# TODO check file for exist

f = open(filename, 'r')

s = f.readline()

result = set(s[:-1])

while s:

s = f.readline()

if s:

result.add(s[:-1])

if not line:

return False

if len(line.split(delimiter)) != 2:

return False

# input: {"ts": ts, "pos": pos, "word": word }

# output: <span style="color: #aaa;">(adv.)</span> actually<br/><span style="color: #666;">/ˈæˌktʃuəli, ˈæktʃli, ˈækʃəli/</span> на самом деле

result = '<span style="color: #aaa;">{pos}</span> {word}<br/><span style="color: #666;">{ts}</span>{tab}{rus}'

pos = ts = ""

if words_dict["pos"]:

pos = "(" + words_dict["pos"] + ")"

if words_dict["ts"].strip():

ts = "/ " + words_dict["ts"] + " /"

result = '<span style="color: #aaa;">{pos}</span> {word}<br/><span style="color: #666;">{ts}</span>{tab}{rus}'

ts = "/"

if pos:

pos = "(" + pos + ")"

for word in words_dict:

if word["ts"].strip() != "":

ts = ts + " " + word["ts"] + " "

ts += "/"

if ts == "//":

ts = ""

"""

>>> handle_line("● Blow away the cobwebs - прогуляться, проветриться")

'Blow away the cobwebs - прогуляться, проветриться'

>>> handle_line("verb [vɜːb] - глагол")

'verb - глагол'

>>> handle_line("verb - глагол(pew) ")

'verb - глагол'

>>> handle_line("fall down – 1) пасть ниц; 2) потерпеть неудачу")

'fall down – 1) пасть ниц; 2) потерпеть неудачу'

:param line:

:return handled line:

"""

# remove [] and ()

while ("[" in line and "]" in line) or ("(" in line and ")" in line):

cutted_line = re.split("\[*\]*", line)

if len(cutted_line) > 1:

del cutted_line[1]

line = " ".join(cutted_line)

cutted_line = re.split("\(*\)*", line)

if len(cutted_line) > 1:

del cutted_line[1]

line = " ".join(cutted_line)

for i in range(len(line)):

if line[i].lower() in ENGLISH_LETTERS or line[i].lower() in RUSSIAN_LETTERS:

break

line = line[i:]

assert type(words) == list

assert len(words) > 1

words_external = []

for word in words:

if len(word) > 2:

words_external.append(dict_api.lookup_ts_pos_force(word))

pos = ""

for word in words_external:

if word["pos"]:

pos = word["pos"]

break

for word in words_external:

if word["pos"] and word["pos"] != pos:

pos = ""

break

assert type(words) == list

if len(words) == 0:

return ""

if len(words) == 1:

ts_pos = dict_api.lookup_ts_pos_force(words[0])

return make_beauty_1_word(ts_pos)

else:

"""

>>> find_delimiter("resume - резюме")

' - '

>>> find_delimiter("occupation — занятие")

' — '

>>> find_delimiter('unemployed / jobless / out-of-work / man out of occupation - безработный')

' - '

>>> find_delimiter("lose (lost, lost) one's job - потерять работу")

' - '

>>> find_delimiter('lump-sum allowance - единовременное пособие')

' - '

>>> find_delimiter('lump-sum allowance — единовременное пособие')

' — '

>>> find_delimiter("43. What's the idea of - В чём смысл, что за глупость -")

' - '

>>> find_delimiter('Мне нужно лекарство от простуды. — I need a cold medicine.')

' — '

:param text:

:return dash:

"""

# in PyCharm they looks similar, but they are differ

if not dash_types:

dash_types = [' — ', ' - ', ' - ']

# current dash is right if it's relevant for more then koeff*100% strings.

koeff = 0.5

for dash in dash_types:

all_line = 0

suitable_for_this_delimiter = 0

for line in text.split("\n"):

if line.strip() != "":

all_line += 1

if len(line.split(dash)) == 2:

l_part, r_part = line.split(dash)

if is_english(l_part) and is_russian(r_part) or is_russian(l_part) and is_english(r_part):

suitable_for_this_delimiter += 1

if float(suitable_for_this_delimiter)/all_line > koeff:

return dash

# logging.error("delimiter not found. text:" + text)

"""

:param text:

:return delimiter:

"""

handled_text = []

possible_delimiter = []

for line in text.split("\n"):

if line.strip() != "" and re.search("[a-zA-Z]+", line) and re.search("[а-яА-Я]+", line):

handled_text.append(line)

for line in handled_text:

possible_delimiter.append(find_delimiter_euristic_line(line))

delimiters_dict = {}

for d in possible_delimiter:

if d not in delimiters_dict.keys():

delimiters_dict[d] = 1

else:

delimiters_dict[d] += 1

delimiter_amount_max = 0

delimiter_most_popular = ""

for delimiter, delimiter_amount in delimiters_dict.items():

if delimiter_amount > delimiter_amount_max:

delimiter_amount = delimiter_amount_max

delimiter_most_popular = delimiter

# если длина делимитера >2, то вероятно он определился не так

# вместо =, определился ...=

if len(delimiter_most_popular) > max_delimiter_size:

logging.info("Delimiter too long:{}".format(delimiter_most_popular))

short_possible_delimiter = set()

# отбираем возможные

for delimiter in possible_delimiter:

if len(delimiter) <= max_delimiter_size:

short_possible_delimiter.add(delimiter)

for pretendent_delimiter in short_possible_delimiter:

relevant = 0

for delimiter in possible_delimiter:

if pretendent_delimiter in delimiter:

relevant += 1

if relevant/len(possible_delimiter) > stake_for_approve_delimiter:

logging.info("I think this delimiter better:{}".format(pretendent_delimiter))

return pretendent_delimiter

"""

>>> find_delimiter_euristic_line("startle at smth– вздрогнуть от чего-то")

'–'

>>> find_delimiter_euristic_line(" pew/PEW-wow @ пышь/ПЫШЬ")

'@'

>>> find_delimiter_euristic_line(" пышь/ПЫШЬ @ pew/PEW-wow ")

'@'

>>> find_delimiter_euristic_line("superior — превосходный")

'—'

>>> find_delimiter_euristic_line("lovey-dovey — шаловливый, игривый, влюбленный (ame)")

problem with euristic detection delimiter in line: lovey-dovey — шаловливый, игривый, влюбленный (ame)

''

:param line:

:return:

"""

finish_1st_part = 0

start_2nd_part = 0

line = line.strip().lower()

# Eng -> Rus

if line[0] in ENGLISH_LETTERS:

first_languages_letters = ENGLISH_LETTERS

second_langueage_letters = RUSSIAN_LETTERS

else:

first_languages_letters = RUSSIAN_LETTERS

second_langueage_letters = ENGLISH_LETTERS

for letter_no in range(len(line)):

if line[letter_no] in first_languages_letters:

finish_1st_part = letter_no

if line[letter_no] in second_langueage_letters and not start_2nd_part:

start_2nd_part = letter_no

if start_2nd_part <= finish_1st_part:

print("problem with euristic detection delimiter in line: {}".format(line))

return ""

delimiter = line[finish_1st_part+1:start_2nd_part].strip()

"""

>>> is_english('abc')

True

>>> is_english('unemployed / jobless / out-of-work / man out of occupation - ')

True

>>> is_english('43. Whats the idea of - В чём смысл, что за глупость -')

False

:param text:

:return boolean:

"""

if re.findall('[а-яА-Я]+', text):

return False

else:

"""

>>> is_russian("абв")

True

>>> is_russian('43. Whats the idea of - В чём смысл, что за глупость -')

False

>>> is_russian("Хотите за 3 минуты узнать свой словарный запас английских слов? ")

True

:param text:

:return boolean:

"""

if re.findall('[a-zA-Z]+', text):

return False

else: