Fix UP031 errors - Part 5

Also:
- Add type annotations.
- Small refactorings.

lib/galaxy/datatypes/interval.py

@@ -284,7 +284,7 @@ def as_ucsc_display_file(self, dataset: DatasetProtocol, **kwd) -> Union[FileObj
             if t >= 0:  # strand column (should) exists
                 for i, elems in enumerate(compression_utils.file_iter(dataset.get_file_name())):
                     strand = "+"
-                    name = "region_%i" % i
+                    name = f"region_{i}"
                     if n >= 0 and n < len(elems):
                         name = cast(str, elems[n])
                     if t < len(elems):
@@ -293,7 +293,7 @@ def as_ucsc_display_file(self, dataset: DatasetProtocol, **kwd) -> Union[FileObj
                     fh.write("{}\n".format("\t".join(tmp)))
             elif n >= 0:  # name column (should) exists
                 for i, elems in enumerate(compression_utils.file_iter(dataset.get_file_name())):
-                    name = "region_%i" % i
+                    name = f"region_{i}"
                     if n >= 0 and n < len(elems):
                         name = cast(str, elems[n])
                     tmp = [elems[c], elems[s], elems[e], name]
@@ -346,8 +346,7 @@ def ucsc_links(self, dataset: DatasetProtocol, type: str, app, base_url: str) ->
                 filename="ucsc_" + site_name,
             )
             display_url = quote_plus(
-                "%s%s/display_as?id=%i&display_app=%s&authz_method=display_at"
-                % (
+                "{}{}/display_as?id={}&display_app={}&authz_method=display_at".format(
                     base_url,
                     app.url_for(controller="root"),
                     dataset.id,
@@ -784,8 +783,7 @@ def _get_remote_call_url(
         internal_url = f"{app.url_for(controller='dataset', dataset_id=dataset.id, action='display_at', filename=f'{type}_{site_name}')}"
         base_url = app.config.get("display_at_callback", base_url)
         display_url = quote_plus(
-            "%s%s/display_as?id=%i&display_app=%s&authz_method=display_at"
-            % (
+            "{}{}/display_as?id={}&display_app={}&authz_method=display_at".format(
                 base_url,
                 app.url_for(controller="root"),
                 dataset.id,
@@ -1567,8 +1565,7 @@ def ucsc_links(self, dataset: DatasetProtocol, type: str, app, base_url: str) ->
                 if site_name in app.datatypes_registry.get_display_sites("ucsc"):
                     internal_url = f"{app.url_for(controller='dataset', dataset_id=dataset.id, action='display_at', filename='ucsc_' + site_name)}"
                     display_url = quote_plus(
-                        "%s%s/display_as?id=%i&display_app=%s&authz_method=display_at"
-                        % (
+                        "{}{}/display_as?id={}&display_app={}&authz_method=display_at".format(
                             base_url,
                             app.url_for(controller="root"),
                             dataset.id,

lib/galaxy/datatypes/mothur.py

@@ -1085,7 +1085,7 @@ def make_html_table(self, dataset: DatasetProtocol, skipchars: Optional[List] =
             out += "<th>2. Flows</th>"
             for i in range(3, dataset.metadata.columns + 1):
                 base = dataset.metadata.flow_order[(i + 1) % 4]
-                out += "<th>%d. %s</th>" % (i - 2, base)
+                out += f"<th>{i - 2}. {base}</th>"
             out += "</tr>"
             out += self.make_html_peek_rows(dataset, skipchars=skipchars)
             out += "</table>"

lib/galaxy/datatypes/sequence.py

@@ -76,7 +76,7 @@ def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
                 parsed_data = json.load(open(dataset.get_file_name()))
                 # dataset.peek = json.dumps(data, sort_keys=True, indent=4)
                 dataset.peek = data.get_file_peek(dataset.get_file_name())
-                dataset.blurb = "%d sections" % len(parsed_data["sections"])
+                dataset.blurb = "{} sections".format(len(parsed_data["sections"]))
             except Exception:
                 dataset.peek = "Not FQTOC file"
                 dataset.blurb = "Not FQTOC file"
@@ -465,7 +465,7 @@ def split(cls, input_datasets: List, subdir_generator_function: Callable, split_
             raise Exception("Tool does not define a split mode")
         elif split_params["split_mode"] == "number_of_parts":
             split_size = int(split_params["split_size"])
-            log.debug("Split %s into %i parts..." % (input_file, split_size))
+            log.debug("Split %s into %i parts...", input_file, split_size)
             # if split_mode = number_of_parts, and split_size = 10, and
             # we know the number of sequences (say 1234), then divide by
             # by ten, giving ten files of approx 123 sequences each.
@@ -484,7 +484,7 @@ def split(cls, input_datasets: List, subdir_generator_function: Callable, split_
             # Split the input file into as many sub-files as required,
             # each containing to_size many sequences
             batch_size = int(split_params["split_size"])
-            log.debug("Split %s into batches of %i records..." % (input_file, batch_size))
+            log.debug("Split %s into batches of %i records...", input_file, batch_size)
             cls._count_split(input_file, batch_size, subdir_generator_function)
         else:
             raise Exception(f"Unsupported split mode {split_params['split_mode']}")
@@ -496,7 +496,7 @@ def _size_split(cls, input_file: str, chunk_size: int, subdir_generator_function
         This does of course preserve complete records - it only splits at the
         start of a new FASTQ sequence record.
         """
-        log.debug("Attemping to split FASTA file %s into chunks of %i bytes" % (input_file, chunk_size))
+        log.debug("Attemping to split FASTA file %s into chunks of %i bytes", input_file, chunk_size)
         with open(input_file) as f:
             part_file = None
             try:
@@ -530,7 +530,7 @@ def _size_split(cls, input_file: str, chunk_size: int, subdir_generator_function
     @classmethod
     def _count_split(cls, input_file: str, chunk_size: int, subdir_generator_function: Callable) -> None:
         """Split a FASTA file into chunks based on counting records."""
-        log.debug("Attemping to split FASTA file %s into chunks of %i sequences" % (input_file, chunk_size))
+        log.debug("Attemping to split FASTA file %s into chunks of %i sequences", input_file, chunk_size)
         with open(input_file) as f:
             part_file = None
             try:

lib/galaxy/datatypes/tabular.py

@@ -1321,7 +1321,7 @@ def set_meta(
                     if line:
                         line_pieces = line.split("\t")
                         if len(line_pieces) != 22:
-                            raise Exception("%s:%d:Corrupt line!" % (dataset.get_file_name(), i))
+                            raise Exception(f"{dataset.get_file_name()}:{i}:Corrupt line!")
                         lanes[line_pieces[2]] = 1
                         tiles[line_pieces[3]] = 1
                         barcodes[line_pieces[6]] = 1
@@ -1353,7 +1353,7 @@ def set_meta(
                 "str",
             ]
             dataset.metadata.lanes = list(lanes.keys())
-            dataset.metadata.tiles = ["%04d" % int(t) for t in tiles.keys()]
+            dataset.metadata.tiles = [f"{int(t):04d}" for t in tiles.keys()]
             dataset.metadata.barcodes = [_ for _ in barcodes.keys() if _ != "0"] + [
                 "NoIndex" for _ in barcodes.keys() if _ == "0"
             ]
@@ -1477,7 +1477,7 @@ def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> N
                 except StopIteration:
                     pass
                 except csv.Error as e:
-                    raise Exception("CSV reader error - line %d: %s" % (reader.line_num, e))
+                    raise Exception(f"CSV reader error - line {reader.line_num}: {e}")
                 else:
                     data_lines = reader.line_num - 1
 

lib/galaxy/datatypes/text.py

@@ -544,7 +544,7 @@ def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> N
                     tax_names = []
                     for entry in json_dict:
                         if "taxonId" in entry:
-                            names = "%d: %s" % (entry["taxonId"], ",".join(entry["speciesNames"]))
+                            names = "{}: {}".format(entry["taxonId"], ",".join(entry["speciesNames"]))
                             tax_names.append(names)
                     dataset.metadata.taxon_names = tax_names
                 except Exception:

lib/galaxy/datatypes/util/gff_util.py

@@ -56,11 +56,11 @@ def __init__(
         # Handle feature, score column.
         self.feature_col = feature_col
         if self.nfields <= self.feature_col:
-            raise MissingFieldError("No field for feature_col (%d)" % feature_col)
+            raise MissingFieldError(f"No field for feature_col ({feature_col})")
         self.feature = self.fields[self.feature_col]
         self.score_col = score_col
         if self.nfields <= self.score_col:
-            raise MissingFieldError("No field for score_col (%d)" % score_col)
+            raise MissingFieldError(f"No field for score_col ({score_col})")
         self.score = self.fields[self.score_col]
 
         # GFF attributes.

lib/galaxy/exceptions/error_codes.py

@@ -28,7 +28,7 @@ def __str__(self):
 
     def __repr__(self):
         """Return object representation of this error code."""
-        return "ErrorCode[code=%d,message=%s]" % (self.code, str(self.default_error_message))
+        return f"ErrorCode[code={self.code},message={str(self.default_error_message)}]"
 
     def __int__(self):
         """Return the error code integer."""

lib/galaxy/job_metrics/instrumenters/core.py

@@ -36,9 +36,9 @@ def format(self, key: str, value: Any) -> FormattedMetric:
             return FormattedMetric("Container Type", value)
         value = int(value)
         if key == GALAXY_SLOTS_KEY:
-            return FormattedMetric("Cores Allocated", "%d" % value)
+            return FormattedMetric("Cores Allocated", f"{value}")
         elif key == GALAXY_MEMORY_MB_KEY:
-            return FormattedMetric("Memory Allocated (MB)", "%d" % value)
+            return FormattedMetric("Memory Allocated (MB)", f"{value}")
         elif key == RUNTIME_SECONDS_KEY:
             return FormattedMetric("Job Runtime (Wall Clock)", seconds_to_str(value))
         else:

lib/galaxy/jobs/__init__.py

@@ -2768,8 +2768,10 @@ def finish(self, stdout, stderr, tool_exit_code=None, **kwds):
 
         # This may have ended too soon
         log.debug(
-            "task %s for job %d ended; exit code: %d"
-            % (self.task_id, self.job_id, tool_exit_code if tool_exit_code is not None else -256)
+            "task %s for job %d ended; exit code: %d",
+            self.task_id,
+            self.job_id,
+            tool_exit_code if tool_exit_code is not None else -256,
         )
         # default post job setup_external_metadata
         task = self.get_task()

lib/galaxy/jobs/handler.py

@@ -552,22 +552,22 @@ def __handle_waiting_jobs(self):
                 if job_state == JOB_WAIT:
                     new_waiting_jobs.append(job.id)
                 elif job_state == JOB_INPUT_ERROR:
-                    log.info("(%d) Job unable to run: one or more inputs in error state" % job.id)
+                    log.info("(%d) Job unable to run: one or more inputs in error state", job.id)
                 elif job_state == JOB_INPUT_DELETED:
-                    log.info("(%d) Job unable to run: one or more inputs deleted" % job.id)
+                    log.info("(%d) Job unable to run: one or more inputs deleted", job.id)
                 elif job_state == JOB_READY:
                     self.dispatcher.put(self.job_wrappers.pop(job.id))
-                    log.info("(%d) Job dispatched" % job.id)
+                    log.info("(%d) Job dispatched", job.id)
                 elif job_state == JOB_DELETED:
-                    log.info("(%d) Job deleted by user while still queued" % job.id)
+                    log.info("(%d) Job deleted by user while still queued", job.id)
                 elif job_state == JOB_ADMIN_DELETED:
-                    log.info("(%d) Job deleted by admin while still queued" % job.id)
+                    log.info("(%d) Job deleted by admin while still queued", job.id)
                 elif job_state in (JOB_USER_OVER_QUOTA, JOB_USER_OVER_TOTAL_WALLTIME):
                     if job_state == JOB_USER_OVER_QUOTA:
-                        log.info("(%d) User (%s) is over quota: job paused" % (job.id, job.user_id))
+                        log.info("(%d) User (%s) is over quota: job paused", job.id, job.user_id)
                         what = "your disk quota"
                     else:
-                        log.info("(%d) User (%s) is over total walltime limit: job paused" % (job.id, job.user_id))
+                        log.info("(%d) User (%s) is over total walltime limit: job paused", job.id, job.user_id)
                         what = "your total job runtime"
 
                     job.set_state(model.Job.states.PAUSED)
@@ -580,7 +580,7 @@ def __handle_waiting_jobs(self):
                     # A more informative message is shown wherever the job state is set to error
                     pass
                 else:
-                    log.error("(%d) Job in unknown state '%s'" % (job.id, job_state))
+                    log.error("(%d) Job in unknown state '%s'", job.id, job_state)
                     new_waiting_jobs.append(job.id)
             except Exception:
                 log.exception("failure running job %d", job.id)
@@ -1277,7 +1277,7 @@ def stop(self, job, job_wrapper):
 
     def recover(self, job, job_wrapper):
         runner_name = (job.job_runner_name.split(":", 1))[0]
-        log.debug("recovering job %d in %s runner" % (job.id, runner_name))
+        log.debug("recovering job %d in %s runner", job.id, runner_name)
         runner = self.get_job_runner(job_wrapper)
         try:
             runner.recover(job, job_wrapper)

lib/galaxy/jobs/runners/__init__.py

@@ -129,7 +129,7 @@ def _init_worker_threads(self):
         self.work_threads = []
         log.debug(f"Starting {self.nworkers} {self.runner_name} workers")
         for i in range(self.nworkers):
-            worker = threading.Thread(name="%s.work_thread-%d" % (self.runner_name, i), target=self.run_next)
+            worker = threading.Thread(name=f"{self.runner_name}.work_thread-{i}", target=self.run_next)
             worker.daemon = True
             worker.start()
             self.work_threads.append(worker)
@@ -493,7 +493,7 @@ def _handle_metadata_externally(self, job_wrapper: "MinimalJobWrapper", resolve_
                     env=os.environ,
                     preexec_fn=os.setpgrp,
                 )
-            log.debug("execution of external set_meta for job %d finished" % job_wrapper.job_id)
+            log.debug("execution of external set_meta for job %d finished", job_wrapper.job_id)
 
     def get_job_file(self, job_wrapper: "MinimalJobWrapper", **kwds) -> str:
         job_metrics = job_wrapper.app.job_metrics

lib/galaxy/jobs/runners/aws.py

@@ -341,7 +341,7 @@ def _register_job_definition(self, jd_name, container_image, destination_params)
             "environment": _add_galaxy_environment_variables(
                 destination_params.get("vcpu"), destination_params.get("memory"),
             ),
-            "user": "%d:%d" % (os.getuid(), os.getgid()),
+            "user": f"{os.getuid()}:{os.getgid()}",
             "privileged": destination_params.get("privileged"),
             "logConfiguration": {"logDriver": "awslogs"},
         }

lib/galaxy/jobs/runners/local.py

@@ -171,7 +171,7 @@ def stop_job(self, job_wrapper):
             return
         pid = int(pid)
         if not check_pg(pid):
-            log.warning("stop_job(): %s: Process group %d was already dead or can't be signaled" % (job.id, pid))
+            log.warning("stop_job(): %s: Process group %d was already dead or can't be signaled", job.id, pid)
             return
         log.debug("stop_job(): %s: Terminating process group %d", job.id, pid)
         kill_pg(pid)

lib/galaxy/jobs/runners/pbs.py

@@ -317,7 +317,7 @@ def queue_job(self, job_wrapper):
                 pbs.pbs_disconnect(c)
                 break
             errno, text = pbs.error()
-            log.warning("(%s) pbs_submit failed (try %d/5), PBS error %d: %s" % (galaxy_job_id, tries, errno, text))
+            log.warning("(%s) pbs_submit failed (try %d/5), PBS error %d: %s", galaxy_job_id, tries, errno, text)
             time.sleep(2)
         else:
             log.error(f"({galaxy_job_id}) All attempts to submit job failed")
@@ -386,7 +386,7 @@ def check_watched_items(self):
                     else:
                         # Unhandled error, continue to monitor
                         log.info(
-                            "(%s/%s) PBS state check resulted in error (%d): %s" % (galaxy_job_id, job_id, errno, text)
+                            "(%s/%s) PBS state check resulted in error (%d): %s", galaxy_job_id, job_id, errno, text
                         )
                         new_watched.append(pbs_job_state)
                 continue

lib/galaxy/jobs/runners/pulsar.py

@@ -723,11 +723,13 @@ def check_pid(self, pid):
             return True
         except OSError as e:
             if e.errno == errno.ESRCH:
-                log.debug("check_pid(): PID %d is dead" % pid)
+                log.debug("check_pid(): PID %d is dead", pid)
             else:
                 log.warning(
-                    "check_pid(): Got errno %s when attempting to check PID %d: %s"
-                    % (errno.errorcode[e.errno], pid, e.strerror)
+                    "check_pid(): Got errno %s when attempting to check PID %d: %s",
+                    errno.errorcode[e.errno],
+                    pid,
+                    e.strerror,
                 )
             return False
 
@@ -747,23 +749,27 @@ def stop_job(self, job_wrapper):
                 return
             pid = int(pid)
             if not self.check_pid(pid):
-                log.warning("stop_job(): %s: PID %d was already dead or can't be signaled" % (job.id, pid))
+                log.warning("stop_job(): %s: PID %d was already dead or can't be signaled", job.id, pid)
                 return
             for sig in [15, 9]:
                 try:
                     os.killpg(pid, sig)
                 except OSError as e:
                     log.warning(
-                        "stop_job(): %s: Got errno %s when attempting to signal %d to PID %d: %s"
-                        % (job.id, errno.errorcode[e.errno], sig, pid, e.strerror)
+                        "stop_job(): %s: Got errno %s when attempting to signal %d to PID %d: %s",
+                        job.id,
+                        errno.errorcode[e.errno],
+                        sig,
+                        pid,
+                        e.strerror,
                     )
                     return  # give up
                 sleep(2)
                 if not self.check_pid(pid):
-                    log.debug("stop_job(): %s: PID %d successfully killed with signal %d" % (job.id, pid, sig))
+                    log.debug("stop_job(): %s: PID %d successfully killed with signal %d", job.id, pid, sig)
                     return
                 else:
-                    log.warning("stop_job(): %s: PID %d refuses to die after signaling TERM/KILL" % (job.id, pid))
+                    log.warning("stop_job(): %s: PID %d refuses to die after signaling TERM/KILL", job.id, pid)
         else:
             # Remote kill
             pulsar_url = job.job_runner_name