Update src/codex_extractor.py

src/codex_extractor.py

@@ -114,15 +114,19 @@ except Exception:
 
 try:
     import nltk
+    import socket as _socket
     _NLTK_DATA = ["punkt", "punkt_tab", "averaged_perceptron_tagger", "cmudict", "stopwords"]
     for _pkg in _NLTK_DATA:
         try:
             nltk.data.find(f"tokenizers/{_pkg}" if "punkt" in _pkg else f"corpora/{_pkg}")
         except LookupError:
             try:
+                _old_timeout = _socket.getdefaulttimeout()
+                _socket.setdefaulttimeout(5)
                 nltk.download(_pkg, quiet=True)
+                _socket.setdefaulttimeout(_old_timeout)
             except Exception:
-                pass
+                _socket.setdefaulttimeout(_old_timeout)
     from nltk.tokenize import sent_tokenize, word_tokenize
     from nltk.corpus import cmudict as _cmudict
     CMU_DICT = _cmudict.dict()
@@ -1909,4 +1913,4 @@ if __name__ == "__main__":
         debug_output_dir="/tmp/codex_debug",
     )
     print(format_fingerprint_report(fp))
-    print("\nDebug artefacts written to:", fp.get("Debug_Artefacts", {}))
+    print("\nDebug artefacts written to:", fp.get("Debug_Artefacts", {}))