Strings: The Complete Guide

# Single and double quotes — interchangeable
name = 'Alice'
greeting = "Hello, World!"

# Use the other quote type to avoid escaping
message = "It's a great day"    # single quote inside double quotes
html = 'He said "Python rocks"' # double quotes inside single quotes

# Triple quotes — for multiline text
bio = """My name is Alice.
I love Python.
I write code every day."""

print(bio)
# My name is Alice.
# I love Python.
# I write code every day.

word = "Python"
#       P y t h o n
# index: 0 1 2 3 4 5
# neg:  -6-5-4-3-2-1

print(word[0])   # P
print(word[1])   # y
print(word[-1])  # n  (last character)
print(word[-2])  # o  (second to last)

text = "Hello, Python!"

print(text[0:5])    # Hello    (index 0 up to but not including 5)
print(text[7:])     # Python!  (from index 7 to end)
print(text[:5])     # Hello    (from start to index 5)
print(text[-7:])    # Python!  (last 7 characters)
print(text[::2])    # Hlo yhn  (every other character)
print(text[::-1])   # !nohtyP ,olleH  (reversed!)

word = "hello"

# This raises a TypeError
# word[0] = "H"  # TypeError: 'str' object does not support item assignment

# Instead, create a new string
word = "H" + word[1:]
print(word)  # Hello

text = "  Hello, Python!  "

print(text.upper())      # "  HELLO, PYTHON!  "
print(text.lower())      # "  hello, python!  "
print(text.title())      # "  Hello, Python!  "
print(text.capitalize()) # "  hello, python!  " (only first char of whole string)
print(text.swapcase())   # "  hELLO, pYTHON!  "

text = "   hello world   "

print(text.strip())    # "hello world"  — removes both ends
print(text.lstrip())   # "hello world   " — removes left only
print(text.rstrip())   # "   hello world" — removes right only

# Strip specific characters
filename = "###report.csv###"
print(filename.strip("#"))  # "report.csv"

# split() — break string into a list
sentence = "the quick brown fox"
words = sentence.split()          # splits on whitespace by default
print(words)  # ['the', 'quick', 'brown', 'fox']

csv_line = "Alice,30,Engineer"
parts = csv_line.split(",")
print(parts)  # ['Alice', '30', 'Engineer']

# split with maxsplit
data = "one:two:three:four"
print(data.split(":", 2))  # ['one', 'two', 'three:four']

# join() — combine a list into a string
words = ['Python', 'is', 'great']
sentence = " ".join(words)
print(sentence)  # Python is great

# Join with different separators
print(", ".join(["apple", "banana", "cherry"]))  # apple, banana, cherry
print("-".join("ABC"))  # A-B-C

text = "The quick brown fox jumps over the lazy dog"

# find() — returns index, or -1 if not found
print(text.find("fox"))    # 16
print(text.find("cat"))    # -1

# index() — like find(), but raises ValueError if not found
print(text.index("fox"))   # 16

# count() — how many times does a substring appear?
print(text.count("the"))   # 1 (case-sensitive)
print(text.lower().count("the"))  # 2

# startswith() and endswith()
url = "https://python.org"
print(url.startswith("https"))  # True
print(url.endswith(".org"))      # True
print(url.startswith(("http", "ftp")))  # True — accepts a tuple!

sentence = "I love Java. Java is great."

new_sentence = sentence.replace("Java", "Python")
print(new_sentence)  # I love Python. Python is great.

# Replace only the first occurrence
partial = sentence.replace("Java", "Python", 1)
print(partial)  # I love Python. Java is great.

print("hello".isalpha())     # True  — all letters
print("hello123".isalpha())  # False — contains digits
print("123".isdigit())       # True  — all digits
print("abc123".isalnum())    # True  — letters or digits
print("  ".isspace())        # True  — all whitespace
print("Hello World".istitle()) # True — title case

text = "Python is amazing"

print("Python" in text)         # True
print("python" in text)         # False — case-sensitive
print("python" in text.lower()) # True
print("Java" not in text)       # True

# Extremely useful in conditionals
email = "user@example.com"
if "@" in email and "." in email:
    print("Looks like a valid email")  # Looks like a valid email

name = "Alice"
age = 30
score = 95.678

# Basic variable embedding
print(f"Name: {name}, Age: {age}")  # Name: Alice, Age: 30

# Expressions — any valid Python expression works inside braces
print(f"In 5 years: {age + 5}")          # In 5 years: 35
print(f"Upper: {name.upper()}")          # Upper: ALICE
print(f"Initials: {name[0]}.")           # Initials: A.

# Number formatting
print(f"Score: {score:.1f}")             # Score: 95.7  (1 decimal)
print(f"Score: {score:.2f}")             # Score: 95.68 (2 decimals)
print(f"Big: {1234567:,}")               # Big: 1,234,567 (comma separator)
print(f"Percent: {0.875:.1%}")           # Percent: 87.5%
print(f"Hex: {255:#x}")                  # Hex: 0xff

# Width and alignment
print(f"{'Left':<10}|{'Center':^10}|{'Right':>10}")
# Left      |  Center  |     Right

# Debugging with = (Python 3.8+)
x = 42
print(f"{x = }")    # x = 42  — shows name AND value

# Without raw string — \n is a newline, \t is a tab
path = "C:\new_folder\table.csv"
print(path)
# C:
# ew_folder	able.csv  — oops!

# With raw string — backslashes are literal
path = r"C:\new_folder\table.csv"
print(path)  # C:\new_folder\table.csv

# Also useful for regex patterns
import re
pattern = r"\d+\.\d+"  # matches decimal numbers like 3.14
matches = re.findall(pattern, "pi is 3.14 and e is 2.71")
print(matches)  # ['3.14', '2.71']

print("apple" == "apple")  # True
print("apple" == "Apple")  # False — case-sensitive
print("apple" < "banana")  # True  — 'a' comes before 'b'
print("b" > "a")           # True
print("Z" < "a")           # True  — uppercase letters come before lowercase in Unicode

# Case-insensitive comparison
s1 = "Hello"
s2 = "hello"
print(s1.lower() == s2.lower())  # True

# HTML template
html_template = """
<!DOCTYPE html>
<html>
  <head><title>{title}</title></head>
  <body><h1>{heading}</h1></body>
</html>
""".strip()

# SQL query stored cleanly
query = """
    SELECT name, email
    FROM users
    WHERE active = 1
    ORDER BY name
""".strip()

print(query)
# SELECT name, email
# FROM users
# WHERE active = 1
# ORDER BY name

def normalize_username(raw_input):
    """Clean and normalize a username."""
    cleaned = raw_input.strip()           # remove leading/trailing spaces
    cleaned = cleaned.lower()             # lowercase
    cleaned = cleaned.replace(" ", "_")   # replace spaces with underscores
    return cleaned

print(normalize_username("  Alice Smith  "))  # alice_smith
print(normalize_username("BOB JONES"))        # bob_jones

def parse_csv_line(line):
    """Parse a CSV line into a dictionary."""
    fields = line.strip().split(",")
    return {
        "name":  fields[0],
        "age":   int(fields[1]),
        "city":  fields[2]
    }

record = parse_csv_line("Alice,30,New York")
print(record)  # {'name': 'Alice', 'age': 30, 'city': 'New York'}
print(f"{record['name']} is {record['age']} years old, lives in {record['city']}.")
# Alice is 30 years old, lives in New York.

def validate_password(password):
    errors = []
    if len(password) < 8:
        errors.append("at least 8 characters required")
    if not any(c.isupper() for c in password):
        errors.append("must contain an uppercase letter")
    if not any(c.isdigit() for c in password):
        errors.append("must contain a digit")
    return errors

issues = validate_password("hello")
if issues:
    print("Password issues: " + ", ".join(issues))
# Password issues: at least 8 characters required, must contain an uppercase letter, must contain a digit

issues = validate_password("SecurePass1")
print(issues)  # []  — no issues!