fix(shaclgen): emit sh:pattern for pattern constraints inside any_of

docs/maintainers/contributing.md

@@ -142,6 +142,11 @@ New tests in any directory should be written using pytest.
   If you make a change that intentionally causes some output to not match the saved snapshot file(s), you should update the snapshots by running `pytest` with the `--generate-snapshots` flag. You should try to run only a single or small group of tests with this flag (as opposed to the entire test suite). An exception to this rule is when preparing a new minor version of linkml after the metamodel changes, changes to the metamodel can have many (inconsequential) changes to multiple snapshots.
   The updated snapshot files should be checked in to Git alongside your other code changes.
 
+  Examples:
+
+  `uv run pytest tests/linkml/test_scripts/test_gen_owl.py --with-slow --generate-snapshots`
+  `uv run pytest tests/linkml/test_scripts/test_gen_shex.py --generate-snapshots --with-network`
+
   Debugging tip: sometimes a snapshot-based test may fail on GitHub actions, but may appear to pass locally. This can happen if the test is marked as a slow test,
   in which case you may need to use `--generate-snapshots` in combination with `--with-slow` (see below).
 

examples/tutorial/tutorial01/personinfo.json

@@ -42,7 +42,7 @@
     "$id": "https://w3id.org/linkml/examples/personinfo",
     "$schema": "https://json-schema.org/draft/2019-09/schema",
     "additionalProperties": true,
-    "metamodel_version": "1.7.0",
+    "metamodel_version": "1.11.0",
     "title": "personinfo",
     "type": "object",
     "version": null

examples/tutorial/tutorial04/personinfo-semantic.shex

@@ -1,4 +1,4 @@
-# metamodel_version: 1.7.0
+# metamodel_version: 1.11.0
 BASE <https://w3id.org/linkml/examples/personinfo/>
 PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
 PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>

examples/tutorial/tutorial05/personinfo.py

@@ -24,7 +24,7 @@
 from linkml_runtime.utils.curienamespace import CurieNamespace
 from linkml_runtime.linkml_model.types import Integer, String
 
-metamodel_version = "1.7.0"
+metamodel_version = "1.11.0"
 
 # Namespaces
 ORCID = CurieNamespace('ORCID', 'https://orcid.org/')

packages/linkml/src/linkml/converter/cli.py

@@ -2,6 +2,7 @@
 import os
 import pathlib
 import sys
+from typing import TYPE_CHECKING
 
 import click
 import yaml
@@ -27,6 +28,9 @@
 from linkml_runtime.utils.inference_utils import infer_all_slot_values
 from linkml_runtime.utils.schemaview import SchemaView
 
+if TYPE_CHECKING:
+    from linkml_runtime.utils.yamlutils import YAMLRoot
+
 logger = logging.getLogger(__name__)
 
 
@@ -197,7 +201,7 @@ def cli(
         target_class = infer_root_class(sv)
     if target_class is None:
         raise Exception("target class not specified and could not be inferred")
-    py_target_class = python_module.__dict__[target_class]
+    py_target_class: YAMLRoot = python_module.__dict__[target_class]
     input_format = _get_format(input, input_format)
     loader = get_loader(input_format)
 
@@ -237,9 +241,7 @@ def cli(
             raise Exception("--schema must be passed in order to validate. Suppress with --no-validate")
         obj_dict = json_dumper.to_dict(obj)
         report = run_validation(obj_dict, schema, target_class)
-        if report.results:
-            errors = "\n".join(r.message for r in report.results)
-            raise Exception(f"Validation failed:\n{errors}")
+        report.raise_for_results()
 
     output_format = _get_format(output, output_format, default="json")
     if output_format == "json-ld":

packages/linkml/src/linkml/generators/common/subproperty.py

@@ -15,6 +15,10 @@
 CURIE_TYPES: frozenset[str] = frozenset({"uriorcurie", "curie"})
 URI_TYPES: frozenset[str] = frozenset({"uri"})
 
+# Types whose XSD mapping is xsd:anyURI (not xsd:string).
+# ``curie`` maps to xsd:string and is deliberately excluded.
+_ANYURI_TYPES: frozenset[str] = frozenset({"uri", "uriorcurie"})
+
 
 def is_uri_range(sv: SchemaView, range_type: str | None) -> bool:
     """
@@ -63,6 +67,35 @@ def is_curie_range(sv: SchemaView, range_type: str | None) -> bool:
     return False
 
 
+def is_xsd_anyuri_range(sv: SchemaView, range_type: str | None) -> bool:
+    """Check if range type resolves to ``xsd:anyURI``.
+
+    Returns True for ``uri``, ``uriorcurie``, and types that inherit from them.
+    Returns False for ``curie`` (which maps to ``xsd:string``).
+
+    This is the correct predicate for the ``--xsd-anyuri-as-iri`` flag: only
+    types whose XSD representation is ``xsd:anyURI`` should be promoted from
+    literal to IRI semantics.  ``curie`` is a compact string representation
+    that resolves to ``xsd:string`` and must not be affected.
+
+    :param sv: SchemaView for type ancestry lookup
+    :param range_type: The range type to check
+    :return: True if range type maps to xsd:anyURI
+    """
+    if range_type is None:
+        return False
+
+    if range_type in _ANYURI_TYPES:
+        return True
+
+    if range_type in sv.all_types():
+        type_ancestors = set(sv.type_ancestors(range_type))
+        if type_ancestors & _ANYURI_TYPES:
+            return True
+
+    return False
+
+
 def format_slot_value_for_range(sv: SchemaView, slot_name: str, range_type: str | None) -> str:
     """
     Format slot value according to the declared range type.

packages/linkml/src/linkml/generators/excelgen.py

@@ -52,18 +52,21 @@ def _create_workbook_and_worksheets(self, output_path: Path, classes: list[str])
         workbook.remove(workbook.active)
         sv = self.schemaview
 
+        # Compute enum lookup before next inner loop
+        enum_set = set(sv.all_enums(imports=self.mergeimports).keys())
+
         for cls_name in classes:
             workbook.create_sheet(cls_name)
 
             # Add columns to the worksheet for the current class
-            slots = [s.name for s in sv.class_induced_slots(cls_name, self.mergeimports)]
-            self.add_columns_to_worksheet(workbook, cls_name, slots)
-            workbook.save(output_path)
+            # (call class_induced_slots, reuse for heading/enum validation)
+            induced_slots = list(sv.class_induced_slots(cls_name, self.mergeimports))
+            slot_names = [s.name for s in induced_slots]
+            self.add_columns_to_worksheet(workbook, cls_name, slot_names)
 
             # Add enum validation for columns with enum types
-            enum_list = list(sv.all_enums(imports=self.mergeimports).keys())
-            for s in sv.class_induced_slots(cls_name, self.mergeimports):
-                if s.range in enum_list:
+            for s in induced_slots:
+                if s.range in enum_set:
                     pv_list = list(sv.get_enum(s.range).permissible_values.keys())
 
                     # Data Validation formula to be applied to the column and
@@ -81,7 +84,6 @@ def _create_workbook_and_worksheets(self, output_path: Path, classes: list[str])
                             "length > 255 characters. Dropdowns may not work properly "
                             f"in {output_path}"
                         )
-                workbook.save(output_path)
 
         workbook.save(output_path)
         if self.split_workbook_by_class:

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

@@ -23,6 +23,10 @@
 
 URI_RANGES = (SHEX.nonliteral, SHEX.bnode, SHEX.iri)
 
+# Extended URI_RANGES that also treats xsd:anyURI as an IRI reference (@id)
+# rather than a typed literal. Opt-in via --xsd-anyuri-as-iri flag.
+URI_RANGES_WITH_XSD = (*URI_RANGES, XSD.anyURI)
+
 ENUM_CONTEXT = {
     "text": "skos:notation",
     "description": "skos:prefLabel",
@@ -72,6 +76,12 @@ class ContextGenerator(Generator):
     _local_slots: set | None = field(default=None, repr=False)
     _external_classes: set | None = field(default=None, repr=False)
     _external_slots: set | None = field(default=None, repr=False)
+    xsd_anyuri_as_iri: bool = False
+    """Map xsd:anyURI-typed ranges (uri, uriorcurie) to ``@type: @id`` instead of ``@type: xsd:anyURI``.
+
+    This aligns the JSON-LD context with the SHACL generator, which emits
+    ``sh:nodeKind sh:IRI`` for the same types.
+    """
 
     # Framing (opt-in via CLI flag)
     emit_frame: bool = False
@@ -239,14 +249,21 @@ def visit_class(self, cls: ClassDefinition) -> bool:
         self.add_mappings(cls)
 
         self._build_element_id(class_def, cls.class_uri)
+
+        # Build scoped context for slots whose range differs from the global definition.
+        # This handles attributes and slot_usage overrides that change a slot's range
+        # within a specific class (see: JSON-LD Scoped Contexts).
+        scoped_context = self._build_scoped_context(cls)
+        if scoped_context:
+            class_def["@context"] = scoped_context
+
         if class_def:
             self.slot_class_maps[cn] = class_def
 
         # prefer explicit tree_root for frame @type
         if getattr(cls, "tree_root", False):
             self.frame_root = cls.name
 
-        # We don't bother to visit class slots - just all slots
         return True
 
     def _literal_coercion_for_ranges(self, ranges: list[str]) -> tuple[bool, str | None]:
@@ -263,6 +280,7 @@ def _literal_coercion_for_ranges(self, ranges: list[str]) -> tuple[bool, str | N
         and "could not resolve safely because the branches disagree".
         """
         coercions: set[str | None] = set()
+        uri_ranges = URI_RANGES_WITH_XSD if self.xsd_anyuri_as_iri else URI_RANGES
         for range_name in ranges:
             if range_name not in self.schema.types:
                 continue
@@ -271,7 +289,7 @@ def _literal_coercion_for_ranges(self, ranges: list[str]) -> tuple[bool, str | N
             range_uri = self.namespaces.uri_for(range_type.uri)
             if range_uri == XSD.string:
                 coercions.add(None)
-            elif range_uri in URI_RANGES:
+            elif range_uri in uri_ranges:
                 coercions.add("@id")
             else:
                 coercions.add(range_type.uri)
@@ -316,9 +334,10 @@ def visit_slot(self, aliased_slot_name: str, slot: SlotDefinition) -> None:
                     self.emit_prefixes.add(skos)
                 else:
                     range_type = self.schema.types[slot.range]
+                    uri_ranges = URI_RANGES_WITH_XSD if self.xsd_anyuri_as_iri else URI_RANGES
                     if self.namespaces.uri_for(range_type.uri) == XSD.string:
                         pass
-                    elif self.namespaces.uri_for(range_type.uri) in URI_RANGES:
+                    elif self.namespaces.uri_for(range_type.uri) in uri_ranges:
                         slot_def["@type"] = "@id"
                     else:
                         slot_def["@type"] = range_type.uri
@@ -339,6 +358,61 @@ def visit_slot(self, aliased_slot_name: str, slot: SlotDefinition) -> None:
             if slot.range in self.schema.classes and slot.inlined is not None:
                 self.frame_body[key] = {"@embed": "@always" if bool(slot.inlined) else "@never"}
 
+    def _resolve_slot_type(self, range_name: str) -> str | None:
+        """Resolve a slot range to its JSON-LD @type value.
+
+        Returns the appropriate @type string for a given range name,
+        or None if the range maps to xsd:string (no @type needed).
+        """
+        if range_name in self.schema.classes:
+            return "@id"
+        if range_name in self.schema.enums:
+            return None
+        if range_name in self.schema.types:
+            range_type = self.schema.types[range_name]
+            uri = self.namespaces.uri_for(range_type.uri)
+            if uri == XSD.string:
+                return None
+            if uri in URI_RANGES:
+                return "@id"
+            return range_type.uri
+        return None
+
+    def _build_scoped_context(self, cls: ClassDefinition) -> dict:
+        """Build a scoped JSON-LD context for class-level slot range overrides.
+
+        When a class overrides a slot's range (via attributes or slot_usage),
+        the global context entry won't have the right @type. This method
+        detects those overrides and returns context entries only when the
+        resolved @type actually differs from the global definition.
+        """
+        scoped: dict = {}
+
+        def _add_if_type_differs(slot_name: str, override_range: str) -> None:
+            """Add a scoped entry if the override's @type differs from the global slot's @type."""
+            global_slot = self.schema.slots[slot_name]
+            global_type = self._resolve_slot_type(global_slot.range) if global_slot.range else None
+            override_type = self._resolve_slot_type(override_range)
+            if override_type == global_type:
+                return
+            entry: dict = {}
+            self._build_element_id(entry, global_slot.slot_uri)
+            if override_type is not None:
+                entry["@type"] = override_type
+            scoped[underscore(slot_name)] = entry
+
+        # Check attributes that shadow global slots
+        for attr_name, attr in cls.attributes.items():
+            if attr.range and attr_name in self.schema.slots:
+                _add_if_type_differs(attr_name, attr.range)
+
+        # Check slot_usage overrides
+        for usage_name, usage in cls.slot_usage.items():
+            if usage.range and usage_name in self.schema.slots:
+                _add_if_type_differs(usage_name, usage.range)
+
+        return scoped
+
     def _build_element_id(self, definition: Any, uri: str) -> None:
         """
         Defines the elements @id attribute according to the default namespace prefix of the schema.
@@ -438,6 +512,12 @@ def serialize(
     help="Exclude elements from URL-based external vocabulary imports while keeping local file imports. "
     "Useful when extending ontologies (e.g. W3C VC v2) whose terms are @protected in their own JSON-LD context.",
 )
+@click.option(
+    "--xsd-anyuri-as-iri/--no-xsd-anyuri-as-iri",
+    default=False,
+    show_default=True,
+    help="Map xsd:anyURI-typed ranges (uri, uriorcurie) to @type: @id instead of @type: xsd:anyURI.",
+)
 @click.version_option(__version__, "-V", "--version")
 def cli(yamlfile, emit_frame, embed_context_in_frame, output, **args):
     """Generate jsonld @context definition from LinkML model"""

packages/linkml/src/linkml/generators/jsonschemagen.py

@@ -386,6 +386,30 @@ def handle_class(self, cls: ClassDefinition) -> None:
                 class_subschema["allOf"] = []
             class_subschema["allOf"].extend(rule_subschemas)
 
+        if cls.any_of is not None and len(cls.any_of) > 0:
+            class_subschema["anyOf"] = [self.get_subschema_for_anonymous_class(c, False) for c in cls.any_of]
+
+        if cls.all_of is not None and len(cls.all_of) > 0:
+            if "allOf" not in class_subschema:
+                class_subschema["allOf"] = []
+            class_subschema["allOf"].extend([self.get_subschema_for_anonymous_class(c, False) for c in cls.all_of])
+
+        if cls.exactly_one_of is not None and len(cls.exactly_one_of) > 0:
+            class_subschema["oneOf"] = [self.get_subschema_for_anonymous_class(c, False) for c in cls.exactly_one_of]
+
+        if cls.none_of is not None and len(cls.none_of) > 0:
+            # properties_required=True so absent slots make their branch fail; otherwise
+            # properties is vacuously true and `not(anyOf)` rejects instances missing the slot.
+            new_not = {"anyOf": [self.get_subschema_for_anonymous_class(c, True) for c in cls.none_of]}
+            if "not" in class_subschema:
+                existing_not = class_subschema.pop("not")
+                if "allOf" not in class_subschema:
+                    class_subschema["allOf"] = []
+                class_subschema["allOf"].append({"not": existing_not})
+                class_subschema["allOf"].append({"not": new_not})
+            else:
+                class_subschema["not"] = new_not
+
         class_subschema = self.after_generate_class(
             ClassResult.model_construct(schema_=class_subschema, source=cls), self.schemaview
         ).schema_
@@ -415,6 +439,11 @@ def get_subschema_for_anonymous_class(
         subschema = JsonSchema()
         for slot in cls.slot_conditions.values():
             prop = self.get_subschema_for_slot(slot, omit_type=True, include_null=False)
+            # Anonymous slot expressions don't carry the underlying slot's `multivalued` flag,
+            # so look it up on the schema's slot definition and wrap so item-level constraints apply.
+            base_slot = self.schemaview.get_slot(slot.name) if slot.name else None
+            if base_slot is not None and base_slot.multivalued and not prop.is_array:
+                prop = JsonSchema.array_of(prop, include_null=False, required=False)
             value_required = False
             value_disallowed = False
             if slot.value_presence: