test: move dump reading helper to dumps module

tests/helpers/samples/artefact.py

@@ -1,5 +1,5 @@
+from tests.helpers.samples.dumps import read_emu_extract
 from tests.helpers.samples.image import SAMPLE_IMAGE_ID
-from tests.helpers.samples.utils import read_emu_extract
 
 # this is taken from ecatalogue.export.20170830.gz but with the MulMultiMediaRefs
 # replaced with a single reference to the SAMPLE_IMAGE_ID

tests/helpers/samples/dumps.py

@@ -1,5 +1,5 @@
 from enum import Enum
-from typing import Optional
+from typing import Optional, Tuple
 from uuid import uuid4
 
 
@@ -54,3 +54,31 @@ def create_eaudit(irn_to_delete: str, table_to_delete_from: str) -> dict:
         "AudTable": table_to_delete_from,
         "AudKey": irn_to_delete,
     }
+
+
+def read_emu_extract(text: str) -> Tuple[str, dict]:
+    data = {}
+    for line in text.split("\n"):
+        line = line.strip()
+        if not line:
+            continue
+
+        # the format is <field>:<index>=<value>
+        field, value = line.split("=", 1)
+        field = field.split(":", 1)[0]
+
+        existing = data.get(field)
+        if existing is None:
+            # the value isn't in the data dict, add it
+            data[field] = value
+        else:
+            if isinstance(existing, tuple):
+                # there is an existing set of values in the data dict, add
+                # the new value in a new tuple
+                data[field] = (*existing, value)
+            else:
+                # there is an existing value (just one) in the data dict,
+                # add the new value in a new tuple
+                data[field] = (existing, value)
+
+    return data["irn"], data

tests/helpers/samples/image.py

@@ -1,4 +1,4 @@
-from tests.helpers.samples.utils import read_emu_extract
+from tests.helpers.samples.dumps import read_emu_extract
 
 # this is taken from emultimedia.export.20230510.gz
 raw_data = f"""

tests/helpers/samples/indexlot.py

@@ -1,5 +1,5 @@
+from tests.helpers.samples.dumps import read_emu_extract
 from tests.helpers.samples.image import SAMPLE_IMAGE_ID
-from tests.helpers.samples.utils import read_emu_extract
 
 # this is taken from ecatalogue.export.20231008.gz but with the MulMultiMediaRefs
 # replaced with a single reference to the SAMPLE_IMAGE_ID

tests/helpers/samples/preparation.py

@@ -1,5 +1,5 @@
+from tests.helpers.samples.dumps import read_emu_extract
 from tests.helpers.samples.specimen import SAMPLE_SPECIMEN_ID
-from tests.helpers.samples.utils import read_emu_extract
 
 # this is taken from ecatalogue.export.20231008.gz but with the EntPreSpecimenRef field
 # replaced with a single reference to the SAMPLE_SPECIMEN_ID

tests/helpers/samples/specimen.py

@@ -1,5 +1,5 @@
+from tests.helpers.samples.dumps import read_emu_extract
 from tests.helpers.samples.image import SAMPLE_IMAGE_ID
-from tests.helpers.samples.utils import read_emu_extract
 
 # this is taken from ecatalogue.export.20231019.gz but with the MulMultiMediaRefs
 # replaced with a single reference to the SAMPLE_IMAGE_ID

tests/helpers/samples/taxonomy.py

@@ -1,4 +1,4 @@
-from tests.helpers.samples.utils import read_emu_extract
+from tests.helpers.samples.dumps import read_emu_extract
 
 # this is taken from etaxonomy.export.20210930.gz
 raw_data = f"""

tests/helpers/samples/threed.py

@@ -1,4 +1,4 @@
-from tests.helpers.samples.utils import read_emu_extract
+from tests.helpers.samples.dumps import read_emu_extract
 
 # this is taken from emultimedia.export.20211117.gz
 raw_data = f"""