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
27 lines
1.6 KiB
Python
27 lines
1.6 KiB
Python
"""Split the Project Gutenberg text of George Horace Lorimer, *Letters from a Self-Made Merchant to His Son*
|
|
(1902, eBook #21959), one story per letter. The body heads each letter with a centred roman numeral on its
|
|
own line; there must be 20, numbered 1..20. Each letter's title is its contents synopsis (the italic line
|
|
saying what occasioned it), which is the closest thing the book has to a story title."""
|
|
import re, sys
|
|
sys.path.insert(0, '..')
|
|
from gutenberg_chunks import gutenberg_body, paragraphs, write
|
|
|
|
VOLUME = 'Letters from a Self-Made Merchant to His Son (George Horace Lorimer, 1902)'
|
|
ROMAN = {'I': 1, 'V': 5, 'X': 10, 'L': 50}
|
|
def roman(s): return sum(-ROMAN[a] if ROMAN[a] < ROMAN.get(b, 0) else ROMAN[a] for a, b in zip(s, s[1:] + ' '))
|
|
|
|
lines = gutenberg_body('corpus/letters-from-a-self-made-merchant.txt')
|
|
c0 = next(i for i, l in enumerate(lines) if l.strip().startswith('CONTENTS'))
|
|
heads = [i for i, l in enumerate(lines) if i > c0 and re.fullmatch(r' {20,}[IVXL]+\s*', l)]
|
|
assert [roman(lines[i].strip()) for i in heads] == list(range(1, 21)), [lines[i].strip() for i in heads]
|
|
toc = '\n'.join(lines[c0 + 1:heads[0]])
|
|
synopses = [re.sub(r'\s+', ' ', s).strip() for s in re.findall(r'_([^_]+)_', toc)]
|
|
assert len(synopses) >= 20, len(synopses)
|
|
stories = []
|
|
for n, a in enumerate(heads):
|
|
body = lines[a + 1:(heads[n + 1] if n + 1 < len(heads) else len(lines))]
|
|
paras = paragraphs('\n'.join(body), drop=(r'THE END\.?', r'\[Illustration[^\]]*\]'))
|
|
stories.append({'volume': VOLUME, 'title': f'Letter {n + 1}: {synopses[n]}', 'words': sum(len(p.split()) for p in paras),
|
|
'text': '\n\n'.join(paras)})
|
|
write('.', stories)
|