Switch to ruff

.github/workflows/pytest.yml

@@ -28,15 +28,10 @@ jobs:
       run: |
         python -m pip install --upgrade pip setuptools
         pip install -e .[test]  # coverage reports need -e to capture properly
-    - name: Lint with flake8
+    - name: Check with ruff
       run: |
-        pip install flake8
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 pori_python --count --select=E9,F63,F7,F82 --show-source --statistics
-    - name: Check with black
-      run: |
-        pip install black==25.11.0
-        black --check -S -l 100 pori_python tests
+        pip install ruff
+        ruff format --check pori_python tests
     - name: Full Tests with pytest
       run: |
         pip list

.github/workflows/quick-pytest.yml

@@ -25,15 +25,10 @@ jobs:
       run: |
         python -m pip install --upgrade pip setuptools
         pip install -e .[test]  # coverage reports need -e to capture properly
-    - name: Lint with flake8
+    - name: Check with ruff
       run: |
-        pip install flake8
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 pori_python --count --select=E9,F63,F7,F82 --show-source --statistics
-    - name: Check with black
-      run: |
-        pip install black==25.11.0
-        black --check -S -l 100 pori_python tests
+        pip install ruff
+        ruff format --check pori_python tests
     - name: Short Tests with pytest
       run: pytest --junitxml=junit/test-results-${{ matrix.python-version }}.xml --cov ipr --cov-report term --cov-report xml
       env:

pori_python/graphkb/constants.py

@@ -5,107 +5,107 @@
 
 DEFAULT_LIMIT = 1000
 
-PREFERRED_GENE_SOURCE_NAME = "HGNC"
+PREFERRED_GENE_SOURCE_NAME = 'HGNC'
 
-BASE_RETURN_PROPERTIES = ["@rid", "@class"]
+BASE_RETURN_PROPERTIES = ['@rid', '@class']
 
 GENERIC_RETURN_PROPERTIES = [
-    "name",
-    "sourceId",
-    "sourceIdVersion",
-    "source.name",
-    "source.@rid",
-    "displayName",
-    "deprecated",
+    'name',
+    'sourceId',
+    'sourceIdVersion',
+    'source.name',
+    'source.@rid',
+    'displayName',
+    'deprecated',
 ] + BASE_RETURN_PROPERTIES
 
-GENE_RETURN_PROPERTIES = ["biotype"] + GENERIC_RETURN_PROPERTIES
+GENE_RETURN_PROPERTIES = ['biotype'] + GENERIC_RETURN_PROPERTIES
 
 VARIANT_RETURN_PROPERTIES = (
     BASE_RETURN_PROPERTIES
-    + [f"type.{p}" for p in GENERIC_RETURN_PROPERTIES]
-    + [f"reference1.{p}" for p in GENE_RETURN_PROPERTIES]
-    + [f"reference2.{p}" for p in GENE_RETURN_PROPERTIES]
-    + ["zygosity", "germline", "displayName"]
+    + [f'type.{p}' for p in GENERIC_RETURN_PROPERTIES]
+    + [f'reference1.{p}' for p in GENE_RETURN_PROPERTIES]
+    + [f'reference2.{p}' for p in GENE_RETURN_PROPERTIES]
+    + ['zygosity', 'germline', 'displayName']
 )
 
 POS_VARIANT_RETURN_PROPERTIES = VARIANT_RETURN_PROPERTIES + [
-    "break1Start",
-    "break1End",
-    "break2Start",
-    "break2End",
-    "break1Repr",
-    "break2Repr",
-    "refSeq",
-    "untemplatedSeq",
-    "untemplatedSeqSize",
-    "truncation",
-    "assembly",
+    'break1Start',
+    'break1End',
+    'break2Start',
+    'break2End',
+    'break1Repr',
+    'break2Repr',
+    'refSeq',
+    'untemplatedSeq',
+    'untemplatedSeqSize',
+    'truncation',
+    'assembly',
 ]
 
 STATEMENT_RETURN_PROPERTIES = (
     BASE_RETURN_PROPERTIES
-    + ["displayNameTemplate", "sourceId", "source.name", "source.displayName"]
-    + [f"conditions.{p}" for p in GENERIC_RETURN_PROPERTIES]
-    + [f"subject.{p}" for p in GENERIC_RETURN_PROPERTIES]
-    + [f"evidence.{p}" for p in GENERIC_RETURN_PROPERTIES]
-    + [f"relevance.{p}" for p in GENERIC_RETURN_PROPERTIES]
-    + [f"evidenceLevel.{p}" for p in GENERIC_RETURN_PROPERTIES]
-    + ["reviewStatus"]
+    + ['displayNameTemplate', 'sourceId', 'source.name', 'source.displayName']
+    + [f'conditions.{p}' for p in GENERIC_RETURN_PROPERTIES]
+    + [f'subject.{p}' for p in GENERIC_RETURN_PROPERTIES]
+    + [f'evidence.{p}' for p in GENERIC_RETURN_PROPERTIES]
+    + [f'relevance.{p}' for p in GENERIC_RETURN_PROPERTIES]
+    + [f'evidenceLevel.{p}' for p in GENERIC_RETURN_PROPERTIES]
+    + ['reviewStatus']
 )
 
 
-ONCOKB_SOURCE_NAME = "oncokb"
-TSO500_SOURCE_NAME = "tso500"
-ONCOGENE = "oncogenic"
-TUMOUR_SUPPRESSIVE = "tumour suppressive"
-CANCER_GENE = "cancer gene"
-FUSION_NAMES = ["structural variant", "fusion"]
+ONCOKB_SOURCE_NAME = 'oncokb'
+TSO500_SOURCE_NAME = 'tso500'
+ONCOGENE = 'oncogenic'
+TUMOUR_SUPPRESSIVE = 'tumour suppressive'
+CANCER_GENE = 'cancer gene'
+FUSION_NAMES = ['structural variant', 'fusion']
 
-GSC_PHARMACOGENOMIC_SOURCE_EXCLUDE_LIST = ["cancer genome interpreter", "civic"]
-GSC_PHARMACOGENOMIC_SOURCE_DISPLAYNAME_EXCLUDE_LIST = ["CGI", "CIViC"]
+GSC_PHARMACOGENOMIC_SOURCE_EXCLUDE_LIST = ['cancer genome interpreter', 'civic']
+GSC_PHARMACOGENOMIC_SOURCE_DISPLAYNAME_EXCLUDE_LIST = ['CGI', 'CIViC']
 
-BASE_THERAPEUTIC_TERMS = ["therapeutic efficacy", "eligibility"]
+BASE_THERAPEUTIC_TERMS = ['therapeutic efficacy', 'eligibility']
 # the order here is the order these are applied, the first category matched is returned
 RELEVANCE_BASE_TERMS: CategoryBaseTermMapping = [
-    ("therapeutic", BASE_THERAPEUTIC_TERMS),
-    ("diagnostic", ["diagnostic indicator"]),
-    ("prognostic", ["prognostic indicator"]),
-    ("pharmacogenomic", ["metabolism", "toxicity", "dosage"]),
-    ("cancer predisposition", ["pathogenic"]),
-    ("biological", ["functional effect", "tumourigenesis", "predisposing"]),
+    ('therapeutic', BASE_THERAPEUTIC_TERMS),
+    ('diagnostic', ['diagnostic indicator']),
+    ('prognostic', ['prognostic indicator']),
+    ('pharmacogenomic', ['metabolism', 'toxicity', 'dosage']),
+    ('cancer predisposition', ['pathogenic']),
+    ('biological', ['functional effect', 'tumourigenesis', 'predisposing']),
 ]
-FAILED_REVIEW_STATUS = "failed"
+FAILED_REVIEW_STATUS = 'failed'
 
-CHROMOSOMES_HG38 = [f"chr{i}" for i in range(1, 23)] + ["chrX", "chrY", "chrM"]
-CHROMOSOMES_HG19 = [str(i) for i in range(1, 23)] + ["x", "y", "mt"]
+CHROMOSOMES_HG38 = [f'chr{i}' for i in range(1, 23)] + ['chrX', 'chrY', 'chrM']
+CHROMOSOMES_HG19 = [str(i) for i in range(1, 23)] + ['x', 'y', 'mt']
 CHROMOSOMES = CHROMOSOMES_HG38 + CHROMOSOMES_HG19
 
-AMBIGUOUS_AA = ["x", "?", "X"]
+AMBIGUOUS_AA = ['x', '?', 'X']
 AA_3to1_MAPPING = {
-    "Ala": "A",
-    "Arg": "R",
-    "Asn": "N",
-    "Asp": "D",
-    "Asx": "B",
-    "Cys": "C",
-    "Glu": "E",
-    "Gln": "Q",
-    "Glx": "Z",
-    "Gly": "G",
-    "His": "H",
-    "Ile": "I",
-    "Leu": "L",
-    "Lys": "K",
-    "Met": "M",
-    "Phe": "F",
-    "Pro": "P",
-    "Ser": "S",
-    "Thr": "T",
-    "Trp": "W",
-    "Tyr": "Y",
-    "Val": "V",
-    "Ter": "*",
+    'Ala': 'A',
+    'Arg': 'R',
+    'Asn': 'N',
+    'Asp': 'D',
+    'Asx': 'B',
+    'Cys': 'C',
+    'Glu': 'E',
+    'Gln': 'Q',
+    'Glx': 'Z',
+    'Gly': 'G',
+    'His': 'H',
+    'Ile': 'I',
+    'Leu': 'L',
+    'Lys': 'K',
+    'Met': 'M',
+    'Phe': 'F',
+    'Pro': 'P',
+    'Ser': 'S',
+    'Thr': 'T',
+    'Trp': 'W',
+    'Tyr': 'Y',
+    'Val': 'V',
+    'Ter': '*',
 }
 
 
@@ -127,89 +127,89 @@ def __getitem__(self, key):
 
 
 INPUT_COPY_CATEGORIES = IterableNamespace(
-    AMP="amplification",
-    ANY_GAIN="copy gain",
-    ANY_LOSS="copy loss",
-    DEEP="deep deletion",
-    GAIN="low level copy gain",
-    LOSS="shallow deletion",
+    AMP='amplification',
+    ANY_GAIN='copy gain',
+    ANY_LOSS='copy loss',
+    DEEP='deep deletion',
+    GAIN='low level copy gain',
+    LOSS='shallow deletion',
 )
 INPUT_EXPRESSION_CATEGORIES = IterableNamespace(
-    UP="increased expression", DOWN="reduced expression"
+    UP='increased expression', DOWN='reduced expression'
 )
 
 # From: https://github.com/bcgsc/pori_graphkb_parser/blob/ae3738842a4c208ab30f58c08ae987594d632504/src/constants.ts#L33-L80
 TYPES_TO_NOTATION: Dict[str, str] = {
-    "acetylation": "ac",
-    "copy gain": "copygain",
-    "copy loss": "copyloss",
-    "deletion": "del",
-    "duplication": "dup",
-    "extension": "ext",
-    "frameshift": "fs",
-    "fusion": "fusion",
-    "indel": "delins",
-    "insertion": "ins",
-    "inversion": "inv",
-    "inverted translocation": "itrans",
-    "methylation": "me",
-    "missense mutation": "mis",
-    "mutation": "mut",
-    "nonsense mutation": ">",
-    "phosphorylation": "phos",
-    "splice-site": "spl",
-    "substitution": ">",
-    "translocation": "trans",
-    "truncating frameshift mutation": "fs",
-    "ubiquitination": "ub",
+    'acetylation': 'ac',
+    'copy gain': 'copygain',
+    'copy loss': 'copyloss',
+    'deletion': 'del',
+    'duplication': 'dup',
+    'extension': 'ext',
+    'frameshift': 'fs',
+    'fusion': 'fusion',
+    'indel': 'delins',
+    'insertion': 'ins',
+    'inversion': 'inv',
+    'inverted translocation': 'itrans',
+    'methylation': 'me',
+    'missense mutation': 'mis',
+    'mutation': 'mut',
+    'nonsense mutation': '>',
+    'phosphorylation': 'phos',
+    'splice-site': 'spl',
+    'substitution': '>',
+    'translocation': 'trans',
+    'truncating frameshift mutation': 'fs',
+    'ubiquitination': 'ub',
     # deprecated forms and aliases
-    "frameshift mutation": "fs",
-    "frameshift truncation": "fs",
-    "missense variant": "mis",
-    "truncating frameshift": "fs",
-    "missense": "mis",
-    "mutations": "mut",
-    "nonsense": ">",
+    'frameshift mutation': 'fs',
+    'frameshift truncation': 'fs',
+    'missense variant': 'mis',
+    'truncating frameshift': 'fs',
+    'missense': 'mis',
+    'mutations': 'mut',
+    'nonsense': '>',
 }
 
 # For match.type_screening() [KBDEV-1056]
-DEFAULT_NON_STRUCTURAL_VARIANT_TYPE = "mutation"
+DEFAULT_NON_STRUCTURAL_VARIANT_TYPE = 'mutation'
 STRUCTURAL_VARIANT_SIZE_THRESHOLD = 48  # bp
 STRUCTURAL_VARIANT_TYPES = [
-    "structural variant",
-    "insertion",
-    "in-frame insertion",
-    "deletion",
-    "deletion polymorphism",
-    "in-frame deletion",
-    "translocation",
-    "inverted translocation",
-    "inversion",
-    "indel",
-    "fusion",
-    "out-of-frame fusion",
-    "oncogenic fusion",
-    "in-frame fusion",
-    "disruptive fusion",
-    "duplication",
-    "internal duplication",
-    "tandem duplication",
-    "internal tandem duplication",
-    "itd",
-    "domain duplication",
-    "kinase domain duplication",
-    "copy variant",
-    "copy number variation",
-    "copy number variant",
-    "copy loss",
-    "copy number loss",
-    "shallow deletion",
-    "deep deletion",
-    "gene deletion",
-    "copy gain",
-    "copy number gain",
-    "low level copy gain",
-    "amplification",
-    "focal amplification",
-    "rearrangement",
+    'structural variant',
+    'insertion',
+    'in-frame insertion',
+    'deletion',
+    'deletion polymorphism',
+    'in-frame deletion',
+    'translocation',
+    'inverted translocation',
+    'inversion',
+    'indel',
+    'fusion',
+    'out-of-frame fusion',
+    'oncogenic fusion',
+    'in-frame fusion',
+    'disruptive fusion',
+    'duplication',
+    'internal duplication',
+    'tandem duplication',
+    'internal tandem duplication',
+    'itd',
+    'domain duplication',
+    'kinase domain duplication',
+    'copy variant',
+    'copy number variation',
+    'copy number variant',
+    'copy loss',
+    'copy number loss',
+    'shallow deletion',
+    'deep deletion',
+    'gene deletion',
+    'copy gain',
+    'copy number gain',
+    'low level copy gain',
+    'amplification',
+    'focal amplification',
+    'rearrangement',
 ]