def test_sonnets(self):
self.assertTrue(
poetrytools.guess_form(self.open_poem('sonnet.txt')) ==
'Shakespearean sonnet')
self.assertTrue(
poetrytools.guess_form(self.open_poem('brokensonnet.txt')) ==
'sonnet with trochaic pentameter or irregular meter')
def test_sonnets(self):
self.assertTrue(
poetrytools.guess_form(self.open_poem('sonnet.txt')) ==
'Shakespearean sonnet')
self.assertTrue(
poetrytools.guess_form(self.open_poem('brokensonnet.txt')) ==
'sonnet with unusual meter')
def analysis(x):
print(len(temp_form))
print(type(x))
poem = poetrytools.tokenize(x)
temp_form.append(poetrytools.guess_form(poem, verbose=False))
temp_metre.append(poetrytools.guess_metre(poem)[3])
temp_rhyme.append(poetrytools.guess_rhyme_type(poem)[1])
temp_stanza_type.append(poetrytools.guess_stanza_type(poem)[1])
def add_poem_form(poems_file_loc):
form = {}
with open(poems_file_loc, 'rb') as f:
poems = cPickle.load(f)
print "nbr of poems: %d" % count_poems(poems)
iter = 0
for author, author_dct in poems.iteritems():
for poem_title, poem in author_dct.iteritems():
try:
form[poem_title] = poetrytools.guess_form(poem)
except:
pass
iter += 1
if iter % 100 == 0:
print "%s: processed %d poems" % (datetime.now(), iter)
return form
def test_rondeau(self):
self.assertTrue(
poetrytools.guess_form(self.open_poem('rondeau.txt')) == 'rondeau')
def test_heroiccouplets(self):
self.assertTrue(
poetrytools.guess_form(self.open_poem('heroiccouplets.txt')) ==
'heroic couplets')
def test_ottavarima(self):
self.assertTrue(
poetrytools.guess_form(self.open_poem('ottavarima.txt')) ==
'ottava rima')
def test_cinquain(self):
self.assertTrue(
poetrytools.guess_form(self.open_poem('cinquain.txt')) ==
'cinquain')
def test_blankverse(self):
self.assertTrue(
poetrytools.guess_form(self.open_poem('blankverse.txt')) ==
'blank verse')
def test_haiku(self):
self.assertTrue(
poetrytools.guess_form(self.open_poem('haiku.txt')) == 'haiku')
self.assertTrue(
poetrytools.guess_form(self.open_poem('tanka.txt')) == 'tanka')
if TEST:
OUTPUT = r"../data/test/input.txt"
VOCAB = 300
SUFFIX = ""
else:
OUTPUT = r"../data/large/gutenberg.txt"
VOCAB = 40000
SUFFIX = "NEW"
def write_out(text, f):
# Write out
with open(f, "w") as fobj:
fobj.write(text)
def read_in(ff):
with open(ff, "r") as fobj:
return fobj.read()
# Prune vocab for most common words
text = read_in(OUTPUT)
#write_out(text, out)
poem = poetrytools.tokenize(text) # need to tokenize the poem first
print(poem)
x = poetrytools.scanscion(poem)
print(x)
poetrytools.guess_form(poem, verbose=True)
