4523: Migrate to pathlib.Path

benchmarks/benchmarks/sperf/combine_regions.py

@@ -4,8 +4,6 @@
 # See LICENSE in the root of the repository for full licensing details.
 """Region combine benchmarks for the SPerf scheme of the UK Met Office's NG-VAT project."""
 
-import os.path
-
 from dask import array as da
 import numpy as np
 

docs/gallery_code/meteorology/plot_COP_maps.py

@@ -26,7 +26,7 @@
 
 """  # noqa: D205, D212, D400
 
-import os.path
+from pathlib import Path
 
 import matplotlib.pyplot as plt
 import numpy as np
@@ -40,7 +40,7 @@ def cop_metadata_callback(cube, field, filename):
     """Add an "Experiment" coordinate which comes from the filename."""
     # Extract the experiment name (such as A1B or E1) from the filename (in
     # this case it is just the start of the file name, before the first ".").
-    fname = os.path.basename(filename)  # filename without path.
+    fname = Path(filename).name  # filename without path.
     experiment_label = fname.split(".")[0]
 
     # Create a coordinate with the experiment label in it...

docs/src/conf.py

@@ -79,13 +79,13 @@ def autolog(message):
 
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
+# documentation root, use pathlib.Path().absolute() to make it absolute, like shown here.
 
 # custom sphinx extensions
-sys.path.append(os.path.abspath("sphinxext"))
+sys.path.append(str((Path("sphinxext").absolute())))
 
 # add some sample files from the developers guide..
-sys.path.append(os.path.abspath(os.path.join("developers_guide")))
+sys.path.append(str(Path("developers_guide").absolute()))
 
 # why isn't the iris path added to it is discoverable too?  We dont need to,
 # the sphinext to generate the api rst knows where the source is.  If it

docs/src/whatsnew/latest.rst

@@ -102,6 +102,8 @@ This document explains the changes made to Iris for this release
    except for mo_pack.
    (:issue:`6832`, :pull:`6976`)
 
+#. `@SgtVarmint` _ migrated codebase from os.path to pathlib.Path where possible
+   (:issue:`4523`, :pull:`7087`)
 .. comment
     Whatsnew author names (@github name) in alphabetical order. Note that,
     core dev names are automatically included by the common_links.inc:

lib/iris/__init__.py

@@ -50,7 +50,7 @@
 
     Filenames can contain `~` or `~user` abbreviations, and/or
     Unix shell-style wildcards (e.g. `*` and `?`). See the
-    standard library function :func:`os.path.expanduser` and
+    standard library function :func:`pathlib.Path(path).expanduser()` and
     module :mod:`fnmatch` for more details.
 
     .. warning::
@@ -101,7 +101,7 @@ def callback(cube, field, filename):
 import contextlib
 import glob
 import importlib
-import os.path
+from pathlib import Path
 import threading
 from typing import Callable, Literal
 
@@ -340,16 +340,16 @@ def sample_data_path(*path_to_join):
         appropriate for general file access.
 
     """
-    target = os.path.join(*path_to_join)
-    if os.path.isabs(target):
+    target = Path(*path_to_join)
+    if target.is_absolute():
         raise ValueError(
             "Absolute paths, such as {!r}, are not supported.\n"
             "NB. This function is only for locating files in the "
             "iris sample data collection. It is not needed or "
             "appropriate for general file access.".format(target)
         )
     if iris_sample_data is not None:
-        target = os.path.join(iris_sample_data.path, target)
+        target = str(Path(iris_sample_data.path) / target)
     else:
         raise ImportError(
             "Please install the 'iris-sample-data' package to access sample data."

lib/iris/config.py

@@ -33,7 +33,8 @@
 import configparser
 import contextlib
 import logging
-import os.path
+import os
+from pathlib import Path
 import warnings
 
 import iris.warnings
@@ -135,7 +136,7 @@ def get_dir_option(section, option, default=None):
     path = default
     if config.has_option(section, option):
         c_path = config.get(section, option)
-        if os.path.isdir(c_path):
+        if Path(c_path).is_dir():
             path = c_path
         else:
             msg = (
@@ -150,14 +151,14 @@ def get_dir_option(section, option, default=None):
 
 
 # Figure out the full path to the "iris" package.
-ROOT_PATH = os.path.abspath(os.path.dirname(__file__))
+ROOT_PATH = Path(__file__).parent.absolute()
 
 # The full path to the configuration directory of the active Iris instance.
-CONFIG_PATH = os.path.join(ROOT_PATH, "etc")
+CONFIG_PATH = ROOT_PATH / "etc"
 
 # Load the optional "site.cfg" file if it exists.
 config = configparser.ConfigParser()
-config.read([os.path.join(CONFIG_PATH, "site.cfg")])
+config.read([CONFIG_PATH / "site.cfg"])
 
 ##################
 # Resource options
@@ -167,19 +168,19 @@ def get_dir_option(section, option, default=None):
 TEST_DATA_DIR = get_dir_option(
     _RESOURCE_SECTION,
     "test_data_dir",
-    default=os.path.join(os.path.dirname(__file__), "test_data"),
+    default=str(Path(__file__) / "test_data"),
 )
 
 # Override the data repository if the appropriate environment variable
 # has been set.
 override = os.environ.get("OVERRIDE_TEST_DATA_REPOSITORY")
 if override:
     TEST_DATA_DIR = None
-    if os.path.isdir(os.path.expanduser(override)):
-        TEST_DATA_DIR = os.path.abspath(override)
+    if Path(override).expanduser().is_dir():
+        TEST_DATA_DIR = str(Path(override).absolute())
 
 PALETTE_PATH = get_dir_option(
-    _RESOURCE_SECTION, "palette_path", os.path.join(CONFIG_PATH, "palette")
+    _RESOURCE_SECTION, "palette_path", CONFIG_PATH / "palette"
 )
 
 # Runtime options

lib/iris/fileformats/abf.py

@@ -20,7 +20,7 @@
 import calendar
 import datetime
 import glob
-import os.path
+from pathlib import Path
 
 import numpy as np
 import numpy.ma as ma
@@ -82,7 +82,7 @@ def __init__(self, filename):
             field = ABFField("AVHRRBUVI01.1985feba.abl")
 
         """
-        basename = os.path.basename(filename)
+        basename = Path(filename).name
         if len(basename) != 24:
             raise ValueError(
                 "ABFField expects a filename of 24 characters: {}".format(basename)
@@ -100,7 +100,7 @@ def __getattr__(self, key):
 
     def _read(self):
         """Read the field from the given filename."""
-        basename = os.path.basename(self._filename)
+        basename = Path(self._filename).name
         self.version = int(basename[9:11])
         self.year = int(basename[12:16])
         self.month = basename[16:19]

lib/iris/fileformats/cf.py

@@ -21,7 +21,7 @@
 
 from abc import ABCMeta, abstractmethod
 from collections.abc import Iterable, MutableMapping
-import os
+from pathlib import Path
 import re
 from typing import ClassVar, Optional
 import warnings
@@ -1365,7 +1365,10 @@ def __init__(self, file_source, warn=False, monotonic=False):
         self._own_file = False
         if isinstance(file_source, str):
             # Create from filepath : open it + own it (=close when we die).
-            self._filename = os.path.expanduser(file_source)
+            self._filename = Path(file_source).expanduser()
+            if file_source.startswith("https:"):
+                self._filename = file_source
+
             self._dataset = _thread_safe_nc.DatasetWrapper(self._filename, mode="r")
             self._own_file = True
         else:

lib/iris/fileformats/dot.py

@@ -11,6 +11,7 @@
 """
 
 import os
+from pathlib import Path
 import subprocess
 
 import iris
@@ -40,16 +41,16 @@ def _dot_path():
         path = _DOT_EXECUTABLE_PATH
     else:
         path = iris.config.get_option("System", "dot_path", default="dot")
-        if not os.path.exists(path):
-            if not os.path.isabs(path):
+        if not Path(path).exists():
+            if not Path(path).is_absolute():
                 try:
                     # Check PATH
                     subprocess.check_output([path, "-V"], stderr=subprocess.STDOUT)
                 except (OSError, subprocess.CalledProcessError):
                     path = None
             else:
                 path = None
-        _DOT_EXECUTABLE_PATH = path
+        _DOT_EXECUTABLE_PATH = str(path)
         _DOT_CHECKED = True
     return path
 

lib/iris/fileformats/netcdf/saver.py

@@ -22,7 +22,7 @@
 import collections
 from itertools import repeat, zip_longest
 import os
-import os.path
+from pathlib import Path
 import re
 import string
 import typing
@@ -418,13 +418,13 @@ def __init__(self, filename, netcdf_format, compute=True):
         else:
             # Given a filepath string/path : create a dataset from that
             try:
-                self.filepath = os.path.abspath(filename)
+                self.filepath = Path(filename)
                 self._dataset = _thread_safe_nc.DatasetWrapper(
                     self.filepath, mode="w", format=netcdf_format
                 )
             except RuntimeError:
-                dir_name = os.path.dirname(self.filepath)
-                if not os.path.isdir(dir_name):
+                dir_name = self.filepath.parent
+                if not dir_name.is_dir():
                     msg = "No such file or directory: {}".format(dir_name)
                     raise IOError(msg)
                 if not os.access(dir_name, os.R_OK | os.W_OK):

lib/iris/fileformats/um/_fast_load.py

@@ -21,7 +21,7 @@
 """
 
 from contextlib import contextmanager
-import os.path
+from pathlib import Path
 import threading
 
 import numpy as np
@@ -120,7 +120,7 @@ def _select_raw_fields_loader(fname):
         from iris.fileformats.um import um_to_pp
 
         with open(fname, "rb") as fh:
-            spec = FORMAT_AGENT.get_spec(os.path.basename(fname), fh)
+            spec = FORMAT_AGENT.get_spec(Path(fname).name, fh)
         if spec.name.startswith(_FF_SPEC_NAME):
             loader = um_to_pp
         elif spec.name.startswith(_PP_SPEC_NAME):

lib/iris/io/__init__.py

@@ -14,7 +14,6 @@
 import collections
 from collections import OrderedDict
 import glob
-import os.path
 import pathlib
 import re
 
@@ -168,7 +167,8 @@ def expand_filespecs(file_specs, files_expected=True):
     """
     # Remove any hostname component - currently unused
     filenames = [
-        os.path.abspath(os.path.expanduser(fn.removeprefix("//"))) for fn in file_specs
+        str(pathlib.Path(fn.removeprefix("//")).expanduser().absolute())
+        for fn in file_specs
     ]
 
     if files_expected:
@@ -214,7 +214,7 @@ def load_files(filenames, callback, constraints=None):
     handler_map = collections.defaultdict(list)
     for fn in all_file_paths:
         with open(fn, "rb") as fh:
-            handling_format_spec = FORMAT_AGENT.get_spec(os.path.basename(fn), fh)
+            handling_format_spec = FORMAT_AGENT.get_spec(pathlib.Path(fn).name, fh)
             handler_map[handling_format_spec].append(fn)
 
     # Call each iris format handler with the appropriate filenames

lib/iris/io/format_picker.py

@@ -48,7 +48,7 @@
 
 from collections.abc import Callable
 import functools
-import os
+from pathlib import Path
 import struct
 
 
@@ -348,7 +348,7 @@ class FileExtension(FileElement):
 
     def get_element(self, basename, file_handle):
         # noqa D102
-        return os.path.splitext(basename)[1]
+        return Path(basename).suffix
 
 
 class LeadingLine(FileElement):

lib/iris/palette.py

@@ -15,7 +15,7 @@
 
 from functools import wraps
 import os
-import os.path
+from pathlib import Path
 import re
 
 import cf_units
@@ -248,15 +248,15 @@ def _load_palette():
         # Identify any target .txt color map palette files.
         filenames.extend(
             [
-                os.path.join(root, filename)
+                str(Path(root) / filename)
                 for filename in files
-                if os.path.splitext(filename)[1] == ".txt"
+                if Path(filename).suffix == ".txt"
             ]
         )
 
     for filename in filenames:
         # Default color map name based on the file base-name (case-SENSITIVE).
-        cmap_name = os.path.splitext(os.path.basename(filename))[0]
+        cmap_name = Path(filename).stem
         cmap_scheme = None
         cmap_keywords = []
         cmap_std_names = []