Housekeeping (#255)

* fixes to pyproject.toml

* also schemas

* check also 3.14

* update test_schema

* pin pandas to >= 2.0, < 3.0

* remove pydantic.v1 stuff

* avoid warning in sac.py

* outer join in picolog

Author: PeterKraus

.github/workflows/pull-request-commit.yml

@@ -6,7 +6,7 @@ jobs:
     build:
         strategy:
             matrix:
-                pyver: ['3.10', '3.11', '3.12', '3.13']
+                pyver: ['3.10', '3.11', '3.12', '3.13', '3.14']
                 os: ['ubuntu-latest']
                 include:
                   - pyver: '3.11'
@@ -19,7 +19,7 @@ jobs:
         needs: [build]
         strategy:
             matrix:
-                pyver: ['3.10', '3.11', '3.12', '3.13']
+                pyver: ['3.10', '3.11', '3.12', '3.13', '3.14']
                 os: ['ubuntu-latest']
                 include:
                   - pyver: '3.11'

pyproject.toml

@@ -16,13 +16,14 @@ maintainers = [
 ]
 description = "yet another datagram"
 readme = "README.md"
+license = "GPL-3.0-or-later"
 classifiers = [
     "Development Status :: 5 - Production/Stable",
-    "License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
     "Operating System :: OS Independent",
 ]
 requires-python = ">= 3.10"
@@ -37,11 +38,11 @@ dependencies = [
     "python-dateutil",
     "openpyxl >= 3.0.0",
     "olefile >= 0.47",
-    "h5netcdf >= 1.0",
-    "pandas >= 2.0",
+    "h5netcdf[h5py] >= 1.8.0",
+    "pandas >= 2.0, < 3.0",
     "babel >= 2.15",
     "xarray >= 2024.10.0",
-    "dgbowl-schemas >= 123",
+    "dgbowl-schemas >= 125",
 ]
 
 [project.optional-dependencies]

src/yadg/dgutils/schemautils.py

@@ -4,7 +4,6 @@
 from dgbowl_schemas.yadg import to_dataschema
 from dgbowl_schemas.yadg.dataschema import DataSchema
 from pydantic import BaseModel
-from pydantic.v1 import BaseModel as BaseModel_v1
 from yadg import dgutils
 
 __latest_dataschema__ = "6.0"
@@ -106,7 +105,7 @@ def schema_3to4(oldschema: list) -> dict:
     return newschema
 
 
-def update_schema(object: list | dict | BaseModel | BaseModel_v1) -> DataSchema:
+def update_schema(object: list | dict | BaseModel) -> DataSchema:
     """
     The ``yadg update`` worker function.
 
@@ -137,7 +136,7 @@ def update_schema(object: list | dict | BaseModel | BaseModel_v1) -> DataSchema:
     elif isinstance(object, dict):
         logger.info("Updating dict-style DataSchema")
         newobj = to_dataschema(**object)
-    elif isinstance(object, (BaseModel, BaseModel_v1)):
+    elif isinstance(object, BaseModel):
         logger.info("Updating an existing DataSchema object")
         newobj = object
     else:

src/yadg/extractors/picolog/tc08.py

@@ -141,7 +141,7 @@ def extract_from_path(
                     },
                     coords={"uts": (["uts"], xvals)},
                 )
-                ds = xr.merge((ds, newds))
+                ds = xr.merge((ds, newds), join="outer")
     for var in ds.variables:
         if f"{var}_std_err" in ds.variables:
             ds[var].attrs["ancillary_variables"] = f"{var}_std_err"

src/yadg/extractors/quadstar/sac.py

@@ -272,7 +272,10 @@ def extract_from_path(
             else:
                 try:
                     traces[f"{ti}"] = xr.concat(
-                        [traces[f"{ti}"], ds], dim="uts", combine_attrs="identical"
+                        [traces[f"{ti}"], ds],
+                        data_vars="all",
+                        dim="uts",
+                        combine_attrs="identical",
                     )
                 except xr.MergeError:
                     raise RuntimeError(

tests/test_schema.py

@@ -4,7 +4,6 @@
 import yadg.core
 from dgbowl_schemas.yadg import to_dataschema, DataSchema_4_0, DataSchema_4_1
 from pydantic import ValidationError
-from pydantic.v1 import ValidationError as ValidationError_v1
 from .utils import datagram_from_file
 
 ts0 = {
@@ -195,29 +194,29 @@ def test_datagram_from_schema_file(inp_fn, ts, datadir):
 @pytest.mark.parametrize(
     "inp_dict, expr",
     [
-        (fts0, r"Discriminator 'parser' is missing in value"),
-        (fts1, r"No match for discriminator 'parser' and value 'dumm'"),
+        (fts0, r"Unable to extract tag using discriminator 'parser'"),
+        (fts1, r"Input tag 'dumm' found using 'parser'"),
         (fts2, r"Both 'files' and 'folders'"),
         (fts3, r"Neither 'files' nor 'folders'"),
-        (fts4, r"steps -> 0 -> Dummy -> key\n  extra fields not permitted"),
+        (fts4, r"Extra inputs are not permitted"),
     ],
 )
 def test_schema_validator_4_0(inp_dict, expr, datadir):
     os.chdir(datadir)
-    with pytest.raises((ValidationError, ValidationError_v1), match=expr):
+    with pytest.raises(ValidationError, match=expr):
         assert DataSchema_4_0(**inp_dict)
 
 
 @pytest.mark.parametrize(
     "inp_dict, expr",
     [
-        (fts5, r"metadata -> provenance\n  value is not a valid dict"),
-        (fts6, r"metadata -> version\n  unexpected value"),
-        (fts7, r"steps -> 0 -> Dummy -> input\n  field required"),
-        (fts8, r"Discriminator 'parser' is missing in value"),
+        (fts5, r"Input should be a valid dictionary or instance of Provenance"),
+        (fts6, r"Input should be '4.1', '4.1.0', '4.1.1', '4.1.2' or '4.1.3'"),
+        (fts7, r"Field required"),
+        (fts8, r"Unable to extract tag using discriminator 'parser'"),
     ],
 )
 def test_schema_validator_4_1(inp_dict, expr, datadir):
     os.chdir(datadir)
-    with pytest.raises((ValidationError, ValidationError_v1), match=expr):
+    with pytest.raises(ValidationError, match=expr):
         assert DataSchema_4_1(**inp_dict)