feat(chunks): aggiungi pipeline chunking consolidata

Nuova cartella chunks/ con chunker.py (step 5), verify_chunks.py e
fix_chunks.py (step 6). Tutto l'I/O va in chunks/<stem>/ invece di
step-5/ e step-6/ separati. Input: conversione/<stem>/clean.md
This commit is contained in:
2026-04-20 11:36:18 +02:00
parent 5215f53ad0
commit 4c0e0db2a5
3 changed files with 999 additions and 0 deletions
+283
View File
@@ -0,0 +1,283 @@
#!/usr/bin/env python3
"""
Fix chunk
Applica correzioni dirette su chunks/<stem>/chunks.json basandosi sul
report.json prodotto da verify_chunks.py. Non tocca clean.md.
Fixes applicati:
empty → rimuove il chunk
incomplete → fonde con il chunk successivo (la frase continua)
no_prefix → aggiunge prefisso [sezione > titolo] se mancante
too_short → fonde con il chunk adiacente nello stesso sezione
too_long → spezza all'ultimo confine di paragrafo/frase entro MAX_CHARS
Input: chunks/<stem>/chunks.json + chunks/<stem>/report.json
Output: chunks/<stem>/chunks.json (sovrascrive)
Uso:
python chunks/fix_chunks.py --stem documento
python chunks/fix_chunks.py --stem documento --dry-run
"""
import argparse
import json
import re
import sys
from pathlib import Path
MAX_CHARS = 800
PUNCT_END = re.compile(r"[.!?»)\]'\u2019\"\u201c\u201d\u2018\u2014\u2013-]$")
# ─── Helpers ──────────────────────────────────────────────────────────────────
def _prefix(chunk: dict) -> str:
sezione = chunk.get("sezione", "")
titolo = chunk.get("titolo", "")
if titolo:
return f"[{sezione} > {titolo}]"
return f"[{sezione}]"
def _strip_prefix(text: str) -> str:
text = text.lstrip()
if text.startswith("["):
end = text.find("]")
if end != -1:
return text[end + 1:].lstrip("\n")
return text
def _rebuild_text(chunk: dict, body: str) -> str:
return f"{_prefix(chunk)}\n{body}"
def _split_at_boundary(text: str, max_chars: int) -> list[str]:
if len(text) <= max_chars:
return [text]
parts = []
remaining = text
while len(remaining) > max_chars:
candidate = remaining[:max_chars]
split_pos = candidate.rfind("\n\n")
if split_pos == -1:
m = None
for m in re.finditer(r"[.!?»]\s+", candidate):
pass
split_pos = m.end() if m else None
if split_pos is None or split_pos == 0:
sp = remaining.find(" ", max_chars)
split_pos = sp if sp != -1 else len(remaining)
parts.append(remaining[:split_pos].rstrip())
remaining = remaining[split_pos:].lstrip()
if remaining:
parts.append(remaining)
return [p for p in parts if p.strip()]
# ─── Operazioni sui chunk ─────────────────────────────────────────────────────
def fix_empty(chunks: list[dict], empty_ids: set[str]) -> tuple[list[dict], int]:
before = len(chunks)
chunks = [c for c in chunks if c["chunk_id"] not in empty_ids]
return chunks, before - len(chunks)
def fix_no_prefix(chunks: list[dict], no_prefix_ids: set[str]) -> tuple[list[dict], int]:
count = 0
for c in chunks:
if c["chunk_id"] in no_prefix_ids:
body = _strip_prefix(c["text"])
c["text"] = _rebuild_text(c, body)
c["n_chars"] = len(c["text"])
count += 1
return chunks, count
def fix_incomplete_and_short(chunks: list[dict],
problem_ids: set[str]) -> tuple[list[dict], int]:
merged = 0
i = 0
result: list[dict] = []
while i < len(chunks):
c = chunks[i]
if c["chunk_id"] in problem_ids and i + 1 < len(chunks):
nxt = chunks[i + 1]
body_c = _strip_prefix(c["text"])
body_nxt = _strip_prefix(nxt["text"])
merged_body = body_c.rstrip() + "\n" + body_nxt.lstrip()
nxt["text"] = _rebuild_text(nxt, merged_body)
nxt["n_chars"] = len(nxt["text"])
merged += 1
i += 1
continue
result.append(c)
i += 1
return result, merged
def fix_too_long(chunks: list[dict],
too_long_ids: set[str],
max_chars: int) -> tuple[list[dict], int]:
result: list[dict] = []
split_count = 0
for c in chunks:
if c["chunk_id"] not in too_long_ids:
result.append(c)
continue
body = _strip_prefix(c["text"])
parts = _split_at_boundary(body, max_chars)
if len(parts) == 1:
result.append(c)
continue
base_id = re.sub(r"__s\d+$", "", c["chunk_id"])
base_sub = c.get("sub_index", 0)
for j, part in enumerate(parts):
new_chunk = dict(c)
new_chunk["sub_index"] = base_sub + j
new_chunk["chunk_id"] = f"{base_id}__s{base_sub + j}"
new_chunk["text"] = _rebuild_text(new_chunk, part)
new_chunk["n_chars"] = len(new_chunk["text"])
result.append(new_chunk)
split_count += 1
return result, split_count
def renumber_ids(chunks: list[dict]) -> list[dict]:
seen: dict[str, int] = {}
for c in chunks:
base = re.sub(r"__s\d+$", "", c["chunk_id"])
idx = seen.get(base, 0)
c["chunk_id"] = f"{base}__s{idx}"
c["sub_index"] = idx
seen[base] = idx + 1
return chunks
# ─── Core ─────────────────────────────────────────────────────────────────────
def fix_stem(stem: str, project_root: Path, max_chars: int, dry_run: bool) -> bool:
stem_dir = project_root / "chunks" / stem
chunks_path = stem_dir / "chunks.json"
report_path = stem_dir / "report.json"
if not chunks_path.exists():
print(f"✗ chunks/{stem}/chunks.json non trovato.")
print(f" Esegui prima: python chunks/chunker.py --stem {stem}")
return False
if not report_path.exists():
print(f"✗ chunks/{stem}/report.json non trovato.")
print(f" Esegui prima: python chunks/verify_chunks.py --stem {stem}")
return False
chunks: list[dict] = json.loads(chunks_path.read_text(encoding="utf-8"))
report: dict = json.loads(report_path.read_text(encoding="utf-8"))
verdict = report.get("verdict", "ok")
print(f"\nDocumento: {stem} (verdict: {verdict})")
if verdict == "ok":
print(" ✅ Nessun problema — nulla da correggere.")
return True
empty_ids = {e["chunk_id"] for e in report.get("blockers", {}).get("empty", [])}
no_prefix_ids = {e["chunk_id"] for e in report.get("blockers", {}).get("no_prefix", [])}
incomplete_ids = {e["chunk_id"] for e in report.get("blockers", {}).get("incomplete", [])}
too_short_ids = {e["chunk_id"] for e in report.get("warnings", {}).get("too_short", [])}
too_long_ids = {e["chunk_id"] for e in report.get("warnings", {}).get("too_long", [])}
ops: list[str] = []
if empty_ids:
ops.append(f" 🗑 rimuovi {len(empty_ids)} chunk vuoti")
if no_prefix_ids:
ops.append(f" 🔧 aggiungi prefisso a {len(no_prefix_ids)} chunk")
if incomplete_ids:
ops.append(f" 🔗 fondi {len(incomplete_ids)} chunk incompleti col successivo")
if too_short_ids:
ops.append(f" 🔗 fondi {len(too_short_ids)} chunk troppo corti col successivo")
if too_long_ids:
ops.append(f" ✂️ spezza {len(too_long_ids)} chunk troppo lunghi")
if not ops:
print(" ✅ Nessuna correzione necessaria.")
return True
print("\n Operazioni pianificate:")
for op in ops:
print(op)
if dry_run:
print("\n [dry-run] Nessuna modifica applicata.")
return True
n_before = len(chunks)
if empty_ids:
chunks, n = fix_empty(chunks, empty_ids)
print(f"\n 🗑 Rimossi {n} chunk vuoti.")
if no_prefix_ids:
chunks, n = fix_no_prefix(chunks, no_prefix_ids)
print(f" 🔧 Aggiunto prefisso a {n} chunk.")
merge_ids = incomplete_ids | too_short_ids
if merge_ids:
chunks, n = fix_incomplete_and_short(chunks, merge_ids)
print(f" 🔗 Fusi {n} chunk (incompleti + corti).")
if too_long_ids:
chunks, n = fix_too_long(chunks, too_long_ids, max_chars)
print(f" ✂️ Spezzati {n} chunk lunghi.")
chunks = renumber_ids(chunks)
n_after = len(chunks)
print(f"\n Totale chunk: {n_before}{n_after}")
chunks_path.write_text(
json.dumps(chunks, ensure_ascii=False, indent=2), encoding="utf-8"
)
print(f" ✅ Salvato: chunks/{stem}/chunks.json")
print(f"\n Riesegui la verifica:")
print(f" python chunks/verify_chunks.py --stem {stem}")
return True
# ─── Entry point ──────────────────────────────────────────────────────────────
if __name__ == "__main__":
project_root = Path(__file__).parent.parent
parser = argparse.ArgumentParser(description="Fix chunk")
parser.add_argument("--stem", required=True, help="Nome del documento (sottocartella di chunks/)")
parser.add_argument(
"--max", type=int, default=MAX_CHARS,
help=f"Soglia massima caratteri per lo split (default: {MAX_CHARS})"
)
parser.add_argument(
"--dry-run", action="store_true",
help="Mostra le operazioni pianificate senza applicarle"
)
args = parser.parse_args()
ok = fix_stem(args.stem, project_root, args.max, args.dry_run)
sys.exit(0 if ok else 1)