Update to cell_method parsing (#6083)

* Provided error message for malformed `cell_method` attribute

* Made `cell_method` pattern matching more lenient w.r.t. space after colon separator

* Changed `cell_methods` regex slightly to fix failures in unit tests.
Also added new unit test to check cell_methods with:
  1. Name only (no colon and method)
  2. Not space between colon separator and method.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Added WhatsNew entry

* Update docs/src/whatsnew/latest.rst

Co-authored-by: Elias <[email protected]>

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Martin Yeo <[email protected]>
Co-authored-by: Elias <[email protected]>

docs/src/whatsnew/latest.rst

@@ -52,6 +52,9 @@ This document explains the changes made to Iris for this release
 #. `@rcomer`_ enabled partial collapse of multi-dimensional string coordinates,
    fixing :issue:`3653`. (:pull:`5955`)
 
+#. `@ukmo-ccbunney`_ improved error handling for malformed `cell_method`
+   attribute. Also made cell_method string parsing more lenient w.r.t.
+   whitespace. (:pull:`6083`)
 
 💣 Incompatible Changes
 =======================

lib/iris/fileformats/_nc_load_rules/helpers.py

@@ -202,11 +202,11 @@
 _CM_INTERVAL = "interval"
 _CM_METHOD = "method"
 _CM_NAME = "name"
-_CM_PARSE_NAME = re.compile(r"([\w_]+\s*?:\s+)+")
+_CM_PARSE_NAME = re.compile(r"([\w_]+\s*?:\s*)+")
 _CM_PARSE = re.compile(
     r"""
-                           (?P<name>([\w_]+\s*?:\s+)+)
-                           (?P<method>[\w_\s]+(?![\w_]*\s*?:))\s*
+                           (?P<name>([\w_]+\s*?:\s*)+)
+                           (?P<method>[^\s][\w_\s]+(?![\w_]*\s*?:))\s*
                            (?:
                                \(\s*
                                (?P<extra>.+)
@@ -296,6 +296,12 @@ def _split_cell_methods(nc_cell_methods: str) -> List[re.Match]:
     for m in _CM_PARSE_NAME.finditer(nc_cell_methods):
         name_start_inds.append(m.start())
 
+    # No matches? Must be malformed cell_method string; warn and return
+    if not name_start_inds:
+        msg = f"Failed to parse cell method string: {nc_cell_methods}"
+        warnings.warn(msg, category=iris.warnings.IrisCfLoadWarning, stacklevel=2)
+        return []
+
     # Remove those that fall inside brackets
     bracket_depth = 0
     for ind, cha in enumerate(nc_cell_methods):

lib/iris/tests/unit/fileformats/nc_load_rules/helpers/test_parse_cell_methods.py

@@ -19,6 +19,7 @@ class Test(tests.IrisTest):
     def test_simple(self):
         cell_method_strings = [
             "time: mean",
+            "time:mean",
             "time : mean",
         ]
         expected = (CellMethod(method="mean", coords="time"),)
@@ -125,6 +126,7 @@ def test_badly_formatted_warning(self):
         cell_method_strings = [
             # "time: maximum (interval: 1 hr comment: first bit "
             # "time: mean (interval: 1 day comment: second bit)",
+            "time",
             "time: (interval: 1 hr comment: first bit) "
             "time: mean (interval: 1 day comment: second bit)",
             "time: maximum (interval: 1 hr comment: first bit) "