story-to-pack: add the corpora and the catalogue v2/v3

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

tools/story-to-pack/probe/nobody/claude/build.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+"""Assemble records.json and groups.json from batches/ and groups_src.py, and check them."""
+import collections, glob, json, pathlib
+from groups_src import G, STANDING
+here = pathlib.Path(__file__).parent
+chunks = json.loads((here.parent / 'chunks.json').read_text())
+stories = json.loads((here.parent / 'stories.json').read_text())
+recs = [r for f in sorted(glob.glob(str(here / 'batches/s*.json'))) for r in json.loads(open(f).read())]
+assert [r['chunk'] for r in recs] == list(range(len(chunks))), 'every scene, once, in order'
+assert all(chunks[r['chunk']]['story'] == r['story'] for r in recs)
+
+seen = collections.Counter(m for g in G for m in g['members'])
+dup = [m for m, n in seen.items() if n > 1]
+assert not dup, f'scenes in two groups: {dup}'
+by = {r['chunk']: r for r in recs}
+out = []
+for g in G:
+    assert 3 <= len(g['options']) <= 5, g['id']
+    st = sorted({by[m]['story'] for m in g['members']})
+    stand = collections.Counter(STANDING[by[m]['story']] for m in g['members'])
+    out.append({
+        'id': g['id'], 'name': g['name'], 'predicament': g['predicament'],
+        'sentence': f"A {g['actor']} wants {g['wants']} from {g['counterpart']}.",
+        'actor': g['actor'], 'wants': g['wants'], 'counterpart': g['counterpart'],
+        'stories': st, 'story_titles': [stories[s]['title'] for s in st],
+        'standing': dict(stand), 'stage': stand.most_common(1)[0][0],
+        'members': [{'chunk': m, 'story': by[m]['story'], 'predicament': by[m]['predicament']} for m in g['members']],
+        'options': [{'text': t, 'source': s, 'moves': mv,
+                     'in_group': (int(s.split(':')[1]) in g['members']) if s.startswith('scene:') else None}
+                    for t, s, mv in g['options']],
+    })
+unassigned = [r['chunk'] for r in recs if r['chunk'] not in seen]
+(here / 'records.json').write_text(json.dumps(recs, indent=1, ensure_ascii=False))
+(here / 'groups.json').write_text(json.dumps({'groups': out, 'unassigned': unassigned}, indent=1, ensure_ascii=False))
+multi = sum(len(g['stories']) >= 2 for g in out)
+print(f'{len(recs)} scenes, {len(out)} groups ({multi} span 2+ stories), '
+      f'{sum(seen.values())} assigned, {len(unassigned)} unassigned: {unassigned}')
+for g in out:
+    print(f"{g['id']} {len(g['members']):2} scenes {len(g['stories'])} stories  stage {g['stage']:6}  {g['name']}")
+src = collections.Counter(o['source'].split(':')[0] for g in out for o in g['options'])
+print('option sources:', dict(src), '| scene options citing a scene outside their group:',
+      sum(o['in_group'] is False for g in out for o in g['options']))