Plan: fix H3 spy tests + _render_pre trailing empty

Empirical audit (Stage 2) found 2 critical spy tests guarding the H3 keystone: - test_register_multilevel_numbering_creates_abstractNum_with_3_levels - test_nested_bullet_list_uses_increasing_ilvl Both passed when register_multilevel_numbering was mutated to 'return 1' (no XML written). Rewrote both to BEHAVIORAL form: trace numId → w:num → w:abstractNumId → w:abstractNum, assert THAT abstractNum has ilvl=[0,1,2]. Also: _render_pre now drops trailing empty line (text.split('\n') artifact).
2026-07-28 00:00:07 +03:00
parent 5891ed892c
commit e36e87966d
1 changed files with 93 additions and 11 deletions
@@ -610,20 +610,48 @@ def test_add_cell_shading_inserts_shd_in_tcPr():


 def test_register_multilevel_numbering_creates_abstractNum_with_3_levels():
-    """H3 Route B: register creates abstractNum with 3 w:lvl elements."""
+    """H3 Route B: register creates ONE abstractNum with 3 w:lvl elements (ilvl 0/1/2).
+
+    BEHAVIORAL: traces num_id → w:num → w:abstractNumId → w:abstractNum, then
+    asserts THAT abstractNum (not all 9 default abstractNums in the template)
+    has exactly the levels we registered. A `return 1` no-op mutation must FAIL
+    because no w:num with our id exists.
+    """
    doc = Document()
    num_id = register_multilevel_numbering(doc, levels=3, kind="bullet")
    assert isinstance(num_id, int)
-    # Inspect numbering.xml part
+
    tmp = Path(__file__).parent / "_tmp_num.docx"
    doc.save(tmp)
    try:
        with zipfile.ZipFile(tmp) as z:
            num_xml = z.read("word/numbering.xml")
        root = ET.fromstring(num_xml)
-        lvls = root.findall(f".//{{{W_NS}}}lvl")
-        # at least 3 levels in the abstractNum we just registered
-        assert len(lvls) >= 3, f"expected >=3 levels, found {len(lvls)}"
+
+        # Find w:num matching our num_id
+        our_num = None
+        for num_el in root.findall(f"{{{W_NS}}}num"):
+            if num_el.get(f"{{{W_NS}}}numId") == str(num_id):
+                our_num = num_el
+                break
+        assert our_num is not None, f"No <w:num> with numId={num_id} (function did nothing)"
+
+        # Follow to abstractNumId
+        abstract_ref = our_num.find(f"{{{W_NS}}}abstractNumId")
+        assert abstract_ref is not None, "missing w:abstractNumId in our w:num"
+        abstract_id = abstract_ref.get(f"{{{W_NS}}}val")
+
+        # Find that abstractNum and verify it has the 3 levels
+        our_abstract = None
+        for an in 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"No <w:abstractNum> with id={abstract_id}"
+
+        lvls = our_abstract.findall(f"{{{W_NS}}}lvl")
+        ilvls = sorted(int(l.get(f"{{{W_NS}}}ilvl")) for l in lvls)
+        assert ilvls == [0, 1, 2], f"expected ilvl=[0,1,2] in OUR abstractNum, got {ilvls}"
    finally:
        tmp.unlink()

@@ -1124,7 +1152,12 @@ def test_flat_bullet_list_produces_3_items_at_ilvl_0():
    assert ilvls == [0, 0, 0], f"expected all ilvl=0, got {ilvls}"


-def test_nested_bullet_list_uses_increasing_ilvl():
+def test_nested_bullet_list_uses_increasing_ilvl_and_resolves_to_multilevel_abstractNum():
+    """BEHAVIORAL: not only must paragraphs have ilvl=[0,1,2], but the numId they
+    reference must resolve 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
@@ -1141,10 +1174,55 @@ def test_nested_bullet_list_uses_increasing_ilvl():
    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")]
-    # Expect ilvl 0, 1, 2 across the nesting
-    assert ilvls == [0, 1, 2], f"expected 0,1,2 nesting, got {ilvls}"
+
+    # Save and read both document.xml AND numbering.xml
+    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 (our registered numbering)
+        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. That numId must resolve (via w:num → w:abstractNumId) to an abstractNum
+        #    that defines ilvl=0,1,2 — otherwise Word renders flat lists.
+        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():
@@ -1406,12 +1484,16 @@ def _render_pre(doc, node, style: dict):

    Preserves newlines via add_break() between lines (Word ignores literal \\n in runs).
    Leading whitespace on each line is preserved as literal spaces (monospace font
-    keeps alignment).
+    keeps alignment). Trailing empty line from markdown's final \\n is dropped.
    """
    code_fill = style.get("code_fill", "f7f8fa")
    # Get text without collapse — preserves whitespace and indentation
    text = node.get_text()
+    # Drop trailing empty line(s) from markdown's terminal \n — would create
+    # spurious extra <w:br/> + empty run.
    lines = text.split("\n")
+    while lines and lines[-1] == "":
+        lines.pop()

    p = doc.add_paragraph()
    for i, line in enumerate(lines):