feat(chunks): sentence-boundary flush, math incomplete detection, structure profile export

- 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

chunks/chunker.py

@@ -44,6 +44,41 @@ def slugify(s: str, max_len: int = 60) -> str:
     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,
@@ -69,16 +104,10 @@ def make_sub_chunks(
             current_len += len(sent) + (1 if len(current) > 1 else 0)
             i += 1
         else:
-            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),
-            })
-            sub_index += 1
+            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)