fix(markdown): fix case of leading list (#174)

Signed-off-by: Panos Vagenas <[email protected]>

Author: vagenas

docling_core/types/doc/document.py

@@ -2488,20 +2488,11 @@ def _ingest_text(text: str, do_escape_html=True, do_escape_underscores=True):
                         visited=visited,
                     )
                     # NOTE: assumes unordered (flag & marker currently in ListItem)
-                    indent_str = f"{(list_level if components else 0) * indent * ' '}"
+                    indent_str = list_level * indent * " "
                     text = "\n".join(
                         [
-                            (
-                                # if starting with sublist, promote to top-level
-                                cpt.lstrip()
-                                if not components
-                                else (
-                                    # avoid additional marker on already evaled sublists
-                                    cpt
-                                    if cpt and cpt[0] == " "
-                                    else f"{indent_str}- {cpt}"
-                                )
-                            )
+                            # avoid additional marker on already evaled sublists
+                            cpt if cpt and cpt[0] == " " else f"{indent_str}- {cpt}"
                             for cpt in comps
                         ]
                     )

test/data/doc/constructed_doc.dt

@@ -1,4 +1,6 @@
-<doctag><title>Title of the Document</title>
+<doctag><unordered_list><list_item>item of leading list</list_item>
+</unordered_list>
+<title>Title of the Document</title>
 <text>Author 1
 Affiliation 1</text>
 <text>Author 2
@@ -19,10 +21,10 @@ Affiliation 2</text>
 <otsl><fcel>Product<fcel>Years<lcel><nl><ucel><fcel>2016<fcel>2017<nl><fcel>Apple<fcel>49823<fcel>695944<nl><caption>This is the caption of table 1.</caption></otsl>
 <picture><caption>This is the caption of figure 1.</caption></picture>
 <picture><caption>This is the caption of figure 2.</caption></picture>
-<unordered_list><unordered_list><list_item>subitem of list</list_item>
+<unordered_list><list_item>item 1 of list</list_item>
 </unordered_list>
-<list_item>item 1 of list</list_item>
-<list_item>item 2 of list</list_item>
+<unordered_list><unordered_list><list_item>item 1 of list after empty list</list_item>
+<list_item>item 2 of list after empty list</list_item>
 </unordered_list>
 <unordered_list><list_item>item 1 of neighboring list</list_item>
 <list_item>item 2 of neighboring list</list_item>
@@ -35,6 +37,7 @@ Affiliation 2</text>
 <formula>E=mc^2</formula>
 <paragraph>(to be displayed inline)</paragraph>
 </unordered_list>
+</unordered_list>
 <paragraph>Here a code block:</paragraph>
 <code<_unknown_>print("Hello world")</code
 <paragraph>Here a formula block:</paragraph>

test/data/doc/constructed_doc.dt.gt

@@ -1,4 +1,6 @@
-<doctag><title>Title of the Document</title>
+<doctag><unordered_list><list_item>item of leading list</list_item>
+</unordered_list>
+<title>Title of the Document</title>
 <text>Author 1
 Affiliation 1</text>
 <text>Author 2
@@ -19,10 +21,10 @@ Affiliation 2</text>
 <otsl><fcel>Product<fcel>Years<lcel><nl><ucel><fcel>2016<fcel>2017<nl><fcel>Apple<fcel>49823<fcel>695944<nl><caption>This is the caption of table 1.</caption></otsl>
 <picture><caption>This is the caption of figure 1.</caption></picture>
 <picture><caption>This is the caption of figure 2.</caption></picture>
-<unordered_list><unordered_list><list_item>subitem of list</list_item>
+<unordered_list><list_item>item 1 of list</list_item>
 </unordered_list>
-<list_item>item 1 of list</list_item>
-<list_item>item 2 of list</list_item>
+<unordered_list><unordered_list><list_item>item 1 of list after empty list</list_item>
+<list_item>item 2 of list after empty list</list_item>
 </unordered_list>
 <unordered_list><list_item>item 1 of neighboring list</list_item>
 <list_item>item 2 of neighboring list</list_item>
@@ -35,6 +37,7 @@ Affiliation 2</text>
 <formula>E=mc^2</formula>
 <paragraph>(to be displayed inline)</paragraph>
 </unordered_list>
+</unordered_list>
 <paragraph>Here a code block:</paragraph>
 <code<_unknown_>print("Hello world")</code
 <paragraph>Here a formula block:</paragraph>

test/data/doc/constructed_doc.embedded.html.gt

@@ -69,6 +69,9 @@
     }
     </style>
     </head>
+<ul>
+<li>item of leading list</li>
+</ul>
 <h1>Title of the Document</h1>
 <p>Author 1<br>Affiliation 1</p>
 <p>Author 2<br>Affiliation 2</p>
@@ -92,11 +95,12 @@
 <figure><figcaption>This is the caption of figure 1.</figcaption></figure>
 <figure><figcaption>This is the caption of figure 2.</figcaption><img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAEAAAABACAIAAAAlC+aJAAAAIklEQVR4nO3BAQ0AAADCoPdPbQ8HFAAAAAAAAAAAAAAA8G4wQAABiwCo9wAAAABJRU5ErkJggg=="></figure>
 <ul>
-<ul>
-<li>subitem of list</li>
-</ul>
 <li>item 1 of list</li>
-<li>item 2 of list</li>
+</ul>
+<ul>
+<ul>
+<li>item 1 of list after empty list</li>
+<li>item 2 of list after empty list</li>
 </ul>
 <ul>
 <li>item 1 of neighboring list</li>
@@ -111,6 +115,7 @@
 <div><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><mrow><mi>E</mi><mo>&#x0003D;</mo><mi>m</mi><msup><mi>c</mi><mn>2</mn></msup></mrow><annotation encoding="TeX">E=mc^2</annotation></math></div>
 <p>(to be displayed inline)</p>
 </ul>
+</ul>
 <p>Here a code block:</p>
 <pre><code>print("Hello world")</code></pre>
 <p>Here a formula block:</p>