String Manipulation Utilities

Basic String Operations #

Case conversions #

text = "Hello World"

# Convert to different cases
upper = text.upper()        # "HELLO WORLD"
lower = text.lower()        # "hello world"
title = text.title()        # "Hello World"
capitalize = text.capitalize()  # "Hello world"

# Check case
is_upper = text.isupper()   # False
is_lower = text.islower()   # False
is_title = text.istitle()   # True

String formatting #

name = "Alice"
age = 30

# f-strings (Python 3.6+, recommended)
message = f"Hello, {name}! You are {age} years old."

# .format() method
message = "Hello, {}! You are {} years old.".format(name, age)

# Named placeholders
message = "Hello, {name}! You are {age} years old.".format(name=name, age=age)

# % formatting (old style)
message = "Hello, %s! You are %d years old." % (name, age)

String Cleaning and Validation #

Remove whitespace #

text = "  Hello World  \n"

stripped = text.strip()        # "Hello World"
left_strip = text.lstrip()     # "Hello World  \n"
right_strip = text.rstrip()    # "  Hello World"

# Remove specific characters
cleaned = text.strip(' \n')    # "Hello World"

Validate string content #

def is_email(email):
    """Simple email validation."""
    return '@' in email and '.' in email.split('@')[1]

def is_phone_number(phone):
    """Check if string contains only digits and common phone characters."""
    allowed = set('0123456789+-() ')
    return all(char in allowed for char in phone)

def is_alphanumeric(text):
    """Check if string contains only letters and numbers."""
    return text.isalnum()

# Examples
print(is_email("[email protected]"))  # True
print(is_phone_number("+1 (555) 123-4567"))  # True
print(is_alphanumeric("Hello123"))  # True

Text Search and Replace #

Find and replace #

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

# Simple replace
new_text = text.replace("fox", "cat")

# Replace with limit
new_text = text.replace("the", "a", 1)  # Replace only first occurrence

# Case-insensitive replace
import re
new_text = re.sub(r'the', 'a', text, flags=re.IGNORECASE)

Extract information #

import re

def extract_emails(text):
    """Extract email addresses from text."""
    pattern = r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b'
    return re.findall(pattern, text)

def extract_phone_numbers(text):
    """Extract phone numbers from text."""
    pattern = r'\b\d{3}[-.]?\d{3}[-.]?\d{4}\b'
    return re.findall(pattern, text)

def extract_urls(text):
    """Extract URLs from text."""
    pattern = r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'
    return re.findall(pattern, text)

# Example usage
text = "Contact us at [email protected] or call 555-123-4567. Visit https://example.com"
emails = extract_emails(text)
phones = extract_phone_numbers(text)
urls = extract_urls(text)

String Splitting and Joining #

Split strings #

text = "apple,banana,cherry,date"

# Split by delimiter
fruits = text.split(',')  # ['apple', 'banana', 'cherry', 'date']

# Split with limit
parts = text.split(',', 2)  # ['apple', 'banana', 'cherry,date']

# Split by whitespace
sentence = "The quick brown fox"
words = sentence.split()  # ['The', 'quick', 'brown', 'fox']

# Split lines
multiline = "Line 1\nLine 2\nLine 3"
lines = multiline.splitlines()  # ['Line 1', 'Line 2', 'Line 3']

Join strings #

words = ['apple', 'banana', 'cherry']

# Join with delimiter
result = ','.join(words)  # "apple,banana,cherry"
result = ' and '.join(words)  # "apple and banana and cherry"

# Join with newlines
result = '\n'.join(words)

Advanced String Manipulation #

Pad strings #

text = "Hello"

# Pad with spaces
left_padded = text.ljust(10)     # "Hello     "
right_padded = text.rjust(10)    # "     Hello"
center_padded = text.center(10)  # "  Hello   "

# Pad with specific character
zero_padded = text.zfill(10)     # "00000Hello"
dash_padded = text.center(10, '-')  # "--Hello---"

Reverse strings #

text = "Hello World"

# Reverse entire string
reversed_text = text[::-1]  # "dlroW olleH"

# Reverse words
words = text.split()
reversed_words = ' '.join(reversed(words))  # "World Hello"

# Reverse each word individually
reversed_each = ' '.join(word[::-1] for word in words)  # "olleH dlroW"

Generate strings #

import string
import random

def generate_password(length=12):
    """Generate a random password."""
    characters = string.ascii_letters + string.digits + "!@#$%^&*"
    return ''.join(random.choice(characters) for _ in range(length))

def generate_slug(text):
    """Convert text to URL-friendly slug."""
    import re
    # Convert to lowercase and replace spaces with hyphens
    slug = re.sub(r'[^\w\s-]', '', text.lower())
    slug = re.sub(r'[\s_-]+', '-', slug)
    return slug.strip('-')

# Examples
password = generate_password(16)
slug = generate_slug("My Blog Post Title!")  # "my-blog-post-title"

Text Processing Utilities #

Count occurrences #

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

# Count specific substring
count = text.count("the")  # Case-sensitive

# Count words
words = text.lower().split()
word_count = {}
for word in words:
    word_count[word] = word_count.get(word, 0) + 1

# Using Counter
from collections import Counter
word_count = Counter(words)

Text statistics #

def text_stats(text):
    """Get basic statistics about text."""
    return {
        'characters': len(text),
        'characters_no_spaces': len(text.replace(' ', '')),
        'words': len(text.split()),
        'sentences': len(text.split('.')),
        'paragraphs': len(text.split('\n\n')),
        'lines': len(text.splitlines())
    }

# Example
text = "Hello world.\nThis is a test.\n\nNew paragraph."
stats = text_stats(text)

Clean and normalize text #

import re

def clean_text(text):
    """Clean and normalize text."""
    # Remove extra whitespace
    text = re.sub(r'\s+', ' ', text)
    
    # Remove special characters (keep letters, numbers, spaces)
    text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
    
    # Convert to lowercase
    text = text.lower()
    
    # Strip leading/trailing whitespace
    text = text.strip()
    
    return text

def remove_html_tags(text):
    """Remove HTML tags from text."""
    clean = re.compile('<.*?>')
    return re.sub(clean, '', text)

# Examples
dirty_text = "  Hello,    World!!!   "
clean = clean_text(dirty_text)  # "hello world"

html_text = "<p>Hello <b>World</b></p>"
no_html = remove_html_tags(html_text)  # "Hello World"

String Templates #

Template strings #

from string import Template

# Simple template
template = Template("Hello, $name! Welcome to $place.")
result = template.substitute(name="Alice", place="Python")

# Safe substitution (won't raise error for missing keys)
result = template.safe_substitute(name="Alice")  # Missing 'place' becomes $place

# Custom delimiter
class MyTemplate(Template):
    delimiter = '%'

template = MyTemplate("Hello, %name!")
result = template.substitute(name="Alice")

Format specifications #

# Number formatting
number = 1234.5678
formatted = f"{number:,.2f}"  # "1,234.57"
percentage = f"{0.1234:.2%}"  # "12.34%"

# Date formatting
from datetime import datetime
now = datetime.now()
formatted_date = f"{now:%Y-%m-%d %H:%M:%S}"

# String alignment and padding
name = "Alice"
formatted = f"{name:>10}"   # Right align in 10 chars
formatted = f"{name:<10}"   # Left align in 10 chars
formatted = f"{name:^10}"   # Center in 10 chars
formatted = f"{name:*^10}"  # Center with * padding