spec_object_parser: a slot for XHTML attribute stripped from namespace info

Author: stanislaw

reqif/helpers/lxml.py

@@ -87,7 +87,15 @@ def stringify_children(node):
             (node.text,),
             chain(
                 *(
-                    (tostring(child, encoding=str, with_tail=False), child.tail)
+                    (
+                        tostring(
+                            child,
+                            encoding=str,
+                            with_tail=False,
+                            pretty_print=True,
+                        ),
+                        child.tail,
+                    )
                     for child in node.getchildren()
                 )
             ),
@@ -111,6 +119,12 @@ def lxml_convert_from_reqif_ns_xhtml_string(lxml_node) -> str:
     ).rstrip()
 
 
+def lxml_convert_children_from_reqif_ns_xhtml_string(lxml_node) -> str:
+    lxml_node_deep_copy = deepcopy(lxml_node)
+    lxml_strip_namespace_from_xml(lxml_node_deep_copy, full=True)
+    return stringify_children(lxml_node_deep_copy)
+
+
 def is_self_closed_tag(xml):
     # The tag cannot be closed if it has children or has a non-None text.
     if len(xml.getchildren()) > 0:

reqif/models/reqif_spec_object.py

@@ -6,16 +6,20 @@
 
 @auto_described
 class SpecObjectAttribute:
-    def __init__(
+    def __init__(  # pylint: disable=too-many-arguments
         self,
         attribute_type: SpecObjectAttributeType,
         definition_ref: str,
         value: Union[str, List[str]],
+        value_stripped_xhtml: Optional[str] = None,
         xml_node: Optional[Any] = None,
     ):
         self.attribute_type: SpecObjectAttributeType = attribute_type
         self.definition_ref: str = definition_ref
         self.value: Union[str, List[str]] = value
+        # Only for XHTML attributes: A valud stripped of the
+        # <xhtml:...> namespace. <xhtml:div> becomes <div>...
+        self.value_stripped_xhtml: Optional[str] = value_stripped_xhtml
         self.xml_node: Optional[Any] = xml_node
 
 

reqif/parsers/spec_object_parser.py

@@ -3,7 +3,11 @@
 
 from lxml import etree
 
-from reqif.helpers.lxml import stringify_namespaced_children
+from reqif.helpers.lxml import (
+    lxml_convert_children_from_reqif_ns_xhtml_string,
+    stringify_namespaced_children,
+)
+from reqif.helpers.string.xhtml_indent import reqif_unindent_xhtml_string
 from reqif.models.reqif_spec_object import (
     ReqIFSpecObject,
     SpecObjectAttribute,
@@ -202,16 +206,20 @@ def parse(spec_object_xml) -> ReqIFSpecObject:
             elif attribute_xml.tag == "ATTRIBUTE-VALUE-XHTML":
                 the_value = attribute_xml.find("THE-VALUE")
                 attribute_value = stringify_namespaced_children(the_value)
+                attribute_value_stripped_xhtml = reqif_unindent_xhtml_string(
+                    lxml_convert_children_from_reqif_ns_xhtml_string(the_value)
+                )
                 attribute_definition_ref = (
                     attribute_xml.find("DEFINITION")
                     .find("ATTRIBUTE-DEFINITION-XHTML-REF")
                     .text
                 )
                 attribute = SpecObjectAttribute(
-                    xml_node=attribute_xml,
                     attribute_type=SpecObjectAttributeType.XHTML,
                     definition_ref=attribute_definition_ref,
                     value=attribute_value,
+                    value_stripped_xhtml=attribute_value_stripped_xhtml,
+                    xml_node=attribute_xml,
                 )
             else:
                 raise NotImplementedError(etree.tostring(attribute_xml))

tests/unit/reqif/parsers/test_spec_object_parser_strip_xhtml.py

@@ -0,0 +1,50 @@
+from reqif.parser import ReqIFParser
+
+
+def test_01_indenting_unintended_xhtml():
+    input_reqif = """\
+<?xml version="1.0" encoding="UTF-8"?>
+<REQ-IF xmlns="http://www.omg.org/spec/ReqIF/20110401/reqif.xsd" xmlns:configuration="http://eclipse.org/rmf/pror/toolextensions/1.0" xmlns:xhtml="http://www.w3.org/1999/xhtml">
+  <CORE-CONTENT>
+    <REQ-IF-CONTENT>
+      <SPEC-OBJECTS>
+        <SPEC-OBJECT IDENTIFIER="TEST_SPEC_OBJECT_IDENTIFIER" LAST-CHANGE="2021-10-15T11:34:36.007+02:00">
+          <VALUES>
+            <ATTRIBUTE-VALUE-XHTML>
+              <DEFINITION>
+                <ATTRIBUTE-DEFINITION-XHTML-REF>_gFhrXWojEeuExICsU7Acmg</ATTRIBUTE-DEFINITION-XHTML-REF>
+              </DEFINITION>
+              <THE-VALUE>
+                <xhtml:div>
+                  <xhtml:p style=" font-style: italic">Delay <xhtml:span style="text-decoration: underline;">&lt;= 5s</xhtml:span></xhtml:p>
+                </xhtml:div>
+              </THE-VALUE>
+            </ATTRIBUTE-VALUE-XHTML>
+          </VALUES>
+          <TYPE>
+            <SPEC-OBJECT-TYPE-REF>TEST_SPEC_OBJECT_TYPE_IDENTIFIER_FUNCTIONAL</SPEC-OBJECT-TYPE-REF>
+          </TYPE>
+        </SPEC-OBJECT>
+      </SPEC-OBJECTS>
+    </REQ-IF-CONTENT>
+  </CORE-CONTENT>
+</REQ-IF>
+"""  # noqa: E501
+
+    expected_stripped_xhtml = """\
+<div>
+  <p style=" font-style: italic">Delay <span style="text-decoration: underline;">&lt;= 5s</span></p>
+</div>\
+"""  # noqa: E501
+
+    reqif_bundle = ReqIFParser.parse_from_string(input_reqif)
+    spec_object = reqif_bundle.get_spec_object_by_ref(
+        "TEST_SPEC_OBJECT_IDENTIFIER"
+    )
+
+    assert (
+        spec_object.attribute_map[
+            "_gFhrXWojEeuExICsU7Acmg"
+        ].value_stripped_xhtml
+        == expected_stripped_xhtml
+    )