Revert get_page_number arg back to pathlib.Path

Author: rlskoeser

src/corppa/ocr/collate_txt.py

@@ -55,7 +55,7 @@ def collate_txt(
         txt_data = {}
         for filename in files:
             with (input_dir / filename).open(encoding="utf-8") as txtfile:
-                txt_data[get_page_number(filename.name)] = txtfile.read()
+                txt_data[get_page_number(filename)] = txtfile.read()
 
         # ensure the parent directory exists
         output_file.parent.mkdir(exist_ok=True)

src/corppa/utils/path_utils.py

@@ -118,7 +118,7 @@ def get_image_relpath(work_id, page_num):
         raise ValueError(f"Unsupported source '{source}'")
 
 
-def get_page_number(filename: str) -> str:
+def get_page_number(pagefile: pathlib.Path) -> str:
     """Extract and return the page number from the filename for page-level
     content (e.g., image or text). Returns the page number as a string
     with leading zeros. (Note: logic is currently
@@ -127,7 +127,7 @@ def get_page_number(filename: str) -> str:
     # which look like CW0112029406_00180.txt
 
     # split the file base/stem name by _ and take the last part
-    source_id, pagenum = os.path.splitext(filename)[0].split("_", 1)
+    source_id, pagenum = pagefile.stem.split("_", 1)
     if get_ppa_source(source_id) != "Gale":
         raise NotImplementedError
     # return the number as a string; strip extra trailing zero

test/test_utils/test_path_utils.py

@@ -107,10 +107,10 @@ def test_get_volume_id():
 
 
 def test_page_number():
-    assert get_page_number("CW0112029406_00180.txt") == "0018"
+    assert get_page_number(pathlib.Path("CW0112029406_00180.txt")) == "0018"
     # raise not implemented error if source id is not Gale/ECCO
     with pytest.raises(NotImplementedError):
-        assert get_page_number("uva.x002075945_00180.txt") == "0018"
+        assert get_page_number(pathlib.Path("uva.x002075945_00180.txt")) == "0018"
 
 
 @patch("corppa.utils.path_utils.get_volume_id", return_value="vol_id")