Class: Identifiers::DOI

Inherits:
Object
  • Object
show all
Defined in:
lib/identifiers/doi.rb

Constant Summary collapse

PATTERN = 
%r{
  \b
  10 # Directory indicator (always 10)
  \.
  (?:
    # ISBN-A
    97[89]\. # ISBN (GS1) Bookland prefix
    \d{2,8}  # ISBN registration group element and publisher prefix
    /        # Prefix/suffix divider
    \d{1,7}  # ISBN title enumerator and check digit
    |
    # DOI
    \d{4,9} # Registrant code
    /       # Prefix/suffix divider
    \S+     # DOI suffix
  )
}x
VALID_ENDING = 
/
  (?:
    \p{^Punct}  # Non-punctuation character
    |
    \(.+\)      # Balanced parentheses
    |
    2-\#        # Early Wiley DOI suffix
  )
  \z
/x

Class Method Summary collapse

Class Method Details

.extract(str) ⇒ Object 



31
32
33
34
35
36
37
38
 
# File 'lib/identifiers/doi.rb', line 31

def self.extract(str)
  str
    .to_s
    .downcase
    .scan(PATTERN)
    .map { |doi| strip_punctuation(doi) }
    .compact
end

.extract_one(str) ⇒ Object 



40
41
42
43
44
45
 
# File 'lib/identifiers/doi.rb', line 40

def self.extract_one(str)
  match = str.to_s.downcase[PATTERN]
  return unless match

  strip_punctuation(match)
end

.strip_punctuation(doi) ⇒ Object 



47
48
49
50
51
 
# File 'lib/identifiers/doi.rb', line 47

def self.strip_punctuation(doi)
  return doi if doi =~ VALID_ENDING

  extract_one(doi.sub(/\p{Punct}\z/, ''))
end