JesseMarkowitzandClaude Opus 5.5
3a4758172d
Fourteen corpora split and classified: aesop, bierce, chekhov, holmes, keefe, lawson, lorimer, maupassant, nobody, plaintales, poe, torchy, wallingford and winesburg, each with its splitter and the hand-written groups and pages; catalogue v2 and v3; and the shared splitters gutenberg_chunks.py, se_split.py and se_build.py. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019rwKTmug58sEsJ72AuWsEi
61 lines
3.2 KiB
Python
61 lines
3.2 KiB
Python
"""Split the Project Gutenberg plain text of Guy de Maupassant, *Original Short Stories, Volume IV*
|
|
(eBook #3080), into stories, then cut scenes with the same rule as ../chunk.py and
|
|
../wharton/split_gutenberg.py (paragraph boundaries, ~320 words, tail >= 80).
|
|
Deterministic: titles are the twelve contents entries, matched as whole upper-case lines after the
|
|
indented contents block. Two body headers differ from their contents entry ("THE TRIP OF LE HORLA",
|
|
"FAREWELL!"), so HEADS maps those. "PART I".."PART V" headings are dropped, as is the one bracketed
|
|
editorial note ("[This story appeared in ...]"); the Gutenberg licence after END is dropped."""
|
|
import json, pathlib, re
|
|
|
|
TITLES = ['The Moribund', 'The Gamekeeper', 'The Story of a Farm Girl', 'The Wreck',
|
|
"Theodule Sabot's Confession", 'The Wrong House', 'The Diamond Necklace',
|
|
'The Marquis de Fumerol', 'The Trip of the Horla', 'Farewell', 'The Wolf', 'The Inn']
|
|
HEADS = {'The Trip of the Horla': 'THE TRIP OF LE HORLA', 'Farewell': 'FAREWELL!'}
|
|
TARGET = 320
|
|
VOLUME = 'Original Short Stories, Volume IV (Guy de Maupassant, tr. 1903)'
|
|
|
|
here = pathlib.Path(__file__).parent
|
|
raw = (here / 'corpus/original-short-stories-vol4.txt').read_text(encoding='utf-8').replace('\r', '')
|
|
raw = raw[:raw.index('*** END OF THE PROJECT GUTENBERG')]
|
|
lines = raw.split('\n')
|
|
start = next(i for i, l in enumerate(lines) if l.strip() == 'VOLUME IV.')
|
|
heads = []
|
|
for t in TITLES:
|
|
h = HEADS.get(t, t.upper())
|
|
# Body headers sit flush left; the contents block is indented, so match the unstripped line.
|
|
hits = [i for i, l in enumerate(lines) if i > start and l.rstrip() == h]
|
|
assert len(hits) == 1, (t, hits)
|
|
heads.append(hits[0])
|
|
assert heads == sorted(heads)
|
|
|
|
stories = []
|
|
for n, (t, a) in enumerate(zip(TITLES, heads)):
|
|
b = heads[n + 1] if n + 1 < len(heads) else len(lines)
|
|
body = '\n'.join(lines[a + 1:b])
|
|
paras = []
|
|
for p in re.split(r'\n\s*\n', body):
|
|
p = re.sub(r'\s+', ' ', p).strip()
|
|
if not p or re.fullmatch(r'PART [IVX]+', p) or re.fullmatch(r'\[.*\]', p): continue
|
|
paras.append(p)
|
|
stories.append({'volume': VOLUME, 'title': t, '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})
|
|
|
|
(here / 'stories.json').write_text(json.dumps(stories, indent=1, ensure_ascii=False), encoding='utf-8')
|
|
(here / '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']:34} {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):,}')
|