5.5. Regex Syntax CharacterClass

  • Character Classes specifies what to find

5.5.1. SetUp

>>> import re

5.5.2. Numeric

  • \d - digit

  • \D - anything but digit

>>> TEXT = 'Email from Mark Watney <mwatney@nasa.gov> received on: Sat, Jan 1st, 2000 at 12:00 AM'
>>> re.findall(r'[0-9]', TEXT)
['1', '2', '0', '0', '0', '1', '2', '0', '0']
>>> re.findall(r'\d', TEXT)
['1', '2', '0', '0', '0', '1', '2', '0', '0']
>>> re.findall(r'\D', TEXT)  
['E', 'm', 'a', 'i', 'l', ' ', 'f', 'r', 'o', 'm', ' ', 'M', 'a', 'r', 'k',
 ' ', 'W', 'a', 't', 'n', 'e', 'y', ' ', '<', 'm', 'w', 'a', 't', 'n', 'e',
 'y', '@', 'n', 'a', 's', 'a', '.', 'g', 'o', 'v', '>', ' ', 'r', 'e', 'c',
 'e', 'i', 'v', 'e', 'd', ' ', 'o', 'n', ':', ' ', 'S', 'a', 't', ',', ' ',
 'J', 'a', 'n', ' ', 's', 't', ',', ' ', ' ', 'a', 't', ' ', ':', ' ', 'A',
 'M']

5.5.3. Whitespaces

  • \s - whitespace (space, tab, newline, non-breaking space)

  • \S - anything but whitespace

  • \n - newline

  • \r\n - windows newline

  • \r - carriage return

  • \b - backspace

  • \t - tab

  • \v - vertical space

  • \f - form feed

>>> TEXT = 'Email from Mark Watney <mwatney@nasa.gov> received on: Sat, Jan 1st, 2000 at 12:00 AM'
>>> re.findall(r'\s', TEXT)
[' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ']
>>> re.findall(r'\S', TEXT)  
['E', 'm', 'a', 'i', 'l', 'f', 'r', 'o', 'm', 'M', 'a', 'r', 'k', 'W', 'a',
 't', 'n', 'e', 'y', '<', 'm', 'w', 'a', 't', 'n', 'e', 'y', '@', 'n', 'a',
 's', 'a', '.', 'g', 'o', 'v', '>', 'r', 'e', 'c', 'e', 'i', 'v', 'e', 'd',
 'o', 'n', ':', 'S', 'a', 't', ',', 'J', 'a', 'n', '1', 's', 't', ',', '2',
 '0', '0', '0', 'a', 't', '1', '2', ':', '0', '0', 'A', 'M']
>>> re.findall(r'\n', TEXT)
[]
>>>
>>> re.findall(r'\r\n', TEXT)
[]
>>>
>>> re.findall(r'\r', TEXT)
[]

5.5.4. Word Boundary

  • Matches the empty string, but only at the beginning or end of a word

  • \b - word boundary

  • \B - anything but word boundary

Examples:

  • \babc\b - performs a "whole words only" search

  • \Babc\B - pattern is fully surrounded by word characters

>>> TEXT = 'Email from Mark Watney <mwatney@nasa.gov> received on: Sat, Jan 1st, 2000 at 12:00 AM'
>>> re.findall(r'[a-z][a-z]', TEXT)  
['ma', 'il', 'fr', 'om', 'ar', 'at', 'ne', 'mw', 'at', 'ne', 'na', 'sa',
 'go', 're', 'ce', 'iv', 'ed', 'on', 'at', 'an', 'st', 'at']
>>> re.findall(r'\b[a-z][a-z]\b', TEXT)
['on', 'at']
>>> re.findall('\b[a-z][a-z]\b', TEXT)  # without raw-string
[]
>>> re.findall(r'\b[a-z][a-z]\B', TEXT)
['fr', 'mw', 'na', 'go', 're']

5.5.5. Word Character

  • \w - any unicode alphabet character (lower or upper, also with diacritics (i.e. ąćęłńóśżź...), numbers and underscores

  • \W - anything but any unicode alphabet character (i.e. whitespace, dots, comas, dashes)

  • lowercase letters including diacritics (i.e. ąćęłńóśżź...) and accents

  • uppercase letters including diacritics (i.e. ĄĆĘŁŃÓŚŻŹ...) and accents

  • digits

  • underscores _

Valid characters are the same as allowed in variable/modules names in Python:

>>> imie = 'Mark'
>>> IMIE = 'Mark'
>>> imię = 'Mark'
>>> imię1 = 'Mark'
>>> Imię_1 = 'Mark'
>>> TEXT = 'Email from Mark Watney <mwatney@nasa.gov> received on: Sat, Jan 1st, 2000 at 12:00 AM'
>>> re.findall(r'\w', TEXT)  
['E', 'm', 'a', 'i', 'l', 'f', 'r', 'o', 'm', 'M', 'a', 'r', 'k', 'W', 'a',
 't', 'n', 'e', 'y', 'm', 'w', 'a', 't', 'n', 'e', 'y', 'n', 'a', 's', 'a',
 'g', 'o', 'v', 'r', 'e', 'c', 'e', 'i', 'v', 'e', 'd', 'o', 'n', 'S', 'a',
 't', 'J', 'a', 'n', '1', 's', 't', '2', '0', '0', '0', 'a', 't', '1', '2',
 '0', '0', 'A', 'M']
>>> re.findall(r'\W', TEXT)  
[' ', ' ', ' ', ' ', '<', '@', '.', '>', ' ', ' ', ':', ' ', ',', ' ', ' ',
 ',', ' ', ' ', ' ', ':', ' ']

Mind, that following code gives similar output to \w but it is not completely true. \w would extract also unicode characters while this [a-zA-Z0-9] will not.

>>> re.findall(r'[a-zA-Z0-9]', TEXT)  
['E', 'm', 'a', 'i', 'l', 'f', 'r', 'o', 'm', 'M', 'a', 'r', 'k', 'W', 'a',
 't', 'n', 'e', 'y', 'm', 'w', 'a', 't', 'n', 'e', 'y', 'n', 'a', 's', 'a',
 'g', 'o', 'v', 'r', 'e', 'c', 'e', 'i', 'v', 'e', 'd', 'o', 'n', 'S', 'a',
 't', 'J', 'a', 'n', '1', 's', 't', '2', '0', '0', '0', 'a', 't', '1', '2',
 '0', '0', 'A', 'M']

Example:

>>> text = 'cześć'
>>>
>>> re.findall(r'[a-z]', text)
['c', 'z', 'e']
>>>
>>> re.findall(r'\w', text)
['c', 'z', 'e', 'ś', 'ć']
>>>
>>> re.findall(r'\w', text, flags=re.ASCII)
['c', 'z', 'e']
>>>
>>> re.findall(r'\w', text, flags=re.UNICODE)
['c', 'z', 'e', 'ś', 'ć']

Flag re.UNICODE is set by default.

5.5.6. Use Case - 0x01

  • Phone

>>> phone = '+48 123 456 789'
>>> re.findall(r'\d', phone)
['4', '8', '1', '2', '3', '4', '5', '6', '7', '8', '9']
>>> phone = '+48 (12) 345 6789'
>>> re.findall(r'\d', phone)
['4', '8', '1', '2', '3', '4', '5', '6', '7', '8', '9']

5.5.7. Use Case - 0x02

  • Compare Phones

>>> PHONE1 = '+48 123 456 789'
>>> PHONE2 = '+48 (12) 345 6789'
>>>
>>> phone1 = re.findall(r'\d', PHONE1)
>>> phone2 = re.findall(r'\d', PHONE2)
>>>
>>> phone1 == phone2
True

5.5.8. Use Case - 0x03

  • EU VAT Tax ID

>>> number = '777-286-18-23'
>>> re.findall(r'\d', number)
['7', '7', '7', '2', '8', '6', '1', '8', '2', '3']
>>> number = '777-28-61-823'
>>> re.findall(r'\d', number)
['7', '7', '7', '2', '8', '6', '1', '8', '2', '3']
>>> number = '7772861823'
>>> re.findall(r'\d', number)
['7', '7', '7', '2', '8', '6', '1', '8', '2', '3']

5.5.9. Use Case - 0x04

  • Number and Spaces

>>> TEXT = 'Email from Mark Watney <mwatney@nasa.gov> received on: Sat, Jan 1st, 2000 at 12:00 AM'
>>> re.findall(r'[0-9]\s', TEXT)
['0 ', '0 ']
>>> re.findall(r'\d\s', TEXT)
['0 ', '0 ']

5.5.10. Assignments

"""
* Assignment: RE Syntax CharacterClass
* Complexity: easy
* Lines of code: 2 lines
* Time: 2 min

English:
    1. Define `result: str` with regular expression to find:
        a. all digits
        b. all non-digits
    2. Run doctests - all must succeed

Polish:
    1. Zdefiniuj `result: str` z wyrażeniem regularnym aby wyszukać:
        a. wszystkie cyfry
        b. wszystkie nie-cyfry
    2. Uruchom doctesty - wszystkie muszą się powieść

References:
    [1] Authors: Wikipedia contributors
        Title: Apollo 11
        Publisher: Wikipedia
        Year: 2019
        Retrieved: 2019-12-14
        URL: https://en.wikipedia.org/wiki/Apollo_11

Tests:
    >>> import sys; sys.tracebacklimit = 0
    >>> from pprint import pprint

    >>> result = re.findall(result_a, DATA)
    >>> pprint(result, compact=True, width=72)
    ['1', '1', '2', '0', '1', '9', '6', '9', '2', '0', '1', '7', '6', '3',
     '9', '2', '1', '1', '9', '6', '9', '0', '2', '5', '6', '1', '5', '1',
     '9', '2', '3', '1', '4', '7', '5', '2', '1', '5', '2', '1', '3', '6']

    >>> result = re.findall(result_b, DATA)
    >>> result = sorted(set(result))
    >>> pprint(result, compact=True, width=72)
    ['\\n', ' ', "'", '(', ')', ',', '.', ':', 'A', 'B', 'C', 'D', 'E', 'J',
     'L', 'M', 'N', 'P', 'R', 'T', 'U', 'V', 'a', 'b', 'c', 'd', 'e', 'f',
     'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't',
     'u', 'w', 'x', 'y', 'z']
"""

import re

DATA = """Apollo 11 was the American spaceflight that first landed
humans on the Moon. Commander (CDR) Neil Armstrong and lunar module
pilot (LMP) Buzz Aldrin landed the Apollo Lunar Module (LM) Eagle on
July 20th, 1969 at 20:17 UTC, and Armstrong became the first person
to step (EVA) onto the Moon's surface (EVA) 6 hours 39 minutes later,
on July 21st, 1969 at 02:56:15 UTC. Aldrin joined him 19 minutes later.
They spent 2 hours 31 minutes exploring the site they had named
Tranquility Base upon landing. Armstrong and Aldrin collected 47.5 pounds
(21.5 kg) of lunar material to bring back to Earth as pilot Michael Collins
(CMP) flew the Command Module (CM) Columbia in lunar orbit, and were on the
Moon's surface for 21 hours 36 minutes before lifting off to rejoin
Columbia."""

# Find all digits in text
# Example: '1', '1', '2', '0', '1', '9', '6', ...
# Note: define only regex pattern (str), not re.findall(...)
# type: str
result_a = r''

# Find all non-digits in text
# Example: '0', '1', '2', '3', '4', '5', '6', '7', '9'
# Note: define only regex pattern (str), not re.findall(...)
# type: str
result_b = r''

"""
* Assignment: RE Syntax CharacterClass
* Complexity: easy
* Lines of code: 2 lines
* Time: 2 min

English:
    1. Define `result: str` with regular expression to find:
        a. whitespace characters
        b. non-whitespace characters
    2. Run doctests - all must succeed

Polish:
    1. Zdefiniuj `result: str` z wyrażeniem regularnym aby wyszukać:
        a. białe-znaki
        b. nie-białe-znaki
    2. Uruchom doctesty - wszystkie muszą się powieść

References:
    [1] Authors: Wikipedia contributors
        Title: Apollo 11
        Publisher: Wikipedia
        Year: 2019
        Retrieved: 2019-12-14
        URL: https://en.wikipedia.org/wiki/Apollo_11

Tests:
    >>> import sys; sys.tracebacklimit = 0
    >>> from pprint import pprint

    >>> result = re.findall(result_a, DATA)
    >>> pprint(result, compact=True, width=72)
    [' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', '\\n', ' ', ' ', ' ', ' ', ' ',
     ' ', ' ', ' ', ' ', ' ', '\\n', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ',
     ' ', ' ', ' ', '\\n', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ',
     ' ', '\\n', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ',
     '\\n', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', '\\n',
     ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', '\\n', ' ', ' ',
     ' ', ' ', ' ', ' ', ' ', ' ', ' ', '\\n', ' ', ' ', ' ', ' ', ' ', ' ',
     ' ', ' ', ' ', ' ', ' ', ' ', ' ', '\\n', ' ', ' ', ' ', ' ', ' ', ' ',
     ' ', ' ', ' ', ' ', ' ', ' ', ' ', '\\n', ' ', ' ', ' ', ' ', ' ', ' ',
     ' ', ' ', ' ', ' ', ' ', '\\n']

    >>> result = re.findall(result_b, DATA)
    >>> pprint(result, compact=True, width=72)
    ['A', 'p', 'o', 'l', 'l', 'o', '1', '1', 'w', 'a', 's', 't', 'h', 'e',
     'A', 'm', 'e', 'r', 'i', 'c', 'a', 'n', 's', 'p', 'a', 'c', 'e', 'f',
     'l', 'i', 'g', 'h', 't', 't', 'h', 'a', 't', 'f', 'i', 'r', 's', 't',
     'l', 'a', 'n', 'd', 'e', 'd', 'h', 'u', 'm', 'a', 'n', 's', 'o', 'n',
     't', 'h', 'e', 'M', 'o', 'o', 'n', '.', 'C', 'o', 'm', 'm', 'a', 'n',
     'd', 'e', 'r', '(', 'C', 'D', 'R', ')', 'N', 'e', 'i', 'l', 'A', 'r',
     'm', 's', 't', 'r', 'o', 'n', 'g', 'a', 'n', 'd', 'l', 'u', 'n', 'a',
     'r', 'm', 'o', 'd', 'u', 'l', 'e', 'p', 'i', 'l', 'o', 't', '(', 'L',
     'M', 'P', ')', 'B', 'u', 'z', 'z', 'A', 'l', 'd', 'r', 'i', 'n', 'l',
     'a', 'n', 'd', 'e', 'd', 't', 'h', 'e', 'A', 'p', 'o', 'l', 'l', 'o',
     'L', 'u', 'n', 'a', 'r', 'M', 'o', 'd', 'u', 'l', 'e', '(', 'L', 'M',
     ')', 'E', 'a', 'g', 'l', 'e', 'o', 'n', 'J', 'u', 'l', 'y', '2', '0',
     't', 'h', ',', '1', '9', '6', '9', 'a', 't', '2', '0', ':', '1', '7',
     'U', 'T', 'C', ',', 'a', 'n', 'd', 'A', 'r', 'm', 's', 't', 'r', 'o',
     'n', 'g', 'b', 'e', 'c', 'a', 'm', 'e', 't', 'h', 'e', 'f', 'i', 'r',
     's', 't', 'p', 'e', 'r', 's', 'o', 'n', 't', 'o', 's', 't', 'e', 'p',
     '(', 'E', 'V', 'A', ')', 'o', 'n', 't', 'o', 't', 'h', 'e', 'M', 'o',
     'o', 'n', "'", 's', 's', 'u', 'r', 'f', 'a', 'c', 'e', '(', 'E', 'V',
     'A', ')', '6', 'h', 'o', 'u', 'r', 's', '3', '9', 'm', 'i', 'n', 'u',
     't', 'e', 's', 'l', 'a', 't', 'e', 'r', ',', 'o', 'n', 'J', 'u', 'l',
     'y', '2', '1', 's', 't', ',', '1', '9', '6', '9', 'a', 't', '0', '2',
     ':', '5', '6', ':', '1', '5', 'U', 'T', 'C', '.', 'A', 'l', 'd', 'r',
     'i', 'n', 'j', 'o', 'i', 'n', 'e', 'd', 'h', 'i', 'm', '1', '9', 'm',
     'i', 'n', 'u', 't', 'e', 's', 'l', 'a', 't', 'e', 'r', '.', 'T', 'h',
     'e', 'y', 's', 'p', 'e', 'n', 't', '2', 'h', 'o', 'u', 'r', 's', '3',
     '1', 'm', 'i', 'n', 'u', 't', 'e', 's', 'e', 'x', 'p', 'l', 'o', 'r',
     'i', 'n', 'g', 't', 'h', 'e', 's', 'i', 't', 'e', 't', 'h', 'e', 'y',
     'h', 'a', 'd', 'n', 'a', 'm', 'e', 'd', 'T', 'r', 'a', 'n', 'q', 'u',
     'i', 'l', 'i', 't', 'y', 'B', 'a', 's', 'e', 'u', 'p', 'o', 'n', 'l',
     'a', 'n', 'd', 'i', 'n', 'g', '.', 'A', 'r', 'm', 's', 't', 'r', 'o',
     'n', 'g', 'a', 'n', 'd', 'A', 'l', 'd', 'r', 'i', 'n', 'c', 'o', 'l',
     'l', 'e', 'c', 't', 'e', 'd', '4', '7', '.', '5', 'p', 'o', 'u', 'n',
     'd', 's', '(', '2', '1', '.', '5', 'k', 'g', ')', 'o', 'f', 'l', 'u',
     'n', 'a', 'r', 'm', 'a', 't', 'e', 'r', 'i', 'a', 'l', 't', 'o', 'b',
     'r', 'i', 'n', 'g', 'b', 'a', 'c', 'k', 't', 'o', 'E', 'a', 'r', 't',
     'h', 'a', 's', 'p', 'i', 'l', 'o', 't', 'M', 'i', 'c', 'h', 'a', 'e',
     'l', 'C', 'o', 'l', 'l', 'i', 'n', 's', '(', 'C', 'M', 'P', ')', 'f',
     'l', 'e', 'w', 't', 'h', 'e', 'C', 'o', 'm', 'm', 'a', 'n', 'd', 'M',
     'o', 'd', 'u', 'l', 'e', '(', 'C', 'M', ')', 'C', 'o', 'l', 'u', 'm',
     'b', 'i', 'a', 'i', 'n', 'l', 'u', 'n', 'a', 'r', 'o', 'r', 'b', 'i',
     't', ',', 'a', 'n', 'd', 'w', 'e', 'r', 'e', 'o', 'n', 't', 'h', 'e',
     'M', 'o', 'o', 'n', "'", 's', 's', 'u', 'r', 'f', 'a', 'c', 'e', 'f',
     'o', 'r', '2', '1', 'h', 'o', 'u', 'r', 's', '3', '6', 'm', 'i', 'n',
     'u', 't', 'e', 's', 'b', 'e', 'f', 'o', 'r', 'e', 'l', 'i', 'f', 't',
     'i', 'n', 'g', 'o', 'f', 'f', 't', 'o', 'r', 'e', 'j', 'o', 'i', 'n',
     'C', 'o', 'l', 'u', 'm', 'b', 'i', 'a', '.']
"""

import re

DATA = """Apollo 11 was the American spaceflight that first landed
humans on the Moon. Commander (CDR) Neil Armstrong and lunar module
pilot (LMP) Buzz Aldrin landed the Apollo Lunar Module (LM) Eagle on
July 20th, 1969 at 20:17 UTC, and Armstrong became the first person
to step (EVA) onto the Moon's surface (EVA) 6 hours 39 minutes later,
on July 21st, 1969 at 02:56:15 UTC. Aldrin joined him 19 minutes later.
They spent 2 hours 31 minutes exploring the site they had named
Tranquility Base upon landing. Armstrong and Aldrin collected 47.5 pounds
(21.5 kg) of lunar material to bring back to Earth as pilot Michael Collins
(CMP) flew the Command Module (CM) Columbia in lunar orbit, and were on the
Moon's surface for 21 hours 36 minutes before lifting off to rejoin
Columbia."""

# Find all whitespace characters in text
# Example: '\n', ' '
# Note: define only regex pattern (str), not re.findall(...)
# type: str
result_a = r''

# Find all non-whitespace characters in text
# Example: "'", '(', ')', ',', '.', '0', '1', '2', '3', '4', '5', '6', ...
# Note: define only regex pattern (str), not re.findall(...)
# type: str
result_b = r''

"""
* Assignment: RE Syntax CharacterClass
* Complexity: easy
* Lines of code: 3 lines
* Time: 2 min

English:
    1. Define `result: str` with regular expression to find:
        a. word characters
        b. non-word characters
    2. Run doctests - all must succeed

Polish:
    1. Zdefiniuj `result: str` z wyrażeniem regularnym aby wyszukać:
        a. znaki słów
        b. nie-znaki słów
    2. Uruchom doctesty - wszystkie muszą się powieść

References:
    [1] Authors: Wikipedia contributors
        Title: Apollo 11
        Publisher: Wikipedia
        Year: 2019
        Retrieved: 2019-12-14
        URL: https://en.wikipedia.org/wiki/Apollo_11

Tests:
    >>> import sys; sys.tracebacklimit = 0
    >>> from pprint import pprint

    >>> result = re.findall(result_a, DATA)
    >>> pprint(result, compact=True, width=72)
    ['A', 'p', 'o', 'l', 'l', 'o', '1', '1', 'w', 'a', 's', 't', 'h', 'e',
     'A', 'm', 'e', 'r', 'i', 'c', 'a', 'n', 's', 'p', 'a', 'c', 'e', 'f',
     'l', 'i', 'g', 'h', 't', 't', 'h', 'a', 't', 'f', 'i', 'r', 's', 't',
     'l', 'a', 'n', 'd', 'e', 'd', 'h', 'u', 'm', 'a', 'n', 's', 'o', 'n',
     't', 'h', 'e', 'M', 'o', 'o', 'n', 'C', 'o', 'm', 'm', 'a', 'n', 'd',
     'e', 'r', 'C', 'D', 'R', 'N', 'e', 'i', 'l', 'A', 'r', 'm', 's', 't',
     'r', 'o', 'n', 'g', 'a', 'n', 'd', 'l', 'u', 'n', 'a', 'r', 'm', 'o',
     'd', 'u', 'l', 'e', 'p', 'i', 'l', 'o', 't', 'L', 'M', 'P', 'B', 'u',
     'z', 'z', 'A', 'l', 'd', 'r', 'i', 'n', 'l', 'a', 'n', 'd', 'e', 'd',
     't', 'h', 'e', 'A', 'p', 'o', 'l', 'l', 'o', 'L', 'u', 'n', 'a', 'r',
     'M', 'o', 'd', 'u', 'l', 'e', 'L', 'M', 'E', 'a', 'g', 'l', 'e', 'o',
     'n', 'J', 'u', 'l', 'y', '2', '0', 't', 'h', '1', '9', '6', '9', 'a',
     't', '2', '0', '1', '7', 'U', 'T', 'C', 'a', 'n', 'd', 'A', 'r', 'm',
     's', 't', 'r', 'o', 'n', 'g', 'b', 'e', 'c', 'a', 'm', 'e', 't', 'h',
     'e', 'f', 'i', 'r', 's', 't', 'p', 'e', 'r', 's', 'o', 'n', 't', 'o',
     's', 't', 'e', 'p', 'E', 'V', 'A', 'o', 'n', 't', 'o', 't', 'h', 'e',
     'M', 'o', 'o', 'n', 's', 's', 'u', 'r', 'f', 'a', 'c', 'e', 'E', 'V',
     'A', '6', 'h', 'o', 'u', 'r', 's', '3', '9', 'm', 'i', 'n', 'u', 't',
     'e', 's', 'l', 'a', 't', 'e', 'r', 'o', 'n', 'J', 'u', 'l', 'y', '2',
     '1', 's', 't', '1', '9', '6', '9', 'a', 't', '0', '2', '5', '6', '1',
     '5', 'U', 'T', 'C', 'A', 'l', 'd', 'r', 'i', 'n', 'j', 'o', 'i', 'n',
     'e', 'd', 'h', 'i', 'm', '1', '9', 'm', 'i', 'n', 'u', 't', 'e', 's',
     'l', 'a', 't', 'e', 'r', 'T', 'h', 'e', 'y', 's', 'p', 'e', 'n', 't',
     '2', 'h', 'o', 'u', 'r', 's', '3', '1', 'm', 'i', 'n', 'u', 't', 'e',
     's', 'e', 'x', 'p', 'l', 'o', 'r', 'i', 'n', 'g', 't', 'h', 'e', 's',
     'i', 't', 'e', 't', 'h', 'e', 'y', 'h', 'a', 'd', 'n', 'a', 'm', 'e',
     'd', 'T', 'r', 'a', 'n', 'q', 'u', 'i', 'l', 'i', 't', 'y', 'B', 'a',
     's', 'e', 'u', 'p', 'o', 'n', 'l', 'a', 'n', 'd', 'i', 'n', 'g', 'A',
     'r', 'm', 's', 't', 'r', 'o', 'n', 'g', 'a', 'n', 'd', 'A', 'l', 'd',
     'r', 'i', 'n', 'c', 'o', 'l', 'l', 'e', 'c', 't', 'e', 'd', '4', '7',
     '5', 'p', 'o', 'u', 'n', 'd', 's', '2', '1', '5', 'k', 'g', 'o', 'f',
     'l', 'u', 'n', 'a', 'r', 'm', 'a', 't', 'e', 'r', 'i', 'a', 'l', 't',
     'o', 'b', 'r', 'i', 'n', 'g', 'b', 'a', 'c', 'k', 't', 'o', 'E', 'a',
     'r', 't', 'h', 'a', 's', 'p', 'i', 'l', 'o', 't', 'M', 'i', 'c', 'h',
     'a', 'e', 'l', 'C', 'o', 'l', 'l', 'i', 'n', 's', 'C', 'M', 'P', 'f',
     'l', 'e', 'w', 't', 'h', 'e', 'C', 'o', 'm', 'm', 'a', 'n', 'd', 'M',
     'o', 'd', 'u', 'l', 'e', 'C', 'M', 'C', 'o', 'l', 'u', 'm', 'b', 'i',
     'a', 'i', 'n', 'l', 'u', 'n', 'a', 'r', 'o', 'r', 'b', 'i', 't', 'a',
     'n', 'd', 'w', 'e', 'r', 'e', 'o', 'n', 't', 'h', 'e', 'M', 'o', 'o',
     'n', 's', 's', 'u', 'r', 'f', 'a', 'c', 'e', 'f', 'o', 'r', '2', '1',
     'h', 'o', 'u', 'r', 's', '3', '6', 'm', 'i', 'n', 'u', 't', 'e', 's',
     'b', 'e', 'f', 'o', 'r', 'e', 'l', 'i', 'f', 't', 'i', 'n', 'g', 'o',
     'f', 'f', 't', 'o', 'r', 'e', 'j', 'o', 'i', 'n', 'C', 'o', 'l', 'u',
     'm', 'b', 'i', 'a']

    >>> result = re.findall(result_b, DATA)
    >>> pprint(result, compact=True, width=72)
    [' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', '\\n', ' ', ' ', ' ', '.', ' ',
     ' ', '(', ')', ' ', ' ', ' ', ' ', ' ', '\\n', ' ', '(', ')', ' ', ' ',
     ' ', ' ', ' ', ' ', ' ', ' ', '(', ')', ' ', ' ', '\\n', ' ', ',', ' ',
     ' ', ' ', ':', ' ', ',', ' ', ' ', ' ', ' ', ' ', ' ', '\\n', ' ', ' ',
     '(', ')', ' ', ' ', ' ', "'", ' ', ' ', '(', ')', ' ', ' ', ' ', ' ',
     ' ', ',', '\\n', ' ', ' ', ',', ' ', ' ', ' ', ':', ':', ' ', '.', ' ',
     ' ', ' ', ' ', ' ', ' ', '.', '\\n', ' ', ' ', ' ', ' ', ' ', ' ', ' ',
     ' ', ' ', ' ', ' ', '\\n', ' ', ' ', ' ', '.', ' ', ' ', ' ', ' ', ' ',
     '.', ' ', '\\n', '(', '.', ' ', ')', ' ', ' ', ' ', ' ', ' ', ' ', ' ',
     ' ', ' ', ' ', ' ', ' ', '\\n', '(', ')', ' ', ' ', ' ', ' ', ' ', '(',
     ')', ' ', ' ', ' ', ' ', ',', ' ', ' ', ' ', ' ', '\\n', "'", ' ', ' ',
     ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', '\\n', '.']
"""

import re

DATA = """Apollo 11 was the American spaceflight that first landed
humans on the Moon. Commander (CDR) Neil Armstrong and lunar module
pilot (LMP) Buzz Aldrin landed the Apollo Lunar Module (LM) Eagle on
July 20th, 1969 at 20:17 UTC, and Armstrong became the first person
to step (EVA) onto the Moon's surface (EVA) 6 hours 39 minutes later,
on July 21st, 1969 at 02:56:15 UTC. Aldrin joined him 19 minutes later.
They spent 2 hours 31 minutes exploring the site they had named
Tranquility Base upon landing. Armstrong and Aldrin collected 47.5 pounds
(21.5 kg) of lunar material to bring back to Earth as pilot Michael Collins
(CMP) flew the Command Module (CM) Columbia in lunar orbit, and were on the
Moon's surface for 21 hours 36 minutes before lifting off to rejoin
Columbia."""

# Find all word characters in text, don't use range [...]
# Example: 'A', 'A', 'M', 'C', 'C', 'D', 'R', ...
# Note: define only regex pattern (str), not re.findall(...)
# type: str
result_a = r''

# Find all non-word characters in text
# Example: '\n', ' ', "'", '(', ')', ',', '.', ':'
# Note: define only regex pattern (str), not re.findall(...)
# type: str
result_b = r''

"""
* Assignment: RE Syntax CharacterClass
* Complexity: easy
* Lines of code: 2 lines
* Time: 2 min

English:
    1. Define `result: str` with regular expression to find:
        a. all two-letter conjunctives (two-letter words)
        b. all three-letter conjunctives (three-letter words)
    2. Run doctests - all must succeed

Polish:
    1. Zdefiniuj `result: str` z wyrażeniem regularnym aby wyszukać:
        a. wszystkie dwu literowe spójniki (dwu-literowe słowa)
        b. wszystkie trzy literowe spójniki (trzy literowe słow)
    2. Uruchom doctesty - wszystkie muszą się powieść

Hint:
    * Use `r-string`

References:
    [1] Authors: Wikipedia contributors
        Title: Apollo 11
        Publisher: Wikipedia
        Year: 2019
        Retrieved: 2019-12-14
        URL: https://en.wikipedia.org/wiki/Apollo_11

Tests:
    >>> import sys; sys.tracebacklimit = 0
    >>> from pprint import pprint

    >>> result = re.findall(result_a, DATA)
    >>> pprint(result, compact=True, width=72)
    ['on', 'on', 'at', 'to', 'on', 'at', 'kg', 'of', 'to', 'to', 'as', 'in',
     'on', 'to']

    >>> result = re.findall(result_b, DATA)
    >>> pprint(result, compact=True, width=72)
    ['was', 'the', 'the', 'and', 'the', 'and', 'the', 'the', 'him', 'the',
     'had', 'and', 'the', 'and', 'the', 'for', 'off']
"""

import re

DATA = """Apollo 11 was the American spaceflight that first landed
humans on the Moon. Commander (CDR) Neil Armstrong and lunar module
pilot (LMP) Buzz Aldrin landed the Apollo Lunar Module (LM) Eagle on
July 20th, 1969 at 20:17 UTC, and Armstrong became the first person
to step (EVA) onto the Moon's surface (EVA) 6 hours 39 minutes later,
on July 21st, 1969 at 02:56:15 UTC. Aldrin joined him 19 minutes later.
They spent 2 hours 31 minutes exploring the site they had named
Tranquility Base upon landing. Armstrong and Aldrin collected 47.5 pounds
(21.5 kg) of lunar material to bring back to Earth as pilot Michael Collins
(CMP) flew the Command Module (CM) Columbia in lunar orbit, and were on the
Moon's surface for 21 hours 36 minutes before lifting off to rejoin
Columbia."""

# Find all two-letter conjunctives in text (standalone two-letter words)
# Example: 'on', 'on', 'at', 'to', ...
# Note: define only regex pattern (str), not re.findall(...)
# type: str
result_a = r''

# Find all three-letter conjunctives in text (standalone three-letter words)
# Example: 'was', 'the', 'the', 'and', ...
# Note: define only regex pattern (str), not re.findall(...)
# type: str
result_b = r''