def test_fill(self):
hyphenator = hyphen.Hyphenator("en_US")
wrapped = textwrap2.fill("A thing of beauty is a joy forever.",
width=10,
use_hyphenator=hyphenator)
# Note that this wrapping depends on the content of the language dictionary
self.assertEqual("""A thing of
beauty is
a joy for-
ever.""", wrapped)
def __init__(self, filename, lang):
if lang == 'de':
self.hyphenation = hyphen.Hyphenator('de_DE')
elif lang == 'en':
self.hyphenation = hyphen.Hyphenator('en_US')
else:
raise Exception(
'Requested language not supported (Supported: \'en\', \'de\').'
)
self.lang = lang
with open(filename, 'r') as content_file:
self.content = content_file.read()
self.words = re.findall(r'[a-zA-ZäöüÄÖÜß]+', self.content)
self.n_sentences = self.count_sentences()
self.n_words = len(self.words)
self.n_syllables = self.count_syllables()
# Copyright (C) 2018 David Arroyo Menéndez
# Author: David Arroyo Menéndez <*****@*****.**>
# Maintainer: David Arroyo Menéndez <*****@*****.**>
# This file is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3, or (at your option)
# any later version.
# This file is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
# You should have received a copy of the GNU General Public License
# along with GNU Emacs; see the file COPYING. If not, write to
# the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
# Boston, MA 02110-1301 USA,
import hyphen
h = hyphen.Hyphenator('en_US')
print(h.syllables(u"Hammond's"))
#It's just included in one syllable
# [u'Ham', u"mond's"]
# But if I do the same using the German dictionary
h = hyphen.Hyphenator('de_CH')
print(h.syllables(u"Hammond's"))
print(h.syllables(u"Bismarck'sche"))
def is_polysyllabic(w, hyphenator=hyphen.Hyphenator('en_US')):
if len(w) > 30: return False
return (len(hyphenator.syllables(unicode(w))) >= 3)
def __init__(self, dataset, locale='en_US', reverse=False):
self._hyphenator = hyphen.Hyphenator(locale)
self._bigrams_dict = self.__build__bigrams_dictionary(
self.__compute_bigrams(dataset), reverse)
def set_language(self, language):
self.hyphenator = hyphen.Hyphenator(language=language,
directory=DICTIONARIES_DIR)
def __init__(self, language):
self.hyphenator = hyphen.Hyphenator(language=language,
directory=DICTIONARIES_DIR)
import os
from os import path
import sys, codecs
import arrow
from string import ascii_letters
import markdown, md_extensions
from PIL import Image
from jinja2 import Environment, FileSystemLoader
import yaml
# Prepare hyphen, load (or install) dictionary...
import hyphen
import hyphen.dictools
if not hyphen.dictools.is_installed('en_US'): hyphen.dictools.install('en_US')
h = hyphen.Hyphenator('en_US')
# DEFAULTS
# Common screen resolutions to fit images in (defaults are all about width).
# None means auto-adapt.
IMAGE_RESIZES = (
480,
#600,
#768,
900,
#1080,
#1200,
1600,
)
