pyobo 0.10.12__py3-none-any.whl → 0.11.1__py3-none-any.whl

pyobo/plugins.py

@@ -1,9 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Tools for loading entry points."""
 
+from collections.abc import Iterable, Mapping
 from functools import lru_cache
-from typing import Callable, Iterable, Mapping, Optional
+from typing import Callable, Optional
 
 from .struct import Obo
 
@@ -14,7 +13,7 @@ __all__ = [
 ]
 
 
-@lru_cache()
+@lru_cache
 def _get_nomenclature_plugins() -> Mapping[str, Callable[[], Obo]]:
     from .sources import ontology_resolver
 

pyobo/reader.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
-
 """OBO Readers."""
 
 import logging
+from collections.abc import Iterable, Mapping
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Iterable, List, Mapping, Optional, Tuple, Union
+from typing import Any, Optional, Union
 
 import bioregistry
 import networkx as nx
@@ -13,7 +12,7 @@ from more_itertools import pairwise
 from tqdm.auto import tqdm
 
 from .constants import DATE_FORMAT, PROVENANCE_PREFIXES
-from .identifier_utils import MissingPrefix, normalize_curie
+from .identifier_utils import MissingPrefixError, normalize_curie
 from .registries import curie_has_blacklisted_prefix, curie_is_blacklisted, remap_prefix
 from .struct import (
     Obo,
@@ -39,7 +38,7 @@ logger = logging.getLogger(__name__)
 
 # FIXME use bioontologies
 # RELATION_REMAPPINGS: Mapping[str, Tuple[str, str]] = bioontologies.upgrade.load()
-RELATION_REMAPPINGS: Mapping[str, Tuple[str, str]] = {
+RELATION_REMAPPINGS: Mapping[str, tuple[str, str]] = {
     "part_of": part_of.pair,
     "has_part": has_part.pair,
     "develops_from": develops_from.pair,
@@ -75,7 +74,7 @@ def from_obo_path(
     return from_obonet(graph, strict=strict, **kwargs)
 
 
-def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noqa:C901
+def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":
     """Get all of the terms from a OBO graph."""
     _ontology = graph.graph["ontology"]
     ontology = bioregistry.normalize_prefix(_ontology)  # probably always okay
@@ -126,12 +125,12 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
         )
         for prefix, identifier, data in _iter_obo_graph(graph=graph, strict=strict)
     )
-    references: Mapping[Tuple[str, str], Reference] = {
+    references: Mapping[tuple[str, str], Reference] = {
         reference.pair: reference for reference in reference_it
     }
 
     #: CURIEs to typedefs
-    typedefs: Mapping[Tuple[str, str], TypeDef] = {
+    typedefs: Mapping[tuple[str, str], TypeDef] = {
         typedef.pair: typedef for typedef in iterate_graph_typedefs(graph, ontology)
     }
 
@@ -152,7 +151,7 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
 
         try:
             node_xrefs = list(iterate_node_xrefs(prefix=prefix, data=data, strict=strict))
-        except MissingPrefix as e:
+        except MissingPrefixError as e:
             e.reference = reference
             raise e
         xrefs, provenance = [], []
@@ -171,7 +170,7 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
 
         try:
             alt_ids = list(iterate_node_alt_ids(data, strict=strict))
-        except MissingPrefix as e:
+        except MissingPrefixError as e:
             e.reference = reference
             raise e
         n_alt_ids += len(alt_ids)
@@ -185,7 +184,7 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
                     strict=strict,
                 )
             )
-        except MissingPrefix as e:
+        except MissingPrefixError as e:
             e.reference = reference
             raise e
         n_parents += len(parents)
@@ -220,7 +219,7 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
                     strict=strict,
                 )
             )
-        except MissingPrefix as e:
+        except MissingPrefixError as e:
             e.reference = reference
             raise e
         for relation, reference in relations_references:
@@ -278,7 +277,7 @@ def _iter_obo_graph(
     graph: nx.MultiDiGraph,
     *,
     strict: bool = True,
-) -> Iterable[Tuple[str, str, Mapping[str, Any]]]:
+) -> Iterable[tuple[str, str, Mapping[str, Any]]]:
     """Iterate over the nodes in the graph with the prefix stripped (if it's there)."""
     for node, data in graph.nodes(data=True):
         prefix, identifier = normalize_curie(node, strict=strict)
@@ -366,7 +365,8 @@ def iterate_graph_typedefs(
 
 def get_definition(
     data, *, prefix: str, identifier: str
-) -> Union[Tuple[None, None], Tuple[str, List[Reference]]]:
+) -> Union[tuple[None, None], tuple[str, list[Reference]]]:
+    """Extract the definition from the data."""
     definition = data.get("def")  # it's allowed not to have a definition
     if not definition:
         return None, None
@@ -379,7 +379,7 @@ def _extract_definition(
     prefix: str,
     identifier: str,
     strict: bool = False,
-) -> Union[Tuple[None, None], Tuple[str, List[Reference]]]:
+) -> Union[tuple[None, None], tuple[str, list[Reference]]]:
     """Extract the definitions."""
     if not s.startswith('"'):
         raise ValueError("definition does not start with a quote")
@@ -405,7 +405,7 @@ def _get_first_nonquoted(s: str) -> Optional[int]:
     return None
 
 
-def _quote_split(s: str) -> Tuple[str, str]:
+def _quote_split(s: str) -> tuple[str, str]:
     s = s.lstrip('"')
     i = _get_first_nonquoted(s)
     if i is None:
@@ -416,9 +416,7 @@ def _quote_split(s: str) -> Tuple[str, str]:
 def _clean_definition(s: str) -> str:
     # if '\t' in s:
     #     logger.warning('has tab')
-    return (
-        s.replace('\\"', '"').replace("\n", " ").replace("\t", " ").replace(r"\d", "")  # noqa:W605
-    )
+    return s.replace('\\"', '"').replace("\n", " ").replace("\t", " ").replace(r"\d", "")
 
 
 def _extract_synonym(
@@ -516,7 +514,7 @@ HANDLED_PROPERTY_TYPES = {
 
 def iterate_node_properties(
     data: Mapping[str, Any], *, property_prefix: Optional[str] = None, term=None
-) -> Iterable[Tuple[str, str]]:
+) -> Iterable[tuple[str, str]]:
     """Extract properties from a :mod:`obonet` node's data."""
     for prop_value_type in data.get("property_value", []):
         try:
@@ -568,7 +566,7 @@ def iterate_node_relationships(
     prefix: str,
     identifier: str,
     strict: bool = True,
-) -> Iterable[Tuple[Reference, Reference]]:
+) -> Iterable[tuple[Reference, Reference]]:
     """Extract relationships from a :mod:`obonet` node's data."""
     for s in data.get("relationship", []):
         relation_curie, target_curie = s.split(" ")

pyobo/registries/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Extract registry information."""
 
 from .metaregistry import (  # noqa: F401

pyobo/registries/metaregistry.py

@@ -1,13 +1,11 @@
-# -*- coding: utf-8 -*-
-
 """Load the manually curated metaregistry."""
 
 import itertools as itt
 import json
 import os
+from collections.abc import Iterable, Mapping
 from functools import lru_cache
 from pathlib import Path
-from typing import Iterable, Mapping, Set, Tuple
 
 import bioregistry
 
@@ -25,7 +23,7 @@ def has_no_download(prefix: str) -> bool:
 
 
 @lru_cache(maxsize=1)
-def _no_download() -> Set[str]:
+def _no_download() -> set[str]:
     """Get the list of prefixes not available as OBO."""
     return {
         prefix
@@ -41,7 +39,7 @@ def curie_has_blacklisted_prefix(curie: str) -> bool:
 
 
 @lru_cache(maxsize=1)
-def get_xrefs_prefix_blacklist() -> Set[str]:
+def get_xrefs_prefix_blacklist() -> set[str]:
     """Get the set of blacklisted xref prefixes."""
     #: Xrefs starting with these prefixes will be ignored
     prefixes = set(
@@ -65,7 +63,7 @@ def curie_has_blacklisted_suffix(curie: str) -> bool:
 
 
 @lru_cache(maxsize=1)
-def get_xrefs_suffix_blacklist() -> Set[str]:
+def get_xrefs_suffix_blacklist() -> set[str]:
     """Get the set of blacklisted xref suffixes."""
     #: Xrefs ending with these suffixes will be ignored
     return set(CURATED_REGISTRY["blacklists"]["suffix"])
@@ -77,7 +75,7 @@ def curie_is_blacklisted(curie: str) -> bool:
 
 
 @lru_cache(maxsize=1)
-def get_xrefs_blacklist() -> Set[str]:
+def get_xrefs_blacklist() -> set[str]:
     """Get the set of blacklisted xrefs."""
     rv = set()
     for x in CURATED_REGISTRY["blacklists"]["full"]:
@@ -123,7 +121,7 @@ def remap_prefix(curie: str) -> str:
     return curie
 
 
-def iter_cached_obo() -> Iterable[Tuple[str, str]]:
+def iter_cached_obo() -> Iterable[tuple[str, str]]:
     """Iterate over cached OBO paths."""
     for prefix in os.listdir(RAW_DIRECTORY):
         if prefix in GLOBAL_SKIP or has_no_download(prefix) or bioregistry.is_deprecated(prefix):

pyobo/resource_utils.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Resource utilities for PyOBO."""
 
+from collections.abc import Sequence
 from functools import lru_cache
-from typing import Sequence
 
 import click
 import pandas as pd

pyobo/resources/__init__.py

@@ -1,3 +1 @@
-# -*- coding: utf-8 -*-
-
 """Pre-cached resources for PyOBO."""

pyobo/resources/ncbitaxon.py

@@ -1,12 +1,11 @@
-# -*- coding: utf-8 -*-
-
 """Loading of the NCBI Taxonomy names."""
 
 import csv
 import gzip
+from collections.abc import Mapping
 from functools import lru_cache
 from pathlib import Path
-from typing import Mapping, Optional, Union
+from typing import Optional, Union
 
 import requests
 

pyobo/resources/ro.py

@@ -1,11 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Loading of the relations ontology names."""
 
 import csv
 import os
+from collections.abc import Mapping
 from functools import lru_cache
-from typing import Mapping, Tuple
 
 import requests
 
@@ -20,7 +18,7 @@ PREFIX = "http://purl.obolibrary.org/obo/"
 
 
 @lru_cache(maxsize=1)
-def load_ro() -> Mapping[Tuple[str, str], str]:
+def load_ro() -> Mapping[tuple[str, str], str]:
     """Load the relation ontology names."""
     if not os.path.exists(PATH):
         download()

pyobo/resources/so.py

@@ -0,0 +1,55 @@
+"""Loading of the relations ontology names."""
+
+from __future__ import annotations
+
+import csv
+import os
+from functools import lru_cache
+
+import requests
+
+__all__ = [
+    "get_so_name",
+    "load_so",
+]
+
+HERE = os.path.abspath(os.path.dirname(__file__))
+SO_PATH = os.path.join(HERE, "so.tsv")
+SO_JSON_URL = "https://github.com/The-Sequence-Ontology/SO-Ontologies/raw/refs/heads/master/Ontology_Files/so-simple.json"
+SO_URI_PREFIX = "http://purl.obolibrary.org/obo/SO_"
+
+
+def get_so_name(so_id: str) -> str | None:
+    """Get the name from the identifier."""
+    return load_so().get(so_id)
+
+
+@lru_cache(maxsize=1)
+def load_so() -> dict[str, str]:
+    """Load the Sequence Ontology names."""
+    if not os.path.exists(SO_PATH):
+        download_so()
+    with open(SO_PATH) as file:
+        return dict(csv.reader(file, delimiter="\t"))
+
+
+def download_so():
+    """Download the latest version of the Relation Ontology."""
+    rows = []
+    res_json = requests.get(SO_JSON_URL).json()
+    for node in res_json["graphs"][0]["nodes"]:
+        uri = node["id"]
+        if not uri.startswith(SO_URI_PREFIX):
+            continue
+        identifier = uri.removeprefix(SO_URI_PREFIX)
+        name = node.get("lbl")
+        if name:
+            rows.append((identifier, name))
+
+    with open(SO_PATH, "w") as file:
+        writer = csv.writer(file, delimiter="\t")
+        writer.writerows(sorted(rows, key=lambda x: int(x[0])))
+
+
+if __name__ == "__main__":
+    download_so()