"""Split the Standard Ebooks single-page HTML of W. W. Jacobs, *The Lady of the Barge*, into stories,
then cut scenes with the same rule as ../chunk.py (paragraph boundaries, ~320 words, tail >= 80).
Deterministic: each story is a <section> with an <h2 epub:type="title">. Front and back matter
(contents, imprint, colophon, uncopyright) are dropped by name."""
import html, json, pathlib, re

SKIP = {'Table of Contents', 'Imprint', 'Colophon', 'Uncopyright'}
TARGET = 320
VOLUME = 'The Lady of the Barge (W. W. Jacobs, 1902)'

raw = pathlib.Path('corpus/lady-of-the-barge.html').read_text(encoding='utf-8')
body = raw[raw.find('<body'):]
parts = re.split(r'<h2[^>]*epub:type="title"[^>]*>(.*?)</h2>', body, flags=re.S)

def text_of(fragment):
    paras = []
    for p in re.findall(r'<p[^>]*>(.*?)</p>', fragment, flags=re.S):
        t = html.unescape(re.sub(r'<[^>]+>', '', p))
        t = re.sub(r'\s+', ' ', t).strip()
        if t: paras.append(t)
    return paras

stories = []
for i in range(1, len(parts), 2):
    title = html.unescape(re.sub(r'<[^>]+>', '', parts[i])).strip()
    if title in SKIP: continue
    paras = text_of(parts[i + 1])
    stories.append({'volume': VOLUME, 'title': title, 'words': sum(len(p.split()) for p in paras),
                    'text': '\n\n'.join(paras)})

chunks = []
for si, s in enumerate(stories):
    buf, n = [], 0
    for p in s['text'].split('\n\n'):
        w = len(p.split())
        if n + w > TARGET and buf:
            chunks.append({'story': si, 'title': s['title'], 'volume': s['volume'], 'text': ' '.join(buf), 'words': n})
            buf, n = [], 0
        buf.append(p); n += w
    if buf and n >= 80:
        chunks.append({'story': si, 'title': s['title'], 'volume': s['volume'], 'text': ' '.join(buf), 'words': n})

pathlib.Path('stories.json').write_text(json.dumps(stories, indent=1, ensure_ascii=False), encoding='utf-8')
pathlib.Path('chunks.json').write_text(json.dumps(chunks, ensure_ascii=False), encoding='utf-8')
for si, s in enumerate(stories):
    print(f"{si:2} {s['title']:24} {s['words']:6} words  {sum(c['story']==si for c in chunks):3} scenes")
ws = sorted(c['words'] for c in chunks)
print(f'stories {len(stories)}  scenes {len(chunks)}  words/scene min {ws[0]} median {ws[len(ws)//2]} max {ws[-1]}  total {sum(ws):,}')