def check_segments(): segments = [] infile = codecs.open(filename, 'r', 'utf-8') headers = TagTester(u'@30', infile, u'@30מצוה ([\u05d0-\u05ea"]{1,5})').grab_each_header() tester = TagTester(u'@44', infile, u'@44\(([\u05d0-\u05ea]{1,2})\)') while not tester.eof: segments.append(tester.grab_each_header(u'@30מצוה ([\u05d0-\u05ea"]{1,5})', 1)) infile.close() for sec_number, section in enumerate(segments): index = 1 for title in section: title = title.replace(u'"', u'') count = util.getGematria(title) if count != index: print headers[sec_number-1] print util.numToHeb(index) index = count index += 1
def check_segments(): segments = [] infile = codecs.open(filename, 'r', 'utf-8') headers = TagTester(u'@30', infile, u'@30מצוה ([\u05d0-\u05ea"]{1,5})').grab_each_header() tester = TagTester(u'@44', infile, u'@44\(([\u05d0-\u05ea]{1,2})\)') while not tester.eof: segments.append( tester.grab_each_header(u'@30מצוה ([\u05d0-\u05ea"]{1,5})', 1)) infile.close() for sec_number, section in enumerate(segments): index = 1 for title in section: title = title.replace(u'"', u'') count = util.getGematria(title) if count != index: print headers[sec_number - 1] print util.numToHeb(index) index = count index += 1
def test_insert_chapters(filename, expected): with codecs.open(filename, 'r', 'utf-8') as infile: tester = TagTester(u'@22', infile, u'^@22\u05d0( |$)') if len(tester.grab_each_header()) == expected: return True else: return False
def check_chapters(): cards = get_cards() good_files, bad_files = [], [] for card in cards: m_ref = Ref(card.replace('Rambam ', '')) with codecs.open('{}.txt'.format(card), 'r', 'utf-8') as infile: tester = TagTester(u'@00', infile, u'@00\u05e4\u05e8\u05e7') tags = tester.grab_each_header() if len(tags) == len( m_ref.all_subrefs()) or card == 'Rambam Pirkei Avot': good_files.append(card) else: bad_files.append(card) return {'good': good_files, 'bad': bad_files}
def check_chapters(): with codecs.open('Minchat_Chinuch.txt', 'r', 'utf-8') as chinuch: test = TagTester(u'@30', chinuch, u'@30מצוה ([\u05d0-\u05ea"]{1,5})') index = 1 for header in test.grab_each_header(capture_group=1): header = header.replace(u'"', u'') count = util.getGematria(header) if count != index: print util.numToHeb(index) index = count index += 1
def check_chapters(): cards = get_cards() good_files, bad_files = [], [] for card in cards: m_ref = Ref(card.replace('Rambam ', '')) with codecs.open('{}.txt'.format(card), 'r', 'utf-8') as infile: tester = TagTester(u'@00', infile, u'@00\u05e4\u05e8\u05e7') tags = tester.grab_each_header() if len(tags) == len(m_ref.all_subrefs()) or card == 'Rambam Pirkei Avot': good_files.append(card) else: bad_files.append(card) return { 'good': good_files, 'bad': bad_files }