Method: Slaw::Parse::Builder#find_term_references

Defined in:
lib/slaw/parse/builder.rb

#find_term_references(doc, terms) ⇒ Object

Find and decorate references to terms in the document. The terms param is a hash from term_id to actual term.



296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
 
# File 'lib/slaw/parse/builder.rb', line 296

def find_term_references(doc, terms)
  logger.info("+ Finding references to terms")

  i = 0

  # sort terms by the length of the defined term, desc,
  # so that we don't find short terms inside longer
  # terms
  terms = terms.to_a.sort_by { |pair| -pair[1].size }

  # look for each term
  for term_id, term in terms
    doc.xpath('//a:body//text()', a: NS).each do |text|
      # replace all occurrences in this text node

      # unless we're already inside a def or term element
      next if (["def", "term"].include?(text.parent.name))

      # don't link to a term inside its own definition
      owner = find_up(text, 'subsection')
      next if owner and owner.at_xpath(".//a:def[@refersTo='##{term_id}']", a: NS)

      while posn = (text.content =~ /\b#{Regexp::escape(term)}\b/)
        # <p>A delegation under subsection (1) shall not prevent the <term refersTo="#term-Minister" id="trm357">Minister</term> from exercising the power himself or herself.</p>
        node = doc.create_element('term', term, refersTo: "##{term_id}", id: "trm#{i}")

        pre = (posn > 0) ? text.content[0..posn-1] : nil
        post = text.content[posn+term.length..-1]

        text.before(node)
        node.before(doc.create_text_node(pre)) if pre
        text.content = post

        i += 1
      end
    end
  end
end