Switch to ruff for formatting and linting

.github/workflows/ci.yml

@@ -21,10 +21,9 @@ jobs:
     steps:
     - uses: actions/checkout@v3
     - name: Code formatting
-      uses: psf/black@stable
+      uses: astral-sh/ruff-action@v3
       with:
-        options: "--check --verbose --diff"
-        src: "./src ./tests"
+        args: "format --check --diff"
 
   pypa-build:
     name: PyPA build
@@ -80,12 +79,8 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install '.[devel,test]'
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Lint with ruff
+      uses: astral-sh/ruff-action@v3
     - name: Test with pytest
       run: |
         python -m pytest

.pre-commit-config.yaml

@@ -0,0 +1,10 @@
+repos:
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.13.2
+  hooks:
+    # Run the linter.
+    - id: ruff-check
+      args: [ --fix ]
+    # Run the formatter.
+    - id: ruff-format

pyproject.toml

@@ -25,8 +25,7 @@ build-backend = "setuptools.build_meta"
 
 [project.optional-dependencies]
 devel = [
-    "flake8",
-    "black",
+    "ruff",
     "pre-commit",
 ]
 test = [
@@ -39,10 +38,10 @@ addopts = ["--cov=access.profiling", "--cov-report=term", "--cov-report=html", "
 testpaths = ["tests"]
 
 [tool.coverage.run]
-omit = ["src/access/profiling/__init__.py"]
+omit = ["setup.py"]
 
-[tool.black]
+[tool.ruff]
 line-length = 120
 
-[tool.flake8]
-max-line-length = 120
+[tool.ruff.lint]
+select = ["E", "F", "B", "C4", "SIM", "PTH", "UP", "I", "N", "C901"]

setup.py

@@ -1,5 +1,5 @@
 # This file is only needed for the automatic versioning in the conda recipe
-from setuptools import setup
 import setuptools_scm
+from setuptools import setup
 
 setup(version=setuptools_scm.get_version())

src/access/profiling/__init__.py

@@ -2,20 +2,18 @@
 access-profiling package.
 """
 
-__version__ = "0.1.0"
-from importlib.metadata import version, PackageNotFoundError
+from contextlib import suppress
+from importlib.metadata import PackageNotFoundError, version
 
-try:
+__version__ = "unknown"
+with suppress(PackageNotFoundError):
     __version__ = version("access-profiling")
-except PackageNotFoundError:
-    # package is not installed
-    pass
 
-from access.profiling.parser import ProfilingParser
+from access.profiling.cice5_parser import CICE5ProfilingParser
 from access.profiling.fms_parser import FMSProfilingParser
-from access.profiling.um_parser import UMProfilingParser
+from access.profiling.parser import ProfilingParser
 from access.profiling.payujson_parser import PayuJSONProfilingParser
-from access.profiling.cice5_parser import CICE5ProfilingParser
+from access.profiling.um_parser import UMProfilingParser
 
 __all__ = [
     "ProfilingParser",

src/access/profiling/cice5_parser.py

@@ -23,9 +23,10 @@
 For example, ESM1.6 has 17 timers printed at the end of ice_diag.d output log.
 """
 
-from access.profiling.parser import ProfilingParser
 import re
 
+from access.profiling.parser import ProfilingParser
+
 
 class CICE5ProfilingParser(ProfilingParser):
     """CICE5 profiling output parser."""
@@ -60,7 +61,10 @@ def read(self, stream: str) -> dict:
 
         # Regex pattern to match timer blocks
         # This captures the region name and the three node timing values
-        pattern = r"Timer\s+\d+:\s+(\w+)\s+[\d.]+\s+seconds\s+Timer stats \(node\): min =\s+([\d.]+) seconds\s+max =\s+([\d.]+) seconds\s+mean=\s+([\d.]+) seconds"
+        pattern = (
+            r"Timer\s+\d+:\s+(\w+)\s+[\d.]+\s+seconds\s+Timer stats \(node\): min =\s+([\d.]+) seconds\s+max ="
+            r"\s+([\d.]+) seconds\s+mean=\s+([\d.]+) seconds"
+        )
 
         # Find all matches
         matches = re.findall(pattern, stream, re.MULTILINE | re.DOTALL)

src/access/profiling/fms_parser.py

@@ -4,18 +4,19 @@
 """Parser for FMS profiling data, such as output by MOM5 and MOM6.
 The data to be parsed is written in the following form:
 
-                                    hits          tmin          tmax          tavg          tstd  tfrac grain pemin pemax
-Total runtime                         1    138.600364    138.600366    138.600365      0.000001  1.000     0     0    11
-Ocean Initialization                  2      2.344926      2.345701      2.345388      0.000198  0.017    11     0    11
-Ocean                                23     86.869466     86.871652     86.870450      0.000744  0.627     1     0    11
-Ocean dynamics                       96     43.721019     44.391032     43.957944      0.244785  0.317    11     0    11
-Ocean thermodynamics and tracers     72     27.377185     33.281659     29.950144      1.792324  0.216    11     0    11
- MPP_STACK high water mark=           0
+                                   hits          tmin          tmax          tavg          tstd  tfrac grain pemin pemax
+Total runtime                        1    138.600364    138.600366    138.600365      0.000001  1.000     0     0    11
+Ocean Initialization                 2      2.344926      2.345701      2.345388      0.000198  0.017    11     0    11
+Ocean                               23     86.869466     86.871652     86.870450      0.000744  0.627     1     0    11
+Ocean dynamics                      96     43.721019     44.391032     43.957944      0.244785  0.317    11     0    11
+Ocean thermodynamics and tracers    72     27.377185     33.281659     29.950144      1.792324  0.216    11     0    11
+ MPP_STACK high water mark=          0
 """
 
-from access.profiling.parser import ProfilingParser, _convert_from_string
 import re
 
+from access.profiling.parser import ProfilingParser, _convert_from_string
+
 
 class FMSProfilingParser(ProfilingParser):
     """FMS profiling output parser."""
@@ -40,7 +41,6 @@ def metrics(self) -> list:
         return self._metrics
 
     def read(self, stream: str) -> dict:
-
         # Regular expression to extract the profiling section from the file
         header = r"\s*" + r"\s*".join(self._metrics) + r"\s*"
         footer = r" MPP_STACK high water mark=\s*\d*"
@@ -57,7 +57,7 @@ def read(self, stream: str) -> dict:
         stats = {"region": []}
         stats.update({m: [] for m in self.metrics})
         match = profiling_section_p.search(stream)
-        if match == None:
+        if match is None:
             raise ValueError("No FMS profiling data found")
         else:
             profiling_section = match.group(1)

src/access/profiling/parser.py

@@ -26,8 +26,9 @@ class ProfilingParser(ABC):
     values, one for each profiling region. Therefore, 'val1a', is the value for metric a of region 1.
     """
 
+    @abstractmethod
     def __init__(self):
-        pass
+        """Instantiate a ProfilingParser."""
 
     @property
     @abstractmethod
@@ -47,7 +48,8 @@ def read(self, stream: str) -> dict:
 
 
 def _convert_from_string(value: str) -> Any:
-    """Tries to convert a string to the most appropriate numeric type. Leaves it unchanged if conversion does not succeed.
+    """Tries to convert a string to the most appropriate numeric type. Leaves it unchanged if conversion does not
+    succeed.
 
     Args:
         value (str): string to convert.
@@ -58,6 +60,6 @@ def _convert_from_string(value: str) -> Any:
     for type_conversion in (int, float):
         try:
             return type_conversion(value)
-        except:
+        except Exception:
             continue
     return value

src/access/profiling/payujson_parser.py

@@ -21,9 +21,10 @@
 }
 """
 
-from access.profiling.parser import ProfilingParser
 import json
 
+from access.profiling.parser import ProfilingParser
+
 
 class PayuJSONProfilingParser(ProfilingParser):
     """Payu JSON job output profiling parser."""
@@ -58,8 +59,8 @@ def read(self, stream: str) -> dict:
 
         try:
             timings = json.loads(stream)["timings"]
-        except:
-            raise ValueError(errmsg)
+        except Exception as e:
+            raise ValueError(errmsg) from e
 
         # remove known keys not relevant to profiling
         for unwanted_key in ("payu_start_time", "payu_finish_time"):

src/access/profiling/um_parser.py

@@ -34,10 +34,10 @@
 
 """
 
-from access.profiling.parser import ProfilingParser, _convert_from_string
-
-import re
 import logging
+import re
+
+from access.profiling.parser import ProfilingParser, _convert_from_string
 
 logger = logging.getLogger(__name__)
 

tests/test_cice5_profiling.py

@@ -85,9 +85,9 @@ def test_cice5_profiling(cice5_required_metrics, cice5_parser, cice5_log_file, c
     for idx, region in enumerate(cice5_profiling["region"]):
         assert region in parsed_log["region"], f"{region} not found in CICE5 parsed log"
         for metric in cice5_required_metrics:
-            assert (
-                cice5_profiling[metric][idx] == parsed_log[metric][idx]
-            ), f"Incorrect {metric} for region {region} (idx: {idx})."
+            assert cice5_profiling[metric][idx] == parsed_log[metric][idx], (
+                f"Incorrect {metric} for region {region} (idx: {idx})."
+            )
 
 
 def test_cice5_incorrect_profiling(cice5_parser, cice5_incorrect_log_file):

tests/test_fms_parser.py

@@ -46,16 +46,16 @@ def fms_nohits_log_file():
 
 Tabulating mpp_clock statistics across     49 PEs...
 
-                                          tmin          tmax          tavg          tstd  tfrac grain pemin pemax
-Total runtime                     16282.797785  16282.797792  16282.797789      0.000001  1.000     0     0    48
-Ocean                             15969.542784  16000.704550  15986.765795      8.643639  0.982     1     0    48
-(Ocean initialization)                4.288529      4.296586      4.291991      0.001470  0.000    11     0    48
-(Ocean ODA)                           0.000000      0.000000      0.000000      0.000000  0.000    11     0    48
-(Red Sea/Gulf Bay salinity fix)       0.024143      0.077235      0.040902      0.013836  0.000    31     0    48
-OASIS init                            0.231678      0.232671      0.232397      0.000242  0.000     1     0    48
-oasis_recv                          168.797136    171.648384    170.460762      0.650894  0.010    31     0    48
-oasis_send                            2.468914      2.756777      2.593809      0.079459  0.000    31     0    48
- MPP_STACK high water mark=           0
+                                         tmin          tmax          tavg          tstd  tfrac grain pemin pemax
+Total runtime                    16282.797785  16282.797792  16282.797789      0.000001  1.000     0     0    48
+Ocean                            15969.542784  16000.704550  15986.765795      8.643639  0.982     1     0    48
+(Ocean initialization)               4.288529      4.296586      4.291991      0.001470  0.000    11     0    48
+(Ocean ODA)                          0.000000      0.000000      0.000000      0.000000  0.000    11     0    48
+(Red Sea/Gulf Bay salinity fix)      0.024143      0.077235      0.040902      0.013836  0.000    31     0    48
+OASIS init                           0.231678      0.232671      0.232397      0.000242  0.000     1     0    48
+oasis_recv                         168.797136    171.648384    170.460762      0.650894  0.010    31     0    48
+oasis_send                           2.468914      2.756777      2.593809      0.079459  0.000    31     0    48
+ MPP_STACK high water mark=          0
  MOM5: --- completed ---
 """
 
@@ -128,19 +128,19 @@ def fms_hits_log_file():
 
 Tabulating mpp_clock statistics across      1 PEs...
 
-                                      hits          tmin          tmax          tavg          tstd  tfrac grain pemin pemax
-Total runtime                            1    100.641190    100.641190    100.641190      0.000000  1.000     0     0     0
-Initialization                           1      0.987726      0.987726      0.987726      0.000000  0.010     0     0     0
-Main loop                                1     98.930085     98.930085     98.930085      0.000000  0.983     0     0     0
-Termination                              1      0.718969      0.718969      0.718969      0.000000  0.007     0     0     0
-Ocean Initialization                     2      1.529830      1.529830      1.529830      0.000000  0.015    11     0     0
-Ocean                                   24     98.279247     98.279247     98.279247      0.000000  0.977     1     0     0
-Ocean dynamics                         192     84.799971     84.799971     84.799971      0.000000  0.843    11     0     0
-Ocean thermodynamics and tracers        72     11.512013     11.512013     11.512013      0.000000  0.114    11     0     0
-Ocean grid generation and remapp         0      0.000000      0.000000      0.000000      0.000000  0.000    11     0     0
-Ocean Other                            192      1.710326      1.710326      1.710326      0.000000  0.017    11     0     0
-(Ocean tracer advection)                48      4.427230      4.427230      4.427230      0.000000  0.044    21     0     0
- MPP_STACK high water mark=           0
+                                   hits          tmin          tmax          tavg          tstd  tfrac grain pemin pemax
+Total runtime                         1    100.641190    100.641190    100.641190      0.000000  1.000     0     0     0
+Initialization                        1      0.987726      0.987726      0.987726      0.000000  0.010     0     0     0
+Main loop                             1     98.930085     98.930085     98.930085      0.000000  0.983     0     0     0
+Termination                           1      0.718969      0.718969      0.718969      0.000000  0.007     0     0     0
+Ocean Initialization                  2      1.529830      1.529830      1.529830      0.000000  0.015    11     0     0
+Ocean                                24     98.279247     98.279247     98.279247      0.000000  0.977     1     0     0
+Ocean dynamics                      192     84.799971     84.799971     84.799971      0.000000  0.843    11     0     0
+Ocean thermodynamics and tracers     72     11.512013     11.512013     11.512013      0.000000  0.114    11     0     0
+Ocean grid generation and remapp      0      0.000000      0.000000      0.000000      0.000000  0.000    11     0     0
+Ocean Other                         192      1.710326      1.710326      1.710326      0.000000  0.017    11     0     0
+(Ocean tracer advection)             48      4.427230      4.427230      4.427230      0.000000  0.044    21     0     0
+ MPP_STACK high water mark=          0
 """
 
 
@@ -151,8 +151,8 @@ def fms_incorrect_log_file():
 
 Tabulating mpp_clock statistics across      1 PEs...
 
-                                      hits                        tmax          tavg          tstd  tfrac grain pemin pemax
-Total runtime                            1    100.641190    100.641190    100.641190      0.000000  1.000     0     0     0
+                                   hits                        tmax          tavg          tstd  tfrac grain pemin pemax
+Total runtime                         1    100.641190    100.641190    100.641190      0.000000  1.000     0     0     0
 high water mark=           0
 """
 
@@ -163,9 +163,9 @@ def test_fms_nohits_profiling(fms_nohits_parser, fms_nohits_log_file, fms_nohits
     for idx, region in enumerate(fms_nohits_profiling.keys()):
         assert region in parsed_log, f"{region} not found in mom5 parsed log"
         for metric in ("tmin", "tmax", "tavg", "tstd"):
-            assert (
-                fms_nohits_profiling[metric][idx] == parsed_log[metric][idx]
-            ), f"Incorrect {metric} for region {region} (idx: {idx})."
+            assert fms_nohits_profiling[metric][idx] == parsed_log[metric][idx], (
+                f"Incorrect {metric} for region {region} (idx: {idx})."
+            )
 
 
 def test_fms_hits_profiling(fms_hits_parser, fms_hits_log_file, fms_hits_profiling):
@@ -174,9 +174,9 @@ def test_fms_hits_profiling(fms_hits_parser, fms_hits_log_file, fms_hits_profili
     for idx, region in enumerate(fms_hits_profiling.keys()):
         assert region in parsed_log, f"{region} not found in mom6 parsed log"
         for metric in ("hits", "tmin", "tmax", "tavg", "tstd"):
-            assert (
-                fms_hits_profiling[metric][idx] == parsed_log[metric][idx]
-            ), f"Incorrect {metric} for region {region} (idx: {idx})."
+            assert fms_hits_profiling[metric][idx] == parsed_log[metric][idx], (
+                f"Incorrect {metric} for region {region} (idx: {idx})."
+            )
 
 
 def test_fms_incorrect_profiling(fms_hits_parser, fms_incorrect_log_file):

tests/test_parser.py

@@ -55,13 +55,13 @@ def test_base_parser(profiling_data):
 def test_str2num():
     """Tests conversion of numbers to most appropriate type."""
     str2int = _convert_from_string("42")
-    assert type(str2int) == int
+    assert type(str2int) is int
     assert str2int == 42
     str2float = _convert_from_string("-1.23")
-    assert type(str2float) == float
+    assert type(str2float) is float
     assert str2float == -1.23
     str2float = _convert_from_string("0.00000")
     assert str2float == 0.0
     str2str = _convert_from_string("somestr")
-    assert type(str2str) == str
+    assert type(str2str) is str
     assert str2str == "somestr"

tests/test_payujson_parser.py

@@ -57,9 +57,9 @@ def test_payujson_profiling(payujson_parser, payujson_log_file, payujson_profili
     parsed_log = payujson_parser.read(payujson_log_file)
     for idx, region in enumerate(payujson_profiling.keys()):
         assert region in parsed_log, f"{region} not found in Payu JSON parsed log."
-        assert (
-            payujson_profiling["walltime"][idx] == parsed_log["walltime"][idx]
-        ), f"Incorrect walltime for region {region} (idx: {idx})."
+        assert payujson_profiling["walltime"][idx] == parsed_log["walltime"][idx], (
+            f"Incorrect walltime for region {region} (idx: {idx})."
+        )
 
 
 def test_payujson_incorrect_profiling(payujson_parser):