cool-seq-tool 0.14.3__tar.gz → 0.14.5__tar.gz

cool_seq_tool-0.14.5/.github/CODEOWNERS

@@ -0,0 +1 @@
+* @GenomicMedLab/cool-seq-tool-maintainers

{cool_seq_tool-0.14.3 → cool_seq_tool-0.14.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cool_seq_tool
-Version: 0.14.3
+Version: 0.14.5
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License

{cool_seq_tool-0.14.3 → cool_seq_tool-0.14.5}/src/cool_seq_tool/mappers/exon_genomic_coords.py

@@ -2,6 +2,7 @@
 
 import logging
 
+from ga4gh.core.models import Extension
 from ga4gh.vrs.models import SequenceLocation, SequenceReference
 from pydantic import ConfigDict, Field, StrictInt, StrictStr, model_validator
 
@@ -66,6 +67,24 @@ class TxSegment(BaseModelForbidExtra):
         ..., description="The genomic position of a transcript segment."
     )
 
+    @model_validator(mode="before")
+    def check_seg_pos(cls, values: dict) -> dict:  # noqa: N805
+        """Ensure that only one of `start` or `end` is set in the
+        genomic_location field
+
+        :param values: The values in the TxSegment class
+        :raises ValueError: If `start` and `end` are both set in
+            `genomic_location`
+        :return: Values in model
+        """
+        loc = values.get("genomic_location")
+        start = getattr(loc, "start", None)
+        end = getattr(loc, "end", None)
+        if start and end:
+            err_msg = "Only one of `start` or `end` may be set as this describes the start or end of a transcript segment"
+            raise ValueError(err_msg)
+        return values
+
     model_config = ConfigDict(
         json_schema_extra={
             "example": {
@@ -78,6 +97,7 @@ class TxSegment(BaseModelForbidExtra):
                         "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                     },
                     "end": 154192135,
+                    "extensions": [{"name": "is_exonic", "value": True}],
                 },
             }
         }
@@ -135,6 +155,7 @@ class GenomicTxSeg(BaseModelForbidExtra):
                             "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                         },
                         "end": 154192135,
+                        "extensions": [{"name": "is_exonic", "value": True}],
                     },
                 },
                 "errors": [],
@@ -201,6 +222,7 @@ class GenomicTxSegService(BaseModelForbidExtra):
                             "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                         },
                         "end": 154192135,
+                        "extensions": [{"name": "is_exonic", "value": True}],
                     },
                 },
                 "seg_end": {
@@ -213,6 +235,7 @@ class GenomicTxSegService(BaseModelForbidExtra):
                             "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                         },
                         "start": 154170399,
+                        "extensions": [{"name": "is_exonic", "value": True}],
                     },
                 },
             }
@@ -705,7 +728,12 @@ class ExonGenomicCoordsMapper:
         ), None
 
     def _get_vrs_seq_loc(
-        self, genomic_ac: str, genomic_pos: int, is_seg_start: bool, strand: Strand
+        self,
+        genomic_ac: str,
+        genomic_pos: int,
+        is_seg_start: bool,
+        strand: Strand,
+        is_exonic: bool = True,
     ) -> tuple[SequenceLocation | None, str | None]:
         """Create VRS Sequence Location for genomic position where transcript segment
         occurs
@@ -715,6 +743,8 @@ class ExonGenomicCoordsMapper:
         :param is_seg_start: ``True`` if ``genomic_pos`` is where the transcript segment
             starts. ``False`` if ``genomic_pos`` is where the transcript segment ends.
         :param strand: Strand
+        :param is_exonic: A boolean indicating if the genomic breakpoint occurs
+            on an exon. By default, this is set to ``True``.
         :return: Tuple containing VRS location (if successful) and error message (if
             unable to get GA4GH identifier for ``genomic_ac``).
         """
@@ -734,6 +764,7 @@ class ExonGenomicCoordsMapper:
             ),
             start=genomic_pos if use_start else None,
             end=genomic_pos if not use_start else None,
+            extensions=[Extension(name="is_exonic", value=is_exonic)],
         ), None
 
     async def _genomic_to_tx_segment(
@@ -895,6 +926,7 @@ class ExonGenomicCoordsMapper:
         # Check if breakpoint occurs on an exon.
         # If not, determine the adjacent exon given the selected transcript
         if not self._is_exonic_breakpoint(genomic_pos, tx_exons):
+            is_exonic = False
             exon_num = self._get_adjacent_exon(
                 tx_exons_genomic_coords=tx_exons,
                 strand=strand,
@@ -902,6 +934,7 @@ class ExonGenomicCoordsMapper:
                 end=genomic_pos if not is_seg_start else None,
             )
         else:
+            is_exonic = True
             exon_data = await self.uta_db.get_tx_exon_aln_v_data(
                 transcript,
                 genomic_pos,
@@ -920,7 +953,7 @@ class ExonGenomicCoordsMapper:
         )
 
         genomic_location, err_msg = self._get_vrs_seq_loc(
-            genomic_ac, genomic_pos, is_seg_start, strand
+            genomic_ac, genomic_pos, is_seg_start, strand, is_exonic
         )
         if err_msg:
             return GenomicTxSeg(errors=[err_msg])

{cool_seq_tool-0.14.3 → cool_seq_tool-0.14.5}/src/cool_seq_tool/resources/status.py

@@ -3,6 +3,7 @@
 import logging
 from collections import namedtuple
 from pathlib import Path
+from urllib.parse import urlparse
 
 from agct._core import ChainfileError
 from asyncpg import InvalidCatalogNameError, UndefinedTableError
@@ -11,7 +12,7 @@ from biocommons.seqrepo import SeqRepo
 from cool_seq_tool.handlers.seqrepo_access import SEQREPO_ROOT_DIR, SeqRepoAccess
 from cool_seq_tool.mappers.liftover import LiftOver
 from cool_seq_tool.resources.data_files import DataFile, get_data_file
-from cool_seq_tool.sources.uta_database import UTA_DB_URL, UtaDatabase
+from cool_seq_tool.sources.uta_database import UTA_DB_URL, ParseResult, UtaDatabase
 
 _logger = logging.getLogger(__name__)
 
@@ -119,14 +120,20 @@ async def check_status(
     else:
         status["liftover"] = True
 
+    parsed_result = ParseResult(urlparse(db_url))
+    sanitized_url = parsed_result.sanitized_url
     try:
         await UtaDatabase.create(db_url)
+    except ValueError:
+        _logger.exception("Database URL is not valid")
     except (OSError, InvalidCatalogNameError, UndefinedTableError):
-        _logger.exception("Encountered error instantiating UTA at URI %s", UTA_DB_URL)
+        _logger.exception(
+            "Encountered error instantiating UTA at URI %s", sanitized_url
+        )
     except Exception as e:
         _logger.critical(
             "Encountered unexpected error instantiating UTA from URI %s: %s",
-            UTA_DB_URL,
+            sanitized_url,
             e,
         )
     else:

{cool_seq_tool-0.14.3 → cool_seq_tool-0.14.5}/src/cool_seq_tool/sources/uta_database.py

@@ -5,7 +5,7 @@ import logging
 from os import environ
 from typing import Any, Literal, TypeVar
 from urllib.parse import ParseResult as UrlLibParseResult
-from urllib.parse import quote, unquote, urlparse
+from urllib.parse import unquote, urlparse, urlunparse
 
 import asyncpg
 import boto3
@@ -101,8 +101,7 @@ class UtaDatabase:
         """
         self.schema = None
         self._connection_pool = None
-        original_pwd = db_url.split("//")[-1].split("@")[0].split(":")[-1]
-        self.db_url = db_url.replace(original_pwd, quote(original_pwd))
+        self.db_url = db_url
         self.args = self._get_conn_args()
 
     def _get_conn_args(self) -> DbConnectionArgs:
@@ -954,3 +953,28 @@ class ParseResult(UrlLibParseResult):
         """Create schema property."""
         path_elems = self.path.split("/")
         return path_elems[2] if len(path_elems) > 2 else None
+
+    @property
+    def sanitized_url(self) -> str:
+        """Sanitized DB URL with the password masked"""
+        netloc = ""
+        if self.username:
+            netloc += self.username
+            if self.password is not None and self.password != "":
+                netloc += ":***"
+            netloc += "@"
+        if self.hostname:
+            netloc += f"{self.hostname}"
+        if self.port:
+            netloc += f":{self.port}"
+
+        return urlunparse(
+            (
+                self.scheme,
+                netloc,
+                self.path,
+                self.params,
+                self.query,
+                self.fragment,
+            )
+        )

{cool_seq_tool-0.14.3 → cool_seq_tool-0.14.5}/src/cool_seq_tool.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cool_seq_tool
-Version: 0.14.3
+Version: 0.14.5
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License

{cool_seq_tool-0.14.3 → cool_seq_tool-0.14.5}/src/cool_seq_tool.egg-info/SOURCES.txt

@@ -6,6 +6,7 @@ CITATION.cff
 LICENSE
 README.md
 pyproject.toml
+.github/CODEOWNERS
 .github/ISSUE_TEMPLATE/bug-report.yaml
 .github/ISSUE_TEMPLATE/feature-request.yaml
 .github/workflows/checks.yaml

{cool_seq_tool-0.14.3 → cool_seq_tool-0.14.5}/tests/mappers/test_exon_genomic_coords.py

@@ -183,6 +183,7 @@ def tpm3_exon1():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "end": 154192135,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
     }
@@ -207,6 +208,7 @@ def tpm3_exon8():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "start": 154170399,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
     }
@@ -292,6 +294,7 @@ def mane_braf():
                     "refgetAccession": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul",
                 },
                 "end": 140801559,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
         "seg_end": {
@@ -304,6 +307,7 @@ def mane_braf():
                     "refgetAccession": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul",
                 },
                 "start": 140753336,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
     }
@@ -328,6 +332,7 @@ def wee1_exon2_exon11():
                     "refgetAccession": "SQ.2NkFm8HK88MqeNkCgj78KidCAXgnsfV1",
                 },
                 "start": 9576092,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
         "seg_end": {
@@ -340,6 +345,7 @@ def wee1_exon2_exon11():
                     "refgetAccession": "SQ.2NkFm8HK88MqeNkCgj78KidCAXgnsfV1",
                 },
                 "end": 9588449,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
     }
@@ -364,6 +370,7 @@ def mane_wee1_exon2_exon11():
                     "refgetAccession": "SQ.2NkFm8HK88MqeNkCgj78KidCAXgnsfV1",
                 },
                 "start": 9576092,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
         "seg_end": {
@@ -376,6 +383,7 @@ def mane_wee1_exon2_exon11():
                     "refgetAccession": "SQ.2NkFm8HK88MqeNkCgj78KidCAXgnsfV1",
                 },
                 "end": 9588449,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
     }
@@ -400,6 +408,7 @@ def ntrk1_exon10_exon17():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "start": 156874570,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
         "seg_end": {
@@ -412,6 +421,7 @@ def ntrk1_exon10_exon17():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "end": 156881850,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
     }
@@ -437,6 +447,7 @@ def zbtb10_exon3_end():
                     "refgetAccession": "SQ.209Z7zJ-mFypBEWLk4rNC6S_OxY5p7bs",
                 },
                 "end": 80514010,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
         },
     }
@@ -461,6 +472,7 @@ def zbtb10_exon5_start():
                     "refgetAccession": "SQ.209Z7zJ-mFypBEWLk4rNC6S_OxY5p7bs",
                 },
                 "start": 80518580,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
         },
         "seg_end": None,
@@ -487,6 +499,7 @@ def tpm3_exon6_end():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "start": 154171410,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
         },
     }
@@ -511,6 +524,7 @@ def tpm3_exon5_start():
                     "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO",
                 },
                 "end": 154173080,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
         },
         "seg_end": None,
@@ -537,6 +551,7 @@ def gusbp3_exon2_end():
                     "refgetAccession": "SQ.aUiQCzCPZ2d0csHbMSbh2NzInhonSXwI",
                 },
                 "start": 69680764,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
         },
     }
@@ -561,6 +576,7 @@ def eln_grch38_intronic():
                     "refgetAccession": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul",
                 },
                 "start": 74028173,
+                "extensions": [{"name": "is_exonic", "value": True}],
             },
         },
         "seg_end": {
@@ -573,6 +589,7 @@ def eln_grch38_intronic():
                     "refgetAccession": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul",
                 },
                 "end": 74043599,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
         },
     }
@@ -597,6 +614,7 @@ def gusbp3_exon5_start():
                     "refgetAccession": "SQ.aUiQCzCPZ2d0csHbMSbh2NzInhonSXwI",
                 },
                 "end": 69645878,
+                "extensions": [{"name": "is_exonic", "value": False}],
             },
         },
         "seg_end": None,
@@ -648,6 +666,10 @@ def genomic_tx_seg_service_checks(actual, expected=None, is_valid=True):
                 assert (
                     actual_seg.genomic_location.end == expected_seg.genomic_location.end
                 )
+                assert (
+                    actual_seg.genomic_location.extensions
+                    == expected_seg.genomic_location.extensions
+                )
 
         assert actual.errors == expected.errors
     else:
@@ -715,6 +737,10 @@ def genomic_tx_seg_checks(actual, expected=None, is_valid=True):
                 actual_seg.genomic_location.start == expected_seg.genomic_location.start
             )
             assert actual_seg.genomic_location.end == expected_seg.genomic_location.end
+            assert (
+                actual_seg.genomic_location.extensions
+                == expected_seg.genomic_location.extensions
+            )
 
         assert actual.errors == expected.errors
     else:

{cool_seq_tool-0.14.3 → cool_seq_tool-0.14.5}/tests/sources/test_uta_database.py

@@ -1,11 +1,14 @@
 """Test UTA data source."""
 
+from urllib.parse import urlparse
+
 import pytest
 
 from cool_seq_tool.schemas import Strand
 from cool_seq_tool.sources.uta_database import (
     GenomicTxData,
     GenomicTxMetadata,
+    ParseResult,
     TxExonAlnData,
 )
 
@@ -360,3 +363,98 @@ async def test_get_mane_transcripts_from_genomic_pos(test_db):
     # invalid ac
     resp = await test_db.get_transcripts_from_genomic_pos("NC_000007.14232", 140753336)
     assert resp == []
+
+
+@pytest.mark.parametrize(
+    ("raw_url", "expected"),
+    [
+        # Username + password
+        (
+            "postgresql://user:pass@localhost:5432/dbname",
+            {
+                "scheme": "postgresql",
+                "username": "user",
+                "password": "pass",
+                "hostname": "localhost",
+                "port": 5432,
+                "database": "dbname",
+                "sanitized_url": "postgresql://user:***@localhost:5432/dbname",
+            },
+        ),
+        # Username with null password
+        (
+            "postgresql://user@localhost/dbname",
+            {
+                "scheme": "postgresql",
+                "username": "user",
+                "password": None,
+                "hostname": "localhost",
+                "port": None,
+                "database": "dbname",
+                "sanitized_url": "postgresql://user@localhost/dbname",
+            },
+        ),
+        # Password is "0"
+        (
+            "postgresql://user:0@localhost/dbname",
+            {
+                "scheme": "postgresql",
+                "username": "user",
+                "password": "0",
+                "hostname": "localhost",
+                "port": None,
+                "database": "dbname",
+                "sanitized_url": "postgresql://user:***@localhost/dbname",
+            },
+        ),
+        # Empty password
+        (
+            "postgresql://user:@localhost/dbname",
+            {
+                "scheme": "postgresql",
+                "username": "user",
+                "password": "",
+                "hostname": "localhost",
+                "port": None,
+                "database": "dbname",
+                "sanitized_url": "postgresql://user@localhost/dbname",
+            },
+        ),
+        # No username
+        (
+            "postgresql://localhost:5432/dbname",
+            {
+                "scheme": "postgresql",
+                "username": None,
+                "password": None,
+                "hostname": "localhost",
+                "port": 5432,
+                "database": "dbname",
+                "sanitized_url": "postgresql://localhost:5432/dbname",
+            },
+        ),
+        # With query params
+        (
+            "postgresql://user:secret@localhost/dbname?query#fragment",
+            {
+                "scheme": "postgresql",
+                "username": "user",
+                "password": "secret",
+                "hostname": "localhost",
+                "port": None,
+                "database": "dbname",
+                "sanitized_url": "postgresql://user:***@localhost/dbname?query#fragment",
+            },
+        ),
+    ],
+)
+async def test_parsed_url(raw_url, expected):
+    parsed_result = ParseResult(urlparse(raw_url))
+
+    assert parsed_result.scheme == expected["scheme"]
+    assert parsed_result.username == expected["username"]
+    assert parsed_result.password == expected["password"]
+    assert parsed_result.hostname == expected["hostname"]
+    assert parsed_result.port == expected["port"]
+    assert parsed_result.database == expected["database"]
+    assert parsed_result.sanitized_url == expected["sanitized_url"]