davide
fe0ecc24ad
- chunker: estrai _flush_chunk() con estensione al confine di frase (max 120%) - verify: rileva chunk matematici incompleti come warning, gestisci hash hex e URL - conversione: esporta structure_profile.json nell'output dir
444 lines
14 KiB
Python
444 lines
14 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
Chunking adattivo
|
||
|
||
Divide il Markdown revisionato in chunk semantici pronti per la
|
||
vettorizzazione. La strategia dipende dal profilo strutturale del documento.
|
||
|
||
Input: conversione/<stem>/clean.md + conversione/<stem>/structure_profile.json
|
||
Output: chunks/<stem>/chunks.json
|
||
|
||
Uso:
|
||
python chunks/chunker.py # tutti i documenti in conversione/
|
||
python chunks/chunker.py --stem documento # un solo documento
|
||
python chunks/chunker.py --stem documento --force
|
||
"""
|
||
|
||
import argparse
|
||
import json
|
||
import re
|
||
import sys
|
||
from pathlib import Path
|
||
|
||
|
||
# ─── Parametri ────────────────────────────────────────────────────────────────
|
||
|
||
MIN_CHARS = 200 # sotto questa soglia → accorpa al chunk successivo
|
||
MAX_CHARS = 800 # sopra questa soglia → spezza su frasi
|
||
OVERLAP_S = 2 # frasi di overlap tra sotto-chunk dello stesso boundary
|
||
|
||
|
||
# ─── Utilità ──────────────────────────────────────────────────────────────────
|
||
|
||
def split_sentences(text: str) -> list[str]:
|
||
parts = re.split(r'(?<=[.!?»])\s+(?=[A-ZÀÈÉÌÒÙA-Z\"])', text.strip())
|
||
if len(parts) <= 1:
|
||
parts = re.split(r'(?<=[.!?»])\s+', text.strip())
|
||
return [p.strip() for p in parts if p.strip()]
|
||
|
||
|
||
def slugify(s: str, max_len: int = 60) -> str:
|
||
s = s.lower()
|
||
s = re.sub(r'[^\w\s-]', '', s)
|
||
s = re.sub(r'[\s_-]+', '_', s).strip('_')
|
||
return s[:max_len] if s else "section"
|
||
|
||
|
||
_SENT_BOUNDARY = re.compile(r"[.!?»)\]'\u2019\"\u201c\u201d/:|\u2026]$")
|
||
|
||
|
||
def _flush_chunk(
|
||
current: list[str],
|
||
sentences: list[str],
|
||
i: int,
|
||
prefix: str,
|
||
sezione: str,
|
||
titolo: str,
|
||
sub_index: int,
|
||
max_chars: int,
|
||
) -> tuple[dict, list[str], int, int]:
|
||
"""Emette un chunk, estendendo fino a un confine di frase (max +20%)."""
|
||
hard_limit = int(max_chars * 1.2)
|
||
current_len = sum(len(s) + 1 for s in current)
|
||
while i < len(sentences) and not _SENT_BOUNDARY.search(" ".join(current)):
|
||
nxt = sentences[i]
|
||
if current_len + len(nxt) + 1 > hard_limit:
|
||
break
|
||
current.append(nxt)
|
||
current_len += len(nxt) + 1
|
||
i += 1
|
||
chunk_text = prefix + " ".join(current)
|
||
chunk = {
|
||
"chunk_id": f"{slugify(sezione)}__{slugify(titolo)}__s{sub_index}",
|
||
"text": chunk_text,
|
||
"sezione": sezione,
|
||
"titolo": titolo,
|
||
"sub_index": sub_index,
|
||
"n_chars": len(chunk_text),
|
||
}
|
||
return chunk, current, i, sub_index + 1
|
||
|
||
|
||
def make_sub_chunks(
|
||
body: str,
|
||
prefix: str,
|
||
sezione: str,
|
||
titolo: str,
|
||
max_chars: int,
|
||
overlap_s: int,
|
||
) -> list[dict]:
|
||
sentences = split_sentences(body)
|
||
if not sentences:
|
||
return []
|
||
|
||
chunks = []
|
||
current: list[str] = []
|
||
current_len = 0
|
||
sub_index = 0
|
||
|
||
i = 0
|
||
while i < len(sentences):
|
||
sent = sentences[i]
|
||
if not current or current_len + len(sent) + 1 <= max_chars:
|
||
current.append(sent)
|
||
current_len += len(sent) + (1 if len(current) > 1 else 0)
|
||
i += 1
|
||
else:
|
||
chunk, current, i, sub_index = _flush_chunk(
|
||
current, sentences, i, prefix, sezione, titolo, sub_index, max_chars
|
||
)
|
||
chunks.append(chunk)
|
||
overlap = current[-overlap_s:] if overlap_s and len(current) > overlap_s else []
|
||
current = overlap[:]
|
||
current_len = sum(len(s) + 1 for s in current)
|
||
|
||
if current:
|
||
chunk_text = prefix + " ".join(current)
|
||
chunks.append({
|
||
"chunk_id": f"{slugify(sezione)}__{slugify(titolo)}__s{sub_index}",
|
||
"text": chunk_text,
|
||
"sezione": sezione,
|
||
"titolo": titolo,
|
||
"sub_index": sub_index,
|
||
"n_chars": len(chunk_text),
|
||
})
|
||
|
||
return chunks
|
||
|
||
|
||
# ─── Parser Markdown ──────────────────────────────────────────────────────────
|
||
|
||
def parse_h3_sections(text: str) -> list[dict]:
|
||
sections = []
|
||
current_h2 = ""
|
||
current_h3 = ""
|
||
current_body_lines: list[str] = []
|
||
|
||
def flush():
|
||
body = "\n".join(current_body_lines).strip()
|
||
if body:
|
||
sections.append({
|
||
"sezione": current_h2,
|
||
"titolo": current_h3,
|
||
"body": body,
|
||
})
|
||
|
||
for line in text.splitlines():
|
||
if re.match(r"^# ", line):
|
||
flush()
|
||
current_h2 = line[2:].strip()
|
||
current_h3 = ""
|
||
current_body_lines = []
|
||
elif re.match(r"^## ", line):
|
||
flush()
|
||
current_h2 = line[3:].strip()
|
||
current_h3 = ""
|
||
current_body_lines = []
|
||
elif re.match(r"^### ", line):
|
||
flush()
|
||
current_h3 = line[4:].strip()
|
||
current_body_lines = []
|
||
else:
|
||
current_body_lines.append(line)
|
||
|
||
flush()
|
||
return sections
|
||
|
||
|
||
def parse_h2_sections(text: str) -> list[dict]:
|
||
sections = []
|
||
current_h2 = ""
|
||
current_body_lines: list[str] = []
|
||
|
||
def flush():
|
||
body = "\n".join(current_body_lines).strip()
|
||
if body:
|
||
sections.append({"sezione": current_h2, "body": body})
|
||
|
||
for line in text.splitlines():
|
||
if re.match(r"^## ", line):
|
||
flush()
|
||
current_h2 = line[3:].strip()
|
||
current_body_lines = []
|
||
elif re.match(r"^# ", line):
|
||
flush()
|
||
current_h2 = line[2:].strip()
|
||
current_body_lines = []
|
||
else:
|
||
current_body_lines.append(line)
|
||
|
||
flush()
|
||
return sections
|
||
|
||
|
||
# ─── Strategie di chunking ────────────────────────────────────────────────────
|
||
|
||
def chunk_h3_aware(text: str, stem: str) -> list[dict]:
|
||
sections = parse_h3_sections(text)
|
||
|
||
merged: list[dict] = []
|
||
pending: dict | None = None
|
||
|
||
for sec in sections:
|
||
if pending is None:
|
||
pending = dict(sec)
|
||
continue
|
||
|
||
if (pending["sezione"] == sec["sezione"]
|
||
and len(pending["body"]) < MIN_CHARS):
|
||
sep_title = " / ".join(filter(None, [pending["titolo"], sec["titolo"]]))
|
||
pending = {
|
||
"sezione": pending["sezione"],
|
||
"titolo": sep_title or pending["titolo"],
|
||
"body": pending["body"] + "\n\n" + sec["body"],
|
||
}
|
||
else:
|
||
merged.append(pending)
|
||
pending = dict(sec)
|
||
|
||
if pending:
|
||
merged.append(pending)
|
||
|
||
chunks = []
|
||
for sec in merged:
|
||
sezione = sec["sezione"] or stem
|
||
titolo = sec["titolo"] or ""
|
||
body = sec["body"]
|
||
|
||
prefix = f"[{sezione} > {titolo}]\n" if titolo else f"[{sezione}]\n"
|
||
sub = make_sub_chunks(body, prefix, sezione, titolo, MAX_CHARS, OVERLAP_S)
|
||
chunks.extend(sub)
|
||
|
||
return chunks
|
||
|
||
|
||
def chunk_h2_paragraph_split(text: str, stem: str) -> list[dict]:
|
||
sections = parse_h2_sections(text)
|
||
chunks = []
|
||
|
||
for sec in sections:
|
||
sezione = sec["sezione"] or stem
|
||
body = sec["body"]
|
||
prefix = f"[{sezione}]\n"
|
||
|
||
paragraphs = [
|
||
p.strip()
|
||
for p in re.split(r"\n{2,}", body)
|
||
if p.strip() and not re.match(r"^#+\s", p.strip())
|
||
]
|
||
|
||
merged_pars: list[str] = []
|
||
pending = ""
|
||
for par in paragraphs:
|
||
if pending and len(pending) < MIN_CHARS:
|
||
pending = pending + "\n\n" + par
|
||
else:
|
||
if pending:
|
||
merged_pars.append(pending)
|
||
pending = par
|
||
if pending:
|
||
merged_pars.append(pending)
|
||
|
||
for idx, par in enumerate(merged_pars):
|
||
sub = make_sub_chunks(par, prefix, sezione, f"par{idx}", MAX_CHARS, OVERLAP_S)
|
||
for c in sub:
|
||
c["chunk_id"] = f"{slugify(sezione)}__p{idx}__s{c['sub_index']}"
|
||
chunks.extend(sub)
|
||
|
||
return chunks
|
||
|
||
|
||
def chunk_paragraph(text: str, stem: str) -> list[dict]:
|
||
paragraphs = [
|
||
p.strip()
|
||
for p in re.split(r"\n{2,}", text)
|
||
if p.strip() and not re.match(r"^#+\s", p.strip())
|
||
]
|
||
prefix = f"[Documento: {stem}]\n"
|
||
|
||
merged: list[str] = []
|
||
pending = ""
|
||
for par in paragraphs:
|
||
if pending and len(pending) < MIN_CHARS:
|
||
pending = pending + "\n\n" + par
|
||
else:
|
||
if pending:
|
||
merged.append(pending)
|
||
pending = par
|
||
if pending:
|
||
merged.append(pending)
|
||
|
||
chunks = []
|
||
for idx, par in enumerate(merged):
|
||
sub = make_sub_chunks(par, prefix, stem, f"par{idx}", MAX_CHARS, OVERLAP_S)
|
||
for c in sub:
|
||
c["chunk_id"] = f"para__{idx}__s{c['sub_index']}"
|
||
chunks.extend(sub)
|
||
|
||
return chunks
|
||
|
||
|
||
def chunk_sliding_window(text: str, stem: str) -> list[dict]:
|
||
sentences = split_sentences(text)
|
||
prefix = f"[Documento: {stem}]\n"
|
||
|
||
chunks = []
|
||
i = 0
|
||
win_idx = 0
|
||
|
||
while i < len(sentences):
|
||
window: list[str] = []
|
||
cur_len = 0
|
||
|
||
j = i
|
||
while j < len(sentences):
|
||
s = sentences[j]
|
||
if window and cur_len + len(s) + 1 > MAX_CHARS:
|
||
break
|
||
window.append(s)
|
||
cur_len += len(s) + (1 if len(window) > 1 else 0)
|
||
j += 1
|
||
|
||
if not window:
|
||
window = [sentences[i]]
|
||
j = i + 1
|
||
|
||
chunk_text = prefix + " ".join(window)
|
||
chunks.append({
|
||
"chunk_id": f"win__{win_idx}",
|
||
"text": chunk_text,
|
||
"sezione": stem,
|
||
"titolo": f"finestra {win_idx}",
|
||
"sub_index": win_idx,
|
||
"n_chars": len(chunk_text),
|
||
})
|
||
win_idx += 1
|
||
i += max(1, len(window) - OVERLAP_S)
|
||
|
||
return chunks
|
||
|
||
|
||
# ─── Dispatcher ───────────────────────────────────────────────────────────────
|
||
|
||
_STRATEGIES: dict[str, callable] = {
|
||
"h3_aware": chunk_h3_aware,
|
||
"h2_paragraph_split": chunk_h2_paragraph_split,
|
||
"paragraph": chunk_paragraph,
|
||
"sliding_window": chunk_sliding_window,
|
||
}
|
||
|
||
|
||
def chunk_document(clean_md: Path, profile: dict, stem: str) -> list[dict]:
|
||
text = clean_md.read_text(encoding="utf-8")
|
||
strategia = profile.get("strategia_chunking", "paragraph")
|
||
fn = _STRATEGIES.get(strategia, chunk_paragraph)
|
||
return fn(text, stem)
|
||
|
||
|
||
# ─── Per-document processing ──────────────────────────────────────────────────
|
||
|
||
def process_stem(stem: str, project_root: Path, force: bool) -> bool:
|
||
conv_dir = project_root / "conversione" / stem
|
||
out_dir = project_root / "chunks" / stem
|
||
clean_md = conv_dir / "clean.md"
|
||
profile_path = conv_dir / "structure_profile.json"
|
||
out_file = out_dir / "chunks.json"
|
||
|
||
print(f"\nDocumento: {stem}")
|
||
|
||
if not clean_md.exists():
|
||
print(f" ✗ clean.md non trovato in conversione/{stem}/ — skip")
|
||
return False
|
||
if not profile_path.exists():
|
||
print(f" ✗ structure_profile.json non trovato in conversione/{stem}/ — skip")
|
||
return False
|
||
|
||
if out_file.exists() and not force:
|
||
print(f" ⚠️ chunks.json già presente — skip")
|
||
print(f" (usa --force per rieseguire)")
|
||
return True
|
||
|
||
profile = json.loads(profile_path.read_text(encoding="utf-8"))
|
||
strategia = profile.get("strategia_chunking", "paragraph")
|
||
print(f" Strategia: {strategia}")
|
||
|
||
chunks = chunk_document(clean_md, profile, stem)
|
||
|
||
if not chunks:
|
||
print(f" ✗ Nessun chunk generato — controlla clean.md")
|
||
return False
|
||
|
||
out_dir.mkdir(parents=True, exist_ok=True)
|
||
out_file.write_text(
|
||
json.dumps(chunks, ensure_ascii=False, indent=2), encoding="utf-8"
|
||
)
|
||
|
||
lengths = [c["n_chars"] for c in chunks]
|
||
min_c = min(lengths)
|
||
max_c = max(lengths)
|
||
avg_c = int(sum(lengths) / len(lengths))
|
||
short = sum(1 for l in lengths if l < MIN_CHARS)
|
||
long_ = sum(1 for l in lengths if l > MAX_CHARS * 1.5)
|
||
|
||
print(f" Chunk totali: {len(chunks)}")
|
||
print(f" Min: {min_c} char Max: {max_c} char Media: {avg_c} char")
|
||
if short:
|
||
print(f" ⚠️ {short} chunk sotto MIN_CHARS ({MIN_CHARS})")
|
||
if long_:
|
||
print(f" ⚠️ {long_} chunk sopra MAX_CHARS×1.5 ({int(MAX_CHARS * 1.5)})")
|
||
print(f" ✅ chunks.json salvato in chunks/{stem}/")
|
||
return True
|
||
|
||
|
||
# ─── Entry point ─────────────────────────────────────────────────────────────
|
||
|
||
if __name__ == "__main__":
|
||
project_root = Path(__file__).parent.parent
|
||
|
||
parser = argparse.ArgumentParser(description="Chunking adattivo")
|
||
parser.add_argument("--stem", help="Nome del documento (sottocartella di conversione/)")
|
||
parser.add_argument("--force", action="store_true", help="Riesegui anche se già presente")
|
||
args = parser.parse_args()
|
||
|
||
if args.stem:
|
||
stems = [args.stem]
|
||
else:
|
||
conv_dir = project_root / "conversione"
|
||
if not conv_dir.exists():
|
||
print(f"Errore: cartella conversione/ non trovata in {project_root}")
|
||
sys.exit(1)
|
||
stems = sorted(
|
||
p.name for p in conv_dir.iterdir()
|
||
if p.is_dir() and (p / "clean.md").exists()
|
||
)
|
||
if not stems:
|
||
print(f"Errore: nessun documento trovato in conversione/")
|
||
sys.exit(1)
|
||
|
||
results = [process_stem(s, project_root, args.force) for s in stems]
|
||
|
||
ok = sum(results)
|
||
total = len(results)
|
||
print(f"\n{'✅' if all(results) else '⚠️ '} {ok}/{total} documenti processati")
|
||
sys.exit(0 if all(results) else 1)
|