def check_ipa_known_segs(mappings_to_check=False):
dst = distance.Distance()
if not mappings_to_check:
mappings_to_check = [x['out_lang'] for x in MAPPINGS_AVAILABLE]
found_error = False
for mapping in [
x for x in MAPPINGS_AVAILABLE if x['out_lang'] in mappings_to_check
]:
if mapping['out_lang'].endswith('-ipa'):
for rule in mapping['mapping_data']:
joined_ipa_segs = ''.join(dst.fm.ipa_segs(rule['out']))
if not joined_ipa_segs == rule['out']:
LOGGER.warning(
f"Output '{rule['out']}' in rule {rule} in mapping between {mapping['in_lang']} and {mapping['out_lang']} is not recognized as valid IPA by panphon. You may ignore this warning if you know it gets remapped to IPA later."
)
found_error = True
if found_error:
LOGGER.warning(
"Please refer to https://github.com/dmort27/panphon for information about panphon."
)
def get_multitree(voc_fd, lang_id):
"""Get a multitree for the given language."""
# Get a dict() where each key is a letter and each value
# is a BK tree of the words that start with that letter
dst = distance.Distance()
ed = EditDistanceWrapper(lang_id, dst, phonemise)
distractors = {}
for line in voc_fd.readlines():
(f, w) = line.strip("\n").split("\t")
first_letter = w[0].lower()
if first_letter not in distractors:
distractors[first_letter] = []
distractors[first_letter].append(w.lower())
distractors_tree = {}
for letter in distractors:
distractors_tree[letter] = pybktree.BKTree(
ed.edit_distance,
distractors[letter],
)
return distractors_tree
def setUp(self):
self.dist = distance.Distance(feature_model=feature_model)
def setUp(self):
self.dist = distance.Distance(feature_model=feature_model)
self.ft = panphon.FeatureTable()