Python Tutorial (13): RegEx dan Pola Teks

# Tanpa RegEx: fragile dan verbose
email = "user@example.com"
parts = email.split("@")
valid = len(parts) == 2 and "." in parts[1]
 
# Dengan RegEx: deklaratif dan reusable
import re
valid = bool(re.match(r"^[\w.-]+@[\w.-]+\.\w+$", email))

import re
 
text = "Hubungi kami di support@example.com atau sales@example.org"
 
# search: cari pertama kali cocok
match = re.search(r"\w+@\w+\.\w+", text)
match.group()   # 'support@example.com'
 
# findall: semua kecocokan
emails = re.findall(r"\w+@\w+\.\w+", text)
# ['support@example.com', 'sales@example.org']
 
# finditer: iterator dengan info posisi
for m in re.finditer(r"\d+", "Order #12345, qty 3"):
    print(m.group(), m.start(), m.end())
 
# sub: ganti pola
re.sub(r"\d+", "X", "abc123def456")   # 'abcXdefX'
 
# split: pecah berdasarkan pola
re.split(r"[,;\s]+", "a,b; c  d")     # ['a', 'b', 'c', 'd']

import re
 
re.findall(r"a+", "aaa b aa c")       # ['aaa', 'aa'] (satu atau lebih)
re.findall(r"a?", "aaa b")            # ['a', 'a', 'a', '', ''] (nol atau satu)
re.findall(r"a{2,4}", "aaaaa")        # ['aaaa'] (2 sampai 4 kali)
re.findall(r"\d{3}-\d{4}", "0812-3456")  # ['0812-3456']

import re
 
text = "John Doe, 30 tahun"
pattern = r"(\w+)\s+(\w+),\s+(\d+)\s+tahun"
match = re.search(pattern, text)
 
match.group(0)    # 'John Doe, 30 tahun' (seluruh match)
match.group(1)    # 'John'
match.group(2)    # 'Doe'
match.group(3)    # '30'
match.groups()    # ('John', 'Doe', '30')
 
# Named groups
pattern = r"(?P<first>\w+)\s+(?P<last>\w+)"
m = re.search(pattern, "Alice Smith")
m.group("first")   # 'Alice'
m.group("last")    # 'Smith'

import re
 
# re.IGNORECASE / re.I
re.search(r"python", "Python Rocks", re.I)
 
# re.MULTILINE / re.M: ^ dan $ per baris
text = "line1\nline2\nline3"
re.findall(r"^line", text, re.M)   # ['line', 'line', 'line']
 
# re.DOTALL / re.S: . match newline juga
re.search(r"a.+b", "a\nb", re.S)
 
# Kombinasi
re.findall(r"ERROR.*", log, re.I | re.M)

# Buruk: perlu escape ganda
re.search("\\d+", "123")
 
# Baik: raw string
re.search(r"\d+", "123")

import re
 
PATTERNS = {
    "email": r"^[\w.-]+@[\w.-]+\.\w{2,}$",
    "phone_id": r"^(\+62|0)8[1-9]\d{7,10}$",
    "username": r"^[a-zA-Z][a-zA-Z0-9_]{2,19}$",
    "ipv4": r"^(\d{1,3}\.){3}\d{1,3}$",
}
 
def validate(field: str, value: str) -> bool:
    pattern = PATTERNS.get(field)
    if not pattern:
        raise ValueError(f"Unknown field: {field}")
    return bool(re.fullmatch(pattern, value))
 
validate("email", "user@example.com")   # True
validate("email", "invalid-email")      # False

import re
 
EMAIL_RE = re.compile(r"^[\w.-]+@[\w.-]+\.\w{2,}$")
 
def is_valid_email(email: str) -> bool:
    return bool(EMAIL_RE.fullmatch(email))

import re
from datetime import datetime
 
LOG_PATTERN = re.compile(
    r"(?P<timestamp>\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}) "
    r"(?P<level>\w+) "
    r"(?P<message>.+)"
)
 
line = "2026-04-30 14:30:00 ERROR Database connection failed"
match = LOG_PATTERN.match(line)
if match:
    data = match.groupdict()
    data["timestamp"] = datetime.strptime(data["timestamp"], "%Y-%m-%d %H:%M:%S")
    print(data)