pubid 2.0.0.pre.alpha.13 → 2.0.0.pre.alpha.15

data/data/parg/tables/iec_typed_stages.yaml

@@ -0,0 +1,130 @@
+- abbr: "TRF"
+- abbr: "PWI Amd"
+- abbr: "NP Amd"
+- abbr: "ANW Amd"
+- abbr: "WD Amd"
+- abbr: "CDAM"
+- abbr: "DAM"
+- abbr: "FDAM"
+- abbr: "PRF Amd"
+- abbr: "Amd"
+- abbr: "AMD"
+- abbr: "PWI Cor"
+- abbr: "NP Cor"
+- abbr: "ANW Cor"
+- abbr: "WDCor"
+- abbr: "CDCor"
+- abbr: "DCOR"
+- abbr: "FDCOR"
+- abbr: "PRF Cor"
+- abbr: "Cor"
+- abbr: "COR"
+- abbr: "CS"
+- abbr: "CA"
+- abbr: "PWI Guide"
+- abbr: "NP Guide"
+- abbr: "ANW Guide"
+- abbr: "WD Guide"
+- abbr: "CD Guide"
+- abbr: "DGuide"
+- abbr: "FDGuide"
+- abbr: "PRF Guide"
+- abbr: "GUIDE"
+- abbr: "Guide"
+- abbr: "PWI"
+- abbr: "NWIP"
+- abbr: "BWG"
+- abbr: "AWIN"
+- abbr: "AMW"
+- abbr: "NP"
+- abbr: "PNW"
+- abbr: "ANW"
+- abbr: "WD"
+- abbr: "CD"
+- abbr: "2CD"
+- abbr: "3CD"
+- abbr: "4CD"
+- abbr: "5CD"
+- abbr: "6CD"
+- abbr: "7CD"
+- abbr: "8CD"
+- abbr: "9CD"
+- abbr: "ACD"
+- abbr: "A2CD"
+- abbr: "A3CD"
+- abbr: "A4CD"
+- abbr: "A5CD"
+- abbr: "A6CD"
+- abbr: "A7CD"
+- abbr: "A8CD"
+- abbr: "A9CD"
+- abbr: "CDM"
+- abbr: "CDV"
+- abbr: "ACDV"
+- abbr: "CCDV"
+- abbr: "CDVM"
+- abbr: "NCDV"
+- abbr: "FDIS"
+- abbr: "PRF"
+- abbr: "NFDIS"
+- abbr: "NADIS"
+- abbr: "RDISH"
+- abbr: "RFDIS"
+- abbr: "CFDIS"
+- abbr: "BPUB"
+- abbr: "PPUB"
+- abbr: "APUB"
+- abbr: "WPUB"
+- abbr: "DELPUB"
+- abbr: "RR"
+- abbr: "CAN"
+- abbr: "PWI ISH"
+- abbr: "NP ISH"
+- abbr: "ANW ISH"
+- abbr: "WD ISH"
+- abbr: "CDISH"
+- abbr: "DISH"
+- abbr: "ISH"
+- abbr: "OD"
+- abbr: "PWI PAS"
+- abbr: "NP PAS"
+- abbr: "ANW PAS"
+- abbr: "WD PAS"
+- abbr: "CDPAS"
+- abbr: "DPAS"
+- abbr: "PAS"
+- abbr: "Trend Report"
+- abbr: "PWI TR"
+- abbr: "NP TR"
+- abbr: "ANW TR"
+- abbr: "WD TR"
+- abbr: "CD TR"
+- abbr: "DTR"
+- abbr: "ADTR"
+- abbr: "CDTR"
+- abbr: "DTRM"
+- abbr: "NDTR"
+- abbr: "DTSM"
+- abbr: "TR"
+- abbr: "SRD"
+- abbr: "Technology Report"
+- abbr: "PWI TS"
+- abbr: "NP TS"
+- abbr: "ANW TS"
+- abbr: "WD TS"
+- abbr: "CD TS"
+- abbr: "DTS"
+- abbr: "ADTS"
+- abbr: "CDTS"
+- abbr: "NDTS"
+- abbr: "TS"
+- abbr: "White Paper"
+- abbr: "PWI Frag"
+- abbr: "NP Frag"
+- abbr: "ANW Frag"
+- abbr: "WD Frag"
+- abbr: "CDFRAG"
+- abbr: "DFRAG"
+- abbr: "FDFRAG"
+- abbr: "PRF Frag"
+- abbr: "FRAG"

data/data/parg/tables/iso_publishers.yaml

@@ -0,0 +1,4 @@
+- abbrev: "ISO"
+  name: "International Organization for Standardization"
+- abbrev: "IEC"
+  name: "International Electrotechnical Commission"

data/data/parg/tables/organizations.yaml

@@ -0,0 +1,12 @@
+- name: "ISO"
+- name: "IEC"
+- name: "IEEE"
+- name: "CIW"
+- name: "SAE"
+- name: "CIE"
+- name: "ASME"
+- name: "ASTM"
+- name: "OECD"
+- name: "HL7"
+- name: "CEI"
+- name: "UNDP"

data/data/parg/tables/tc_types.yaml

@@ -0,0 +1,42 @@
+- name: "TC"
+- name: "JTC"
+- name: "PC"
+- name: "IT"
+- name: "CAB"
+- name: "CASCO"
+- name: "COPOLCO"
+- name: "COUNCIL"
+- name: "CPSG"
+- name: "CS"
+- name: "DEVCO"
+- name: "GA"
+- name: "GAAB"
+- name: "INFCO"
+- name: "ITN"
+- name: "ISOlutions"
+- name: "REMCO"
+- name: "TMB"
+- name: "TMBG"
+- name: "WMO"
+- name: "DMT"
+- name: "JCG"
+- name: "SGPM"
+- name: "ATMG"
+- name: "CCCC"
+- name: "CCCC-TG"
+- name: "JDMT"
+- name: "JSAG"
+- name: "JSCTF-TF"
+- name: "JTCG"
+- name: "JTCG-TF"
+- name: "SAG_Acc"
+- name: "SAG_CRMI"
+- name: "SAG_CRMI_CG"
+- name: "SAG_ESG"
+- name: "SAG_ESG_CG"
+- name: "SAG_MRS"
+- name: "SAG_SF"
+- name: "SAG_SF_CG"
+- name: "SMCC"
+- name: "STMG"
+- name: "MENA_STAR"

data/data/parg/tables/typed_stages.yaml

@@ -0,0 +1,114 @@
+- abbr: "PWI TS"
+- abbr: "NP TS"
+- abbr: "AWI TS"
+- abbr: "WD TS"
+- abbr: "CDTS"
+- abbr: "CD TS"
+- abbr: "PDTS"
+- abbr: "DTS"
+- abbr: "FDTS"
+- abbr: "PRF TS"
+- abbr: "TS"
+- abbr: "PWI TTA"
+- abbr: "NP TTA"
+- abbr: "AWI TTA"
+- abbr: "WD TTA"
+- abbr: "CD TTA"
+- abbr: "DTTA"
+- abbr: "FDTTA"
+- abbr: "PRF TTA"
+- abbr: "TTA"
+- abbr: "NP DATA"
+- abbr: "AWI DATA"
+- abbr: "WD DATA"
+- abbr: "CD DATA"
+- abbr: "D DATA"
+- abbr: "PRF DATA"
+- abbr: "DATA"
+- abbr: "DIR"
+- abbr: "Directives Part"
+- abbr: "Directives, Part"
+- abbr: "Directives,"
+- abbr: "Directives"
+- abbr: "DIR SUP"
+- abbr: "SUP"
+- abbr: "Supplement"
+- abbr: "PWI Guide"
+- abbr: "NP Guide"
+- abbr: "NP GUIDE"
+- abbr: "AWI Guide"
+- abbr: "AWI GUIDE"
+- abbr: "WD Guide"
+- abbr: "WD GUIDE"
+- abbr: "CD Guide"
+- abbr: "CD GUIDE"
+- abbr: "DGuide"
+- abbr: "DGUIDE"
+- abbr: "FDGuide"
+- abbr: "FD Guide"
+- abbr: "FD GUIDE"
+- abbr: "PRF Guide"
+- abbr: "PRF GUIDE"
+- abbr: "Guide"
+- abbr: "GUIDE"
+- abbr: "DP"
+- abbr: "PWI"
+- abbr: "NP"
+- abbr: "NWIP"
+- abbr: "AWI"
+- abbr: "WD"
+- abbr: "WDS"
+- abbr: "preCD"
+- abbr: "PreCD"
+- abbr: "CD"
+- abbr: "DIS"
+- abbr: "FPD"
+- abbr: "FCD"
+- abbr: "FDIS"
+- abbr: "PRF"
+- abbr: "Fpr"
+- abbr: "IS"
+- abbr: "WDR"
+- abbr: "WDA"
+- abbr: "WDAR"
+- abbr: "PWI ISP"
+- abbr: "NP ISP"
+- abbr: "AWI ISP"
+- abbr: "WD ISP"
+- abbr: "CD ISP"
+- abbr: "DISP"
+- abbr: "DIS ISP"
+- abbr: "FDISP"
+- abbr: "FDIS ISP"
+- abbr: "PRF ISP"
+- abbr: "ISP"
+- abbr: "PWI IWA"
+- abbr: "NP IWA"
+- abbr: "AWI IWA"
+- abbr: "WD IWA"
+- abbr: "CD IWA"
+- abbr: "DIWA"
+- abbr: "PRF IWA"
+- abbr: "IWA"
+- abbr: "PWI PAS"
+- abbr: "NP PAS"
+- abbr: "AWI PAS"
+- abbr: "WD PAS"
+- abbr: "CD PAS"
+- abbr: "DPAS"
+- abbr: "FDPAS"
+- abbr: "PRF PAS"
+- abbr: "PAS"
+- abbr: "R"
+- abbr: "PWI TR"
+- abbr: "NP TR"
+- abbr: "AWI TR"
+- abbr: "WD TR"
+- abbr: "CD TR"
+- abbr: "PDTR"
+- abbr: "DTR"
+- abbr: "DIS TR"
+- abbr: "FDTR"
+- abbr: "FDIS TR"
+- abbr: "PRF TR"
+- abbr: "TR"

data/data/parg/tables/typed_stages_supplements.yaml

@@ -0,0 +1,64 @@
+- abbr: "PWI Suppl"
+- abbr: "NP Suppl"
+- abbr: "AWI Suppl"
+- abbr: "WD Suppl"
+- abbr: "CD Suppl"
+- abbr: "DSuppl"
+- abbr: "DIS Suppl"
+- abbr: "FDSuppl"
+- abbr: "FDIS Suppl"
+- abbr: "PRF Suppl"
+- abbr: "Suppl"
+- abbr: "Suppl."
+- abbr: "PWI Add"
+- abbr: "NP Add"
+- abbr: "AWI Add"
+- abbr: "WD Add"
+- abbr: "CD Add"
+- abbr: "DAD"
+- abbr: "DAdd"
+- abbr: "D ADD"
+- abbr: "Dad"
+- abbr: "DIS Add"
+- abbr: "FDAD"
+- abbr: "FDAdd"
+- abbr: "FD ADD"
+- abbr: "FDad"
+- abbr: "FDIS Add"
+- abbr: "Add"
+- abbr: "ADD"
+- abbr: "Add."
+- abbr: "Addendum"
+- abbr: "PWI Amd"
+- abbr: "NP Amd"
+- abbr: "AWI Amd"
+- abbr: "WD Amd"
+- abbr: "CD Amd"
+- abbr: "PDAM"
+- abbr: "DAM"
+- abbr: "DAmd"
+- abbr: "FDAM"
+- abbr: "FDAmd"
+- abbr: "FPDAM"
+- abbr: "PRF Amd"
+- abbr: "Amd"
+- abbr: "AMD"
+- abbr: "Amd."
+- abbr: "PWI Cor"
+- abbr: "NP Cor"
+- abbr: "AWI Cor"
+- abbr: "WD Cor"
+- abbr: "CD Cor"
+- abbr: "pDCOR"
+- abbr: "DCor"
+- abbr: "DCOR"
+- abbr: "DIS Cor"
+- abbr: "FDCor"
+- abbr: "FDCOR"
+- abbr: "FCOR"
+- abbr: "FDIS Cor"
+- abbr: "PRF Cor"
+- abbr: "Cor"
+- abbr: "COR"
+- abbr: "Cor."
+- abbr: "Ext"

data/data/parg/tables/wg_types.yaml

@@ -0,0 +1,21 @@
+- name: "AG"
+- name: "AhG"
+- name: "WG"
+- name: "JWG"
+- name: "QC"
+- name: "TF"
+- name: "PPC"
+- name: "CAG"
+- name: "CSC"
+- name: "ITSAG"
+- name: "CSC/FIN"
+- name: "CSC/NOM"
+- name: "CSC/OVE"
+- name: "CSC/SP"
+- name: "SF"
+- name: "ITSG"
+- name: "JAG"
+- name: "JCTF"
+- name: "JSG"
+- name: "JTAG"
+- name: "JTG"

data/data/parg/tgpp.json

@@ -0,0 +1 @@
+{"version":"0.1.0","grammar":"PubidTgpp","shape":"parsanol-tree/v2","binding_version":1,"entries":{"identifier":{"root":"identifier","grammar":{"atoms":[{"Str":{"pattern":"3GPP "}},{"Repetition":{"atom":0,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":6}},{"Str":{"pattern":"TR"}},{"Str":{"pattern":"TS"}},{"Alternative":{"atoms":[3,4]}},{"Named":{"name":"type","atom":5}},{"Entity":{"atom":8}},{"Str":{"pattern":" "}},{"Entity":{"atom":17}},{"Entity":{"atom":11}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":10,"min":1,"max":null,"tag":"Repetition"}},{"Str":{"pattern":"."}},{"Entity":{"atom":11}},{"Repetition":{"atom":14,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[12,13,15]}},{"Named":{"name":"number","atom":16}},{"Entity":{"atom":24}},{"Entity":{"atom":22}},{"Re":{"pattern":"[\\x41-\\x5a]"}},{"Re":{"pattern":"[\\x61-\\x7a]"}},{"Alternative":{"atoms":[20,21]}},{"Repetition":{"atom":19,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"suffix","atom":23}},{"Repetition":{"atom":18,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":34}},{"Entity":{"atom":32}},{"Str":{"pattern":"-"}},{"Entity":{"atom":11}},{"Repetition":{"atom":29,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"part","atom":30}},{"Sequence":{"atoms":[28,31]}},{"Repetition":{"atom":27,"min":0,"max":null,"tag":"Repetition"}},{"Named":{"name":"parts","atom":33}},{"Entity":{"atom":36}},{"Str":{"pattern":":"}},{"Entity":{"atom":60}},{"Entity":{"atom":47}},{"Entity":{"atom":11}},{"Repetition":{"atom":39,"min":1,"max":null,"tag":"Repetition"}},{"Str":{"pattern":"."}},{"Entity":{"atom":11}},{"Repetition":{"atom":42,"min":1,"max":null,"tag":"Repetition"}},{"Str":{"pattern":"."}},{"Entity":{"atom":11}},{"Repetition":{"atom":45,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[40,41,43,44,46]}},{"Entity":{"atom":49}},{"Re":{"pattern":"[\\x01-\\u{10ffff}]"}},{"Lookahead":{"atom":48,"positive":false}},{"Sequence":{"atoms":[38,50]}},{"Lookahead":{"atom":51,"positive":false}},{"Entity":{"atom":57}},{"Re":{"pattern":"[\\x01-\\x2e]"}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Re":{"pattern":"[\\x3b-\\u{10ffff}]"}},{"Alternative":{"atoms":[54,55,56]}},{"Repetition":{"atom":53,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"release","atom":58}},{"Sequence":{"atoms":[52,59]}},{"Sequence":{"atoms":[35,37]}},{"Repetition":{"atom":61,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":64}},{"Str":{"pattern":"/"}},{"Entity":{"atom":67}},{"Entity":{"atom":47}},{"Named":{"name":"version","atom":66}},{"Sequence":{"atoms":[63,65]}},{"Repetition":{"atom":68,"min":0,"max":1,"tag":"Maybe"}},{"Sequence":{"atoms":[1,2,7,9,25,26,62,69]}}],"root":70},"bindings":[]}},"preprocess":{},"tables":{},"lint":{"order_warnings":["rule release_char: branches 1 and 3 are order-dependent (first set not statically known)","rule release_char: branches 2 and 3 are order-dependent (first set not statically known)"]},"default_entry":"identifier","render":{},"derive":{},"tests":[{"entry":"identifier","kind":"accept","input":"3GPP TS 21.101","expect":{}},{"entry":"identifier","kind":"accept","input":"TS 25.999","expect":{}},{"entry":"identifier","kind":"reject","input":"nonsense","expect":{}}],"docs":{},"source":"# Port of lib/pubid/tgpp/parser.rb:\n# [3GPP ]<TR|TS> <NN.NNN>[suffix][-part…][:<release>][/<version>]\n# The release excludes \"/\" and \":\" (match[\"^/:\"]), byte-wise here; the\n# mistyped-version guard (!version…!any) is ported literally.\n\ngrammar PubidTgpp version \"0.1.0\" {\n  release_char = %x01-2E / %x30-39 / %x3B-10FFFF\n  any_char = %x01-10FFFF\n  type = (\"TR\" / \"TS\") as type\n  number = (1*digit \".\" 1*digit) as number\n  suffix = (1*letter) as suffix\n  part = \"-\" (1*digit) as part\n  parts = (*part) as parts\n  version_core = 1*digit \".\" 1*digit \".\" 1*digit\n  release = !(version_core !any_char) (1*release_char) as release\n  version = version_core as version\n  identifier = [\"3GPP \"] type space number [suffix] parts [(colon release)] [(slash version)]\n  letter = %x41-5A / %x61-7A\n  digit = %x30-39\n  space = \" \"\n  colon = \":\"\n  slash = \"/\"\n  entry identifier: identifier\n\n  test {\n    accept \"3GPP TS 21.101\"\n    accept \"TS 25.999\"\n    reject \"nonsense\"\n  }\n}\n","checksum":"sha256:6446a79c9b880d0cc0565fdd9bdb13a665b8d6b5bf5b91c055404ddab778c0c9"}

data/data/parg/un.json

@@ -0,0 +1 @@
+{"version":"0.1.0","grammar":"PubidUn","shape":"parsanol-tree/v2","binding_version":1,"entries":{"identifier":{"root":"identifier","grammar":{"atoms":[{"Str":{"pattern":"UN "}},{"Repetition":{"atom":0,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":9}},{"Entity":{"atom":7}},{"Re":{"pattern":"[\\x41-\\x5a]"}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Re":{"pattern":"[.]"}},{"Alternative":{"atoms":[4,5,6]}},{"Repetition":{"atom":3,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"token","atom":8}},{"Entity":{"atom":11}},{"Str":{"pattern":"/"}},{"Entity":{"atom":9}},{"Sequence":{"atoms":[10,12]}},{"Repetition":{"atom":13,"min":1,"max":null,"tag":"Repetition"}},{"Sequence":{"atoms":[1,2,14]}}],"root":15},"bindings":[]}},"preprocess":{},"tables":{},"lint":{"order_warnings":[]},"default_entry":"identifier","render":{},"derive":{},"tests":[{"entry":"identifier","kind":"accept","input":"UN/CEFACT/TBG14","expect":{}},{"entry":"identifier","kind":"accept","input":"CEFACT/TBG14","expect":{}},{"entry":"identifier","kind":"reject","input":"nonsense","expect":{}}],"docs":{},"source":"# Port of lib/pubid/un/parser.rb. `token` matches [A-Z0-9.] runs.\n\ngrammar PubidUn version \"0.1.0\" {\n  token_char = %x41-5A / %x30-39 / %x2E\n  token = (1*token_char) as token\n  identifier = [\"UN \"] token 1*(slash token)\n  slash = \"/\"\n  entry identifier: identifier\n\n  test {\n    accept \"UN/CEFACT/TBG14\"\n    accept \"CEFACT/TBG14\"\n    reject \"nonsense\"\n  }\n}\n","checksum":"sha256:1ca1befe71541f581fe67befd3499e399c3a8463c17dcc641e00dba1858a4bbf"}

data/data/parg/w3c.json

@@ -0,0 +1 @@
+{"version":"0.1.0","grammar":"PubidW3c","shape":"parsanol-tree/v2","binding_version":1,"entries":{"identifier":{"root":"identifier","grammar":{"atoms":[{"Str":{"pattern":"W3C "}},{"Entity":{"atom":16}},{"Entity":{"atom":13}},{"Str":{"pattern":"DNOTE"}},{"Str":{"pattern":"NOTE"}},{"Str":{"pattern":"WD"}},{"Str":{"pattern":"CRD"}},{"Str":{"pattern":"CR"}},{"Str":{"pattern":"REC"}},{"Str":{"pattern":"PER"}},{"Str":{"pattern":"PR"}},{"Str":{"pattern":"SPSD"}},{"Str":{"pattern":"OBSL"}},{"Alternative":{"atoms":[3,4,5,6,7,8,9,10,11,12]}},{"Named":{"name":"type","atom":2}},{"Str":{"pattern":"-"}},{"Sequence":{"atoms":[14,15]}},{"Repetition":{"atom":1,"min":0,"max":1,"tag":"Maybe"}},{"Entity":{"atom":22}},{"Entity":{"atom":20}},{"Re":{"pattern":"[\\x01-\\u{10ffff}]"}},{"Repetition":{"atom":19,"min":1,"max":null,"tag":"Repetition"}},{"Named":{"name":"rest","atom":21}},{"Sequence":{"atoms":[0,17,18]}}],"root":23},"bindings":[]}},"preprocess":{},"tables":{},"lint":{"order_warnings":["rule type_token: branches 4 and 5 are order-dependent (shared first bytes; ordered choice is decisive)","rule type_token: branches 7 and 8 are order-dependent (shared first bytes; ordered choice is decisive)"]},"default_entry":"identifier","render":{},"derive":{},"tests":[{"entry":"identifier","kind":"accept","input":"W3C REC-html40-19981224","expect":{}},{"entry":"identifier","kind":"accept","input":"W3C NOTE-datetime-19980827","expect":{}},{"entry":"identifier","kind":"reject","input":"nonsense","expect":{}}],"docs":{},"source":"# Port of lib/pubid/w3c/parser.rb: split off the leading maturity token;\n# code/date boundary is builder-side by design. Token order matters for\n# shared prefixes (CRD before CR, PER before PR, DNOTE before NOTE).\n\ngrammar PubidW3c version \"0.1.0\" {\n  any_char = %x01-10FFFF\n  type_token = \"DNOTE\" / \"NOTE\" / \"WD\" / \"CRD\" / \"CR\" / \"REC\" / \"PER\" / \"PR\" / \"SPSD\" / \"OBSL\"\n  type_part = type_token as type \"-\"\n  rest = (1*any_char) as rest\n  identifier = \"W3C \" [type_part] rest\n  entry identifier: identifier\n\n  test {\n    accept \"W3C REC-html40-19981224\"\n    accept \"W3C NOTE-datetime-19980827\"\n    reject \"nonsense\"\n  }\n}\n","checksum":"sha256:1bd04533a9817c662357acb14e9aad070df46535c537ee95b67b0aa752016164"}

data/data/parg/xsf.json

@@ -0,0 +1 @@
+{"version":"0.1.0","grammar":"PubidXsf","shape":"parsanol-tree/v2","binding_version":1,"entries":{"identifier":{"root":"identifier","grammar":{"atoms":[{"Str":{"pattern":"XEP "}},{"Entity":{"atom":10}},{"Entity":{"atom":3}},{"Re":{"pattern":"[\\x30-\\x39]"}},{"Repetition":{"atom":2,"min":1,"max":null,"tag":"Repetition"}},{"Entity":{"atom":8}},{"Str":{"pattern":"README"}},{"Str":{"pattern":"xxxx"}},{"Alternative":{"atoms":[6,7]}},{"Alternative":{"atoms":[4,5]}},{"Named":{"name":"number","atom":9}},{"Sequence":{"atoms":[0,1]}}],"root":11},"bindings":[]}},"preprocess":{},"tables":{},"lint":{"order_warnings":[]},"default_entry":"identifier","render":{},"derive":{},"tests":[{"entry":"identifier","kind":"accept","input":"XEP 0001","expect":{}},{"entry":"identifier","kind":"accept","input":"XEP README","expect":{}},{"entry":"identifier","kind":"reject","input":"nonsense","expect":{}}],"docs":{},"source":"# Port of lib/pubid/xsf/parser.rb: \"XEP NNNN\" plus the two named\n# documents (README, xxxx) in SPECIAL_NUMBERS.\n  grammar PubidXsf version \"0.1.0\" {\n  digit = %x30-39\n  special_number = \"README\" / \"xxxx\"\n  number = (1*digit / special_number) as number\n  identifier = \"XEP \" number\n  entry identifier: identifier\n\n  test {\n    accept \"XEP 0001\"\n    accept \"XEP README\"\n    reject \"nonsense\"\n  }\n}\n","checksum":"sha256:f70d07de892c58f8386c80aae269fa29f30705100d2aee6266d1bf588f5eeeda"}

data/lib/pubid/adobe/identifier.rb

@@ -18,7 +18,17 @@ module Pubid
       # @return [Pubid::Adobe::Identifier]
       # @raise [Pubid::Errors::ParseError] If parsing fails
       def self.parse(identifier)
-        parsed = Parser.parse(identifier)
+        unless identifier.is_a?(String)
+          raise Pubid::Errors::InvalidInputError,
+                Pubid::INPUT_NOT_A_STRING_MESSAGE
+        end
+
+        if identifier.length > Pubid::MAX_INPUT_LENGTH
+          raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
+        end
+
+        # R1 parser swap: the baked PG artifact is the parser of record.
+        parsed = Pubid::Parg::Backend.parse(:adobe, identifier.strip)
         Builder.build(parsed)
       end
 

data/lib/pubid/amca/identifiers/base.rb

@@ -17,7 +17,7 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
-        parsed = Parser.parse(identifier)
+        parsed = Pubid::Parg::Backend.parse(:amca, identifier)
         Builder.build(parsed)
       end
 

data/lib/pubid/ansi/identifier.rb

@@ -23,7 +23,7 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
-        parsed = Pubid::Ansi::Parser.new.parse(string)
+        parsed = Pubid::Parg::Backend.parse(:ansi, string)
         Pubid::Ansi::Builder.new.build(parsed)
       end
     end

data/lib/pubid/api/identifier.rb

@@ -34,7 +34,7 @@ module Pubid
         # this was the one public parse in the gem that could return nil, which
         # a caller reading `id.to_s` sees as a NoMethodError far from the cause.
         # Both API fixture loaders already drop `#` lines themselves.
-        tree = Parser.new.parse(input)
+        tree = Pubid::Parg::Backend.parse(:api, Api::Parser.normalize_input(input))
         Builder.new.build(tree)
       end
     end

data/lib/pubid/api/parser.rb

@@ -129,11 +129,15 @@ module Pubid
 
       root(:identifier)
 
-      # Preprocessing to normalize common typos
-      def parse(input)
+      # Pre-parse ingestion normalization (R2): every parse path feeds
+      # the grammar the same normalized string.
+      def self.normalize_input(input)
         # Normalize MPMP typo to MPMS
-        normalized = input.gsub("API MPMP", "API MPMS")
-        super(normalized)
+        input.gsub("API MPMP", "API MPMS")
+      end
+
+      def parse(input)
+        super(self.class.normalize_input(input))
       end
     end
   end

data/lib/pubid/ashrae/identifiers/base.rb

@@ -10,7 +10,16 @@ module Pubid
       # @return [Pubid::Ashrae::Identifier] The appropriate identifier object
       # @raise [Pubid::Errors::ParseError] If parsing fails
       def self.parse(identifier)
-        parsed = Parser.parse(identifier)
+        unless identifier.is_a?(String)
+          raise Pubid::Errors::InvalidInputError,
+                Pubid::INPUT_NOT_A_STRING_MESSAGE
+        end
+
+        if identifier.length > Pubid::MAX_INPUT_LENGTH
+          raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
+        end
+
+        parsed = Pubid::Parg::Backend.parse(:ashrae, Parser.normalize_input(identifier))
         Builder.build(parsed)
       end
 

data/lib/pubid/ashrae/parser.rb

@@ -698,16 +698,10 @@ module Pubid
 
       root(:identifier)
 
-      def self.parse(string)
-        unless string.is_a?(String)
-          raise Pubid::Errors::InvalidInputError,
-                Pubid::INPUT_NOT_A_STRING_MESSAGE
-        end
-
-        if string.length > Pubid::MAX_INPUT_LENGTH
-          raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
-        end
-
+      # Pre-parse ingestion normalizations (R2): every parse path —
+      # parslet and PG artifact alike — feeds the grammar the same
+      # normalized string.
+      def self.normalize_input(string)
         # Strip leading/trailing whitespace
         cleaned = string.strip
 
@@ -775,7 +769,20 @@ module Pubid
                                  "Addenda \\1, ")
         end
 
-        new.parse(cleaned)
+        cleaned
+      end
+
+      def self.parse(string)
+        unless string.is_a?(String)
+          raise Pubid::Errors::InvalidInputError,
+                Pubid::INPUT_NOT_A_STRING_MESSAGE
+        end
+
+        if string.length > Pubid::MAX_INPUT_LENGTH
+          raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
+        end
+
+        new.parse(normalize_input(string))
       end
     end
   end

data/lib/pubid/asme/identifier.rb

@@ -16,7 +16,7 @@ module Pubid
         parser = Parser.new
         builder = Builder.new
 
-        parsed = parser.parse(str)
+        parsed = Pubid::Parg::Backend.parse(:asme, str)
         builder.build(parsed)
       end
     end

data/lib/pubid/astm/identifier.rb

@@ -16,7 +16,7 @@ module Pubid
         parser = Parser.new
         builder = Builder.new
 
-        parsed = parser.parse(str)
+        parsed = Pubid::Parg::Backend.parse(:astm, str)
         builder.build(parsed)
       end
     end

data/lib/pubid/bipm/identifier.rb

@@ -277,7 +277,7 @@ module Pubid
         # Normalize legacy/docnumber-style spellings before parsing
         # (data/bipm/update_codes.yaml), mirroring Pubid::Ccsds / Pubid::Plateau.
         normalized = Core::UpdateCodes.apply(identifier, :bipm)
-        parsed = Parser.parse(normalized)
+        parsed = Pubid::Parg::Backend.parse(:bipm, normalized)
         Builder.build(parsed)
       end
     end

data/lib/pubid/bsi/single_identifier.rb

@@ -28,9 +28,7 @@ module Pubid
           return Pubid::Iec.parse(string)
         end
 
-        parser = Parser.new
-
-        parsed = parser.parse(string)
+        parsed = Pubid::Parg::Backend.parse(:bsi, string)
         Builder.build(parsed)
       end
 

data/lib/pubid/calconnect/identifier.rb

@@ -118,7 +118,7 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
-        Builder.build(Parser.parse(identifier))
+        Builder.build(Pubid::Parg::Backend.parse(:calconnect, identifier))
       end
     end
   end

data/lib/pubid/ccsds/identifier.rb

@@ -77,7 +77,7 @@ module Pubid
 
         # Apply legacy update_codes normalization first
         normalized = Core::UpdateCodes.apply(identifier, :ccsds)
-        parsed = Pubid::Ccsds::Parser.parse(normalized)
+        parsed = Pubid::Parg::Backend.parse(:ccsds, normalized)
         Pubid::Ccsds::Builder.build(parsed)
       end
 

data/lib/pubid/cen_cenelec/identifier.rb

@@ -102,7 +102,8 @@ module Pubid
           raise Pubid::Errors::InvalidInputError, Pubid::INPUT_TOO_LONG_MESSAGE
         end
 
-        parsed = Parser.parse(identifier)
+        normalized = Parser.normalize_input(identifier)
+        parsed = Pubid::Parg::Backend.parse(:cen_cenelec, normalized)
         Builder.new.build(parsed)
       end
 

data/lib/pubid/cen_cenelec/parser.rb

@@ -131,7 +131,10 @@ module Pubid
 
       rule(:root) { identifier }
 
-      def self.parse(input)
+      # Pre-parse ingestion normalizations (R2): every parse path —
+      # parslet and PG artifact alike — feeds the grammar the same
+      # normalized string.
+      def self.normalize_input(input)
         # Normalize special dash characters
         normalized = input.gsub(/[\u2011\u00AD]/, "-")
 
@@ -145,7 +148,11 @@ module Pubid
         normalized = normalized.gsub("CEN-CLC", "CEN/CLC")
           .gsub("CLC-CEN", "CLC/CEN")
           .gsub("GUIDE", "Guide")
-        new.parse(normalized)
+        normalized
+      end
+
+      def self.parse(input)
+        new.parse(normalize_input(input))
       end
     end
   end