PR Changes

Author: tkachyna

src/sec_certs/dataset/cc.py

@@ -5,7 +5,7 @@
 from collections.abc import Iterator
 from datetime import datetime
 from pathlib import Path
-from typing import ClassVar, cast
+from typing import TYPE_CHECKING, ClassVar, cast
 
 import numpy as np
 import pandas as pd
@@ -39,6 +39,9 @@
 from sec_certs.utils import helpers, sanitization
 from sec_certs.utils.profiling import staged
 
+if TYPE_CHECKING:
+    from sec_certs.converter import PDFConverter
+
 
 class CCDataset(Dataset[CCCertificate], ComplexSerializableType):
     """
@@ -151,10 +154,6 @@ def to_pandas(self) -> pd.DataFrame:
 
         return df
 
-    @property
-    def dataset_name(self) -> str:
-        return "CC"
-
     @property
     @only_backed(throw=False)
     def reports_dir(self) -> Path:

src/sec_certs/dataset/cc_eucc_common.py

@@ -17,8 +17,6 @@
 from collections.abc import Callable
 from typing import TYPE_CHECKING
 
-from sec_certs.configuration import config
-from sec_certs.converter import PDFConverter
 from sec_certs.dataset.auxiliary_dataset_handling import (
     CCSchemeDatasetHandler,
     CPEDatasetHandler,
@@ -59,6 +57,8 @@
 from sec_certs.utils.profiling import staged
 
 if TYPE_CHECKING:
+    from sec_certs.configuration import config
+    from sec_certs.converter import PDFConverter
     from sec_certs.dataset.cc import CCDataset
     from sec_certs.dataset.eucc import EUCCDataset
 
@@ -82,7 +82,7 @@ def download_pdfs(
 
     if not fresh:
         logger.info(
-            f"Downloading {len(certs_to_process)} PDFs of {obj.dataset_name} {doc_type.long}s for which previous download failed."
+            f"Downloading {len(certs_to_process)} PDFs of {obj.name} {doc_type.long}s for which previous download failed."
         )
 
     download_pdf_funcs = {
@@ -94,7 +94,7 @@ def download_pdfs(
     cert_processing.process_parallel(
         download_pdf_funcs[doc_type],
         certs_to_process,
-        progress_bar_desc=f"Downloading PDFs of {obj.dataset_name} {doc_type.long}s",
+        progress_bar_desc=f"Downloading PDFs of {obj.name} {doc_type.long}s",
     )
 
 
@@ -136,7 +136,7 @@ def convert_pdfs(
 
     if not fresh:
         logger.info(
-            f"Converting {len(certs_to_process)} PDFs of {obj.dataset_name} {doc_type.long}s for which previous conversion failed."
+            f"Converting {len(certs_to_process)} PDFs of {obj.name} {doc_type.long}s for which previous conversion failed."
         )
 
     convert_pdf_funcs = {
@@ -152,7 +152,7 @@ def convert_pdfs(
         certs_to_process,
         config.pdf_conversion_workers,
         config.pdf_conversion_max_chunk_size,
-        progress_bar_desc=f"Converting PDFs of {obj.dataset_name} {doc_type.long}s",
+        progress_bar_desc=f"Converting PDFs of {obj.name} {doc_type.long}s",
     )
 
     obj.update_with_certs(processed_certs)
@@ -189,7 +189,7 @@ def extract_generic(obj: CCDataset | EUCCDataset, doc_type: DocType, worker_func
         worker_func,
         certs_to_process,
         use_threading=False,
-        progress_bar_desc=f"Extracting {obj.dataset_name} {doc_type.long} {worker_func.__name__.split('_')[-1]}",
+        progress_bar_desc=f"Extracting {obj.name} {doc_type.long} {worker_func.__name__.split('_')[-1]}",
     )
     obj.update_with_certs(processed)
 

src/sec_certs/dataset/eucc.py

@@ -138,10 +138,6 @@ def __init__(
                 ),
             }
 
-    @property
-    def dataset_name(self) -> str:
-        return "EUCC"
-
     @property
     @only_backed(throw=False)
     def reports_dir(self) -> Path: