fix(markdown): handle nested lists (#910)

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

tests/data/groundtruth/docling_v2/nested.md.md

@@ -0,0 +1,31 @@
+# Nesting
+
+A list featuring nesting:
+
+- abc
+    - abc123
+        - abc1234
+            - abc12345
+                - a.
+                - b.
+        - abcd1234：
+            - abcd12345：
+                - a.
+                - b.
+- def：
+    - def1234：
+        - def12345。
+- after one empty line
+    - foo
+- afer two empty lines
+    - bar
+
+- changing symbol
+
+A nested HTML list:
+
+- First item
+- Second item with subitems:
+    - Subitem 1
+    - Subitem 2
+- Last list item

tests/data/md/nested.md

@@ -0,0 +1,66 @@
+# Nesting
+
+A list featuring nesting:
+
+- abc
+	- abc123
+		- abc1234
+			- abc12345
+				- a.
+				- b.
+		- abcd1234：
+			- abcd12345：
+				- a.
+				- b.
+- def：
+	- def1234：
+		- def12345。
+
+- after one empty line
+	- foo
+
+
+- afer two empty lines
+	- bar
+* changing symbol
+
+A nested HTML list:
+
+<ul>
+    <li>First item</li>
+    <li>Second item with subitems:
+        <ul>
+            <li>Subitem 1</li>
+            <li>Subitem 2</li>
+        </ul>
+    </li>
+    <li>Last list item</li>
+</ul>
+
+<!--
+Table nesting apparently not yet suported by HTML backend:
+
+<table>
+  <tr>
+    <td>Cell</td>
+    <td>Nested Table
+      <table>
+        <tr>
+          <td>Cell 1</td>
+		  <>
+        </tr>
+        <tr>
+          <td>Cell 2</td>
+        </tr>
+        <tr>
+          <td>Cell 3</td>
+        </tr>
+        <tr>
+          <td>Cell 4</td>
+        </tr>
+      </table>
+    </td>
+  </tr>
+  <tr><td>additional row</td></tr>
+</table>
+-->

tests/test_backend_markdown.py

@@ -4,6 +4,8 @@ from docling.backend.md_backend import MarkdownDocumentBackend
 from docling.datamodel.base_models import InputFormat
 from docling.datamodel.document import InputDocument
 
+from .test_data_gen_flag import GEN_TEST_DATA
+
 
 def test_convert_valid():
     fmt = InputFormat.MD
@@ -30,6 +32,10 @@ def test_convert_valid():
         act_doc = backend.convert()
         act_data = act_doc.export_to_markdown()
 
-        with open(gt_path, "r", encoding="utf-8") as f:
-            exp_data = f.read().rstrip()
-        assert act_data == exp_data
+        if GEN_TEST_DATA:
+            with open(gt_path, mode="w", encoding="utf-8") as f:
+                f.write(f"{act_data}\n")
+        else:
+            with open(gt_path, encoding="utf-8") as f:
+                exp_data = f.read().rstrip()
+            assert exp_data == act_data

tests/test_data_gen_flag.py

@@ -0,0 +1,9 @@
+import os
+
+from pydantic import TypeAdapter
+
+GEN_TEST_DATA = TypeAdapter(bool).validate_python(os.getenv("DOCLING_GEN_TEST_DATA", 0))
+
+
+def test_gen_test_data_flag():
+    assert not GEN_TEST_DATA