Merge pull request #118 from ajmedeio/main

Explicitly match protocol

xbrl/helper/uri_helper.py

@@ -18,15 +18,15 @@ def resolve_uri(dir_uri: str, relative_uri: str) -> str:
     @param relative_uri:
     @return:
     """
-    if relative_uri.startswith('http'):
+    if relative_uri.startswith('http://') or relative_uri.startswith('https://'):
         return relative_uri
 
     # remove redundant characters in the relative uri
     if relative_uri.startswith('/'): relative_uri = relative_uri[1:]
     if relative_uri.startswith('./'): relative_uri = relative_uri[2:]
-    
+
     dir_uri = str(dir_uri)
-    if not dir_uri.startswith('http'):
+    if not dir_uri.startswith('http://') and not dir_uri.startswith('https://'):
         # check if the dir_uri was really a path to a directory or a file
         if '.' in dir_uri.split(os.sep)[-1]:
             return os.path.normpath(os.path.dirname(dir_uri) + os.sep + relative_uri)
@@ -40,7 +40,7 @@ def resolve_uri(dir_uri: str, relative_uri: str) -> str:
         dir_uri += '/'
 
     absolute_uri = dir_uri + relative_uri
-    if not dir_uri.startswith('http'):
+    if not dir_uri.startswith('http://') and not dir_uri.startswith('https://'):
         # make sure the path is correct
         absolute_uri = os.path.normpath(absolute_uri)
 

xbrl/instance.py

@@ -347,7 +347,7 @@ def parse_xbrl(instance_path: str, cache: HttpCache, instance_url: str or None =
     schema_uri: str = schema_ref.attrib[XLINK_NS + 'href']
     # check if the schema uri is relative or absolute
     # submissions from SEC normally have their own schema files, whereas submissions from the uk have absolute schemas
-    if schema_uri.startswith('http'):
+    if schema_uri.startswith('http://') or schema_uri.startswith("https://"):
         # fetch the taxonomy extension schema from remote
         taxonomy: TaxonomySchema = parse_taxonomy_url(schema_uri, cache)
     elif instance_url:
@@ -727,9 +727,9 @@ def parse_instance(self, uri: str, instance_url: str or None = None, encoding: s
         :return:
         """
         if uri.split('.')[-1] == 'xml' or uri.split('.')[-1] == 'xbrl':
-            return parse_xbrl_url(uri, self.cache) if uri.startswith('http') \
+            return parse_xbrl_url(uri, self.cache) if uri.startswith('http://') or uri.startswith('https://') \
                 else parse_xbrl(uri, self.cache, instance_url)
-        return parse_ixbrl_url(uri, self.cache) if uri.startswith('http') \
+        return parse_ixbrl_url(uri, self.cache) if uri.startswith('http://') or uri.startswith('https://') \
             else parse_ixbrl(uri, self.cache, instance_url, encoding)
 
     def __str__(self) -> str:

xbrl/taxonomy.py

@@ -593,7 +593,7 @@ def parse_taxonomy_url(schema_url: str, cache: HttpCache) -> TaxonomySchema:
     :param cache: :class:`xbrl.cache.HttpCache` instance
     :return: parsed :class:`xbrl.taxonomy.TaxonomySchema` object
     """
-    if not schema_url.startswith('http'): raise XbrlParseException(
+    if not schema_url.startswith('http://') and not schema_url.startswith('https://'): raise XbrlParseException(
         'This function only parses remotely saved taxonomies. Please use parse_taxonomy to parse local taxonomy schemas')
 
     schema_path: str = cache.cache_file(schema_url)
@@ -611,7 +611,7 @@ def parse_taxonomy(schema_path: str, cache: HttpCache, schema_url: str or None =
     :return: parsed :class:`xbrl.taxonomy.TaxonomySchema` object
     """
     schema_path = str(schema_path)
-    if schema_path.startswith('http'): raise XbrlParseException(
+    if schema_path.startswith('http://') or schema_path.startswith('https://'): raise XbrlParseException(
         'This function only parses locally saved taxonomies. Please use parse_taxonomy_url to parse remote taxonomy schemas')
     if not os.path.exists(schema_path):
         raise TaxonomyNotFound(f"Could not find taxonomy schema at {schema_path}")
@@ -632,7 +632,7 @@ def parse_taxonomy(schema_path: str, cache: HttpCache, schema_url: str or None =
             continue
 
         # sometimes the import schema location is relative. i.e schemaLocation="xbrl-linkbase-2003-12-31.xsd"
-        if import_uri.startswith('http'):
+        if import_uri.startswith('http://') or import_uri.startswith('https://'):
             # fetch the schema file from remote
             taxonomy.imports.append(parse_taxonomy_url(import_uri, cache))
         elif schema_url:
@@ -683,7 +683,7 @@ def parse_taxonomy(schema_path: str, cache: HttpCache, schema_url: str or None =
             linkbase_uri)
 
         # check if the linkbase url is relative
-        if linkbase_uri.startswith('http'):
+        if linkbase_uri.startswith('http://') or linkbase_uri.startswith('https://'):
             # fetch the linkbase from remote
             linkbase: Linkbase = parse_linkbase_url(linkbase_uri, linkbase_type, cache)
         elif schema_url: