🔧 Common String Methods — Advanced Techniques

Master method chaining, edge cases, case folding, and locale-aware operations.

🎯 Method Chaining & Fluent Interface

# Chain multiple methods for data transformation
text = "  HELLO world  "
result = text.strip().lower().replace("hello", "hi")
print(result)  # hi world

# Complex transformation pipeline
def process_name(input_text):
    return (input_text
            .strip()
            .title()
            .replace("'", "")
            .replace("-", " "))

print(process_name("  o'brien-smith  "))
# O Brien Smith

# Performance: Each method creates new string
# "  HELLO  " → "HELLO  " → "hello  " → "hello world  " → "hi world  "

💡 Case Folding vs Case Conversion

# case_fold() for case-insensitive comparisons
german_text = "Straße"
print(german_text.lower())       # straße
print(german_text.casefold())    # strasse (more aggressive)

# For internationalization
import locale
locale.setlocale(locale.LC_ALL, 'de_DE.UTF-8')

# Turkish I problem
text = "Istanbul"
print(text.lower())              # istanbul
print(text.casefold())           # istanbul
# Turkish has two i's: i and ı

# Use casefold for robust comparison
email1 = "User@Example.COM"
email2 = "user@example.com"
print(email1.casefold() == email2.casefold())  # True

🎨 Unicode-Aware Operations

# Combining characters
import unicodedata

text1 = "é"  # Single character
text2 = "e\u0301"  # e + combining acute

print(text1 == text2)  # False!
print(len(text1), len(text2))  # 1, 2

# Normalize for comparison
norm1 = unicodedata.normalize("NFC", text1)
norm2 = unicodedata.normalize("NFC", text2)
print(norm1 == norm2)  # True

# Useful normalization forms
text = "café"
print(unicodedata.normalize("NFD", text))  # Decomposed
print(unicodedata.normalize("NFC", text))  # Composed

📊 Advanced String Methods

🔑 partition() Method

# partition() returns (before, separator, after)
url = "user:password@host:5432"
before, sep, after = url.partition("@")
print(f"Credentials: {before}, Host: {after}")
# Credentials: user:password, Host: host:5432

# rpartition() from the right
email = "john.doe+tag@example.com"
user, sep, domain = email.rpartition("@")
print(f"User: {user}, Domain: {domain}")

# Useful for key-value parsing
config = "database.host=localhost"
key, sep, value = config.partition("=")
if sep:
    print(f"Setting {key} = {value}")

💡 translate() & Character Mapping

# Fast character replacement without regex
text = "Hello 123 World!"

# Create translation table
table = str.maketrans("0123456789", "9876543210")
result = text.translate(table)
print(result)  # Hello 987 654 321 World!

# Remove characters
punctuation = "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"
table = str.maketrans("", "", punctuation)
clean = "Hello! World? Yes!".translate(table)
print(clean)  # Hello World Yes

# Cipher example: ROT13
def rot13(text):
    from string import ascii_letters
    letters = ascii_letters
    shifted = ascii_letters[13:] + ascii_letters[:13]
    table = str.maketrans(letters, shifted)
    return text.translate(table)

print(rot13("Hello World"))  # Uryyb Jbeyq

🎨 Advanced Whitespace Handling

# expandtabs() - replace tabs with spaces
text = "Name\tAge\tCity"
print(text)              # Name	Age	City
print(text.expandtabs(20))  # Name                Age                 City

# splitlines() with keepends
text = "line1\nline2\rline3\r\nline4"
lines = text.splitlines(keepends=True)
for line in lines:
    print(repr(line))
# 'line1\n'
# 'line2\r'
# 'line3\r\n'
# 'line4'

# Strip specific characters
text = "...hello..."
print(text.strip("."))   # hello
print(text.lstrip("."))  # hello...
print(text.rstrip("."))  # ...hello

🔑 Performance Optimization

import timeit

# For repeated replacements, translate is faster
text = "The quick brown fox" * 1000

# Method 1: Multiple replace calls
def method_replace(t):
    return t.replace("a", "@").replace("e", "3").replace("i", "1")

# Method 2: Using translate
def method_translate(t):
    table = str.maketrans("aei", "@31")
    return t.translate(table)

# Method 3: Using regex
import re
def method_regex(t):
    return re.sub("[aei]", lambda m: {"a": "@", "e": "3", "i": "1"}[m.group()], t)

print("replace:", timeit.timeit(lambda: method_replace(text), number=100))
print("translate:", timeit.timeit(lambda: method_translate(text), number=100))
print("regex:", timeit.timeit(lambda: method_regex(text), number=100))

🔑 Key Takeaways

🔗 What's Next?

Learn advanced string formatting and localization.

Ready to practice? Challenges | Quiz