Merge branch 'master' of https://github.com/qurator-spk/mods4pandas

.editorconfig

@@ -1,2 +1,29 @@
+root = true
+
 [*]
+charset = utf-8
+end_of_line = lf
+indent_size = 4
+indent_style = space
+insert_final_newline = true
+trim_trailing_whitespace = true
 max_line_length = 120
+tab_width = 4
+
+[{*.cfg, *.ini, *.html, *.yaml, *.yml}]
+indent_size = 2
+
+[*.json]
+indent_size = 2
+insert_final_newline = true
+
+# trailing spaces in markdown indicate word wrap
+[*.md]
+trim_trailing_whitespace = false
+
+[*.py]
+multi_line_output = 3
+include_trailing_comma = True
+force_grid_wrap = 0
+use_parentheses = True
+ensure_newline_before_comments = True

.pre-commit-config.yaml

@@ -16,7 +16,7 @@ repos:
     -   id: black
 
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.13
+    rev: v0.12.7
     hooks:
     -   args:
         -   --fix
@@ -24,7 +24,7 @@ repos:
         id: ruff-check
 
 -   repo: https://gitlab.com/vojko.pribudic.foss/pre-commit-update
-    rev: v0.7.0
+    rev: v0.8.0
     hooks:
     -   id: pre-commit-update
 

README-DEV.md

@@ -16,6 +16,14 @@ To run a test with profiling:
   pytest --profile-svg -k test_page_info
   ```
 
+To directly test the CLIs using our test data, run:
+
+```
+mods4pandas src/mods4pandas/tests/data/mets-mods
+alto4pandas src/mods4pandas/tests/data/alto
+```
+
+
 # How to use pre-commit
 
 This project optionally uses [pre-commit](https://pre-commit.com) to check commits. To use it:

src/mods4pandas/mods4pandas.py

@@ -449,6 +449,8 @@ def pages_to_dict(mets, raise_errors=True) -> List[Dict]:
     def get_mets_div(*, ID):
         if ID:
             return structMap_LOGICAL.findall(f'.//mets:div[@ID="{ID}"]', ns)
+        else:
+            return []
 
     for page in div_physSequence:
         # TODO sort by ORDER?
@@ -591,6 +593,8 @@ def process(mets_files: list[str], output_file: str, output_page_info: str, mets
         with contextlib.suppress(FileNotFoundError):
             os.remove(output_page_info_sqlite3)
         con_page_info = sqlite3.connect(output_page_info_sqlite3)
+    else:
+        con_page_info = None
 
     # Process METS files
     with open(output_file + ".warnings.csv", "w") as csvfile:

src/mods4pandas/tests/test_alto.py

@@ -135,6 +135,7 @@ def test_dtypes(tmp_path):
             assert dt == edt, f"Unexpected dtype {dt} for column {c} (expected {edt})"
 
             if edt == "object":
+                assert einner_types is not None
                 inner_types = set(type(v).__name__ for v in df[c])
                 assert all(
                     it in einner_types for it in inner_types

src/mods4pandas/tests/test_mods4pandas.py

@@ -153,6 +153,7 @@ def test_originInfo_no_event_type():
     assert d == {}  # empty
 
     assert len(ws) == 1
+    assert isinstance(ws[0].message, Warning)
     assert (
         ws[0].message.args[0]
         == "Filtered {http://www.loc.gov/mods/v3}originInfo element (has no eventType)"