Class: Alexandria::PseudoMarcParser

Inherits:
Object
  • Object
show all
Defined in:
lib/alexandria/book_providers/pseudomarc.rb

Overview

A really simple regex-based parser to grab data out of marc text records.

Constant Summary collapse

BNF_FR_MAPPINGS = 
{
  title: ['200', 'a'],
  authors: ['700', 'a'],
  isbn: ['010', 'a'],
  publisher: ['210', 'g'],
  year: ['210', 'd'],
  binding: ['225', 'a'],
  notes: ['520', 'a']
}.freeze
USMARC_MAPPINGS = 
{
  title: ['245', 'a', 'b'],
  authors: ['100', 'a'],
  isbn: ['020', 'a'],
  publisher: ['490', 'a'],
  year: ['260', 'c'],
  binding: ['020', 'a'], # listed with isbn here
  notes: ['520', 'a']
}.freeze

Class Method Summary collapse

Class Method Details

.get_fields(data, type, stripping, m = USMARC_MAPPINGS) ⇒ Object 



44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
 
# File 'lib/alexandria/book_providers/pseudomarc.rb', line 44

def self.get_fields(data, type, stripping, m = USMARC_MAPPINGS)
  field = ''
  m[type][1..m[type].length - 1].each do |part|
    if data.first[part]
      part_data = data.first[part].strip
      if part_data =~ stripping
        part_data = Regexp.last_match[1]
        part_data = part_data.strip
      end
      field += ': ' if field != ''
      field += part_data
    end
  end
  field = nil if field == ''
  field
end

.marc_text_to_book(marc, m = USMARC_MAPPINGS) ⇒ Object 



61
62
63
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
 
# File 'lib/alexandria/book_providers/pseudomarc.rb', line 61

def self.marc_text_to_book(marc, m = USMARC_MAPPINGS)
  details = marc_text_to_details(marc)
  unless details.empty?
    title = nil
    title_data = details[m[:title][0]]
    if title_data
      title_data_all = get_fields(title_data, :title, /(.*)[\/:]$/, m)
      title = title_data_all if title_data_all
    end

    authors = []
    author_data = details[m[:authors][0]]
    author_data&.each do |ad|
      author = ad[m[:authors][1]]
      if author
        author = author.strip
        author = Regexp.last_match[1] if author =~ /(.*),$/
        authors << author
      end
    end

    isbn = nil
    binding = nil
    isbn_data = details[m[:isbn][0]]
    if isbn_data
      isbn = Regexp.last_match[1] if isbn_data.first[m[:isbn][1]] =~ /([-0-9xX]+)/
    end

    binding_data = details[m[:binding][0]]
    if binding_data
      binding = Regexp.last_match[1] if binding_data.first[m[:binding][1]] =~ /([a-zA-Z][a-z\s]+[a-z])/
    end

    publisher = nil
    publisher_data = details[m[:publisher][0]]
    publisher = publisher_data.first[m[:publisher][1]] if publisher_data

    year = nil
    publication_data = details[m[:year][0]]
    if publication_data
      year = publication_data.first[m[:year][1]]
      year = Regexp.last_match[1].to_i if year =~ /(\d+)/
    end

    notes = ''
    notes_data = details[m[:notes][0]]
    notes_data&.each do |note|
      txt = note[m[:notes][1]]
      notes += txt if txt
    end

    if title.nil? && isbn.nil?
      # probably didn't undertand the MARC dialect
      return nil
    end

    book = Alexandria::Book.new(title, authors, isbn,
                                publisher, year, binding)
    book.notes = notes unless notes.empty?
    book
  end
end

.marc_text_to_details(marc) ⇒ Object 



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
 
# File 'lib/alexandria/book_providers/pseudomarc.rb', line 124

def self.marc_text_to_details(marc)
  details = {}
  marc.each_line do |line|
    if line =~ /(\d+)\s*(.+)/
      code = Regexp.last_match[1]
      data = Regexp.last_match[2]

      this_line_data = {}

      # puts code
      # puts data
      d_idx = 0
      while d_idx < data.size
        d_str = data[d_idx..-1]
        # puts d_str
        if (idx = d_str =~ /\$([a-z]) ([^\$]+)/)
          # puts idx
          sub_code = Regexp.last_match[1]
          sub_data = Regexp.last_match[2]
          this_line_data[sub_code] = sub_data
          # puts "  " + $1
          # puts "    " + $2
          # puts idx
          d_idx += idx + 2 # (2 extra to push beyond this '$a' etc.)
        else
          break
        end
      end

      unless this_line_data.empty?
        details[code] = [] unless details.key?(code)
        details[code] << this_line_data
      end

    end
  end
  details
end