pytest-split 0.9.0__tar.gz → 0.11.0__tar.gz

{pytest_split-0.9.0 → pytest_split-0.11.0}/PKG-INFO

@@ -1,28 +1,29 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: pytest-split
-Version: 0.9.0
+Version: 0.11.0
 Summary: Pytest plugin which splits the test suite to equally sized sub suites based on test execution time.
-Home-page: https://jerry-git.github.io/pytest-split
 License: MIT
+License-File: LICENSE
 Keywords: pytest,plugin,split,tests
 Author: Jerry Pussinen
 Author-email: jerry.pussinen@gmail.com
-Requires-Python: >=3.8.1,<4.0
+Requires-Python: >=3.10,<4.0
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Typing :: Typed
-Requires-Dist: pytest (>=5,<9)
+Requires-Dist: pytest (>=5,<10)
 Project-URL: Documentation, https://jerry-git.github.io/pytest-split
+Project-URL: Homepage, https://jerry-git.github.io/pytest-split
 Project-URL: Repository, https://github.com/jerry-git/pytest-split
 Description-Content-Type: text/markdown
 
@@ -124,7 +125,7 @@ The `least_duration` algorithm walks the list of tests and assigns each test to
 * Clone this repository
 * Requirements:
   * [Poetry](https://python-poetry.org/)
-  * Python 3.8+
+  * Python 3.10+
 * Create a virtual environment and install the dependencies
 
 ```sh

{pytest_split-0.9.0 → pytest_split-0.11.0}/README.md

@@ -96,7 +96,7 @@ The `least_duration` algorithm walks the list of tests and assigns each test to
 * Clone this repository
 * Requirements:
   * [Poetry](https://python-poetry.org/)
-  * Python 3.8+
+  * Python 3.10+
 * Create a virtual environment and install the dependencies
 
 ```sh

{pytest_split-0.9.0 → pytest_split-0.11.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pytest-split"
-version = "0.9.0"
+version = "0.11.0"
 description = "Pytest plugin which splits the test suite to equally sized sub suites based on test execution time."
 authors = [
     "Jerry Pussinen <jerry.pussinen@gmail.com>",
@@ -18,11 +18,11 @@ classifiers = [
   "Operating System :: OS Independent",
   "Programming Language :: Python",
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3.8",
-  "Programming Language :: Python :: 3.9",
   "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",
   "Topic :: Software Development :: Libraries :: Python Modules",
   "Typing :: Typed",
 ]
@@ -32,11 +32,11 @@ packages = [{ include = 'pytest_split', from = 'src' }]
 
 
 [tool.poetry.dependencies]
-python = ">=3.8.1, <4.0"
-pytest = "^5 | ^6 | ^7 | ^8"
+python = ">=3.10, <4.0"
+pytest = "^5 | ^6 | ^7 | ^8 | ^9"
 
 
-[tool.poetry.dev-dependencies]
+[tool.poetry.group.dev.dependencies]
 importlib-metadata = "==4.11.*"
 mkdocstrings = {version = ">=0.18", extras = ["python"]}
 mkdocs-material = "*"
@@ -60,7 +60,7 @@ slowest-tests = "pytest_split.cli:list_slowest_tests"
 pytest-split = "pytest_split.plugin"
 
 [tool.black]
-target-version = ["py37", "py38", "py39"]
+target-version = ["py310", "py311", "py312", "py313", "py314"]
 include = '\.pyi?$'
 
 [tool.pytest.ini_options]
@@ -92,7 +92,7 @@ disallow_untyped_calls = false
 
 
 [tool.ruff]
-target-version = "py38" # The lowest supported version
+target-version = "py310" # The lowest supported version
 
 [tool.ruff.lint]
 # By default, enable all the lint rules.

pytest_split-0.11.0/src/pytest_split/algorithms.py

@@ -0,0 +1,186 @@
+import enum
+import heapq
+from abc import ABC, abstractmethod
+from operator import itemgetter
+from typing import TYPE_CHECKING, NamedTuple
+
+if TYPE_CHECKING:
+    from _pytest import nodes
+
+
+class TestGroup(NamedTuple):
+    selected: "list[nodes.Item]"
+    deselected: "list[nodes.Item]"
+    duration: float
+
+
+class AlgorithmBase(ABC):
+    """Abstract base class for the algorithm implementations."""
+
+    @abstractmethod
+    def __call__(
+        self, splits: int, items: "list[nodes.Item]", durations: "dict[str, float]"
+    ) -> "list[TestGroup]":
+        pass
+
+    def __hash__(self) -> int:
+        return hash(self.__class__.__name__)
+
+    def __eq__(self, other: object) -> bool:
+        if not isinstance(other, AlgorithmBase):
+            return NotImplemented
+        return self.__class__.__name__ == other.__class__.__name__
+
+
+class LeastDurationAlgorithm(AlgorithmBase):
+    """
+    Split tests into groups by runtime.
+    It walks the test items, starting with the test with largest duration.
+    It assigns the test with the largest runtime to the group with the smallest duration sum.
+
+    The algorithm sorts the items by their duration. Since the sorting algorithm is stable, ties will be broken by
+    maintaining the original order of items. It is therefore important that the order of items be identical on all nodes
+    that use this plugin. Due to issue #25 this might not always be the case.
+
+    :param splits: How many groups we're splitting in.
+    :param items: Test items passed down by Pytest.
+    :param durations: Our cached test runtimes. Assumes contains timings only of relevant tests
+    :return:
+        List of groups
+    """
+
+    def __call__(
+        self, splits: int, items: "list[nodes.Item]", durations: "dict[str, float]"
+    ) -> "list[TestGroup]":
+        items_with_durations = _get_items_with_durations(items, durations)
+
+        # add index of item in list
+        items_with_durations_indexed = [
+            (*tup, i) for i, tup in enumerate(items_with_durations)
+        ]
+
+        # Sort by name to ensure it's always the same order
+        items_with_durations_indexed = sorted(
+            items_with_durations_indexed, key=lambda tup: str(tup[0])
+        )
+
+        # sort in ascending order
+        sorted_items_with_durations = sorted(
+            items_with_durations_indexed, key=lambda tup: tup[1], reverse=True
+        )
+
+        selected: list[list[tuple[nodes.Item, int]]] = [[] for _ in range(splits)]
+        deselected: list[list[nodes.Item]] = [[] for _ in range(splits)]
+        duration: list[float] = [0 for _ in range(splits)]
+
+        # create a heap of the form (summed_durations, group_index)
+        heap: list[tuple[float, int]] = [(0, i) for i in range(splits)]
+        heapq.heapify(heap)
+        for item, item_duration, original_index in sorted_items_with_durations:
+            # get group with smallest sum
+            summed_durations, group_idx = heapq.heappop(heap)
+            new_group_durations = summed_durations + item_duration
+
+            # store assignment
+            selected[group_idx].append((item, original_index))
+            duration[group_idx] = new_group_durations
+            for i in range(splits):
+                if i != group_idx:
+                    deselected[i].append(item)
+
+            # store new duration - in case of ties it sorts by the group_idx
+            heapq.heappush(heap, (new_group_durations, group_idx))
+
+        groups = []
+        for i in range(splits):
+            # sort the items by their original index to maintain relative ordering
+            # we don't care about the order of deselected items
+            s = [
+                item
+                for item, original_index in sorted(selected[i], key=lambda tup: tup[1])
+            ]
+            group = TestGroup(
+                selected=s, deselected=deselected[i], duration=duration[i]
+            )
+            groups.append(group)
+        return groups
+
+
+class DurationBasedChunksAlgorithm(AlgorithmBase):
+    """
+    Split tests into groups by runtime.
+    Ensures tests are split into non-overlapping groups.
+    The original list of test items is split into groups by finding boundary indices i_0, i_1, i_2
+    and creating group_1 = items[0:i_0], group_2 = items[i_0, i_1], group_3 = items[i_1, i_2], ...
+
+    :param splits: How many groups we're splitting in.
+    :param items: Test items passed down by Pytest.
+    :param durations: Our cached test runtimes. Assumes contains timings only of relevant tests
+    :return: List of TestGroup
+    """
+
+    def __call__(
+        self, splits: int, items: "list[nodes.Item]", durations: "dict[str, float]"
+    ) -> "list[TestGroup]":
+        items_with_durations = _get_items_with_durations(items, durations)
+        time_per_group = sum(map(itemgetter(1), items_with_durations)) / splits
+
+        selected: list[list[nodes.Item]] = [[] for i in range(splits)]
+        deselected: list[list[nodes.Item]] = [[] for i in range(splits)]
+        duration: list[float] = [0 for i in range(splits)]
+
+        group_idx = 0
+        for item, item_duration in items_with_durations:
+            if duration[group_idx] >= time_per_group:
+                group_idx += 1
+
+            selected[group_idx].append(item)
+            for i in range(splits):
+                if i != group_idx:
+                    deselected[i].append(item)
+            duration[group_idx] += item_duration
+
+        return [
+            TestGroup(
+                selected=selected[i], deselected=deselected[i], duration=duration[i]
+            )
+            for i in range(splits)
+        ]
+
+
+def _get_items_with_durations(
+    items: "list[nodes.Item]", durations: "dict[str, float]"
+) -> "list[tuple[nodes.Item, float]]":
+    durations = _remove_irrelevant_durations(items, durations)
+    avg_duration_per_test = _get_avg_duration_per_test(durations)
+    items_with_durations = [
+        (item, durations.get(item.nodeid, avg_duration_per_test)) for item in items
+    ]
+    return items_with_durations
+
+
+def _get_avg_duration_per_test(durations: "dict[str, float]") -> float:
+    if durations:
+        avg_duration_per_test = sum(durations.values()) / len(durations)
+    else:
+        # If there are no durations, give every test the same arbitrary value
+        avg_duration_per_test = 1
+    return avg_duration_per_test
+
+
+def _remove_irrelevant_durations(
+    items: "list[nodes.Item]", durations: "dict[str, float]"
+) -> "dict[str, float]":
+    # Filtering down durations to relevant ones ensures the avg isn't skewed by irrelevant data
+    test_ids = [item.nodeid for item in items]
+    durations = {name: durations[name] for name in test_ids if name in durations}
+    return durations
+
+
+class Algorithms(enum.Enum):
+    duration_based_chunks = DurationBasedChunksAlgorithm()
+    least_duration = LeastDurationAlgorithm()
+
+    @staticmethod
+    def names() -> "list[str]":
+        return [x.name for x in Algorithms]

{pytest_split-0.9.0 → pytest_split-0.11.0}/src/pytest_split/cli.py

@@ -1,9 +1,5 @@
 import argparse
 import json
-from typing import TYPE_CHECKING
-
-if TYPE_CHECKING:
-    from typing import Dict
 
 
 def list_slowest_tests() -> None:
@@ -28,7 +24,7 @@ def list_slowest_tests() -> None:
     return _list_slowest_tests(json.load(args.durations_path), args.count)
 
 
-def _list_slowest_tests(durations: "Dict[str, float]", count: int) -> None:
+def _list_slowest_tests(durations: "dict[str, float]", count: int) -> None:
     slowest_tests = tuple(
         sorted(durations.items(), key=lambda item: item[1], reverse=True)
     )[:count]

{pytest_split-0.9.0 → pytest_split-0.11.0}/src/pytest_split/ipynb_compatibility.py

@@ -1,8 +1,6 @@
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
-    from typing import List
-
     from pytest_split.algorithms import TestGroup
 
 
@@ -45,8 +43,8 @@ def ensure_ipynb_compatibility(group: "TestGroup", items: list) -> None:  # type
 
 
 def _find_sibiling_ipynb_cells(
-    ipynb_node_id: str, item_node_ids: "List[str]"
-) -> "List[str]":
+    ipynb_node_id: str, item_node_ids: "list[str]"
+) -> "list[str]":
     """
     Returns all sibling IPyNb cells given an IPyNb cell nodeid.
     """

{pytest_split-0.9.0 → pytest_split-0.11.0}/src/pytest_split/plugin.py

@@ -10,8 +10,6 @@ from pytest_split import algorithms
 from pytest_split.ipynb_compatibility import ensure_ipynb_compatibility
 
 if TYPE_CHECKING:
-    from typing import Dict, List, Optional, Union
-
     from _pytest import nodes
     from _pytest.config import Config
     from _pytest.config.argparsing import Parser
@@ -77,7 +75,7 @@ def pytest_addoption(parser: "Parser") -> None:
 
 
 @pytest.hookimpl(tryfirst=True)
-def pytest_cmdline_main(config: "Config") -> "Optional[Union[int, ExitCode]]":
+def pytest_cmdline_main(config: "Config") -> "int | ExitCode | None":
     """
     Validate options.
     """
@@ -153,7 +151,7 @@ class PytestSplitPlugin(Base):
 
     @hookimpl(trylast=True)
     def pytest_collection_modifyitems(
-        self, config: "Config", items: "List[nodes.Item]"
+        self, config: "Config", items: "list[nodes.Item]"
     ) -> None:
         """
         Collect and select the tests we want to run, and deselect the rest.
@@ -193,7 +191,7 @@ class PytestSplitCachePlugin(Base):
         https://github.com/pytest-dev/pytest/blob/main/src/_pytest/main.py#L308
         """
         terminal_reporter = self.config.pluginmanager.get_plugin("terminalreporter")
-        test_durations: Dict[str, float] = {}
+        test_durations: dict[str, float] = {}
 
         for test_reports in terminal_reporter.stats.values():  # type: ignore[union-attr]
             for test_report in test_reports:

pytest_split-0.9.0/src/pytest_split/algorithms.py

@@ -1,162 +0,0 @@
-import enum
-import functools
-import heapq
-from operator import itemgetter
-from typing import TYPE_CHECKING, NamedTuple
-
-if TYPE_CHECKING:
-    from typing import Dict, List, Tuple
-
-    from _pytest import nodes
-
-
-class TestGroup(NamedTuple):
-    selected: "List[nodes.Item]"
-    deselected: "List[nodes.Item]"
-    duration: float
-
-
-def least_duration(
-    splits: int, items: "List[nodes.Item]", durations: "Dict[str, float]"
-) -> "List[TestGroup]":
-    """
-    Split tests into groups by runtime.
-    It walks the test items, starting with the test with largest duration.
-    It assigns the test with the largest runtime to the group with the smallest duration sum.
-
-    The algorithm sorts the items by their duration. Since the sorting algorithm is stable, ties will be broken by
-    maintaining the original order of items. It is therefore important that the order of items be identical on all nodes
-    that use this plugin. Due to issue #25 this might not always be the case.
-
-    :param splits: How many groups we're splitting in.
-    :param items: Test items passed down by Pytest.
-    :param durations: Our cached test runtimes. Assumes contains timings only of relevant tests
-    :return:
-        List of groups
-    """
-    items_with_durations = _get_items_with_durations(items, durations)
-
-    # add index of item in list
-    items_with_durations_indexed = [
-        (*tup, i) for i, tup in enumerate(items_with_durations)
-    ]
-
-    # Sort by name to ensure it's always the same order
-    items_with_durations_indexed = sorted(
-        items_with_durations_indexed, key=lambda tup: str(tup[0])
-    )
-
-    # sort in ascending order
-    sorted_items_with_durations = sorted(
-        items_with_durations_indexed, key=lambda tup: tup[1], reverse=True
-    )
-
-    selected: List[List[Tuple[nodes.Item, int]]] = [[] for _ in range(splits)]
-    deselected: List[List[nodes.Item]] = [[] for _ in range(splits)]
-    duration: List[float] = [0 for _ in range(splits)]
-
-    # create a heap of the form (summed_durations, group_index)
-    heap: List[Tuple[float, int]] = [(0, i) for i in range(splits)]
-    heapq.heapify(heap)
-    for item, item_duration, original_index in sorted_items_with_durations:
-        # get group with smallest sum
-        summed_durations, group_idx = heapq.heappop(heap)
-        new_group_durations = summed_durations + item_duration
-
-        # store assignment
-        selected[group_idx].append((item, original_index))
-        duration[group_idx] = new_group_durations
-        for i in range(splits):
-            if i != group_idx:
-                deselected[i].append(item)
-
-        # store new duration - in case of ties it sorts by the group_idx
-        heapq.heappush(heap, (new_group_durations, group_idx))
-
-    groups = []
-    for i in range(splits):
-        # sort the items by their original index to maintain relative ordering
-        # we don't care about the order of deselected items
-        s = [
-            item for item, original_index in sorted(selected[i], key=lambda tup: tup[1])
-        ]
-        group = TestGroup(selected=s, deselected=deselected[i], duration=duration[i])
-        groups.append(group)
-    return groups
-
-
-def duration_based_chunks(
-    splits: int, items: "List[nodes.Item]", durations: "Dict[str, float]"
-) -> "List[TestGroup]":
-    """
-    Split tests into groups by runtime.
-    Ensures tests are split into non-overlapping groups.
-    The original list of test items is split into groups by finding boundary indices i_0, i_1, i_2
-    and creating group_1 = items[0:i_0], group_2 = items[i_0, i_1], group_3 = items[i_1, i_2], ...
-
-    :param splits: How many groups we're splitting in.
-    :param items: Test items passed down by Pytest.
-    :param durations: Our cached test runtimes. Assumes contains timings only of relevant tests
-    :return: List of TestGroup
-    """
-    items_with_durations = _get_items_with_durations(items, durations)
-    time_per_group = sum(map(itemgetter(1), items_with_durations)) / splits
-
-    selected: List[List[nodes.Item]] = [[] for i in range(splits)]
-    deselected: List[List[nodes.Item]] = [[] for i in range(splits)]
-    duration: List[float] = [0 for i in range(splits)]
-
-    group_idx = 0
-    for item, item_duration in items_with_durations:
-        if duration[group_idx] >= time_per_group:
-            group_idx += 1
-
-        selected[group_idx].append(item)
-        for i in range(splits):
-            if i != group_idx:
-                deselected[i].append(item)
-        duration[group_idx] += item_duration
-
-    return [
-        TestGroup(selected=selected[i], deselected=deselected[i], duration=duration[i])
-        for i in range(splits)
-    ]
-
-
-def _get_items_with_durations(
-    items: "List[nodes.Item]", durations: "Dict[str, float]"
-) -> "List[Tuple[nodes.Item, float]]":
-    durations = _remove_irrelevant_durations(items, durations)
-    avg_duration_per_test = _get_avg_duration_per_test(durations)
-    items_with_durations = [
-        (item, durations.get(item.nodeid, avg_duration_per_test)) for item in items
-    ]
-    return items_with_durations
-
-
-def _get_avg_duration_per_test(durations: "Dict[str, float]") -> float:
-    if durations:
-        avg_duration_per_test = sum(durations.values()) / len(durations)
-    else:
-        # If there are no durations, give every test the same arbitrary value
-        avg_duration_per_test = 1
-    return avg_duration_per_test
-
-
-def _remove_irrelevant_durations(
-    items: "List[nodes.Item]", durations: "Dict[str, float]"
-) -> "Dict[str, float]":
-    # Filtering down durations to relevant ones ensures the avg isn't skewed by irrelevant data
-    test_ids = [item.nodeid for item in items]
-    durations = {name: durations[name] for name in test_ids if name in durations}
-    return durations
-
-
-class Algorithms(enum.Enum):
-    # values have to wrapped inside functools to avoid them being considered method definitions
-    duration_based_chunks = functools.partial(duration_based_chunks)
-    least_duration = functools.partial(least_duration)
-
-    @staticmethod
-    def names() -> "List[str]":
-        return [x.name for x in Algorithms]