Chiusura fase di ristrutturazione e modularizzazione del workflow per favorire sviluppo modulare

harness/tht/vendor/thoth_lsh.py

@@ -4,11 +4,12 @@
 """Core LSH (MinHash) per la ricerca di valori simili nei campi del database."""
 
 import logging
-from typing import Dict, List, Tuple
 
 from datasketch import MinHash, MinHashLSH
 from tqdm import tqdm
 
+logger = logging.getLogger(__name__)
+
 
 def create_minhash(signature_size: int, string: str, n_gram: int) -> MinHash:
     m = MinHash(num_perm=signature_size)
@@ -33,7 +34,7 @@ NAME_LIKE_TOKENS: tuple[str, ...] = (
 
 def skip_column(
     column_name: str,
-    column_values: List[str],
+    column_values: list[str],
     max_total_chars: int = 50000,
     max_avg_length: int = 20,
     name_tokens: tuple[str, ...] = NAME_LIKE_TOKENS,
@@ -51,20 +52,20 @@ def jaccard_similarity(m1: MinHash, m2: MinHash) -> float:
 
 
 def create_lsh_index(
-    unique_values: Dict[str, Dict[str, List[str]]],
+    unique_values: dict[str, dict[str, list[str]]],
     signature_size: int,
     n_gram: int,
     threshold: float,
     verbose: bool = True,
-) -> Tuple[MinHashLSH, Dict[str, Tuple[MinHash, str, str, str]]]:
+) -> tuple[MinHashLSH, dict[str, tuple[MinHash, str, str, str]]]:
     lsh = MinHashLSH(threshold=threshold, num_perm=signature_size)
-    minhashes: Dict[str, Tuple[MinHash, str, str, str]] = {}
+    minhashes: dict[str, tuple[MinHash, str, str, str]] = {}
     total = sum(
         len(column_values)
         for table_values in unique_values.values()
         for column_values in table_values.values()
     )
-    logging.info("Total unique values: %s", total)
+    logger.info("Total unique values: %s", total)
     progress_bar = tqdm(total=total, desc="Creating LSH") if verbose else None
 
     for table_name, table_values in unique_values.items():