haystack/test/core/pipeline/test_utils.py
mathislucka eec91824bc
fix: pipeline run bugs in cyclic and acyclic pipelines (#8707)
* add component checks

* pipeline should run deterministically

* add FIFOQueue

* add agent tests

* add order dependent tests

* run new tests

* remove code that is not needed

* test: intermediate from cycle outputs are available outside cycle

* add tests for component checks (Claude)

* adapt tests for component checks (o1 review)

* chore: format

* remove tests that aren't needed anymore

* add _calculate_priority tests

* revert accidental change in pyproject.toml

* test format conversion

* adapt to naming convention

* chore: proper docstrings and type hints for PQ

* format

* add more unit tests

* rm unneeded comments

* test input consumption

* lint

* fix: docstrings

* lint

* format

* format

* fix license header

* fix license header

* add component run tests

* fix: pass correct input format to tracing

* fix types

* format

* format

* types

* add defaults from Socket instead of signature

- otherwise components with dynamic inputs would fail

* fix test names

* still wait for optional inputs on greedy variadic sockets

- mirrors previous behavior

* fix format

* wip: warn for ambiguous running order

* wip: alternative warning

* fix license header

* make code more readable

Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>

* Introduce content tracing to a behavioral test

* Fixing linting

* Remove debug print statements

* Fix tracer tests

* remove print

* test: test for component inputs

* test: remove testing for run order

* chore: update component checks from experimental

* chore: update pipeline and base from experimental

* refactor: remove unused method

* refactor: remove unused method

* refactor: outdated comment

* refactor: inputs state is updated as side effect

- to prepare for AsyncPipeline implementation

* format

* test: add file conversion test

* format

* fix: original implementation deepcopies outputs

* lint

* fix: from_dict was updated

* fix: format

* fix: test

* test: add test for thread safety

* remove unused imports

* format

* test: FIFOPriorityQueue

* chore: add release note

* fix: resolve merge conflict with mermaid changes

* fix: format

* fix: remove unused import

* refactor: rename to avoid accidental conflicts

* chore: remove unused inputs, add missing license header

* chore: extend release notes

* Update releasenotes/notes/fix-pipeline-run-2fefeafc705a6d91.yaml

Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>

* fix: format

* fix: format

* Update release note

---------

Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>
Co-authored-by: David S. Batista <dsbatista@gmail.com>
2025-02-06 14:19:47 +00:00

178 lines
5.3 KiB
Python

# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
#
# SPDX-License-Identifier: Apache-2.0
import pytest
from haystack.core.pipeline.utils import parse_connect_string, FIFOPriorityQueue
def test_parse_connection():
assert parse_connect_string("foobar") == ("foobar", None)
assert parse_connect_string("foo.bar") == ("foo", "bar")
@pytest.fixture
def empty_queue():
"""Fixture providing a fresh empty queue for each test."""
return FIFOPriorityQueue()
def test_empty_queue_initialization(empty_queue):
"""Test that a new queue is empty."""
assert len(empty_queue) == 0
assert not bool(empty_queue)
def test_push_single_item(empty_queue):
"""Test pushing a single item."""
empty_queue.push("item1", 1)
assert len(empty_queue) == 1
assert bool(empty_queue)
assert empty_queue.peek() == (1, "item1")
def test_push_multiple_items_different_priorities(empty_queue):
"""Test pushing multiple items with different priorities."""
items = [("item3", 3), ("item1", 1), ("item2", 2)]
for item, priority in items:
empty_queue.push(item, priority)
# Items should come out in priority order
assert empty_queue.pop() == (1, "item1")
assert empty_queue.pop() == (2, "item2")
assert empty_queue.pop() == (3, "item3")
def test_push_multiple_items_same_priority(empty_queue):
"""Test FIFO behavior for items with equal priority."""
items = [("first", 1), ("second", 1), ("third", 1)]
for item, priority in items:
empty_queue.push(item, priority)
# Items should come out in insertion order
assert empty_queue.pop() == (1, "first")
assert empty_queue.pop() == (1, "second")
assert empty_queue.pop() == (1, "third")
def test_mixed_priority_and_fifo(empty_queue):
"""Test mixed priority levels with some equal priorities."""
empty_queue.push("medium1", 2)
empty_queue.push("high", 1)
empty_queue.push("medium2", 2)
empty_queue.push("low", 3)
# Check extraction order
assert empty_queue.pop() == (1, "high")
assert empty_queue.pop() == (2, "medium1")
assert empty_queue.pop() == (2, "medium2")
assert empty_queue.pop() == (3, "low")
def test_peek_behavior(empty_queue):
"""Test that peek returns items without removing them."""
empty_queue.push("item1", 1)
empty_queue.push("item2", 2)
# Peek multiple times
for _ in range(3):
assert empty_queue.peek() == (1, "item1")
assert len(empty_queue) == 2
def test_get_behavior(empty_queue):
"""Test the get method with both empty and non-empty queues."""
# Test on empty queue
assert empty_queue.get() is None
# Test with items
empty_queue.push("item1", 1)
assert empty_queue.get() == (1, "item1")
assert empty_queue.get() is None # Queue should be empty again
def test_pop_empty_queue(empty_queue):
"""Test that pop raises IndexError on empty queue."""
with pytest.raises(IndexError, match="pop from empty queue"):
empty_queue.pop()
def test_peek_empty_queue(empty_queue):
"""Test that peek raises IndexError on empty queue."""
with pytest.raises(IndexError, match="peek at empty queue"):
empty_queue.peek()
def test_length_updates(empty_queue):
"""Test that length updates correctly with pushes and pops."""
initial_len = len(empty_queue)
assert initial_len == 0
# Test length increases
empty_queue.push("item1", 1)
assert len(empty_queue) == 1
empty_queue.push("item2", 2)
assert len(empty_queue) == 2
# Test length decreases
empty_queue.pop()
assert len(empty_queue) == 1
empty_queue.pop()
assert len(empty_queue) == 0
def test_bool_conversion(empty_queue):
"""Test boolean conversion in various states."""
# Empty queue should be False
assert not bool(empty_queue)
# Queue with items should be True
empty_queue.push("item", 1)
assert bool(empty_queue)
# Queue should be False again after removing item
empty_queue.pop()
assert not bool(empty_queue)
def test_large_number_of_items(empty_queue):
"""Test handling of a large number of items with mixed priorities."""
# Add 1000 items with 10 different priority levels
for i in range(1000):
priority = i % 10
empty_queue.push(f"item{i}", priority)
# Verify FIFO order within same priority
last_priority = -1
last_index = -1
for _ in range(1000):
priority, item = empty_queue.pop()
current_index = int(item[4:]) # Extract index from "itemX"
if priority == last_priority:
assert current_index > last_index, "FIFO order violated within same priority"
else:
assert priority > last_priority, "Priority order violated"
last_priority = priority
last_index = current_index
@pytest.mark.parametrize(
"items",
[
[(1, "A"), (1, "B"), (1, "C")], # Same priority
[(3, "A"), (2, "B"), (1, "C")], # Different priorities
[(2, "A"), (1, "B"), (2, "C")], # Mixed priorities
],
)
def test_queue_ordering_parametrized(empty_queue, items):
"""Parametrized test for different ordering scenarios."""
for priority, item in items:
empty_queue.push(item, priority)
sorted_items = sorted(items, key=lambda x: (x[0], items.index(x)))
for priority, item in sorted_items:
assert empty_queue.pop() == (priority, item)