Enable simple region checking for cli (#664)

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

data/catalogs/deltares_data.yml

@@ -761,7 +761,7 @@ ghs_pop_2015_4326_v2019a:
   path: socio_economic/ghs/GHS_POP_E2015_GLOBE_R2019A_4326_9ss_V1_0.tif
 
 ghs_pop_2015_54009_v2019a:
-  crs: 54009
+  crs: "ESRI:54009"
   data_type: RasterDataset
   driver: raster
   kwargs:
@@ -779,7 +779,7 @@ ghs_pop_2015_54009_v2019a:
 ghs_smod:
   alias: ghs_smod_2015_54009_v2019a
 ghs_smod_2015_54009_v2016a:
-  crs: 54009
+  crs: "ESRI:54009"
   data_type: RasterDataset
   driver: raster
   kwargs:
@@ -796,7 +796,7 @@ ghs_smod_2015_54009_v2016a:
   path: socio_economic/ghs/GHS_SMOD_POP2015_GLOBE_R2016A_54009_1k_v1_0.tif
 
 ghs_smod_2015_54009_v2019a:
-  crs: 54009
+  crs: "ESRI:54009"
   data_type: RasterDataset
   driver: raster
   kwargs:

docs/changelog.rst

@@ -15,6 +15,7 @@ Added
 -----
 - Export CLI now also accepts time tuples (#660)
 - New stats.skills VE and RSR (#666)
+- Check CLI command can now validate bbox and geom regions (#664)
 
 Changed
 -------

docs/user_guide/data_overview.rst

@@ -77,7 +77,9 @@ However, we do plan to expand its functionality over time. It can be use for exa
 
 .. code-block:: console
 
-    hydromt check grid -d /path/to/data_catalog.yml -i /path/to/model_config.yml
+    hydromt check grid -d /path/to/data_catalog.yml -i /path/to/model_config.yml -r '{'bbox': [-1,-1,1,1]}'
+
+currently only `bbox` and `geom` variants of regions are supported in validation. Also note that the geom variant will only check whether the file exists not its contents. We also plan to expand this functionality in the future.
 
 .. _get_data_python:
 

hydromt/cli/main.py

@@ -16,7 +16,8 @@
 
 from hydromt.data_catalog import DataCatalog
 from hydromt.validators.data_catalog import DataCatalogValidator
-from hydromt.validators.model_config import HydromtModelStep
+from hydromt.validators.model_config import HydromtModelSetup
+from hydromt.validators.region import validate_region
 
 from .. import __version__, log
 from ..models import MODELS
@@ -332,39 +333,51 @@ def update(
 
 
 @main.command(
-    short_help="Validate config files are correct",
+    short_help="Validate config / data catalog / region",
 )
-@click.argument(
-    "MODEL",
+@click.option(
+    "-m",
+    "--model",
     type=str,
+    default=None,
+    help="Model name, e.g. wflow, sfincs, etc. to validate config file.",
 )
 @opt_config
 @data_opt
-@deltares_data_opt
 @quiet_opt
 @verbose_opt
+@region_opt
 @click.pass_context
 def check(
     ctx,
     model,
     config,
     data,
-    dd,
+    region: Optional[Dict[Any, Any]],
     quiet: int,
     verbose: int,
 ):
-    """Verify that provided data catalog files are in the correct format.
+    """
+    Verify that provided data catalog and config files are in the correct format.
+
+    Additionnaly region bbox and geom can also be validated.
 
     Example usage:
     --------------
 
-    hydromt check grid -d /path/to/data_catalog.yml -i /path/to/model_config.yml
+    Check data catalog file:
+    hydromt check -d /path/to/data_catalog.yml -v
+
+    Check data catalog and grid_model config file:
+    hydromt check -m grid_model -d /path/to/data_catalog.yml -i /path/to/model_config.yml -v
+
+    With region:
+    hydromt check -m grid_model -d /path/to/data_catalog.yml -i /path/to/model_config.yml -r '{'bbox': [-1,-1,1,1]}' -v
 
     """  # noqa: E501
     # logger
     log_level = max(10, 30 - 10 * (verbose - quiet))
     logger = log.setuplog("check", join(".", "hydromt.log"), log_level=log_level)
-    logger.info(f"Output dir: {export_dest_path}")
     try:
         all_exceptions = []
         for cat_path in data:
@@ -376,24 +389,36 @@ def check(
                 all_exceptions.append(e)
                 logger.info("Catalog has errors")
 
-        mod = MODELS.load(model)
-        try:
-            config_dict = cli_utils.parse_config(config)
-            logger.info(f"Validating config at {config}")
+        if region:
+            logger.info(f"Validating region {region}")
+            try:
+                validate_region(region)
+                logger.info("Region is valid!")
+
+            except (ValidationError, ValueError, NotImplementedError) as e:
+                logger.info("region has errors")
+                all_exceptions.append(e)
 
-            HydromtModelStep.from_dict(config_dict, model=mod)
-            logger.info("Model config valid!")
+        if config:
+            mod = MODELS.load(model)
+            logger.info(f"Validating for model {model} of type {type(mod).__name__}")
+            try:
+                config_dict = cli_utils.parse_config(config)
+                logger.info(f"Validating config at {config}")
 
-        except (ValidationError, ValueError) as e:
-            logger.info("Model has errors")
-            all_exceptions.append(e)
+                HydromtModelSetup.from_dict(config_dict, model=mod)
+                logger.info("Model config valid!")
+
+            except (ValidationError, ValueError) as e:
+                logger.info("Model has errors")
+                all_exceptions.append(e)
 
         if len(all_exceptions) > 0:
-            raise Exception(all_exceptions)
+            raise ValueError(all_exceptions)
 
     except Exception as e:
         logger.exception(e)  # catch and log errors
-        raise
+        raise e
     finally:
         for handler in logger.handlers[:]:
             handler.close()

hydromt/validators/__init__.py

@@ -6,23 +6,11 @@
     DataCatalogMetaData,
     DataCatalogValidator,
 )
-from .model_config import HydromtModelStep
+from .model_config import HydromtModelSetup, HydromtModelStep
 from .region import (
-    BoundingBoxBasinRegion,
-    BoundingBoxInterBasinRegion,
     BoundingBoxRegion,
-    BoundingBoxSubBasinRegion,
-    GeometryBasinRegion,
-    GeometryInterBasinRegion,
-    GeometryRegion,
-    GeometrySubBasinRegion,
-    GridRegion,
-    MeshRegion,
-    MultiPointBasinRegion,
-    MultiPointSubBasinRegion,
-    PointBasinRegion,
-    PointSubBasinRegion,
-    WGS84Point,
+    PathRegion,
+    Region,
     validate_region,
 )
 
@@ -31,21 +19,10 @@
     "DataCatalogItemMetadata",
     "DataCatalogMetaData",
     "DataCatalogValidator",
-    "BoundingBoxBasinRegion",
-    "BoundingBoxInterBasinRegion",
     "BoundingBoxRegion",
-    "BoundingBoxSubBasinRegion",
-    "GeometryBasinRegion",
-    "GeometryInterBasinRegion",
-    "GeometryRegion",
-    "GeometrySubBasinRegion",
-    "GridRegion",
-    "MeshRegion",
-    "MultiPointBasinRegion",
-    "MultiPointSubBasinRegion",
-    "PointBasinRegion",
-    "PointSubBasinRegion",
-    "WGS84Point",
+    "PathRegion",
+    "Region",
     "validate_region",
     "HydromtModelStep",
+    "HydromtModelSetup",
 ]

hydromt/validators/data_catalog.py

@@ -1,10 +1,12 @@
 """Pydantic models for the validation of Data catalogs."""
 from pathlib import Path
-from typing import Any, Dict, Optional, Union
+from typing import Any, Dict, List, Literal, Optional, Union
 
-from pydantic import AnyUrl, BaseModel, ConfigDict
+from pydantic import AnyUrl, BaseModel, ConfigDict, model_validator
 from pydantic.fields import Field
 from pydantic_core import Url
+from pyproj import CRS
+from pyproj.exceptions import CRSError
 
 from hydromt.data_catalog import _yml_from_uri_or_path
 from hydromt.typing import Bbox, Number, TimeRange
@@ -23,6 +25,17 @@ def from_dict(input_dict):
         return SourceSpecDict(**input_dict)
 
 
+class SourceVariant(BaseModel):
+    """A variant for a data source."""
+
+    provider: Optional[Literal["local", "aws", "gcs"]] = None
+    version: Optional[Union[str, Number]] = None
+    path: Path
+    rename: Optional[Dict[str, str]] = None
+    filesystem: Optional[Literal["local", "s3", "gcs"]] = None
+    storage_options: Optional[Dict[str, Any]] = None
+
+
 class Extent(BaseModel):
     """A validation model for describing the space and time a dataset covers."""
 
@@ -34,7 +47,7 @@ class DataCatalogMetaData(BaseModel):
     """The metadata section of a Hydromt data catalog."""
 
     root: Optional[Path] = None
-    version: Optional[Union[str, int]] = None
+    version: Optional[Union[str, Number]] = None
     name: Optional[str] = None
     model_config: ConfigDict = ConfigDict(
         str_strip_whitespace=True,
@@ -81,24 +94,48 @@ class DataCatalogItem(BaseModel):
     """A validated data source."""
 
     name: str
-    data_type: str
-    driver: str
-    path: Path
-    crs: Optional[int] = None
+    data_type: Literal["RasterDataset", "GeoDataset", "GeoDataFrame", "DataFrame"]
+    driver: Literal[
+        "csv",
+        "fwf",
+        "netcdf",
+        "parquet",
+        "raster",
+        "raster_tindex",
+        "vector",
+        "vector_table",
+        "xls",
+        "xlsx",
+        "zarr",
+    ]
+    path: Optional[Path] = None
+    crs: Optional[Union[int, str]] = None
     filesystem: Optional[str] = None
     kwargs: Dict[str, Any] = Field(default_factory=dict)
     storage_options: Dict[str, Any] = Field(default_factory=dict)
+    placeholders: Optional[Dict[str, Any]] = None
     rename: Dict[str, str] = Field(default_factory=dict)
     nodata: Optional[Number] = None
     meta: Optional[DataCatalogItemMetadata] = None
     unit_add: Optional[Dict[str, Number]] = None
     unit_mult: Optional[Dict[str, Number]] = None
+    variants: Optional[List[SourceVariant]] = None
+    version: Optional[Union[str, Number]] = None
 
     model_config: ConfigDict = ConfigDict(
         str_strip_whitespace=True,
         extra="forbid",
     )
 
+    @model_validator(mode="after")
+    def _check_valid_crs(self) -> "DataCatalogItem":
+        try:
+            if self.crs:
+                _ = CRS.from_user_input(self.crs)
+        except CRSError as e:
+            raise ValueError(e)
+        return self
+
     @staticmethod
     def from_dict(input_dict, name=None):
         """Convert a dictionary into a validated source item."""

hydromt/validators/model_config.py

@@ -1,14 +1,14 @@
 """Pydantic models for the validation of model config files."""
 from inspect import Parameter, signature
-from typing import Any, Callable, Dict, Type
+from typing import Any, Callable, Dict, List, Type
 
 from pydantic import BaseModel, ConfigDict, Field
 
 from hydromt.models import Model
 
 
 class HydromtModelStep(BaseModel):
-    """A Pydantic model for the validation of model config files."""
+    """A Pydantic model for the validation of model setup functions."""
 
     model: Type[Model]
     fn: Callable
@@ -28,7 +28,9 @@ def from_dict(input_dict: Dict[str, Any], model: Model):
         try:
             fn = getattr(model, fn_name)
         except AttributeError:
-            raise ValueError(f"Model does not have function {fn_name}")
+            raise ValueError(
+                f"Model of type {model.__name__} does not have function {fn_name}"
+            )
 
         sig = signature(fn)
         sig_has_var_keyword = (
@@ -54,3 +56,19 @@ def from_dict(input_dict: Dict[str, Any], model: Model):
             )
 
         return HydromtModelStep(model=model, fn=fn, args=arg_dict)
+
+
+class HydromtModelSetup(BaseModel):
+    """A Pydantic model for the validation of model setup files."""
+
+    steps: List[HydromtModelStep]
+
+    @staticmethod
+    def from_dict(input_dict: Dict[str, Any], model: Model):
+        """Generate a validated model of a sequence steps in a model config file."""
+        return HydromtModelSetup(
+            steps=[
+                HydromtModelStep.from_dict({fn_name: fn_args}, model)
+                for fn_name, fn_args in input_dict.items()
+            ]
+        )