Merge pull request #25 from abhillman/master

Update valid cc and global TLDs

Author: dryan

twitter_text/regex.py

@@ -180,8 +180,8 @@ def regex_range(start, end = None):
 DOMAIN_VALID_CHARS = ur'[^%s%s%s%s%s]' % (PUNCTUATION_CHARS, SPACE_CHARS, CTRL_CHARS, ur''.join(REGEXEN['invalid_control_characters']), ur''.join(UNICODE_SPACES))
 REGEXEN['valid_subdomain'] = re.compile(ur'(?:(?:%s(?:[_-]|%s)*)?%s\.)' % (DOMAIN_VALID_CHARS, DOMAIN_VALID_CHARS, DOMAIN_VALID_CHARS), re.IGNORECASE | re.UNICODE)
 REGEXEN['valid_domain_name'] = re.compile(ur'(?:(?:%s(?:[-]|%s)*)?%s\.)' % (DOMAIN_VALID_CHARS, DOMAIN_VALID_CHARS, DOMAIN_VALID_CHARS), re.IGNORECASE | re.UNICODE)
-REGEXEN['valid_gTLD'] = re.compile(ur'(?:(?:aero|asia|biz|cat|com|coop|edu|gov|info|int|jobs|mil|mobi|museum|name|net|org|pro|tel|travel|xxx)(?=[^0-9a-z]|$))', re.IGNORECASE | re.UNICODE)
-REGEXEN['valid_ccTLD'] = re.compile(ur'(?:(?:ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw)(?=[^0-9a-z]|$))', re.IGNORECASE | re.UNICODE)
+REGEXEN['valid_gTLD'] = re.compile(ur'(?:(?:academy|actor|aero|agency|arpa|asia|bar|bargains|berlin|best|bid|bike|biz|blue|boutique|build|builders|buzz|cab|camera|camp|cards|careers|cat|catering|center|ceo|cheap|christmas|cleaning|clothing|club|codes|coffee|com|community|company|computer|construction|contractors|cool|coop|cruises|dance|dating|democrat|diamonds|directory|domains|edu|education|email|enterprises|equipment|estate|events|expert|exposed|farm|fish|flights|florist|foundation|futbol|gallery|gift|glass|gov|graphics|guitars|guru|holdings|holiday|house|immobilien|industries|info|institute|int|international|jobs|kaufen|kim|kitchen|kiwi|koeln|kred|land|lighting|limo|link|luxury|management|mango|marketing|menu|mil|mobi|moda|monash|museum|nagoya|name|net|neustar|ninja|okinawa|onl|org|partners|parts|photo|photography|photos|pics|pink|plumbing|post|pro|productions|properties|pub|qpon|recipes|red|rentals|repair|report|reviews|rich|ruhr|sexy|shiksha|shoes|singles|social|solar|solutions|supplies|supply|support|systems|tattoo|technology|tel|tienda|tips|today|tokyo|tools|training|travel|uno|vacations|ventures|viajes|villas|vision|vote|voting|voto|voyage|wang|watch|wed|wien|wiki|works|xxx|xyz|zone|дети|онлайн|орг|сайт|بازار|شبكة|みんな|中信|中文网|公司|公>益|在线|我爱你|政务|游戏|移动|网络|集团|삼성)(?=[^0-9a-z]|$))', re.IGNORECASE | re.UNICODE)
+REGEXEN['valid_ccTLD'] = re.compile(ur'(?:(?:ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bl|bm|bn|bo|bq|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cu|cv|cw|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mf|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|um|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw|мон|рф|срб|укр|қаз|الاردن|الجزائر|السعودية|المغرب|امارات|ایران|بھارت|تونس|سودان|سورية|عمان|فلسطين|قطر|مصر|مليسيا|پاکستان|भारत|বাংলা|ভারত|ਭਾਰਤ|ભારત|இந்தியா|இலங்கை|சிங்கப்பூர்|భారత్|ලංකා|ไทย|გე|中国|中加坡|湾|台灣|新香港|한국)(?=[^0-9a-z]|$))', re.IGNORECASE | re.UNICODE)
 REGEXEN['valid_punycode'] = re.compile(ur'(?:xn--[0-9a-z]+)', re.IGNORECASE | re.UNICODE)
 
 REGEXEN['valid_domain'] = re.compile(ur'(?:%s*%s(?:%s|%s|%s))' % (REGEXEN['valid_subdomain'].pattern, REGEXEN['valid_domain_name'].pattern, REGEXEN['valid_gTLD'].pattern, REGEXEN['valid_ccTLD'].pattern, REGEXEN['valid_punycode'].pattern), re.IGNORECASE | re.UNICODE)