refactor: enable ruff PTH110 for Path.exists() (thousandbrainsproject#601)

Author: carver

pyproject.toml

@@ -256,7 +256,6 @@ ignore = [
     "PT009", # PT009: Use a regular `assert` instead of unittest-style `assertEqual`
     "PT018", # PT018: Assertion should be broken down into multiple parts
     "PT027", # PT027: Use `pytest.raises` instead of unittest-style `assertRaises`
-    "PTH110", # PTH110: `os.path.exists()` should be replaced by `Path.exists()`
     "PTH111", # PTH111: `os.path.expanduser()` should be replaced by `Path.expanduser()`
     "PTH119", # PTH119: `os.path.basename()` should be replaced by `Path.name`
     "PTH120", # PTH120: `os.path.dirname()` should be replaced by `Path.parent`

src/tbp/monty/frameworks/environments/two_d_data.py

@@ -725,7 +725,7 @@ def load_new_scene_data(self):
         current_rgb_path = self.data_path / f"rgb_{self.current_scene}.png"
         # Load rgb image
         wait_count = 0
-        while not os.path.exists(current_rgb_path):
+        while not current_rgb_path.exists():
             if wait_count % 10 == 0:
                 # Print every 10 seconds
                 print("Waiting for new RGBD data...")
@@ -743,7 +743,7 @@ def load_new_scene_data(self):
         height, width, _ = current_rgb_image.shape
 
         # Load depth image
-        while not os.path.exists(current_depth_path):
+        while not current_depth_path.exists():
             print(f"Waiting for new depth data. Looking for {current_depth_path}")
             time.sleep(1)
         load_succeeded = False

src/tbp/monty/frameworks/models/evidence_sdr_matching.py

@@ -9,7 +9,6 @@
 # https://opensource.org/licenses/MIT.
 
 import logging
-import os
 import shutil
 from pathlib import Path
 
@@ -50,7 +49,7 @@ def __init__(self, path):
         path = Path(path).expanduser()
 
         # overwrite existing logs
-        if os.path.exists(path):
+        if path.exists():
             shutil.rmtree(path)
         path.mkdir(parents=True)
 

src/tbp/monty/frameworks/run_parallel.py

@@ -71,7 +71,7 @@ def mv_files(filenames: Iterable[Path], outdir: Path):
 
 def cat_files(filenames, outfile):
     outfile = Path(outfile)
-    if os.path.exists(outfile):
+    if outfile.exists():
         print(f"Removing existing file before writing new one: {outfile}")
         outfile.unlink()
 
@@ -96,7 +96,7 @@ def sample_params_to_init_args(params):
 
 
 def post_parallel_log_cleanup(filenames, outfile, cat_fn):
-    existing_files = [f for f in filenames if os.path.exists(f)]
+    existing_files = [f for f in map(Path, filenames) if f.exists()]
     if len(existing_files) == 0:
         return
 
@@ -105,7 +105,7 @@ def post_parallel_log_cleanup(filenames, outfile, cat_fn):
 
     # Remove json files
     for f in existing_files:
-        Path(f).unlink(missing_ok=True)
+        f.unlink(missing_ok=True)
 
 
 def post_parallel_profile_cleanup(parallel_dirs, base_dir, mode):
@@ -135,7 +135,7 @@ def post_parallel_profile_cleanup(parallel_dirs, base_dir, mode):
 
 def move_reproducibility_data(base_dir, parallel_dirs):
     outdir = Path(base_dir) / "reproduce_episode_data"
-    if os.path.exists(outdir):
+    if outdir.exists():
         shutil.rmtree(outdir)
 
     outdir.mkdir(parents=True)
@@ -649,7 +649,7 @@ def run_episodes_parallel(
         post_parallel_train(experiments, base_dir)
         if log_parallel_wandb:
             csv_path = base_dir / "train_stats.csv"
-            if os.path.exists(csv_path):
+            if csv_path.exists():
                 train_stats = pd.read_csv(csv_path)
                 train_table = wandb.Table(dataframe=train_stats)
                 if run is not None:
@@ -660,7 +660,7 @@ def run_episodes_parallel(
         post_parallel_eval(experiments, base_dir)
         if log_parallel_wandb:
             csv_path = base_dir / "eval_stats.csv"
-            if os.path.exists(csv_path):
+            if csv_path.exists():
                 eval_stats = pd.read_csv(csv_path)
                 eval_table = wandb.Table(dataframe=eval_stats)
                 run.log({"eval_stats": eval_table})

tools/github_readme_sync/export.py

@@ -9,7 +9,6 @@
 # https://opensource.org/licenses/MIT.
 
 import logging
-import os
 import shutil
 from pathlib import Path
 
@@ -25,7 +24,7 @@ def export(output_dir: str, rdme: ReadMe):
     hierarchy = []
     categories = rdme.get_categories()
 
-    if os.path.exists(output_dir):
+    if output_dir.exists():
         shutil.rmtree(output_dir)
 
     output_dir.mkdir(exist_ok=True, parents=True)

tools/github_readme_sync/hierarchy.py

@@ -74,7 +74,7 @@ def check_hierarchy_file(folder: str):
     hierarchy = []
 
     hierarchy_file = folder / HIERARCHY_FILE
-    if not os.path.exists(hierarchy_file):
+    if not hierarchy_file.exists():
         logging.error(f"File {hierarchy_file} does not exist")
         sys.exit(1)
 
@@ -135,7 +135,7 @@ def extract_slug(line: str):
 
 
 def sanity_check(path):
-    if not os.path.exists(path):
+    if not path.exists():
         return [f"File {path} does not exist"]
 
     return check_links(path)
@@ -163,7 +163,7 @@ def check_links(path):
         f"{YELLOW} {len(table_matches)} tables{RESET}"
     )
 
-    current_dir = path.parent
+    current_dir = path.resolve().parent
     errors = []
 
     for match in table_matches:
@@ -172,29 +172,26 @@ def check_links(path):
             continue
 
         path_to_check = current_dir / match
-        path_to_check = os.path.normpath(path_to_check)
-        if not os.path.exists(path_to_check):
+        if not path_to_check.exists():
             errors.append(f"  CSV {match} does not exist")
 
     for match in md_link_matches:
         if match[1].startswith(("http://", "https://", "mailto:")):
             continue
 
         path_to_check = current_dir / match[1].split("#")[0]
-        path_to_check = os.path.normpath(path_to_check)
         if any(placeholder in match[1] for placeholder in IGNORE_DOCS):
             continue
-        logging.debug(f"{GREEN}  {path_to_check.split('/')[-1]}{RESET}")
-        if not os.path.exists(path_to_check):
+        logging.debug(f"{GREEN}  {path_to_check.name}{RESET}")
+        if not path_to_check.exists():
             errors.append(f"  Linked {match[1]} does not exist")
 
     for match in image_link_matches:
         path_to_check = current_dir / match.split("#")[0]
-        path_to_check = os.path.normpath(path_to_check)
         if any(placeholder in match for placeholder in IGNORE_IMAGES):
             continue
-        logging.debug(f"{CYAN}  {path_to_check.split('/')[-1]}{RESET}")
-        if not os.path.exists(path_to_check):
+        logging.debug(f"{CYAN}  {path_to_check.name}{RESET}")
+        if not path_to_check.exists():
             errors.append(f"  Image {path_to_check} does not exist")
 
     if errors:

tools/github_readme_sync/tests/hierarchy_test.py

@@ -10,7 +10,6 @@
 
 import contextlib
 import http.server
-import os
 import socketserver
 import tempfile
 import threading
@@ -63,7 +62,7 @@ def test_create_hierarchy_file(self):
         create_hierarchy_file(self.test_dir, hierarchy_structure)
 
         hierarchy_file_path = self.test_dir / HIERARCHY_FILE
-        self.assertTrue(os.path.exists(hierarchy_file_path))
+        self.assertTrue(hierarchy_file_path.exists())
 
         with open(hierarchy_file_path) as f:
             content = f.read()

tools/github_readme_sync/upload.py

@@ -9,7 +9,6 @@
 # https://opensource.org/licenses/MIT.
 
 import logging
-import os
 from pathlib import Path
 
 from tools.github_readme_sync.colors import BLUE, CYAN, GRAY, RESET, WHITE
@@ -125,7 +124,7 @@ def print_child(level: int, doc: dict, created: bool):
 
 def load_doc(file_path: str, category_slug: str, child: dict):
     file_path = Path(file_path) / category_slug / f"{child['slug']}.md"
-    if not os.path.exists(file_path):
+    if not file_path.exists():
         raise ValueError(f"File {file_path} does not exist")
 
     with open(file_path, encoding="utf-8") as file: