Extract 5 digit Segment ID from (some) ≥FV2410 AHBs

src/kohlrahbi/unfoldedahb/unfoldedahbline.py

@@ -81,6 +81,7 @@ class UnfoldedAhbLine(BaseModel):
     segment_name: str  # Ansprechpartner
     segment_gruppe: str | None  # SG3
     segment: str | None  # CTA
+    segment_id: str | None = None  # 00009
     datenelement: str | None  # 3055
     code: str | None  # IC
     qualifier: str | None  # Name vom Ansprechpartner

src/kohlrahbi/unfoldedahb/unfoldedahbtable.py

@@ -5,6 +5,7 @@
 import copy
 import json
 import re
+from functools import lru_cache
 from pathlib import Path
 from uuid import uuid4
 
@@ -26,6 +27,7 @@
 from kohlrahbi.unfoldedahb.unfoldedahbtablemetadata import UnfoldedAhbTableMetaData
 
 _segment_group_pattern = re.compile(r"^SG\d+$")
+_segment_id_pattern = re.compile(r"^\d{5}$")
 
 
 def _lines_are_equal_when_ignoring_guid(line1: AhbLine, line2: AhbLine) -> bool:
@@ -39,6 +41,24 @@ def _lines_are_equal_when_ignoring_guid(line1: AhbLine, line2: AhbLine) -> bool:
     return line1_copy == line2_copy
 
 
+@lru_cache
+def _split_data_element_and_segment_id(value: str | None) -> tuple[str | None, str | None]:
+    """
+    returns the data element id and segment id
+    """
+    if value is None:
+        return None, None
+    datenelement_id: str | None
+    segment_id: str | None
+    if _segment_id_pattern.match(value):
+        datenelement_id = None
+        segment_id = value
+    else:
+        datenelement_id = value
+        segment_id = None
+    return datenelement_id, segment_id
+
+
 def _keep_guids_of_unchanged_lines_stable(
     updated_ahb: FlatAnwendungshandbuch, existing_ahb: FlatAnwendungshandbuch
 ) -> None:
@@ -159,7 +179,8 @@ def from_ahb_table(cls, ahb_table: AhbTable, pruefi: str) -> "UnfoldedAhb":
                         segment_name=current_section_name,
                         segment_gruppe=row["Segment Gruppe"] or None,
                         segment=row["Segment"] or None,
-                        datenelement=row["Datenelement"] or None,
+                        datenelement=_split_data_element_and_segment_id(row["Datenelement"])[0],
+                        segment_id=_split_data_element_and_segment_id(row["Datenelement"])[1],
                         code=value_pool_entry,
                         qualifier="",
                         beschreibung=description,
@@ -284,6 +305,8 @@ def _is_just_segment(ahb_row: pd.Series) -> bool:  # type:ignore[type-arg]
             and not ahb_row["Datenelement"]
         ):
             return True
+        if ahb_row["Datenelement"] is not None and _segment_id_pattern.match(ahb_row["Datenelement"]):
+            return True
         return False
 
     @staticmethod
@@ -325,6 +348,7 @@ def convert_to_flat_ahb(self) -> FlatAnwendungshandbuch:
                     segment_group_key=unfolded_ahb_line.segment_gruppe,
                     segment_code=unfolded_ahb_line.segment,
                     data_element=unfolded_ahb_line.datenelement,
+                    segment_id=unfolded_ahb_line.segment_id,
                     value_pool_entry=unfolded_ahb_line.code,
                     name=unfolded_ahb_line.beschreibung or unfolded_ahb_line.qualifier,
                     ahb_expression=unfolded_ahb_line.bedingung_ausdruck,

unittests/test_ahb_sub_table.py

@@ -5,10 +5,12 @@
 from pathlib import Path
 
 import docx
+import pytest
 from docx.table import Table
 
 from kohlrahbi.ahbtable.ahbsubtable import AhbSubTable
-from kohlrahbi.read_functions import get_all_paragraphs_and_tables
+from kohlrahbi.read_functions import get_ahb_table, get_all_paragraphs_and_tables
+from kohlrahbi.unfoldedahb import UnfoldedAhb
 
 
 class TestAhbSubTable:
@@ -41,3 +43,50 @@ def test_from_table(self) -> None:
             assert isinstance(ahb_sub_table, AhbSubTable)
         else:
             raise TypeError("You did not pass a docx table instance.")
+
+    @pytest.mark.parametrize(
+        "docx_path, segment_id, segment_code",
+        [
+            pytest.param(
+                Path(__file__).parent
+                / Path(
+                    # pylint: disable=line-too-long
+                    "test-files/docx_files/UTILMDAHBStrom-informatorischeLesefassung1.2aKonsolidierteLesefassungmitFehlerkorrekturenStand05.04.2024_99991231_20240405.docx"
+                ),
+                "00003",
+                "UNH",
+            ),
+            pytest.param(
+                Path(__file__).parent
+                / Path(
+                    # pylint: disable=line-too-long
+                    "test-files/docx_files/UTILMDAHBStrom-informatorischeLesefassung1.2aKonsolidierteLesefassungmitFehlerkorrekturenStand05.04.2024_99991231_20240405.docx"
+                ),
+                "00004",
+                "BGM",
+            ),
+            pytest.param(
+                Path(__file__).parent
+                / Path(
+                    # pylint: disable=line-too-long
+                    "test-files/docx_files/UTILMDAHBStrom-informatorischeLesefassung1.2aKonsolidierteLesefassungmitFehlerkorrekturenStand05.04.2024_99991231_20240405.docx"
+                ),
+                "00540",
+                "UNT",
+            ),
+        ],
+    )
+    def test_segment_id_parsing(self, docx_path: Path, segment_id: str, segment_code: str) -> None:
+        """
+        https://github.com/Hochfrequenz/kohlrahbi/issues/304
+        """
+        assert docx_path.exists()
+        doc = docx.Document(str(docx_path))  # Creating word reader object.
+        ahb_table = get_ahb_table(document=doc, pruefi="55109")
+        assert ahb_table is not None
+        unfolded_ahb = UnfoldedAhb.from_ahb_table(ahb_table=ahb_table, pruefi="55109")
+        assert unfolded_ahb is not None
+        flat_ahb = unfolded_ahb.convert_to_flat_ahb()
+        assert flat_ahb is not None
+        assert any(l for l in flat_ahb.lines if l.segment_id is not None)
+        assert any(l for l in flat_ahb.lines if l.segment_id == segment_id and l.segment_code == segment_code)