virtool-workflow 6.0.0a7__tar.gz → 6.0.0a9__tar.gz

{virtool_workflow-6.0.0a7 → virtool_workflow-6.0.0a9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virtool-workflow
-Version: 6.0.0a7
+Version: 6.0.0a9
 Summary: A framework for developing bioinformatics workflows for Virtool.
 Home-page: https://github.com/virtool/virtool-workflow
 License: MIT
@@ -19,7 +19,7 @@ Requires-Dist: orjson (>=3.9.9,<4.0.0)
 Requires-Dist: pydantic-factories (>=1.17.3,<2.0.0)
 Requires-Dist: pyfixtures (>=1.0.0,<2.0.0)
 Requires-Dist: sentry-sdk (>=1.5.7,<2.0.0)
-Requires-Dist: virtool-core (>=10.0.1,<11.0.0)
+Requires-Dist: virtool-core (>=11.0.0,<12.0.0)
 Project-URL: Repository, https://github.com/virtool/virtool-workflow
 Description-Content-Type: text/markdown
 

{virtool_workflow-6.0.0a7 → virtool_workflow-6.0.0a9}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "virtool-workflow"
-version = "6.0.0-alpha.7"
+version = "6.0.0-alpha.9"
 description = "A framework for developing bioinformatics workflows for Virtool."
 authors = ["Ian Boyes", "Blake Smith", "Ryan Fang"]
 license = "MIT"
@@ -19,7 +19,7 @@ python = "~3.10"
 click = "^8.1.7"
 aiohttp = "^3.8.1"
 aiofiles = "^0.7.0"
-virtool-core = "^10.0.1"
+virtool-core = "^11.0.0"
 aioredis = "1.3.1"
 sentry-sdk = "^1.5.7"
 pyfixtures = "^1.0.0"
@@ -58,17 +58,9 @@ exclude = [
     ".ruff_cache",
     "__pypackages__",
 ]
-indent-width = 4
-line-length = 88
-target-version = "py310"
 
 [tool.ruff.lint]
-fixable = ["ALL", "I001"]
-
-[tool.ruff.format]
-indent-style = "space"
-line-ending = "auto"
-quote-style = "double"
+select = ["ALL"]
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]

{virtool_workflow-6.0.0a7 → virtool_workflow-6.0.0a9}/virtool_workflow/analysis/fastqc.py

@@ -2,12 +2,12 @@
 from __future__ import annotations
 
 import asyncio
-import statistics
 import shutil
+import statistics
 import tempfile
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Protocol, TextIO, IO
+from typing import IO, Protocol, TextIO
 
 from pyfixtures import fixture
 
@@ -49,16 +49,16 @@ class BaseQualityParser:
                 mean=statistics.mean([this.mean, other.mean]),
                 median=statistics.mean([this.median, other.median]),
                 lower_quartile=statistics.mean(
-                    [this.lower_quartile, other.lower_quartile]
+                    [this.lower_quartile, other.lower_quartile],
                 ),
                 upper_quartile=statistics.mean(
-                    [this.upper_quartile, other.upper_quartile]
+                    [this.upper_quartile, other.upper_quartile],
                 ),
                 tenth_percentile=statistics.mean(
-                    [this.tenth_percentile, other.tenth_percentile]
+                    [this.tenth_percentile, other.tenth_percentile],
                 ),
                 ninetieth_percentile=statistics.mean(
-                    [this.ninetieth_percentile, other.ninetieth_percentile]
+                    [this.ninetieth_percentile, other.ninetieth_percentile],
                 ),
             )
             for this, other in zip(self.data, parser.data)
@@ -109,7 +109,7 @@ class BaseQualityParser:
                         upper_quartile=upper_quartile,
                         tenth_percentile=tenth_percentile,
                         ninetieth_percentile=ninetieth_percentile,
-                    )
+                    ),
                 )
 
                 if i - max_index != 1:
@@ -208,7 +208,7 @@ class NucleotideCompositionParser:
             split = line.split()
 
             try:
-                g, a, t, c = [float(value) for value in split[1:]]
+                g, a, t, c = (float(value) for value in split[1:])
             except ValueError as err:
                 if "NaN" not in str(err):
                     raise
@@ -276,8 +276,7 @@ def _calculate_index_range(base: str) -> range:
 
 
 def _handle_base_quality_nan(split_line: list) -> list:
-    """
-    Parse a per-base quality line from FastQC containing NaN values.
+    """Parse a per-base quality line from FastQC containing NaN values.
 
     :param split_line: the quality line split into a :class:`.List`
     :return: replacement values
@@ -301,8 +300,7 @@ def _handle_base_quality_nan(split_line: list) -> list:
 
 
 def _parse_fastqc(fastqc_path: Path, output_path: Path) -> dict:
-    """
-    Parse the FastQC results at `fastqc_path`.
+    """Parse the FastQC results at `fastqc_path`.
 
     All FastQC data except the textual data file are removed.
 
@@ -333,7 +331,7 @@ def _parse_fastqc(fastqc_path: Path, output_path: Path) -> dict:
             nucleotide_composition = NucleotideCompositionParser()
             sequence_quality = SequenceQualityParser()
 
-            with open(new_path, "r") as f:
+            with open(new_path) as f:
                 while True:
                     line = f.readline()
 
@@ -358,7 +356,7 @@ def _parse_fastqc(fastqc_path: Path, output_path: Path) -> dict:
                     basic_statistics=basic_statistics,
                     nucleotide_composition=nucleotide_composition,
                     sequence_quality=sequence_quality,
-                )
+                ),
             )
 
     if len(sides) == 1:
@@ -412,7 +410,7 @@ def _parse_fastqc(fastqc_path: Path, output_path: Path) -> dict:
         "composition": [
             [round(n, 1) for n in [point.g, point.a, point.t, point.c]]
             for point in left.nucleotide_composition.composite(
-                right.nucleotide_composition
+                right.nucleotide_composition,
             ).data
         ],
         "count": basic.count,
@@ -432,14 +430,13 @@ class FastQCRunner(Protocol):
 
 @fixture
 async def fastqc(run_subprocess: RunSubprocess):
-    """
-    Provides an asynchronous function that can run FastQC as a subprocess.
+    """Provides an asynchronous function that can run FastQC as a subprocess.
 
     The function takes a one or two paths to FASTQ read files (:class:`.ReadPaths`) in
     a tuple.
 
     Example:
-
+    -------
     .. code-block:: python
 
         @step

{virtool_workflow-6.0.0a7 → virtool_workflow-6.0.0a9}/virtool_workflow/analysis/skewer.py

@@ -1,5 +1,5 @@
-"""
-Utilities and a fixture for using `Skewer <https://github.com/relipmoc/skewer>`_ to trim reads.
+"""Utilities and a fixture for using `Skewer <https://github.com/relipmoc/skewer>`_ to
+trim reads.
 """
 import asyncio
 import os
@@ -85,18 +85,16 @@ class SkewerResult:
 
     @property
     def left(self) -> Path:
-        """
-        The path to one of:
-            - the FASTQ trimming result for an unpaired Illumina dataset
-            - the FASTA trimming result for the left reads of a paired Illumina dataset
+        """The path to one of:
+        - the FASTQ trimming result for an unpaired Illumina dataset
+        - the FASTA trimming result for the left reads of a paired Illumina dataset
 
         """
         return self.read_paths[0]
 
     @property
     def right(self) -> Path | None:
-        """
-        The path to the rights reads of a paired Illumina dataset.
+        """The path to the rights reads of a paired Illumina dataset.
 
         ``None`` if the dataset in unpaired.
 
@@ -110,16 +108,14 @@ class SkewerResult:
 
 
 def calculate_skewer_trimming_parameters(
-    sample: WFSample, min_read_length: int
+    sample: WFSample, min_read_length: int,
 ) -> SkewerConfiguration:
-    """
-    Calculates trimming parameters based on the library type, and minimum allowed trim length.
+    """Calculates trimming parameters based on the library type, and minimum allowed trim length.
 
     :param sample: The sample to calculate trimming parameters for.
     :param min_read_length: The minimum length of a read before it is discarded.
     :return: the trimming parameters
     """
-
     config = SkewerConfiguration(
         min_length=min_read_length,
         mode=SkewerMode.PAIRED_END if sample.paired else SkewerMode.SINGLE_END,
@@ -145,15 +141,14 @@ class SkewerRunner(Protocol):
     """A protocol describing callables that can be used to run Skewer."""
 
     async def __call__(
-        self, config: SkewerConfiguration, paths: ReadPaths, output_path: Path
+        self, config: SkewerConfiguration, paths: ReadPaths, output_path: Path,
     ) -> SkewerResult:
         ...
 
 
 @fixture
 def skewer(proc: int, run_subprocess: RunSubprocess) -> SkewerRunner:
-    """
-    Provides an asynchronous function that can run skewer.
+    """Provides an asynchronous function that can run skewer.
 
     The provided function takes a :class:`.SkewerConfiguration` and a tuple of paths to
     the left and right reads to trim. If a single member tuple is provided, the dataset
@@ -163,7 +158,7 @@ def skewer(proc: int, run_subprocess: RunSubprocess) -> SkewerRunner:
     for the workflow run.
 
     Example:
-
+    -------
     .. code-block:: python
 
         @step
@@ -183,7 +178,7 @@ def skewer(proc: int, run_subprocess: RunSubprocess) -> SkewerRunner:
         raise RuntimeError("skewer is not installed.")
 
     async def func(
-        config: SkewerConfiguration, read_paths: ReadPaths, output_path: Path
+        config: SkewerConfiguration, read_paths: ReadPaths, output_path: Path,
     ):
         temp_path = Path(await asyncio.to_thread(mkdtemp, suffix="_virtool_skewer"))
 
@@ -224,7 +219,7 @@ def skewer(proc: int, run_subprocess: RunSubprocess) -> SkewerRunner:
         )
 
         read_paths = await asyncio.to_thread(
-            _rename_trimming_results, temp_path, output_path
+            _rename_trimming_results, temp_path, output_path,
         )
 
         return SkewerResult(command, output_path, process, read_paths)
@@ -233,12 +228,10 @@ def skewer(proc: int, run_subprocess: RunSubprocess) -> SkewerRunner:
 
 
 def _rename_trimming_results(temp_path: Path, output_path: Path) -> ReadPaths:
-    """
-    Rename Skewer output to a simple name used in Virtool.
+    """Rename Skewer output to a simple name used in Virtool.
 
     :param path: The path containing the results from Skewer
     """
-
     shutil.move(
         temp_path / "reads-trimmed.log",
         output_path / "trim.log",

{virtool_workflow-6.0.0a7 → virtool_workflow-6.0.0a9}/virtool_workflow/analysis/trimming.py

@@ -8,10 +8,9 @@ from virtool_workflow.data.samples import WFSample
 
 
 def calculate_trimming_cache_key(
-    sample_id: str, trimming_parameters: dict, program: str = "skewer"
+    sample_id: str, trimming_parameters: dict, program: str = "skewer",
 ):
-    """
-    Compute a unique cache key.
+    """Compute a unique cache key.
 
     **This is not currently used.**
 
@@ -21,7 +20,6 @@ def calculate_trimming_cache_key(
     :return: A unique cache key.
 
     """
-
     raw_key = "reads-" + json.dumps(
         {
             "id": sample_id,
@@ -35,8 +33,7 @@ def calculate_trimming_cache_key(
 
 
 def calculate_trimming_min_length(sample: WFSample) -> int:
-    """
-    Calculate the minimum trimming length that should be used for the passed sample.
+    """Calculate the minimum trimming length that should be used for the passed sample.
 
     This takes into account the library type (:class:`.LibraryType`) and the maximum
     observed read length in the sample.

{virtool_workflow-6.0.0a7 → virtool_workflow-6.0.0a9}/virtool_workflow/api/acquire.py

@@ -1,10 +1,10 @@
 import asyncio
 
-from aiohttp import ClientSession, TCPConnector, ClientConnectionError
+from aiohttp import ClientConnectionError, ClientSession, TCPConnector
 from structlog import get_logger
 from virtool_core.models.job import JobAcquired
 
-from virtool_workflow.errors import JobAlreadyAcquired, JobsAPIServerError, JobsAPIError
+from virtool_workflow.errors import JobAlreadyAcquired, JobsAPIError, JobsAPIServerError
 
 logger = get_logger("api")
 
@@ -13,16 +13,14 @@ async def acquire_job_by_id(
     jobs_api_connection_string: str,
     job_id: str,
 ) -> JobAcquired:
-    """
-    Acquire the job with a given ID via the API.
+    """Acquire the job with a given ID via the API.
 
     :param jobs_api_connection_string: The url for the jobs API.
     :param job_id: The id of the job to acquire
     :return: a job including its API key
     """
-
     async with ClientSession(
-        connector=TCPConnector(force_close=True, limit=100)
+        connector=TCPConnector(force_close=True, limit=100),
     ) as session:
         attempts = 4
 

{virtool_workflow-6.0.0a7 → virtool_workflow-6.0.0a9}/virtool_workflow/api/client.py

@@ -2,14 +2,14 @@ from contextlib import asynccontextmanager
 from pathlib import Path
 
 import aiofiles
-from aiohttp import ClientSession, BasicAuth
+from aiohttp import BasicAuth, ClientSession
 
 from virtool_workflow.api.utils import (
-    raise_exception_by_status_code,
     decode_json_response,
+    raise_exception_by_status_code,
 )
-from virtool_workflow.files import VirtoolFileFormat
 from virtool_workflow.errors import JobsAPIError
+from virtool_workflow.files import VirtoolFileFormat
 
 CHUNK_SIZE = 1024 * 1024 * 2
 
@@ -21,19 +21,17 @@ class APIClient:
 
     async def get_json(self, path: str) -> dict:
         """Get the JSON response from the provided API ``path``."""
-
         async with self.http.get(f"{self.jobs_api_connection_string}{path}") as resp:
             await raise_exception_by_status_code(resp)
             return await decode_json_response(resp)
 
     async def get_file(self, path: str, target_path: Path):
-        """
-        Download the file at URL ``path`` to the local filesystem path ``target_path``.
+        """Download the file at URL ``path`` to the local filesystem path ``target_path``.
         """
         async with self.http.get(f"{self.jobs_api_connection_string}{path}") as resp:
             if resp.status != 200:
                 raise JobsAPIError(
-                    f"Encountered {resp.status} while downloading '{path}'"
+                    f"Encountered {resp.status} while downloading '{path}'",
                 )
             async with aiofiles.open(target_path, "wb") as f:
                 async for chunk in resp.content.iter_chunked(CHUNK_SIZE):
@@ -42,8 +40,7 @@ class APIClient:
             return target_path
 
     async def patch_json(self, path: str, data: dict) -> dict:
-        """
-        Make a patch request against the provided API ``path`` and return the response
+        """Make a patch request against the provided API ``path`` and return the response
         as a dictionary of decoded JSON.
 
         :param path: the API path to make the request against
@@ -51,7 +48,7 @@ class APIClient:
         :return: the response as a dictionary of decoded JSON
         """
         async with self.http.patch(
-            f"{self.jobs_api_connection_string}{path}", json=data
+            f"{self.jobs_api_connection_string}{path}", json=data,
         ) as resp:
             await raise_exception_by_status_code(resp)
             return await decode_json_response(resp)
@@ -78,7 +75,7 @@ class APIClient:
 
     async def post_json(self, path: str, data: dict) -> dict:
         async with self.http.post(
-            f"{self.jobs_api_connection_string}{path}", json=data
+            f"{self.jobs_api_connection_string}{path}", json=data,
         ) as resp:
             await raise_exception_by_status_code(resp)
             return await decode_json_response(resp)
@@ -105,7 +102,7 @@ class APIClient:
 
     async def put_json(self, path: str, data: dict) -> dict:
         async with self.http.put(
-            f"{self.jobs_api_connection_string}{path}", json=data
+            f"{self.jobs_api_connection_string}{path}", json=data,
         ) as resp:
             await raise_exception_by_status_code(resp)
             return await decode_json_response(resp)
@@ -127,10 +124,9 @@ async def api_client(
     job_id: str,
     key: str,
 ):
-    """
-    An authenticated :class:``APIClient`` to make requests against the jobs API.
+    """An authenticated :class:``APIClient`` to make requests against the jobs API.
     """
     async with ClientSession(
-        auth=BasicAuth(login=f"job-{job_id}", password=key)
+        auth=BasicAuth(login=f"job-{job_id}", password=key),
     ) as http:
         yield APIClient(http, jobs_api_connection_string)

{virtool_workflow-6.0.0a7 → virtool_workflow-6.0.0a9}/virtool_workflow/api/utils.py

@@ -2,27 +2,26 @@ import asyncio
 import functools
 
 from aiohttp import (
-    ServerDisconnectedError,
     ClientConnectorError,
     ClientResponse,
     ContentTypeError,
+    ServerDisconnectedError,
 )
 from structlog import get_logger
 
 from virtool_workflow.errors import (
-    JobsAPIServerError,
-    JobsAPINotFound,
     JobsAPIBadRequest,
-    JobsAPIForbidden,
     JobsAPIConflict,
+    JobsAPIForbidden,
+    JobsAPINotFound,
+    JobsAPIServerError,
 )
 
 logger = get_logger("api")
 
 
 def retry(func):
-    """
-    Retry an API call five times when encountering the following exceptions:
+    """Retry an API call five times when encountering the following exceptions:
       * ``ConnectionRefusedError``.
       * ``ClientConnectorError``.
       * ``ServerDisconnectedError``.
@@ -47,7 +46,7 @@ def retry(func):
 
             attempts += 1
             get_logger("runtime").info(
-                f"Encountered {type(err).__name__}. Retrying in 5 seconds."
+                f"Encountered {type(err).__name__}. Retrying in 5 seconds.",
             )
             await asyncio.sleep(5)
 
@@ -57,8 +56,7 @@ def retry(func):
 
 
 async def decode_json_response(resp: ClientResponse) -> dict | list | None:
-    """
-    Decode a JSON response from a :class:``ClientResponse``.
+    """Decode a JSON response from a :class:``ClientResponse``.
 
     Raise a :class:`ValueError` if the response is not JSON.
 
@@ -72,8 +70,7 @@ async def decode_json_response(resp: ClientResponse) -> dict | list | None:
 
 
 async def raise_exception_by_status_code(resp: ClientResponse):
-    """
-    Raise an exception based on the status code of the response.
+    """Raise an exception based on the status code of the response.
 
     :param resp: the response to check
     :raise JobsAPIBadRequest: the response status code is 400
@@ -108,5 +105,5 @@ async def raise_exception_by_status_code(resp: ClientResponse):
             raise status_exception_map[resp.status](message)
         else:
             raise ValueError(
-                f"Status code {resp.status} not handled for response\n {resp}"
+                f"Status code {resp.status} not handled for response\n {resp}",
             )

{virtool_workflow-6.0.0a7 → virtool_workflow-6.0.0a9}/virtool_workflow/data/analyses.py

@@ -52,17 +52,14 @@ class WFAnalysis:
         """The workflow being run to populate the analysis."""
 
     async def delete(self):
-        """
-        Delete the analysis.
+        """Delete the analysis.
 
         This method should be called if the workflow fails before a result is uploaded.
         """
-
         await self._api.delete(f"/analyses/{self.id}")
 
     async def upload_file(self, path: Path, fmt: VirtoolFileFormat = "unknown"):
-        """
-        Upload files in the workflow environment that should be associated with the
+        """Upload files in the workflow environment that should be associated with the
         current analysis.
 
         :param path: the path to the file to upload
@@ -76,8 +73,7 @@ class WFAnalysis:
         )
 
     async def upload_result(self, results: dict[str, Any]):
-        """
-        Upload the results dict for the analysis.
+        """Upload the results dict for the analysis.
 
         :param results: the analysis results
         """
@@ -89,8 +85,7 @@ async def analysis(
     _api: APIClient,
     job: Job,
 ) -> WFAnalysis:
-    """
-    A :class:`.WFAnalysis` object that represents the analysis associated with the running
+    """A :class:`.WFAnalysis` object that represents the analysis associated with the running
     workflow.
     """
     id_ = job.args["analysis_id"]

{virtool_workflow-6.0.0a7 → virtool_workflow-6.0.0a9}/virtool_workflow/data/hmms.py

@@ -17,8 +17,7 @@ from virtool_workflow.runtime.run_subprocess import RunSubprocess
 
 @dataclass
 class WFHMMs:
-    """
-    A class that exposes:
+    """A class that exposes:
 
     1. A :class:`dict` the links `HMMER <http://hmmer.org/>`_ cluster IDs to Virtool
        annotation IDs.
@@ -37,24 +36,21 @@ class WFHMMs:
 
     @cached_property
     def cluster_annotation_map(self) -> dict[int, str]:
-        """
-        A :class:`dict` that maps cluster IDs used to identify HMMs in
+        """A :class:`dict` that maps cluster IDs used to identify HMMs in
         `HMMER <http://hmmer.org/>`_ to annotation IDs used in Virtool.
         """
         return {hmm.cluster: hmm.id for hmm in self.annotations}
 
     @property
     def profiles_path(self):
-        """
-        The path to the ``profiles.hmm`` file.
+        """The path to the ``profiles.hmm`` file.
 
         It can be provided directly to HMMER.
         """
         return self.path / "profiles.hmm"
 
     def get_id_by_cluster(self, cluster: int) -> str:
-        """
-        Get the Virtool HMM annotation ID for a given cluster ID.
+        """Get the Virtool HMM annotation ID for a given cluster ID.
 
         :param cluster: a cluster ID
         :return: the corresponding annotation ID
@@ -69,8 +65,7 @@ async def hmms(
     run_subprocess: RunSubprocess,
     work_path: Path,
 ):
-    """
-    A fixture for accessing HMM data.
+    """A fixture for accessing HMM data.
 
     The ``*.hmm`` file is copied from the data directory and ``hmmpress`` is run to
     create all the HMM files.