feat: support <Uebertragungsdatei> tag in AHBs and MIGs (#58)

src/fundamend/reader/ahbreader.py

@@ -27,6 +27,7 @@
     _is_format,
     _is_segment,
     _is_segment_group,
+    _is_uebertragungsdatei,
 )
 
 # pylint:disable=duplicate-code
@@ -35,10 +36,13 @@
 
 def _to_code(element: ET.Element) -> Code:
     assert _is_code(element)
+    value = element.text
+    if value is not None:
+        value = value.strip()
     return Code(
         name=element.attrib["Name"],
         description=element.attrib["Description"] or None,
-        value=element.text,
+        value=value,
         ahb_status=element.attrib["AHB_Status"],
     )
 
@@ -220,7 +224,7 @@ def get_anwendungsfaelle(self) -> list[Anwendungsfall]:
     def _iter_segments_and_segment_groups(self, element: ET.Element) -> list[SegmentGroup | Segment]:
         """recursive function that builds a list of all segments and segment groups"""
         result: list[Segment | SegmentGroup] = []
-        if _is_anwendungsfall(element) or _is_format(element):
+        if _is_anwendungsfall(element) or _is_format(element) or _is_uebertragungsdatei(element):
             for sub_element in element:
                 result.extend(self._iter_segments_and_segment_groups(sub_element))
         if _is_segment_group(element):
@@ -231,7 +235,8 @@ def _iter_segments_and_segment_groups(self, element: ET.Element) -> list[Segment
 
     def _read_anwendungsfall(self, original_element: ET.Element) -> Anwendungsfall:
         segments_and_groups = []
-        for element in self._element_tree.getroot():
+        root = self._element_tree.getroot()
+        for element in root:
             segments_and_groups.extend(self._iter_segments_and_segment_groups(element))
         return Anwendungsfall(
             pruefidentifikator=original_element.attrib["Pruefidentifikator"],

src/fundamend/reader/element_distinction.py

@@ -46,3 +46,8 @@ def _is_format(element: ET.Element) -> bool:
 def _is_anwendungsfall(element: ET.Element) -> bool:
     """returns true iff the element is an AHB anwendungsfall"""
     return element.tag == "AWF"
+
+
+def _is_uebertragungsdatei(element: ET.Element) -> bool:
+    """returns true iff the element is an Uebertragsdatei element (usually below the format level)"""
+    return element.tag == "Uebertragungsdatei"

src/fundamend/reader/migreader.py

@@ -21,6 +21,7 @@
     _is_data_element_group,
     _is_segment,
     _is_segment_group,
+    _is_uebertragungsdatei,
 )
 
 
@@ -117,6 +118,13 @@ def _to_segment_group(element: ET.Element) -> SegmentGroup:
     )
 
 
+def _get_first_tag_starting_with_m(element: ET.Element) -> ET.Element:
+    for elem in element.iter():
+        if elem.tag.startswith("M_"):
+            return elem
+    raise ValueError("No element starting with M_ found")
+
+
 class MigReader:
     """
     Accesses information from an XML based message implementation guide
@@ -133,26 +141,31 @@ def get_publishing_date(self) -> date:
         """
         returns the publishing date of the message implementation guide
         """
-        raw_value = self._element_tree.getroot().attrib["Veroeffentlichungsdatum"]  # e.g. '24.10.2023'
+        root = self._element_tree.getroot()  # might be either <M_FORMAT> or <Uebertragungsdatei>
+        raw_value = root.attrib["Veroeffentlichungsdatum"]  # e.g. '24.10.2023'
         result = datetime.strptime(raw_value, "%d.%m.%Y").date()
         return result
 
     def get_author(self) -> str:
         """
         returns the author of the message implementation guide
         """
-        return self._element_tree.getroot().attrib["Author"]
+        root = self._element_tree.getroot()  # might be either <M_FORMAT> or <Uebertragungsdatei>
+        return root.attrib["Author"]
 
     def get_version(self) -> str:
         """
         returns the version of the message implementation guide
         """
-        return self._element_tree.getroot().attrib["Versionsnummer"]
+        root = self._element_tree.getroot()  # might be either <M_FORMAT> or <Uebertragungsdatei>
+        return root.attrib["Versionsnummer"]
 
     def get_format(self) -> str:
         """returns the format of the message implementation guide, e.g. 'UTILTS'"""
-        root_tag: str = self._element_tree.getroot().tag
-        return root_tag.lstrip("M_")  # converts 'M_UTILTS' to 'UTILTS'
+        root = self._element_tree.getroot()
+        if _is_uebertragungsdatei(root):
+            root = _get_first_tag_starting_with_m(root)
+        return root.tag.lstrip("M_")  # converts 'M_UTILTS' to 'UTILTS'
 
     def _iter_segments_and_segment_groups(self, element: ET.Element) -> list[SegmentGroup | Segment]:
         """recursive function that builds a list of all segments and segment groups"""
@@ -168,7 +181,13 @@ def read(self) -> MessageImplementationGuide:
         read the entire file and convert it to a MessageImplementationGuid instance
         """
         segments_and_groups = []
-        for index, element in enumerate(self._element_tree.getroot()):
+        root = self._element_tree.getroot()
+        if _is_uebertragungsdatei(root):
+            for elem in root.iter():
+                if elem.tag.startswith("M_"):
+                    root = elem
+                    break
+        for index, element in enumerate(root):
             if index == 0:
                 continue
             segments_and_groups.extend(self._iter_segments_and_segment_groups(element))

tox.ini

@@ -16,7 +16,7 @@ deps =
     -r requirements.txt
     .[tests]
 setenv = PYTHONPATH = {toxinidir}/src
-commands = python -m pytest --basetemp={envtmpdir} {posargs}
+commands = python -m pytest --basetemp={envtmpdir} {posargs} -vv
 
 [testenv:linting]
 # the linting environment is called by the Github Action that runs the linter