Review comments

.github/workflows/ci-fmudataio.yml

@@ -18,11 +18,9 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
 

.github/workflows/fmudataio-documention.yml

@@ -20,8 +20,6 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
 
       - name: Set up Python
         uses: actions/setup-python@v4

.github/workflows/fmudataio-publish-pypi.yml

@@ -10,16 +10,18 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
+
       - name: Set up Python 3.10
         uses: actions/setup-python@v4
         with:
           python-version: "3.10"
+
       - name: Install pypa/build
         run: python -m pip install build twine
+
       - name: Build package
         run: python -m build . --sdist --wheel --outdir dist/
+
       - name: Upload deploy
         env:
           TWINE_USERNAME: __token__

.github/workflows/linting.yml

@@ -10,8 +10,6 @@ jobs:
         python-version: ["3.10"]
     steps:
       - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
       - name: Set up python
         uses: actions/setup-python@v4
       - name: Install dev-env.

.github/workflows/mypy.yml

@@ -7,23 +7,17 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.8", "3.10"]
     steps:
       - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
+
       - name: Set up python
         uses: actions/setup-python@v4
-      - name: Cache pip
-        uses: actions/cache@v3
-        with:
-          path: ~/.cache/pip
-          key: ${{ runner.os }}-pip-${{ hashFiles('**/pyproject.toml') }}
-          restore-keys: |
-            ${{ runner.os }}-pip-
+
       - name: Install dev-env.
         run: |
           pip install -U pip
           pip install ".[dev]"
+
       - name: Mypy
         run: mypy .

src/fmu/dataio/_definitions.py

@@ -59,7 +59,7 @@ class _ValidFormats:
     )
 
 
-ALLOWED_CONTENTS = {
+ALLOWED_CONTENTS: Final = {
     "depth": None,
     "time": None,
     "thickness": None,
@@ -92,14 +92,14 @@ class _ValidFormats:
     "transmissibilities": None,
 }
 
-STANDARD_TABLE_INDEX_COLUMNS = {
+STANDARD_TABLE_INDEX_COLUMNS: Final = {
     "inplace_volumes": ["ZONE", "REGION", "FACIES", "LICENCE"],
     "timeseries": ["DATE"],  # summary
     "rft": ["measured_depth", "well", "time"],
     "wellpicks": ["WELL", "HORIZON"],
 }
 
-DEPRECATED_CONTENTS = {
+DEPRECATED_CONTENTS: Final = {
     "seismic": {
         "offset": {
             "replaced_by": "stacking_offset",
@@ -109,15 +109,15 @@ class _ValidFormats:
 
 # This setting will set if subkeys is required or not. If not found in list then
 # assume False.
-CONTENTS_REQUIRED = {
+CONTENTS_REQUIRED: Final = {
     "fluid_contact": {"contact": True},
     "field_outline": {"contact": False},
     "field_region": {"id": True},
 }
 
 # This setting sets the FMU context for the output. If detected as a non-fmu run,
 # the code will internally set actual_context=None
-ALLOWED_FMU_CONTEXTS = {
+ALLOWED_FMU_CONTEXTS: Final = {
     "realization": "To realization-N/iter_M/share",
     "case": "To casename/share, but will also work on project disk",
     "case_symlink_realization": "To case/share, with symlinks on realizations level",

src/fmu/dataio/_design_kw.py

@@ -27,7 +27,6 @@ def run(
     # If FWL key is having multiple entries in the parameters file
     # KeyError is raised. This will be logged, and no OK
     # file is written
-
     _logger.setLevel(log_level)
 
     with open(parameters_file_name) as parameters_file:
@@ -40,19 +39,21 @@ def run(
     with open(template_file_name) as template_file:
         template = template_file.readlines()
 
+    valid = True
     with open(result_file_name, "w") as result_file:
         for line in template:
             if not is_comment(line):
                 for key, value in key_vals.items():
                     line = line.replace(f"<{key}>", str(value))
 
                 if not all_matched(line, template_file_name, template):
-                    pass
+                    valid = False
 
             result_file.write(line)
 
-    with open(_STATUS_FILE_NAME, "w") as status_file:
-        status_file.write("DESIGN_KW OK\n")
+    if valid:
+        with open(_STATUS_FILE_NAME, "w") as status_file:
+            status_file.write("DESIGN_KW OK\n")
 
 
 def all_matched(line: str, template_file_name: str, template: list[str]) -> bool:

src/fmu/dataio/_filedata_provider.py

@@ -68,7 +68,6 @@ def __post_init__(self) -> None:
 
     def derive_filedata(self) -> None:
         relpath, symrelpath = self._get_path()
-        assert relpath is not None
         relative, absolute = self._derive_filedata_generic(relpath)
         self.relative_path = relative
         self.absolute_path = absolute

src/fmu/dataio/_objectdata_provider.py

@@ -89,7 +89,7 @@
 from dataclasses import dataclass, field
 from datetime import datetime as dt
 from pathlib import Path
-from typing import Any, Dict, Final, Optional
+from typing import Any, Final, Optional
 from warnings import warn
 
 import numpy as np
@@ -159,7 +159,7 @@ def _derive_name_stratigraphy(self) -> dict:
 
         """
         logger.info("Evaluate data:name attribute and stratigraphy")
-        result: Dict[str, Any] = {}
+        result: dict[str, Any] = {}
 
         name = self.dataio.name
 
@@ -209,7 +209,7 @@ def _validate_get_ext(
     def _derive_objectdata(self) -> dict:
         """Derive object spesific data."""
         logger.info("Evaluate data settings for object")
-        result: Dict[str, Any] = {}
+        result: dict[str, Any] = {}
 
         if isinstance(self.obj, xtgeo.RegularSurface):
             result["subtype"] = "RegularSurface"
@@ -393,14 +393,14 @@ def _derive_spec_bbox_polygons(self) -> tuple[dict, dict]:
         bbox["zmax"] = float(zmax)
         return specs, bbox
 
-    def _derive_spec_bbox_points(self) -> tuple[Dict[str, Any], Dict[str, Any]]:
+    def _derive_spec_bbox_points(self) -> tuple[dict[str, Any], dict[str, Any]]:
         """Process/collect the data.spec and data.bbox for Points"""
         logger.info("Derive bbox and specs for Points")
         pnts = self.obj
 
-        specs: Dict[str, Any] = {}
+        specs: dict[str, Any] = {}
 
-        bbox: Dict[str, Any] = {}
+        bbox: dict[str, Any] = {}
 
         if len(pnts.dataframe.columns) > 3:
             attrnames = pnts.dataframe.columns[3:]
@@ -482,8 +482,8 @@ def _derive_spec_bbox_cpgridproperty(self) -> tuple[dict, dict]:
         logger.info("Derive bbox and specs for GridProperty")
         gridprop = self.obj
 
-        specs: Dict[str, Any] = {}
-        bbox: Dict[str, Any] = {}
+        specs: dict[str, Any] = {}
+        bbox: dict[str, Any] = {}
 
         specs["ncol"] = gridprop.ncol
         specs["nrow"] = gridprop.nrow
@@ -493,15 +493,15 @@ def _derive_spec_bbox_cpgridproperty(self) -> tuple[dict, dict]:
     def _derive_spec_bbox_dataframe(
         self,
     ) -> tuple[
-        Dict[str, Any],
-        Dict[str, Any],
+        dict[str, Any],
+        dict[str, Any],
     ]:
         """Process/collect the data items for DataFrame."""
         logger.info("Process data metadata for DataFrame (tables)")
         dfr = self.obj
 
-        specs: Dict[str, Any] = {}
-        bbox: Dict[str, Any] = {}
+        specs: dict[str, Any] = {}
+        bbox: dict[str, Any] = {}
 
         specs["columns"] = list(dfr.columns)
         specs["size"] = int(dfr.size)
@@ -511,22 +511,22 @@ def _derive_spec_bbox_dataframe(
     def _derive_spec_bbox_arrowtable(
         self,
     ) -> tuple[
-        Dict[str, Any],
-        Dict[str, Any],
+        dict[str, Any],
+        dict[str, Any],
     ]:
         """Process/collect the data items for Arrow table."""
         logger.info("Process data metadata for arrow (tables)")
         table = self.obj
 
-        specs: Dict[str, Any] = {}
-        bbox: Dict[str, Any] = {}
+        specs: dict[str, Any] = {}
+        bbox: dict[str, Any] = {}
 
         specs["columns"] = list(table.column_names)
         specs["size"] = table.num_columns * table.num_rows
 
         return specs, bbox
 
-    def _derive_spec_bbox_dict(self) -> tuple[Dict[str, Any], Dict[str, Any]]:
+    def _derive_spec_bbox_dict(self) -> tuple[dict[str, Any], dict[str, Any]]:
         """Process/collect the data items for dictionary."""
         logger.info("Process data metadata for dictionary")
         return {}, {}
@@ -591,12 +591,12 @@ def _derive_timedata(self) -> dict:
             timedata = self._derive_timedata_newformat()
         return timedata
 
-    def _derive_timedata_legacy(self) -> Dict[str, Any]:
+    def _derive_timedata_legacy(self) -> dict[str, Any]:
         """Format input timedata to metadata. legacy version."""
         # TODO(JB): Covnert tresult to TypedDict or Dataclass.
         tdata = self.dataio.timedata
 
-        tresult: Dict[str, Any] = {}
+        tresult: dict[str, Any] = {}
         tresult["time"] = []
         if len(tdata) == 1:
             elem = tdata[0]
@@ -640,7 +640,7 @@ def _derive_timedata_newformat(self) -> dict[str, Any]:
         set for those who wants it turned around).
         """
         tdata = self.dataio.timedata
-        tresult: Dict[str, Any] = {}
+        tresult: dict[str, Any] = {}
 
         if len(tdata) == 1:
             elem = tdata[0]

src/fmu/dataio/_utils.py

@@ -13,7 +13,7 @@
 from copy import deepcopy
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Final
+from typing import Any, Final, Literal
 
 import pandas as pd
 import yaml
@@ -83,7 +83,10 @@ def drop_nones(dinput: dict) -> dict:
 
 
 def export_metadata_file(
-    yfile: Path, metadata: dict, savefmt: str = "yaml", verbosity: str = "WARNING"
+    yfile: Path,
+    metadata: dict,
+    savefmt: Literal["yaml", "json"] = "yaml",
+    verbosity: str = "WARNING",
 ) -> None:
     """Export genericly and ordered to the complementary metadata file."""
     logger.setLevel(level=verbosity)

src/fmu/dataio/dataio.py

@@ -11,7 +11,7 @@
 from copy import deepcopy
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Any, ClassVar, Final, List, Optional, Union
+from typing import Any, ClassVar, Final, List, Literal, Optional, Union
 from warnings import warn
 
 import pandas as pd
@@ -74,7 +74,6 @@ def _validate_variable(key: str, value: type, legals: dict[str, str | type]) ->
         validcheck = valid_type
 
     if "typing." not in str(validcheck):
-        print(f"{value=}, {validcheck=}, {type(value)=}, {type(validcheck)=}")
         if not isinstance(value, validcheck):
             logger.warning("Wrong type of value, raise an error")
             raise ValidationError(
@@ -550,7 +549,7 @@ class ExportData:
     grid_fformat: ClassVar[str] = "roff"
     include_ert2jobs: ClassVar[bool] = False  # if True, include jobs.json from ERT2
     legacy_time_format: ClassVar[bool] = False
-    meta_format: ClassVar[str] = "yaml"
+    meta_format: ClassVar[Literal["yaml", "json"]] = "yaml"
     polygons_fformat: ClassVar[str] = "csv"  # or use "csv|xtgeo"
     points_fformat: ClassVar[str] = "csv"  # or use "csv|xtgeo"
     surface_fformat: ClassVar[str] = "irap_binary"
@@ -976,7 +975,7 @@ class InitializeCase:  # pylint: disable=too-few-public-methods
     """
 
     # class variables
-    meta_format: ClassVar[str] = "yaml"
+    meta_format: ClassVar[Literal["yaml", "json"]] = "yaml"
 
     # instance
     config: dict
@@ -1209,7 +1208,7 @@ class AggregatedData:
     """
 
     # class variable(s)
-    meta_format: ClassVar[str] = "yaml"
+    meta_format: ClassVar[Literal["yaml", "json"]] = "yaml"
 
     # instance
     aggregation_id: Optional[str] = None