"""Print an OCR chunk without the repeated 'Text in image' block (for reading). python tools/strip_dup.py file [first_page last_page]"""
import re, sys
s = open(sys.argv[1], encoding="utf-8").read()
s = re.sub(r"!\[[^\]]*\]\([^)]*\)\s*<!--image-meta[^>]*-->\s*\*\*Text in image:\*\*.*?(?=\n---\n|\Z)", "", s, flags=re.S)
if len(sys.argv) > 3:
    a, b = int(sys.argv[2]), int(sys.argv[3])
    pages = re.split(r"(?m)^(?=# Page \d+)", s)
    s = "".join(p for p in pages if (m := re.match(r"# Page (\d+)", p)) and a <= int(m.group(1)) <= b)
sys.stdout.reconfigure(encoding="utf-8")
print(re.sub(r"\n{3,}", "\n\n", s))