pyobo 0.10.12__py3-none-any.whl → 0.11.0__py3-none-any.whl

pyobo/utils/cache.py

@@ -1,13 +1,12 @@
-# -*- coding: utf-8 -*-
-
 """Utilities for caching files."""
 
 import gzip
 import json
 import logging
 import os
+from collections.abc import Iterable, Mapping
 from pathlib import Path
-from typing import Generic, Iterable, List, Mapping, TypeVar, Union
+from typing import Generic, TypeVar, Union
 
 import networkx as nx
 from pystow.cache import Cached
@@ -46,6 +45,7 @@ class _CachedMapping(Cached[X], Generic[X]):
         use_tqdm: bool = False,
         force: bool = False,
     ):
+        """Initialize the mapping cache."""
         super().__init__(path=path, force=force)
         self.header = header
         self.use_tqdm = use_tqdm
@@ -55,9 +55,11 @@ class CachedMapping(_CachedMapping[Mapping[str, str]]):
     """A cache for simple mappings."""
 
     def load(self) -> Mapping[str, str]:
+        """Load a TSV file."""
         return open_map_tsv(self.path, use_tqdm=self.use_tqdm)
 
     def dump(self, rv: Mapping[str, str]) -> None:
+        """Write a TSV file."""
         write_map_tsv(path=self.path, header=self.header, rv=rv)
 
 
@@ -77,23 +79,29 @@ def write_gzipped_graph(graph: nx.MultiDiGraph, path: Union[str, Path]) -> None:
 
 
 class CachedGraph(Cached[nx.MultiDiGraph]):
+    """A cache for multidigraphs."""
+
     def load(self) -> nx.MultiDiGraph:
+        """Load a graph file."""
         return get_gzipped_graph(self.path)
 
     def dump(self, rv: nx.MultiDiGraph) -> None:
+        """Write a graph file."""
         write_gzipped_graph(rv, self.path)
 
 
 cached_graph = CachedGraph
 
 
-class CachedMultidict(_CachedMapping[Mapping[str, List[str]]]):
+class CachedMultidict(_CachedMapping[Mapping[str, list[str]]]):
     """A cache for complex mappings."""
 
-    def load(self) -> Mapping[str, List[str]]:
+    def load(self) -> Mapping[str, list[str]]:
+        """Load a TSV file representing a multimap."""
         return open_multimap_tsv(self.path, use_tqdm=self.use_tqdm)
 
-    def dump(self, rv: Mapping[str, List[str]]) -> None:
+    def dump(self, rv: Mapping[str, list[str]]) -> None:
+        """Write a TSV file representing a multimap."""
         write_multimap_tsv(path=self.path, header=self.header, rv=rv)
 
 

pyobo/utils/io.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """I/O utilities."""
 
 import collections.abc
@@ -8,9 +6,10 @@ import gzip
 import logging
 import time
 from collections import defaultdict
+from collections.abc import Iterable, Mapping
 from contextlib import contextmanager
 from pathlib import Path
-from typing import Dict, Iterable, List, Mapping, Optional, Set, Tuple, TypeVar, Union
+from typing import Optional, TypeVar, Union
 from xml.etree.ElementTree import Element
 
 import pandas as pd
@@ -78,7 +77,7 @@ def open_multimap_tsv(
     *,
     use_tqdm: bool = False,
     has_header: bool = True,
-) -> Mapping[str, List[str]]:
+) -> Mapping[str, list[str]]:
     """Load a mapping TSV file that has multiple mappings for each."""
     return multidict(_help_multimap_tsv(path=path, use_tqdm=use_tqdm, has_header=has_header))
 
@@ -88,7 +87,7 @@ def _help_multimap_tsv(
     *,
     use_tqdm: bool = False,
     has_header: bool = True,
-) -> Iterable[Tuple[str, str]]:
+) -> Iterable[tuple[str, str]]:
     with open(path) as file:
         if has_header:
             next(file)  # throw away header
@@ -97,7 +96,7 @@ def _help_multimap_tsv(
         yield from get_reader(file)
 
 
-def multidict(pairs: Iterable[Tuple[X, Y]]) -> Mapping[X, List[Y]]:
+def multidict(pairs: Iterable[tuple[X, Y]]) -> Mapping[X, list[Y]]:
     """Accumulate a multidict from a list of pairs."""
     rv = defaultdict(list)
     for key, value in pairs:
@@ -105,7 +104,7 @@ def multidict(pairs: Iterable[Tuple[X, Y]]) -> Mapping[X, List[Y]]:
     return dict(rv)
 
 
-def multisetdict(pairs: Iterable[Tuple[X, Y]]) -> Dict[X, Set[Y]]:
+def multisetdict(pairs: Iterable[tuple[X, Y]]) -> dict[X, set[Y]]:
     """Accumulate a multisetdict from a list of pairs."""
     rv = defaultdict(set)
     for key, value in pairs:
@@ -118,7 +117,7 @@ def write_map_tsv(
     *,
     path: Union[str, Path],
     header: Optional[Iterable[str]] = None,
-    rv: Union[Iterable[Tuple[str, str]], Mapping[str, str]],
+    rv: Union[Iterable[tuple[str, str]], Mapping[str, str]],
     sep: str = "\t",
 ) -> None:
     """Write a mapping dictionary to a TSV file."""
@@ -132,7 +131,7 @@ def write_multimap_tsv(
     *,
     path: Union[str, Path],
     header: Iterable[str],
-    rv: Mapping[str, List[str]],
+    rv: Mapping[str, list[str]],
     sep: str = "\t",
 ) -> None:
     """Write a multiple mapping dictionary to a TSV file."""
@@ -144,7 +143,7 @@ def write_iterable_tsv(
     *,
     path: Union[str, Path],
     header: Optional[Iterable[str]] = None,
-    it: Iterable[Tuple[str, ...]],
+    it: Iterable[tuple[str, ...]],
     sep: str = "\t",
 ) -> None:
     """Write a mapping dictionary to a TSV file."""

pyobo/utils/iter.py

@@ -1,10 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Tools for iterating over things."""
 
 import csv
 import gzip
-from typing import Iterable, List, Tuple, TypeVar
+from collections.abc import Iterable
+from typing import TypeVar
 
 from more_itertools import peekable
 
@@ -18,7 +17,7 @@ Z = TypeVar("Z")
 Y = TypeVar("Y")
 
 
-def iterate_gzips_together(a_path, b_path) -> Iterable[Tuple[str, str, List[str]]]:
+def iterate_gzips_together(a_path, b_path) -> Iterable[tuple[str, str, list[str]]]:
     """Iterate over two gzipped files together."""
     with gzip.open(a_path, mode="rt", errors="ignore") as a, gzip.open(b_path, mode="rt") as b:
         a = csv.reader(a, delimiter="\t", quoting=csv.QUOTE_MINIMAL)
@@ -27,8 +26,8 @@ def iterate_gzips_together(a_path, b_path) -> Iterable[Tuple[str, str, List[str]
 
 
 def iterate_together(
-    a: Iterable[Tuple[X, Y]], b: Iterable[Tuple[X, Z]]
-) -> Iterable[Tuple[X, Y, List[Z]]]:
+    a: Iterable[tuple[X, Y]], b: Iterable[tuple[X, Z]]
+) -> Iterable[tuple[X, Y, list[Z]]]:
     """Iterate over two sorted lists that have the same keys.
 
     The lists have to have the following invariants:

pyobo/utils/misc.py

@@ -1,12 +1,10 @@
-# -*- coding: utf-8 -*-
-
 """Miscellaneous utilities."""
 
 import gzip
 import logging
 import os
 from datetime import datetime
-from subprocess import check_output  # noqa:S404
+from subprocess import check_output
 from typing import Optional
 
 __all__ = [

pyobo/utils/ndex_utils.py

@@ -1,10 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Utilities for caching files from NDEx."""
 
 import json
 import os
-from typing import Any, Iterable, List, Mapping, Tuple
+from collections.abc import Iterable, Mapping
+from typing import Any
 
 import requests
 from tqdm.auto import tqdm
@@ -21,7 +20,7 @@ __all__ = [
 NDEX_BASE_URL = "http://public.ndexbio.org/v2"
 NETWORK_ENDPOINT = f"{NDEX_BASE_URL}/network"
 NETWORKSET_ENDPOINT = f"{NDEX_BASE_URL}/networkset"
-CX = List[Mapping[str, Any]]
+CX = list[Mapping[str, Any]]
 
 
 def iterate_aspect(cx: CX, aspect: str) -> Iterable[Any]:
@@ -47,7 +46,7 @@ def ensure_ndex_network(prefix: str, uuid: str, force: bool = False) -> CX:
 
 def ensure_ndex_network_set(
     prefix: str, uuid: str, use_tqdm: bool = False, force: bool = False
-) -> Iterable[Tuple[str, CX]]:
+) -> Iterable[tuple[str, CX]]:
     """Ensure the list of networks that goes with NCI PID on NDEx."""
     it = _help_ensure_ndex_network_set(prefix, uuid, force=force)
     if use_tqdm:
@@ -56,7 +55,7 @@ def ensure_ndex_network_set(
         yield network_uuid, ensure_ndex_network(prefix, network_uuid, force=force)
 
 
-def _help_ensure_ndex_network_set(prefix: str, uuid: str, force: bool = False) -> List[str]:
+def _help_ensure_ndex_network_set(prefix: str, uuid: str, force: bool = False) -> list[str]:
     """Ensure the list of networks that goes with NCI PID on NDEx."""
     networkset_path = prefix_directory_join(prefix, name="networks.txt")
     if os.path.exists(networkset_path) and not force:
@@ -69,5 +68,5 @@ def _help_ensure_ndex_network_set(prefix: str, uuid: str, force: bool = False) -
     network_uuids = res_json["networks"]
     with open(networkset_path, "w") as file:
         for network_uuid in sorted(network_uuids):
-            print(network_uuid, file=file)  # noqa: T201
+            print(network_uuid, file=file)
     return network_uuids

pyobo/utils/path.py

@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Utilities for building paths."""
 
 import logging
 from pathlib import Path
-from typing import Any, Callable, Dict, Literal, Optional, Union
+from typing import Any, Callable, Literal, Optional, Union
 
 import pandas as pd
 import requests_ftp
@@ -46,7 +44,8 @@ def prefix_directory_join(
         logger.info("[%s] got version %s", prefix, version)
     elif not isinstance(version, str):
         raise TypeError(f"Invalid type: {version} ({type(version)})")
-    assert version is not None
+    if version is None:
+        raise AssertionError
     version = cleanup_version(version, prefix=prefix)
     if version is not None and "/" in version:
         raise ValueError(f"[{prefix}] Can not have slash in version: {version}")
@@ -78,7 +77,7 @@ def ensure_path(
     if not path.exists() and error_on_missing:
         raise FileNotFoundError
 
-    kwargs: Dict[str, Any]
+    kwargs: dict[str, Any]
     if verify:
         kwargs = {"backend": backend}
     else:

pyobo/version.py

@@ -1,12 +1,10 @@
-# -*- coding: utf-8 -*-
-
 """Version information for PyOBO.
 
 Run with ``python -m pyobo.version``
 """
 
 import os
-from subprocess import CalledProcessError, check_output  # noqa: S404
+from subprocess import CalledProcessError, check_output
 
 __all__ = [
     "VERSION",
@@ -14,14 +12,14 @@ __all__ = [
     "get_git_hash",
 ]
 
-VERSION = "0.10.12"
+VERSION = "0.11.0"
 
 
 def get_git_hash() -> str:
     """Get the PyOBO git hash."""
     with open(os.devnull, "w") as devnull:
         try:
-            ret = check_output(  # noqa: S603,S607
+            ret = check_output(
                 ["git", "rev-parse", "HEAD"],
                 cwd=os.path.dirname(__file__),
                 stderr=devnull,

pyobo/xrefdb/__init__.py

@@ -1,3 +1 @@
-# -*- coding: utf-8 -*-
-
 """Extraction of mappings from OBO documents."""

pyobo/xrefdb/canonicalizer.py

@@ -1,10 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Tools for canonicalizing a CURIE based on a priority list."""
 
+from collections.abc import Iterable, Mapping
 from dataclasses import dataclass, field
 from functools import lru_cache
-from typing import Iterable, List, Mapping, Optional, Set, Tuple
+from typing import Optional
 
 import networkx as nx
 import pandas as pd
@@ -34,7 +33,7 @@ class Canonicalizer:
     graph: nx.Graph
 
     #: A list of prefixes. The ones with the lower index are higher priority
-    priority: Optional[List[str]] = None
+    priority: Optional[list[str]] = None
 
     #: Longest length paths allowed
     cutoff: int = 5
@@ -54,7 +53,7 @@ class Canonicalizer:
     def _get_priority_dict(self, curie: str) -> Mapping[str, int]:
         return dict(self._iterate_priority_targets(curie))
 
-    def _iterate_priority_targets(self, curie: str) -> Iterable[Tuple[str, int]]:
+    def _iterate_priority_targets(self, curie: str) -> Iterable[tuple[str, int]]:
         for target in nx.single_source_shortest_path(self.graph, curie, cutoff=self.cutoff):
             priority = self._key(target)
             if priority is not None:
@@ -79,20 +78,20 @@ class Canonicalizer:
         return cls._get_default_helper(priority=priority)
 
     @classmethod
-    @lru_cache()
-    def _get_default_helper(cls, priority: Optional[Tuple[str, ...]] = None) -> "Canonicalizer":
+    @lru_cache
+    def _get_default_helper(cls, priority: Optional[tuple[str, ...]] = None) -> "Canonicalizer":
         """Help get the default canonicalizer."""
         graph = cls._get_default_graph()
         return cls(graph=graph, priority=list(priority) if priority else None)
 
     @staticmethod
-    @lru_cache()
+    @lru_cache
     def _get_default_graph() -> nx.Graph:
         df = resource_utils.ensure_inspector_javert_df()
         graph = get_graph_from_xref_df(df)
         return graph
 
-    def iterate_flat_mapping(self, use_tqdm: bool = True) -> Iterable[Tuple[str, str]]:
+    def iterate_flat_mapping(self, use_tqdm: bool = True) -> Iterable[tuple[str, str]]:
         """Iterate over the canonical mapping from all nodes to their canonical CURIEs."""
         nodes = self.graph.nodes()
         if use_tqdm:
@@ -114,13 +113,13 @@ class Canonicalizer:
         self,
         curie: str,
         cutoff: Optional[int] = None,
-    ) -> Optional[Mapping[str, List[Mapping[str, str]]]]:
+    ) -> Optional[Mapping[str, list[Mapping[str, str]]]]:
         """Get all shortest paths between given entity and its equivalent entities."""
         return single_source_shortest_path(graph=self.graph, curie=curie, cutoff=cutoff)
 
     def all_shortest_paths(
         self, source_curie: str, target_curie: str
-    ) -> List[List[Mapping[str, str]]]:
+    ) -> list[list[Mapping[str, str]]]:
         """Get all shortest paths between the two entities."""
         return all_shortest_paths(
             graph=self.graph, source_curie=source_curie, target_curie=target_curie
@@ -134,11 +133,14 @@ class Canonicalizer:
 
 def all_shortest_paths(
     graph: nx.Graph, source_curie: str, target_curie: str
-) -> List[List[Mapping[str, str]]]:
+) -> list[list[Mapping[str, str]]]:
     """Get all shortest paths between the two CURIEs."""
     _paths = nx.all_shortest_paths(graph, source=source_curie, target=target_curie)
     return [
-        [dict(source=s, target=t, provenance=graph[s][t]["source"]) for s, t in pairwise(_path)]
+        [
+            {"source": s, "target": t, "provenance": graph[s][t]["source"]}
+            for s, t in pairwise(_path)
+        ]
         for _path in _paths
     ]
 
@@ -147,7 +149,7 @@ def single_source_shortest_path(
     graph: nx.Graph,
     curie: str,
     cutoff: Optional[int] = None,
-) -> Optional[Mapping[str, List[Mapping[str, str]]]]:
+) -> Optional[Mapping[str, list[Mapping[str, str]]]]:
     """Get the shortest path from the CURIE to all elements of its equivalence class.
 
     Things that didn't work:
@@ -156,7 +158,9 @@ def single_source_shortest_path(
     ------------
     .. code-block:: python
 
-        for curies in tqdm(nx.connected_components(graph), desc='filling connected components', unit_scale=True):
+        for curies in tqdm(
+            nx.connected_components(graph), desc="filling connected components", unit_scale=True
+        ):
             for c1, c2 in itt.combinations(curies, r=2):
                 if not graph.has_edge(c1, c2):
                     graph.add_edge(c1, c2, inferred=True)
@@ -165,7 +169,9 @@ def single_source_shortest_path(
     ------------
     .. code-block:: python
 
-        for curie in tqdm(graph, total=graph.number_of_nodes(), desc='mapping connected components', unit_scale=True):
+        for curie in tqdm(
+            graph, total=graph.number_of_nodes(), desc="mapping connected components", unit_scale=True
+        ):
             for incident_curie in nx.node_connected_component(graph, curie):
                 if not graph.has_edge(curie, incident_curie):
                     graph.add_edge(curie, incident_curie, inferred=True)
@@ -177,13 +183,16 @@ def single_source_shortest_path(
         return None
     rv = nx.single_source_shortest_path(graph, curie, cutoff=cutoff)
     return {
-        k: [dict(source=s, target=t, provenance=graph[s][t]["provenance"]) for s, t in pairwise(v)]
+        k: [
+            {"source": s, "target": t, "provenance": graph[s][t]["provenance"]}
+            for s, t in pairwise(v)
+        ]
         for k, v in rv.items()
         if k != curie  # don't map to self
     }
 
 
-def get_equivalent(curie: str, cutoff: Optional[int] = None) -> Set[str]:
+def get_equivalent(curie: str, cutoff: Optional[int] = None) -> set[str]:
     """Get equivalent CURIEs."""
     canonicalizer = Canonicalizer.get_default()
     r = canonicalizer.single_source_shortest_path(curie=curie, cutoff=cutoff)

pyobo/xrefdb/priority.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Configuration for the default priority list."""
 
 import bioregistry

pyobo/xrefdb/sources/__init__.py

@@ -1,10 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Sources of xrefs not from OBO."""
 
 import logging
+from collections.abc import Iterable, Mapping
 from functools import lru_cache
-from typing import Callable, Iterable, Mapping, Optional
+from typing import Callable, Optional
 
 import pandas as pd
 from class_resolver import FunctionResolver
@@ -22,7 +21,7 @@ logger = logging.getLogger(__name__)
 XrefGetter = Callable[[], pd.DataFrame]
 
 
-@lru_cache()
+@lru_cache
 def _get_xref_plugins() -> Mapping[str, XrefGetter]:
     resolver: FunctionResolver[XrefGetter] = FunctionResolver.from_entrypoint("pyobo.xrefs")
     return resolver.lookup_dict

pyobo/xrefdb/sources/biomappings.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Get the Biomappings manually curated equivalences."""
 
 import pandas as pd

pyobo/xrefdb/sources/cbms2019.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Cross references from cbms2019.
 
 .. seealso:: https://github.com/pantapps/cbms2019

pyobo/xrefdb/sources/chembl.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Get ChEMBL xrefs."""
 
 from typing import Optional

pyobo/xrefdb/sources/compath.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Import ComPath mappings between pathways."""
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 from pystow.utils import get_commit

pyobo/xrefdb/sources/famplex.py

@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Get FamPlex xrefs."""
 
 import logging
+from collections.abc import Mapping
 from functools import lru_cache
-from typing import Mapping, Tuple
 
 import bioregistry
 import pandas as pd
@@ -50,8 +48,8 @@ def get_famplex_xrefs_df(force: bool = False) -> pd.DataFrame:
     return df
 
 
-@lru_cache()
-def get_remapping(force: bool = False) -> Mapping[Tuple[str, str], Tuple[str, str, str]]:
+@lru_cache
+def get_remapping(force: bool = False) -> Mapping[tuple[str, str], tuple[str, str, str]]:
     """Get a mapping from database/identifier pairs to famplex identifiers."""
     df = _get_famplex_df(force=force)
     rv = {}

pyobo/xrefdb/sources/gilda.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Cross references from Gilda.
 
 .. seealso:: https://github.com/indralabs/gilda

pyobo/xrefdb/sources/intact.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Get the xrefs from IntAct."""
 
-from typing import Mapping
+from collections.abc import Mapping
 
 import pandas as pd
 
@@ -49,7 +47,8 @@ def get_complexportal_mapping() -> Mapping[str, str]:
     .. code-block:: python
 
         from pyobo import get_filtered_xrefs
-        intact_complexportal_mapping = get_filtered_xrefs('intact', 'complexportal')
+
+        intact_complexportal_mapping = get_filtered_xrefs("intact", "complexportal")
     """
 
     @cached_mapping(
@@ -87,7 +86,8 @@ def get_reactome_mapping() -> Mapping[str, str]:
     .. code-block:: python
 
         from pyobo import get_filtered_xrefs
-        intact_complexportal_mapping = get_filtered_xrefs('intact', 'reactome')
+
+        intact_complexportal_mapping = get_filtered_xrefs("intact", "reactome")
     """
 
     @cached_mapping(

pyobo/xrefdb/sources/ncit.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Import NCIT mappings."""
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/xrefdb/sources/pubchem.py

@@ -1,12 +1,10 @@
-# -*- coding: utf-8 -*-
-
 """Get xrefs from PubChem Compound to MeSH."""
 
 from typing import Optional
 
 import pandas as pd
 
-from ...api.utils import get_version
+from ...api.utils import safe_get_version
 from ...constants import XREF_COLUMNS
 from ...sources.pubchem import _get_pubchem_extras_url, get_pubchem_id_to_mesh_id
 
@@ -18,8 +16,7 @@ __all__ = [
 def get_pubchem_mesh_df(version: Optional[str] = None) -> pd.DataFrame:
     """Get PubChem Compound-MeSH xrefs."""
     if version is None:
-        version = get_version("pubchem")
-        assert version is not None
+        version = safe_get_version("pubchem")
     cid_mesh_url = _get_pubchem_extras_url(version, "CID-MeSH")
     return pd.DataFrame(
         [

pyobo/xrefdb/sources/wikidata.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Get Wikidata xrefs.
 
 Run with ``python -m pyobo.xrefdb.sources.wikidata``.
@@ -7,7 +5,7 @@ Run with ``python -m pyobo.xrefdb.sources.wikidata``.
 
 import json
 import logging
-from typing import Iterable, Tuple
+from collections.abc import Iterable
 
 import bioregistry
 import click
@@ -68,7 +66,7 @@ def get_wikidata_df(prefix: str, wikidata_property: str) -> pd.DataFrame:
 
 def iter_wikidata_mappings(
     wikidata_property: str, *, cache: bool = True
-) -> Iterable[Tuple[str, str]]:
+) -> Iterable[tuple[str, str]]:
     """Iterate over Wikidata xrefs."""
     path = WIKIDATA_MAPPING_DIRECTORY.join(name=f"{wikidata_property}.json")
     if path.exists() and cache: