Chapter 9: String Manipulation

message = "Hello World"

# Indexing - get a single character
print(message[0])     # First character
print(message[6])     # Seventh character (index 6)

# Slicing - get a section of the string
print(message[0:5])   # Characters from index 0 up to (not including) 5
print(message[-5:])   # Last 5 characters

# The full string, backwards
print(message[::-1])

text = "  Hello, Python Learners!  "

# Changing case
print(text.upper())          # ALL CAPS
print(text.lower())          # all lowercase
print(text.title())          # Title Case

# Removing whitespace
print(text.strip())          # Remove spaces from both ends

# Replacing text
print(text.replace("Python", "Amazing"))

# Counting and finding
message = "abracadabra"
print(message.count("a"))    # How many times does 'a' appear?
print(message.find("cad"))   # At which index does 'cad' start?

# Checking what a string starts or ends with
filename = "homework.pdf"
print(filename.startswith("home"))   # True
print(filename.endswith(".pdf"))     # True
print(filename.endswith(".docx"))    # False

# Checking character types
pin = "1234"
word = "Hello"
mixed = "abc123"

print(pin.isdigit())     # True - all characters are digits
print(word.isalpha())    # True - all characters are letters
print(mixed.isalpha())   # False - contains digits too

# Using 'in' to search within a string
sentence = "The quick brown fox jumps over the lazy dog"
print("fox" in sentence)         # True
print("cat" in sentence)         # False
print("fox" not in sentence)     # False

# Splitting a sentence into words (splits on spaces by default)
sentence = "Python is a powerful language"
words = sentence.split()
print(words)
print("There are", len(words), "words")

# Splitting CSV-like data on commas
csv_line = "Alice,17,Computer Science,A*"
fields = csv_line.split(",")
print(fields)
print("Name:", fields[0])
print("Age:", fields[1])
print("Subject:", fields[2])
print("Grade:", fields[3])

# Joining a list back into a string
rejoined = " - ".join(fields)
print(rejoined)

# Practical: reformat comma-separated data as tab-separated
tab_separated = "\t".join(fields)
print(tab_separated)

# Simple traversal: print each character
word = "Python"
for char in word:
    print(char, end=" ")
print()  # New line

# Building a new string: remove all vowels
original = "String Manipulation"
result = ""
for char in original:
    if char.lower() not in "aeiou":
        result = result + char
print("Without vowels:", result)

# Building a new string: add a dash between each character
spaced = ""
for i in range(len(original)):
    spaced = spaced + original[i]
    if i < len(original) - 1:
        spaced = spaced + "-"
print("Dashed:", spaced)

# Count different character types
text = "Hello World 123!"
letters = 0
digits = 0
spaces = 0
other = 0
for char in text:
    if char.isalpha():
        letters += 1
    elif char.isdigit():
        digits += 1
    elif char == " ":
        spaces += 1
    else:
        other += 1
print(f"Letters: {letters}, Digits: {digits}, Spaces: {spaces}, Other: {other}")

def validate_email(email):
    """Check if an email address is valid."""
    # Remove any accidental whitespace
    email = email.strip()

    # Check 1: Must contain exactly one @ symbol
    if email.count("@") != 1:
        return "Invalid: must contain exactly one @ symbol"

    # Check 2: Split into local part and domain
    parts = email.split("@")
    local = parts[0]
    domain = parts[1]

    # Check 3: Local part must not be empty
    if len(local) == 0:
        return "Invalid: nothing before the @ symbol"

    # Check 4: Domain must not be empty
    if len(domain) == 0:
        return "Invalid: nothing after the @ symbol"

    # Check 5: Domain must contain a dot
    if "." not in domain:
        return "Invalid: domain must contain a dot (e.g. .com, .co.uk)"

    # Check 6: Must end with a valid domain extension
    valid_endings = [".com", ".org", ".co.uk", ".net", ".edu", ".ac.uk"]
    has_valid_ending = False
    for ending in valid_endings:
        if email.endswith(ending):
            has_valid_ending = True
    if not has_valid_ending:
        return "Invalid: unrecognised domain extension"

    return "Valid email address"

# Test with different email addresses
test_emails = [
    "student@school.co.uk",
    "alice@gmail.com",
    "missing-at-sign.com",
    "@nodomain.com",
    "user@",
    "double@@at.com",
    "bob@website.xyz"
]

for email in test_emails:
    result = validate_email(email)
    print(f"{email:30s} -> {result}")