activated new registry, fixed #75, fixed #69, fixed #59, fixed #53, f…

…ixed #40
manusimidt · Feb 18, 2022 · 6348b22 · 6348b22
1 parent ca6a9cc
commit 6348b22
Show file tree

Hide file tree

Showing 5 changed files with 37 additions and 198 deletions.
diff --git a/setup.py b/setup.py
@@ -27,8 +27,8 @@ def read(filename):
     packages=find_packages(exclude=('tests', 'cache', 'workdir')),
 
     install_requires=[
-        "requests", # needed for fetching xml files from the internet
-        "urllib3" # needed for http retries
+        "requests",  # needed for fetching xml files from the internet
+        "urllib3"  # needed for http retries
     ],
 
     classifiers=[

diff --git a/tests/data/example.html b/tests/data/example.html
@@ -7,7 +7,8 @@
       xmlns:link="http://www.xbrl.org/2003/linkbase"
       xmlns:xbrli="http://www.xbrl.org/2003/instance"
       xmlns:iso4217="http://www.xbrl.org/2003/iso4217"
-      xmlns:example="http://www.example.com/20210101">
+      xmlns:example="http://www.example.com/20210101"
+      xmlns:ixt="http://www.xbrl.org/inlineXBRL/transformation/2015-02-26">
 <head>
     <title>Sample iXBRL file</title>
     <style>* {

diff --git a/tests/test_transformation.py b/tests/test_transformation.py
@@ -9,8 +9,7 @@
 import sys
 import unittest
 
-from xbrl.helper.transformation import transform_ixt, transform_ixt_sec
-from xbrl.transformations import normalize
+from xbrl.transformations import normalize, TransformationException
 
 logging.basicConfig(stream=sys.stdout, level=logging.INFO)
 
@@ -21,9 +20,8 @@
 
         ['booleantrue', 'yeah', 'true'],
 
-        ['datedaymonth', '2.12', '--12-02'],
-        ['datedaymonth', '1.1', '--01-01'],
-        ['datedaymonth', '12.11', '--11-12'],
+        ['datedaymonth', '11.12', '--12-11'],
+        ['datedaymonth', '1.2', '--02-01'],
 
         ['datedaymonthen', '2. December', '--12-02'],
         ['datedaymonthen', '2 Sept.', '--09-02'],
@@ -177,8 +175,15 @@ def test_normalize(self):
         for namespace in testTransforms:
             for i, testCase in enumerate(testTransforms[namespace]):
                 formatCode, testInput, expected = testCase
-                testOutput = normalize(namespace, formatCode, testInput)
-                self.assertEqual(expected, testOutput, msg=f'Failed at test elem {i} of registry {namespace}')
+                if expected == 'exception':
+                    try:
+                        testOutput = normalize(namespace, formatCode, testInput)
+                        self.fail('Expected Transformation Exception, received ' + testOutput)
+                    except TransformationException:
+                        pass
+                else:
+                    testOutput = normalize(namespace, formatCode, testInput)
+                    self.assertEqual(expected, testOutput, msg=f'Failed at test elem {i} of registry {namespace}')
 
 
 if __name__ == '__main__':

diff --git a/xbrl/helper/transformation.py b/xbrl/helper/transformation.py
diff --git a/xbrl/instance.py b/xbrl/instance.py
@@ -14,10 +14,10 @@
 
 from xbrl import TaxonomyNotFound, InstanceParseException
 from xbrl.cache import HttpCache
-from xbrl.helper import transformation
 from xbrl.taxonomy import Concept, TaxonomySchema, parse_taxonomy, parse_common_taxonomy, parse_taxonomy_url
 from xbrl.helper.uri_helper import resolve_uri
 from xbrl.helper.xml_parser import parse_file
+from xbrl.transformations import normalize, TransformationException, TransformationNotImplemented
 
 logger = logging.getLogger(__name__)
 LINK_NS: str = "{http://www.xbrl.org/2003/linkbase}"
@@ -450,8 +450,6 @@ def _extract_non_numeric_value(fact_elem: ET.Element) -> str:
     """
     This function parses a ix:nonNumeric fact as defined in:
     https://www.xbrl.org/Specification/inlineXBRL-part1/PWD-2013-02-13/inlineXBRL-part1-PWD-2013-02-13.html#d1e6391
-
-
     :param fact_elem:
     :return:
     """
@@ -463,12 +461,16 @@ def _extract_non_numeric_value(fact_elem: ET.Element) -> str:
 
     fact_format = fact_elem.attrib['format'] if 'format' in fact_elem.attrib else None
     if fact_format:
+        # extract transformation registry namespace and transformation rule code
+        registryPrefix, formatCode = fact_format.split(':')
+        registryNS: str = fact_elem.attrib['ns_map'][registryPrefix]
         try:
-            if fact_format.startswith('ixt:'):
-                fact_value = transformation.transform_ixt(fact_value, fact_format.split(':')[1])
-            elif fact_format.startswith('ixt-sec'):
-                fact_value = transformation.transform_ixt_sec(fact_value, fact_format.split(':')[1])
-        except Exception:
+            fact_value = normalize(registryNS, formatCode, fact_value)
+        except TransformationNotImplemented:
+            logging.info(f'Transformation rule {formatCode} of registry {registryPrefix} is not supported. '
+                         f'The parser will just parse the value as it is and not transform it according to the rule.')
+            return fact_value
+        except TransformationException:
             logging.warning(f'Could not transform value "{fact_value}" with format {fact_format}')
             return fact_value
     return fact_value
@@ -495,14 +497,18 @@ def _extract_non_fraction_value(fact_elem: ET.Element) -> float or None or str:
     value_sign: str or None = fact_elem.attrib['sign'] if 'sign' in fact_elem.attrib else None
 
     if fact_format:
+        # extract transformation registry namespace and transformation rule code
+        registryPrefix, formatCode = fact_format.split(':')
+        registryNS: str = fact_elem.attrib['ns_map'][registryPrefix]
         try:
-            if fact_format.startswith('ixt:'):
-                fact_value = transformation.transform_ixt(fact_value, fact_format.split(':')[1])
-            elif fact_format.startswith('ixt-sec'):
-                fact_value = transformation.transform_ixt_sec(fact_value, fact_format.split(':')[1])
-        except Exception:
+            fact_value = normalize(registryNS, formatCode, fact_value)
+        except TransformationNotImplemented:
+            logging.info(f'Transformation rule {formatCode} of registry {registryPrefix} is not supported. '
+                         f'The parser will just parse the value as it is and not transform it according to the rule.')
+            return fact_value
+        except TransformationException:
             logging.warning(f'Could not transform value "{fact_value}" with format {fact_format}')
-            # return fact_value
+            return fact_value
 
     scaled_value = float(fact_value) * pow(10, value_scale)
     # Floating-point error mitigation
@@ -515,6 +521,7 @@ def _extract_non_fraction_value(fact_elem: ET.Element) -> float or None or str:
 
 def _extract_text_value(element: ET.Element) -> str:
     text = '' if element.text is None else element.text
+    if element.tail: text += element.tail
     for children in element:
         text += _extract_text_value(children)
     return text