text/german.py

import text.ger_to_ipa as ipa
from text.ger_to_ipa import normalize_numbers
import re
from unidecode import unidecode

# List of (ipa, lazy ipa) pairs:
_lazy_ipa = [(re.compile('%s' % x[0]), x[1]) for x in [
    ('r', 'ɹ'),
    ('æ', 'e'),
    ('ɑ', 'a'),
    ('ɔ', 'o'),
    ('ð', 'z'),
    ('θ', 's'),
    ('ɛ', 'e'),
    ('ɪ', 'i'),
    ('ʊ', 'u'),
    ('ʒ', 'ʥ'),
    ('ʤ', 'ʥ'),
    ('ˈ', '↓'),
]]

# List of (ipa, lazy ipa2) pairs:
_lazy_ipa2 = [(re.compile('%s' % x[0]), x[1]) for x in [
    ('r', 'ɹ'),
    ('ʤ', 'dʒ'),
    ('ʧ', 'tʃ'),
    ('r', 'ɹ'),
    ('æ', 'e'),
    ('ɑ', 'a'),
    ('ɔ', 'o'),
    ('ð', 'z'),
    ('θ', 's'),
    ('ɛ', 'e'),
    ('ɪ', 'i'),
    ('ʊ', 'u'),
    ('ʒ', 'ʥ'),
    ('ʤ', 'ʥ'),
    ('ˈ', '↓'),
    ('ɡ', 'g'),
    ('ɔ', 'o'),
    ('ɪ','i')
]]

# List of (ipa, ipa2) pairs
_ipa_to_ipa2 = [(re.compile('%s' % x[0]), x[1]) for x in [
    ('æ', 'e'),
    ('ɑ', 'a'),
    ('ɔ', 'o'),
    ('β', 'ss'),
    ('ɛ', 'e'),
    ('ɪ', 'i'),
    ('ʊ', 'u'),
    ('ɡ', 'g'),
    ('ɔ', 'o'),
    ('ɪ','i'),

]]

def german_to_ipa(text):
    text = unidecode(text).lower()
    text = normalize_numbers(text)
    phonemes = ipa.convert(text)
    phonemes = ipa.collapse_whitespace(phonemes)
    for regex, replacement in _lazy_ipa2:
        phonemes = re.sub(regex, replacement, phonemes)
    return phonemes

def german_to_lazy_ipa2(text):
    text = german_to_ipa(text)
    for regex, replacement in _lazy_ipa2:
        text = re.sub(regex, replacement, text)
    return text