Ejemplo n.º 1
0
    def execute(self, context):
        """
        Loads and merges data from report files of all finished tasks in a DAG.
        Relocates results to the "outputs_folder", removes "tmp_folder"
        """

        setup_cwl_logger(context["ti"])
        post_status(context)

        _, workflow_report = relocate_outputs(
            workflow=context["dag"].workflow,
            job_data=collect_reports(context),
            cwl_args=context["dag"].default_args["cwl"])

        return workflow_report
Ejemplo n.º 2
0
    def execute(self, context):
        """
        Loads job Object from the context. Sets "tmp_folder" and "output_folder"
        if they have not been set before in the job. In case "tmp_folder" and/or
        "output_folder" were read from the job and are relative, resolves paths
        relative to the "tmp_folder" and/or "outputs_folder" from "cwl_args".
        Dumps step outputs as a json file into "tmp_folder". Writes to X-Com report
        file location.
        """

        setup_cwl_logger(context["ti"])
        post_status(context)

        # for easy access
        dag_id = context["dag"].dag_id
        workflow = context["dag"].workflow
        run_id = context["run_id"].replace(":", "_").replace(
            "+", "_")  # to make it dumpable by json
        cwl_args = context["dag"].default_args["cwl"]

        # Loads job from dag_run configuration. Sets defaults from "workflow". Fails on missing input files
        job_data = load_job(workflow=workflow,
                            job=context["dag_run"].conf["job"],
                            cwl_args=cwl_args)

        job_data["tmp_folder"] = get_dir(
            get_absolute_path(
                job_data.get(
                    "tmp_folder",
                    mkdtemp(dir=cwl_args["tmp_folder"],
                            prefix=dag_id + "_" + run_id + "_")),
                cwl_args["tmp_folder"]))

        job_data["outputs_folder"] = get_dir(
            get_absolute_path(
                job_data.get(
                    "outputs_folder",
                    os.path.join(cwl_args["outputs_folder"], dag_id, run_id)),
                cwl_args["outputs_folder"]))

        _, _, _, step_report = get_temp_folders(task_id=self.task_id,
                                                job_data=job_data)

        dump_json(job_data, step_report)

        return step_report
Ejemplo n.º 3
0
    def execute(self, context):
        """
        Creates job from collected reports of all finished tasks in a DAG.
        Then executes a workflow constructed from the workflow step. Writes
        report file location to X-Com.
        """

        post_status(context)

        self.job_data = collect_reports(
            context)  # we need it also in "on_kill"
        _, step_report = execute_workflow_step(
            workflow=context["dag"].workflow,
            task_id=self.task_id,
            job_data=self.job_data,
            cwl_args=context["dag"].default_args["cwl"])

        return step_report
Ejemplo n.º 4
0
    def execute(self, context):
        """
        Creates job from collected reports of all finished tasks in a DAG.
        Then executes a workflow constructed from the workflow step. Writes
        report file location to X-Com.
        """

        setup_cwl_logger(context["ti"])
        post_status(context)

        self.job_data = collect_reports(context)         # we need it also in "on_kill"
        _, step_report, skipped = execute_workflow_step(
            workflow=context["dag"].workflow,
            task_id=self.task_id,
            job_data=self.job_data,
            cwl_args=context["dag"].default_args["cwl"]
        )

        if skipped:
            self.xcom_push(context, XCOM_RETURN_KEY, step_report)       # need to save empty report before raising exception
            raise AirflowSkipException("Skip workflow step execution")  # to mark it as skipped for Airflow

        return step_report