Update

Author: cthoyt

src/bioontologies/constants.py

@@ -15,6 +15,10 @@
     "one": "http://purl.obolibrary.org/obo/ONE",
     "ons": "https://raw.githubusercontent.com/enpadasi/Ontology-for-Nutritional-Studies/master/ons.owl",
     "ontie": "https://ontology.iedb.org/ontology/ontie.owl",
+    "aro": "http://purl.obolibrary.org/obo/antibiotic_resistance.owl",
+    "http://purl.obolibrary.org/obo/iao/cdt.owl": "cdt",
+    "http://purl.obolibrary.org/obo/clo/clo_merged.owl": "clo",
+    "http://purl.obolibrary.org/obo/clyh/clyh.owl": "clyh",
 }
 
 IRI_TO_PREFIX = {v: k for k, v in CANONICAL.items()}

src/bioontologies/obograph.py

@@ -12,9 +12,10 @@
 from collections.abc import Iterable, Mapping
 from functools import lru_cache
 from pathlib import Path
-from typing import Any, Literal
+from typing import TYPE_CHECKING, Any, Literal
 
 import bioregistry
+import curies
 import pandas as pd
 from bioregistry import NormalizedNamableReference as Reference
 from bioregistry import manager
@@ -25,6 +26,9 @@
 from .constants import CANONICAL, IRI_TO_PREFIX
 from .relations import get_normalized_label, ground_relation, label_norm
 
+if TYPE_CHECKING:
+    import networkx as nx
+
 __all__ = [
     "Definition",
     "Edge",
@@ -55,7 +59,7 @@ def standardize(self) -> Self:
         """Standardize the data in this class."""
         raise NotImplementedError
 
-    def raise_on_unstandardized(self):
+    def raise_on_unstandardized(self) -> None:
         """Raise an exception if standarization has not occurred."""
         if not self.standardized:
             raise ValueError
@@ -215,7 +219,7 @@ class Meta(BaseModel, StandardizeMixin):
     subsets: list[str] | None = None
     xrefs: list[Xref] | None = None
     synonyms: list[Synonym] | None = None
-    comments: list | None = None
+    comments: list[str] | None = None
     version: str | None = None
     properties: list[Property] | None = Field(None, alias="basicPropertyValues")
     deprecated: bool = False
@@ -303,7 +307,7 @@ def from_parsed(
         )
 
 
-def _help_get_properties(self, predicate_iris: str | list[str]) -> list[str]:
+def _help_get_properties(self: Graph | Node, predicate_iris: str | list[str]) -> list[str]:
     if not self.meta:
         return []
     if isinstance(predicate_iris, str):
@@ -330,12 +334,16 @@ class Node(BaseModel, StandardizeMixin):
     @property
     def prefix(self) -> str | None:
         """Get the prefix for the node if it has been standardized."""
-        return self.reference and self.reference.prefix
+        if self.reference:
+            return self.reference.prefix
+        return None
 
     @property
     def identifier(self) -> str | None:
         """Get the identifier for the node if it has been standardized."""
-        return self.reference and self.reference.identifier
+        if self.reference is not None:
+            return self.reference.identifier
+        return None
 
     def standardize(self) -> Self:
         """Ground the node to a standard prefix and luid based on its id (URI)."""
@@ -536,17 +544,23 @@ def roots(self) -> list[str]:
     @property
     def license(self) -> str | None:
         """Get the license of the ontology."""
-        return self._get_property("http://purl.org/dc/terms/license")
+        return self._get_property(
+            ["http://purl.org/dc/terms/license", "http://purl.org/dc/elements/1.1/license"]
+        )
 
     @property
     def title(self) -> str | None:
         """Get the title of the ontology."""
-        return self._get_property("http://purl.org/dc/elements/1.1/title")
+        return self._get_property(
+            ["http://purl.org/dc/terms/title", "http://purl.org/dc/elements/1.1/title"]
+        )
 
     @property
     def description(self) -> str | None:
         """Get the license of the ontology."""
-        return self._get_property("http://purl.org/dc/elements/1.1/description")
+        return self._get_property(
+            ["http://purl.org/dc/terms/description", "http://purl.org/dc/elements/1.1/description"]
+        )
 
     @property
     def version_iri(self) -> str | None:
@@ -643,9 +657,9 @@ def standardize(
 
         return self
 
-    def _standardize_prefix(self):
+    def _standardize_prefix(self) -> None:
         if not self.id:
-            return
+            return None
         if self.id in IRI_TO_PREFIX:
             self.prefix = IRI_TO_PREFIX[self.id]
         elif self.id.startswith("http://purl.obolibrary.org/obo/"):
@@ -656,10 +670,12 @@ def _standardize_prefix(self):
                     self.id.removeprefix("http://purl.obolibrary.org/obo/")
                     .removesuffix(suffix)
                     .removesuffix("_import")
+                    .removesuffix("_merged")
                 )
                 if prefix != bioregistry.normalize_prefix(prefix):
                     tqdm.write(f"could not guess prefix from {self.id}")
                     return
+                # FIXME check if clyh/clyh
                 self.prefix = prefix
                 return
 
@@ -696,7 +712,9 @@ def get_xrefs(self) -> list[tuple[Reference, Reference, Reference]]:
                 rv.append((node.reference, xref.predicate, xref.value))
         return rv
 
-    def _get_edge_predicate_label(self, edge: Edge, ctn, require_label: bool = False) -> str:
+    def _get_edge_predicate_label(
+        self, edge: Edge, ctn: Mapping[str, str], require_label: bool = False
+    ) -> str:
         if edge.predicate:
             label = get_normalized_label(edge.predicate.curie)
             if label:
@@ -870,7 +888,7 @@ def get_curie_to_name(self) -> Mapping[str, str]:
             node.curie: node.name for node in self.nodes if node.name and node.reference is not None
         }
 
-    def get_networkx(self):
+    def get_networkx(self) -> nx.MultiDiGraph:
         """Get a networkx multi-directional graph."""
         import networkx as nx
 
@@ -902,7 +920,7 @@ def write_warned(path: str | Path) -> None:
 
 
 @lru_cache(1)
-def _get_converter():
+def _get_converter() -> curies.Converter:
     return bioregistry.manager.get_converter(include_prefixes=True)
 
 
@@ -933,7 +951,7 @@ def _get_reference(s: str, *, debug: bool = False) -> Reference | None:  # noqa:
         if reference is not None:
             return reference
         if s not in WARNED:
-            logger.warning("could not parse OBO internal relation: %s", s)
+            logger.debug("could not parse OBO internal relation: %s", s)
         WARNED[s] += 1
 
     if "upload.wikimedia.org" in s:

src/bioontologies/robot.py

@@ -17,9 +17,11 @@
 from typing import Any, Literal
 
 import bioregistry
+import click
 import pystow
 import requests
 from pystow.utils import download, name_from_url
+from tqdm import tqdm
 
 from .obograph import Graph, GraphDocument
 
@@ -178,7 +180,8 @@ def get_obograph_by_prefix(
     json_path: None | str | Path = None,
     cache: bool = False,
     check: bool = True,
-    reason: bool = True,
+    reason: bool = False,
+    merge: bool = False,
 ) -> ParseResults:
     """Get an ontology by its Bioregistry prefix."""
     if prefix != bioregistry.normalize_prefix(prefix):
@@ -194,7 +197,7 @@ def get_obograph_by_prefix(
             msg = f"[{prefix}] could not parse JSON from {json_iri}: {e}"
             messages.append(msg)
             GETTER_MESSAGES.append(msg)
-            logger.warning(msg)
+            tqdm.write(click.style(msg, fg="red"))
         else:
             return parse_results
 
@@ -211,17 +214,26 @@ def get_obograph_by_prefix(
                     path = os.path.join(d, name_from_url(iri))
                     download(iri, path=path)
                     parse_results = convert_to_obograph_local(
-                        path, json_path=json_path, from_iri=iri, check=check
+                        path,
+                        json_path=json_path,
+                        from_iri=iri,
+                        check=check,
+                        merge=merge,
+                        reason=reason,
                     )
             else:
                 parse_results = convert_to_obograph_remote(
-                    iri, json_path=json_path, check=check, reason=reason
+                    iri,
+                    json_path=json_path,
+                    check=check,
+                    reason=reason,
+                    merge=merge,
                 )
         except (subprocess.CalledProcessError, KeyError):
             msg = f"[{prefix}] could not parse {label} from {iri}"
             messages.append(msg)
             GETTER_MESSAGES.append(msg)
-            logger.warning(msg)
+            tqdm.write(click.style(msg, fg="red"))
             continue
         else:
             # stick all messages before
@@ -237,6 +249,8 @@ def convert_to_obograph_local(
     json_path: None | str | Path = None,
     from_iri: str | None = None,
     check: bool = True,
+    reason: bool = False,
+    merge: bool = False,
 ) -> ParseResults:
     """Convert a local OWL/OBO file to an OBO Graph JSON object.
 
@@ -255,7 +269,13 @@ def convert_to_obograph_local(
         output from the ROBOT conversion program
     """
     return convert_to_obograph(
-        input_path=path, input_flag="-i", json_path=json_path, from_iri=from_iri, check=check
+        input_path=path,
+        input_flag="-i",
+        json_path=json_path,
+        from_iri=from_iri,
+        check=check,
+        reason=reason,
+        merge=merge,
     )
 
 
@@ -265,6 +285,7 @@ def convert_to_obograph_remote(
     json_path: None | str | Path = None,
     check: bool = True,
     reason: bool = True,
+    merge: bool = True,
 ) -> ParseResults:
     """Convert a remote OWL/OBO file to an OBO Graph JSON object.
 
@@ -290,6 +311,7 @@ def convert_to_obograph_remote(
         input_is_iri=True,
         check=check,
         reason=reason,
+        merge=merge,
     )
 
 
@@ -301,9 +323,9 @@ def convert_to_obograph(
     input_is_iri: bool = False,
     extra_args: list[str] | None = None,
     from_iri: str | None = None,
-    merge: bool = True,
+    merge: bool = False,
     check: bool = True,
-    reason: bool = True,
+    reason: bool = False,
     debug: bool = False,
 ) -> ParseResults:
     """Convert a local OWL file to a JSON file.
@@ -402,7 +424,7 @@ def correct_raw_json(graph_document_raw) -> None:
     return graph_document_raw
 
 
-def _clean_raw_meta(element):
+def _clean_raw_meta(element: dict[str, Any]) -> None:
     meta = element.get("meta")
     if not meta:
         return
@@ -494,7 +516,7 @@ def convert(
     output_path: str | Path,
     input_flag: Literal["-i", "-I"] | None = None,
     *,
-    merge: bool = True,
+    merge: bool = False,
     fmt: str | None = None,
     check: bool = True,
     reason: bool = False,