expected-big-50.txt

defaultdict(collections.Counter,
            {'project': Counter({'Project': 5, 'PROJECT': 1}),
             'gutenberg': Counter({'Gutenberg': 3, 'GUTENBERG': 1}),
             'ebook': Counter({'EBook': 1}),
             'of': Counter({'of': 6, 'OF': 3}),
             'the': Counter({'The': 3, 'the': 8, 'THE': 2}),
             'adventures': Counter({'Adventures': 2, 'ADVENTURES': 2}),
             'sherlock': Counter({'Sherlock': 2, 'SHERLOCK': 1}),
             'holmes': Counter({'Holmes': 2, 'HOLMES': 2}),
             'sir': Counter({'Sir': 3}),
             'arthur': Counter({'Arthur': 3}),
             'conan': Counter({'Conan': 3}),
             'doyle': Counter({'Doyle': 2}),
             'in': Counter({'in': 2}),
             'our': Counter({'our': 1}),
             'series': Counter({'series': 1}),
             'by': Counter({'by': 2, 'By': 3}),
             'doyle)': Counter({'Doyle)': 1}),
             'laws': Counter({'laws': 2}),
             'are': Counter({'are': 1}),
             'changing': Counter({'changing': 1}),
             'all': Counter({'all': 1}),
             'over': Counter({'over': 1}),
             'world.': Counter({'world.': 1}),
             'be': Counter({'Be': 1, 'be': 2}),
             'sure': Counter({'sure': 1}),
             'to': Counter({'to': 4, 'To': 1}),
             'check': Counter({'check': 1}),
             'for': Counter({'for': 1}),
             'your': Counter({'your': 2}),
             'country': Counter({'country': 1}),
             'before': Counter({'before': 1}),
             'downloading': Counter({'downloading': 1}),
             'or': Counter({'or': 3}),
             'redistributing': Counter({'redistributing': 1}),
             'any': Counter({'any': 1}),
             'other': Counter({'other': 2}),
             'ebook.': Counter({'eBook.': 1}),
             'header': Counter({'header': 1}),
             'should': Counter({'should': 1}),
             'first': Counter({'first': 1}),
             'thing': Counter({'thing': 1}),
             'seen': Counter({'seen': 1}),
             'when': Counter({'when': 1}),
             'viewing': Counter({'viewing': 1}),
             'this': Counter({'this': 2}),
             'file.': Counter({'file.': 2}),
             'please': Counter({'Please': 1}),
             'do': Counter({'do': 1, 'Do': 1}),
             'not': Counter({'not': 2}),
             'remove': Counter({'remove': 1}),
             'it.': Counter({'it.': 1}),
             'change': Counter({'change': 1}),
             'edit': Counter({'edit': 1}),
             'without': Counter({'without': 1}),
             'written': Counter({'written': 1}),
             'permission.': Counter({'permission.': 1}),
             'read': Counter({'read': 1}),
             '"legal': Counter({'"legal': 1}),
             'small': Counter({'small': 1}),
             'print,"': Counter({'print,"': 1}),
             'and': Counter({'and': 5}),
             'information': Counter({'information': 2}),
             'about': Counter({'about': 3}),
             'at': Counter({'at': 1}),
             'bottom': Counter({'bottom': 1}),
             'included': Counter({'Included': 1}),
             'is': Counter({'is': 1}),
             'specific': Counter({'specific': 1}),
             'rights': Counter({'rights': 1}),
             'restrictions': Counter({'restrictions': 1}),
             'file': Counter({'file': 1}),
             'may': Counter({'may': 1}),
             'used.': Counter({'used.': 1}),
             'you': Counter({'You': 1}),
             'can': Counter({'can': 1}),
             'also': Counter({'also': 1}),
             'find': Counter({'find': 1}),
             'out': Counter({'out': 1}),
             'how': Counter({'how': 2}),
             'make': Counter({'make': 1}),
             'a': Counter({'a': 1}),
             'gutenberg,': Counter({'Gutenberg,': 1}),
             'get': Counter({'get': 1}),
             'involved.': Counter({'involved.': 1}),
             'world': Counter({'World': 1}),
             'free': Counter({'Free': 1}),
             'plain': Counter({'Plain': 1}),
             'vanilla': Counter({'Vanilla': 1}),
             'electronic': Counter({'Electronic': 1}),
             'texts**': Counter({'Texts**': 1}),
             'readable': Counter({'Readable': 1}),
             'both': Counter({'Both': 1}),
             'humans': Counter({'Humans': 1}),
             'computers,': Counter({'Computers,': 1}),
             'since': Counter({'Since': 1}),
             'ebooks': Counter({'eBooks': 1}),
             'were': Counter({'Were': 1}),
             'prepared': Counter({'Prepared': 1}),
             'thousands': Counter({'Thousands': 1}),
             'volunteers!*****': Counter({'Volunteers!*****': 1}),
             'date:': Counter({'Date:': 1}),
             'march,': Counter({'March,': 1}),
             '[ebook': Counter({'[EBook': 1}),
             'recently': Counter({'recently': 1}),
             'updated:': Counter({'updated:': 1}),
             'november': Counter({'November': 1}),
             'english': Counter({'English': 1}),
             'set': Counter({'set': 1}),
             'encoding:': Counter({'encoding:': 1}),
             'ascii': Counter({'ASCII': 1}),
             'start': Counter({'START': 1}),
             'ebook,': Counter({'EBOOK,': 1}),
             'editing': Counter({'editing': 1}),
             'jose': Counter({'Jose': 1}),
             'menendez)': Counter({'Menendez)': 1})})