130 lines
3.8 KiB
Python
130 lines
3.8 KiB
Python
# Split Miner - BPMN process discovery from event logs.
|
|
# Authors:
|
|
# imacat@mail.imacat.idv.tw (imacat), 2026/3/10
|
|
# AI assistance: Claude Code (Anthropic)
|
|
|
|
# Copyright (c) 2026 imacat.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
# implied. See the License for the specific language governing
|
|
# permissions and limitations under the License.
|
|
"""Tests for the DFG construction with a 5-task example.
|
|
|
|
Uses a small event log with 5 tasks to verify DFG construction,
|
|
edge frequencies, and source/sink detection.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import unittest
|
|
|
|
from split_miner.bpmn import Node, Task
|
|
from split_miner.dfg import DirectlyFollowsGraph
|
|
|
|
|
|
def _make_tasks(
|
|
labels: str,
|
|
) -> dict[str, Task]:
|
|
"""Create a Task for each single-character label.
|
|
|
|
:param labels: The labels as a string.
|
|
:return: A dict mapping label to Task.
|
|
"""
|
|
return {ch: Task(ch, ch) for ch in labels}
|
|
|
|
|
|
def _make_five_task_log() -> tuple[
|
|
dict[tuple[Node, ...], int], dict[str, Task]
|
|
]:
|
|
"""Build a 5-task event log.
|
|
|
|
L = {<a,b,c,d>^3, <a,c,b,d>^2, <a,e,d>^1}
|
|
|
|
:return: The event log and the task map.
|
|
"""
|
|
t: dict[str, Task] = _make_tasks("abcde")
|
|
traces: dict[tuple[Node, ...], int] = {
|
|
(t["a"], t["b"], t["c"], t["d"]): 3,
|
|
(t["a"], t["c"], t["b"], t["d"]): 2,
|
|
(t["a"], t["e"], t["d"]): 1,
|
|
}
|
|
return traces, t
|
|
|
|
|
|
class TestFiveTaskDFG(unittest.TestCase):
|
|
"""Tests for DFG with 5 tasks (a, b, c, d, e)."""
|
|
|
|
def setUp(self) -> None:
|
|
"""Set up the test.
|
|
|
|
:return: None.
|
|
"""
|
|
traces: dict[tuple[Node, ...], int]
|
|
traces, self.__t = _make_five_task_log()
|
|
self.__dfg: DirectlyFollowsGraph = (
|
|
DirectlyFollowsGraph(traces)
|
|
)
|
|
|
|
def test_nodes(self) -> None:
|
|
"""DFG has the correct 5 nodes."""
|
|
self.assertEqual(
|
|
self.__dfg.nodes,
|
|
set(self.__t.values()),
|
|
)
|
|
|
|
def test_edge_frequencies(self) -> None:
|
|
"""All 8 edge frequencies are correct."""
|
|
t: dict[str, Task] = self.__t
|
|
expected: dict[tuple[Node, Node], int] = {
|
|
(t["a"], t["b"]): 3,
|
|
(t["a"], t["c"]): 2,
|
|
(t["a"], t["e"]): 1,
|
|
(t["b"], t["c"]): 3,
|
|
(t["b"], t["d"]): 2,
|
|
(t["c"], t["b"]): 2,
|
|
(t["c"], t["d"]): 3,
|
|
(t["e"], t["d"]): 1,
|
|
}
|
|
for (src, tgt), freq in expected.items():
|
|
self.assertEqual(
|
|
self.__dfg.df_frequency(src, tgt),
|
|
freq,
|
|
f"|{src.node_id} -> {tgt.node_id}|"
|
|
f" should be {freq}"
|
|
)
|
|
|
|
def test_edges(self) -> None:
|
|
"""DFG has the correct 8 edges."""
|
|
t: dict[str, Task] = self.__t
|
|
expected: set[tuple[Node, Node]] = {
|
|
(t["a"], t["b"]), (t["a"], t["c"]),
|
|
(t["a"], t["e"]),
|
|
(t["b"], t["c"]), (t["b"], t["d"]),
|
|
(t["c"], t["b"]), (t["c"], t["d"]),
|
|
(t["e"], t["d"]),
|
|
}
|
|
self.assertEqual(self.__dfg.edges, expected)
|
|
|
|
def test_sources(self) -> None:
|
|
"""Sources include a (first task of traces)."""
|
|
self.assertIn(
|
|
self.__t["a"], self.__dfg.sources
|
|
)
|
|
|
|
def test_sinks(self) -> None:
|
|
"""Sinks include d (last task of traces)."""
|
|
self.assertIn(
|
|
self.__t["d"], self.__dfg.sinks
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|