def get_text_generator(max_string_length, alphabet=None):
"""Generates a lists of tuples of the form (category, content)
where category is always "characters."
"""
gen = essential_generators.DocumentGenerator()
while True:
sentence = ''.join([s for s in gen.sentence()
if (alphabet is None or s in alphabet)])[:max_string_length]
yield [('characters', sentence)]
def get_text_generator(alphabet=None, lowercase=False, max_string_length=None):
"""Generates strings of sentences using only the letters in alphabet.
Args:
alphabet: The alphabet of permitted characters
lowercase: Whether to convert all strings to lowercase.
max_string_length: The maximum length of the string
"""
gen = essential_generators.DocumentGenerator()
while True:
sentence = gen.sentence()
if lowercase:
sentence = sentence.lower()
sentence = ''.join([s for s in sentence if (alphabet is None or s in alphabet)])
if max_string_length is not None:
sentence = sentence[:max_string_length]
yield sentence
