# Words by the Numbers 7, Exercise 2
import pathlib, re, urllib.request

BOOKS = {"Alice in Wonderland": 11, "The Time Machine": 35,
         "Pride and Prejudice": 1342, "The Federalist Papers": 1404}

def load(number):
    path = pathlib.Path(f"pg{number}.txt")
    if not path.exists():
        url = f"https://www.gutenberg.org/cache/epub/{number}/pg{number}.txt"
        req = urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0"})
        path.write_bytes(urllib.request.urlopen(req).read())
    raw = path.read_text(encoding="utf-8-sig").replace("\r", "")
    start = raw.index("\n", raw.index("*** START OF")) + 1
    return raw[start:raw.index("*** END OF")]

def careful(word):
    w = re.sub(r"[^a-z]", "", word.lower())
    if not w:
        return 0
    n = len(re.findall(r"[aeiouy]+", w))
    if w.endswith("e") and not w.endswith("le") and n > 1:
        n -= 1
    if w.endswith("ed") and not w.endswith(("ted", "ded")) and n > 1:
        n -= 1
    return max(n, 1)

def naive(word):                                  # just count the vowel runs
    return max(len(re.findall(r"[aeiouy]+", word.lower())), 1)

def grade(text, counter):
    for fancy, plain in (("\u2019", "'"), ("\u201c", '"'), ("\u201d", '"')):
        text = text.replace(fancy, plain)
    text = re.sub(r"\s+", " ", text)
    sentences = [s for s in re.split(r"(?<=[.!?])[\"')\]]*\s+", text.strip()) if s]
    words = re.findall(r"[A-Za-z]+(?:'[A-Za-z]+)?", text)
    syl = sum(counter(w) for w in words)
    return 0.39 * len(words) / len(sentences) + 11.8 * syl / len(words) - 15.59

print(f"{'book':22} {'careful':>8} {'naive':>7} {'difference':>11}")
for title, number in BOOKS.items():
    text = load(number)
    a, b = grade(text, careful), grade(text, naive)
    print(f"{title:22} {a:8.2f} {b:7.2f} {b - a:11.2f}")

# Output when run (Python 3.14; texts from the Project Gutenberg plain-text files):
# book                    careful   naive  difference
# Alice in Wonderland        5.97    7.46        1.49
# The Time Machine           7.46    9.01        1.55
# Pride and Prejudice        8.35    9.77        1.43
# The Federalist Papers     16.17   17.55        1.39