ogc-na 0.3.44__py3-none-any.whl → 0.3.46__py3-none-any.whl

ogc/na/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.3.44'
-__version_tuple__ = version_tuple = (0, 3, 44)
+__version__ = version = '0.3.46'
+__version_tuple__ = version_tuple = (0, 3, 46)

ogc/na/annotate_schema.py

@@ -122,12 +122,12 @@ import json
 import logging
 import re
 import sys
-from collections import deque
 from operator import attrgetter
 from pathlib import Path
 from typing import Any, AnyStr, Callable, Sequence, Iterable
 from urllib.parse import urlparse, urljoin
 
+import jsonpointer
 import jsonschema
 import requests_cache
 
@@ -147,6 +147,8 @@ ANNOTATION_IGNORE_EXPAND = [ANNOTATION_CONTEXT, ANNOTATION_EXTRA_TERMS, ANNOTATI
 
 CURIE_TERMS = '@id', '@type', '@index'
 
+UNDEFINED = object()
+
 context_term_cache = LRUCache(maxsize=20)
 requests_session = requests_cache.CachedSession('ogc.na.annotate_schema', backend='memory', expire_after=180)
 
@@ -179,26 +181,21 @@ class SchemaResolver:
 
     def __init__(self, working_directory=Path()):
         self.working_directory = working_directory.resolve()
-        self._schema_cache: dict[str | Path, tuple[Any, bool]] = {}
+        self._schema_cache: dict[str | Path, Any] = {}
 
     @staticmethod
     def _get_branch(schema: dict, ref: str):
-        path = re.sub(r'^#?/?', '', ref).split('/')
-        pointer = schema
-        for item in path:
-            if item:
-                pointer = pointer[item]
-        return pointer
+        return jsonpointer.resolve_pointer(schema, re.sub('^#', '', ref))
 
     def load_contents(self, s: str | Path) -> tuple[dict, bool]:
         """
         Load the contents of a schema. Can be overriden by subclasses to alter the loading process.
         """
-        contents, is_json = self._schema_cache.get(s, (None, False))
+        contents = self._schema_cache.get(s)
         if contents is None:
-            contents, is_json = load_json_yaml(read_contents(s)[0])
-            self._schema_cache[s] = contents, is_json
-        return contents, is_json
+            contents = read_contents(s)[0]
+            self._schema_cache[s] = contents
+        return load_json_yaml(contents)
 
     def resolve_ref(self, ref: str | Path, from_schema: ReferencedSchema | None = None) -> tuple[Path | str, str]:
         location = ref
@@ -229,7 +226,8 @@ class SchemaResolver:
 
         return location, fragment
 
-    def resolve_schema(self, ref: str | Path, from_schema: ReferencedSchema | None = None) -> ReferencedSchema | None:
+    def resolve_schema(self, ref: str | Path, from_schema: ReferencedSchema | None = None,
+                       force_contents: dict | None = None) -> ReferencedSchema | None:
         chain = from_schema.chain + [from_schema] if from_schema else []
         try:
             schema_source, fragment = self.resolve_ref(ref, from_schema)
@@ -250,6 +248,8 @@ class SchemaResolver:
                                         is_json=from_schema.is_json)
 
             contents, is_json = self.load_contents(schema_source)
+            if force_contents:
+                contents = force_contents
             if fragment:
                 return ReferencedSchema(location=schema_source, fragment=fragment,
                                         subschema=SchemaResolver._get_branch(contents, fragment),
@@ -347,6 +347,8 @@ def resolve_context(ctx: Path | str | dict | list, expand_uris=True) -> Resolved
             prefix, localpart = curie.split(':', 1)
         else:
             prefix, localpart = None, None
+
+        vocab = UNDEFINED
         for c in reversed(ctx_stack):
             if localpart:
                 # prefix:localpart format
@@ -355,9 +357,11 @@ def resolve_context(ctx: Path | str | dict | list, expand_uris=True) -> Resolved
                     prefix_uri = term_val if isinstance(term_val, str) else term_val.get('@id')
                     prefixes[prefix] = prefix_uri
                     return f"{prefix_uri}{localpart}"
-            elif '@vocab' in c:
-                # look for @vocab
-                return f"{c['@vocab']}{curie}"
+            elif '@vocab' in c and vocab is UNDEFINED:
+                # look for @vocab unless it has been overridden (e.g. set to null) somewhere down the chain
+                vocab = c['@vocab']
+                if isinstance(vocab, str):
+                    return f"{c['@vocab']}{curie}"
 
         return curie
 
@@ -389,7 +393,11 @@ def resolve_context(ctx: Path | str | dict | list, expand_uris=True) -> Resolved
             resolved_ctx = {}
             inner_prefixes = {}
             for ctx_entry in inner_ctx:
-                resolved_entry = resolve_context(ctx_entry)
+                if isinstance(ctx_entry, dict):
+                    # Array entries must be wrapped with @context
+                    resolved_entry = resolve_context({'@context': ctx_entry})
+                else:
+                    resolved_entry = resolve_context(ctx_entry)
                 inner_prefixes.update(resolved_entry.prefixes)
                 resolved = ResolvedContext(merge_dicts(resolved_entry.context, resolved_ctx), inner_prefixes)
         else:
@@ -448,12 +456,8 @@ class SchemaAnnotator:
     def process_schema(self, location: Path | str | None,
                        default_context: str | Path | dict | None = None,
                        contents: dict | None = None) -> AnnotatedSchema | None:
-        resolved_schema = self.schema_resolver.resolve_schema(location)
-        if contents:
-            # overriden
-            schema = contents
-        else:
-            schema = resolved_schema.subschema
+        resolved_schema = self.schema_resolver.resolve_schema(location, force_contents=contents)
+        schema = resolved_schema.subschema
 
         if all(x not in schema for x in ('schema', 'openapi')):
             validate_schema(schema)
@@ -482,8 +486,10 @@ class SchemaAnnotator:
         updated_refs: set[int] = set()
 
         def find_prop_context(prop, context_stack) -> dict | None:
+            vocab = UNDEFINED
             for ctx in reversed(context_stack):
-                vocab = ctx.get('@vocab')
+                if vocab is UNDEFINED and '@vocab' in ctx:
+                    vocab = ctx.get('@vocab')
                 if prop in ctx:
                     prop_ctx = ctx[prop]
                     if isinstance(prop_ctx, str):
@@ -501,7 +507,7 @@ class SchemaAnnotator:
                             elif ':' not in prop_id and prop_id not in JSON_LD_KEYWORDS:
                                 result['@id'] = f"{vocab}{prop_id}"
                         return result
-                elif '@vocab' in ctx:
+                elif isinstance(vocab, str):
                     return {'@id': f"{ctx['@vocab']}{prop}"}
 
         def process_properties(obj: dict, context_stack: list[dict[str, Any]],
@@ -557,6 +563,13 @@ class SchemaAnnotator:
 
             used_terms = set()
 
+            # Annotate definitions and $defs - can later be overridden if referenced from a different path
+            for p in ('definitions', '$defs'):
+                defs = subschema.get(p)
+                if defs and isinstance(defs, dict):
+                    for entry in defs.values():
+                        used_terms.update(process_subschema(entry, context_stack, from_schema, level + 1))
+
             if '$ref' in subschema and id(subschema) not in updated_refs:
                 if self._ref_mapper:
                     subschema['$ref'] = self._ref_mapper(subschema['$ref'], subschema)
@@ -574,13 +587,6 @@ class SchemaAnnotator:
                     for entry in collection:
                         used_terms.update(process_subschema(entry, context_stack, from_schema, level + 1))
 
-            # Annotate definitions and $defs
-            for p in ('definitions', '$defs'):
-                defs = subschema.get(p)
-                if defs and isinstance(defs, dict):
-                    for entry in defs.values():
-                        used_terms.update(process_subschema(entry, context_stack, from_schema, level + 1))
-
             for p in ('then', 'else', 'additionalProperties'):
                 branch = subschema.get(p)
                 if branch and isinstance(branch, dict):
@@ -862,8 +868,9 @@ class ContextBuilder:
                     if isinstance(term_value, str):
                         branch[term] = compact_uri(term_value)
                     elif isinstance(term_value, dict):
-                        if '@id' in term_value:
-                            term_value['@id'] = compact_uri(term_value['@id'])
+                        for k in CURIE_TERMS:
+                            if k in term_value:
+                                term_value[k] = compact_uri(term_value[k])
                         if len(term_value) == 1 and '@id' in term_value:
                             branch[term] = term_value['@id']
                         elif '@context' in term_value:

{ogc_na-0.3.44.dist-info → ogc_na-0.3.46.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ogc_na
-Version: 0.3.44
+Version: 0.3.46
 Summary: OGC Naming Authority tools
 Author-email: Rob Atkinson <ratkinson@ogc.org>, Piotr Zaborowski <pzaborowski@ogc.org>, Alejandro Villar <avillar@ogc.org>
 Project-URL: Homepage, https://github.com/opengeospatial/ogc-na-tools/
@@ -26,6 +26,7 @@ Requires-Dist: GitPython >=3.1.32
 Requires-Dist: rfc3987
 Requires-Dist: requests-cache
 Requires-Dist: xmltodict
+Requires-Dist: jsonpointer ~=2.4
 Requires-Dist: setuptools
 Provides-Extra: dev
 Requires-Dist: mkdocs >=1.4.2 ; extra == 'dev'

{ogc_na-0.3.44.dist-info → ogc_na-0.3.46.dist-info}/RECORD

@@ -1,6 +1,6 @@
 ogc/na/__init__.py,sha256=uzcNiJ3uKFNJ1HBfKxIwgAy2HMUFsLAe5RkrUg8ncac,464
-ogc/na/_version.py,sha256=X8gyyh7AkxhUcMUHqBeELBXHJ4sJvOKOOobJXSUQR78,413
-ogc/na/annotate_schema.py,sha256=lM_YZ5f9d55pskEKRQGSXSLWfhMTBIZIWl5fv2HgVxU,39808
+ogc/na/_version.py,sha256=nKT1cOpmRV-LeICJaPCDMdhIUkMGhRcN3p0Hyw8DrwA,413
+ogc/na/annotate_schema.py,sha256=bVzQ-YjQ0ULJxaLxWk5ZFaVTKky2TbEY91VlYMqxmSs,40335
 ogc/na/domain_config.py,sha256=C6ao37dbXEKv_K7WcfzQgI3H1Hr3c4-3p24hgl2oH54,13896
 ogc/na/download.py,sha256=2afrLyl4WsAlxkCgXsl47fs9mNKfDmhVpeT2iwNSoq0,3354
 ogc/na/gsp.py,sha256=KGa2G9i8kPefYTHNPUDoXnNyF7Tiwt8K__Ew_Qa7eeg,6048
@@ -14,7 +14,7 @@ ogc/na/validation.py,sha256=5xjHH55NZKM8HtUk8XgVzm8W5ZlZY00u_qsWfXK_8dM,3732
 ogc/na/input_filters/__init__.py,sha256=AhE7n_yECwxFKwOM3Jc0ft96TtF5i_Z-fHrS4HYOjaE,1179
 ogc/na/input_filters/csv.py,sha256=nFfB1XQF_QApcGGzMqEvzD_b3pBtCtsfUECsZ9UGE6s,2616
 ogc/na/input_filters/xml.py,sha256=9qYjp_w5JLInFM48zB15IYH9eTafjp1Aqd_8kfuW3aA,2074
-ogc_na-0.3.44.dist-info/METADATA,sha256=JcbuO0vtp33AwDss-kPzDdBxLyDm_IdVGkhMiHEkoc8,3796
-ogc_na-0.3.44.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-ogc_na-0.3.44.dist-info/top_level.txt,sha256=Kvy3KhzcIhNPT4_nZuJCmS946ptRr_MDyU4IIhZJhCY,4
-ogc_na-0.3.44.dist-info/RECORD,,
+ogc_na-0.3.46.dist-info/METADATA,sha256=gMk9QGd1n214nQuZUPe3vp7RdERy5yCus7q1lWTdJFk,3829
+ogc_na-0.3.46.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+ogc_na-0.3.46.dist-info/top_level.txt,sha256=Kvy3KhzcIhNPT4_nZuJCmS946ptRr_MDyU4IIhZJhCY,4
+ogc_na-0.3.46.dist-info/RECORD,,