chore: Update ruff to 0.9 (#596)

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 repos:
   - repo: https://github.com/charliermarsh/ruff-pre-commit
     # Ruff version.
-    rev: v0.8.2
+    rev: v0.9.1
     hooks:
       - id: ruff
         args: [ --fix ]

environment.yml

@@ -51,7 +51,7 @@ dependencies:
   - coveralls ~=4.0.1
   - pytabix >=0.1.0,<1
   # formatting, linting, dev
-  - ruff ~=0.4.8
+  - ruff >=0.9.0,<1
   - snakefmt ~=0.8.5
   - pre-commit ~=3.7.1
   # docs

pyproject.toml

@@ -72,7 +72,7 @@ test = [
 ]
 dev = [
     # ruff code linter + formatter
-    "ruff >=0.8.2,<1",
+    "ruff >=0.9.0,<1",
     # "snakefmt" code formatter and checker.
     "snakefmt >=0.10.2,<1",
     "pre-commit >=4.0.1,<5"

snappy_pipeline/apps/snappy_snake.py

@@ -293,7 +293,7 @@ def main(argv=None):
     )
     group = parser.add_argument_group(
         "Snakemake Verbosity / Debugging",
-        "Arguments from Snakemake that are useful for debugging, such as " "increasing verbosity",
+        "Arguments from Snakemake that are useful for debugging, such as increasing verbosity",
     )
     group.add_argument(
         "-p", "--printshellcmds", action="store_true", default=False, help="Print shell commands"

snappy_pipeline/apps/snappy_start_project.py

@@ -117,8 +117,7 @@ def main(argv=None):
         default=True,
         action="store_false",
         help=(
-            "Do not check config.yaml for existing configuration or change it (IOW: "
-            "leave it alone)"
+            "Do not check config.yaml for existing configuration or change it (IOW: leave it alone)"
         ),
     )
 

snappy_pipeline/apps/snappy_start_step.py

@@ -263,8 +263,7 @@ def main(argv=None):
         default=True,
         action="store_false",
         help=(
-            "Do not check config.yaml for existing configuration or change it (IOW: "
-            "leave it alone)"
+            "Do not check config.yaml for existing configuration or change it (IOW: leave it alone)"
         ),
     )
 

snappy_pipeline/models/__init__.py

@@ -102,7 +102,7 @@ def camel_to_snake(name: str) -> str:
                 return re.sub("([a-z0-9])([A-Z])", r"\1_\2", name).lower()
 
             name = camel_to_snake(cls.__name__)
-            config_str = "step_config:\n" f"{' ' * INDENTATION}{name}:\n" f"{''.join(config_str)}"
+            config_str = f"step_config:\n{' ' * INDENTATION}{name}:\n{''.join(config_str)}"
 
         return config_str
 
@@ -173,7 +173,7 @@ def option_str(option: tuple[str, typing.Any]) -> str:
                 else:
                     return f"{repr(value)}"
 
-            comment.append(f"Options: " f"{', '.join(map(option_str, options))}")
+            comment.append(f"Options: {', '.join(map(option_str, options))}")
 
         comment = "; ".join(comment)
 

snappy_pipeline/workflows/gene_expression_quantification/__init__.py

@@ -228,7 +228,7 @@ class GeneExpressionQuantificationStepPart(BaseStepPart):
     def __init__(self, parent):
         super().__init__(parent)
         self.base_path_out = (
-            "work/{{mapper}}.{tool}.{{library_name}}/out/" "{{mapper}}.{tool}.{{library_name}}{ext}"
+            "work/{{mapper}}.{tool}.{{library_name}}/out/{{mapper}}.{tool}.{{library_name}}{ext}"
         )
 
     def get_input_files(self, action):
@@ -238,7 +238,7 @@ def input_function(wildcards):
             ngs_mapping = self.parent.sub_workflows["ngs_mapping"]
             # Get names of primary libraries of the selected cancer bio sample and the
             # corresponding primary normal sample
-            base_path = "output/{mapper}.{library_name}/out/" "{mapper}.{library_name}".format(
+            base_path = "output/{mapper}.{library_name}/out/{mapper}.{library_name}".format(
                 **wildcards
             )
             return {

snappy_pipeline/workflows/gene_expression_report/__init__.py

@@ -31,8 +31,7 @@ class GeneExpressionReportStepPart(BaseStepPart):
     def __init__(self, parent):
         super().__init__(parent)
         self.base_path_out = (
-            "work/{{mapper}}.{{tool}}.{{ngs_library}}/out/"
-            "{{mapper}}.{{tool}}.{{ngs_library}}{ext}"
+            "work/{{mapper}}.{{tool}}.{{ngs_library}}/out/{{mapper}}.{{tool}}.{{ngs_library}}{ext}"
         )
         # Build shortcut from cancer bio sample name to matched cancer sample
         self.tumor_ngs_library_to_sample_pair = OrderedDict()

snappy_pipeline/workflows/ngs_mapping/__init__.py

@@ -653,7 +653,7 @@ def _get_output_files_run_work(self):
             yield ext[1:].replace(".", "_"), self.base_path_out.format(mapper=self.name, ext=ext)
         for ext in (".bamstats.txt", ".flagstats.txt", ".idxstats.txt"):
             path = (
-                "work/{mapper}.{{library_name}}/report/bam_qc/" "{mapper}.{{library_name}}.bam{ext}"
+                "work/{mapper}.{{library_name}}/report/bam_qc/{mapper}.{{library_name}}.bam{ext}"
             ).format(mapper=self.name, ext=ext)
             yield "report_" + ".".join(ext.split(".")[1:3]).replace(".", "_"), path
         for ext in (
@@ -662,7 +662,7 @@ def _get_output_files_run_work(self):
             ".idxstats.txt.md5",
         ):
             path = (
-                "work/{mapper}.{{library_name}}/report/bam_qc/" "{mapper}.{{library_name}}.bam{ext}"
+                "work/{mapper}.{{library_name}}/report/bam_qc/{mapper}.{{library_name}}.bam{ext}"
             ).format(mapper=self.name, ext=ext)
             yield "report_" + ".".join(ext.split(".")[1:3]).replace(".", "_") + "_md5", path
 

snappy_pipeline/workflows/repeat_expansion/__init__.py

@@ -374,7 +374,6 @@ def check_config(self):
         self.ensure_w_config(
             config_keys=("static_data_config", "reference", "path"),
             msg=(
-                "Path to reference FASTA not configured but required "
-                "for repeat expansion analysis."
+                "Path to reference FASTA not configured but required for repeat expansion analysis."
             ),
         )

snappy_pipeline/workflows/somatic_msi_calling/__init__.py

@@ -127,7 +127,7 @@ def input_function(wildcards):
                 )
             )
             tumor_base_path = (
-                "output/{mapper}.{tumor_library}/out/" "{mapper}.{tumor_library}"
+                "output/{mapper}.{tumor_library}/out/{mapper}.{tumor_library}"
             ).format(**wildcards)
             return {
                 "normal_bam": ngs_mapping(normal_base_path + ".bam"),

snappy_pipeline/workflows/somatic_targeted_seq_cnv_calling/__init__.py

@@ -188,9 +188,9 @@ def input_function(wildcards):
                     normal_library=self.get_normal_lib_name(wildcards), **wildcards
                 )
             )
-            tumor_base_path = (
-                "output/{mapper}.{library_name}/out/" "{mapper}.{library_name}"
-            ).format(**wildcards)
+            tumor_base_path = ("output/{mapper}.{library_name}/out/{mapper}.{library_name}").format(
+                **wildcards
+            )
             yield "normal_bam", ngs_mapping(normal_base_path + ".bam")
             yield "normal_bai", ngs_mapping(normal_base_path + ".bam.bai")
             yield "tumor_bam", ngs_mapping(tumor_base_path + ".bam")
@@ -780,10 +780,7 @@ def _get_output_files_export():
             ("vcf_tbi", "vcf.gz.tbi"),
         )
         output_files = {}
-        tpl = (
-            "work/{{mapper}}.cnvkit.{{library_name}}/out/"
-            "{{mapper}}.cnvkit.{{library_name}}.{ext}"
-        )
+        tpl = "work/{{mapper}}.cnvkit.{{library_name}}/out/{{mapper}}.cnvkit.{{library_name}}.{ext}"
         for export, ext in exports:
             output_files[export] = tpl.format(export=export, ext=ext)
             output_files[export + "_md5"] = output_files[export] + ".md5"
@@ -867,9 +864,9 @@ def input_function_run(wildcards):
                     normal_library=self.get_normal_lib_name(wildcards), **wildcards
                 )
             )
-            tumor_base_path = (
-                "output/{mapper}.{library_name}/out/" "{mapper}.{library_name}"
-            ).format(**wildcards)
+            tumor_base_path = ("output/{mapper}.{library_name}/out/{mapper}.{library_name}").format(
+                **wildcards
+            )
             return {
                 "normal_bam": ngs_mapping(normal_base_path + ".bam"),
                 "normal_bai": ngs_mapping(normal_base_path + ".bam.bai"),

snappy_pipeline/workflows/somatic_variant_annotation/__init__.py

@@ -137,8 +137,7 @@ def get_input_files(self, action):
         # Validate action
         self._validate_action(action)
         tpl = (
-            "output/{mapper}.{var_caller}.{tumor_library}/out/"
-            "{mapper}.{var_caller}.{tumor_library}"
+            "output/{mapper}.{var_caller}.{tumor_library}/out/{mapper}.{var_caller}.{tumor_library}"
         )
         key_ext = {"vcf": ".vcf.gz", "vcf_tbi": ".vcf.gz.tbi"}
         variant_calling = self.parent.sub_workflows["somatic_variant_calling"]

snappy_pipeline/workflows/somatic_variant_calling/__init__.py

@@ -214,7 +214,7 @@ def input_function(wildcards):
             # Get names of primary libraries of the selected cancer bio sample and the
             # corresponding primary normal sample
             tumor_base_path = (
-                "output/{mapper}.{tumor_library}/out/" "{mapper}.{tumor_library}"
+                "output/{mapper}.{tumor_library}/out/{mapper}.{tumor_library}"
             ).format(**wildcards)
             input_files = {
                 "tumor_bam": ngs_mapping(tumor_base_path + ".bam"),
@@ -410,9 +410,9 @@ def _get_input_files_run(self, wildcards):
         ngs_mapping = self.parent.sub_workflows["ngs_mapping"]
         # Get names of primary libraries of the selected cancer bio sample and the
         # corresponding primary normal sample
-        tumor_base_path = (
-            "output/{mapper}.{tumor_library}/out/" "{mapper}.{tumor_library}"
-        ).format(**wildcards)
+        tumor_base_path = ("output/{mapper}.{tumor_library}/out/{mapper}.{tumor_library}").format(
+            **wildcards
+        )
         input_files = {
             "tumor_bam": ngs_mapping(tumor_base_path + ".bam"),
             "tumor_bai": ngs_mapping(tumor_base_path + ".bam.bai"),
@@ -737,7 +737,7 @@ def __init__(self, parent):
         if self.__class__.name is None:
             raise RuntimeError("Step name not given, override in sub class")
         self.base_path_out = (
-            "work/{{mapper}}.{name}.{{donor_name}}/out/" "{{mapper}}.{name}.{{donor_name}}{ext}"
+            "work/{{mapper}}.{name}.{{donor_name}}/out/{{mapper}}.{name}.{{donor_name}}{ext}"
         )
         # Build shortcut from donor name to donor.
         self.donor_by_name = OrderedDict()
@@ -783,8 +783,7 @@ def _get_log_file(self, action):
         """Return dict of log files."""
         _ = action
         prefix = (
-            "work/{{mapper}}.{var_caller}.{{donor_name}}/log/"
-            "{{mapper}}.{var_caller}.{{donor_name}}"
+            "work/{{mapper}}.{var_caller}.{{donor_name}}/log/{{mapper}}.{var_caller}.{{donor_name}}"
         ).format(var_caller=self.__class__.name)
         key_ext = (
             ("log", ".log"),

snappy_pipeline/workflows/somatic_variant_filtration/__init__.py

@@ -546,7 +546,7 @@ def get_input_files(self, action):
             name_pattern += ".{annotator}"
 
         # VCF file and index
-        tpl = f"output/{name_pattern}." "{tumor_library}/" f"out/{name_pattern}." "{tumor_library}"
+        tpl = f"output/{name_pattern}.{{tumor_library}}/out/{name_pattern}.{{tumor_library}}"
         key_ext = {"vcf": ".vcf.gz", "vcf_tbi": ".vcf.gz.tbi"}
         somatic_variant = self.parent.sub_workflows["somatic_variant"]
         for key, ext in key_ext.items():

snappy_pipeline/workflows/somatic_wgs_cnv_calling/__init__.py

@@ -157,7 +157,7 @@ def input_function(wildcards):
                 )
             )
             cancer_base_path = (
-                "output/{mapper}.{cancer_library}/out/" "{mapper}.{cancer_library}"
+                "output/{mapper}.{cancer_library}/out/{mapper}.{cancer_library}"
             ).format(**wildcards)
             yield "normal_bam", ngs_mapping(normal_base_path + ".bam")
             yield "normal_bai", ngs_mapping(normal_base_path + ".bam.bai")
@@ -564,10 +564,7 @@ def _get_output_files_plot(self):
     def _get_output_files_export():
         exports = (("bed", "bed"), ("seg", "seg"), ("vcf", "vcf.gz"), ("tbi", "vcf.gz.tbi"))
         output_files = {}
-        tpl = (
-            "work/{{mapper}}.cnvkit.{{library_name}}/out/"
-            "{{mapper}}.cnvkit.{{library_name}}.{ext}"
-        )
+        tpl = "work/{{mapper}}.cnvkit.{{library_name}}/out/{{mapper}}.cnvkit.{{library_name}}.{ext}"
         for export, ext in exports:
             output_files[export] = tpl.format(export=export, ext=ext)
             output_files[export + "_md5"] = output_files[export] + ".md5"

snappy_pipeline/workflows/somatic_wgs_sv_calling/__init__.py

@@ -145,7 +145,7 @@ def input_function(wildcards):
                 )
             )
             cancer_base_path = (
-                "output/{mapper}.{cancer_library}/out/" "{mapper}.{cancer_library}"
+                "output/{mapper}.{cancer_library}/out/{mapper}.{cancer_library}"
             ).format(**wildcards)
             return {
                 "normal_bam": ngs_mapping(normal_base_path + ".bam"),

snappy_pipeline/workflows/variant_denovo_filtration/__init__.py

@@ -192,9 +192,9 @@ def input_function(wildcards):
             yield "ped", real_path
             # BAM and BAI file of the offspring
             ngs_mapping = self.parent.sub_workflows["ngs_mapping"]
-            path_bam = (
-                "output/{mapper}.{index_library}/out/{mapper}." "{index_library}.bam"
-            ).format(**wildcards)
+            path_bam = ("output/{mapper}.{index_library}/out/{mapper}.{index_library}.bam").format(
+                **wildcards
+            )
             yield "bam", ngs_mapping(path_bam)
             yield "bai", ngs_mapping(path_bam + ".bai")
             # Input file comes from previous step.

snappy_pipeline/workflows/variant_filtration/model.py

@@ -170,13 +170,13 @@ def ensure_filter_combinations_are_valid(self):
         score: set[str] = set(self.score_thresholds.keys()) | {"all_scores"}
         het_comp: set[str] = {"passthrough", "intervals500", "tads", "gene"}
         pattern: str = r".".join(
-            f'({"|".join(p)})' for p in [thresholds, inherit, freq, region, score, het_comp]
+            f"({'|'.join(p)})" for p in [thresholds, inherit, freq, region, score, het_comp]
         )
         pattern: re.Pattern[str] = re.compile(pattern)
         for combination in self.filter_combinations:
             if pattern.fullmatch(combination) is None:
                 raise ValueError(
-                    f"Invalid combination: {combination}, " f"must match pattern {pattern.pattern}"
+                    f"Invalid combination: {combination}, must match pattern {pattern.pattern}"
                 )
 
         return self

snappy_pipeline/workflows/wgs_cnv_export_external/__init__.py

@@ -207,8 +207,7 @@ def _get_log_file_merge_vcf(self):
     @dictify
     def _get_log_file_annotate(self):
         prefix = (
-            "work/varfish_annotated.{index_ngs_library}/log/"
-            "varfish_annotated.{index_ngs_library}"
+            "work/varfish_annotated.{index_ngs_library}/log/varfish_annotated.{index_ngs_library}"
         )
         key_ext = (
             ("log", ".log"),

snappy_pipeline/workflows/wgs_sv_export_external/__init__.py

@@ -207,8 +207,7 @@ def _get_log_file_merge_vcf(self):
     @dictify
     def _get_log_file_annotate(self):
         prefix = (
-            "work/varfish_annotated.{index_ngs_library}/log/"
-            "varfish_annotated.{index_ngs_library}"
+            "work/varfish_annotated.{index_ngs_library}/log/varfish_annotated.{index_ngs_library}"
         )
         key_ext = (
             ("log", ".log"),

snappy_wrappers/tools/ped_to_vcf_header.py

@@ -102,7 +102,7 @@ def run(args):
 def main(argv=None):
     """Program entry point for parsing the command line."""
     parser = argparse.ArgumentParser(
-        description=("Parse PED file and transform pedigree information into" "VCF header format")
+        description=("Parse PED file and transform pedigree information into VCF header format")
     )
     parser.add_argument(
         "--ped-file",

snappy_wrappers/tools/vcf_filter_denovo.py

@@ -985,8 +985,7 @@ def main(argv=None):
     # Setup command line parser
     parser = argparse.ArgumentParser(
         description=(
-            "Annotate VCF file with various of soft filters for sequence variant de "
-            "novo filtration"
+            "Annotate VCF file with various of soft filters for sequence variant de novo filtration"
         )
     )
 

snappy_wrappers/wrappers/hts_screen/match_vector_to_report.py

@@ -64,7 +64,7 @@ def run(args):
         file=args.out_file,
     )
     for i, genome in enumerate(genomes):
-        tpl = "{}\t{}\t{}\t{:0.2f}\t{}\t{:0.2f}\t{}\t{:0.2f}\t" "{}\t{:0.2f}\t{}\t{:0.2f}"
+        tpl = "{}\t{}\t{}\t{:0.2f}\t{}\t{:0.2f}\t{}\t{:0.2f}\t{}\t{:0.2f}\t{}\t{:0.2f}"
         print(
             tpl.format(
                 genome,