Get rid of RETURNCODE_OK. This is not C99.

3 files changed, 15 insertions, 27 deletions

diff --git a/src/sec_certs/utils/extract.py b/src/sec_certs/utils/extract.py
index 6af7f4cc..35361e94 100644
--- a/src/sec_certs/utils/extract.py
+++ b/src/sec_certs/utils/extract.py
@@ -267,19 +267,9 @@ def search_only_headers_anssi(filepath: Path):  # noqa: C901
         relative_filepath = "/".join(str(filepath).split("/")[-4:])
         error_msg = f"Failed to parse ANSSI frontpage headers from {relative_filepath}; {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg) from e
 
-    # if True:
-    #     print('# hits for rule')
-    #     sorted_rules = sorted(num_rules_hits.items(),
-    #                           key=operator.itemgetter(1), reverse=True)
-    #     used_rules = []
-    #     for rule in sorted_rules:
-    #         print('{:4d} : {}'.format(rule[1], rule[0]))
-    #         if rule[1] > 0:
-    #             used_rules.append(rule[0])
-
-    return constants.RETURNCODE_OK, items_found
+    return items_found
 
 
 def search_only_headers_bsi(filepath: Path):  # noqa: C901
@@ -376,9 +366,9 @@ def search_only_headers_bsi(filepath: Path):  # noqa: C901
         relative_filepath = "/".join(str(filepath).split("/")[-4:])
         error_msg = f"Failed to parse BSI headers from frontpage: {relative_filepath}; {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg) from e
 
-    return constants.RETURNCODE_OK, items_found
+    return items_found
 
 
 def search_only_headers_nscib(filepath: Path):  # noqa: C901
@@ -456,9 +446,9 @@ def search_only_headers_nscib(filepath: Path):  # noqa: C901
     except Exception as e:
         error_msg = f"Failed to parse NSCIB headers from frontpage: {filepath}; {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg) from e
 
-    return constants.RETURNCODE_OK, items_found
+    return items_found
 
 
 def search_only_headers_niap(filepath: Path):
@@ -507,9 +497,9 @@ def search_only_headers_niap(filepath: Path):
     except Exception as e:
         error_msg = f"Failed to parse NIAP headers from frontpage: {filepath}; {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg) from e
 
-    return constants.RETURNCODE_OK, items_found
+    return items_found
 
 
 def search_only_headers_canada(filepath: Path):  # noqa: C901
@@ -580,9 +570,9 @@ def search_only_headers_canada(filepath: Path):  # noqa: C901
     except Exception as e:
         error_msg = f"Failed to parse Canada headers from frontpage: {filepath}; {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg) from e
 
-    return constants.RETURNCODE_OK, items_found
+    return items_found
 
 
 def flatten_matches(dct: dict) -> dict:
diff --git a/src/sec_certs/utils/helpers.py b/src/sec_certs/utils/helpers.py
index 63de6fd9..4c3ab43b 100644
--- a/src/sec_certs/utils/helpers.py
+++ b/src/sec_certs/utils/helpers.py
@@ -142,13 +142,12 @@ def download_file(  # noqa: C901
                     if show_progress_bar:
                         pbar.update(len(data))
 
-            return r.status_code
+        return r.status_code
     except requests.exceptions.Timeout:
         return requests.codes.timeout
     except Exception as e:
         logger.error(f"Failed to download from {url}; {e}")
         return constants.RETURNCODE_NOK
-    return constants.RETURNCODE_NOK
 
 
 def download_parallel(
diff --git a/src/sec_certs/utils/pdf.py b/src/sec_certs/utils/pdf.py
index 3195e67e..39046717 100644
--- a/src/sec_certs/utils/pdf.py
+++ b/src/sec_certs/utils/pdf.py
@@ -13,7 +13,6 @@ import pikepdf
 import pytesseract
 from PIL import Image
 
-from sec_certs import constants
 from sec_certs.constants import (
     GARBAGE_ALPHA_CHARS_THRESHOLD,
     GARBAGE_AVG_LLEN_THRESHOLD,
@@ -151,7 +150,7 @@ def parse_pdf_date(dateval: bytes | None) -> datetime | None:
         return None
 
 
-def extract_pdf_metadata(filepath: Path) -> tuple[str, dict[str, Any] | None]:  # noqa: C901
+def extract_pdf_metadata(filepath: Path) -> dict[str, Any]:  # noqa: C901
     """
     Extract PDF metadata, such as the number of pages, author, title, etc.
 
@@ -237,9 +236,9 @@ def extract_pdf_metadata(filepath: Path) -> tuple[str, dict[str, Any] | None]:
         relative_filepath = "/".join(str(filepath).split("/")[-4:])
         error_msg = f"Failed to read metadata of {relative_filepath}, error: {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg)
 
-    return constants.RETURNCODE_OK, metadata
+    return metadata
 
 
 def text_is_garbage(text: str) -> bool:
@@ -274,7 +273,7 @@ def text_is_garbage(text: str) -> bool:
     # If the average length of a line is small, this is garbage.
     if avg_line_len < GARBAGE_AVG_LLEN_THRESHOLD:
         return True
-    # If there a small amount of lines that have more than one character at every second character, this is garbage.
+    # If there is a small amount of lines that have more than one character at every second character, this is garbage.
     # This detects the ANSSI spacing issues.
     if every_second < GARBAGE_EVERY_SECOND_CHAR_THRESHOLD:
         return True