#!/usr/bin/env python3
"""Decode / re-encode the __bundler/template of the apex-fusion site.

  python3 bundle.py decode  index.html  page.html     # template -> editable HTML
  python3 bundle.py encode  index.html  page.html  out.html   # editable HTML -> site file

The bundler stores the page as a JSON string with '</' written as '<\\u002F'
(so the inner page's </script> tags cannot terminate the outer tag). Encoding
mirrors that exactly, and `encode` proves it by asserting that an untouched
page round-trips byte-identical before writing.
"""
import json, re, sys

TAG = re.compile(r'(<script type="__bundler/template">)(.*?)(</script>)', re.S)

def decode(site):
    return json.loads(TAG.search(site).group(2))

def encode_template(page):
    e = json.dumps(page, ensure_ascii=False)
    return '\n' + e.replace('</', '<\\u002F') + '\n  '

def encode(site, page):
    m = TAG.search(site)
    return site[:m.start(2)] + encode_template(page) + site[m.end(2):]

if __name__ == '__main__':
    cmd, site_path, page_path = sys.argv[1:4]
    site = open(site_path, encoding='utf-8').read()
    if cmd == 'decode':
        open(page_path, 'w', encoding='utf-8').write(decode(site))
        print('decoded', len(decode(site)), 'chars')
    elif cmd == 'encode':
        out_path = sys.argv[4]
        # fidelity proof: the original template must re-encode to itself
        orig_block = TAG.search(site).group(2)
        assert encode_template(decode(site)) == orig_block, 'encoder no longer byte-exact for the untouched page'
        page = open(page_path, encoding='utf-8').read()
        out = encode(site, page)
        assert decode(out) == page, 'round-trip mismatch after encode'
        open(out_path, 'w', encoding='utf-8').write(out)
        print('encoded', len(out), 'bytes ->', out_path)