Class: AnyStyle::Parser

Inherits:
ParserCore show all
Includes:
Format::BibTeX, Format::CSL
Defined in:
lib/anystyle/parser.rb

Constant Summary

Constants included from Format::BibTeX

Format::BibTeX::TYPES

Instance Attribute Summary

Attributes inherited from ParserCore

#features, #model, #normalizers, #options

Instance Method Summary collapse

Methods included from Format::CSL

#format_csl

Methods included from Format::BibTeX

#format_bibtex, #names_to_bibtex

Methods inherited from ParserCore

#check, instance, #label, #learn, load, #load_model, #normalize, #train

Methods included from StringUtils

canonize, count, display_chars, display_width, indent, page_break?, scrub, transliterate

Constructor Details

#initialize(options = {}) ⇒ Parser 



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
 
# File 'lib/anystyle/parser.rb', line 108

def initialize(options = {})
  super(options)

  @features = [
    Feature::Canonical.new,
    Feature::Category.new,
    Feature::Affix.new(size: 2),
    Feature::Affix.new(size: 2, suffix: true),
    Feature::Caps.new,
    Feature::Number.new,
    Feature::Dictionary.new(dictionary: options[:dictionary] || Dictionary.instance),
    Feature::Keyword.new,
    Feature::Position.new,
    Feature::Punctuation.new,
    Feature::Brackets.new,
    Feature::Terminal.new,
    Feature::Locator.new
  ]

  @normalizers = [
    Normalizer::Quotes.new,
    Normalizer::Brackets.new,
    Normalizer::Punctuation.new,
    Normalizer::Journal.new,
    Normalizer::Container.new,
    Normalizer::Edition.new,
    Normalizer::Volume.new,
    Normalizer::Page.new,
    Normalizer::Date.new,
    Normalizer::Location.new,
    Normalizer::Locator.new,
    Normalizer::Publisher.new,
    Normalizer::PubMed.new,
    Normalizer::Names.new,
    Normalizer::Locale.new,
    Normalizer::Type.new
  ]
end

Instance Method Details

#expand(dataset) ⇒ Object 



147
148
149
150
151
152
153
154
155
156
 
# File 'lib/anystyle/parser.rb', line 147

def expand(dataset)
  dataset.each do |seq|
    seq.tokens.each_with_index do |tok, idx|
      alpha = scrub tok.value
      tok.observations = features.map { |f|
        f.observe tok.value, alpha: alpha, idx: idx, seq: seq
      }
    end
  end
end

#flatten_values(hash, skip: [], spacer: ' ') ⇒ Object 



164
165
166
167
168
169
170
171
172
173
174
 
# File 'lib/anystyle/parser.rb', line 164

def flatten_values(hash, skip: [], spacer: ' ')
  hash.each_pair do |key, value|
    unless !value.is_a?(Array) || skip.include?(key)
      if value.length > 1 && value[0].respond_to?(:join)
        hash[key] = value.join(spacer)
      else
        hash[key] = value[0]
      end
    end
  end
end

#format_hash(dataset, symbolize_keys: true) ⇒ Object 



158
159
160
161
162
 
# File 'lib/anystyle/parser.rb', line 158

def format_hash(dataset, symbolize_keys: true)
  dataset.inject([]) { |out, seq|
    out << normalize(seq.to_h(symbolize_keys: symbolize_keys), prev: out)
  }
end

#parse(input, format: , **opts) ⇒ Object 



180
181
182
183
184
185
186
187
188
189
190
 
# File 'lib/anystyle/parser.rb', line 180

def parse(input, format: options[:format], **opts)
  case format.to_sym
  when :wapiti
    label(input, **opts)
  when :hash, :bibtex, :citeproc, :csl
    formatter = "format_#{format}".to_sym
    send(formatter, label(input, **opts), **opts)
  else
    raise ArgumentError, "format not supported: #{format}"
  end
end

#prepare(input, **opts) ⇒ Object 



192
193
194
195
196
197
 
# File 'lib/anystyle/parser.rb', line 192

def prepare(input, **opts)
  opts[:separator] ||= options[:separator]
  opts[:delimiter] ||= options[:delimiter]
  input = input.join("\n") if input.is_a?(Array) && input[0].is_a?(String)
  super(input, opts)
end

#rename_value(hash, name, new_name) ⇒ Object 



176
177
178
 
# File 'lib/anystyle/parser.rb', line 176

def rename_value(hash, name, new_name)
  hash[new_name] = hash.delete name if hash.key?(name)
end