Merge pull request #128 from josephnowak/feature/use-pyproject

Feature/use pyproject

docs/build/html/_static/doctools.js

@@ -248,10 +248,10 @@ var Documentation = {
       var src = $(this).attr('src');
       var idnum = $(this).attr('id').substr(7);
       $('tr.cg-' + idnum).toggle();
-      if (src.substr(-9) === 'minus.png')
-        $(this).attr('src', src.substr(0, src.length-9) + 'plus.png');
+      if (substr(-9) === 'minus.png')
+        $(this).attr('src', substr(0, length-9) + 'plus.png');
       else
-        $(this).attr('src', src.substr(0, src.length-8) + 'minus.png');
+        $(this).attr('src', substr(0, length-8) + 'minus.png');
     }).css('display', '');
     if (DOCUMENTATION_OPTIONS.COLLAPSE_INDEX) {
         togglers.click();

docs/build/html/_static/jquery-3.5.1.js

@@ -5708,29 +5708,29 @@ jQuery.Event = function( src, props ) {
 	}
 
 	// Event object
-	if ( src && src.type ) {
+	if ( src && type ) {
 		this.originalEvent = src;
-		this.type = src.type;
+		this.type = type;
 
 		// Events bubbling up the document may have been marked as prevented
 		// by a handler lower down the tree; reflect the correct value.
-		this.isDefaultPrevented = src.defaultPrevented ||
-				src.defaultPrevented === undefined &&
+		this.isDefaultPrevented = defaultPrevented ||
+				defaultPrevented === undefined &&
 
 				// Support: Android <=2.3 only
-				src.returnValue === false ?
+				returnValue === false ?
 			returnTrue :
 			returnFalse;
 
 		// Create target properties
 		// Support: Safari <=6 - 7 only
 		// Target should not be a text node (#504, #13143)
-		this.target = ( src.target && src.target.nodeType === 3 ) ?
-			src.target.parentNode :
-			src.target;
+		this.target = ( target && target.nodeType === 3 ) ?
+			target.parentNode :
+			target;
 
-		this.currentTarget = src.currentTarget;
-		this.relatedTarget = src.relatedTarget;
+		this.currentTarget = currentTarget;
+		this.relatedTarget = relatedTarget;
 
 	// Event type
 	} else {
@@ -5743,7 +5743,7 @@ jQuery.Event = function( src, props ) {
 	}
 
 	// Create a timestamp if incoming event doesn't have one
-	this.timeStamp = src && src.timeStamp || Date.now();
+	this.timeStamp = src && timeStamp || Date.now();
 
 	// Mark it as fixed
 	this[ jQuery.expando ] = true;
@@ -6035,12 +6035,12 @@ function fixInput( src, dest ) {
 	var nodeName = dest.nodeName.toLowerCase();
 
 	// Fails to persist the checked state of a cloned checkbox or radio button.
-	if ( nodeName === "input" && rcheckableType.test( src.type ) ) {
-		dest.checked = src.checked;
+	if ( nodeName === "input" && rcheckableType.test( type ) ) {
+		dest.checked = checked;
 
 	// Fails to return the selected option to the default selected state when cloning options
 	} else if ( nodeName === "input" || nodeName === "textarea" ) {
-		dest.defaultValue = src.defaultValue;
+		dest.defaultValue = defaultValue;
 	}
 }
 

pyproject.toml

@@ -0,0 +1,82 @@
+[tool.pdm]
+
+[project]
+name = "TensorDB"
+version = "0.32.0"
+description = "Database based in a file system storage combined with Xarray and Zarr"
+keywords = ["Database Files Xarray Handler Zarr Store Read Write Append Update Upsert Backup Delete S3"]
+readme = "README.md"
+authors = [
+    { name = "Joseph Nowak", email = "josephgonowak97@gmail.com" },
+]
+classifiers = [
+    "Development Status :: 1 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: General",
+    "Intended Audience :: Science/Research",
+    "Natural Language :: English",
+    "Programming Language :: Python :: 3.9",
+]
+dependencies = [
+    "dask[complete]>=2024.0.0",
+    "loguru>=0.7.0",
+    "more-itertools>=10.0.0",
+    "numbagg>=0.8.0",
+    "numpy>=1.26.0",
+    "orjson>=3.0.0",
+    "pandas>=2.0.0",
+    "pydantic>=2.0.0",
+    "xarray[accel]>=2023.0.0",
+    "zarr>=2.0.0",
+]
+requires-python = ">=3.11"
+
+[build-system]
+requires = ["pdm-backend"]
+build-backend = "pdm.backend"
+
+[project.optional-dependencies]
+dev = [
+    "ruff",
+    "pytest",
+    "pytest-cov",
+    "pytest-env",
+    "pytest-xdist",
+    "sphinx",
+]
+
+[tool.ruff]
+
+[tool.ruff.lint]
+# E402: module level import not at top of file
+# E501: line too long - let black worry about that
+# E731: do not assign a lambda expression, use a def
+extend-safe-fixes = [
+    "TID252", # absolute imports
+]
+ignore = [
+    "E402",
+    "E501",
+    "E731",
+    "UP007",
+    "UP038"
+]
+extend-select = [
+    "B", # flake8-bugbear
+    "F", # Pyflakes
+    "E", # Pycodestyle
+    "W",
+    "TID", # flake8-tidy-imports (absolute imports)
+    "I", # isort
+    "UP", # Pyupgrade
+]
+
+[tool.ruff.lint.per-file-ignores]
+# don't enforce absolute imports
+
+[tool.ruff.lint.isort]
+known-first-party = ["tensordb"]
+
+[tool.ruff.lint.flake8-tidy-imports]
+# Disallow all relative imports.
+ban-relative-imports = "all"

src/tensordb/__init__.py

@@ -0,0 +1,16 @@
+from tensordb import tensor_definition, utils
+from tensordb.algorithms import Algorithms
+from tensordb.clients import BaseTensorClient, FileCacheTensorClient, TensorClient
+from tensordb.tensor_definition import TensorDefinition
+from tensordb.utils.tools import extract_paths_from_formula
+
+__all__ = (
+    "tensor_definition",
+    "utils",
+    "Algorithms",
+    "TensorClient",
+    "FileCacheTensorClient",
+    "BaseTensorClient",
+    "TensorDefinition",
+    "extract_paths_from_formula",
+)

tensordb/algorithms.py → src/tensordb/algorithms.py

@@ -1,4 +1,5 @@
-from typing import Union, List, Dict, Literal, Any, Callable
+from collections.abc import Callable
+from typing import Any, Literal, Union
 
 import bottleneck as bn
 import dask
@@ -143,7 +144,7 @@ def map_blocks_along_axis(
         dim: str,
         dtype,
         drop_dim: bool = False,
-        kwargs: Dict = None,
+        kwargs: dict = None,
     ) -> xr.DataArray:
         kwargs = kwargs or {}
         template = new_data.chunk({dim: -1})
@@ -320,7 +321,7 @@ def rolling_along_axis(
     def replace(
         cls,
         new_data: Union[xr.DataArray, xr.Dataset],
-        to_replace: Dict,
+        to_replace: dict,
         dtype: Any = None,
         default_replace=None,
     ):
@@ -355,7 +356,7 @@ def replace(
     def vindex(
         cls,
         new_data: Union[xr.DataArray, xr.Dataset],
-        coords: Dict,
+        coords: dict,
     ):
         """
         Implementation of dask vindex using xarray
@@ -395,12 +396,12 @@ def vindex(
     def apply_on_groups(
         cls,
         new_data: Union[xr.DataArray, xr.Dataset],
-        groups: Union[Dict, xr.DataArray],
+        groups: Union[dict, xr.DataArray],
         dim: str,
         func: Union[str, Callable],
         keep_shape: bool = False,
         unique_groups: np.ndarray = None,
-        kwargs: Dict[str, Any] = None,
+        kwargs: dict[str, Any] = None,
         template: Union[xr.DataArray, xr.Dataset, str] = None,
     ):
         """
@@ -556,7 +557,7 @@ def merge_duplicates_coord(
         new_data: Union[xr.DataArray, xr.Dataset],
         dim: str,
         func: str,
-        kwargs: Dict[str, Any] = None,
+        kwargs: dict[str, Any] = None,
     ):
         """
         Group and merge duplicates coord base on a function, this can be a sum or a max. Read numpy-groupies
@@ -583,7 +584,7 @@ def merge_duplicates_coord(
     def dropna(
         cls,
         new_data: Union[xr.DataArray, xr.Dataset],
-        dims: List[str],
+        dims: list[str],
         how: Literal["all"] = "all",
         client: Client = None,
     ):
@@ -598,7 +599,7 @@ def dropna(
     def drop_unmarked(
         cls,
         new_data: Union[xr.DataArray, xr.Dataset],
-        dims: List[str],
+        dims: list[str],
         how: Literal["all"] = "all",
         client: Client = None,
     ):
@@ -613,7 +614,7 @@ def drop_unmarked(
             valid_coords = dask.compute(*valid_coords)
         else:
             valid_coords = [c.result() for c in client.compute(valid_coords)]
-        return new_data.sel(dict(zip(dims, valid_coords)))
+        return new_data.sel(dict(zip(dims, valid_coords, strict=False)))
 
     @classmethod
     def append_previous(
@@ -824,7 +825,7 @@ def reindex_with_pad(
         cls,
         data: xr.DataArray | xr.Dataset,
         coords,
-        preferred_chunks: Dict[str, int],
+        preferred_chunks: dict[str, int],
         fill_value: Any,
         apply_chunk: bool = True,
     ) -> xr.Dataset | xr.DataArray:
@@ -875,7 +876,11 @@ def reindex_with_pad(
         }
         # If it is not necessary to pad additional data then just use
         # reindex directly
-        if len(pad_width) == 0 or any(len(coord) == 0 for coord in coords):
+        if (
+            len(pad_width) == 0
+            or any(len(coord) == 0 for coord in coords)
+            or any(v == 0 for v in data.sizes.values())
+        ):
             data = data.reindex(coords, fill_value=fill_value)
             if apply_chunk:
                 data = data.chunk(preferred_chunks)

tensordb/clients/__init__.py → src/tensordb/clients/__init__.py

@@ -1,3 +1,5 @@
 from tensordb.clients.base import BaseTensorClient
 from tensordb.clients.file_cache_tensor_client import FileCacheTensorClient
 from tensordb.clients.tensor_client import TensorClient
+
+__all__ = ("BaseTensorClient", "FileCacheTensorClient", "TensorClient")