Use pint instead of cf_units

compliance_checker/cfutil.py

@@ -8,9 +8,10 @@
 from collections import defaultdict
 from functools import lru_cache, partial
 
-from cf_units import Unit
 from importlib_resources import files
 
+from compliance_checker.units import UndefinedUnitError, units
+
 _UNITLESS_DB = None
 _SEA_NAMES = None
 
@@ -111,8 +112,8 @@ def is_dimensionless_standard_name(standard_name_table, standard_name):
  f".//entry[@id='{standard_name}']",
  )
  if found_standard_name is not None:
- canonical_units = Unit(found_standard_name.find("canonical_units").text)
- return canonical_units.is_dimensionless()
+ canonical_units = units(found_standard_name.find("canonical_units").text)
+ return canonical_units.dimensionless
  # if the standard name is not found, assume we need units for the time being
  else:
  return False
@@ -2037,8 +2038,8 @@ def units_convertible(units1, units2, reftimeistime=True):
  :param str units2: A string representing the units
  """
  try:
- u1 = Unit(units1)
- u2 = Unit(units2)
- except ValueError:
+ u1 = units(units1)
+ u2 = units(units2)
+ except UndefinedUnitError:
  return False
- return u1.is_convertible(u2)
+ return u1.is_compatible_with(u2)

compliance_checker/tests/test_cf.py

@@ -1211,6 +1211,7 @@ def test_dimensionless_vertical(self):
  # Check negative compliance -- 3 out of 4 pass
 
  dataset = self.load_dataset(STATIC_FILES["bad"])
+ print(f"{STATIC_FILES["bad"]=}")
  results = self.cf.check_dimensionless_vertical_coordinates(dataset)
  scored, out_of, messages = get_results(results)
  assert len(results) == 4

compliance_checker/units.py

@@ -0,0 +1,124 @@
+"""Module to provide unit support via pint approximating UDUNITS/CF."""
+
+import functools
+import re
+
+import pint
+from pint import ( # noqa: F401
+ DimensionalityError,
+ UndefinedUnitError,
+ UnitStrippedWarning,
+)
+
+# from `xclim`'s unit support module with permission of the maintainers
+try:
+
+ @pint.register_unit_format("cf")
+ def short_formatter(unit, registry, **options):
+ """Return a CF-compliant unit string from a `pint` unit.
+
+ Parameters
+ ----------
+ unit : pint.UnitContainer
+ Input unit.
+ registry : pint.UnitRegistry
+ the associated registry
+ **options
+ Additional options (may be ignored)
+
+ Returns
+ -------
+ out : str
+ Units following CF-Convention, using symbols.
+ """
+ import re
+
+ # convert UnitContainer back to Unit
+ unit = registry.Unit(unit)
+ # Print units using abbreviations (millimeter -> mm)
+ s = f"{unit:~D}"
+
+ # Search and replace patterns
+ pat = r"(?P<inverse>(?:1 )?/ )?(?P<unit>\w+)(?: \*\* (?P<pow>\d))?"
+
+ def repl(m):
+ i, u, p = m.groups()
+ p = p or (1 if i else "")
+ neg = "-" if i else ""
+
+ return f"{u}{neg}{p}"
+
+ out, n = re.subn(pat, repl, s)
+
+ # Remove multiplications
+ out = out.replace(" * ", " ")
+ # Delta degrees:
+ out = out.replace("Δ°", "delta_deg")
+ return out.replace("percent", "%")
+
+except ImportError:
+ pass
+
+# ------
+# Reused with modification from MetPy under the terms of the BSD 3-Clause License.
+# Copyright (c) 2015,2017,2019 MetPy Developers.
+# Create registry, with preprocessors for UDUNITS-style powers (m2 s-2) and percent signs
+units = pint.UnitRegistry(
+ autoconvert_offset_to_baseunit=True,
+ preprocessors=[
+ lambda x: (
+ "count" if x == "1" else x
+ ), # Should be salinity as well but all we can is that it is integer and dimensionless
+ lambda x: "S_K" if x.lower() in ["0.001", "1e-3"] else x,
+ functools.partial(
+ re.compile(
+ r"(?<=[A-Za-z])(?![A-Za-z])(?<![0-9\-][eE])(?<![0-9\-])(?=[0-9\-])",
+ ).sub,
+ "**",
+ ),
+ lambda string: string.replace("%", "percent"),
+ ],
+ force_ndarray_like=True,
+)
+# ----- end block copied from metpy
+
+# need to insert to make sure this is the first preprocessor
+# This ensures we convert integer `1` to string `"1"`, as needed by pint.
+units.preprocessors.insert(0, str)
+
+# -----
+units.define("percent = 0.01 = %")
+
+# Define commonly encountered units (both CF and non-CF) not defined by pint
+units.define("@alias meter = gpm")
+# ----- end block copied from metpy
+
+# -----
+# The following redefinitions were copied from xclim under the terms of their Apache-2 license
+# In pint, the default symbol for year is "a" which is not CF-compliant (stands for "are")
+units.define("year = 365.25 * day = yr")
+
+# Define commonly encountered units not defined by pint
+units.define("@alias degC = C = deg_C = Celsius = degrees_Celsius")
+units.define("@alias degK = deg_K")
+units.define("@alias day = d")
+units.define("@alias hour = h") # Not the Planck constant...
+units.define(
+ "degrees_north = degree = degrees_north = degrees_N = degreesN = degree_north = degree_N = Degrees_N = degreeN",
+)
+units.define(
+ "degrees_east = degree = degrees_east = degrees_E = degreesE = degree_east = degree_E = Degrees_E = degreeE",
+)
+# degrees for grid_longitude / grid_latitude for grid_mappings
+units.define("degrees = degree = degrees")
+units.define("[speed] = [length] / [time]")
+# ----- end block copied from xclim
+
+# Add other specific aliases (by cf_xarray developers)
+units.define("practical_salinity_unit = [] = psu = PSU")
+units.define("parts_per_thousand = 0.001 = sea_water_knudsen_salinity = S_K")
+
+# end of vendored code from MetPy
+
+# Set as application registry
+pint.set_application_registry(units)

requirements.txt

@@ -9,6 +9,7 @@ netcdf4>=1.6.4
 owslib>=0.8.3
 packaging
 pendulum>=1.2.4
+pint
 pygeoif>=0.6
 pyproj>=2.2.1
 regex>=2017.07.28