def assign_country_codes(filtered_languages, all_languages):
sorted_languages = sorted(
all_languages,
key=lambda lang: len(all_languages[lang].get('counter', [])),
reverse=True)
previous_lang = None
previous_code = None
countries = 0
for current_code in sorted(filtered_languages):
current_lang = current_code.split('-')[0]
# count country codes per language
if current_lang == previous_lang:
countries += 1
else:
if previous_lang is not None:
# if language has no single country code
if countries == 0:
# try to get country code with most supported engines
for l in sorted_languages:
l_parts = l.split('-')
if len(l_parts) == 2 and l_parts[0] == previous_lang:
filtered_languages[l] = all_languages[l]
filtered_languages[l]['country'] = ''
countries = 1
break
if countries == 0:
# get most likely country code from babel
subtags = get_global('likely_subtags').get(
previous_lang)
if subtags:
subtag_parts = subtags.split('_')
new_code = subtag_parts[0] + '-' + subtag_parts[-1]
filtered_languages[new_code] = all_languages[
previous_lang]
countries = 1
if countries == 1:
# remove countryless version of language if there's only one country
del filtered_languages[previous_lang]
if previous_code in filtered_languages:
filtered_languages[previous_code]['country'] = ''
countries = 0
previous_lang = current_lang
previous_code = current_code
def assign_country_codes(filtered_languages, all_languages):
sorted_languages = sorted(all_languages,
key=lambda lang: len(all_languages[lang].get('counter', [])),
reverse=True)
previous_lang = None
previous_code = None
countries = 0
for current_code in sorted(filtered_languages):
current_lang = current_code.split('-')[0]
# count country codes per language
if current_lang == previous_lang:
countries += 1
else:
if previous_lang is not None:
# if language has no single country code
if countries == 0:
# try to get country code with most supported engines
for l in sorted_languages:
l_parts = l.split('-')
if len(l_parts) == 2 and l_parts[0] == previous_lang:
filtered_languages[l] = all_languages[l]
filtered_languages[l]['country'] = ''
countries = 1
break
if countries == 0:
# get most likely country code from babel
subtags = get_global('likely_subtags').get(previous_lang)
if subtags:
subtag_parts = subtags.split('_')
new_code = subtag_parts[0] + '-' + subtag_parts[-1]
filtered_languages[new_code] = all_languages[previous_lang]
countries = 1
if countries == 1:
# remove countryless version of language if there's only one country
del filtered_languages[previous_lang]
if previous_code in filtered_languages:
filtered_languages[previous_code]['country'] = ''
countries = 0
previous_lang = current_lang
previous_code = current_code
def filter_language_list(all_languages):
min_engines_per_lang = 15
min_engines_per_country = 10
main_engines = [
engine_name for engine_name in engines.keys()
if 'general' in engines[engine_name].categories
and engines[engine_name].supported_languages
and not engines[engine_name].disabled
]
# filter list to include only languages supported by most engines or all default general engines
filtered_languages = {
code: lang
for code, lang in all_languages.items()
if (len(lang['counter']) >= min_engines_per_lang or all(
main_engine in lang['counter'] for main_engine in main_engines))
}
def _copy_lang_data(lang, country_name=None):
new_dict = dict()
new_dict['name'] = all_languages[lang]['name']
new_dict['english_name'] = all_languages[lang]['english_name']
if country_name:
new_dict['country_name'] = country_name
return new_dict
def _country_count(i):
return len(countries[sorted_countries[i]]['counter'])
# for each language get country codes supported by most engines or at least one country code
filtered_languages_with_countries = dict()
for lang, lang_data in filtered_languages.items():
countries = lang_data['countries']
filtered_countries = dict()
# get language's country codes with enough supported engines
for lang_country, country_data in countries.items():
if len(country_data['counter']) >= min_engines_per_country:
filtered_countries[lang_country] = _copy_lang_data(
lang, country_data['country_name'])
# add language without countries too if there's more than one country to choose from
if len(filtered_countries) > 1:
filtered_countries[lang] = _copy_lang_data(lang)
elif len(filtered_countries) == 1:
# if there's only one country per language, it's not necessary to show country name
lang_country = next(iter(filtered_countries))
filtered_countries[lang_country]['country_name'] = None
# if no country has enough engines try to get most likely country code from babel
if not filtered_countries:
lang_country = None
subtags = get_global('likely_subtags').get(lang)
if subtags:
country_code = subtags.split('_')[-1]
if len(country_code) == 2:
lang_country = "{lang}-{country}".format(
lang=lang, country=country_code)
if lang_country:
filtered_countries[lang_country] = _copy_lang_data(lang)
else:
filtered_countries[lang] = _copy_lang_data(lang)
filtered_languages_with_countries.update(filtered_countries)
return filtered_languages_with_countries