ruff enforce pathlib

3 files changed, 26 insertions, 22 deletions

diff --git a/pyproject.toml b/pyproject.toml
index 5b17dfc7..2e4e0c10 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -100,6 +100,7 @@
     "C90", # mccabe
     "UP",  # pyupgrade
     "PL",  # pylint
+    "PTH", # enforce pathlib usage
   ]
   ignore = [
     "E501",    # line-length, should be handled by black
diff --git a/src/sec_certs/dataset/fips.py b/src/sec_certs/dataset/fips.py
index f6292dca..14bcfcf1 100644
--- a/src/sec_certs/dataset/fips.py
+++ b/src/sec_certs/dataset/fips.py
@@ -198,7 +198,7 @@ class FIPSDataset(Dataset[FIPSCertificate, FIPSAuxillaryDatasets], ComplexSerial
         )
 
     def _get_certificates_from_html(self, html_file: Path) -> list[FIPSCertificate]:
-        with open(html_file, encoding="utf-8") as handle:
+        with html_file.open("r", encoding="utf-8") as handle:
             html = BeautifulSoup(handle.read(), "html5lib")
 
         table = [x for x in html.find(id="searchResultsTable").tbody.contents if x != "\n"]
diff --git a/src/sec_certs/utils/extract.py b/src/sec_certs/utils/extract.py
index 37d79f73..82808ca9 100644
--- a/src/sec_certs/utils/extract.py
+++ b/src/sec_certs/utils/extract.py
@@ -6,7 +6,7 @@ import re
 from collections import Counter
 from enum import Enum
 from pathlib import Path
-from typing import Any, Iterator
+from typing import Any
 
 import numpy as np
 
@@ -585,11 +585,6 @@ def search_only_headers_canada(filepath: Path):  # noqa: C901
     return constants.RETURNCODE_OK, items_found
 
 
-def search_files(folder: str | Path) -> Iterator[str]:
-    for root, _, files in os.walk(str(folder)):
-        yield from [os.path.join(root, x) for x in files]
-
-
 def flatten_matches(dct: dict) -> dict:
     """
     Function to flatten dictionary of matches.
@@ -719,7 +714,7 @@ def load_text_file(
             logger.warning("UnicodeDecodeError, opening as utf8")
 
     if was_unicode_decode_error:
-        with open(file_name, encoding="utf8", errors=FILE_ERRORS_STRATEGY) as f2:
+        with Path(file_name).open("r", encoding="utf8", errors=FILE_ERRORS_STRATEGY) as f2:
             # coding failure, try line by line
             line = " "
             while line:
@@ -746,23 +741,31 @@ def load_text_file(
     return whole_text, whole_text_with_newlines, was_unicode_decode_error
 
 
-def load_cert_html_file(file_name: str) -> str:
-    with open(file_name, errors=FILE_ERRORS_STRATEGY) as f:
-        try:
-            return f.read()
-        except UnicodeDecodeError:
-            logger.warning("UnicodeDecodeError, opening as utf8")
+def rules_get_subset(desired_path: str) -> dict:
+    """
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 
-    with open(file_name, encoding="utf8", errors=FILE_ERRORS_STRATEGY) as f2:
-        try:
-            return f2.read()
-        except UnicodeDecodeError:
-            logger.error(f"Failed to read file {file_name}")
-    return ""
 
 
-def rules_get_subset(desired_path: str) -> dict:
-    """
     Recursively applies cc_certs.get(key) on tokens from desired_path,
     returns the keys of the inner-most layer.
     """