null,"preprocess":null},{"capture":"annex_edition","path":"annex_edition","type":"string","card":null,"preprocess":null},{"capture":"annex_year","path":"annex_year","type":"string","card":null,"preprocess":null},{"capture":"appendix","path":"appendix","type":"string","card":null,"preprocess":null},{"capture":"appendix_subnumber","path":"appendix_subnumber","type":"string","card":null,"preprocess":null},{"capture":"appendix_edition","path":"appendix_edition","type":"string","card":null,"preprocess":null},{"capture":"appendix_year","path":"appendix_year","type":"string","card":null,"preprocess":null},{"capture":"supplement","path":"supplement","type":"string","card":null,"preprocess":null},{"capture":"supplement_edition","path":"supplement_edition","type":"string","card":null,"preprocess":null},{"capture":"supplement_year","path":"supplement_year","type":"string","card":null,"preprocess":null},{"capture":"edition","path":"edition","type":"string","card":null,"preprocess":null},{"capture":"edition_shorthand","path":"edition_shorthand","type":"string","card":null,"preprocess":null},{"capture":"year","path":"year","type":"string","card":null,"preprocess":null},{"capture":"volume","path":"volume","type":"string","card":null,"preprocess":null},{"capture":"volume_edition","path":"volume_edition","type":"string","card":null,"preprocess":null},{"capture":"volume_year","path":"volume_year","type":"string","card":null,"preprocess":null},{"capture":"issue","path":"issue","type":"string","card":null,"preprocess":null}]}},"preprocess":{},"tables":{},"lint":{"order_warnings":["rule volume_issue: branches 1 and 2 are order-dependent (shared first bytes; ordered choice is decisive)"]},"default_entry":"identifier","render":{},"derive":{},"tests":[{"entry":"identifier","kind":"accept","input":"S-5","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-5 Appendix 2","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO B-12 3.0.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-5 2024","expect":{}},{"entry":"identifier","kind":"accept","input":"P-5 2024","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-5 Vol. 2024","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-5/2024","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO B-7 Vol. 2023","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-1 Vol. 30","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-1 Vol. 30 (2)","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-1 Vol. 30 Issue 2","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-1/21","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-1/21 1.0.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-100 5.0.0 Part 2","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-98 1.0.0 Part A","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-65 1.1.0 Annex A","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-122 1.0.0 Appendix D-2","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-52 4.0.0 Appendix 1","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO M-2 Sup 1","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO M-2 Suppl 6","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-66 2.0.0 Sup 4","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-5-B","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-100-1","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-100-1 1.0.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-6-3 1.0.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-5A","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-5A 1.0.2","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-5 1.0.2 Part A","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-100 5.0.0 Part 2 (2024)","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-100 v5.1","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-100 v1","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-100 1.0.0 (2024) Part A","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-53 Ap. 1 1.0.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-98 Part A 1.0.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-158:100 1.0.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-158:100 Part 2 1.0.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-1001","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-158 Part S-102 0.2.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-158-S-102 0.2.0","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-6 1.0.0 Vol. 2","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO P-6 Vol. 2 1.0.1","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-98 1.0.0 Annex A","expect":{}},{"entry":"identifier","kind":"accept","input":"IHO S-100 5.0.0 Sup 1 2.0.0","expect":{}},{"entry":"identifier","kind":"reject","input":"nonsense","expect":{}},{"entry":"identifier","kind":"reject","input":"IHO B-12 3.0","expect":{}},{"entry":"identifier","kind":"reject","input":"IHO P-5 1850","expect":{}}],"docs":{},"source":"# Port of lib/pubid/iho/parser.rb — IHO identifiers: letter series\n# (S/P/M/B/C), a number with an optional suffix, and the full component\n# tail (edition, supplement, part, annex, appendix + subnumber, volume,\n# issue, year qualifier).\n#\n# == Component model (owner rulings, 2026-11-03)\n#\n# Every component below is a first-class semantic component: its own\n# named capture, its own typed binding, independently addressable in\n# the model, URN-encodable and matchable — never a regex/string suffix.\n#\n#   component    face                capture             binding type\n#   edition      x.y.z (bare)        edition             string\n#   edition      v1 / v5.1 (alias)   edition_shorthand   string (parse-only;\n#                                                        the builder pads to\n#                                                        x.y.0 — official IHO\n#                                                        edition is dotted\n#                                                        x.y.z WITHOUT a year)\n#   supplement   Sup N (Suppl N)     supplement          string\n#   part         Part X / Part S-102 part                string (letter,\n#                                                        number, or SERIES\n#                                                        REFERENCE)\n#   part         -X / -S-102 (short) part                string (hyphenated)\n#   annex        Annex A             annex               string\n#   appendix     Appendix B          appendix            string\n#   appendix     Appendix D-2        appendix_subnumber  string (the -2)\n#   volume       Vol. N              volume              string\n#   volume       /N (short)          volume              string (the slash\n#                                                        chain, P-1/21 or\n#                                                        P-5/2020)\n#   volume       N (bare, legacy)    volume              string (the yearbook\n#                                                        year IS a volume —\n#                                                        one serial-locator\n#                                                        component)\n#   issue        (N) / Issue N       issue               string\n#   year         (2024)              year                string (the with-year\n#                                                        qualifier on\n#                                                        standards; NOT a\n#                                                        serial locator)\n#\n# == Component-edition duality (owner ruling: \"this can happen with any\n#    independently publishable artifacts\")\n#\n# Supplement, part, annex, appendix and volume can be published on\n# their own publication cycle, so EACH carries an optional\n# `<kind>_edition` (+ `<kind>_year` qualifier) of its own, mutually\n# exclusive with the base edition context:\n#\n#   within-edition:        IHO P-6 1.0.0 Vol. 2       (the volume rides\n#                                                   the base's edition)\n#   separately-published:  IHO P-6 Vol. 2 1.0.1       (the volume carries\n#                          IHO S-98 Part A 1.0.0       its own edition;\n#                          IHO S-158 Part S-102 0.2.0  the base is\n#                                                      cited edition-less)\n#\n# In the URN the ed- segment attaches to the node it follows, so the\n# same positional slot records both modes.\n#\n# The part has a COMPACT face, hyphenated onto the code — `IHO S-5-B`\n# (lettered part), `IHO S-100-1` (numbered part), `IHO S-158-S-102`\n# (series-reference part) — which both parses and renders; the\n# canonical expanded face stays `IHO S-100 x.y.z Part 1`. Gluing a part\n# onto the code without a separator (S-5A) is DISALLOWED as a form: it\n# cannot extend to numbered parts without ambiguity (S-1001 = series\n# 1001 vs series 100 part 1). The four lettered bases the corpus\n# records (S-5A, S-5B, S-8A, S-8B) are LEGACY data spellings: they\n# still parse as aliases (S-5A == S-5 Part A) but are never rendered;\n# the owner rules later whether to reject them outright.\n#\n# Series-reference parts: a check standard applied to another IHO\n# series cites the applied series as its part — `IHO S-158 0.2.0 Part\n# S-102` (the wild glued `S-158-102` spelling is a legacy alias whose\n# normalization to Part S-102 needs an IHO series table; the syntax\n# alone cannot tell it from S-100-1 = Part 1, so it currently parses\n# as the plain number part).\n#\n# Two main syntaxes per the owner ruling: `IHO S-100 1.0.0` (dated =\n# edition-specific) and `IHO S-100` (undated = edition-non-specific).\n# A year beside an edition is the with-year variant qualifier\n# (`IHO S-100 1.0.0 Part X (2024)`), never a year-keyed docidentifier —\n# year-keyed docidentifiers for edition-keyed products are wrong. The\n# continuously-updated series have ONE serial locator, the volume:\n# P-1 and P-6 are volume-keyed (`IHO P-1 Vol. 30 (1)`), and the\n# yearbook year IS a volume (`IHO P-5 Vol. 2020`) — the bare year\n# (`IHO P-5 2020`) and all year-faced forms are parse-only legacy\n# aliases that bind into the volume component, never rendered.\n#\n# Aliases: \"Suppl\" (canonical face Sup, the M-2 spelling — why abbreviate\n# by two letters when Annex and Appendix stay full-length), \"App\"/\"Ap.\"\n# (canonical face Appendix), the hyphenated compact part face (S-5-B ==\n# S-5 Part B, S-100-1 == S-100 Part 1), the legacy glued lettered bases\n# (S-5A, parse-only), \"S-100 v1..v5.1\" (edition shorthand), \"Issue N\"\n# (canonical (N)), the bare year (canonical Vol. N).\n#\n# == URN segment grammar (positional, containment-ordered)\n#\n# The URN mirrors the containment tree, one semantic atom per segment:\n# Part contains Annexes; Annex contains Appendices; a D-2 subnumber is\n# a child atom of Appendix D. No key.value concatenations — every\n# non-number component is a marker-prefixed segment whose marker is the\n# lowercased human-face token (edition follows ISO's ed- precedent):\n#\n#   urn:iho:<type>:<number>[:ed-<x.y.z>][:year-<yyyy>]\n#     [:sup-<n>[:ed-<x.y.z>][:year-<yyyy>]]\n#     [:part-<X>[:ed-<x.y.z>][:year-<yyyy>]]\n#     [:annex-<A>[...]]\n#     [:appendix-<B>[:<sub>][...]]\n#     [:vol-<n>[:issue-<n>][...]]\n#     [:year-<yyyy>]\n#\n#   position  segment          value vocabulary            containment\n#   --------  ---------------  --------------------------  ------------------\n#   1         <type>           s / p / m / b / c           namespace root\n#   2         <number>         digits + : suffix; may      document code\n#                              span bare segments until\n#                              the first marker\n#   3         ed-<x.y.z>       dotted a.b.c                edition qualifier;\n#   4         year-<yyyy>      19xx/20xx                   ATTACHES TO THE\n#                                                      NODE IT FOLLOWS: the\n#                                                      base (no component\n#                                                      before it) or the\n#                                                      component whose\n#                                                      segment precedes\n#   5         sup-<n>          1*digit                     wraps the base\n#   6         part-<X>         letter (case kept),         contains annexes\n#                              digits [*letter], or a\n#                              series reference\n#                              [SPMBC]-<digits>\n#   7         annex-<A>        upper letter (case kept)    contains appendices\n#   8         appendix-<B>     upper letter or digits      contains subnumber\n#   9         <sub>            1*digit, BARE, only         child of appendix\n#                              directly after appendix-\n#   10        vol-<n>          1*digit (incl. yearbook     contains issue\n#                              years, Vol. 2020)\n#   11        issue-<n>        1*digit, only after vol-    child of volume\n#\n# The number occupies every leading bare segment up to the first\n# marker, so a colon number (S-158:100) round-trips without escaping;\n# after the markers the only bare segment allowed is the appendix\n# subnumber in its own slot. Both the year qualifier and the volume are\n# marker-tagged so neither can collide with a colon-number segment (the\n# #637 hazard, kept under the positional scheme). Letters are\n# case-preserved: part-A and part-a are distinct documents.\n#\n# Legacy 2.0.x spellings remain decodable but are never emitted: the\n# bare a.b.c segment (edition), the dotted keys part./annex./suppl./\n# ap./appendix./vol./issue. and the single-letter y. year tag (whose\n# value decodes into the volume — the serial-locator unification).\n#\n# Edition 2: ruby#400's capture-flatten keeps text captures over\n# reference-built rules as the matched text, so the v2 tree is the v1\n# tree plus named leaves for non-captured structure.\n\ngrammar PubidIho version \"0.2.0\" edition 2 {\n  digit = %x30-39\n  upper = %x41-5A\n  lower = %x61-7A\n  letter = upper / lower\n  space = \" \"\n  dash = \"-\"\n  dot = \".\"\n\n  series = (\"S\" / \"P\" / \"M\" / \"B\" / \"C\") as type\n  number_suffix = (\":\" 1*digit)\n  number = (1*digit [number_suffix]) as number\n  # The compact part face, hyphenated onto the code: S-5-B (lettered),\n  # S-100-1 (numbered) and S-158-S-102 (series reference) — the dash\n  # replaces the old bare-glued suffix, so a number like S-1001 stays a\n  # whole number (the dash is what makes the part unambiguous). The\n  # dash is an inlined literal: a named dash ref here collides with the\n  # sequence's own dash node in the edition-2 tree.\n  compact_part = \"-\" (((\"S\" / \"P\" / \"M\" / \"B\" / \"C\") dash (1*digit)) / (1*digit [*letter]) / upper) as part\n  # LEGACY glued lettered bases (S-5A, S-5B, S-8A, S-8B in the corpus):\n  # parse-only aliases, never rendered. Kept because the records exist;\n  # the owner rules later whether to reject them.\n  glued = upper as part\n\n  # The official edition is the dotted x.y.z; \"v1\"/\"v5.1\" is the S-100\n  # shorthand (parse-only, the builder pads to x.y.0).\n  edition = space (1*digit dot 1*digit dot 1*digit) as edition\n  v_edition = space \"v\" ((1*digit) [\".\" (1*digit)]) as edition_shorthand\n  # The with-year qualifier on standards: a parenthesized year beside an\n  # edition. This is the ONLY base-level year capture — periodical\n  # years are volumes (the serial-locator unification).\n  year_qualifier = space \"(\" ((\"19\" / \"20\") 2*digit) as year \")\"\n\n  # The series-reference part value: a check standard applied to\n  # another IHO series (S-158 checks S-102). Ordered FIRST so \"Part\n  # S-102\" takes the series-reference branch, not the lone letter.\n  part_series_ref = ((\"S\" / \"P\" / \"M\" / \"B\" / \"C\") dash (1*digit))\n  part_value = (part_series_ref / (1*digit [*letter]) / upper) as part\n\n  # Component-edition duality: each independently-publishable component\n  # may carry its own edition (+ year qualifier), mutually exclusive\n  # with the base edition context. The captures are position-scoped\n  # (<kind>_edition / <kind>_year) so the model knows which component\n  # the edition belongs to and the URN attaches ed- to the node it\n  # follows.\n  part = space \"Part\" space part_value [part_dated]\n  part_dated = {\n    part_edition_rule\n    [part_year_rule]\n  }\n  part_edition_rule = space (1*digit dot 1*digit dot 1*digit) as part_edition\n  part_year_rule = space \"(\" ((\"19\" / \"20\") 2*digit) as part_year \")\"\n\n  supplement = space (\"Suppl\" / \"Sup\") space (1*digit) as supplement [supplement_dated]\n  supplement_dated = {\n    supplement_edition_rule\n    [supplement_year_rule]\n  }\n  supplement_edition_rule = space (1*digit dot 1*digit dot 1*digit) as supplement_edition\n  supplement_year_rule = space \"(\" ((\"19\" / \"20\") 2*digit) as supplement_year \")\"\n\n  annex = space \"Annex\" space upper as annex [annex_dated]\n  annex_dated = {\n    annex_edition_rule\n    [annex_year_rule]\n  }\n  annex_edition_rule = space (1*digit dot 1*digit dot 1*digit) as annex_edition\n  annex_year_rule = space \"(\" ((\"19\" / \"20\") 2*digit) as annex_year \")\"\n\n  appendix_value = (upper / (1*digit)) as appendix\n  appendix_subnumber = dash (1*digit) as appendix_subnumber\n  appendix = space (\"Appendix\" / \"App\" / \"Ap.\") space appendix_value [appendix_subnumber] [appendix_dated]\n  appendix_dated = {\n    appendix_edition_rule\n    [appendix_year_rule]\n  }\n  appendix_edition_rule = space (1*digit dot 1*digit dot 1*digit) as appendix_edition\n  appendix_year_rule = space \"(\" ((\"19\" / \"20\") 2*digit) as appendix_year \")\"\n\n  volume = space \"Vol.\" space (1*digit) as volume [volume_issue]\n  volume_issue = (space \"Issue\" space (1*digit) as issue) / (space \"(\" (1*digit) as issue \")\")\n  # The volume's short face — the slash chain (\"IHO P-1/21\",\n  # \"IHO P-5/2020\"). The slash no longer joins the number.\n  volume_short = \"/\" ((1*digit) as volume) [volume_dated]\n  # LEGACY bare year (\"IHO P-5 2024\"): the yearbook year IS a volume,\n  # so a bare year binds INTO the volume component. Parse-only alias;\n  # the canonical print is \"Vol. N\".\n  volume_bare_year = space ((\"19\" / \"20\") 2*digit) as volume\n  # The volume's own edition (+ year), shared by the Vol. and slash\n  # forms.\n  volume_dated = {\n    volume_edition_rule\n    [volume_year_rule]\n  }\n  volume_edition_rule = space (1*digit dot 1*digit dot 1*digit) as volume_edition\n  volume_year_rule = space \"(\" ((\"19\" / \"20\") 2*digit) as volume_year \")\"\n\n  # The edition slot accepts the dotted form or the v-shorthand; the\n  # with-year qualifier may sit right after it.\n  dated = {\n    (edition / v_edition)\n    [year_qualifier]\n  }\n\n  # The serial tail picks exactly one discriminator: the long volume\n  # (with its optional issue) or the legacy bare year — both bind the\n  # volume component, and both may carry the volume's own edition.\n  serial = {\n    (volume / volume_bare_year)\n    [volume_dated]\n  }\n\n  identifier = {\n    [(\"IHO\" space)]\n    series\n    dash\n    number\n    [compact_part]\n    [glued]\n    [volume_short]\n    [dated]\n    [supplement]\n    [part]\n    [annex]\n    [appendix]\n    [serial]\n    [year_qualifier]\n  }\n\n  entry identifier: identifier\n\n  test {\n    accept \"S-5\"\n    accept \"IHO S-5 Appendix 2\"\n    accept \"IHO B-12 3.0.0\"\n    accept \"IHO P-5 2024\"\n    accept \"P-5 2024\"\n    accept \"IHO P-5 Vol. 2024\"\n    accept \"IHO P-5/2024\"\n    accept \"IHO B-7 Vol. 2023\"\n    accept \"IHO P-1 Vol. 30\"\n    accept \"IHO P-1 Vol. 30 (2)\"\n    accept \"IHO P-1 Vol. 30 Issue 2\"\n    accept \"IHO P-1/21\"\n    accept \"IHO P-1/21 1.0.0\"\n    accept \"IHO S-100 5.0.0 Part 2\"\n    accept \"IHO S-98 1.0.0 Part A\"\n    accept \"IHO S-65 1.1.0 Annex A\"\n    accept \"IHO S-122 1.0.0 Appendix D-2\"\n    accept \"IHO S-52 4.0.0 Appendix 1\"\n    accept \"IHO M-2 Sup 1\"\n    accept \"IHO M-2 Suppl 6\"\n    accept \"IHO S-66 2.0.0 Sup 4\"\n    accept \"IHO S-5-B\"\n    accept \"IHO S-100-1\"\n    accept \"IHO S-100-1 1.0.0\"\n    accept \"IHO P-6-3 1.0.0\"\n    accept \"IHO S-5A\"\n    accept \"IHO S-5A 1.0.2\"\n    accept \"IHO S-5 1.0.2 Part A\"\n    accept \"IHO S-100 5.0.0 Part 2 (2024)\"\n    accept \"IHO S-100 v5.1\"\n    accept \"IHO S-100 v1\"\n    accept \"IHO S-100 1.0.0 (2024) Part A\"\n    accept \"IHO S-53 Ap. 1 1.0.0\"\n    accept \"IHO S-98 Part A 1.0.0\"\n    accept \"IHO S-158:100 1.0.0\"\n    accept \"IHO S-158:100 Part 2 1.0.0\"\n    accept \"IHO S-1001\"\n    accept \"IHO S-158 Part S-102 0.2.0\"\n    accept \"IHO S-158-S-102 0.2.0\"\n    accept \"IHO P-6 1.0.0 Vol. 2\"\n    accept \"IHO P-6 Vol. 2 1.0.1\"\n    accept \"IHO S-98 1.0.0 Annex A\"\n    accept \"IHO S-100 5.0.0 Sup 1 2.0.0\"\n    reject \"nonsense\"\n    reject \"IHO B-12 3.0\"\n    reject \"IHO P-5 1850\"\n  }\n\n  bindings identifier {\n    type -> type (string)\n    number -> number (string)\n    part -> part (string)\n    part_edition -> part_edition (string)\n    part_year -> part_year (string)\n    annex -> annex (string)\n    annex_edition -> annex_edition (string)\n    annex_year -> annex_year (string)\n    appendix -> appendix (string)\n    appendix_subnumber -> appendix_subnumber (string)\n    appendix_edition -> appendix_edition (string)\n    appendix_year -> appendix_year (string)\n    supplement -> supplement (string)\n    supplement_edition -> supplement_edition (string)\n    supplement_year -> supplement_year (string)\n    edition -> edition (string)\n    edition_shorthand -> edition_shorthand (string)\n    year -> year (string)\n    volume -> volume (string)\n    volume_edition -> volume_edition (string)\n    volume_year -> volume_year (string)\n    issue -> issue (string)\n  }\n}\n","source_hash":"66d50de135e5c416bfe003de604effff57ed3b556a7126262c449b5c850995ac","unicode_tables":"onigmo (Ruby 3.4.8)","compiler_version":"1.3.126","edition":2,"semantics_hash":"sha256:711b011976f08ffc691672fafa41f9b60e3f6024a2608451043836fd6d05eff0","checksum":"sha256:15324490896b11703cb63893072ed77fbc43f43e47dd166ae8ddb235e3c2202e"}

data/data/parg/iho.parg

@@ -0,0 +1,358 @@
+# Port of lib/pubid/iho/parser.rb — IHO identifiers: letter series
+# (S/P/M/B/C), a number with an optional suffix, and the full component
+# tail (edition, supplement, part, annex, appendix + subnumber, volume,
+# issue, year qualifier).
+#
+# == Component model (owner rulings, 2026-11-03)
+#
+# Every component below is a first-class semantic component: its own
+# named capture, its own typed binding, independently addressable in
+# the model, URN-encodable and matchable — never a regex/string suffix.
+#
+#   component    face                capture             binding type
+#   edition      x.y.z (bare)        edition             string
+#   edition      v1 / v5.1 (alias)   edition_shorthand   string (parse-only;
+#                                                        the builder pads to
+#                                                        x.y.0 — official IHO
+#                                                        edition is dotted
+#                                                        x.y.z WITHOUT a year)
+#   supplement   Sup N (Suppl N)     supplement          string
+#   part         Part X / Part S-102 part                string (letter,
+#                                                        number, or SERIES
+#                                                        REFERENCE)
+#   part         -X / -S-102 (short) part                string (hyphenated)
+#   annex        Annex A             annex               string
+#   appendix     Appendix B          appendix            string
+#   appendix     Appendix D-2        appendix_subnumber  string (the -2)
+#   volume       Vol. N              volume              string
+#   volume       /N (short)          volume              string (the slash
+#                                                        chain, P-1/21 or
+#                                                        P-5/2020)
+#   volume       N (bare, legacy)    volume              string (the yearbook
+#                                                        year IS a volume —
+#                                                        one serial-locator
+#                                                        component)
+#   issue        (N) / Issue N       issue               string
+#   year         (2024)              year                string (the with-year
+#                                                        qualifier on
+#                                                        standards; NOT a
+#                                                        serial locator)
+#
+# == Component-edition duality (owner ruling: "this can happen with any
+#    independently publishable artifacts")
+#
+# Supplement, part, annex, appendix and volume can be published on
+# their own publication cycle, so EACH carries an optional
+# `<kind>_edition` (+ `<kind>_year` qualifier) of its own, mutually
+# exclusive with the base edition context:
+#
+#   within-edition:        IHO P-6 1.0.0 Vol. 2       (the volume rides
+#                                                   the base's edition)
+#   separately-published:  IHO P-6 Vol. 2 1.0.1       (the volume carries
+#                          IHO S-98 Part A 1.0.0       its own edition;
+#                          IHO S-158 Part S-102 0.2.0  the base is
+#                                                      cited edition-less)
+#
+# In the URN the ed- segment attaches to the node it follows, so the
+# same positional slot records both modes.
+#
+# The part has a COMPACT face, hyphenated onto the code — `IHO S-5-B`
+# (lettered part), `IHO S-100-1` (numbered part), `IHO S-158-S-102`
+# (series-reference part) — which both parses and renders; the
+# canonical expanded face stays `IHO S-100 x.y.z Part 1`. Gluing a part
+# onto the code without a separator (S-5A) is DISALLOWED as a form: it
+# cannot extend to numbered parts without ambiguity (S-1001 = series
+# 1001 vs series 100 part 1). The four lettered bases the corpus
+# records (S-5A, S-5B, S-8A, S-8B) are LEGACY data spellings: they
+# still parse as aliases (S-5A == S-5 Part A) but are never rendered;
+# the owner rules later whether to reject them outright.
+#
+# Series-reference parts: a check standard applied to another IHO
+# series cites the applied series as its part — `IHO S-158 0.2.0 Part
+# S-102` (the wild glued `S-158-102` spelling is a legacy alias whose
+# normalization to Part S-102 needs an IHO series table; the syntax
+# alone cannot tell it from S-100-1 = Part 1, so it currently parses
+# as the plain number part).
+#
+# Two main syntaxes per the owner ruling: `IHO S-100 1.0.0` (dated =
+# edition-specific) and `IHO S-100` (undated = edition-non-specific).
+# A year beside an edition is the with-year variant qualifier
+# (`IHO S-100 1.0.0 Part X (2024)`), never a year-keyed docidentifier —
+# year-keyed docidentifiers for edition-keyed products are wrong. The
+# continuously-updated series have ONE serial locator, the volume:
+# P-1 and P-6 are volume-keyed (`IHO P-1 Vol. 30 (1)`), and the
+# yearbook year IS a volume (`IHO P-5 Vol. 2020`) — the bare year
+# (`IHO P-5 2020`) and all year-faced forms are parse-only legacy
+# aliases that bind into the volume component, never rendered.
+#
+# Aliases: "Suppl" (canonical face Sup, the M-2 spelling — why abbreviate
+# by two letters when Annex and Appendix stay full-length), "App"/"Ap."
+# (canonical face Appendix), the hyphenated compact part face (S-5-B ==
+# S-5 Part B, S-100-1 == S-100 Part 1), the legacy glued lettered bases
+# (S-5A, parse-only), "S-100 v1..v5.1" (edition shorthand), "Issue N"
+# (canonical (N)), the bare year (canonical Vol. N).
+#
+# == URN segment grammar (positional, containment-ordered)
+#
+# The URN mirrors the containment tree, one semantic atom per segment:
+# Part contains Annexes; Annex contains Appendices; a D-2 subnumber is
+# a child atom of Appendix D. No key.value concatenations — every
+# non-number component is a marker-prefixed segment whose marker is the
+# lowercased human-face token (edition follows ISO's ed- precedent):
+#
+#   urn:iho:<type>:<number>[:ed-<x.y.z>][:year-<yyyy>]
+#     [:sup-<n>[:ed-<x.y.z>][:year-<yyyy>]]
+#     [:part-<X>[:ed-<x.y.z>][:year-<yyyy>]]
+#     [:annex-<A>[...]]
+#     [:appendix-<B>[:<sub>][...]]
+#     [:vol-<n>[:issue-<n>][...]]
+#     [:year-<yyyy>]
+#
+#   position  segment          value vocabulary            containment
+#   --------  ---------------  --------------------------  ------------------
+#   1         <type>           s / p / m / b / c           namespace root
+#   2         <number>         digits + : suffix; may      document code
+#                              span bare segments until
+#                              the first marker
+#   3         ed-<x.y.z>       dotted a.b.c                edition qualifier;
+#   4         year-<yyyy>      19xx/20xx                   ATTACHES TO THE
+#                                                      NODE IT FOLLOWS: the
+#                                                      base (no component
+#                                                      before it) or the
+#                                                      component whose
+#                                                      segment precedes
+#   5         sup-<n>          1*digit                     wraps the base
+#   6         part-<X>         letter (case kept),         contains annexes
+#                              digits [*letter], or a
+#                              series reference
+#                              [SPMBC]-<digits>
+#   7         annex-<A>        upper letter (case kept)    contains appendices
+#   8         appendix-<B>     upper letter or digits      contains subnumber
+#   9         <sub>            1*digit, BARE, only         child of appendix
+#                              directly after appendix-
+#   10        vol-<n>          1*digit (incl. yearbook     contains issue
+#                              years, Vol. 2020)
+#   11        issue-<n>        1*digit, only after vol-    child of volume
+#
+# The number occupies every leading bare segment up to the first
+# marker, so a colon number (S-158:100) round-trips without escaping;
+# after the markers the only bare segment allowed is the appendix
+# subnumber in its own slot. Both the year qualifier and the volume are
+# marker-tagged so neither can collide with a colon-number segment (the
+# #637 hazard, kept under the positional scheme). Letters are
+# case-preserved: part-A and part-a are distinct documents.
+#
+# Legacy 2.0.x spellings remain decodable but are never emitted: the
+# bare a.b.c segment (edition), the dotted keys part./annex./suppl./
+# ap./appendix./vol./issue. and the single-letter y. year tag (whose
+# value decodes into the volume — the serial-locator unification).
+#
+# Edition 2: ruby#400's capture-flatten keeps text captures over
+# reference-built rules as the matched text, so the v2 tree is the v1
+# tree plus named leaves for non-captured structure.
+
+grammar PubidIho version "0.2.0" edition 2 {
+  digit = %x30-39
+  upper = %x41-5A
+  lower = %x61-7A
+  letter = upper / lower
+  space = " "
+  dash = "-"
+  dot = "."
+
+  series = ("S" / "P" / "M" / "B" / "C") as type
+  number_suffix = (":" 1*digit)
+  number = (1*digit [number_suffix]) as number
+  # The compact part face, hyphenated onto the code: S-5-B (lettered),
+  # S-100-1 (numbered) and S-158-S-102 (series reference) — the dash
+  # replaces the old bare-glued suffix, so a number like S-1001 stays a
+  # whole number (the dash is what makes the part unambiguous). The
+  # dash is an inlined literal: a named dash ref here collides with the
+  # sequence's own dash node in the edition-2 tree.
+  compact_part = "-" ((("S" / "P" / "M" / "B" / "C") dash (1*digit)) / (1*digit [*letter]) / upper) as part
+  # LEGACY glued lettered bases (S-5A, S-5B, S-8A, S-8B in the corpus):
+  # parse-only aliases, never rendered. Kept because the records exist;
+  # the owner rules later whether to reject them.
+  glued = upper as part
+
+  # The official edition is the dotted x.y.z; "v1"/"v5.1" is the S-100
+  # shorthand (parse-only, the builder pads to x.y.0).
+  edition = space (1*digit dot 1*digit dot 1*digit) as edition
+  v_edition = space "v" ((1*digit) ["." (1*digit)]) as edition_shorthand
+  # The with-year qualifier on standards: a parenthesized year beside an
+  # edition. This is the ONLY base-level year capture — periodical
+  # years are volumes (the serial-locator unification).
+  year_qualifier = space "(" (("19" / "20") 2*digit) as year ")"
+
+  # The series-reference part value: a check standard applied to
+  # another IHO series (S-158 checks S-102). Ordered FIRST so "Part
+  # S-102" takes the series-reference branch, not the lone letter.
+  part_series_ref = (("S" / "P" / "M" / "B" / "C") dash (1*digit))
+  part_value = (part_series_ref / (1*digit [*letter]) / upper) as part
+
+  # Component-edition duality: each independently-publishable component
+  # may carry its own edition (+ year qualifier), mutually exclusive
+  # with the base edition context. The captures are position-scoped
+  # (<kind>_edition / <kind>_year) so the model knows which component
+  # the edition belongs to and the URN attaches ed- to the node it
+  # follows.
+  part = space "Part" space part_value [part_dated]
+  part_dated = {
+    part_edition_rule
+    [part_year_rule]
+  }
+  part_edition_rule = space (1*digit dot 1*digit dot 1*digit) as part_edition
+  part_year_rule = space "(" (("19" / "20") 2*digit) as part_year ")"
+
+  supplement = space ("Suppl" / "Sup") space (1*digit) as supplement [supplement_dated]
+  supplement_dated = {
+    supplement_edition_rule
+    [supplement_year_rule]
+  }
+  supplement_edition_rule = space (1*digit dot 1*digit dot 1*digit) as supplement_edition
+  supplement_year_rule = space "(" (("19" / "20") 2*digit) as supplement_year ")"
+
+  annex = space "Annex" space upper as annex [annex_dated]
+  annex_dated = {
+    annex_edition_rule
+    [annex_year_rule]
+  }
+  annex_edition_rule = space (1*digit dot 1*digit dot 1*digit) as annex_edition
+  annex_year_rule = space "(" (("19" / "20") 2*digit) as annex_year ")"
+
+  appendix_value = (upper / (1*digit)) as appendix
+  appendix_subnumber = dash (1*digit) as appendix_subnumber
+  appendix = space ("Appendix" / "App" / "Ap.") space appendix_value [appendix_subnumber] [appendix_dated]
+  appendix_dated = {
+    appendix_edition_rule
+    [appendix_year_rule]
+  }
+  appendix_edition_rule = space (1*digit dot 1*digit dot 1*digit) as appendix_edition
+  appendix_year_rule = space "(" (("19" / "20") 2*digit) as appendix_year ")"
+
+  volume = space "Vol." space (1*digit) as volume [volume_issue]
+  volume_issue = (space "Issue" space (1*digit) as issue) / (space "(" (1*digit) as issue ")")
+  # The volume's short face — the slash chain ("IHO P-1/21",
+  # "IHO P-5/2020"). The slash no longer joins the number.
+  volume_short = "/" ((1*digit) as volume) [volume_dated]
+  # LEGACY bare year ("IHO P-5 2024"): the yearbook year IS a volume,
+  # so a bare year binds INTO the volume component. Parse-only alias;
+  # the canonical print is "Vol. N".
+  volume_bare_year = space (("19" / "20") 2*digit) as volume
+  # The volume's own edition (+ year), shared by the Vol. and slash
+  # forms.
+  volume_dated = {
+    volume_edition_rule
+    [volume_year_rule]
+  }
+  volume_edition_rule = space (1*digit dot 1*digit dot 1*digit) as volume_edition
+  volume_year_rule = space "(" (("19" / "20") 2*digit) as volume_year ")"
+
+  # The edition slot accepts the dotted form or the v-shorthand; the
+  # with-year qualifier may sit right after it.
+  dated = {
+    (edition / v_edition)
+    [year_qualifier]
+  }
+
+  # The serial tail picks exactly one discriminator: the long volume
+  # (with its optional issue) or the legacy bare year — both bind the
+  # volume component, and both may carry the volume's own edition.
+  serial = {
+    (volume / volume_bare_year)
+    [volume_dated]
+  }
+
+  identifier = {
+    [("IHO" space)]
+    series
+    dash
+    number
+    [compact_part]
+    [glued]
+    [volume_short]
+    [dated]
+    [supplement]
+    [part]
+    [annex]
+    [appendix]
+    [serial]
+    [year_qualifier]
+  }
+
+  entry identifier: identifier
+
+  test {
+    accept "S-5"
+    accept "IHO S-5 Appendix 2"
+    accept "IHO B-12 3.0.0"
+    accept "IHO P-5 2024"
+    accept "P-5 2024"
+    accept "IHO P-5 Vol. 2024"
+    accept "IHO P-5/2024"
+    accept "IHO B-7 Vol. 2023"
+    accept "IHO P-1 Vol. 30"
+    accept "IHO P-1 Vol. 30 (2)"
+    accept "IHO P-1 Vol. 30 Issue 2"
+    accept "IHO P-1/21"
+    accept "IHO P-1/21 1.0.0"
+    accept "IHO S-100 5.0.0 Part 2"
+    accept "IHO S-98 1.0.0 Part A"
+    accept "IHO S-65 1.1.0 Annex A"
+    accept "IHO S-122 1.0.0 Appendix D-2"
+    accept "IHO S-52 4.0.0 Appendix 1"
+    accept "IHO M-2 Sup 1"
+    accept "IHO M-2 Suppl 6"
+    accept "IHO S-66 2.0.0 Sup 4"
+    accept "IHO S-5-B"
+    accept "IHO S-100-1"
+    accept "IHO S-100-1 1.0.0"
+    accept "IHO P-6-3 1.0.0"
+    accept "IHO S-5A"
+    accept "IHO S-5A 1.0.2"
+    accept "IHO S-5 1.0.2 Part A"
+    accept "IHO S-100 5.0.0 Part 2 (2024)"
+    accept "IHO S-100 v5.1"
+    accept "IHO S-100 v1"
+    accept "IHO S-100 1.0.0 (2024) Part A"
+    accept "IHO S-53 Ap. 1 1.0.0"
+    accept "IHO S-98 Part A 1.0.0"
+    accept "IHO S-158:100 1.0.0"
+    accept "IHO S-158:100 Part 2 1.0.0"
+    accept "IHO S-1001"
+    accept "IHO S-158 Part S-102 0.2.0"
+    accept "IHO S-158-S-102 0.2.0"
+    accept "IHO P-6 1.0.0 Vol. 2"
+    accept "IHO P-6 Vol. 2 1.0.1"
+    accept "IHO S-98 1.0.0 Annex A"
+    accept "IHO S-100 5.0.0 Sup 1 2.0.0"
+    reject "nonsense"
+    reject "IHO B-12 3.0"
+    reject "IHO P-5 1850"
+  }
+
+  bindings identifier {
+    type -> type (string)
+    number -> number (string)
+    part -> part (string)
+    part_edition -> part_edition (string)
+    part_year -> part_year (string)
+    annex -> annex (string)
+    annex_edition -> annex_edition (string)
+    annex_year -> annex_year (string)
+    appendix -> appendix (string)
+    appendix_subnumber -> appendix_subnumber (string)
+    appendix_edition -> appendix_edition (string)
+    appendix_year -> appendix_year (string)
+    supplement -> supplement (string)
+    supplement_edition -> supplement_edition (string)
+    supplement_year -> supplement_year (string)
+    edition -> edition (string)
+    edition_shorthand -> edition_shorthand (string)
+    year -> year (string)
+    volume -> volume (string)
+    volume_edition -> volume_edition (string)
+    volume_year -> volume_year (string)
+    issue -> issue (string)
+  }
+}