November 10, 2025
Learning Objectives for Document Engineering
re module for regex operationsre.compile()r'') prevent escape confusionimport rer'pattern're.compile(pattern)match(), search(), or findall()\d matches any digit (0-9){3} means exactly 3 occurrences. means any char+ means one or more[...] is a character class[a-z] matches any character in range[^abc] matches any character except those listed. matches any single character except newline^ matches start of string$ matches end of string* matches zero or more repetitions+ matches one or more repetitions? matches zero or one repetition{n} matches exactly n repetitions{n,m} matches between n and m repetitions\ escapes special characters like \. to match a literal dot[abc] matches any single character a, b, or c[a-z] matches any lowercase letter[A-Z] matches any uppercase letter[0-9] matches any digit[^abc] matches any character except a, b, or c\d matches any digit (this is the same as [0-9])\w matches word characters (i.e., letters, digits, and underscore)\s matches whitespace (i.e., spaces, tabs, and newlines)\D, \W, \S are negations of the above three classes* and +\d+ or \d* to see how matching behavior changes! What did you discover and learn?re.match(pattern, string): checks if pattern matches at start of stringre.search(pattern, string): finds first occurrence of pattern anywherere.findall(pattern, string): returns list of non-overlapping matchesre.finditer(pattern, string): returns iterator of match objectsre.sub(pattern, repl, string): replaces matches with new stringre.split(pattern, string): splits string by pattern occurrencespattern.fullmatch(string): checks if entire string matches patternfindallimport re
text = 'Contact us at support@example.com or sales@company.org'
email_pattern = r'\b[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}\b'
# find all email addresses
emails = re.findall(email_pattern, text)
print(f"Found {len(emails)} email addresses:")
for email in emails:
print(f" - {email}")Found 2 email addresses:
- support@example.com
- sales@company.org\b represents word boundaries+ matches one or more characters[...] define valid charactersISO versus US) require different patternsunittest or pytestunittestimport unittest
import re
class TestEmailRegex(unittest.TestCase):
def setUp(self):
"""Set up test fixtures."""
self.email_pattern = r'\b[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}\b'
self.regex = re.compile(self.email_pattern)
def test_valid_email(self):
"""Test that valid emails match."""
self.assertTrue(self.regex.fullmatch('user@example.com'))
self.assertTrue(self.regex.fullmatch('test.user@domain.co.uk'))
def test_invalid_email(self):
"""Test that invalid emails do not match."""
self.assertFalse(self.regex.fullmatch('invalid@'))
self.assertFalse(self.regex.fullmatch('@example.com'))
self.assertFalse(self.regex.fullmatch('no-at-sign.com'))
unittest.main(argv=['ignored'], verbosity=2, exit=False)<unittest.main.TestProgram at 0x7f00c441c320>import unittest
import re
def extract_dates(text: str) -> list:
"""Extract all ISO format dates from text."""
pattern = r'\d{4}-\d{2}-\d{2}'
return re.findall(pattern, text)
class TestDateExtraction(unittest.TestCase):
def test_single_date(self):
"""Test extraction of single date."""
result = extract_dates("Meeting on 2024-03-15")
self.assertEqual(result, ['2024-03-15'])
def test_multiple_dates(self):
"""Test extraction of multiple dates."""
text = "From 2024-01-01 to 2024-12-31"
result = extract_dates(text)
self.assertEqual(len(result), 2)
def test_no_dates(self):
"""Test text with no dates."""
result = extract_dates("No dates here")
self.assertEqual(result, [])
unittest.main(argv=['ignored'], verbosity=2, exit=False)<unittest.main.TestProgram at 0x7f00c41f3860>try-except blocks for malformed inputr'' to avoid escape character confusion(?P<name>...)GatorGrader:MULTILINECOMMENT_RE_JAVA = r"""/\*([^*]|[\r\n]|(\*+([^*/]|[\r\n])))*\*+/"""
SINGLELINECOMMENT_RE_JAVA = r"""^(?:[^"/\\]|\"(?:[^\"\\]|\\.)*
\"|/(?:[^/"\\]|\\.)|/\"(?:[^\"\\]|\\.)*\"|\\.)*//(.*)$"""
SINGLELINECOMMENT_RE_PYTHON = r"""^(?:[^"#\\]|\"(?:[^\"\\]|\\.)*\"|
/(?:[^#"\\]|\\.)|/\"(?:[^\"\\]|\\.)*\"|\\.)*#(.*)$"""
MULTILINECOMMENT_RE_PYTHON = r'^[ \t]*"""(.*?)"""[ \t]*$'r'') and re.compile() for clarity and reusesearch, match, findall, and sub appropriatelyProsegrammers