fix(generators): add --normalize-prefixes flag for well-known prefix names

packages/linkml/pyproject.toml

@@ -49,7 +49,10 @@ dependencies = [ # Specifier syntax: https://peps.python.org/pep-0631/
     "openpyxl",
     "parse",
     "prefixcommons >= 0.1.7",
-    "prefixmaps >= 0.2.2",
+    # TODO(prefixmaps-0.2.8): Replace git pin with "prefixmaps >= 0.2.8" once released,
+    #   then remove [tool.hatch.metadata] allow-direct-references and regenerate uv.lock.
+    #   Tracked in: https://github.com/linkml/prefixmaps/issues/82
+    "prefixmaps @ git+https://github.com/linkml/prefixmaps@75435150a1b31760b9780af2b64a265943a9b263",
     "pydantic >= 2.0.0, < 3.0.0",
     "pyjsg >= 0.11.6",
     "pyshex >= 0.7.20",
@@ -196,6 +199,10 @@ vcs = "git"
 style = "pep440"
 fallback-version = "0.0.0"
 
+[tool.hatch.metadata]
+# TODO(prefixmaps-0.2.8): Remove this section once the git pin is replaced with >= 0.2.8
+allow-direct-references = true
+
 [tool.hatch.version]
 source = "uv-dynamic-versioning"
 

packages/linkml/src/linkml/generators/jsonldcontextgen.py

@@ -15,7 +15,7 @@
 
 from linkml._version import __version__
 from linkml.utils.deprecation import deprecated_fields
-from linkml.utils.generator import Generator, shared_arguments
+from linkml.utils.generator import Generator, shared_arguments, well_known_prefix_map
 from linkml_runtime.linkml_model.meta import ClassDefinition, EnumDefinition, SlotDefinition
 from linkml_runtime.linkml_model.types import SHEX
 from linkml_runtime.utils.formatutils import camelcase, underscore
@@ -90,6 +90,9 @@ class ContextGenerator(Generator):
     frame_root: str | None = None
 
     def __post_init__(self) -> None:
+        # Must be set before super().__post_init__() because the parent triggers
+        # the visitor pattern (visit_schema), which accesses _prefix_remap.
+        self._prefix_remap: dict[str, str] = {}
         super().__post_init__()
         if self.namespaces is None:
             raise TypeError("Schema text must be supplied to context generator.  Preparsed schema will not work")
@@ -127,22 +130,92 @@ def _collect_external_elements(sv: SchemaView) -> tuple[set[str], set[str]]:
                 external_slots.update(schema_def.slots.keys())
         return external_classes, external_slots
 
+    def add_prefix(self, ncname: str) -> None:
+        """Add a prefix, applying well-known prefix normalisation when enabled."""
+        super().add_prefix(self._prefix_remap.get(ncname, ncname))
+
     def visit_schema(self, base: str | Namespace | None = None, output: str | None = None, **_):
-        # Add any explicitly declared prefixes
+        # Add any explicitly declared prefixes.
+        # Direct .add() is safe here: the normalisation block below explicitly
+        # rewrites emit_prefixes entries for any renamed prefixes (Cases 1-3).
         for prefix in self.schema.prefixes.values():
             self.emit_prefixes.add(prefix.prefix_prefix)
 
         # Add any prefixes explicitly declared
         for pfx in self.schema.emit_prefixes:
             self.add_prefix(pfx)
 
+        # Normalise well-known prefix names when --normalize-prefixes is set.
+        # If the schema declares a non-standard alias for a namespace that has
+        # a well-known standard name (e.g. ``sdo`` for
+        # ``https://schema.org/``), replace the alias with the standard name
+        # so that generated JSON-LD contexts use the conventional prefix.
+        #
+        # Three cases are handled:
+        # 1. Standard prefix is not yet bound → just rebind from old to new.
+        # 2. Standard prefix is bound to a *different* URI:
+        #    a. User-declared (in schema.prefixes) → collision, skip with warning.
+        #    b. Runtime default (e.g. linkml-runtime's ``schema: http://…``)
+        #       → remove stale binding, then rebind.
+        # 3. Standard prefix is already bound to the *same* URI (duplicate)
+        #    → just drop the non-standard alias.
+        #
+        # A remap dict is stored for ``_build_element_id`` because
+        # ``prefix_suffix()`` splits CURIEs on ``:`` without looking up the
+        # namespace dict.
+        self._prefix_remap.clear()
+        if self.normalize_prefixes:
+            wk = well_known_prefix_map()
+            for old_pfx in list(self.namespaces):
+                url = str(self.namespaces[old_pfx])
+                std_pfx = wk.get(url)
+                if not std_pfx or std_pfx == old_pfx:
+                    continue
+                if std_pfx in self.namespaces:
+                    if str(self.namespaces[std_pfx]) != url:
+                        # Case 2: std_pfx is bound to a different URI.
+                        # If the user explicitly declared std_pfx in the schema,
+                        # it is intentional — skip to avoid data loss.
+                        if std_pfx in self.schema.prefixes:
+                            self.logger.warning(
+                                "Prefix collision: cannot rename '%s' to '%s' because '%s' is "
+                                "already declared for <%s>; skipping normalisation for <%s>",
+                                old_pfx,
+                                std_pfx,
+                                std_pfx,
+                                str(self.namespaces[std_pfx]),
+                                url,
+                            )
+                            continue
+                        # Not user-declared (e.g. linkml-runtime default) — safe to remove
+                        self.emit_prefixes.discard(std_pfx)
+                        del self.namespaces[std_pfx]
+                    else:
+                        # Case 3: standard prefix already bound to same URI
+                        # — just drop the non-standard alias
+                        del self.namespaces[old_pfx]
+                        if old_pfx in self.emit_prefixes:
+                            self.emit_prefixes.discard(old_pfx)
+                            self.emit_prefixes.add(std_pfx)
+                        self._prefix_remap[old_pfx] = std_pfx
+                        continue
+                # Case 1 (or Case 2 after stale removal): bind standard name
+                self.namespaces[std_pfx] = self.namespaces[old_pfx]
+                del self.namespaces[old_pfx]
+                if old_pfx in self.emit_prefixes:
+                    self.emit_prefixes.discard(old_pfx)
+                    self.emit_prefixes.add(std_pfx)
+                self._prefix_remap[old_pfx] = std_pfx
+
         # Add the default prefix
         if self.schema.default_prefix:
             dflt = self.namespaces.prefix_for(self.schema.default_prefix)
             if dflt:
                 self.default_ns = dflt
             if self.default_ns:
                 default_uri = self.namespaces[self.default_ns]
+                # Direct .add() is safe: default_ns is already resolved from
+                # the (possibly normalised) namespace bindings above.
                 self.emit_prefixes.add(self.default_ns)
             else:
                 default_uri = self.schema.default_prefix
@@ -486,6 +559,11 @@ def _build_element_id(self, definition: Any, uri: str) -> None:
         @return: None
         """
         uri_prefix, uri_suffix = self.namespaces.prefix_suffix(uri)
+        # Apply well-known prefix normalisation (e.g. sdo → schema).
+        # prefix_suffix() splits CURIEs on ':' without checking the
+        # namespace dict, so it may return a stale alias.
+        if uri_prefix and uri_prefix in self._prefix_remap:
+            uri_prefix = self._prefix_remap[uri_prefix]
         is_default_namespace = uri_prefix == self.context_body["@vocab"] or uri_prefix == self.namespaces.prefix_for(
             self.context_body["@vocab"]
         )

packages/linkml/src/linkml/generators/jsonldgen.py

@@ -179,6 +179,8 @@ def end_schema(self, context: str | Sequence[str] | None = None, context_kwargs:
             # TODO: The _visit function above alters the schema in situ
             # force some context_kwargs
             context_kwargs["metadata"] = False
+            # Forward prefix normalisation into the inline @context.
+            context_kwargs.setdefault("normalize_prefixes", self.normalize_prefixes)
             add_prefixes = ContextGenerator(self.original_schema, **context_kwargs).serialize()
             add_prefixes_json = loads(add_prefixes)
             metamodel_ctx = self.metamodel_context or METAMODEL_CONTEXT_URI

packages/linkml/src/linkml/generators/owlgen.py

@@ -21,7 +21,7 @@
 from linkml._version import __version__
 from linkml.generators.common.subproperty import is_xsd_anyuri_range
 from linkml.utils.deprecation import deprecation_warning
-from linkml.utils.generator import Generator, shared_arguments
+from linkml.utils.generator import Generator, normalize_graph_prefixes, shared_arguments
 from linkml_runtime import SchemaView
 from linkml_runtime.linkml_model.meta import (
     AnonymousClassExpression,
@@ -264,6 +264,10 @@ def as_graph(self) -> Graph:
             self.graph.bind(prefix, self.metamodel.namespaces[prefix])
         for pfx in schema.prefixes.values():
             self.graph.namespace_manager.bind(pfx.prefix_prefix, URIRef(pfx.prefix_reference))
+        if self.normalize_prefixes:
+            normalize_graph_prefixes(
+                graph, {str(v.prefix_prefix): str(v.prefix_reference) for v in schema.prefixes.values()}
+            )
         graph.add((base, RDF.type, OWL.Ontology))
 
         # Add main schema elements

packages/linkml/src/linkml/generators/shaclgen.py

@@ -13,7 +13,7 @@
 from linkml.generators.common.subproperty import get_subproperty_values, is_uri_range
 from linkml.generators.shacl.shacl_data_type import ShaclDataType
 from linkml.generators.shacl.shacl_ifabsent_processor import ShaclIfAbsentProcessor
-from linkml.utils.generator import Generator, shared_arguments
+from linkml.utils.generator import Generator, normalize_graph_prefixes, shared_arguments
 from linkml_runtime.linkml_model.meta import ClassDefinition, ElementName
 from linkml_runtime.utils.formatutils import underscore
 from linkml_runtime.utils.yamlutils import TypedNode, extended_float, extended_int, extended_str
@@ -105,6 +105,10 @@ def as_graph(self) -> Graph:
 
         for pfx in self.schema.prefixes.values():
             g.bind(str(pfx.prefix_prefix), pfx.prefix_reference)
+        if self.normalize_prefixes:
+            normalize_graph_prefixes(
+                g, {str(v.prefix_prefix): str(v.prefix_reference) for v in self.schema.prefixes.values()}
+            )
 
         for c in sv.all_classes(imports=not self.exclude_imports).values():