+--------+------------------------------------------------------+
| code | meaning |
+========+======================================================+
| ^ | Start of string, or line |
+--------+------------------------------------------------------+
| $ | End of string, or line |
+--------+------------------------------------------------------+
| \A | Start of string |
+--------+------------------------------------------------------+
| \Z | End of string |
+--------+------------------------------------------------------+
| \b | Empty string at the beginning or end of a word |
+--------+------------------------------------------------------+
| \B | Empty string NOT at the beginning or end of a word |
+--------+------------------------------------------------------+
"""
from py_09_rePatterns import test_patterns
if __name__ == "__main__":
test_patterns([(r'^\w+', 'word at start of string'),
(r'\A\w+', 'word at start of string'),
(r'\w+\S*$', 'word near end of string'),
(r'\w+\S*\Z', 'word near end of string'),
(r'\w*t\w*', 'word containing t'),
(r'\bt\w+', 't at start of word'),
(r'\w+t\b', 't at end of word'),
(r'\Bt\B', 't, not start or end of word')],
'This is some text -- with punctuation.')
| code | meaning |
+========+=======================================+
| \d | A digit |
+--------+---------------------------------------+
| \D | A non-digit |
+--------+---------------------------------------+
| \s | Whitespace (tab, space, newline, etc.)|
+--------+---------------------------------------+
| \S | Non-whitespace |
+--------+---------------------------------------+
| \w | Alphanumeric |
+--------+---------------------------------------+
| \W | Non-alphanumeric |
+--------+---------------------------------------+
"""
from py_09_rePatterns import test_patterns
if __name__ == "__main__":
test_patterns(
[
(r'\d+', 'sequence of digits'),
(r'\D+', 'sequence of non-digits'),
(r'\s+', 'sequence of whitespace'),
(r'\S+', 'sequence of non-whitespace'),
(r'\w+', 'alphanumeric characters'),
(r'\W+', 'non-alphanumeric')
],
'A prime #1 example!'
)
r'(?P<ends_with_t>\w+t)\b',
]
for pattern in patterns:
regex = re.compile(pattern)
match = regex.search(text)
print("'{}'".format(pattern))
print(' ', match.groups())
print(' ', match.groupdict())
print()
if __name__ == "__main__":
test_patterns([
('a(ab)', 'a followed by literal ab'),
('a(a*b*)', 'a followed by 0-n a and 0-n b'),
('a(ab)*', 'a followed by 0-n ab'),
('a(ab)+', 'a followed by 1-n ab'),
], 'abbaaabbbbaaaaa')
# match.groups()
re_groups_match()
# index reference: match.group(index)
re_group_individual()
# name reference: match.groupdict()
re_groups_named()
# match.groupdict()
test_patterns_updated_ver(
[(r'a((a*)(b*))', 'a followed by optional 0-n a and 0-n b')],
'abbaabbba')
# match.groups() is useful for specifying alternative patterns. using pipe symbol(|)
test_patterns_updated_ver([
(r'a((a+)|(b+))', 'a then seq. of a or seq. of b'),
from py_09_rePatterns import test_patterns
if __name__ == "__main__":
test_patterns([
('[ab]', 'either a or b'),
('a[ab]+', 'a followed by 1 or more a or b'),
('a[ab]+?', 'a followed by 1 or more a or b, not greedy'),
], 'abbaabbba')
# exclude using ^. [^ ]
test_patterns([
('[^-. ]+', 'sequences without -, ., or space'),
], 'This is some text -- with punctuation.')
# ranges
test_patterns([
('[a-z]+', 'sequences of lowercase letters'),
('[A-Z]+', 'sequences of uppercase letters'),
('[a-zA-Z]+', 'sequences of lower- or uppercase letters'),
('[A-Z][a-z]+', 'one uppercase followed by lowercase'),
], 'This is some text -- with punctuation.')
# dot
test_patterns([('a.', 'a followed by any one character'),
('b.', 'b followed by any one character'),
('a.*b', 'a followed by anything, ending in b'),
('a.*?b', 'a followed by anything, ending in b')],
'abbaabbba')
# import sys, os
# sys.path.append(os.path.dirname(os.path.dirname(__file__)))
# from pkg.breaker import addBreaker
from py_09_rePatterns import test_patterns, text
if __name__ == "__main__":
# default behavior is greedy
test_patterns(
[('ab*', 'a followed by zero or more b'),
('ab+', 'a followed by one or more b'),
('ab?', 'a followed by zero or one b'),
('ab{3}', 'a followed by three b'),
('ab{2, 3}', 'a followed by two or three b')],
text='abbaabbba'
)
# non-greedy via turning off by following the repetition instruction with ?
test_patterns(
[('ab*?', 'a followed by zero or more b'),
('ab+?', 'a followed by one or more b'),
('ab??', 'a followed by zero or one b'),
('ab{3}?', 'a followed by three b'),
('ab{2, 3}?', 'a followed by two or three b')],
text='abbaabbba'
)