def _create_job_runner()

in services/worker/src/worker/job_runner_factory.py [0:0]

• 156 lines of code
• 29 McCabe index (conditional complexity)

    def _create_job_runner(self, job_info: JobInfo) -> JobRunner:
        job_type = job_info["type"]
        if job_type == DatasetConfigNamesJobRunner.get_job_type():
            return DatasetConfigNamesJobRunner(
                job_info=job_info,
                app_config=self.app_config,
                hf_datasets_cache=self.hf_datasets_cache,
            )
        if job_type == DatasetFiletypesJobRunner.get_job_type():
            return DatasetFiletypesJobRunner(
                job_info=job_info,
                app_config=self.app_config,
                hf_datasets_cache=self.hf_datasets_cache,
            )
        if job_type == ConfigSplitNamesJobRunner.get_job_type():
            return ConfigSplitNamesJobRunner(
                job_info=job_info,
                app_config=self.app_config,
                hf_datasets_cache=self.hf_datasets_cache,
            )
        if job_type == SplitFirstRowsJobRunner.get_job_type():
            return SplitFirstRowsJobRunner(
                job_info=job_info,
                app_config=self.app_config,
                hf_datasets_cache=self.hf_datasets_cache,
                parquet_metadata_directory=self.parquet_metadata_directory,
                storage_client=self.storage_client,
            )
        if job_type == ConfigParquetAndInfoJobRunner.get_job_type():
            return ConfigParquetAndInfoJobRunner(
                job_info=job_info,
                app_config=self.app_config,
                hf_datasets_cache=self.hf_datasets_cache,
            )
        if job_type == ConfigParquetJobRunner.get_job_type():
            return ConfigParquetJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == ConfigParquetMetadataJobRunner.get_job_type():
            return ConfigParquetMetadataJobRunner(
                job_info=job_info,
                app_config=self.app_config,
                parquet_metadata_directory=self.parquet_metadata_directory,
            )
        if job_type == DatasetParquetJobRunner.get_job_type():
            return DatasetParquetJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == DatasetInfoJobRunner.get_job_type():
            return DatasetInfoJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == ConfigInfoJobRunner.get_job_type():
            return ConfigInfoJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == DatasetSizeJobRunner.get_job_type():
            return DatasetSizeJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == ConfigSizeJobRunner.get_job_type():
            return ConfigSizeJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == DatasetSplitNamesJobRunner.get_job_type():
            return DatasetSplitNamesJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == SplitIsValidJobRunner.get_job_type():
            return SplitIsValidJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == ConfigIsValidJobRunner.get_job_type():
            return ConfigIsValidJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == DatasetIsValidJobRunner.get_job_type():
            return DatasetIsValidJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == SplitImageUrlColumnsJobRunner.get_job_type():
            return SplitImageUrlColumnsJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == SplitOptInOutUrlsScanJobRunner.get_job_type():
            return SplitOptInOutUrlsScanJobRunner(
                job_info=job_info,
                app_config=self.app_config,
                hf_datasets_cache=self.hf_datasets_cache,
            )
        if job_type == ConfigOptInOutUrlsCountJobRunner.get_job_type():
            return ConfigOptInOutUrlsCountJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == DatasetOptInOutUrlsCountJobRunner.get_job_type():
            return DatasetOptInOutUrlsCountJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )

        if job_type == SplitOptInOutUrlsCountJobRunner.get_job_type():
            return SplitOptInOutUrlsCountJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == SplitPresidioEntitiesScanJobRunner.get_job_type():
            return SplitPresidioEntitiesScanJobRunner(
                job_info=job_info,
                app_config=self.app_config,
                hf_datasets_cache=self.hf_datasets_cache,
            )
        if job_type == DatasetPresidioEntitiesCountJobRunner.get_job_type():
            return DatasetPresidioEntitiesCountJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == SplitDescriptiveStatisticsJobRunner.get_job_type():
            return SplitDescriptiveStatisticsJobRunner(
                job_info=job_info,
                app_config=self.app_config,
                statistics_cache_directory=self.statistics_cache_directory,
                parquet_metadata_directory=self.parquet_metadata_directory,
            )
        if job_type == DatasetHubCacheJobRunner.get_job_type():
            return DatasetHubCacheJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == DatasetCompatibleLibrariesJobRunner.get_job_type():
            return DatasetCompatibleLibrariesJobRunner(
                job_info=job_info,
                app_config=self.app_config,
                hf_datasets_cache=self.hf_datasets_cache,
            )
        if job_type == DatasetModalitiesJobRunner.get_job_type():
            return DatasetModalitiesJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        if job_type == DatasetCroissantCrumbsJobRunner.get_job_type():
            return DatasetCroissantCrumbsJobRunner(
                job_info=job_info,
                app_config=self.app_config,
            )
        raise KeyError(f"Unsupported job type: '{job_type}'.")