Ruff PTH: moved to pathlib anywhere I could

evertlammerts · evertlammerts · commit ed4f1811d75b · 2025-09-18T13:50:06.000+02:00
diff --git a/duckdb/experimental/spark/sql/types.py b/duckdb/experimental/spark/sql/types.py
@@ -1182,9 +1182,7 @@ def __contains__(self, item: Any) -> bool:  # noqa: D105, ANN401
     def __call__(self, *args: Any) -> "Row":  # noqa: ANN401
         """Create new Row object."""
         if len(args) > len(self):
-            raise ValueError(
-                f"Can not create Row with fields {self}, expected {len(self):d} values but got {args}"
-            )
+            raise ValueError(f"Can not create Row with fields {self}, expected {len(self):d} values but got {args}")
         return _create_row(self, args)
 
     def __getitem__(self, item: Any) -> Any:  # noqa: D105, ANN401
diff --git a/duckdb/query_graph/__main__.py b/duckdb/query_graph/__main__.py
@@ -1,10 +1,10 @@
 import argparse  # noqa: D100
 import json
-import os
 import re
 import sys
 import webbrowser
 from functools import reduce
+from pathlib import Path
 
 qgraph_css = """
 .styled-table {
@@ -122,7 +122,7 @@ def get_sum_of_all_timings(self) -> float:  # noqa: D102
 
 
 def open_utf8(fpath: str, flags: str) -> object:  # noqa: D103
-    return open(fpath, flags, encoding="utf8")
+    return Path(fpath).open(mode=flags, encoding="utf8")
 
 
 def get_child_timings(top_node: object, query_timings: object) -> str:  # noqa: D103
@@ -355,7 +355,7 @@ def main() -> None:  # noqa: D103
     translate_json_to_html(input, output)
 
     if open_output:
-        webbrowser.open("file://" + os.path.abspath(output), new=2)
+        webbrowser.open(f"file://{Path(output).resolve()}", new=2)
 
 
 if __name__ == "__main__":
diff --git a/duckdb_packaging/build_backend.py b/duckdb_packaging/build_backend.py
@@ -13,7 +13,6 @@
 Also see https://peps.python.org/pep-0517/#in-tree-build-backends.
 """
 
-import os
 import subprocess
 import sys
 from pathlib import Path
@@ -91,7 +90,7 @@ def _duckdb_submodule_path() -> Path:
             elif line.strip().startswith("path"):
                 cur_module_path = line.split("=")[-1].strip()
             elif line.strip().startswith("url"):
-                basename = os.path.basename(line.split("=")[-1].strip())
+                basename = Path(line.split("=")[-1].strip()).name
                 cur_module_reponame = basename[:-4] if basename.endswith(".git") else basename
         if cur_module_reponame is not None and cur_module_path is not None:
             modules[cur_module_reponame] = cur_module_path
diff --git a/scripts/generate_connection_methods.py b/scripts/generate_connection_methods.py
@@ -30,8 +30,7 @@ def is_py_args(method):
 
 def generate():
     # Read the PYCONNECTION_SOURCE file
-    with open(PYCONNECTION_SOURCE) as source_file:
-        source_code = source_file.readlines()
+    source_code = Path(PYCONNECTION_SOURCE).read_text().splitlines()
 
     start_index = -1
     end_index = -1
@@ -56,8 +55,7 @@ def generate():
     # ---- Generate the definition code from the json ----
 
     # Read the JSON file
-    with open(JSON_PATH) as json_file:
-        connection_methods = json.load(json_file)
+    connection_methods = json.loads(Path(JSON_PATH).read_text())
 
     DEFAULT_ARGUMENT_MAP = {
         "True": "true",
@@ -127,8 +125,7 @@ def create_definition(name, method) -> str:
     new_content = start_section + with_newlines + end_section
 
     # Write out the modified PYCONNECTION_SOURCE file
-    with open(PYCONNECTION_SOURCE, "w") as source_file:
-        source_file.write("".join(new_content))
+    Path(PYCONNECTION_SOURCE).write_text("".join(new_content))
 
 
 if __name__ == "__main__":
diff --git a/scripts/generate_connection_stubs.py b/scripts/generate_connection_stubs.py
@@ -13,8 +13,7 @@
 
 def generate():
     # Read the DUCKDB_STUBS_FILE file
-    with open(DUCKDB_STUBS_FILE) as source_file:
-        source_code = source_file.readlines()
+    source_code = Path(DUCKDB_STUBS_FILE).read_text().splitlines()
 
     start_index = -1
     end_index = -1
@@ -39,8 +38,7 @@ def generate():
     # ---- Generate the definition code from the json ----
 
     # Read the JSON file
-    with open(JSON_PATH) as json_file:
-        connection_methods = json.load(json_file)
+    connection_methods = json.loads(Path(JSON_PATH).read_text())
 
     body = []
 
@@ -95,8 +93,7 @@ def create_overloaded_definition(name, method) -> str:
     new_content = start_section + with_newlines + end_section
 
     # Write out the modified DUCKDB_STUBS_FILE file
-    with open(DUCKDB_STUBS_FILE, "w") as source_file:
-        source_file.write("".join(new_content))
+    Path(DUCKDB_STUBS_FILE).write_text("".join(new_content))
 
 
 if __name__ == "__main__":
diff --git a/scripts/generate_connection_wrapper_methods.py b/scripts/generate_connection_wrapper_methods.py
@@ -39,8 +39,7 @@
 INIT_PY_END = "# END OF CONNECTION WRAPPER"
 
 # Read the JSON file
-with open(WRAPPER_JSON_PATH) as json_file:
-    wrapper_methods = json.load(json_file)
+wrapper_methods = json.loads(Path(WRAPPER_JSON_PATH).read_text())
 
 # On DuckDBPyConnection these are read_only_properties, they're basically functions without requiring () to invoke
 # that's not possible on 'duckdb' so it becomes a function call with no arguments (i.e duckdb.description())
@@ -96,20 +95,17 @@ def remove_section(content, start_marker, end_marker) -> tuple[list[str], list[s
 
 def generate():
     # Read the DUCKDB_PYTHON_SOURCE file
-    with open(DUCKDB_PYTHON_SOURCE) as source_file:
-        source_code = source_file.readlines()
+    source_code = Path(DUCKDB_PYTHON_SOURCE).read_text().splitlines()
     start_section, end_section = remove_section(source_code, START_MARKER, END_MARKER)
 
     # Read the DUCKDB_INIT_FILE file
-    with open(DUCKDB_INIT_FILE) as source_file:
-        source_code = source_file.readlines()
+    source_code = Path(DUCKDB_INIT_FILE).read_text().splitlines()
     py_start, py_end = remove_section(source_code, INIT_PY_START, INIT_PY_END)
 
     # ---- Generate the definition code from the json ----
 
     # Read the JSON file
-    with open(JSON_PATH) as json_file:
-        connection_methods = json.load(json_file)
+    connection_methods = json.loads(Path(JSON_PATH).read_text())
 
     # Collect the definitions from the pyconnection.hpp header
 
@@ -241,8 +237,7 @@ def create_definition(name, method, lambda_def) -> str:
     # Recreate the file content by concatenating all the pieces together
     new_content = start_section + with_newlines + end_section
     # Write out the modified DUCKDB_PYTHON_SOURCE file
-    with open(DUCKDB_PYTHON_SOURCE, "w") as source_file:
-        source_file.write("".join(new_content))
+    Path(DUCKDB_PYTHON_SOURCE).write_text("".join(new_content))
 
     item_list = "\n".join([f"\t{name}," for name in all_names])
     str_item_list = "\n".join([f"\t'{name}'," for name in all_names])
@@ -251,8 +246,7 @@ def create_definition(name, method, lambda_def) -> str:
 
     init_py_content = py_start + imports + py_end
     # Write out the modified DUCKDB_INIT_FILE file
-    with open(DUCKDB_INIT_FILE, "w") as source_file:
-        source_file.write("".join(init_py_content))
+    Path(DUCKDB_INIT_FILE).write_text("".join(init_py_content))
 
 
 if __name__ == "__main__":
diff --git a/scripts/generate_connection_wrapper_stubs.py b/scripts/generate_connection_wrapper_stubs.py
@@ -14,8 +14,7 @@
 
 def generate():
     # Read the DUCKDB_STUBS_FILE file
-    with open(DUCKDB_STUBS_FILE) as source_file:
-        source_code = source_file.readlines()
+    source_code = Path(DUCKDB_STUBS_FILE).read_text().splitlines()
 
     start_index = -1
     end_index = -1
@@ -41,12 +40,9 @@ def generate():
 
     methods = []
 
-    # Read the JSON file
-    with open(JSON_PATH) as json_file:
-        connection_methods = json.load(json_file)
-
-    with open(WRAPPER_JSON_PATH) as json_file:
-        wrapper_methods = json.load(json_file)
+    # Read the JSON files
+    connection_methods = json.loads(Path(JSON_PATH).read_text())
+    wrapper_methods = json.loads(Path(WRAPPER_JSON_PATH).read_text())
 
     methods.extend(connection_methods)
     methods.extend(wrapper_methods)
@@ -119,8 +115,7 @@ def create_overloaded_definition(name, method) -> str:
     new_content = start_section + with_newlines + end_section
 
     # Write out the modified DUCKDB_STUBS_FILE file
-    with open(DUCKDB_STUBS_FILE, "w") as source_file:
-        source_file.write("".join(new_content))
+    Path(DUCKDB_STUBS_FILE).write_text("".join(new_content))
 
 
 if __name__ == "__main__":
diff --git a/scripts/generate_import_cache_cpp.py b/scripts/generate_import_cache_cpp.py
@@ -7,8 +7,7 @@
 json_data = {}
 json_cache_path = Path(script_dir) / "cache_data.json"
 try:
-    with open(json_cache_path) as file:
-        json_data = json.load(file)
+    json_data = json.loads(Path(json_cache_path).read_text())
 except FileNotFoundError:
     print("Please first use 'generate_import_cache_json.py' first to generate json")
 
@@ -183,8 +182,7 @@ def to_string(self):
     content = file.to_string()
     path = f"src/duckdb_py/include/duckdb_python/import_cache/modules/{file.file_name}"
     import_cache_path = Path(script_dir) / ".." / path
-    with open(import_cache_path, "w") as f:
-        f.write(content)
+    import_cache_path.write_text(content)
 
 
 def get_root_modules(files: list[ModuleFile]):
@@ -237,8 +235,7 @@ def get_root_modules(files: list[ModuleFile]):
 """
 
 import_cache_path = Path(script_dir) / ".." / "src/duckdb_py/include/duckdb_python/import_cache/python_import_cache.hpp"
-with open(import_cache_path, "w") as f:
-    f.write(import_cache_file)
+import_cache_path.write_text(import_cache_file)
 
 
 def get_module_file_path_includes(files: list[ModuleFile]):
@@ -253,8 +250,7 @@ def get_module_file_path_includes(files: list[ModuleFile]):
 modules_header = (
     Path(script_dir) / ".." / ("src/duckdb_py/include/duckdb_python/import_cache/python_import_cache_modules.hpp")
 )
-with open(modules_header, "w") as f:
-    f.write(module_includes)
+modules_header.write_text(module_includes)
 
 # Generate the python_import_cache_modules.hpp file
 # listing all the generated header files
diff --git a/scripts/generate_import_cache_json.py b/scripts/generate_import_cache_json.py
@@ -3,8 +3,7 @@
 from typing import Union
 
 script_dir = Path(__file__).parent
-
-lines: list[str] = [file for file in open(f"{script_dir}/imports.py").read().split("\n") if file != ""]
+lines = [line for line in (script_dir / "imports.py").read_text().splitlines() if line]
 
 
 class ImportCacheAttribute:
@@ -157,8 +156,7 @@ def to_json(self):
 existing_json_data = {}
 json_cache_path = Path(script_dir) / "cache_data.json"
 try:
-    with open(json_cache_path) as file:
-        existing_json_data = json.load(file)
+    existing_json_data = json.loads(json_cache_path.read_text())
 except FileNotFoundError:
     pass
 
@@ -184,5 +182,4 @@ def update_json(existing: dict, new: dict) -> dict:
 json_data = update_json(existing_json_data, json_data)
 
 # Save the merged JSON data back to the file
-with open(json_cache_path, "w") as file:
-    json.dump(json_data, file, indent=4)
+json_cache_path.write_text(json.dumps(json_data, indent=4))
diff --git a/tests/conftest.py b/tests/conftest.py
@@ -1,9 +1,7 @@
-import glob
 import os
 import shutil
 import warnings
 from importlib import import_module
-from os.path import abspath
 from pathlib import Path
 from typing import Any
 
@@ -210,9 +208,9 @@ def _require(extension_name, db_name="") -> duckdb.DuckDBPyConnection | None:
 
         extension_paths_found = []
         for pattern in extension_search_patterns:
-            extension_pattern_abs = abspath(pattern)
+            extension_pattern_abs = Path(pattern).resolve()
             print(f"Searching path: {extension_pattern_abs}")
-            for path in glob.glob(extension_pattern_abs):
+            for path in extension_pattern_abs.glob():
                 extension_paths_found.append(path)
 
         for path in extension_paths_found:
diff --git a/tests/fast/api/test_connection_close.py b/tests/fast/api/test_connection_close.py
@@ -1,6 +1,4 @@
 # cursor description
-
-import os
 import tempfile
 
 import pytest
@@ -19,9 +17,8 @@ def check_exception(f):
 
 class TestConnectionClose:
     def test_connection_close(self, duckdb_cursor):
-        fd, db = tempfile.mkstemp()
-        os.close(fd)
-        os.remove(db)
+        with tempfile.NamedTemporaryFile(delete=False) as tmp:
+            db = tmp.name
         con = duckdb.connect(db)
         cursor = con.cursor()
         cursor.execute("create table a (i integer)")
@@ -36,9 +33,8 @@ def test_open_and_exit(self):
             raise TypeError()
 
     def test_reopen_connection(self, duckdb_cursor):
-        fd, db = tempfile.mkstemp()
-        os.close(fd)
-        os.remove(db)
+        with tempfile.NamedTemporaryFile(delete=False) as tmp:
+            db = tmp.name
         con = duckdb.connect(db)
         cursor = con.cursor()
         cursor.execute("create table a (i integer)")
diff --git a/tests/fast/api/test_dbapi11.py b/tests/fast/api/test_dbapi11.py
@@ -1,6 +1,5 @@
 # cursor description
 
-import os
 import tempfile
 
 import duckdb
@@ -17,9 +16,8 @@ def check_exception(f):
 
 class TestReadOnly:
     def test_readonly(self, duckdb_cursor):
-        fd, db = tempfile.mkstemp()
-        os.close(fd)
-        os.remove(db)
+        with tempfile.NamedTemporaryFile(delete=False) as tmp:
+            db = tmp.name
 
         # this is forbidden
         check_exception(lambda: duckdb.connect(":memory:", True))
diff --git a/tests/fast/api/test_fsspec.py b/tests/fast/api/test_fsspec.py
@@ -11,8 +11,7 @@ def test_fsspec_deadlock(self, duckdb_cursor, tmp_path):
         # Create test parquet data
         file_path = tmp_path / "data.parquet"
         duckdb_cursor.sql(f"COPY (FROM range(50_000)) TO '{file_path!s}' (FORMAT parquet)")
-        with open(file_path, "rb") as f:
-            parquet_data = f.read()
+        parquet_data = file_path.read_bytes()
 
         class TestFileSystem(fsspec.AbstractFileSystem):
             protocol = "deadlock"
diff --git a/tests/fast/pandas/test_pandas_unregister.py b/tests/fast/pandas/test_pandas_unregister.py
@@ -1,5 +1,4 @@
 import gc
-import os
 import tempfile
 
 import pytest
@@ -25,9 +24,8 @@ def test_pandas_unregister1(self, duckdb_cursor, pandas):
 
     @pytest.mark.parametrize("pandas", [NumpyPandas(), ArrowPandas()])
     def test_pandas_unregister2(self, duckdb_cursor, pandas):
-        fd, db = tempfile.mkstemp()
-        os.close(fd)
-        os.remove(db)
+        with tempfile.NamedTemporaryFile(delete=False) as tmp:
+            db = tmp.name
 
         connection = duckdb.connect(db)
         df = pandas.DataFrame([[1, 2, 3], [4, 5, 6]])
diff --git a/tests/fast/relational_api/test_pivot.py b/tests/fast/relational_api/test_pivot.py
@@ -1,5 +1,5 @@
-import os
 import tempfile
+from pathlib import Path
 
 
 class TestPivot:
@@ -24,5 +24,4 @@ def test_pivot_issue_14601(self, duckdb_cursor):
         pivot_1.create("pivot_1")
         export_dir = tempfile.mkdtemp()
         duckdb_cursor.query(f"EXPORT DATABASE '{export_dir}'")
-        with open(os.path.join(export_dir, "schema.sql")) as f:  # noqa: PTH118
-            assert "CREATE TYPE" not in f.read()
+        assert "CREATE TYPE" not in (Path(export_dir) / "schema.sql").read_text()
diff --git a/tests/fast/spark/test_spark_readcsv.py b/tests/fast/spark/test_spark_readcsv.py
diff --git a/tests/fast/test_filesystem.py b/tests/fast/test_filesystem.py
diff --git a/tests/fast/test_import_export.py b/tests/fast/test_import_export.py
diff --git a/tests/fast/test_many_con_same_file.py b/tests/fast/test_many_con_same_file.py
diff --git a/tests/fast/test_multi_statement.py b/tests/fast/test_multi_statement.py
diff --git a/tests/fast/test_windows_abs_path.py b/tests/fast/test_windows_abs_path.py
diff --git a/tests/slow/test_h2oai_arrow.py b/tests/slow/test_h2oai_arrow.py
