# Words by the Numbers 7, Exercise 3
import pathlib, re, statistics, 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 syllables(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 grade(text):
    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(syllables(w) for w in words)
    return 0.39 * len(words) / len(sentences) + 11.8 * syl / len(words) - 15.59

SIZE = 1000
print(f"{'book':22} {'chunks':>6} {'mean':>6} {'sd':>5} {'min':>6} {'max':>6}  share above grade 10")
for title, number in BOOKS.items():
    words = load(number).split()
    chunks = [" ".join(words[i:i + SIZE]) for i in range(0, len(words) - SIZE, SIZE)]
    g = [grade(c) for c in chunks]
    share = sum(x > 10 for x in g) / len(g)
    print(f"{title:22} {len(g):6d} {statistics.mean(g):6.1f} {statistics.stdev(g):5.1f} {min(g):6.1f} {max(g):6.1f}  {share:5.0%}")

# Output when run (Python 3.14; texts from the Project Gutenberg plain-text files):
# book                   chunks   mean    sd    min    max  share above grade 10
# Alice in Wonderland        26    6.1   1.8    3.6   12.1     4%
# The Time Machine           32    7.6   1.6    4.4   10.9     9%
# Pride and Prejudice       127    8.6   2.1    4.5   15.7    24%
# The Federalist Papers     192   16.1   2.0   10.9   23.3   100%