String Processing

Creating Strings

Various Methods

# Single quotes
name = 'Python'

# Double quotes
message = "Hello, World!"

# Triple quotes (multiline)
text = """첫 번째 줄
두 번째 줄
세 번째 줄"""

poem = '''장미는 빨갛고
제비꽃은 파랗다'''

# Escape sequences
quote = "He said, \"Hello!\""
path = "C:\\Users\\Documents"
new_line = "첫 줄\n두 번째 줄"
tab = "이름\t나이"

# Raw string (ignores escape)
path = r"C:\Users\Documents"

String Indexing and Slicing

Indexing

text = "Python"

# Positive index (from left: 0, 1, 2...)
print(text[0])   # P
print(text[1])   # y
print(text[5])   # n

# Negative index (from right: -1, -2, -3...)
print(text[-1])  # n
print(text[-2])  # o
print(text[-6])  # P

# Error
# print(text[10])  # IndexError

Slicing

text = "Python Programming"

# [start:end] - end not included
print(text[0:6])    # Python
print(text[7:18])   # Programming

# Can be omitted
print(text[:6])     # Python (from beginning)
print(text[7:])     # Programming (to end)
print(text[:])      # Python Programming (entire)

# Negative index
print(text[-11:])   # Programming
print(text[:-12])   # Python

# Specify step [start:end:step]
print(text[::2])    # Pto rgamn (every 2nd char)
print(text[::-1])   # gnimmargorP nohtyP (reversed)

# Practical example
url = "https://www.example.com"
domain = url[8:-4]  # www.example
print(domain)

String Operations

Concatenation and Repetition

# Concatenation (+)
first = "Hello"
second = "World"
greeting = first + " " + second
print(greeting)  # Hello World

# Repetition (*)
line = "=" * 20
print(line)  # ====================

border = "-" * 10
print(f"{border} 제목 {border}")
# ---------- 제목 ----------

# Join multiple strings
words = ["Python", "is", "awesome"]
sentence = " ".join(words)
print(sentence)  # Python is awesome

Comparison

# Equality/Inequality
print("hello" == "hello")   # True
print("hello" != "Hello")   # True

# Size comparison (lexicographic)
print("apple" < "banana")   # True
print("apple" < "Apple")    # False (uppercase first)

# Membership test
text = "Python Programming"
print("Python" in text)     # True
print("Java" in text)       # False
print("Java" not in text)   # True

String Methods

Case Conversion

text = "Hello, Python!"

print(text.upper())        # HELLO, PYTHON!
print(text.lower())        # hello, python!
print(text.capitalize())   # Hello, python!
print(text.title())        # Hello, Python!
print(text.swapcase())     # hELLO, pYTHON!

# Practical example - normalize user input
user_input = "  YES  "
if user_input.strip().lower() == "yes":
    print("확인되었습니다")

Search and Check

text = "Python Programming"

# Find
print(text.find("Python"))      # 0 (first position)
print(text.find("Java"))        # -1 (not found)
print(text.index("Programming"))  # 7
# print(text.index("Java"))     # ValueError

# Count
print(text.count("o"))          # 1
print(text.count("m"))          # 3

# Start/end check
print(text.startswith("Python"))  # True
print(text.endswith("ing"))       # True

# Membership check
print("gram" in text)            # True

Character Type Check

# Alphabetic only
print("abc".isalpha())       # True
print("abc123".isalpha())    # False

# Digits only
print("123".isdigit())       # True
print("12.3".isdigit())      # False

# Alphanumeric
print("abc123".isalnum())    # True
print("abc 123".isalnum())   # False

# Whitespace only
print("   ".isspace())       # True
print("  a  ".isspace())     # False

# Upper/lowercase
print("ABC".isupper())       # True
print("abc".islower())       # True

# Practical example - password validation
password = "Pass123"
has_digit = any(c.isdigit() for c in password)
has_upper = any(c.isupper() for c in password)
has_lower = any(c.islower() for c in password)

if len(password) >= 8 and has_digit and has_upper and has_lower:
    print("강한 비밀번호입니다")

Whitespace Removal

text = "   hello world   "

print(text.strip())    # "hello world" (both sides)
print(text.lstrip())   # "hello world   " (left)
print(text.rstrip())   # "   hello world" (right)

# Remove specific characters
url = "https://example.com/"
print(url.strip("https://"))  # example.com/
print(url.rstrip("/"))         # https://example.com

# Practical example - CSV parsing
data = "  홍길동,  25,  서울  "
parts = [part.strip() for part in data.split(",")]
print(parts)  # ['홍길동', '25', '서울']

Transformation and Replacement

text = "Hello, Python!"

# Replace
print(text.replace("Python", "World"))  # Hello, World!
print(text.replace("l", "L"))           # HeLLo, Python!
print(text.replace("l", "L", 1))        # HeLlo, Python! (only 1)

# Split
words = text.split(", ")
print(words)  # ['Hello', 'Python!']

csv = "홍길동,25,서울"
data = csv.split(",")
print(data)   # ['홍길동', '25', '서울']

# Join
words = ["Python", "is", "fun"]
sentence = " ".join(words)
print(sentence)  # Python is fun

# Join with specific character
print("-".join(words))  # Python-is-fun

# Split lines
text = """첫 줄
두 번째 줄
세 번째 줄"""
lines = text.splitlines()
print(lines)  # ['첫 줄', '두 번째 줄', '세 번째 줄']

Alignment

# Left align
print("Python".ljust(10))      # "Python    "
print("Python".ljust(10, "-")) # "Python----"

# Right align
print("Python".rjust(10))      # "    Python"
print("Python".rjust(10, "0")) # "0000Python"

# Center align
print("Python".center(10))     # "  Python  "
print("Python".center(10, "*"))# "**Python**"

# Practical example - table output
print("이름".ljust(10) + "나이".rjust(5))
print("홍길동".ljust(10) + "25".rjust(5))
print("김철수".ljust(10) + "30".rjust(5))

String Formatting

f-string (Python 3.6+, recommended)

name = "홍길동"
age = 25
height = 175.5

# Basic usage
print(f"이름: {name}, 나이: {age}")

# Expressions
print(f"내년 나이: {age + 1}")
print(f"키(cm): {height}")

# Format specifiers
price = 1234567
print(f"가격: {price:,}원")        # 가격: 1,234,567원

pi = 3.14159265
print(f"원주율: {pi:.2f}")         # 원주율: 3.14

# Alignment and width
print(f"{'Python':>10}")          # "    Python"
print(f"{'Python':<10}")          # "Python    "
print(f"{'Python':^10}")          # "  Python  "
print(f"{'Python':*^10}")         # "**Python**"

# Number bases
num = 255
print(f"10진수: {num}")           # 10진수: 255
print(f"16진수: {num:x}")         # 16진수: ff
print(f"8진수: {num:o}")          # 8진수: 377
print(f"2진수: {num:b}")          # 2진수: 11111111

format() Method

# Position-based
print("이름: {}, 나이: {}".format("홍길동", 25))

# Specify index
print("{1}, {0}".format("World", "Hello"))  # Hello, World

# Specify name
print("이름: {name}, 나이: {age}".format(name="홍길동", age=25))

# Specify format
print("가격: {:,}원".format(1234567))
print("비율: {:.1%}".format(0.856))

% Formatting (Legacy)

name = "홍길동"
age = 25

print("이름: %s, 나이: %d" % (name, age))
print("비율: %.2f%%" % 85.678)

Practical Examples

Email Validation

def validate_email(email):
    """Simple email validation"""
    # Check if @ is included
    if "@" not in email:
        return False

    # Split by @
    parts = email.split("@")
    if len(parts) != 2:
        return False

    local, domain = parts

    # Validate local part and domain
    if not local or not domain:
        return False

    # Check if domain contains .
    if "." not in domain:
        return False

    return True

# Test
emails = [
    "user@example.com",      # ✅
    "invalid.email",         # ❌
    "@example.com",          # ❌
    "user@",                 # ❌
]

for email in emails:
    result = "유효" if validate_email(email) else "무효"
    print(f"{email}: {result}")

Text Masking

def mask_phone(phone):
    """Mask phone number"""
    if len(phone) == 11:
        return phone[:3] + "****" + phone[7:]
    elif len(phone) == 10:
        return phone[:3] + "***" + phone[6:]
    return phone

def mask_email(email):
    """Mask email"""
    local, domain = email.split("@")
    if len(local) <= 2:
        masked_local = local[0] + "*"
    else:
        masked_local = local[0] + "*" * (len(local) - 2) + local[-1]
    return f"{masked_local}@{domain}"

# Usage
print(mask_phone("01012345678"))    # 010****5678
print(mask_email("hong@example.com"))  # h**g@example.com

String Analyzer

def analyze_string(text):
    """Detailed string analysis"""
    return {
        "길이": len(text),
        "단어수": len(text.split()),
        "대문자": sum(1 for c in text if c.isupper()),
        "소문자": sum(1 for c in text if c.islower()),
        "숫자": sum(1 for c in text if c.isdigit()),
        "공백": sum(1 for c in text if c.isspace()),
        "특수문자": sum(1 for c in text if not c.isalnum() and not c.isspace())
    }

text = "Hello Python 2024! Welcome to coding."
result = analyze_string(text)

print("=== 문자열 분석 ===")
for key, value in result.items():
    print(f"{key}: {value}")

URL Parser

def parse_url(url):
    """Parse URL"""
    # Split protocol
    if "://" in url:
        protocol, rest = url.split("://", 1)
    else:
        protocol = "http"
        rest = url

    # Split path
    if "/" in rest:
        domain, path = rest.split("/", 1)
        path = "/" + path
    else:
        domain = rest
        path = "/"

    # Split port
    if ":" in domain:
        domain, port = domain.split(":")
    else:
        port = "80" if protocol == "http" else "443"

    return {
        "프로토콜": protocol,
        "도메인": domain,
        "포트": port,
        "경로": path
    }

url = "https://www.example.com:8080/api/users"
result = parse_url(url)

for key, value in result.items():
    print(f"{key}: {value}")

Unicode and Encoding

Working with Unicode

# Korean
text = "안녕하세요"
print(len(text))  # 5

# Emoji
emoji = "😀🎉"
print(len(emoji))  # 2

# Unicode code points
print(ord("A"))      # 65
print(chr(65))       # A
print(ord("가"))     # 44032
print(chr(44032))    # 가

Encoding/Decoding

text = "안녕하세요"

# Encoding (string → bytes)
utf8_bytes = text.encode("utf-8")
print(utf8_bytes)  # b'\xec\x95\x88\xeb\x85\x95...'

euckr_bytes = text.encode("euc-kr")
print(euckr_bytes)

# Decoding (bytes → string)
decoded = utf8_bytes.decode("utf-8")
print(decoded)  # 안녕하세요

Frequently Asked Questions

Q1. Are strings immutable?

A: Yes, strings are immutable.

text = "hello"
# text[0] = "H"  # ❌ TypeError

# Create new string
text = "H" + text[1:]  # ✅ "Hello"

Q2. + vs join, which is faster?

A: join is faster when concatenating many strings.

# ❌ Slow (many string creations)
result = ""
for i in range(1000):
    result += str(i)

# ✅ Fast
result = "".join(str(i) for i in range(1000))

Q3. How to handle indentation in multiline strings?

A: Use the textwrap module

from textwrap import dedent

text = dedent("""
    첫 번째 줄
    두 번째 줄
    세 번째 줄
""").strip()

print(text)
# 첫 번째 줄
# 두 번째 줄
# 세 번째 줄

Q4. Do I need regular expressions?

A: They are necessary for complex pattern matching.

import re

# Simple case: string methods
email = "user@example.com"
if "@" in email and "." in email:
    print("이메일 형식")

# Complex case: regular expressions
pattern = r"^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$"
if re.match(pattern, email):
    print("유효한 이메일")

Next Steps

You've mastered string processing!

Key Takeaways:
✅ Indexing and slicing
✅ Various string methods
✅ String formatting (f-string)
✅ Search, transform, validate
✅ Practical examples

Next Step: Learn collections in Lists and Tuples!