from difflib import SequenceMatcher

def similarity(a, b):
    return SequenceMatcher(None, a, b).ratio()

print(similarity("Apple Inc.", "Apple Incorporated"))
# Output: 0.7...

from difflib import SequenceMatcher

def get_similarity(str1, str2):
    """Returns a ratio between 0 and 1."""
    return SequenceMatcher(None, str1, str2).ratio()

# Example
s1 = "Acme Corp"
s2 = "Acme Corporation"
print(f"Similarity: {get_similarity(s1, s2)}")

from difflib import get_close_matches

word = "appel"
possibilities = ["ape", "apple", "peach", "puppy"]
matches = get_close_matches(word, possibilities, n=1, cutoff=0.6)
print(matches)
# Output: ['apple']

from rapidfuzz import fuzz, process

# Simple Ratio
score = fuzz.ratio("this is a test", "this is a test!")
print(score)

# Partial Ratio (good for substrings)
score = fuzz.partial_ratio("this is a test", "this is a test!")
print(score)

# Extraction
choices = ["Atlanta Falcons", "New York Jets", "New York Giants", "Dallas Cowboys"]
best_match = process.extractOne("new york jets", choices)
print(best_match)
# Output: ('New York Jets', 100.0, 1)

import re

def normalize(text):
    # Convert to lowercase
    text = text.lower()
    # Remove special characters
    text = re.sub(r'[^\w\s]', '', text)
    # Normalize whitespace
    text = " ".join(text.split())
    # Common abbreviations
    text = text.replace("limited", "ltd").replace("corporation", "corp")
    return text

s1 = "Acme  Corporation, Inc."
s2 = "acme corp inc"
print(normalize(s1) == normalize(s2))

clean_names = ["Google LLC", "Microsoft Corp", "Apple Inc"]
dirty_names = ["google", "Microsft", "Apple"]

results = {}
for dirty in dirty_names:
    # simple containment check first
    match = None
    for clean in clean_names:
        if dirty.lower() in clean.lower():
            match = clean
            break

    # fallback to fuzzy
    if not match:
        matches = get_close_matches(dirty, clean_names, n=1, cutoff=0.6)
        if matches:
            match = matches[0]

    results[dirty] = match