Merge tests and fixes from stale PRs

CHANGELOG.md

@@ -26,6 +26,13 @@
     (including `None`) are no longer allowed, hence missing base IRIs in the 
     JSON-LD context are now handled outside the function call.
   - Add unittests
+ - **BREAKING**: The `IdentifierIssuer` class was moved to `identifier_issuer.py`. It's now available 
+   at `pyld.identifier_issuer`.
+ - **BREAKING**: The classes `URDNA2015` and `URGNA2012` were moved to `canon.py`. They are now available 
+   at `pyld.canon`. 
+ - `jsonld.expand()` now accepts a `on_key_dropped` parameter which is a handler called on every ignored key.
+ - **BREAKING**: In cases where there is no document base (for instance, when using a string as input), 
+   'http://example.org/base/' is used as the base IRI when `@base` is absent or explicitely set to `null`.
 
 ## 2.0.4 - 2024-02-16
 

README.rst

@@ -170,6 +170,21 @@ If Requests_ is not available, the loader is set to aiohttp_. The fallback
 document loader is a dummy document loader that raises an exception on every
 invocation.
 
+Handling ignored keys during JSON-LD expansion
+----------------------------------------------
+
+If a key in a JSON-LD document does not map to an absolute IRI then it is ignored and logged by default. 
+You can customize this behaviour by passing a customizable handler to `on_key_dropped` parameter of `jsonld.expand()`.
+
+For example, you can introduce a strict mode by raising a ValueError on every dropped key:
+
+```python
+def raise_this(value):
+    raise ValueError(value)
+
+jsonld.expand(doc, None, on_key_dropped=raise_this)
+```
+
 Commercial Support
 ------------------
 

lib/pyld/context_resolver.py

@@ -153,8 +153,8 @@ def _fetch_context(self, active_ctx, url, cycles):
                 'non-JSON response, or more than one HTTP Link Header was ' +
                 'provided for a remote context.',
                 'jsonld.InvalidUrl',
-                {'url': url, 'cause': cause},
-                code='loading remote context failed')
+                {'url': url},
+                code='loading remote context failed') from cause
 
         # ensure ctx is an object
         if not isinstance(context, dict) and not isinstance(context, frozendict):

lib/pyld/documentloader/aiohttp.py

@@ -123,8 +123,8 @@ async def async_loader(url, headers):
         except Exception as cause:
             raise JsonLdError(
                 'Could not retrieve a JSON-LD document from the URL.',
-                'jsonld.LoadDocumentError', code='loading document failed',
-                cause=cause)
+                'jsonld.LoadDocumentError', 
+                code='loading document failed') from cause
 
     def loader(url, options=None):
         """

lib/pyld/documentloader/requests.py

@@ -101,7 +101,7 @@ def loader(url, options={}):
         except Exception as cause:
             raise JsonLdError(
                 'Could not retrieve a JSON-LD document from the URL.',
-                'jsonld.LoadDocumentError', code='loading document failed',
-                cause=cause)
+                'jsonld.LoadDocumentError', 
+                code='loading document failed') from cause
 
     return loader

lib/pyld/identifier_issuer.py

@@ -0,0 +1,52 @@
+class IdentifierIssuer(object):
+    """
+    An IdentifierIssuer issues unique identifiers, keeping track of any
+    previously issued identifiers.
+    """
+
+    def __init__(self, prefix):
+        """
+        Initializes a new IdentifierIssuer.
+
+        :param prefix: the prefix to use ('<prefix><counter>').
+        """
+        self.prefix = prefix
+        self.counter = 0
+        self.existing = {}
+        self.order = []
+
+        """
+        Gets the new identifier for the given old identifier, where if no old
+        identifier is given a new identifier will be generated.
+
+        :param [old]: the old identifier to get the new identifier for.
+
+        :return: the new identifier.
+        """
+    def get_id(self, old=None):
+        # return existing old identifier
+        if old and old in self.existing:
+            return self.existing[old]
+
+        # get next identifier
+        id_ = self.prefix + str(self.counter)
+        self.counter += 1
+
+        # save mapping
+        if old is not None:
+            self.existing[old] = id_
+            self.order.append(old)
+
+        return id_
+
+    def has_id(self, old):
+        """
+        Returns True if the given old identifier has already been assigned a
+        new identifier.
+
+        :param old: the old identifier to check.
+
+        :return: True if the old identifier has been assigned a new identifier,
+          False if not.
+        """
+        return old in self.existing