Class: Pubid::Iec::UrnParser

Inherits:
Object
  • Object
show all
Defined in:
lib/pubid/iec/urn_parser.rb

Overview

Parses RFC 5141-bis compliant URNs into IEC identifiers

URN format: urn:iec:std:publisher:type:number:year:supplements

Examples:

  • urn:iec:std:iec:60050:2011

  • urn:iec:std:iec:tr:60050:2011

  • urn:iec:std:iec:60050-100:2011

  • urn:iec:std:iec:60050:2011:amd:1:2020

Constant Summary collapse

TYPED_STAGE_REVERSE_MAP =

Reverse mappings from URN format to PubID components

{
  "WD" => :wd,
  "WDS" => :wds,
  "CD" => :cd,
  "CDV" => :cdv,
  "DIS" => :dis,
  "FDIS" => :fdis,
  "PDAM" => :pdam,
  "DAM" => :dam,
  "FDAM" => :fdamd,
  "DCOR" => :dcor,
  "FDCOR" => :fdcor,
  "CDTS" => :cdts,
  "DTS" => :dts,
  "FDTS" => :fdts,
  "PRF" => :prf,
  "PWI" => :pwi,
  "NP" => :np,
  "AWI" => :awi,
  "NWIP" => :nwip,
}.freeze
SUPPLEMENT_TYPE_MAP =
{
  "amd" => :amd,
  "cor" => :cor,
}.freeze
TYPE_CODE_REVERSE_MAP =
{
  "tr" => :tr,
  "ts" => :ts,
  "pas" => :pas,
  "guide" => :guide,
  "isp" => :isp,
  "r" => :r,
  "sr" => :sr,
  "tap" => :tap,
}.freeze

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.parse(urn) ⇒ Identifier

Parse IEC URN string

Parameters:

  • urn (String)

    URN string to parse

Returns:



57
58
59
# File 'lib/pubid/iec/urn_parser.rb', line 57

def self.parse(urn)
  new.parse_urn(urn)
end

Instance Method Details

#parse_urn(urn) ⇒ Identifier

Parse URN string into identifier

Parameters:

  • urn (String)

    URN string

Returns:



64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
# File 'lib/pubid/iec/urn_parser.rb', line 64

def parse_urn(urn)
  # Remove urn:iec:std: prefix
  unless urn.start_with?("urn:iec:std:")
    raise Errors::ParseError,
          "Invalid IEC URN: #{urn}"
  end

  parts = urn.sub("urn:iec:std:", "").split(":")

  # Parse publisher(s) - first part
  publishers = parse_publisher(parts.shift)

  # Parse type - optional (defaults to IS)
  type_code = nil
  type_code = parse_type(parts.first) if parts.first && TYPE_CODE_REVERSE_MAP.key?(parts.first.downcase)
  parts.shift if type_code

  # Parse number
  number_part = parts.shift
  number, part, subpart = parse_number_part(number_part)

  # Check for stage (stage-XX.XX or typed stage like WD, CD, etc.)
  stage_code = nil
  stage_iteration = nil
  if parts.first&.start_with?("stage-")
    stage_code, stage_iteration = parse_stage_code(parts.shift)
  elsif TYPED_STAGE_REVERSE_MAP.key?(parts.first&.upcase)
    stage_abbr = parts.shift.upcase
    stage_code = TYPED_STAGE_REVERSE_MAP[stage_abbr]
    # Check for iteration (WD.2 format)
    if stage_abbr.include?(".")
      stage_code, stage_iteration = stage_abbr.split(".")
      stage_code = TYPED_STAGE_REVERSE_MAP[stage_code]
      stage_iteration = stage_iteration.to_i
    end
  end

  # Parse date if present (year or year-month)
  date = nil
  if parts.first&.match(/^\d{4}(-\d{2})?$/)
    date = parts.shift
  end

  # Parse edition if present (ed.N format)
  edition = nil
  if parts.first&.start_with?("ed.")
    edition = parts.shift.sub("ed.", "").to_i
  end

  # Check for supplements (amd, cor)
  supplements = []
  while parts.any?
    supp_type = nil
    supp_number = nil
    supp_date = nil
    supp_stage = nil

    # Check for supplement stage
    if parts.first&.start_with?("stage-")
      supp_stage_data = parts.shift
      supp_stage, = parse_stage_code(supp_stage_data)
    elsif TYPED_STAGE_REVERSE_MAP.key?(parts.first&.upcase)
      supp_stage_abbr = parts.shift.upcase
      supp_stage = TYPED_STAGE_REVERSE_MAP[supp_stage_abbr]
    end

    # Check for supplement type (amd, cor)
    if SUPPLEMENT_TYPE_MAP.key?(parts.first&.downcase)
      supp_type = SUPPLEMENT_TYPE_MAP[parts.shift.downcase]
    end

    # Check for version (v1, v2, etc.) or number
    if parts.first&.start_with?("v")
      version_str = parts.shift
      supp_number = version_str.sub("v", "").to_i
    elsif parts.first&.match(/^\d+$/)
      # Could be year or supplement number
      if parts.first&.match(/^\d{4}$/)
        # 4 digits = year
        supp_date = parts.shift
      else
        # 1-3 digits = supplement number
        supp_number = parts.shift.to_i
      end
    end

    # Next part might be year if not already set
    if supp_date.nil? && parts.first&.match(/^\d{4}(-\d{2})?$/)
      supp_date = parts.shift
    end

    # Safety: consume unrecognized token to prevent infinite loop
    unless supp_type || supp_number || supp_date || supp_stage
      parts.shift
    end

    supplements << {
      type: supp_type,
      number: supp_number,
      date: supp_date,
      stage: supp_stage,
    }
  end

  # Build the identifier hash
  build_identifier(publishers, number, part, subpart, type_code, stage_code, stage_iteration,
                   date, edition, supplements)
end