JSONDecodeError / RefResolutionError validating the issued field of a CSL item

[dhimmel]

Greetings, I'm new to using this library and would like to validate objects based on the Citation Styles Language schema as part of manubot/manubot#47.

In the code snippet below with Python v3.6.6 and jsonschema v2.6.0, I'm getting a JSONDecodeError / RefResolutionError. If I remove the issued object of my CSL data, there are no errors. issued is defined in the schema as:

            "issued": {
                "$ref": "date-variable" 
            },

I saw in #343 and #371 that there may be some complexities with internal reference resolution. Not sure if that is the issue here.

Code snippet

import json
import jsonschema
import requests

# Load instance
csl = r'''\
[
  {
    "issued": {
      "date-parts": [
        [
          "2014",
          "07",
          "14"
        ]
      ]
    },
    "type": "report",
    "id": "nkzHjOdS"
  }
]
'''
csl = json.loads(csl)

# Load schema
url = 'https://github.com/citation-style-language/schema/raw/4846e02f0a775a8272819204379a4f8d7f45c16c/csl-data.json'
schema = requests.get(url).json()
jsonschema.Draft3Validator.check_schema(schema)
validator = jsonschema.Draft3Validator(schema)

# Validate
errors = list(validator.iter_errors(csl))

Stacktrace / error

---------------------------------------------------------------------------
JSONDecodeError                           Traceback (most recent call last)
~/anaconda3/lib/python3.6/site-packages/jsonschema/validators.py in resolve_from_url(self, url)
    382             try:
--> 383                 document = self.resolve_remote(url)
    384             except Exception as exc:

~/anaconda3/lib/python3.6/site-packages/jsonschema/validators.py in resolve_remote(self, uri)
    468             if callable(requests.Response.json):
--> 469                 result = requests.get(uri).json()
    470             else:

~/anaconda3/lib/python3.6/site-packages/requests/models.py in json(self, **kwargs)
    895                     pass
--> 896         return complexjson.loads(self.text, **kwargs)
    897 

~/anaconda3/lib/python3.6/json/__init__.py in loads(s, encoding, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)
    353             parse_constant is None and object_pairs_hook is None and not kw):
--> 354         return _default_decoder.decode(s)
    355     if cls is None:

~/anaconda3/lib/python3.6/json/decoder.py in decode(self, s, _w)
    338         """
--> 339         obj, end = self.raw_decode(s, idx=_w(s, 0).end())
    340         end = _w(s, end).end()

~/anaconda3/lib/python3.6/json/decoder.py in raw_decode(self, s, idx)
    356         except StopIteration as err:
--> 357             raise JSONDecodeError("Expecting value", s, err.value) from None
    358         return obj, end

JSONDecodeError: Expecting value: line 1 column 1 (char 0)

During handling of the above exception, another exception occurred:

RefResolutionError                        Traceback (most recent call last)
<ipython-input-4-45bebd6dd750> in <module>()
     29 
     30 # Validate
---> 31 errors = list(validator.iter_errors(csl))

~/anaconda3/lib/python3.6/site-packages/jsonschema/validators.py in iter_errors(self, instance, _schema)
    103 
    104                     errors = validator(self, v, instance, _schema) or ()
--> 105                     for error in errors:
    106                         # set details if not already set by the called fn
    107                         error._set(

~/anaconda3/lib/python3.6/site-packages/jsonschema/_validators.py in items(validator, items, instance, schema)
     53     if validator.is_type(items, "object"):
     54         for index, item in enumerate(instance):
---> 55             for error in validator.descend(item, items, path=index):
     56                 yield error
     57     else:

~/anaconda3/lib/python3.6/site-packages/jsonschema/validators.py in descend(self, instance, schema, path, schema_path)
    119 
    120         def descend(self, instance, schema, path=None, schema_path=None):
--> 121             for error in self.iter_errors(instance, schema):
    122                 if path is not None:
    123                     error.path.appendleft(path)

~/anaconda3/lib/python3.6/site-packages/jsonschema/validators.py in iter_errors(self, instance, _schema)
    103 
    104                     errors = validator(self, v, instance, _schema) or ()
--> 105                     for error in errors:
    106                         # set details if not already set by the called fn
    107                         error._set(

~/anaconda3/lib/python3.6/site-packages/jsonschema/_validators.py in properties_draft3(validator, properties, instance, schema)
    251                 subschema,
    252                 path=property,
--> 253                 schema_path=property,
    254             ):
    255                 yield error

~/anaconda3/lib/python3.6/site-packages/jsonschema/validators.py in descend(self, instance, schema, path, schema_path)
    119 
    120         def descend(self, instance, schema, path=None, schema_path=None):
--> 121             for error in self.iter_errors(instance, schema):
    122                 if path is not None:
    123                     error.path.appendleft(path)

~/anaconda3/lib/python3.6/site-packages/jsonschema/validators.py in iter_errors(self, instance, _schema)
    103 
    104                     errors = validator(self, v, instance, _schema) or ()
--> 105                     for error in errors:
    106                         # set details if not already set by the called fn
    107                         error._set(

~/anaconda3/lib/python3.6/site-packages/jsonschema/_validators.py in ref(validator, ref, instance, schema)
    210                 yield error
    211     else:
--> 212         scope, resolved = validator.resolver.resolve(ref)
    213         validator.resolver.push_scope(scope)
    214 

~/anaconda3/lib/python3.6/site-packages/jsonschema/validators.py in resolve(self, ref)
    373     def resolve(self, ref):
    374         url = self._urljoin_cache(self.resolution_scope, ref)
--> 375         return url, self._remote_cache(url)
    376 
    377     def resolve_from_url(self, url):

~/anaconda3/lib/python3.6/site-packages/jsonschema/validators.py in resolve_from_url(self, url)
    383                 document = self.resolve_remote(url)
    384             except Exception as exc:
--> 385                 raise RefResolutionError(exc)
    386 
    387         return self.resolve_fragment(document, fragment)

RefResolutionError: Expecting value: line 1 column 1 (char 0)

[dhimmel]

One workaround is dereference the schema before feeding it to jsonschema. I was able to do this with the jsonref package

import jsonref
schema = jsonref.load_uri(url, jsonschema=True)

[Julian]

This is almost certainly one of the other two issues there.

Closing this one, since it's tied up in all the other unrelated stuff, but feel free to follow those.