"""Сверка txt с PDF: какие слова из pdftotext не попали в txt (с учётом количества)."""
import re
import subprocess
import sys
from collections import Counter
from pathlib import Path

WORD = re.compile(r"[\wё]+", re.I)


def words(text: str) -> Counter[str]:
    text = re.sub(r"(\w)-\s*\n\s*(\w)", r"\1\2", text)  # переносы
    return Counter(w.lower() for w in WORD.findall(text))


args = sys.argv[1:]
out = None
if "--out" in args:
    i = args.index("--out")
    out = Path(args[i + 1])
    del args[i : i + 2]
for arg in args:
    pdf = Path(arg)
    ref = words(subprocess.run(["pdftotext", str(pdf), "-"], capture_output=True, text=True).stdout)
    got = words(((out / pdf.name) if out else pdf).with_suffix(".txt").read_text())
    lost = ref - got
    total = sum(ref.values())
    print(f"{pdf.name}: слов {total}, потеряно {sum(lost.values())} ({sum(lost.values()) / total:.2%})")
    print("   ", lost.most_common(40))