spec_object_parser: a yet another edge case when handling ATTRIBUTE-VALUE-XHTML

Author: stanislaw

reqif/helpers/lxml.py

@@ -45,6 +45,9 @@ def my_escape_title(string: str) -> str:
 # FIXME: Would be great to find a better solution for this.
 def stringify_namespaced_children(node, namespace_tag=None) -> str:
     if namespace_tag is None:
+        assert (
+            len(node.nsmap) > 0
+        ), f"This method must be called on a namespaced tag:\n{dump_xml_node(node)}"  # noqa: E501
         nskey = next(iter(node.nsmap.keys()))
     else:
         nskey = namespace_tag
@@ -79,7 +82,7 @@ def _stringify_reqif_ns_node(node):
     return string
 
 
-# https://stackoverflow.com/a/4624146/598057
+# https://stackoverflow.com/a/28173933/598057
 def stringify_children(node):
     return "".join(
         chunk
@@ -92,14 +95,17 @@ def stringify_children(node):
                             child,
                             encoding=str,
                             with_tail=False,
-                            pretty_print=True,
+                            pretty_print=False,
                         ),
                         child.tail,
                     )
                     for child in node.getchildren()
                 )
             ),
-            (node.tail,),
+            # The original snippet prints the node tail for some reason which is
+            # surprisingly unnecessary.
+            # (node.tail,),  # noqa: ERA001
+            (None,),
         )
         if chunk
     )

reqif/parsers/spec_object_parser.py

@@ -5,6 +5,7 @@
 
 from reqif.helpers.lxml import (
     lxml_convert_children_from_reqif_ns_xhtml_string,
+    stringify_children,
     stringify_namespaced_children,
 )
 from reqif.helpers.string.xhtml_indent import reqif_unindent_xhtml_string
@@ -205,10 +206,22 @@ 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)
-                )
+
+                # Edge: There are not <xhtml:...> or <reqif-xhtml...> tags.
+                if len(the_value.nsmap) > 0:
+                    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
+                            )
+                        )
+                    )
+                else:
+                    attribute_value = stringify_children(the_value)
+                    attribute_value_stripped_xhtml = (
+                        reqif_unindent_xhtml_string(attribute_value)
+                    )
                 attribute_definition_ref = (
                     attribute_xml.find("DEFINITION")
                     .find("ATTRIBUTE-DEFINITION-XHTML-REF")

…-OBJECTS/02_XHTML_attribute/sample.reqif …UE-XHTML/01_XHTML_attribute/sample.reqiftests/integration/reqif/SPEC-OBJECTS/02_XHTML_attribute/sample.reqif renamed to tests/integration/reqif/SPEC-OBJECTS/ATTRIBUTE-VALUE-XHTML/01_XHTML_attribute/sample.reqif tests/integration/reqif/SPEC-OBJECTS/02_XHTML_attribute/sample.reqif renamed to tests/integration/reqif/SPEC-OBJECTS/ATTRIBUTE-VALUE-XHTML/01_XHTML_attribute/sample.reqif

@@ -0,0 +1,24 @@
+<?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>
+                Some text without any tags.
+              </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>

…EC-OBJECTS/02_XHTML_attribute/test.itest …ALUE-XHTML/01_XHTML_attribute/test.itesttests/integration/reqif/SPEC-OBJECTS/02_XHTML_attribute/test.itest renamed to tests/integration/reqif/SPEC-OBJECTS/ATTRIBUTE-VALUE-XHTML/01_XHTML_attribute/test.itest tests/integration/reqif/SPEC-OBJECTS/02_XHTML_attribute/test.itest renamed to tests/integration/reqif/SPEC-OBJECTS/ATTRIBUTE-VALUE-XHTML/01_XHTML_attribute/test.itest

@@ -0,0 +1,3 @@
+RUN: mkdir -p %S/output
+RUN: %reqif passthrough %S/sample.reqif %S/output/sample.reqif
+RUN: diff %S/sample.reqif %S/output/sample.reqif