<p>下面是一个小的python脚本。
你仍然需要编辑一些由几个单词组成的国家。你知道吗</p>
<pre><code>file_name = "nat.txt"
with open(file_name) as f:
for line in f:
for word in line.split(" "):
print "(\'" + word.decode('utf-8').upper().encode('utf-8') +"\', \'" + word +"\'),"
</code></pre>
<p>它还处理unicode字符</p>
<p>最后的名单是:</p>
<pre><code>('AFGHANS', 'Afghans'),
('ALBANIANS', 'Albanians'),
('ALGERIANS', 'Algerians'),
('AMERICANS', 'Americans'),
('ANDORRANS', 'Andorrans'),
('ANGOLANS', 'Angolans'),
('ARGENTINES', 'Argentines'),
('ARMENIANS', 'Armenians'),
('AROMANIANS', 'Aromanians'),
('ARUBANS', 'Arubans'),
('AUSTRALIANS', 'Australians'),
('AUSTRIANS', 'Austrians'),
('AZERBAIJANIS', 'Azerbaijanis'),
('BAHAMIANS', 'Bahamians'),
('BAHRAINIS', 'Bahrainis'),
('BANGLADESHIS', 'Bangladeshis'),
('BARBADIANS', 'Barbadians'),
('BASOTHO', 'Basotho'),
('BASQUES', 'Basques'),
('BELARUSIANS', 'Belarusians'),
('BELGIANS', 'Belgians'),
('BELIZEANS', 'Belizeans'),
('BERMUDIANS', 'Bermudians'),
('BOERS', 'Boers'),
('BOSNIAKS', 'Bosniaks'),
('BRAZILIANS', 'Brazilians'),
('BRETONS', 'Bretons'),
('BRITISH', 'British'),
('BRITISH', 'British'),
('VIRGIN', 'Virgin'),
('ISLANDERS', 'Islanders'),
('BRUNEIANS', 'Bruneians'),
('BULGARIANS', 'Bulgarians'),
('MACEDONIAN', 'Macedonian'),
('BULGARIANS', 'Bulgarians'),
('BURKINABÈS', 'Burkinabès'),
('BURUNDIANS', 'Burundians'),
('CAMBODIANS', 'Cambodians'),
('CAMEROONIANS', 'Cameroonians'),
('CANADIANS', 'Canadians'),
('CATALANS', 'Catalans'),
('CAPE', 'Cape'),
('VERDEANS', 'Verdeans'),
('CHADIANS', 'Chadians'),
('CHILEANS', 'Chileans'),
('CHINESE', 'Chinese'),
('COLOMBIANS', 'Colombians'),
('COMORIANS', 'Comorians'),
('CONGOLESE', 'Congolese'),
('CROATIANS', 'Croatians'),
('CUBANS', 'Cubans'),
('CYPRIOTS', 'Cypriots'),
('TURKISH', 'Turkish'),
('CYPRIOTS', 'Cypriots'),
('CZECHS', 'Czechs'),
('DANES', 'Danes'),
('DOMINICANS', 'Dominicans'),
('(REPUBLIC)', '(Republic)'),
('DOMINICANS', 'Dominicans'),
('(COMMONWEALTH)', '(Commonwealth)'),
('DUTCH', 'Dutch'),
('EAST', 'East'),
('TIMORESE', 'Timorese'),
('ECUADORIANS', 'Ecuadorians'),
('EGYPTIANS', 'Egyptians'),
('EMIRATIS', 'Emiratis'),
('ENGLISH', 'English'),
('ERITREANS', 'Eritreans'),
('ESTONIANS', 'Estonians'),
('ETHIOPIANS', 'Ethiopians'),
('FALKLAND', 'Falkland'),
('ISLANDERS', 'Islanders'),
('FAROESE', 'Faroese'),
('FINNS', 'Finns'),
('FINNISH', 'Finnish'),
('SWEDISH', 'Swedish'),
('FIJIANS', 'Fijians'),
('FILIPINOS', 'Filipinos'),
('FRENCH', 'French'),
('CITIZENS', 'citizens'),
('GEORGIANS', 'Georgians'),
('GERMANS', 'Germans'),
('BALTIC', 'Baltic'),
('GERMANS', 'Germans'),
('GHANAIANS', 'Ghanaians'),
('GIBRALTAR', 'Gibraltar'),
('GREEKS', 'Greeks'),
('GREEK', 'Greek'),
('MACEDONIANS', 'Macedonians'),
('GRENADIANS', 'Grenadians'),
('GUATEMALANS', 'Guatemalans'),
('GUIANESE', 'Guianese'),
('(FRENCH)', '(French)'),
('GUINEANS', 'Guineans'),
('GUINEA-BISSAU', 'Guinea-Bissau'),
('NATIONALS', 'nationals'),
('GUYANESE', 'Guyanese'),
('HAITIANS', 'Haitians'),
('HONDURANS', 'Hondurans'),
('HONG', 'Hong'),
('KONG', 'Kong'),
('HUNGARIANS', 'Hungarians'),
('ICELANDERS', 'Icelanders'),
('I-KIRIBATI', 'I-Kiribati'),
('INDIANS', 'Indians'),
('INDONESIANS', 'Indonesians'),
('IRANIANS', 'Iranians'),
('IRAQIS', 'Iraqis'),
('IRISH', 'Irish'),
('ISRAELIS', 'Israelis'),
('ITALIANS', 'Italians'),
('IVOIRIANS', 'Ivoirians'),
('JAMAICANS', 'Jamaicans'),
('JAPANESE', 'Japanese'),
('JORDANIANS', 'Jordanians'),
('KAZAKHS', 'Kazakhs'),
('KENYANS', 'Kenyans'),
('KOREANS', 'Koreans'),
('KOSOVARS', 'Kosovars'),
('KURDS', 'Kurds'),
('KUWAITIS', 'Kuwaitis'),
('KYRGYZS', 'Kyrgyzs'),
('LAO', 'Lao'),
('LATVIANS', 'Latvians'),
('LEBANESE', 'Lebanese'),
('LIBERIANS', 'Liberians'),
('LIBYANS', 'Libyans'),
('LIECHTENSTEINERS', 'Liechtensteiners'),
('LITHUANIANS', 'Lithuanians'),
('LUXEMBOURGERS', 'Luxembourgers'),
('MACAO', 'Macao'),
('MACEDONIANS', 'Macedonians'),
('MALAGASY', 'Malagasy'),
('MALAYSIANS', 'Malaysians'),
('MALAWIANS', 'Malawians'),
('MALDIVIANS', 'Maldivians'),
('MALIANS', 'Malians'),
('MALTESE', 'Maltese'),
('MANX', 'Manx'),
('MAURITIANS', 'Mauritians'),
('MEXICANS', 'Mexicans'),
('MOLDOVANS', 'Moldovans'),
('MOROCCANS', 'Moroccans'),
('MONGOLIANS', 'Mongolians'),
('MONTENEGRINS', 'Montenegrins'),
('NAMIBIANS', 'Namibians'),
('NEPALESE', 'Nepalese'),
('NEW', 'New'),
('ZEALANDERS', 'Zealanders'),
('NICARAGUANS', 'Nicaraguans'),
('NIGERIENS', 'Nigeriens'),
('NIGERIANS', 'Nigerians'),
('NORWEGIANS', 'Norwegians'),
('PAKISTANIS', 'Pakistanis'),
('PALAUANS', 'Palauans'),
('PALESTINIANS', 'Palestinians'),
('PANAMANIANS', 'Panamanians'),
('PAPUA', 'Papua'),
('NEW', 'New'),
('GUINEANS', 'Guineans'),
('PARAGUAYANS', 'Paraguayans'),
('PERUVIANS', 'Peruvians'),
('POLES', 'Poles'),
('PORTUGUESE', 'Portuguese'),
('PUERTO', 'Puerto'),
('RICANS', 'Ricans'),
('QUEBECERS', 'Quebecers'),
('RÉUNIONNAIS', 'Réunionnais'),
('ROMANIANS', 'Romanians'),
('RUSSIANS', 'Russians'),
('BALTIC', 'Baltic'),
('RUSSIANS', 'Russians'),
('RWANDANS', 'Rwandans'),
('SALVADORANS', 'Salvadorans'),
('SÃO', 'São'),
('TOMÉ', 'Tomé'),
('AND', 'and'),
('PRÍNCIPE', 'Príncipe'),
('SAUDIS', 'Saudis'),
('SCOTS', 'Scots'),
('SENEGALESE', 'Senegalese'),
('SERBS', 'Serbs'),
('SIERRA', 'Sierra'),
('LEONEANS', 'Leoneans'),
('SINGAPOREANS', 'Singaporeans'),
('SINDHIAN', 'Sindhian'),
('SLOVAKS', 'Slovaks'),
('SLOVENES', 'Slovenes'),
('SOMALIS', 'Somalis'),
('SOMALILANDERS', 'Somalilanders'),
('SOUTH', 'South'),
('AFRICANS', 'Africans'),
('SPANIARDS', 'Spaniards'),
('SRI', 'Sri'),
('LANKANS', 'Lankans'),
('ST', 'St'),
('LUCIANS', 'Lucians'),
('SUDANESE', 'Sudanese'),
('SURINAMESE', 'Surinamese'),
('SWEDES', 'Swedes'),
('SWISS', 'Swiss'),
('SYRIACS', 'Syriacs'),
('SYRIANS', 'Syrians'),
('TAJIK', 'Tajik'),
('TAIWANESE', 'Taiwanese'),
('TANZANIANS', 'Tanzanians'),
('THAIS', 'Thais'),
('TIBETANS', 'Tibetans'),
('TOBAGONIANS', 'Tobagonians'),
('TRINIDADIANS', 'Trinidadians'),
('TUNISIANS', 'Tunisians'),
('TURKS', 'Turks'),
('TUVALUANS', 'Tuvaluans'),
('UGANDANS', 'Ugandans'),
('UKRAINIANS', 'Ukrainians'),
('URUGUAYANS', 'Uruguayans'),
('UZBEKS', 'Uzbeks'),
('VANUATUANS', 'Vanuatuans'),
('VENEZUELANS', 'Venezuelans'),
('VIETNAMESE', 'Vietnamese'),
('WELSH', 'Welsh'),
('YEMENIS', 'Yemenis'),
('ZAMBIANS', 'Zambians'),
('ZIMBABWEANS', 'Zimbabweans'),
('ASSYRIANS', 'Assyrians'),
('AZERIS', 'Azeris'),
('BASQUES', 'Basques'),
('BENGALIS', 'Bengalis'),
('BERBERS', 'Berbers'),
('BOERS', 'Boers'),
('BURYATS', 'Buryats'),
('CAJUNS', 'Cajuns'),
('CATALANS', 'Catalans'),
('CELTS', 'Celts'),
('CHUVASH', 'Chuvash'),
('GREEKS', 'Greeks'),
('HAN', 'Han'),
('CHINESE', 'Chinese'),
('HISPANIC', 'Hispanic'),
('AND', 'and'),
('LATINO', 'Latino'),
('AMERICANS', 'Americans'),
('HUTUS', 'Hutus'),
('IGBO', 'Igbo'),
('INDIGENOUS', 'Indigenous'),
('AUSTRALIANS', 'Australians'),
('INDIGENOUS', 'Indigenous'),
('PEOPLE', 'people'),
('OF', 'of'),
('THE', 'the'),
('AMERICAS', 'Americas'),
('FIRST', 'First'),
('NATIONS', 'Nations'),
('HUAORANI', 'Huaorani'),
('PEOPLE', 'people'),
('INUIT', 'Inuit'),
('CANADIAN', 'Canadian'),
('INUIT', 'Inuit'),
('GREENLANDIC', 'Greenlandic'),
('INUIT', 'Inuit'),
('MÉTIS', 'Métis'),
('PEOPLE', 'people'),
('NATIVE', 'Native'),
('AMERICANS', 'Americans'),
('JAPANESE', 'Japanese'),
('KAREN', 'Karen'),
('KODAVAS', 'Kodavas'),
('KURDS', 'Kurds'),
('MACEDONIANS', 'Macedonians'),
('MALAYS', 'Malays'),
('MONGOLIANS', 'Mongolians'),
('ROMA', 'Roma'),
('SAMIS', 'Samis'),
('SIKHS', 'Sikhs'),
('SILESIANS', 'Silesians'),
('SINHALESE', 'Sinhalese'),
('SYRIACS', 'Syriacs'),
('KANNADIGAS', 'Kannadigas'),
('TAMILS', 'Tamils'),
('TATARS', 'Tatars'),
('TUTSIS', 'Tutsis'),
('ZULUS', 'Zulus'),
</code></pre>
<p>编辑:</p>
<p>对于语言,您可以使用:</p>
<pre><code>file_name = "languages.txt" #each word on a separate line
with open(file_name) as f:
for line in f:
for word in line:
print "(\'" + word.decode('utf-8').upper().encode('utf-8') +"\', \'" + word +"\'),"
</code></pre>