Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
123 commits
Select commit Hold shift + click to select a range
d2ac198
Update yscope-dev-utils
sitaowang1998 Jul 15, 2025
cc8a097
Use boost install task
sitaowang1998 Jul 15, 2025
7f68bdc
Update install task variable names
sitaowang1998 Jul 15, 2025
2394649
Set CMP0074 to NEW to find boost
sitaowang1998 Jul 15, 2025
6ff3e33
Add uv to install script
sitaowang1998 Jul 15, 2025
7ae8a78
Fix cpp-lint root paths
sitaowang1998 Jul 15, 2025
56502f9
Fix clang-tidy file pattern
sitaowang1998 Jul 15, 2025
6f6becf
Limit build parallelism
sitaowang1998 Jul 17, 2025
a74523d
Bug fix
sitaowang1998 Jul 17, 2025
2345d22
Merge branch 'dep-concurrency' into yscope-dev-utils
sitaowang1998 Jul 17, 2025
77ee494
Bug fix
sitaowang1998 Jul 17, 2025
38b86c8
Merge branch 'dep-concurrency' into yscope-dev-utils
sitaowang1998 Jul 17, 2025
3698339
Bug fix
sitaowang1998 Jul 17, 2025
369e9f1
Rename variables to mirror CLP core
sitaowang1998 Aug 4, 2025
90aa5a2
Rename variables to mirror clp core
sitaowang1998 Aug 4, 2025
1769c95
Merge branch 'dep-concurrency' of github.com:sitaowang1998/spider int…
sitaowang1998 Aug 4, 2025
edaa834
Merge branch 'dep-concurrency' into yscope-dev-utils
sitaowang1998 Aug 4, 2025
7faac8f
Revert "Merge branch 'dep-concurrency' of github.com:sitaowang1998/sp…
sitaowang1998 Aug 4, 2025
f494a90
Add comment for deps parallelism default value
sitaowang1998 Aug 4, 2025
eb01bb2
Merge branch 'dep-concurrency' into yscope-dev-utils
sitaowang1998 Aug 4, 2025
ff2fe1c
Update yscope-dev-utils
sitaowang1998 Aug 4, 2025
d476e42
Merge branch 'main' into yscope-dev-utils
sitaowang1998 Aug 4, 2025
850126d
Merge branch 'yscope-dev-utils' into python_lint
sitaowang1998 Aug 4, 2025
65841a0
Add latest python lint config files
sitaowang1998 Aug 4, 2025
8564fc2
Update ruff lint tasks
sitaowang1998 Aug 4, 2025
a6e7d29
Fix ruff lint
sitaowang1998 Aug 4, 2025
573b448
Fix ruff lint
sitaowang1998 Aug 4, 2025
6ad72c3
Bug fix
sitaowang1998 Aug 4, 2025
ba7c6e5
Fix ruff
sitaowang1998 Aug 4, 2025
209acb1
Fix ruff
sitaowang1998 Aug 4, 2025
406b514
Reformat files
sitaowang1998 Aug 4, 2025
66892f5
Remove .inc from cpp linting
sitaowang1998 Aug 4, 2025
80f0a10
Merge branch 'yscope-dev-utils' into python_lint
sitaowang1998 Aug 4, 2025
3186a42
Add mypy and merge lint and test requirements.txt
sitaowang1998 Aug 4, 2025
0925938
Fix mysql connection type
sitaowang1998 Aug 4, 2025
6936a9b
Fix socket name type
sitaowang1998 Aug 4, 2025
7407090
Fix return type from db cursor
sitaowang1998 Aug 4, 2025
6a95b24
Fix db cursor return type
sitaowang1998 Aug 4, 2025
f29dcba
Fix mypy import untyped
sitaowang1998 Aug 4, 2025
453f209
Fix mypy and Popen
sitaowang1998 Aug 5, 2025
d1011c7
Fix generator type hint
sitaowang1998 Aug 5, 2025
a7dc642
Fix mypy
sitaowang1998 Aug 5, 2025
a7d92c2
Fix ruff
sitaowang1998 Aug 5, 2025
1c6213b
Simply socket return types.
sitaowang1998 Aug 5, 2025
0f13d07
Merge branch 'main' into python_lint
sitaowang1998 Aug 5, 2025
14d6326
Merge branch 'python_lint' into mypy_lint
sitaowang1998 Aug 5, 2025
55a727a
Add tombi lint tasks
sitaowang1998 Aug 5, 2025
c98fea1
Rename cpp build tasks
sitaowang1998 Aug 5, 2025
ef64454
Merge branch 'main' into mypy_lint
sitaowang1998 Aug 5, 2025
09ba8ad
Merge branch 'main' into tombi
sitaowang1998 Aug 5, 2025
4e7237e
Add basic python structure
sitaowang1998 Aug 5, 2025
1f944d0
Fix code structure
sitaowang1998 Aug 5, 2025
68992fc
Fix ruff lint
sitaowang1998 Aug 5, 2025
1127b22
Extend lint tasks to python directory
sitaowang1998 Aug 5, 2025
4c51c91
Add python build tasks
sitaowang1998 Aug 5, 2025
56878b2
Merge branch 'main' into mypy_lint
sitaowang1998 Aug 5, 2025
bb428c9
Merge branch 'mypy_lint' into tombi
sitaowang1998 Aug 5, 2025
944bd5e
Merge branch 'tombi' into build-task
sitaowang1998 Aug 5, 2025
d75bc15
Merge branch 'build-task' into python_structure
sitaowang1998 Aug 5, 2025
4b7eca2
Merge branch 'main' into tombi
sitaowang1998 Aug 5, 2025
8ddbda7
Merge branch 'tombi' into build-task
sitaowang1998 Aug 5, 2025
0d998ec
Merge branch 'build-task' into python_structure
sitaowang1998 Aug 5, 2025
6004d64
Fix yaml lint error
sitaowang1998 Aug 5, 2025
bcab5db
Fix tombi lint
sitaowang1998 Aug 5, 2025
a50d25a
Remove wrong mypy config
sitaowang1998 Aug 5, 2025
fbebb96
Fix typo and format file
sitaowang1998 Aug 5, 2025
0322bd5
Use typed msgpack and remove mypy config for msgpack from pyproject
sitaowang1998 Aug 6, 2025
2a08155
Update uv lock
sitaowang1998 Aug 6, 2025
dd29c23
Add task module
sitaowang1998 Aug 6, 2025
570cf2f
Merge branch 'python_structure' into python_task
sitaowang1998 Aug 6, 2025
9b2a175
Add data and improve type alias
sitaowang1998 Aug 6, 2025
32afe0a
Add task graph and reformat files
sitaowang1998 Aug 6, 2025
0b62f73
Merge branch 'main' into tombi
sitaowang1998 Aug 6, 2025
7384158
Merge branch 'main' into build-task
sitaowang1998 Aug 6, 2025
70ef90a
Merge branch 'main' into python_structure
sitaowang1998 Aug 6, 2025
1aae0cb
Merge branch 'main' into python_task
sitaowang1998 Aug 6, 2025
2f9b4a0
Fix typo
sitaowang1998 Aug 6, 2025
4e080ac
Fix set remove key error
sitaowang1998 Aug 6, 2025
b09515c
Increase min version of tombi
sitaowang1998 Aug 6, 2025
bad9675
Merge branch 'tombi' into build-task
sitaowang1998 Aug 6, 2025
e009ff4
Merge branch 'tombi' into python_structure
sitaowang1998 Aug 6, 2025
f11a3b6
Merge branch 'python_structure' into python_task
sitaowang1998 Aug 6, 2025
a0407a7
Merge branch 'main' into tombi
sitaowang1998 Aug 6, 2025
aa9a8de
Merge branch 'tombi' into build-task
sitaowang1998 Aug 6, 2025
3c7e794
Merge branch 'tombi' into python_structure
sitaowang1998 Aug 6, 2025
ca4ec29
Merge branch 'python_structure' into python_task
sitaowang1998 Aug 6, 2025
b4d6576
Add uv in README
sitaowang1998 Aug 6, 2025
23f31cd
Merge branch 'main' into build-task
sitaowang1998 Aug 6, 2025
0167ac0
Merge branch 'build-task' into python_structure
sitaowang1998 Aug 6, 2025
5a9cb76
Merge branch 'python_structure' into python_task
sitaowang1998 Aug 6, 2025
f447614
Fix redenduncy caused by merge
sitaowang1998 Aug 6, 2025
a84de83
Merge branch 'build-task' into python_structure
sitaowang1998 Aug 6, 2025
f94460f
Merge branch 'python_structure' into python_task
sitaowang1998 Aug 6, 2025
2d1b6fc
Merge branch 'main' into python_structure
sitaowang1998 Aug 7, 2025
5a35122
Merge branch 'main' into python_task
sitaowang1998 Aug 7, 2025
061d101
Merge branch 'main' into python_structure
sitaowang1998 Aug 7, 2025
451a80e
Merge branch 'main' into python_task
sitaowang1998 Aug 7, 2025
de149ee
Add integral types
sitaowang1998 Aug 7, 2025
d332dbe
Revert "Add integral types"
sitaowang1998 Aug 7, 2025
8c27b16
Restructure under src/spider
sitaowang1998 Aug 8, 2025
1b7ab77
Merge branch 'python_structure' into python_task
sitaowang1998 Aug 8, 2025
95b98c8
Merge branch 'main' into python_structure
sitaowang1998 Aug 8, 2025
e7b119c
Merge branch 'main' into python_task
sitaowang1998 Aug 8, 2025
8ffbd03
Fix import path
sitaowang1998 Aug 8, 2025
427dd6b
Merge branch 'main' into python_structure
sitaowang1998 Aug 8, 2025
a9c9e57
Merge branch 'main' into python_task
sitaowang1998 Aug 8, 2025
854cd11
Fix missing link
sitaowang1998 Aug 8, 2025
5565c9e
Merge branch 'python_structure' of github.com:sitaowang1998/spider in…
sitaowang1998 Aug 8, 2025
a9791e5
Merge branch 'python_structure' into python_task
sitaowang1998 Aug 8, 2025
01dd0c6
Fix task executor path
sitaowang1998 Aug 8, 2025
c6ccce6
Merge branch 'python_structure' into python_task
sitaowang1998 Aug 8, 2025
01c9c64
Merge branch 'main' into python_task
sitaowang1998 Aug 8, 2025
b86d47c
Merge branch 'main' into python_task
sitaowang1998 Aug 9, 2025
008c6fb
Export core
sitaowang1998 Aug 10, 2025
4d10f88
"Add default values for tasks"
sitaowang1998 Aug 10, 2025
f6192a3
Merge branch 'main' into python_task
sitaowang1998 Aug 14, 2025
ea76464
Fix merge
sitaowang1998 Aug 14, 2025
9448189
Fix merge
sitaowang1998 Aug 14, 2025
be143a7
Rename taskgraph.py to task_graph.py
sitaowang1998 Aug 15, 2025
c4c035a
Move class members to class docstring
sitaowang1998 Aug 15, 2025
fa935d1
Fix docstring
sitaowang1998 Aug 15, 2025
08b7965
Explicity check list not none and not empty
sitaowang1998 Aug 15, 2025
b07c858
Merge branch 'main' into python_task
sitaowang1998 Aug 15, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 31 additions & 0 deletions python/spider-py/src/spider_py/core/__init__.py
Original file line number Diff line number Diff line change
@@ -1 +1,32 @@
"""Spider core package."""

from .data import Data, DataId
from .task import (
Task,
TaskId,
TaskInput,
TaskInputData,
TaskInputOutput,
TaskInputValue,
TaskOutput,
TaskOutputData,
TaskOutputValue,
TaskState,
)
from .task_graph import TaskGraph

__all__ = [
"Data",
"DataId",
"Task",
"TaskGraph",
"TaskId",
"TaskInput",
"TaskInputData",
"TaskInputOutput",
"TaskInputValue",
"TaskOutput",
"TaskOutputData",
"TaskOutputValue",
"TaskState",
]
14 changes: 14 additions & 0 deletions python/spider-py/src/spider_py/core/data.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
"""Data module for Spider."""

from dataclasses import dataclass
from uuid import UUID

DataId = UUID


@dataclass
class Data:
"""Represents a data object."""

id: DataId
value: bytes
45 changes: 45 additions & 0 deletions python/spider-py/src/spider_py/core/task.py
Original file line number Diff line number Diff line change
@@ -1,5 +1,50 @@
"""Task module for Spider."""

from dataclasses import dataclass, field
from enum import IntEnum
from uuid import UUID, uuid4

from spider_py.core.data import DataId

TaskId = UUID


@dataclass
class TaskInputOutput:
"""Represents a task input that references the output of another task by its ID and position."""

task_id: TaskId
position: int


TaskInputValue = bytes
TaskInputData = DataId
TaskInput = TaskInputOutput | TaskInputValue | TaskInputData

TaskOutputValue = bytes
TaskOutputData = DataId
TaskOutput = TaskOutputValue | TaskOutputData


class TaskState(IntEnum):
"""Represents the state of a task"""

Pending = 0
Ready = 1
Running = 2
Succeeded = 3
Failed = 4
Cancelled = 5


@dataclass
class Task:
"""Represents a task in Spider."""

task_id: TaskId = field(default_factory=uuid4)
function_name: str = ""
state: TaskState = TaskState.Pending
timeout: float = 0
max_retries: int = 0
task_inputs: list[TaskInput] = field(default_factory=list)
task_outputs: list[TaskOutput] = field(default_factory=list)
Comment on lines +44 to +50

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🛠️ Refactor suggestion

Validate basic Task invariants (non-negative timeout and retries)

Prevent obviously invalid state early.

 @dataclass
 class Task:
@@
     task_outputs: list[TaskOutput] = field(default_factory=list)
+
+    def __post_init__(self) -> None:
+        if self.timeout < 0:
+            raise ValueError("timeout must be non-negative")
+        if self.max_retries < 0:
+            raise ValueError("max_retries must be non-negative")
🤖 Prompt for AI Agents
In python/spider-py/src/spider_py/core/task.py around lines 44 to 50, add
validation to enforce non-negative timeout and max_retries by implementing a
__post_init__ on the dataclass that checks if self.timeout < 0 or
self.max_retries < 0 and raises a ValueError with a clear message (e.g.,
"timeout must be >= 0" / "max_retries must be >= 0"); keep existing defaults and
types, and ensure tests or callers that create Task instances will see the
exception immediately for invalid values.

62 changes: 62 additions & 0 deletions python/spider-py/src/spider_py/core/task_graph.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,62 @@
"""TaskGraph module for Spider."""

from spider_py.core.task import Task, TaskId


class TaskGraph:
"""
Represents a task graph in Spider.
TaskGraph represents a directed acyclic graph (DAG) of tasks.
It stores:
- tasks: A dictionary mapping task ids to Task objects.
- dependencies: A list of tuples representing the dependencies between tasks. Each tuple
contains:
- parent task id
- child task id
- input_tasks: A set of task ids that have no parents (input tasks).
- output_tasks: A set of task ids that have no children (output tasks).
"""

def __init__(self) -> None:
"""Initializes an empty task graph."""
self.tasks: dict[TaskId, Task] = {}
self.dependencies: list[tuple[TaskId, TaskId]] = []
self.input_tasks: set[TaskId] = set()
self.output_tasks: set[TaskId] = set()

def add_task(
self, task: Task, parents: list[TaskId] | None = None, children: list[TaskId] | None = None
) -> None:
"""
Adds a task to the graph.
:param task: The task to add.
:param parents: The parent ids of the task. Must be already in the task graph.
:param children: The children ids of the task. Must be already in the task graph.
"""
self.tasks[task.task_id] = task
if parents is not None and len(parents) > 0:
for parent in parents:
self.dependencies.append((parent, task.task_id))
self.output_tasks.discard(parent)
else:
self.input_tasks.add(task.task_id)
if children is not None and len(children) > 0:
for child in children:
self.dependencies.append((task.task_id, child))
self.input_tasks.discard(child)
else:
self.output_tasks.add(task.task_id)

def get_parents(self, task_id: TaskId) -> list[Task]:
"""
:param task_id:
:return: Parent tasks of the task identified by `task_id`.
"""
return [self.tasks[parent] for (parent, child) in self.dependencies if child == task_id]

def get_children(self, task_id: TaskId) -> list[Task]:
"""
:param task_id:
:return: Child tasks of the task identified by `task_id`.
"""
return [self.tasks[child] for (parent, child) in self.dependencies if parent == task_id]