def update_entry(entry: dict) -> dict:
name = entry["PaxName"].split()
# Get name.
entry["PassengerLastName"] = name[0] if len(name) >= 1 else ""
entry["PassengerFirstName"] = name[1] if len(name) >= 2 else ""
entry["PassengerSecondName"] = name[2] if len(name) >= 3 else ""
entry["PassengerFirstName_en"] = (transliterate(
entry["PassengerFirstName"]).replace("'", "").upper())
entry["PassengerSecondName_en"] = (transliterate(
entry["PassengerSecondName"]).replace("'", "").upper())
entry["PassengerLastName_en"] = (transliterate(
entry["PassengerLastName"]).replace("'", "").upper())
entry["PassengerFirstName_sx"] = soundex(entry["PassengerFirstName_en"])
entry["PassengerSecondName_sx"] = soundex(entry["PassengerSecondName_en"])
entry["PassengerLastName_sx"] = soundex(entry["PassengerLastName_en"])
# Transliterate name.
entry["PassengerFirstName_en"] = (translit(entry["PassengerFirstName"],
"ru",
reversed=True).replace(
"'", "").upper())
entry["PassengerSecondName_en"] = (translit(entry["PassengerSecondName"],
"ru",
reversed=True).replace(
"'", "").upper())
entry["PassengerLastName_en"] = (translit(entry["PassengerLastName"],
"ru",
reversed=True).replace(
"'", "").upper())
return entry
def check_for_english_alternative(unwords, eng_words):
possible_replace_words = set()
for uword in unwords:
transliterated_word = transliteration.transliterate(uword)
for ew in eng_words:
if levenstein.levenshtein_ratio_and_distance(
transliterated_word, ew, ratio_calc=True) > 0.9:
# print(f'---bg---{uword}---transliterated as---{transliterated_word} --- is close to---{ew}')
possible_replace_words.add(uword)
return possible_replace_words
def main(filter_region=None):
csv.register_dialect('csv', delimiter=';', quoting=csv.QUOTE_NONE)
regions = {}
with open(config.VLAN_PATH, 'r', encoding='utf-8-sig') as xl:
result = csv.reader(xl, 'csv')
for row in result:
if row[0] != '' and row[1] == '':
regions.update({transliterate(row[0]): []})
elif len(row) == 16 and transliterate(row[15]) in regions:
regions[transliterate(row[15])].append(row)
else:
regions.update({'description': row})
if (os.path.isfile(config.VLAN_PATH_JSON)):
os.remove(config.VLAN_PATH_JSON)
json_file = open(config.VLAN_PATH_JSON, 'a+', encoding='utf-8-sig')
json_file.write(json.dumps(regions))
json_file.close()
def on_transliterate():
global browser_context
global trans_var
global current_row
global trans_widget
global hidden
trans_var.set("Loading...")
if browser_context is None:
browser_context = get_browser_context()
try:
transliteration = transliterate(browser_context, current_row[1])
trans_var.set("To Roman Urdu")
trans_widget.pack()
trans_widget.delete(1.0, tk.END)
trans_widget.insert(tk.END, "{}".format(transliteration))
hidden = False
except:
trans_var.set("Error Loading")
browser_context = get_browser_context()
def identify(word, lang='H'):
word = word.lower().replace(',', '').replace('.', '')
english_probability = 1.
other_probability = 1.
slang_probability = 1.
word = handle_slang_words(word)
# print '***', word, slang_dictionary()[word] if word in slang_dictionary() else False
if word in slang_dictionary():
slang_probability *= 0.8
english_probability *= 0.1
other_probability *= 0.1
e_syn_set = word_synset(word)
o_best_words = []
o_words = transliterate(word, lang)
# print o_words
for ow in o_words:
o_synsets = word_synset(ow, lang=lang)
o_top_word = top_other_words(ow, lang)
if o_synsets and len(o_synsets) > 0 and o_top_word:
o_best_words.append((ow, o_synsets, True))
elif o_synsets and len(o_synsets) > 0:
o_best_words.append((ow, o_synsets, False))
elif o_top_word:
o_best_words.append((ow, None, None))
if o_best_words and len(o_best_words) > 0:
o_best_words = sorted(o_best_words,
key=lambda item: len(item[1]) if item[1] else 0,
reverse=True)
if o_best_words and len(o_best_words) > 0:
slang_probability *= 0.30
english_probability *= 0.30
other_probability *= 0.40
if any(u[2] for u in o_best_words):
slang_probability *= 0.25
english_probability *= 0.25
other_probability *= 0.5
elif sum(1 for u in o_best_words if u[1] is not None) > 0:
slang_probability *= 0.30
english_probability *= 0.30
other_probability *= 0.40
if e_syn_set is not None:
slang_probability *= 0.30
english_probability *= 0.40
other_probability *= 0.30
if top_english_words(word):
slang_probability *= 0.15
english_probability *= 0.7
other_probability *= 0.15
if slang_probability > english_probability and slang_probability > other_probability:
return word, 'S', [slang_dictionary()[word]]
elif english_probability > other_probability:
return word, 'E', []
else:
values = word, 'O', [u[0] for u in o_best_words]
return values
def transliterate_massage(update, context):
"""Transliterate the the user message from Hebrew to Syriac or vice versa."""
update.effective_message.reply_text(
transliterate(update.effective_message.text))
def testEnglishToHindi():
result = t.transliterate(en, "hi_IN")
print result.encode('utf-8')