mlcast-dataset-validator 0.1.0__py3-none-any.whl → 0.2.0__py3-none-any.whl

mlcast_dataset_validator/checks/coords/names.py

@@ -2,8 +2,7 @@ from typing import Dict, List, Sequence
 
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from . import SECTION_ID as PARENT_SECTION_ID
 
 SECTION_ID = f"{PARENT_SECTION_ID}.1"

mlcast_dataset_validator/checks/coords/spatial.py

@@ -1,7 +1,6 @@
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from . import SECTION_ID as PARENT_SECTION_ID
 
 SECTION_ID = f"{PARENT_SECTION_ID}.2"

mlcast_dataset_validator/checks/coords/temporal.py

@@ -5,8 +5,7 @@ import numpy as np
 import pandas as pd
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from . import SECTION_ID as PARENT_SECTION_ID
 
 SECTION_ID = f"{PARENT_SECTION_ID}.3"

mlcast_dataset_validator/checks/data_vars/chunking.py

@@ -1,7 +1,6 @@
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from ..data_vars_filter import iter_data_vars
 from . import SECTION_ID as PARENT_SECTION_ID
 

mlcast_dataset_validator/checks/data_vars/compression.py

@@ -2,8 +2,7 @@ from typing import Sequence
 
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from . import SECTION_ID as PARENT_SECTION_ID
 
 SECTION_ID = f"{PARENT_SECTION_ID}.2"

mlcast_dataset_validator/checks/data_vars/data_structure.py

@@ -2,8 +2,7 @@ from typing import Sequence
 
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from . import SECTION_ID as PARENT_SECTION_ID
 
 SECTION_ID = f"{PARENT_SECTION_ID}.3"

mlcast_dataset_validator/checks/data_vars/data_variable.py

@@ -2,8 +2,7 @@ from typing import Dict, Sequence
 
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from . import SECTION_ID as PARENT_SECTION_ID
 
 SECTION_ID = f"{PARENT_SECTION_ID}.4"

mlcast_dataset_validator/checks/data_vars/georeferencing.py

@@ -2,8 +2,7 @@ from typing import Sequence
 
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from . import SECTION_ID as PARENT_SECTION_ID
 
 SECTION_ID = f"{PARENT_SECTION_ID}.5"

mlcast_dataset_validator/checks/data_vars/naming.py

@@ -4,8 +4,7 @@ from typing import Dict, Iterable
 
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from ..data_vars_filter import iter_data_vars
 from . import SECTION_ID as PARENT_SECTION_ID
 

mlcast_dataset_validator/checks/global_attributes/conditional.py

@@ -2,8 +2,7 @@ from typing import Sequence
 
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from ..coords.temporal import analyze_dataset_timesteps
 from . import SECTION_ID as PARENT_SECTION_ID
 

mlcast_dataset_validator/checks/global_attributes/licensing.py

@@ -4,8 +4,7 @@ from typing import Iterable
 import xarray as xr
 from license_expression import ExpressionError, get_spdx_licensing
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from . import SECTION_ID as PARENT_SECTION_ID
 
 SECTION_ID = f"{PARENT_SECTION_ID}.2"

mlcast_dataset_validator/checks/global_attributes/mlcast_metadata.py

@@ -12,7 +12,7 @@ from packaging.version import parse as parse_version
 from parse import compile as parse_compile
 from requests import RequestException
 
-from ...specs.base import ValidationReport
+from ...specs.reporting import ValidationReport
 from ...utils.logging_decorator import log_function_call
 from . import SECTION_ID as PARENT_SECTION_ID
 

mlcast_dataset_validator/checks/global_attributes/zarr_format.py

@@ -3,8 +3,7 @@ from typing import Sequence
 import fsspec
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from . import SECTION_ID as PARENT_SECTION_ID
 
 SECTION_ID = f"{PARENT_SECTION_ID}.3"
@@ -53,6 +52,9 @@ def check_zarr_format(
     """Check Zarr format requirements."""
     report = ValidationReport()
 
+    if storage_options is None:
+        storage_options = ds.encoding.get("storage_options")
+
     zarr_format = getattr(ds, "zarr_format", 2)  # Default to Zarr v2
     if zarr_format in allowed_versions:
         report.add(

mlcast_dataset_validator/checks/tool_compatibility/cartopy.py

@@ -10,8 +10,7 @@ from typing import Optional
 import numpy as np
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from ..data_vars_filter import select_data_var
 from . import SECTION_ID as PARENT_SECTION_ID
 

mlcast_dataset_validator/checks/tool_compatibility/gdal.py

@@ -11,8 +11,7 @@ from typing import Dict, Optional
 
 import xarray as xr
 
-from ...specs.base import ValidationReport
-from ...utils.logging_decorator import log_function_call
+from ...specs.reporting import ValidationReport, log_function_call
 from ..data_vars_filter import select_data_var
 from . import SECTION_ID as PARENT_SECTION_ID
 

mlcast_dataset_validator/specs/cli.py

@@ -8,9 +8,11 @@ import pkgutil
 import sys
 from typing import Dict, List, Sequence
 
+import xarray as xr
 from loguru import logger
 
 from .. import __version__
+from .reporting import skip_all_checks
 
 SPEC_PACKAGE = "mlcast_dataset_validator.specs"
 
@@ -96,6 +98,14 @@ def build_parser(catalog: Dict[str, List[str]]) -> argparse.ArgumentParser:
         action="store_true",
         help="List available data_stage/product combinations and exit.",
     )
+    parser.add_argument(
+        "--print-spec-markdown",
+        action="store_true",
+        help=(
+            "Print the selected specification as Markdown without running validation checks. "
+            "Requires data_stage and product, dataset_path is optional."
+        ),
+    )
     parser.epilog = "Available combinations:\n" + _format_catalog(catalog)
     return parser
 
@@ -134,7 +144,12 @@ def main(argv: Sequence[str] | None = None) -> int:
             print(f"  - {product}")
         return 0
 
-    if not (args.data_stage and args.product and args.dataset_path):
+    if args.print_spec_markdown:
+        if not (args.data_stage and args.product):
+            parser.error(
+                "--print-spec-markdown requires a data_stage and product to select the specification."
+            )
+    elif not (args.data_stage and args.product and args.dataset_path):
         parser.print_help()
         return 1
 
@@ -164,9 +179,25 @@ def main(argv: Sequence[str] | None = None) -> int:
         f"{__version__})"
     )
 
-    report = module.validate_dataset(
-        args.dataset_path, storage_options=storage_options or None
-    )
+    if args.print_spec_markdown:
+        with skip_all_checks():
+            _, spec_text = module.validate_dataset(None)
+        if not spec_text:
+            raise SystemExit(
+                "Specification text could not be retrieved from validate_dataset()."
+            )
+        print(spec_text)
+        return 0
+    else:
+        ds = xr.open_zarr(args.dataset_path, storage_options=storage_options or None)
+        if storage_options:
+            ds.encoding.setdefault("storage_options", storage_options)
+        logger.info(
+            f"Opened dataset at {args.dataset_path}"
+            + (f" with storage options {storage_options}" if storage_options else "")
+        )
+
+    report, _ = module.validate_dataset(ds=ds)
     report.console_print()
 
     return 1 if report.has_fails() else 0

mlcast_dataset_validator/specs/{base.py → reporting.py}

@@ -1,11 +1,43 @@
 from __future__ import annotations
 
+from contextlib import ExitStack, contextmanager
 from dataclasses import dataclass, field
-from typing import List, Optional
+from functools import wraps
+from typing import Callable, Dict, List, Optional, Tuple
+from unittest import mock
 
+from loguru import logger
 from rich.console import Console
 from rich.table import Table
 
+# -------------------------
+# Logging decorator and registry
+# -------------------------
+CHECK_REGISTRY: Dict[Tuple[str, str], Callable] = {}
+
+
+def log_function_call(func):
+    """Decorator to log function calls with their arguments.
+
+    The original callable is stored in ``CHECK_REGISTRY`` so that it can be
+    monkey patched (e.g., when printing specs without running validations).
+    """
+
+    if (func.__module__, func.__name__) not in CHECK_REGISTRY:
+        CHECK_REGISTRY[(func.__module__, func.__name__)] = func
+
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        logger.info(f"Applying {func.__name__} with {kwargs}")
+        func_from_registry = CHECK_REGISTRY[(func.__module__, func.__name__)]
+        report = func_from_registry(*args, **kwargs)
+        for result in report.results:
+            result.module = func.__module__
+            result.function = func.__name__
+        return report
+
+    return wrapper
+
 
 # -------------------------
 # Data structures
@@ -89,14 +121,17 @@ class ValidationReport:
         out.results = [*self.results, *other.results]
         return out
 
-    def console_print(self) -> None:
+    def console_print(self, *, file=None) -> None:
         """
         Print all results in the validation report as a table using the rich library.
 
+        Args:
+            file: Optional file-like object to write to (defaults to stdout).
+
         Returns:
             None
         """
-        console = Console()
+        console = Console(file=file)
         table = Table(title="Validation Report")
 
         table.add_column("Section", style="bold")
@@ -144,3 +179,38 @@ class ValidationReport:
             bool: True if there is at least one WARNING result, False otherwise.
         """
         return any(r.status == "WARNING" for r in self.results)
+
+
+@contextmanager
+def skip_all_checks():
+    """Context manager to bypass check functions and dataset loading.
+
+    Assumes check functions are decorated with ``log_function_call`` which
+    records them in ``CHECK_REGISTRY``. Each registered check is monkey patched
+    to a stub returning an empty ``ValidationReport`` and dataset loading is
+    bypassed.
+    """
+
+    def _stubbed_check(*_args, **_kwargs):
+        return ValidationReport()
+
+    with ExitStack() as stack:
+        # Avoid calling into real xarray when rendering specs.
+        try:
+            stack.enter_context(mock.patch("xarray.open_zarr", lambda *a, **kw: None))
+            import xarray as xr
+
+            stack.enter_context(
+                mock.patch.object(xr, "open_zarr", lambda *a, **kw: None)
+            )
+        except ModuleNotFoundError:
+            # xarray not available in this environment; skip patching dataset load.
+            pass
+
+        stack.enter_context(
+            mock.patch.dict(
+                CHECK_REGISTRY,
+                {key: _stubbed_check for key in list(CHECK_REGISTRY.keys())},
+            )
+        )
+        yield

mlcast_dataset_validator/specs/source_data/radar_precipitation.py

@@ -7,7 +7,7 @@ against this specification. The specification text is written inline with the
 calls to checking operations that match the specification requirements.
 """
 
-from typing import Optional
+import textwrap
 
 import xarray as xr
 from loguru import logger
@@ -26,7 +26,7 @@ from ...checks.global_attributes.mlcast_metadata import check_mlcast_metadata
 from ...checks.global_attributes.zarr_format import check_zarr_format
 from ...checks.tool_compatibility.cartopy import check_cartopy_compatibility
 from ...checks.tool_compatibility.gdal import check_gdal_compatibility
-from ..base import ValidationReport
+from ..reporting import ValidationReport
 
 VERSION = "0.2.0"
 IDENTIFIER = __spec__.name.split(".")[-1]
@@ -35,12 +35,16 @@ IDENTIFIER = __spec__.name.split(".")[-1]
 # -------------------------
 # Core public API
 # -------------------------
-def validate_dataset(
-    path: str, storage_options: Optional[dict] = None
-) -> ValidationReport:
+def validate_dataset(ds: xr.Dataset) -> ValidationReport:
     """Validate a radar precipitation dataset against the MLCast specification."""
     report = ValidationReport()
-    spec_text = """
+    spec_text = f"""
+    ---
+    data_stage: source_data
+    product: {IDENTIFIER}
+    version: {VERSION}
+    ---
+
     ## 1. Introduction
 
     This document specifies the requirements for 2D radar precipitation and
@@ -59,9 +63,6 @@ def validate_dataset(
     (see inline comments below for rest of specification)
     """
 
-    # Load dataset
-    ds = xr.open_zarr(path, storage_options=storage_options)
-    logger.info(f"Opened dataset at {path}")
     logger.info(str(ds))
 
     spec_text += """
@@ -71,8 +72,8 @@ def validate_dataset(
     spec_text += """
     ### 3.1 Coordinate Variables
 
-    > "The dataset MUST expose CF-compliant coordinates: latitude/longitude and projected x/y."
-    > "Coordinate metadata MUST provide `standard_name`/`axis`/`units` per CF (with a valid `time` coordinate as well)."
+    - The dataset MUST expose CF-compliant coordinates: latitude/longitude and projected x/y.
+    - Coordinate metadata MUST provide `standard_name`/`axis`/`units` per CF (with a valid `time` coordinate as well).
     """
     report += check_coordinate_names(
         ds,
@@ -84,9 +85,9 @@ def validate_dataset(
     spec_text += """
     ### 3.2 Spatial Requirements
 
-    > "The dataset MUST provide 2D radar composites with a spatial resolution of 1 kilometer or finer."
-    > "The valid sensing area MUST support at least one 256×256 pixel square crop that is fully contained within the radar sensing range."
-    > "The spatial domain, including resolution, size, and geographical coverage, MUST remain constant across all times in the archive."
+    - The dataset MUST provide 2D radar composites with a spatial resolution of 1 kilometer or finer.
+    - The valid sensing area MUST support at least one 256×256 pixel square crop that is fully contained within the radar sensing range.
+    - The spatial domain, including resolution, size, and geographical coverage, MUST remain constant across all times in the archive.
     """
     report += check_spatial_requirements(
         ds,
@@ -98,9 +99,9 @@ def validate_dataset(
     spec_text += """
     ### 3.3 Temporal Requirements
 
-    - "The timestep (the duration between successive time values for which a single data-point is valid) MAY be variable throughout the archive, but in that case a global attribute named `consistent_timestep_start` MUST be included to indicate the first timestamp where regular timestepping begins. In the absence of this attribute, the timestep MUST be regular throughout the archive."
-    - "Times for which data is missing MUST be given expicitly in the variable `missing_times` as CF-compliant time values. The timestep is defined as the interval between consecutive times (including missing times). These times MUST NOT be included in the main time coordinate."
-    - "Time values MUST be strictly monotonically increasing."
+    - The timestep (the duration between successive time values for which a single data-point is valid) MAY be variable throughout the archive, but in that case a global attribute named `consistent_timestep_start` MUST be included to indicate the first timestamp where regular timestepping begins. In the absence of this attribute, the timestep MUST be regular throughout the archive.
+    - Times for which data is missing MUST be given expicitly in the variable `missing_times` as CF-compliant time values. The timestep is defined as the interval between consecutive times (including missing times). These times MUST NOT be included in the main time coordinate.
+    - Time values MUST be strictly monotonically increasing.
     """
     report += check_temporal_requirements(
         ds,
@@ -115,7 +116,7 @@ def validate_dataset(
     spec_text += """
     ### 4.1 Chunking Strategy
 
-    > "The dataset MUST use a chunking strategy of 1 × height × width (one chunk per timestep)."
+    - The dataset MUST use a chunking strategy of 1 × height × width (one chunk per timestep).
     """
     report += check_chunking_strategy(
         ds,
@@ -125,9 +126,9 @@ def validate_dataset(
     spec_text += """
     ### 4.2 Compression
 
-    > "The main data arrays MUST use compression to reduce storage requirements."
-    > "ZSTD compression is RECOMMENDED for optimal performance of the main data arrays."
-    > "Coordinate arrays MAY use different compression algorithms (e.g., lz4) as appropriate."
+    - The main data arrays MUST use compression to reduce storage requirements.
+    - ZSTD compression is RECOMMENDED for optimal performance of the main data arrays.
+    - Coordinate arrays MAY use different compression algorithms (e.g., lz4) as appropriate.
     """
     report += check_compression(
         ds,
@@ -139,8 +140,8 @@ def validate_dataset(
     spec_text += """
     ### 4.3 Data Structure
 
-    > "The main data variable MUST be encoded with dimensions in the order: time × height (y, lat) × width (x, lon)."
-    > "The data type MUST be floating-point (float16, float32, or float64)."
+    - The main data variable MUST be encoded with dimensions in the order: time × height (y, lat) × width (x, lon).
+    - The data type MUST be floating-point (float16, float32, or float64).
     """
     report += check_data_structure(
         ds,
@@ -151,8 +152,8 @@ def validate_dataset(
     spec_text += """
     ### 4.4 Data Variable Naming and Attributes
 
-    > "The data variable name SHOULD be a CF convention standard name or use a sensible name from the ECMWF parameter database."
-    > "The data variable MUST include the `long_name`, `standard_name` and `units` attributes following CF conventions."
+    - The data variable name SHOULD be a CF convention standard name or use a sensible name from the ECMWF parameter database.
+    - The data variable MUST include the `long_name`, `standard_name` and `units` attributes following CF conventions.
     """
     allowed_standard_names = (
         "rainfall_flux",
@@ -169,9 +170,9 @@ def validate_dataset(
     spec_text += """
     ### 4.5 Georeferencing
 
-    > "The dataset MUST include proper georeferencing information following the GeoZarr specification."
-    > "The data variable MUST include a `grid_mapping` attribute that references the coordinate reference system (crs) variable."
-    > "The crs variable MUST include both a `spatial_ref` and a `crs_wkt` attribute with a WKT string."
+    - The dataset MUST include proper georeferencing information following the GeoZarr specification.
+    - The data variable MUST include a `grid_mapping` attribute that references the coordinate reference system (crs) variable.
+    - The crs variable MUST include both a `spatial_ref` and a `crs_wkt` attribute with a WKT string.
     """
     report += check_georeferencing(
         ds,
@@ -188,7 +189,7 @@ def validate_dataset(
     spec_text += """
     ### 5.1 Conditional Global Attributes
 
-    > "The global attribute `consistent_timestep_start` is CONDITIONALLY REQUIRED if the dataset uses a variable timestep. It MUST be an ISO formatted datetime string indicating the first timestamp where regular timestepping begins."
+    - The global attribute `consistent_timestep_start` is CONDITIONALLY REQUIRED if the dataset uses a variable timestep. It MUST be an ISO formatted datetime string indicating the first timestamp where regular timestepping begins.
     """
     report += check_conditional_global_attributes(
         ds,
@@ -198,9 +199,9 @@ def validate_dataset(
     spec_text += """
     ### 5.2 Licensing Requirements
 
-    > "The dataset MUST include a global `license` attribute containing a valid SPDX identifier."
-    > "The following licenses are RECOMMENDED: `CC-BY`, `CC-BY-SA`, `OGL`."
-    > "Licenses with `NC` or `ND` restrictions SHOULD generate warnings but MAY be accepted after review."
+    - The dataset MUST include a global `license` attribute containing a valid SPDX identifier.
+    - The following licenses are RECOMMENDED: `CC-BY`, `CC-BY-SA`, `OGL`.
+    - Licenses with `NC` or `ND` restrictions SHOULD generate warnings but MAY be accepted after review.
     """
     report += check_license(
         ds,
@@ -225,26 +226,26 @@ def validate_dataset(
     spec_text += """
     ### 5.3 Zarr Format
 
-    > "The dataset MUST use Zarr version 2 or version 3 format."
-    > "If Zarr version 2 is used, the dataset MUST include consolidated metadata."
+    - The dataset MUST use Zarr version 2 or version 3 format.
+    - If Zarr version 2 is used, the dataset MUST include consolidated metadata.
     """
     report += check_zarr_format(
         ds,
         allowed_versions=[2, 3],
         require_consolidated_if_v2=True,
-        storage_options=storage_options,
     )
 
     spec_text += """
     ### 5.4 MLCast Metadata
 
-    > "The dataset MUST include the following global attributes:
-    >   - `mlcast_created_on`: ISO formatted datetime of dataset creation.
-    >   - `mlcast_created_by`: Creator contact in `Name <email>` format.
-    >   - `mlcast_created_with`: GitHub URL of the creating software including version (e.g., https://github.com/mlcast-community/mlcast-dataset-radklim@v0.1.0) and the repository/revision MUST exist.
-    >   - `mlcast_dataset_version`: Dataset specification version (semver or calver).
-    >   - `mlcast_dataset_identifier`: Unique dataset identifier formatted as `<country_code>-<entity>-<physical_variable>` by default.
-    >   - `mlcast_dataset_identifier_format`: OPTIONAL format string that MUST start with `<country_code>-<entity>-<physical_variable>` and MAY include only the approved identifier parts: `country_code`, `entity`, `physical_variable`, `time_resolution`, `common_name`."
+    The dataset MUST include the following global attributes:
+
+    - `mlcast_created_on`: ISO formatted datetime of dataset creation.
+    - `mlcast_created_by`: Creator contact in `Name <email>` format.
+    - `mlcast_created_with`: GitHub URL of the creating software including version (e.g., https://github.com/mlcast-community/mlcast-dataset-radklim@v0.1.0) and the repository/revision MUST exist.
+    - `mlcast_dataset_version`: Dataset specification version (semver or calver).
+    - `mlcast_dataset_identifier`: Unique dataset identifier formatted as `<country_code>-<entity>-<physical_variable>` by default.
+    - `mlcast_dataset_identifier_format`: OPTIONAL format string that MUST start with `<country_code>-<entity>-<physical_variable>` and MAY include only the approved identifier parts: `country_code`, `entity`, `physical_variable`, `time_resolution`, `common_name`.
     """
     report += check_mlcast_metadata(ds)
 
@@ -257,17 +258,17 @@ def validate_dataset(
     spec_text += """
     ### 6.1 GDAL Compatibility
 
-    > "The dataset SHOULD expose georeferencing metadata readable by GDAL, including a CRS WKT."
-    > "A basic GeoTIFF export SHOULD roundtrip through GDAL with geotransform/projection metadata."
+    - The dataset SHOULD expose georeferencing metadata readable by GDAL, including a CRS WKT.
+    - A basic GeoTIFF export SHOULD roundtrip through GDAL with geotransform/projection metadata.
     """
     report += check_gdal_compatibility(ds)
 
     spec_text += """
     ### 6.2 Cartopy Compatibility
 
-    > "The CRS WKT SHOULD be parseable by cartopy."
-    > "Coordinate grids SHOULD transform cleanly into PlateCarree for mapping workflows."
+    - The CRS WKT SHOULD be parseable by cartopy.
+    - Coordinate grids SHOULD transform cleanly into PlateCarree for mapping workflows.
     """
     report += check_cartopy_compatibility(ds)
 
-    return report
+    return report, textwrap.dedent(spec_text)

mlcast_dataset_validator/utils/logging_decorator.py

@@ -1,19 +1,5 @@
-from functools import wraps
+"""Compat shim: import logging helpers from specs.reporting."""
 
-from loguru import logger
+from ..specs.reporting import CHECK_REGISTRY, log_function_call
 
-
-def log_function_call(func):
-    """Decorator to log function calls with their arguments."""
-
-    @wraps(func)
-    def wrapper(*args, **kwargs):
-        logger.info(f"Applying {func.__name__} with {kwargs}")
-        report = func(*args, **kwargs)
-        # Set module and function name on the result object
-        for result in report.results:
-            result.module = func.__module__
-            result.function = func.__name__
-        return report
-
-    return wrapper
+__all__ = ["CHECK_REGISTRY", "log_function_call"]

{mlcast_dataset_validator-0.1.0.dist-info → mlcast_dataset_validator-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mlcast-dataset-validator
-Version: 0.1.0
+Version: 0.2.0
 Summary: Add your description here
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
@@ -23,6 +23,8 @@ Dynamic: license-file
 
 # mlcast-dataset-validator
 
+[![Spec Docs](https://img.shields.io/badge/spec%20docs-HTML-blue)](https://mlcast-community.github.io/mlcast-dataset-validator/)
+
 Dataset validator for the MLCast Intake catalog ([mlcast-datasets](https://github.com/mlcast-community/mlcast-datasets)).
 
 ## What is this?

mlcast_dataset_validator-0.2.0.dist-info/RECORD

@@ -0,0 +1,36 @@
+mlcast_dataset_validator/__init__.py,sha256=8EyAIaXvAvj4xzQVXeGeDuottFvUy4BsxgCpU9zfTdc,317
+mlcast_dataset_validator/checks/data_vars_filter.py,sha256=2bS6YRqPBWYYOEjRoUQRx16XpQ9lYoF8O8kVEXB117A,1641
+mlcast_dataset_validator/checks/coords/__init__.py,sha256=tpAlg9zunrUeyqJ4DYu605HR_v18A30-L0xLET4bO98,15
+mlcast_dataset_validator/checks/coords/names.py,sha256=v102OC2Usmd9X5gqSXWWcMd7iR7rjMSYC8xtT85RQe0,8372
+mlcast_dataset_validator/checks/coords/spatial.py,sha256=f7xj5L7dGLkDP6xMu_P1ZQDbbSFKcrGi1ZWUrCeej_w,3619
+mlcast_dataset_validator/checks/coords/temporal.py,sha256=SDcEYYudK4WjCCekj8Oa-EG8yhMeokGG0LC5KWCEbTc,12507
+mlcast_dataset_validator/checks/data_vars/__init__.py,sha256=x0QGejaph-2tbTVbEsOTqWG7uOvqWo-OIz0vFriF0Z4,15
+mlcast_dataset_validator/checks/data_vars/chunking.py,sha256=eGk5hEB-ksvwNMNGVJvhIVok-U4Cy0iPqwZaLAkZk8M,1692
+mlcast_dataset_validator/checks/data_vars/compression.py,sha256=0EbOc388nnXWOx-NFkrbreIfMrVO6zQDUSZSDdxNKUQ,4042
+mlcast_dataset_validator/checks/data_vars/data_structure.py,sha256=dvDl51D3ZIQStYsf3lyIE3lmQGMZc3WJ06suruwdUnc,1872
+mlcast_dataset_validator/checks/data_vars/data_variable.py,sha256=H36elAD1uUtGVCeaeE1V_getvAyQFWq8enaBeBBtqms,1943
+mlcast_dataset_validator/checks/data_vars/georeferencing.py,sha256=CbH6vK1ucoRKnZD2y_p02tvWwbJuVk_Ejr9QJzkP57c,2232
+mlcast_dataset_validator/checks/data_vars/naming.py,sha256=1HuL4C5CJQoE9b7Ww80b3G0fNB6FrlR7_7WfBh9yAlI,5457
+mlcast_dataset_validator/checks/global_attributes/__init__.py,sha256=OGycUmJKEN3J7KD5XDtwp3tIN20aJcWCfI4dh7NvLp0,15
+mlcast_dataset_validator/checks/global_attributes/conditional.py,sha256=HmqNfU7hbnU_cyUj9V2s1IqHiLdqYZEw4fxT9hftetI,1931
+mlcast_dataset_validator/checks/global_attributes/licensing.py,sha256=bPeZYIYgt5MguvXgyBRbi8nMoFZx4pGEtz7IrEfwcg4,4659
+mlcast_dataset_validator/checks/global_attributes/mlcast_metadata.py,sha256=21c_69cY3BwCmfX68esN7Ja7KJvNvn0a0941OFM7X3k,21663
+mlcast_dataset_validator/checks/global_attributes/zarr_format.py,sha256=nq3be1nR4wUs2GnUJP6EG3q49BcQsPGOMc-bt4snSeU,2671
+mlcast_dataset_validator/checks/tool_compatibility/__init__.py,sha256=lPaUZM1rQCeQCtpTxzhvvLB5WoRordTvJt5gJ8ApYcE,15
+mlcast_dataset_validator/checks/tool_compatibility/cartopy.py,sha256=0n1X4ANIZ6U11QxqVOOHIvcxSTpw8KpwijgNQ0hWpWU,5543
+mlcast_dataset_validator/checks/tool_compatibility/gdal.py,sha256=nACc8Kv-D5E47THxfLmbQGTj1bzSIvHrCqLlNUYq6CQ,7448
+mlcast_dataset_validator/specs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mlcast_dataset_validator/specs/cli.py,sha256=G1c4rMeBocHvbd3Z9-BHt9PnCmC4nwqHuor9n46Mt0o,6645
+mlcast_dataset_validator/specs/reporting.py,sha256=jcoNw9fdv51TljtOGXflwMqdyXZ3cBDqtKJAVd9lVFI,7045
+mlcast_dataset_validator/specs/source_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mlcast_dataset_validator/specs/source_data/radar_precipitation.py,sha256=7ftMti8f0DlCmjxFZ-bqhIvIpmG7Kk5UwX2RN8Qebwc,10336
+mlcast_dataset_validator/specs/training_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mlcast_dataset_validator/utils/logging_decorator.py,sha256=nub3yic77svFZFp0AHpK9S1doW_kyfeoDRCfgZbj6LM,180
+mlcast_dataset_validator-0.2.0.dist-info/licenses/LICENSE,sha256=OJwqNMiebzDI5xO80428flMTXjYT_NTzGid_LrlAdQE,346
+mlcast_dataset_validator-0.2.0.dist-info/licenses/LICENSE-APACHE,sha256=zjN0GIESbq-pIfRMHPnKuYAtB09yJEqAZxJ2eTmUN0M,11347
+mlcast_dataset_validator-0.2.0.dist-info/licenses/LICENSE-BSD,sha256=nxwpuv65fwXrfZtDbnObrC5gyCryKO-QZoKdjoYX-Cw,1481
+mlcast_dataset_validator-0.2.0.dist-info/METADATA,sha256=7ALR2bg8ibf_Cme8_QrgHGk1VuJcEaXs7DR9O9_83EY,6340
+mlcast_dataset_validator-0.2.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+mlcast_dataset_validator-0.2.0.dist-info/entry_points.txt,sha256=agJXVv9X2zWETDGjZzEWVZi_BAivfFB72QgoCuKoW-I,84
+mlcast_dataset_validator-0.2.0.dist-info/top_level.txt,sha256=cn53cAYHj7S05A2j8JKGV30YgEbqylDYaRsFn6Ppp60,25
+mlcast_dataset_validator-0.2.0.dist-info/RECORD,,

mlcast_dataset_validator-0.1.0.dist-info/RECORD

@@ -1,36 +0,0 @@
-mlcast_dataset_validator/__init__.py,sha256=8EyAIaXvAvj4xzQVXeGeDuottFvUy4BsxgCpU9zfTdc,317
-mlcast_dataset_validator/checks/data_vars_filter.py,sha256=2bS6YRqPBWYYOEjRoUQRx16XpQ9lYoF8O8kVEXB117A,1641
-mlcast_dataset_validator/checks/coords/__init__.py,sha256=tpAlg9zunrUeyqJ4DYu605HR_v18A30-L0xLET4bO98,15
-mlcast_dataset_validator/checks/coords/names.py,sha256=NSRAZ3tXVjamGpoO2oZIaDR0VWEUxMxWcZrf2UthYHI,8405
-mlcast_dataset_validator/checks/coords/spatial.py,sha256=67DNv9LXJ7h60viZi0lSXiz6Kewjm626G1vfnJO3ZEM,3652
-mlcast_dataset_validator/checks/coords/temporal.py,sha256=Rf7lG_w92xMEHZ5oBEb6aFl9Fu81YSILd4GRuCOGqyw,12540
-mlcast_dataset_validator/checks/data_vars/__init__.py,sha256=x0QGejaph-2tbTVbEsOTqWG7uOvqWo-OIz0vFriF0Z4,15
-mlcast_dataset_validator/checks/data_vars/chunking.py,sha256=WwywuPHzPuwkTM0UJjDVcD40Ns_nNFofihiFzNals1c,1725
-mlcast_dataset_validator/checks/data_vars/compression.py,sha256=UL8D5jd69HYtz884yXOPzKfEm6gQs3tNzRsuJGhJxts,4075
-mlcast_dataset_validator/checks/data_vars/data_structure.py,sha256=kBLahdABZF5dpPlhsZEomNhsp0APgNnmoNUVmWrmYIc,1905
-mlcast_dataset_validator/checks/data_vars/data_variable.py,sha256=P10qzfhV0P5X0xXyatoxBmzXf1lxTZKg1U_Ez_PTpLg,1976
-mlcast_dataset_validator/checks/data_vars/georeferencing.py,sha256=CKraolEGPXxgfy4q_9TYnYMIdegiGr0vdGOfECZa47o,2265
-mlcast_dataset_validator/checks/data_vars/naming.py,sha256=fZMpDJKNfOvtqs_1QYEUGmJxhp3BR_eTf6rjaqk7hb4,5490
-mlcast_dataset_validator/checks/global_attributes/__init__.py,sha256=OGycUmJKEN3J7KD5XDtwp3tIN20aJcWCfI4dh7NvLp0,15
-mlcast_dataset_validator/checks/global_attributes/conditional.py,sha256=z5i0AKEK42BT2_3XzleJD5w6i91VbVhatf3fNT9atpM,1964
-mlcast_dataset_validator/checks/global_attributes/licensing.py,sha256=sUCyVNx_PegagTROg57REll10jKT_KfU3zGuGnJPi-k,4692
-mlcast_dataset_validator/checks/global_attributes/mlcast_metadata.py,sha256=EoqFvRkobOkKdHcQSvItmAXRIVe-u1aNqGNv-bGnXUc,21658
-mlcast_dataset_validator/checks/global_attributes/zarr_format.py,sha256=kAy66Z5VZhXAnDVFiVM5mm3pyE78j3sLdwycUOVJlpI,2610
-mlcast_dataset_validator/checks/tool_compatibility/__init__.py,sha256=lPaUZM1rQCeQCtpTxzhvvLB5WoRordTvJt5gJ8ApYcE,15
-mlcast_dataset_validator/checks/tool_compatibility/cartopy.py,sha256=ofq82tH2w5Fe8QUlMvehkVozvzoAe3QzTJQXwINGt1E,5576
-mlcast_dataset_validator/checks/tool_compatibility/gdal.py,sha256=LemeGk-XugFg43b0sAJyWUz0M8PF1w1Iy-6N0QmZ2eY,7481
-mlcast_dataset_validator/specs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mlcast_dataset_validator/specs/base.py,sha256=uoIIdTXJBTi6QISUsWzkI2r1-gxMPhcED8OeghY3t-8,4702
-mlcast_dataset_validator/specs/cli.py,sha256=Kz8Ky9JNGR3l9UpNDGqDwDhjTWl9bkatdIe09NA13e8,5449
-mlcast_dataset_validator/specs/source_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mlcast_dataset_validator/specs/source_data/radar_precipitation.py,sha256=RFd3VBbz_Ce8YaoEexfG41SoSLLLmkfCY2JpfqGXr9c,10512
-mlcast_dataset_validator/specs/training_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mlcast_dataset_validator/utils/logging_decorator.py,sha256=s0zgRiTzMzyOrPrreNKjnyP_ftl8Tjp2fVMz62_vE-A,532
-mlcast_dataset_validator-0.1.0.dist-info/licenses/LICENSE,sha256=OJwqNMiebzDI5xO80428flMTXjYT_NTzGid_LrlAdQE,346
-mlcast_dataset_validator-0.1.0.dist-info/licenses/LICENSE-APACHE,sha256=zjN0GIESbq-pIfRMHPnKuYAtB09yJEqAZxJ2eTmUN0M,11347
-mlcast_dataset_validator-0.1.0.dist-info/licenses/LICENSE-BSD,sha256=nxwpuv65fwXrfZtDbnObrC5gyCryKO-QZoKdjoYX-Cw,1481
-mlcast_dataset_validator-0.1.0.dist-info/METADATA,sha256=jn90Q5yk9-jky-aIZkaNOZe6z-VVE5XKGA941Q4YKiw,6210
-mlcast_dataset_validator-0.1.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-mlcast_dataset_validator-0.1.0.dist-info/entry_points.txt,sha256=agJXVv9X2zWETDGjZzEWVZi_BAivfFB72QgoCuKoW-I,84
-mlcast_dataset_validator-0.1.0.dist-info/top_level.txt,sha256=cn53cAYHj7S05A2j8JKGV30YgEbqylDYaRsFn6Ppp60,25
-mlcast_dataset_validator-0.1.0.dist-info/RECORD,,