def extract_subjects(parse_tree, enum=True):
"""
Returns a list of subject words.
"""
for node in extract_subject_nodes(parse_tree):
word = get_node_string(node)
if enum:
yield (parse_tree.indexOf(node), word)
else:
yield word
def _parse(self, raw_input_string):
"""
Fills out message meta and frame attributes.
"""
tokenizer = nltk.WordPunctTokenizer()
tokenized_string = tokenizer.tokenize(raw_input_string)
subjects = extract_subject_nodes(tokenized_string)
if subjects:
self.frame['subject'] = [get_node_string(subject)
for subject in subjects]
words_temporary_pos = extract_close_keywords(
PreferenceMessage.keywords_temporary_pos,
tokenized_string,
2)
words_temporary_neg = extract_close_keywords(
PreferenceMessage.keywords_temporary_neg,
tokenized_string,
2)
words_permanent_pos = extract_close_keywords(
PreferenceMessage.keywords_permanent_pos,
tokenized_string,
2)
words_permanent_neg = extract_close_keywords(
PreferenceMessage.keywords_permanent_neg,
tokenized_string,
2)
words_temporary = words_temporary_pos + words_temporary_neg
words_permanent = words_permanent_pos + words_permanent_neg
if words_temporary and words_permanent:
# Confused
# self.frame['temporal'] = None
# self.frame['word'] = None
# This check is skipped due to an error in not using the POS
# when looking up synsets.
# TODO: Fix (example: fish)
pass
if words_temporary:
self.frame['temporal'] = 'temporary'
self.frame['word'] = words_temporary[0]
else: # words_permanent
self.frame['temporal'] = 'permanent'
self.frame['word'] = words_permanent[0]
words_pos = words_temporary_pos + words_permanent_pos
words_neg = words_temporary_neg + words_permanent_neg
if words_pos and words_neg:
# Confused
self.frame['prefer'] = None
if words_pos:
self.frame['prefer'] = True
else: # words_neg
self.frame['prefer'] = False
def _parse(self, raw_input_string):
"""
Fills out message meta and frame attributes.
"""
tokenizer = nltk.WordPunctTokenizer()
tokenized_string = tokenizer.tokenize(raw_input_string)
tagger = utils.combined_taggers
tagged_string = tagger.tag(tokenized_string)
# Ingredients
for i, ingredient in get_ingredients(tokenized_string, enum=True):
self.frame['ingredient'].append({'id': i,
'name': ingredient,
'descriptor': [], # TODO: siblings JJ
'preference': 0, # TODO: RB = not or n't
'relationship': 'and', #TODO: Implement
})
# Meals
for i, meal in get_meals(tokenized_string, enum=True):
meal = tokenized_string[i]
self.frame['meal'].append({'id': i,
'name': meal,
'descriptor': [], # TODO: siblings JJ
'preference': 0, # TODO: RB = not or n't
'relationship': 'and', #TODO: Implement
})
# Cuisine
for i, cuisine in get_cuisines(tokenized_string, enum=True):
self.frame['cuisine'].append({'id': i,
'name': cuisine,
'descriptor': [], # TODO: siblings JJ
'preference': 0, # TODO: RB = not or n't
'relationship': 'and', #TODO: Implement
})
# Dish
# TODO: Get the subject of the sentence (aka what the verb is reffering to)
dishesSet = [(i, w) for i,w in extract_subject_nodes(tokenized_string, enum=True) if
w not in self.frame['ingredient'] and
w not in self.frame['meal']]
for i, dish in dishesSet:
self.frame['dish'].append({'id': i,
'name': dish,
'descriptor': [], # TODO: siblings JJ
'preference': 0, # TODO: RB = not or n't
'relationship': 'and', #TODO: Implement
})
def _parse(self, raw_input_string, g):
"""
Fills out message meta and frame attributes.
"""
tokenized_string = g.generate_tokenized_string(raw_input_string)
parseTree = g.generate_stanford_parse_tree(raw_input_string)
subjects = extract_subject_nodes(parseTree)
if subjects:
self.frame['subject'] = [
get_node_string(subject) for subject in subjects
]
words_temporary_pos = extract_close_keywords(
PreferenceMessage.keywords_temporary_pos, tokenized_string, 2)
words_temporary_neg = extract_close_keywords(
PreferenceMessage.keywords_temporary_neg, tokenized_string, 2)
words_permanent_pos = extract_close_keywords(
PreferenceMessage.keywords_permanent_pos, tokenized_string, 2)
words_permanent_neg = extract_close_keywords(
PreferenceMessage.keywords_permanent_neg, tokenized_string, 2)
words_temporary = words_temporary_pos + words_temporary_neg
words_permanent = words_permanent_pos + words_permanent_neg
if words_temporary and words_permanent:
# Confused
# self.frame['temporal'] = None
# self.frame['word'] = None
# This check is skipped due to an error in not using the POS
# when looking up synsets.
# TODO: Fix (example: fish)
pass
if words_temporary:
self.frame['temporal'] = 'temporary'
self.frame['word'] = words_temporary[0]
else: # words_permanent
self.frame['temporal'] = 'permanent'
self.frame['word'] = words_permanent[0]
words_pos = words_temporary_pos + words_permanent_pos
words_neg = words_temporary_neg + words_permanent_neg
if words_pos and words_neg:
# Confused
self.frame['prefer'] = None
if words_pos:
self.frame['prefer'] = True
else: # words_neg
self.frame['prefer'] = False
