def search_line(line, search, searchtype):
if searchtype == 're':
return re.search(search, line) #, re.IGNORECASE)
elif searchtype == 'pos':
return Search.search_out(line, search)
elif searchtype == 'hyper':
return Search.hypernym_search(line, search)
def create_description(self):
pat = 'VB|VBD|VBZ|VBG * NN IN * NN'
#pat = 'PRP * VB|VBD|VBZ|VBG * NN'
phrases = search.search_out(self.source_text, pat)
conjugated_phrases = []
for phrase in phrases:
words = []
for word, pos in tag(phrase):
if pos in ["VBZ", "VBD", "VB", "VBG"]:
words.append(conjugate(word, "3sg"))
#elif pos == "NN" and random.random() < .1:
#words.append(self.define_word(word))
else:
words.append(word)
conjugated_phrases.append(' '.join(words))
artifacts = list(self.artifacts)
sentence_prefixes = ["The present invention", "The device", "The invention"]
paragraph_prefixes = ["The present invention", "According to a beneficial embodiment, the invention", "According to another embodiment, the device", "According to a preferred embodiment, the invention", "In accordance with an alternative specific embodiment, the present invention"]
i = 0
self.description = ''
for phrase in conjugated_phrases:
line = ""
if i == 0:
line = paragraph_prefixes[0] + " " + phrase
else:
if random.random() < .1:
line = "\n\n" + random.choice(paragraph_prefixes) + " " + phrase
else:
line = random.choice(sentence_prefixes) + " " + phrase
self.description += line + ". "
i += 1
def search_line(line, search, searchtype):
if searchtype == 're':
return re.search(search, line) #, re.IGNORECASE)
elif searchtype == 'pos':
return Search.search_out(line, search)
elif searchtype == 'hyper':
return Search.hypernym_search(line, search)
def create_illustrations(self):
self.illustrations = []
templates = ["Figure {0} illustrates {1}.",
"Figure {0} is a schematic drawing of {1}.",
"Figure {0} is a perspective view of {1}.",
"Figure {0} is an isometric view of {1}.",
"Figure {0} schematically illustrates {1}.",
"Figure {0} is a block diagram of {1}.",
"Figure {0} is a cross section of {1}.",
"Figure {0} is a diagrammatical view of {1}."]
illustrations = list(set(search.search_out(self.source_text, 'DT JJ NP IN * NN')))
self.unformatted_illustrations = illustrations
for i in range(len(illustrations)):
self.illustrations.append(random.choice(templates).format(i+1, illustrations[i]))
def create_gerund_title(self, text):
search_patterns = [
'VBG DT NN RB', 'VBG NNP * NP', 'VBG NNP * .',
'RB VBG NNP', 'VBG JJ NP', 'VBG * JJ * NP', 'VBG * JJ *',
'VBG * NN', 'VBG * JJ *? NP NP?', 'VBG * JJ? NP']
gerund_phrases = search.search_out(text, search_patterns[-1])
self.possible_titles = []
for title in gerund_phrases:
self.possible_titles.append(title)
self.partial_title = random.choice(self.possible_titles)
title = self.prefix() + self.partial_title
self.set_keywords(self.partial_title)
return title.capitalize()
def create_gerund_title(self, text):
search_patterns = [
'VBG DT NN RB', 'VBG NNP * NP', 'VBG NNP * .', 'RB VBG NNP',
'VBG JJ NP', 'VBG * JJ * NP', 'VBG * JJ *', 'VBG * NN',
'VBG * JJ *? NP NP?', 'VBG * JJ? NP'
]
gerund_phrases = search.search_out(text, search_patterns[-1])
self.possible_titles = []
for title in gerund_phrases:
self.possible_titles.append(title)
self.partial_title = random.choice(self.possible_titles)
title = self.prefix() + self.partial_title
self.set_keywords(self.partial_title)
return title.capitalize()
def create_illustrations(self):
self.illustrations = []
templates = [
"Figure {0} illustrates {1}.",
"Figure {0} is a schematic drawing of {1}.",
"Figure {0} is a perspective view of {1}.",
"Figure {0} is an isometric view of {1}.",
"Figure {0} schematically illustrates {1}.",
"Figure {0} is a block diagram of {1}.",
"Figure {0} is a cross section of {1}.",
"Figure {0} is a diagrammatical view of {1}."
]
illustrations = list(
set(search.search_out(self.source_text, 'DT JJ NP IN * NN')))
self.unformatted_illustrations = illustrations
for i in range(len(illustrations)):
self.illustrations.append(
random.choice(templates).format(i + 1, illustrations[i]))
def create_description(self):
pat = 'VB|VBD|VBZ|VBG * NN IN * NN'
#pat = 'PRP * VB|VBD|VBZ|VBG * NN'
phrases = search.search_out(self.source_text, pat)
conjugated_phrases = []
for phrase in phrases:
words = []
for word, pos in tag(phrase):
if pos in ["VBZ", "VBD", "VB", "VBG"]:
words.append(conjugate(word, "3sg"))
#elif pos == "NN" and random.random() < .1:
#words.append(self.define_word(word))
else:
words.append(word)
conjugated_phrases.append(' '.join(words))
artifacts = list(self.artifacts)
sentence_prefixes = [
"The present invention", "The device", "The invention"
]
paragraph_prefixes = [
"The present invention",
"According to a beneficial embodiment, the invention",
"According to another embodiment, the device",
"According to a preferred embodiment, the invention",
"In accordance with an alternative specific embodiment, the present invention"
]
i = 0
self.description = ''
for phrase in conjugated_phrases:
line = ""
if i == 0:
line = paragraph_prefixes[0] + " " + phrase
else:
if random.random() < .1:
line = "\n\n" + random.choice(
paragraph_prefixes) + " " + phrase
else:
line = random.choice(sentence_prefixes) + " " + phrase
self.description += line + ". "
i += 1
def find_lines(self):
lines = search.search_out(self.source_text, "|".join(self.nouns + self.verbs + self.adjectives))
print lines
def find_lines(self):
lines = search.search_out(
self.source_text,
'|'.join(self.nouns + self.verbs + self.adjectives))
print lines
