"""Split three Project Gutenberg volumes of Sewell Ford's Torchy stories into one corpus, one story per
chapter (each chapter is a self-contained episode): *Torchy* (#20626), *On With Torchy* (#17301) and
*Torchy, Private Sec.* (#20627), in that order, which is the order of his rise from office boy.
Chapter titles come from each volume's contents; the body heads each chapter with a bare
`CHAPTER <roman>` line, and those must number 1..N with N equal to the contents count.

KNOWN DEFECT, kept on purpose: volumes 1 and 3 end in the publisher's advertisements, which this script
does not cut, so they ran into the last chapter of each. Chunks 245, 736 and 737 are advertising only;
chunks 244 and 735 are the real end of a story followed by the start of the advertising. They are listed in
NOT_STORY.json and excluded from grouping. The script was not changed afterwards, because readers had
already written records against these chunk numbers and cutting the advertising in volume 1 would shift
every later id. Fix it (stop each volume at its GROSSET & DUNLAP line) only together with a renumbering
of claude/batches."""
import re, sys
sys.path.insert(0, '..')
from gutenberg_chunks import gutenberg_body, paragraphs, write

VOLUMES = [('corpus/torchy.txt', 'Torchy (Sewell Ford, 1911)'),
           ('corpus/on-with-torchy.txt', 'On With Torchy (Sewell Ford, 1914)'),
           ('corpus/torchy-private-sec.txt', 'Torchy, Private Sec. (Sewell Ford, 1917)')]
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:] + ' '))

stories = []
for path, volume in VOLUMES:
    lines = gutenberg_body(path)
    c0 = next(i for i, l in enumerate(lines) if l.strip() == 'CONTENTS')
    contents = []
    for l in lines[c0 + 1:]:
        m = re.fullmatch(r'\s*([IVXL]+)\.\s+(.+?)(\s+\d+)?\s*', l)
        if m: contents.append(m.group(2).strip())
        elif contents and not l.strip(): continue
        elif contents and l.strip(): break
    heads = [i for i, l in enumerate(lines) if re.fullmatch(r'CHAPTER [IVXL]+', l.strip())]
    nums = [roman(lines[i].split()[1]) for i in heads]
    assert nums == list(range(1, len(contents) + 1)), (path, nums, len(contents))
    ends = heads[1:] + [len(lines)]
    for n, (a, b) in enumerate(zip(heads, ends)):
        body = lines[a + 1:b]
        k = next(j for j, l in enumerate(body) if l.strip())      # the chapter title line(s) under the heading
        while k < len(body) and body[k].strip() and body[k].strip().upper() == body[k].strip(): k += 1
        paras = paragraphs('\n'.join(body[k:]), drop=(r'THE END\.?', r'\[Illustration[^\]]*\]'))
        stories.append({'volume': volume, 'title': contents[n].title() if contents[n].isupper() else contents[n],
                        'words': sum(len(p.split()) for p in paras), 'text': '\n\n'.join(paras)})
write('.', stories)