Run black

src/ephemeris/_config_models.py

@@ -12,7 +12,6 @@
     Extra,
 )
 
-
 StrOrPath = Union[Path, str]
 
 
@@ -30,6 +29,7 @@ class RepositoryInstallTarget(BaseModel):
 
 class RepositoryInstallTargets(BaseModel):
     """ """
+
     api_key: Optional[str]
     galaxy_instance: Optional[str]
     tools: List[RepositoryInstallTarget]
@@ -58,7 +58,9 @@ class Genome(BaseModel):
     version: Optional[str]  # Any version information associated with the data
 
     # Description of actions (data managers) to run on target genome.
-    indexers: Optional[List[str]]  # indexers to run - keyed on repository name - see data_managers.yml for how to resolve these to tools
+    indexers: Optional[
+        List[str]
+    ]  # indexers to run - keyed on repository name - see data_managers.yml for how to resolve these to tools
     skiplist: Optional[List[str]]  # unimplemented: but if we implement classes of indexers, these will be ones to skip
 
 
@@ -67,7 +69,7 @@ class Genomes(BaseModel):
 
 
 def _read_yaml(path: StrOrPath):
-    with open(path, "r") as f:
+    with open(path) as f:
         return yaml.safe_load(f)
 
 

src/ephemeris/_idc_data_managers_to_tools.py

@@ -84,8 +84,8 @@ def _parser():
     general_group = parser.add_argument_group("General options")
     add_verbosity_argument(general_group)
     add_log_file_argument(general_group)
-    parser.add_argument('--data-managers-conf', default="data_managers.yml")
-    parser.add_argument('--shed-install-output-conf', default="tools.yml")
+    parser.add_argument("--data-managers-conf", default="data_managers.yml")
+    parser.add_argument("--shed-install-output-conf", default="tools.yml")
     return parser
 
 

src/ephemeris/_idc_lint.py

@@ -10,7 +10,7 @@
 
 
 def read_yaml(path: Path):
-    with open(path, "r") as f:
+    with open(path) as f:
         return yaml.safe_load(f)
 
 
@@ -25,11 +25,13 @@ def lint_idc_directory(directory: Path):
     for data_manager in data_managers.values():
         data_manager_tool_id = data_manager.tool_id
         if not data_manager_tool_id.startswith("toolshed.g2.bx.psu.edu/"):
-            raise Exception(f"Expected a data manager repository from main Galaxy tool shed but discovered tool ID {data_manager_tool_id}")
+            raise Exception(
+                f"Expected a data manager repository from main Galaxy tool shed but discovered tool ID {data_manager_tool_id}"
+            )
 
     for genome in genomes.genomes:
         print(genome)
-        for indexer in (genome.indexers or []):
+        for indexer in genome.indexers or []:
             if indexer not in data_managers:
                 raise Exception(f"Failed to find data manager {indexer} referenced for genome {genome}")
 

src/ephemeris/_idc_split_data_manager_genomes.py

@@ -9,6 +9,7 @@
 import logging
 import os
 import re
+import xml.etree.ElementTree as ElementTree
 from copy import deepcopy
 from typing import (
     Any,
@@ -17,7 +18,6 @@
     List,
     Optional,
 )
-import xml.etree.ElementTree as ElementTree
 
 import requests
 import yaml
@@ -32,9 +32,7 @@
     DataManager,
     read_data_managers_configuration,
 )
-from .common_parser import (
-    get_common_args,
-)
+from .common_parser import get_common_args
 from .ephemeris_log import (
     disable_external_library_logging,
     setup_global_logger,
@@ -184,9 +182,7 @@ def walk_over_incomplete_runs(split_options: SplitOptions):
                 fetch_params.append({"sequence_name": description})
             elif re.match("^[A-Z_]+[0-9.]+", source):
                 fetch_params.append({"reference_source|reference_source_selector": "ncbi"})
-                fetch_params.append(
-                    {"reference_source|requested_identifier": source}
-                )
+                fetch_params.append({"reference_source|requested_identifier": source})
                 fetch_params.append({"sequence_name": genome["description"]})
                 fetch_params.append({"sequence.id": genome["id"]})
             elif re.match("^http", source):
@@ -247,7 +243,6 @@ def walk_over_incomplete_runs(split_options: SplitOptions):
 
 
 def split_genomes(split_options: SplitOptions) -> None:
-
     def write_task_file(build_id: str, indexer: str, run_data_manager: RunDataManager):
         split_genomes_path = split_options.split_genomes_path
         if not os.path.exists(split_options.split_genomes_path):
@@ -262,7 +257,6 @@ def write_task_file(build_id: str, indexer: str, run_data_manager: RunDataManage
 
 
 class GalaxyHistoryIsBuildComplete:
-
     def __init__(self, history_names: List[str]):
         self._history_names = history_names
 
@@ -272,7 +266,6 @@ def __call__(self, build_id: str, indexer_name: str) -> bool:
 
 
 class CVMFSPublishIsComplete:
-
     def __init__(self, records: Dict[str, List[str]]):
         self.records = records
 
@@ -284,18 +277,18 @@ def _parser():
     """returns the parser object."""
     # login required to check history...
     parser = get_common_args(login_required=True, log_file=True)
-    parser.add_argument('--merged-genomes-path', '-m', default="genomes.yml")
-    parser.add_argument('--split-genomes-path', '-s', default="data_manager_tasks")
-    parser.add_argument('--data-managers-path', default="data_managers.yml")
-    parser.add_argument('--complete-check-cvmfs', default=False, action="store_true")
-    parser.add_argument('--cvmfs-root', default="/cvmfs/idc.galaxyproject.org")
+    parser.add_argument("--merged-genomes-path", "-m", default="genomes.yml")
+    parser.add_argument("--split-genomes-path", "-s", default="data_manager_tasks")
+    parser.add_argument("--data-managers-path", default="data_managers.yml")
+    parser.add_argument("--complete-check-cvmfs", default=False, action="store_true")
+    parser.add_argument("--cvmfs-root", default="/cvmfs/idc.galaxyproject.org")
 
     parser.add_argument("--tool-id-mode", choices=["tool_shed_guid", "short"], default=DEFAULT_TOOL_ID_MODE)
 
     # filters
-    parser.add_argument('--filter-stage', default=None)
-    parser.add_argument('--filter-data-manager', default=None)
-    parser.add_argument('--filter-build-id', default=None)
+    parser.add_argument("--filter-stage", default=None)
+    parser.add_argument("--filter-data-manager", default=None)
+    parser.add_argument("--filter-build-id", default=None)
 
     return parser
 

src/ephemeris/run_data_managers.py

@@ -296,7 +296,10 @@ def run_jobs(jobs, skipped_jobs):
                     all_skipped_jobs.append(skipped_job)
             for job in jobs:
                 started_job = self.tool_client.run_tool(
-                    history_id=history_id, tool_id=job["tool_id"], tool_inputs=job["inputs"], data_manager_mode=data_manager_mode
+                    history_id=history_id,
+                    tool_id=job["tool_id"],
+                    tool_inputs=job["inputs"],
+                    data_manager_mode=data_manager_mode,
                 )
                 log.info(
                     'Dispatched job %i. Running DM: "%s" with parameters: %s'
@@ -357,7 +360,9 @@ def _parser():
         action="store_true",
         help="Do not stop running when jobs have failed.",
     )
-    parser.add_argument("--data-manager-mode", "--data_manager_mode", choices=["bundle", "populate", "dry_run"], default="populate")
+    parser.add_argument(
+        "--data-manager-mode", "--data_manager_mode", choices=["bundle", "populate", "dry_run"], default="populate"
+    )
     parser.add_argument("--history-name", default=None)
     return parser
 
@@ -374,7 +379,13 @@ def main(argv=None):
     gi = get_galaxy_connection(args, file=args.config, log=log, login_required=True)
     config = load_yaml_file(args.config)
     data_managers = DataManagers(gi, config)
-    data_managers.run(log, args.ignore_errors, args.overwrite, data_manager_mode=args.data_manager_mode, history_name=args.history_name)
+    data_managers.run(
+        log,
+        args.ignore_errors,
+        args.overwrite,
+        data_manager_mode=args.data_manager_mode,
+        history_name=args.history_name,
+    )
 
 
 if __name__ == "__main__":

src/ephemeris/shed_tools.py

@@ -33,6 +33,7 @@
 Galaxy's configuration directory and set Galaxy configuration option
 `tool_config_file` to include it.
 """
+
 import datetime as dt
 import json
 import logging

tests/test_idc_lint.py

@@ -5,7 +5,6 @@
 from ephemeris._idc_lint import lint_idc_directory
 from .test_split_genomes import setup_mock_idc_dir
 
-
 MISSPELLED_DATA_MANAGER_YAML_STR = """
 data_manager_fetch_genome_dbkeys_all_fasta:
   tool_id: 'toolshed.g2.bx.psu.edu/repos/devteam/data_manager_fetch_genome_dbkeys_all_fasta/data_manager_fetch_genome_all_fasta_dbkey/0.0.3'

tests/test_split_genomes.py

@@ -59,7 +59,7 @@ def setup_mock_idc_dir(directory: Path):
 
 
 def read_and_validate_run_data_manager_yaml(path):
-    with open(path, "r") as f:
+    with open(path) as f:
         return RunDataManagers(**yaml.safe_load(f))
 
 
@@ -90,7 +90,10 @@ def test_split_genomes(tmp_path: Path):
     run = read_and_validate_run_data_manager_yaml(new_task_run_yaml)
     assert len(run.data_managers) == 1
     data_manager = run.data_managers[0]
-    assert data_manager.id == "toolshed.g2.bx.psu.edu/repos/devteam/data_manager_twobit_builder/twobit_builder_data_manager/0.0.2"
+    assert (
+        data_manager.id
+        == "toolshed.g2.bx.psu.edu/repos/devteam/data_manager_twobit_builder/twobit_builder_data_manager/0.0.2"
+    )
     assert data_manager.items[0]["id"] == "hg19_rCRS_pUC18_phiX174"
     assert data_manager.items[0]["dbkey"] == "hg19_rCRS_pUC18_phiX174"