Fixed test data, fixed filename regexp

src/access_nri_intake/source/builders.py

@@ -162,10 +162,15 @@ def validate_parser(self):
                 "asset list provided is None. Please run `.get_assets()` first"
             )
 
+        i = 0
+        j = 0
         for asset in self.assets:
+            # import pdb; pdb.set_trace()
             info = self.parser(asset)
+            i += 1
             if INVALID_ASSET not in info:
                 validate_against_schema(info, ESM_JSONSCHEMA)
+                j += 1
                 return self
 
         raise ParserError(
@@ -519,12 +524,12 @@ class AccessOm4Builder(BaseBuilder):
     """Intake-ESM datastore builder for ACCESS-OM4 COSIMA datasets"""
 
     PATTERNS = [
-        rf"[^\.]*\.{PATTERNS_HELPERS['ymd-ns']}\..*({PATTERNS_HELPERS['om4_components']}).*$",  # ACCESS-OM3
+        rf"[^\.]*({PATTERNS_HELPERS['ymd-ns']})\.{PATTERNS_HELPERS['om4_components']}.*$",  # ACCESS-OM4
     ]
 
     def __init__(self, path):
         """
-        Initialise a AccessOm3Builder
+        Initialise a AccessOm4Builder
 
         Parameters
         ----------
@@ -534,7 +539,7 @@ def __init__(self, path):
 
         kwargs = dict(
             path=path,
-            depth=2,
+            depth=1,
             exclude_patterns=[
                 "*restart*",
                 "*MOM_IC.nc",
@@ -577,11 +582,11 @@ def parser(cls, file):
                 variable_units_list,
             ) = cls.parse_access_ncfile(file)
 
-            if "mom6" in filename:
+            if "ocean" in filename:
                 realm = "ocean"
-            elif "ww3" in filename:
-                realm = "wave"
-            elif "cice" in filename:
+            # elif "ww3" in filename:
+            #     realm = "wave"
+            elif "ice" in filename:
                 realm = "seaIce"
             else:
                 raise ParserError(f"Cannot determine realm for file {file}")

tests/data/access-om4/README

@@ -0,0 +1,39 @@
+Generated using the following Python on NCI ARE:
+
+```
+import netCDF4
+import glob
+import os
+
+srcdir = "/g/data/ik11/outputs/mom6-om4-025/OM4_025.JRA_RYF/"
+destdir = "/home/120/mcw120/scratch/"
+
+targets = ["output000", "output001"]
+target_glob = "190*.nc"
+
+for target in targets:
+    srcglob = os.path.join(srcdir, target, target_glob)
+    srcfns = [os.path.basename(_) for _ in glob.glob(srcglob)]
+    for srcfn in srcfns:
+        with netCDF4.Dataset(os.path.join(srcdir, target, srcfn), "r") as old, netCDF4.Dataset(os.path.join(destdir, target, srcfn), "w") as new:
+            print(old.filepath())
+            print(new.filepath())
+            new.setncattr("file_format", old.file_format)
+            new.setncatts(old.__dict__)
+            # new.set_fill_off()
+            for name, dimension in old.dimensions.items():
+                if name == "nv":
+                        dimn = 2
+                elif not dimension.isunlimited():
+                    dimn = 1
+                else:
+                    dimn = dimension.size
+                new.createDimension(name, dimn)
+            for name, variable in old.variables.items():
+                x = new.createVariable(name, variable.datatype, variable.dimensions)
+                new[name].setncatts(old[name].__dict__)
+                if name == "time" or name == "nv":  # Need time-related data only
+                    new[name][:] = old[name][:]
+            print(">> Complete!")
+            print("--")
+```