Externalize dictionaries and add anonymization review corpus

tools/validate_full_corpus.py

@@ -17,6 +17,7 @@ import re
 
 sys.path.insert(0, str(Path(__file__).parent.parent))
 
+from config_defaults import RUNTIME_DICTIONARIES_CONFIG_PATH
 from anonymizer_core_refactored_onnx import process_pdf
 
 def validate_full_corpus():
@@ -70,7 +71,7 @@ def validate_full_corpus():
                 output_dir,
                 make_vector_redaction=False,
                 also_make_raster_burn=True,
-                config_path=Path("config/dictionnaires.yml")
+                config_path=RUNTIME_DICTIONARIES_CONFIG_PATH
             )
             doc_time = time.time() - doc_start