Merge branch 'main' of https://github.com/ahoward-ch/py-xbrl

Author: ahoward-ch

requirements.txt

@@ -1,3 +1,3 @@
-setuptools==63.2.0
+setuptools==65.5.1
 requests~=2.28.1
 urllib3~=1.26.11

setup.py

@@ -15,7 +15,7 @@ def read(filename):
 
 setup(
     name="py-xbrl",
-    version="2.2.3",
+    version="2.2.6",
     url="https://github.com/manusimidt/xbrl_parser",
     license='GNU General Public License v3 (GPLv3)',
     author="Manuel Schmidt",

xbrl/__init__.py

@@ -76,7 +76,7 @@ class ContextParseException(InstanceParseException):
     pass
 
 
-__version__ = '2.2.3'
+__version__ = '2.2.6'
 __author__ = 'Manuel Schmidt <[email protected]>'
 __all__ = [
     XbrlParseException,

xbrl/instance.py

@@ -286,11 +286,12 @@ def __str__(self) -> str:
         file_name: str = self.instance_url.split('/')[-1]
         return "{} with {} facts".format(file_name, len(self.facts))
 
-    def json(self, file_path: str = None, override_fact_ids: bool = True) -> str or None:
+    def json(self, file_path: str = None, override_fact_ids: bool = True, **kwargs) -> str or None:
         """
         Converts the instance document into json format
         :param file_path: if a path is given the function will store the json there
         :param override_fact_ids:
+        :param kwargs: additional arguments for the json parser
         :return: string (serialized json) or None (if file_path was given)
 
         https://www.xbrl.org/Specification/xbrl-json/REC-2021-10-13/xbrl-json-REC-2021-10-13.html
@@ -308,9 +309,9 @@ def json(self, file_path: str = None, override_fact_ids: bool = True) -> str or
             json_dict['facts'][fact_id] = fact.json()
         if file_path:
             with open(file_path, 'w', encoding='utf8') as f:
-                return json.dump(json_dict, f)
+                return json.dump(json_dict, f, **kwargs)
         else:
-            return json.dumps(json_dict)
+            return json.dumps(json_dict, **kwargs)
 
 
 def parse_xbrl_url(instance_url: str, cache: HttpCache) -> XbrlInstance:
@@ -409,16 +410,17 @@ def parse_xbrl(instance_path: str, cache: HttpCache, instance_url: str or None =
     return XbrlInstance(instance_url if instance_url else instance_path, taxonomy, facts, context_dir, unit_dir)
 
 
-def parse_ixbrl_url(instance_url: str, cache: HttpCache) -> XbrlInstance:
+def parse_ixbrl_url(instance_url: str, cache: HttpCache, encoding: str or None = None) -> XbrlInstance:
     """
     Parses a inline XBRL (iXBRL) instance file.
 
     :param cache: HttpCache instance
     :param instance_url: url to the instance file(on the internet)
+    :param encoding: specifies the encoding of the file
     :return: parsed XbrlInstance object containing all facts with additional information
     """
     instance_path: str = cache.cache_file(instance_url)
-    return parse_ixbrl(instance_path, cache, instance_url)
+    return parse_ixbrl(instance_path, cache, instance_url, encoding)
 
 
 def parse_ixbrl(instance_path: str, cache: HttpCache, instance_url: str or None = None, encoding=None, schema_root=None) -> XbrlInstance:
@@ -708,7 +710,7 @@ class XbrlParser:
     def __init__(self, cache: HttpCache):
         self.cache = cache
 
-    def parse_instance(self, uri: str, instance_url: str or None = None) -> XbrlInstance:
+    def parse_instance(self, uri: str, instance_url: str or None = None, encoding: str or None = None) -> XbrlInstance:
         """
         Parses a xbrl instance (either xbrl or ixbrl)
 
@@ -721,11 +723,14 @@ def parse_instance(self, uri: str, instance_url: str or None = None) -> XbrlInst
             i.e: https://www.sec.gov/Archives/edgar/data/320193/000032019320000096/aapl-20200926.
         :param instance_url: this parameter overrides the above described behaviour. If you also provide the url where the
             instance document was downloaded, the parser can fetch relative imports using this base url
+        :param encoding: specifies the encoding of the file
         :return:
         """
         if uri.split('.')[-1] == 'xml' or uri.split('.')[-1] == 'xbrl':
-            return parse_xbrl_url(uri, self.cache) if uri.startswith('http') else parse_xbrl(uri, self.cache, instance_url)
-        return parse_ixbrl_url(uri, self.cache) if uri.startswith('http') else parse_ixbrl(uri, self.cache, instance_url)
+            return parse_xbrl_url(uri, self.cache) if uri.startswith('http') \
+                else parse_xbrl(uri, self.cache, instance_url)
+        return parse_ixbrl_url(uri, self.cache) if uri.startswith('http') \
+            else parse_ixbrl(uri, self.cache, instance_url, encoding)
 
     def __str__(self) -> str:
         return 'XbrlParser with cache dir at {}'.format(self.cache.cache_dir)

xbrl/linkbase.py

@@ -383,14 +383,16 @@ class Linkbase:
     Represents a complete Linkbase (non-generic).
     """
 
-    def __init__(self, extended_links: List[ExtendedLink], linkbase_type: LinkbaseType) -> None:
+    def __init__(self, extended_links: List[ExtendedLink], linkbase_type: LinkbaseType, linkbase_uri: None or str = None) -> None:
         """
         :param extended_links: All standard extended links that are defined in the linkbase
         :type extended_links: [ExtendedDefinitionLink] or [ExtendedCalculationLink] or [ExtendedPresentationLink] or [ExtendedLabelArc]
         :param linkbase_type: Type of the linkbase
+        :param linkbase_uri: Either the path or the url to the linkbase (depends from where the parser loaded it for parsing)
         """
         self.extended_links: List[ExtendedLink] = extended_links
         self.type = linkbase_type
+        self.linkbase_uri = linkbase_uri
 
     def to_dict(self) -> dict:
         """
@@ -564,4 +566,4 @@ def parse_linkbase(linkbase_path: str, linkbase_type: LinkbaseType, linkbase_url
                 ExtendedLink(extended_link_role, role_refs[extended_link_role], root_locators))
         elif linkbase_type == LinkbaseType.LABEL:
             extended_links.append(ExtendedLink(extended_link_role, None, root_locators))
-    return Linkbase(extended_links, linkbase_type)
+    return Linkbase(extended_links, linkbase_type, linkbase_url if linkbase_url else linkbase_path)

xbrl/transformations/__init__.py

@@ -577,7 +577,11 @@ def normalize(namespace: str, formatCode: str, value: str) -> str:
     value = value.strip().lower()
 
     try:
-        if namespace == 'http://www.xbrl.org/inlineXBRL/transformation/2010-04-20':
+        if namespace == 'http://www.xbrl.org/2008/inlineXBRL/transformation':
+            # WARNING: I could not find a specification for this ancient transformation registry..
+            # however the transformations will probably be the same as defined in the 2010 version
+            return ixt[formatCode](value)
+        elif namespace == 'http://www.xbrl.org/inlineXBRL/transformation/2010-04-20':
             return ixt[formatCode](value)
         elif namespace == 'http://www.xbrl.org/2008/inlineXBRL/transformation':
             return ixt[formatCode](value)