feat(md2doc): recursive list renderer with manual numbering

tests/test_md2doc_lists.py

@@ -0,0 +1,130 @@
+"""Tests for list rendering — verifies nested levels use correct ilvl."""
+import zipfile
+import xml.etree.ElementTree as ET
+from pathlib import Path
+
+from docx import Document
+from bs4 import BeautifulSoup
+
+from md2doc import STYLES, _render_list
+
+W_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+
+def get_doc_xml(doc):
+    tmp = Path(__file__).parent / "_tmp_list.docx"
+    doc.save(tmp)
+    try:
+        with zipfile.ZipFile(tmp) as z:
+            return ET.fromstring(z.read("word/document.xml"))
+    finally:
+        tmp.unlink()
+
+
+def test_flat_bullet_list_produces_3_items_at_ilvl_0():
+    html = """
+    <ul>
+      <li>Item A</li>
+      <li>Item B</li>
+      <li>Item C</li>
+    </ul>
+    """
+    doc = Document()
+    node = BeautifulSoup(html, "html.parser").find("ul")
+    _render_list(doc, node, style=STYLES["elegant"])
+    root = get_doc_xml(doc)
+    ilvls = [int(el.get(f"{{{W_NS}}}val")) for el in root.iter(f"{{{W_NS}}}ilvl")]
+    assert ilvls == [0, 0, 0], f"expected all ilvl=0, got {ilvls}"
+
+
+def test_nested_bullet_list_uses_increasing_ilvl_and_resolves_to_multilevel_abstractNum():
+    """BEHAVIORAL: paragraphs have ilvl=[0,1,2], AND the numId they reference
+    resolves to an abstractNum that actually defines those levels. A no-op
+    register_multilevel_numbering (return 1) would leave paragraphs pointing to
+    default-template numId=1 (single-level), so the test must FAIL.
+    """
+    html = """
+    <ul>
+      <li>Top
+        <ul>
+          <li>Nested 1
+            <ul>
+              <li>Deep nested</li>
+            </ul>
+          </li>
+        </ul>
+      </li>
+    </ul>
+    """
+    doc = Document()
+    node = BeautifulSoup(html, "html.parser").find("ul")
+    _render_list(doc, node, style=STYLES["elegant"])
+
+    tmp = Path(__file__).parent / "_tmp_list_full.docx"
+    doc.save(tmp)
+    try:
+        with zipfile.ZipFile(tmp) as z:
+            doc_xml = z.read("word/document.xml")
+            num_xml = z.read("word/numbering.xml")
+        doc_root = ET.fromstring(doc_xml)
+        num_root = ET.fromstring(num_xml)
+
+        # 1. Paragraphs must have ilvl=[0,1,2]
+        ilvls = [int(el.get(f"{{{W_NS}}}val"))
+                 for el in doc_root.iter(f"{{{W_NS}}}ilvl")]
+        assert ilvls == [0, 1, 2], f"expected paragraph ilvl=[0,1,2], got {ilvls}"
+
+        # 2. All paragraphs must reference the SAME numId
+        numIds = [el.get(f"{{{W_NS}}}val")
+                  for el in doc_root.iter(f"{{{W_NS}}}numId")]
+        assert len(set(numIds)) == 1, \
+            f"expected all paragraphs to share one numId, got {set(numIds)}"
+        our_num_id = numIds[0]
+
+        # 3. numId resolves to abstractNum that defines ilvl=0,1,2
+        our_num = None
+        for num_el in num_root.findall(f"{{{W_NS}}}num"):
+            if num_el.get(f"{{{W_NS}}}numId") == our_num_id:
+                our_num = num_el
+                break
+        assert our_num is not None, f"our numId={our_num_id} not found in numbering.xml"
+
+        abstract_ref = our_num.find(f"{{{W_NS}}}abstractNumId")
+        assert abstract_ref is not None
+        abstract_id = abstract_ref.get(f"{{{W_NS}}}val")
+
+        our_abstract = None
+        for an in num_root.findall(f"{{{W_NS}}}abstractNum"):
+            if an.get(f"{{{W_NS}}}abstractNumId") == abstract_id:
+                our_abstract = an
+                break
+        assert our_abstract is not None, f"abstractNum {abstract_id} not found"
+
+        abstract_ilvls = sorted(int(l.get(f"{{{W_NS}}}ilvl"))
+                                for l in our_abstract.findall(f"{{{W_NS}}}lvl"))
+        assert abstract_ilvls == [0, 1, 2], \
+            f"our abstractNum must define ilvl=[0,1,2], got {abstract_ilvls}"
+    finally:
+        tmp.unlink()
+
+
+def test_numbered_list_uses_decimal_format():
+    html = """
+    <ol>
+      <li>First</li>
+      <li>Second</li>
+    </ol>
+    """
+    doc = Document()
+    node = BeautifulSoup(html, "html.parser").find("ol")
+    _render_list(doc, node, style=STYLES["elegant"])
+    tmp = Path(__file__).parent / "_tmp_num.docx"
+    doc.save(tmp)
+    try:
+        with zipfile.ZipFile(tmp) as z:
+            num_xml = z.read("word/numbering.xml")
+        num_root = ET.fromstring(num_xml)
+        fmts = [el.get(f"{{{W_NS}}}val") for el in num_root.iter(f"{{{W_NS}}}numFmt")]
+        assert "decimal" in fmts
+    finally:
+        tmp.unlink()