"""Cut stories into scene-sized chunks on paragraph boundaries."""
import json, pathlib, re

TARGET = 320   # words; a scene is a situation with people in it

stories = json.loads(pathlib.Path('stories.json').read_text(encoding='utf-8'))
chunks = []
for si, s in enumerate(stories):
    paras = [p.strip() for p in re.split(r'\n\s*\n', s['text']) if p.strip()]
    buf, n = [], 0
    for p in paras:
        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('chunks.json').write_text(json.dumps(chunks), encoding='utf-8')
ws = sorted(c['words'] for c in chunks)
print(f'chunks: {len(chunks)}  from {len(stories)} stories')
print(f'words/chunk  min {ws[0]}  median {ws[len(ws)//2]}  max {ws[-1]}')
print(f'total words: {sum(ws):,}')