Complete mypy type coverage for entire codebase

.github/workflows/ci-fmudataio.yml

@@ -17,10 +17,10 @@ jobs:
         os: [ubuntu-latest]
 
     steps:
-      - uses: actions/checkout@v1
+      - uses: actions/checkout@v4
 
       - 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

@@ -15,11 +15,11 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ["3.8"]
+        python-version: ["3.10"]
         os: [ubuntu-latest]
 
     steps:
-      - uses: actions/checkout@v1
+      - uses: actions/checkout@v4
 
       - name: Set up Python
         uses: actions/setup-python@v4

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

@@ -9,15 +9,19 @@ jobs:
     name: Build and publish Python 🐍 distributions 📦 to PyPI
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+
       - 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

@@ -9,12 +9,13 @@ jobs:
       matrix:
         python-version: ["3.10"]
     steps:
-      - uses: actions/checkout@v2
-
+      - uses: actions/checkout@v4
       - name: Set up python
         uses: actions/setup-python@v4
-      - name: Check black style and linting
-        run: pip install ruff
+      - name: Install dev-env.
+        run: |
+          pip install -U pip
+          pip install ".[dev]"
       - name: Ruff check
         if: ${{ always() }}
         run: ruff check .

.github/workflows/mypy.yml

@@ -0,0 +1,23 @@
+name: Mypy
+
+on: [push, pull_request]
+
+jobs:
+  mypy:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.10"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up python
+        uses: actions/setup-python@v4
+
+      - name: Install dev-env.
+        run: |
+          pip install -U pip
+          pip install ".[dev]"
+
+      - name: Mypy
+        run: mypy .

.gitignore

@@ -96,3 +96,9 @@ venv.bak/
 
 # setuptools_scm version
 src/fmu/dataio/version.py
+
+# mypy
+.dmypy.json
+
+# Apple macOS
+.DS_Store 

mypy.ini

@@ -1,5 +1,10 @@
 [mypy]
-
-[mypy-numpy.*]
-# Applies to Python 3.6:
+disallow_untyped_defs = True
+exclude = ^((tests|docs|examples|build)/|conftest.py?)
+extra_checks = True
 ignore_missing_imports = True
+python_version = 3.8
+strict_equality = True
+warn_redundant_casts = True
+warn_unused_configs = True
+warn_unused_ignores = True

pyproject.toml

@@ -58,6 +58,7 @@ dev = [
     "rstcheck",
     "ruff",
     "termcolor",
+    "types-PyYAML",
 ]
 docs = [
     "autoapi",

src/fmu/dataio/_definitions.py

@@ -1,44 +1,65 @@
 """Various definitions and hard settings used in fmu-dataio."""
+from __future__ import annotations
+
 from dataclasses import dataclass, field
+from typing import Final
 
-SCHEMA = (
+SCHEMA: Final = (
     "https://main-fmu-schemas-prod.radix.equinor.com/schemas/0.8.0/fmu_results.json"
 )
-VERSION = "0.8.0"
-SOURCE = "fmu"
+VERSION: Final = "0.8.0"
+SOURCE: Final = "fmu"
 
 
 @dataclass
 class _ValidFormats:
-    surface: dict = field(default_factory=dict)
-    grid: dict = field(default_factory=dict)
-    cube: dict = field(default_factory=dict)
-    table: dict = field(default_factory=dict)
-    polygons: dict = field(default_factory=dict)
-    points: dict = field(default_factory=dict)
-    dictionary: dict = field(default_factory=dict)
-
-    def __post_init__(self):
-        self.surface = {"irap_binary": ".gri"}
-        self.grid = {"hdf": ".hdf", "roff": ".roff"}
-        self.cube = {"segy": ".segy"}
-        self.table = {"hdf": ".hdf", "csv": ".csv", "arrow": ".arrow"}
-        self.polygons = {
+    surface: dict = field(
+        default_factory=lambda: {
+            "irap_binary": ".gri",
+        }
+    )
+    grid: dict = field(
+        default_factory=lambda: {
+            "hdf": ".hdf",
+            "roff": ".roff",
+        }
+    )
+    cube: dict = field(
+        default_factory=lambda: {
+            "segy": ".segy",
+        }
+    )
+    table: dict = field(
+        default_factory=lambda: {
+            "hdf": ".hdf",
+            "csv": ".csv",
+            "arrow": ".arrow",
+        }
+    )
+    polygons: dict = field(
+        default_factory=lambda: {
             "hdf": ".hdf",
             "csv": ".csv",  # columns will be X Y Z, ID
             "csv|xtgeo": ".csv",  # use default xtgeo columns: X_UTME, ... POLY_ID
             "irap_ascii": ".pol",
         }
-        self.points = {
+    )
+    points: dict = field(
+        default_factory=lambda: {
             "hdf": ".hdf",
             "csv": ".csv",  # columns will be X Y Z
             "csv|xtgeo": ".csv",  # use default xtgeo columns: X_UTME, Y_UTMN, Z_TVDSS
             "irap_ascii": ".poi",
         }
-        self.dictionary = {"json": ".json"}
+    )
+    dictionary: dict = field(
+        default_factory=lambda: {
+            "json": ".json",
+        }
+    )
 
 
-ALLOWED_CONTENTS = {
+ALLOWED_CONTENTS: Final = {
     "depth": None,
     "time": None,
     "thickness": None,
@@ -71,14 +92,14 @@ def __post_init__(self):
     "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",
@@ -88,15 +109,15 @@ def __post_init__(self):
 
 # 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

@@ -5,31 +5,30 @@
 It is copied here instead of pip-installed in order to avoid dragging
 along all dependencies of semeio"""
 
-# pylint: disable=logging-fstring-interpolation
+from __future__ import annotations
+
 import logging
 import re
 import shlex
+from typing import Any, Final, Iterable
 
-_STATUS_FILE_NAME = "DESIGN_KW.OK"
+_STATUS_FILE_NAME: Final = "DESIGN_KW.OK"
 
-_logger = logging.getLogger(__name__)
+_logger: Final = logging.getLogger(__name__)
 
 
 def run(
-    template_file_name,
-    result_file_name,
-    log_level,
-    parameters_file_name="parameters.txt",
-):
+    template_file_name: str,
+    result_file_name: str,
+    log_level: str,
+    parameters_file_name: str = "parameters.txt",
+) -> None:
     # Get all key, value pairs
     # 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)
 
-    valid = True
-
     with open(parameters_file_name) as parameters_file:
         parameters = parameters_file.readlines()
 
@@ -40,24 +39,24 @@ def run(
     with open(template_file_name) as template_file:
         template = template_file.readlines()
 
-    if valid:
-        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))
+    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):
-                        valid = False
+                if not all_matched(line, template_file_name, template):
+                    valid = False
 
-                result_file.write(line)
+            result_file.write(line)
 
     if valid:
         with open(_STATUS_FILE_NAME, "w") as status_file:
             status_file.write("DESIGN_KW OK\n")
 
 
-def all_matched(line, template_file_name, template):
+def all_matched(line: str, template_file_name: str, template: list[str]) -> bool:
     valid = True
     for unmatched in unmatched_templates(line):
         if is_perl(template_file_name, template):
@@ -73,24 +72,24 @@ def all_matched(line, template_file_name, template):
     return valid
 
 
-def is_perl(file_name, template):
-    return file_name.endswith(".pl") or template[0].find("perl") != -1
+def is_perl(file_name: str, template: list[str]) -> bool:
+    return bool(file_name.endswith(".pl") or template[0].find("perl") != -1)
 
 
-def unmatched_templates(line):
+def unmatched_templates(line: str) -> list[str]:
     bracketpattern = re.compile("<.+?>")
     if bracketpattern.search(line):
         return bracketpattern.findall(line)
     return []
 
 
-def is_comment(line):
+def is_comment(line: str) -> bool:
     ecl_comment_pattern = re.compile("^--")
     std_comment_pattern = re.compile("^#")
-    return ecl_comment_pattern.search(line) or std_comment_pattern.search(line)
+    return bool(ecl_comment_pattern.search(line) or std_comment_pattern.search(line))
 
 
-def extract_key_value(parameters):
+def extract_key_value(parameters: Iterable[str]) -> dict[str, str]:
     """Parses a list of strings, looking for key-value pairs pr. line
     separated by whitespace, into a dictionary.
 
@@ -128,7 +127,10 @@ def extract_key_value(parameters):
     return res
 
 
-def rm_genkw_prefix(paramsdict, ignoreprefixes="LOG10_"):
+def rm_genkw_prefix(
+    paramsdict: dict[str, Any],
+    ignoreprefixes: str | list[str] | None = "LOG10_",
+) -> dict[str, Any]:
     """Strip prefixes from keys in a dictionary.
 
     Prefix is any string before a colon. No colon means no prefix.
@@ -152,7 +154,8 @@ def rm_genkw_prefix(paramsdict, ignoreprefixes="LOG10_"):
         ignoreprefixes = []
     if isinstance(ignoreprefixes, str):
         ignoreprefixes = [ignoreprefixes]
-    ignoreprefixes = filter(None, ignoreprefixes)
+
+    ignoreprefixes = list(filter(None, ignoreprefixes))
 
     for ignore_str in ignoreprefixes:
         paramsdict = {