def parse(self, path='shakespeare/sonnets.txt'):
self.get_file(path)
self.format_file(path)
with open('{}.clean'.format(path), 'r') as sonnetfile:
remainder = []
project = self.sequence_model.get_or_create_project()
for line in sonnetfile:
line = line.strip()
if line == '' or isroman(line):
# start new at a new sonnet (just in case a punctuation mark was missing)
remainder = []
continue
sentences = re.split('\. |\? |! ', line)
sentences = [sentence.split() for sentence in sentences]
sentences[0] = remainder + sentences[0]
if line.endswith(('.', '?', '!')):
remainder = sentences.pop(-1)
for sentence in sentences:
words = [Word.objects.get_or_create(name=word)[0] for word in sentence]
for wordset in list_subsets(words, size=project.max_lookahead):
sequence = ShakespeareSequence(title=self.title, project=project)
sequence.save()
for i in range(len(wordset)):
SequenceOrder(word=wordset[i], sequence=sequence, position=i+1).save()
def get(self, request):
context = {'project': ShakespeareSequence.get_or_create_project()}
return render(request, self.template_name, context)