Merge pull request #13 from bcdev/forman-print_config_option

CLI `--print-config` option

Author: forman

.gitignore

@@ -1,5 +1,6 @@
 # xrlint
 /xrlint_config.*
+/notebooks/xrlint_config.*
 
 # Logs
 *.log

CHANGES.md

@@ -2,9 +2,12 @@
 
 ## Version 0.1.0 (in development)
 
+- Added CLI option `--print-config PATH`, see same option in ESLint
 - XRLint CLI now outputs single results immediately to console,
   instead only after all results have been collected.
-
+- Refactored and renamed `CliEngine` into `XRLint`. Documented the class.
+- `new_linter()` now uses a config name arg instead of a bool arg.
+- Split example notebook into two
 
 ## Early development snapshots
 

docs/api.md

@@ -2,6 +2,10 @@
 
 All described objects can be imported from the `xrlint.all` module.
 
+## Class `XRLint`
+
+::: xrlint.cli.engine.XRLint
+
 ## Function `new_linter()`
 
 ::: xrlint.linter.new_linter

docs/cli.md

@@ -8,28 +8,33 @@ Usage: xrlint [OPTIONS] [FILES]...
 
   Validate the given dataset FILES.
 
-  Reads configuration from `xrlint.config.*` if file exists and unless `--no-
-  default-config` is set or `--config PATH` is provided. Then validates each
-  dataset in FILES against the configuration. The validation result is dumped
-  to standard output if not otherwise stated by `--output-file PATH`. The
-  output format is `simple`. Other inbuilt formats are `json` and `html` which
-  can by setting the `--format NAME` option.
+  Reads configuration from `./xrlint_config.*` if such file exists and unless
+  `--no_config_lookup` is set or `--config` is provided. Then validates each
+  dataset in FILES against the configuration. The default dataset patters are
+  `**/*.zarr` and `**/.nc`. FILES may comprise also directories. If a
+  directory is not matched by any file pattern, it will be traversed
+  recursively. The validation result is dumped to standard output if not
+  otherwise stated by `--output-file`. The output format is `simple` by
+  default. Other inbuilt formats are `json` and `html` which you can specify
+  using the `--format` option.
 
 Options:
-  --no-default-config     Disable use of default configuration from
+  --no-config-lookup      Disable use of default configuration from
                           xrlint_config.*
-  -c, --config PATH       Use this configuration, overriding xrlint_config.*
+  -c, --config FILE       Use this configuration, overriding xrlint_config.*
                           config options if present
+  --print-config FILE     Print the configuration for the given file
   --plugin MODULE         Specify plugins. MODULE is the name of Python module
                           that defines an 'export_plugin()' function.
   --rule SPEC             Specify rules. SPEC must have format '<rule-name>:
                           <rule-config>' (note the space character).
-  -o, --output-file PATH  Specify file to write report to
+  -o, --output-file FILE  Specify file to write report to
   -f, --format NAME       Use a specific output format - default: simple
   --color / --no-color    Force enabling/disabling of color
   --max-warnings COUNT    Number of warnings to trigger nonzero exit code -
                           default: 5
   --init                  Write initial configuration file and exit.
   --version               Show the version and exit.
   --help                  Show this message and exit.
+
 ```

docs/start.md

@@ -105,6 +105,6 @@ import xrlint.all as xrl
 
 test_ds = xr.Dataset(attrs={"title": "Test Dataset"})
 
-linter = xrl.new_linter(recommended=True)
+linter = xrl.new_linter("recommended")
 linter.verify_dataset(test_ds)
 ```

docs/todo.md

@@ -13,16 +13,11 @@
 - project logo
 - if configuration for given FILE is empty,
   report an error, see TODO in CLI main tests
-- rename `xrlint.cli.CliEngine` into `xrlint.cli.XRLint`
-  (with similar API as the `ESLint` class) and export it 
-  from `xrlint.all`. Value of `FILES` should be passed to
-  `verify_datasets()` methods.
 - use `RuleMeta.docs_url` in formatters to create links
 - implement xarray backend for xcube 'levels' format
   so can validate them too
 - add some more tests so we reach 99% coverage
 - support rule op args/kwargs schema validation
-- support CLI option `--print-config FILE`, see ESLint
 - Support `RuleTest.expected`, it is currently unused
 
 ## Nice to have

notebooks/mkdataset.py

@@ -0,0 +1,64 @@
+import numpy as np
+import xarray as xr
+
+nx = 2
+ny = 3
+nt = 4
+
+
+def make_dataset() -> xr.Dataset:
+    """Create a dataset that passes xrlint core rules."""
+    
+    return xr.Dataset(
+        attrs=dict(title="SST-Climatology Subset"),
+        coords={
+            "x": xr.DataArray(
+                np.linspace(-180, 180, nx),
+                dims="x", 
+                attrs={"units": "degrees"}
+            ),
+            "y": xr.DataArray(
+                np.linspace(-90, 90, ny),
+                dims="y", 
+                attrs={"units": "degrees"}
+            ),
+            "time": xr.DataArray(
+                [2010 + y for y in range(nt)], 
+                dims="time", 
+                attrs={"units": "years"}
+            ),
+            "spatial_ref": xr.DataArray(
+                0,
+                attrs={
+                    "grid_mapping_name": "latitude_longitude",
+                    "semi_major_axis": 6371000.0,
+                    "inverse_flattening": 0,
+                },
+            ),
+        },
+        data_vars={
+            "sst": xr.DataArray(
+                np.random.random((nt, ny, nx)), 
+                dims=["time", "y", "x"], 
+                attrs={"units": "kelvin", "grid_mapping": "spatial_ref"}
+            ),
+            "sst_anomaly": xr.DataArray(
+                np.random.random((nt, ny, nx)), 
+                dims=["time", "y", "x"], 
+                attrs={"units": "kelvin", "grid_mapping": "spatial_ref"}
+            )
+        },
+    )
+
+
+def make_dataset_with_issues() -> xr.Dataset:    
+    """Create a dataset that produces issues with xrlint core rules."""
+    invalid_ds = make_dataset()
+    invalid_ds.attrs = {}
+    invalid_ds.sst.attrs["units"] = 1
+    invalid_ds["sst_avg"] = xr.DataArray(
+        np.random.random((nx, ny)), 
+        dims=["x", "y"], 
+        attrs={"units": "kelvin"}
+    )
+    return invalid_ds