Source code for debusine.tasks.debdiff
# Copyright 2024 The Debusine Developers
# See the AUTHORS file at the top-level directory of this distribution
#
# This file is part of Debusine. It is subject to the license terms
# in the LICENSE file found in the top-level directory of this
# distribution. No part of Debusine, including this file, may be copied,
# modified, propagated, or distributed except according to the terms
# contained in the LICENSE file.
"""Task to use debdiff in debusine."""
from pathlib import Path
from typing import Any
from debusine import utils
from debusine.artifacts import DebDiffArtifact
from debusine.artifacts.models import CollectionCategory
from debusine.client.models import RelationType
from debusine.tasks import BaseTaskWithExecutor, RunCommandTask
from debusine.tasks.models import DebDiffData, DebDiffDynamicData
from debusine.tasks.server import TaskDatabaseInterface
[docs]
class DebDiff(
RunCommandTask[DebDiffData, DebDiffDynamicData],
BaseTaskWithExecutor[DebDiffData, DebDiffDynamicData],
):
"""Task to use debdiff in debusine."""
TASK_VERSION = 1
CAPTURE_OUTPUT_FILENAME = "debdiff.txt"
[docs]
def __init__(
self,
task_data: dict[str, Any],
dynamic_task_data: dict[str, Any] | None = None,
) -> None:
"""Initialize object."""
super().__init__(task_data, dynamic_task_data)
# list of packages to be diffed
self._original_targets: list[Path] = []
self._new_targets: list[Path] = []
[docs]
def compute_dynamic_data(
self, task_database: TaskDatabaseInterface
) -> DebDiffDynamicData:
"""Resolve artifact lookups for this task."""
return DebDiffDynamicData(
environment_id=self.get_environment(
task_database,
self.data.environment,
default_category=CollectionCategory.ENVIRONMENTS,
),
input_source_artifacts_ids=(
None
if self.data.input.source_artifacts is None
else [
task_database.lookup_single_artifact(artifact)
for artifact in self.data.input.source_artifacts
]
),
input_binary_artifacts_ids=(
None
if self.data.input.binary_artifacts is None
else [
task_database.lookup_multiple_artifacts(artifact)
for artifact in self.data.input.binary_artifacts
]
),
)
def _cmdline(self) -> list[str]:
"""
Build the debdiff command line.
Use configuration of self.data and self.debdiff_target.
"""
cmd = [
"debdiff",
]
if extra_flags := self.data.extra_flags:
for flag in extra_flags:
# we already checked that the flags are sane...
cmd.append(flag)
cmd.extend(str(path) for path in self._original_targets)
cmd.extend(str(path) for path in self._new_targets)
return cmd
[docs]
def fetch_input(self, destination: Path) -> bool:
"""Download the required artifacts."""
assert self.dynamic_data
(original_directory := destination / "original").mkdir()
(new_directory := destination / "new").mkdir()
if self.dynamic_data.input_source_artifacts_ids:
assert len(self.dynamic_data.input_source_artifacts_ids) == 2
self.fetch_artifact(
self.dynamic_data.input_source_artifacts_ids[0],
original_directory,
)
self.fetch_artifact(
self.dynamic_data.input_source_artifacts_ids[1],
new_directory,
)
if self.dynamic_data.input_binary_artifacts_ids:
assert len(self.dynamic_data.input_binary_artifacts_ids) == 2
for artifact_id in self.dynamic_data.input_binary_artifacts_ids[0]:
self.fetch_artifact(artifact_id, original_directory)
for artifact_id in self.dynamic_data.input_binary_artifacts_ids[1]:
self.fetch_artifact(artifact_id, new_directory)
return True
[docs]
def configure_for_execution(self, download_directory: Path) -> bool:
"""
Set self._(original|new)_targets to the relevant files.
:param download_directory: where to search the files
:return: True if valid files were found
"""
self._prepare_executor_instance()
if self.executor_instance is None:
raise AssertionError("self.executor_instance cannot be None")
assert self.dynamic_data is not None
self.executor_instance.run(
["apt-get", "update"], run_as_root=True, check=True
)
self.executor_instance.run(
["apt-get", "--yes", "install", "devscripts"],
run_as_root=True,
check=True,
)
file_ending = ".dsc"
if self.dynamic_data.input_binary_artifacts_ids:
file_ending = ".changes"
original_files = utils.find_files_suffixes(
download_directory / "original", [file_ending]
)
if len(original_files) == 0:
list_of_files = sorted(
map(str, (download_directory / "original").iterdir())
)
self.append_to_log_file(
"configure_for_execution.log",
[
f"No original *{file_ending} file to be analyzed. "
f"Files: {list_of_files}"
],
)
return False
self._original_targets.append(original_files[0])
new_files = utils.find_files_suffixes(
download_directory / "new", [file_ending]
)
if len(new_files) == 0:
list_of_files = sorted(
map(str, (download_directory / "new").iterdir())
)
self.append_to_log_file(
"configure_for_execution.log",
[
f"No new *{file_ending} file to be analyzed. "
f"Files: {list_of_files}"
],
)
return False
self._new_targets.append(new_files[0])
return True
[docs]
def upload_artifacts(
self, exec_directory: Path, *, execution_success: bool # noqa: U100
) -> None:
"""Upload the DebDiffArtifact with the files and relationships."""
if not self.debusine:
raise AssertionError("self.debusine not set")
debdiff_file = exec_directory / self.CAPTURE_OUTPUT_FILENAME
original = " ".join(path.name for path in self._original_targets)
new = " ".join(path.name for path in self._new_targets)
debdiff_artifact = DebDiffArtifact.create(
debdiff_output=debdiff_file, original=original, new=new
)
uploaded = self.debusine.upload_artifact(
debdiff_artifact,
workspace=self.workspace_name,
work_request=self.work_request_id,
)
for source_artifact_id in self._source_artifacts_ids:
self.debusine.relation_create(
uploaded.id, source_artifact_id, RelationType.RELATES_TO
)
[docs]
def task_succeeded(
self, returncode: int | None, execute_directory: Path # noqa: U100
) -> bool:
"""
Evaluate task output and return success.
We don't actually check the output, but use the return code of
debdiff.
:return: True for success, False failure.
"""
return returncode in [0, 1]
[docs]
def get_label(self) -> str:
"""Return the task label."""
# TODO: copy the source package information in dynamic task data and
# use them here if available
return "debdiff"