cleanup: resolve pylint warnings

.pre-commit-config.yaml

@@ -1,10 +1,16 @@
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
-  - repo: https://github.com/pycqa/pylint
-    rev: v2.15.9
+  - repo: local
     hooks:
       - id: pylint
+        name: pylint
+        entry: pylint
+        language: system
+        types: [python]
+        require_serial: true
+        exclude: ^tests/
         args:
           - src/ga4gh/core
           - src/ga4gh/vrs
+          - --fail-under=10

.pylintrc

@@ -28,6 +28,18 @@ max-line-length=120
 # Maximum number of lines in a module.
 max-module-lines=1000
 
+[MESSAGES CONTROL]
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once). You can also use "--disable=all" to
+# disable everything first and then re-enable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use "--disable=all --enable=classes
+# --disable=W".
+disable=fixme
 
 [STRING]
 

notebooks/Extras.ipynb

@@ -122,7 +122,7 @@
         "from ga4gh.vrs.extras.translator import Translator\n",
         "tlr = Translator(data_proxy=dp,\n",
         "                 translate_sequence_identifiers=True,  # default\n",
-        "                 normalize=True,                       # default\n",
+        "                 do_normalize=True,                       # default\n",
         "                 identify=True)                        # default"
       ]
     },
@@ -407,7 +407,7 @@
         "# Translator with default behaviors disabled\n",
         "tlr2 = Translator(data_proxy=dp,\n",
         "                  translate_sequence_identifiers=False,\n",
-        "                  normalize=False,\n",
+        "                  do_normalize=False,\n",
         "                  identify=False)"
       ]
     },
@@ -508,9 +508,9 @@
   ],
   "metadata": {
     "kernelspec": {
-      "display_name": "Python 3 (ipykernel)",
+      "display_name": "vrs-python",
       "language": "python",
-      "name": "python3"
+      "name": "vrs-python"
     },
     "language_info": {
       "codemirror_mode": {
@@ -522,7 +522,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.9.13"
+      "version": "3.10.8"
     },
     "toc": {
       "base_numbering": 1,

src/ga4gh/core/__init__.py

@@ -12,7 +12,7 @@
                                     parse_ga4gh_identifier)
 from ._internal.jsonschema import (build_models, build_class_referable_attribute_map, is_pjs_class, is_pjs_instance,
                                    is_curie, is_identifiable, is_literal, pjs_copy)
-
+# pylint: disable=duplicate-code
 try:
     __version__ = get_distribution(__name__).version
 except DistributionNotFound:    # pragma: nocover

src/ga4gh/core/_internal/identifiers.py

@@ -36,7 +36,8 @@
 
 # Assume that ga4gh.yaml and vrs.yaml files are in the same directory for now
 schema_dir = os.environ.get("VRS_SCHEMA_DIR", pkg_resources.resource_filename(__name__, "data/schema"))
-cfg = yaml.safe_load(open(schema_dir + "/ga4gh.yaml"))
+with open(schema_dir + "/ga4gh.yaml", "r", encoding="utf-8") as f:
+    cfg = yaml.safe_load(f)
 type_prefix_map_default = cfg["identifiers"]["type_prefix_map"]
 namespace = cfg["identifiers"]["namespace"]
 curie_sep = cfg["identifiers"]["curie_sep"]
@@ -144,7 +145,7 @@ def ga4gh_serialize(vro):
 
     """
 
-    def dictify(vro, enref=True):
+    def dictify(vro, enref=True):  # pylint: disable=too-many-return-statements,too-many-branches
         """recursively converts (any) object to dictionary prior to
         serialization
 
@@ -157,7 +158,7 @@ def dictify(vro, enref=True):
             return None
 
         if is_literal(vro):
-            v = vro._value
+            v = vro._value  # pylint: disable=protected-access
             if is_curie_type(vro):
                 if is_ga4gh_identifier(v):
                     # CURIEs are stripped to just the digest so that digests are independent of type prefixes
@@ -184,7 +185,7 @@ def dictify(vro, enref=True):
                 if is_curie_type(vro[0]):
                     return sorted(dictify(o) for o in vro.data)
 
-                arr = list()
+                arr = []
                 for o in vro.typed_elems:
                     d = dictify(o)
                     if isinstance(d, dict):

src/ga4gh/core/_internal/jsonschema.py

@@ -27,7 +27,7 @@
 
 def build_models(path, standardize_names=False):
     """load models from json schema at path"""
-    with open(path, "r") as yaml_file:
+    with open(path, "r", encoding="utf-8") as yaml_file:
         y = yaml.load(yaml_file, yaml.SafeLoader)
     builder = pjs.ObjectBuilder(pjs_filter(y))
     models = builder.build_classes(standardize_names=standardize_names)

src/ga4gh/vrs/__init__.py

@@ -23,4 +23,4 @@
 
 logging.basicConfig(
     filename="vrs-python.log",
-    format="[%(asctime)s] - %(name)s - %(levelname)s : %(message)s")
+    format="[%(asctime)s] - %(name)s - %(levelname)s : %(message)s")

src/ga4gh/vrs/dataproxy.py

@@ -152,7 +152,7 @@ def _get_sequence(self, identifier, start=None, end=None):
         url = self.base_url + f"sequence/{identifier}"
         _logger.info("Fetching %s", url)
         params = {"start": start, "end": end}
-        resp = requests.get(url, params=params)
+        resp = requests.get(url, params=params, timeout=5)
         if resp.status_code == 404:
             raise KeyError(identifier)
         resp.raise_for_status()
@@ -161,7 +161,7 @@ def _get_sequence(self, identifier, start=None, end=None):
     def _get_metadata(self, identifier):
         url = self.base_url + f"metadata/{identifier}"
         _logger.info("Fetching %s", url)
-        resp = requests.get(url)
+        resp = requests.get(url, timeout=5)
         if resp.status_code == 404:
             raise KeyError(identifier)
         resp.raise_for_status()

src/ga4gh/vrs/extras/localizer.py

@@ -2,9 +2,6 @@
 reference to external data
 
 """
-
-import copy
-
 from bioutils.accessions import coerce_namespace
 from bioutils.assemblies import make_name_ac_map
 from bioutils.cytobands import get_cytoband_maps
@@ -45,12 +42,15 @@ def __init__(self):
         self._ana_maps = {k: make_name_ac_map(k) for k in assy_name_to_map_name}
 
 
-    def localize_allele(self, allele):
-        # copy input variant and replace location
-        # N.B. deepcopy leads to recursion errors
+    def localize_allele(self, allele, assembly_name = "GRCh38"):
+        """copy input variant and replace location
+        N.B. deepcopy leads to recursion errors
+        """
+        #
+        #
         allele_sl = ga4gh.vrs.models.Variation(**allele.as_dict())
         del allele_sl._id
-        allele_sl.location = self.localize(allele.location)
+        allele_sl.location = self.localize_named_feature(allele.location, assembly_name)
         return allele_sl
 
 
@@ -59,13 +59,13 @@ def localize_named_feature(self, loc, assembly_name):
 
         """
 
-        assert loc.type._value == "ChromosomeLocation", "Expected a ChromosomeLocation object"
+        assert loc.type._value == "ChromosomeLocation", "Expected a ChromosomeLocation object"  # pylint: disable=protected-access
 
         def _get_coords(m, cb):
             """return (start,end) of band `cb` in map `m`"""
             if cb is None:
                 return None
-            return chr_cb_map[cb][0:2]
+            return m[cb][0:2]
 
         try:
             map_name = assy_name_to_map_name[assembly_name]
@@ -108,9 +108,6 @@ def _get_coords(m, cb):
             )
 
 
-
-
-
 if __name__ == "__main__":
     cbl = ga4gh.vrs.models.ChromosomeLocation(chr="11", start="q22.3", end="q23.1")
     lr = Localizer()

src/ga4gh/vrs/extras/translator.py

@@ -28,7 +28,7 @@
 class ValidationError(Exception):
     """Class for validation errors during translation"""
 
-    pass
+    pass  # pylint: disable=unnecessary-pass
 
 
 class Translator:
@@ -48,17 +48,17 @@ class Translator:
     spdi_re = re.compile(r"(?P<ac>[^:]+):(?P<pos>\d+):(?P<del_len_or_seq>\w*):(?P<ins_seq>\w*)")
 
 
-    def __init__(self,
+    def __init__(self,  # pylint: disable=too-many-arguments
                  data_proxy,
                  default_assembly_name="GRCh38",
                  translate_sequence_identifiers=True,
-                 normalize=True,
+                 do_normalize=True,
                  identify=True):
         self.default_assembly_name = default_assembly_name
         self.data_proxy = data_proxy
         self.translate_sequence_identifiers = translate_sequence_identifiers
         self.identify = identify
-        self.normalize = normalize
+        self.normalize = do_normalize
         self.hgvs_tools = None
 
 
@@ -82,7 +82,7 @@ def translate_from(self, var, fmt=None, require_validation=True):
                 raise ValueError(f"Unable to parse data as {fmt} variation")
             return o
 
-        for fmt, t in self.from_translators.items():
+        for _, t in self.from_translators.items():
             o = t(self, var, require_validation=require_validation)
             if o:
                 return o
@@ -116,7 +116,7 @@ def ensure_allele_is_latest_model(self, allele):
     ############################################################################
     ## INTERNAL
 
-    def _from_beacon(self, beacon_expr, assembly_name=None, require_validation=True):
+    def _from_beacon(self, beacon_expr, assembly_name=None, require_validation=True):  # pylint: disable=too-many-locals, unused-argument
         """Parse beacon expression into VRS Allele
 
         #>>> a = tlr.from_beacon("19 : 44908822 C > T")
@@ -158,7 +158,7 @@ def _from_beacon(self, beacon_expr, assembly_name=None, require_validation=True)
         return allele
 
 
-    def _from_gnomad(self, gnomad_expr, assembly_name=None, require_validation=True):
+    def _from_gnomad(self, gnomad_expr, assembly_name=None, require_validation=True):  # pylint: disable=unused-argument, too-many-locals
         """Parse gnomAD-style VCF expression into VRS Allele
 
         :param str gnomad_expr: chr-pos-ref-alt
@@ -208,7 +208,7 @@ def _from_gnomad(self, gnomad_expr, assembly_name=None, require_validation=True)
         return allele
 
 
-    def _from_hgvs(self, hgvs_expr, require_validation=True):
+    def _from_hgvs(self, hgvs_expr, require_validation=True):  # pylint: disable=unused-argument
         """parse hgvs into a VRS object (typically an Allele)
 
         #>>> a = tlr.from_hgvs("NM_012345.6:c.22A>T")
@@ -233,7 +233,7 @@ def _from_hgvs(self, hgvs_expr, require_validation=True):
         if not self.hgvs_re.match(hgvs_expr):
             return None
 
-        sv = self._hgvs_parser.parse_hgvs_variant(hgvs_expr)
+        sv = self._hgvs_parser.parse_hgvs_variant(hgvs_expr)  # pylint: disable=no-member
 
         # prefix accession with namespace
         sequence_id = coerce_namespace(sv.ac)
@@ -277,7 +277,7 @@ def _from_hgvs(self, hgvs_expr, require_validation=True):
         return allele
 
 
-    def _from_spdi(self, spdi_expr, require_validation=True):
+    def _from_spdi(self, spdi_expr, require_validation=True):  # pylint: disable=unused-argument
 
         """Parse SPDI expression in to a GA4GH Allele
 
@@ -322,7 +322,7 @@ def _from_spdi(self, spdi_expr, require_validation=True):
         return allele
 
 
-    def _from_vrs(self, var, require_validation=True):
+    def _from_vrs(self, var, require_validation=True):  # pylint: disable=unused-argument
         """convert from dict representation of VRS JSON to VRS object"""
         if not isinstance(var, Mapping):
             return None
@@ -342,7 +342,7 @@ def _get_hgvs_tools(self):
             self.hgvs_tools = HgvsTools(uta_conn)
         return self.hgvs_tools
 
-    def _to_hgvs(self, vo, namespace="refseq"):
+    def _to_hgvs(self, vo, namespace="refseq"):  # pylint: disable=too-many-locals
         """generates a *list* of HGVS expressions for VRS Allele.
 
         If `namespace` is not None, returns HGVS strings for the
@@ -385,11 +385,11 @@ def ir_stype(a):
         stype = stypes[0]
 
         # build interval and edit depending on sequence type
-        if stype == "p":
+        if stype == "p":  # pylint: disable=no-else-raise
             raise ValueError("Only nucleic acid variation is currently supported")
             # ival = hgvs.location.Interval(start=start, end=end)
             # edit = hgvs.edit.AARefAlt(ref=None, alt=vo.state.sequence)
-        else:                   # pylint: disable=no-else-raise
+        else:
             start, end = vo.location.interval.start.value, vo.location.interval.end.value
             # ib: 0 1 2 3 4 5
             #  h:  1 2 3 4 5
@@ -421,7 +421,7 @@ def ir_stype(a):
             if ns.startswith("GRC") and namespace is None:
                 continue
 
-            if not (any(a.startswith(pfx) for pfx in ("NM", "NP", "NC", "NG"))):
+            if not any(a.startswith(pfx) for pfx in ("NM", "NP", "NC", "NG")):
                 continue
 
             var.ac = a
@@ -435,7 +435,7 @@ def ir_stype(a):
 
                 hgvs_exprs += [str(var)]
             except hgvs.exceptions.HGVSDataNotAvailableError:
-                _logger.warning(f"No data found for accession {a}")
+                _logger.warning("No data found for accession %s", a)
 
         return list(set(hgvs_exprs))
 
@@ -493,6 +493,9 @@ def _is_valid_ref_seq(self, sequence_id: str, start_pos: int, end_pos: int,
 
 
     def is_valid_allele(self, vo):
+        """Ensure that `vo` is a valid VRS Allele with SequenceLocation and
+        LiteralSequenceExpression
+        """
         return (vo.type == "Allele"
                 and vo.location.type == "SequenceLocation"
                 and vo.state.type == "LiteralSequenceExpression")
@@ -511,14 +514,14 @@ def _post_process_imported_allele(self, allele):
         """
 
         if self.translate_sequence_identifiers:
-            seq_id = self.data_proxy.translate_sequence_identifier(allele.location.sequence_id._value, "ga4gh")[0]
+            seq_id = self.data_proxy.translate_sequence_identifier(allele.location.sequence_id._value, "ga4gh")[0]  # pylint: disable=protected-access
             allele.location.sequence_id = seq_id
 
         if self.normalize:
             allele = normalize(allele, self.data_proxy)
 
         if self.identify:
-            allele._id = ga4gh_identify(allele)
+            allele._id = ga4gh_identify(allele)  # pylint: disable=protected-access
 
         return allele
 
@@ -582,16 +585,16 @@ def _seq_id_mapper(self, ir):
             "type": "SequenceInterval"
         }
     ]
-    formats = ["hgvs", "gnomad", "beacon", "spdi", "vrs", None]
+    from_formats = ["hgvs", "gnomad", "beacon", "spdi", "vrs", None]
 
     for e in expressions:
         print(f"* {e}")
-        for f in formats:
+        for f in from_formats:
             try:
-                o = tlr.translate_from(e, f)
-                r = o.type
+                vrs_obj = tlr.translate_from(e, f)
+                r = vrs_obj.type
             except ValueError:
                 r = "-"
-            except Exception as ex:
+            except Exception as ex:  # pylint: disable=broad-except
                 r = ex.__class__.__name__
             print(f"  {f}: {r}")