feat(md2doc): XML helpers — borders, shading, multi-level numbering

2026-07-28 10:23:18 +03:00
parent e3176a789e
commit 322eaad887
2 changed files with 286 additions and 0 deletions
@@ -84,6 +84,154 @@ def _bulletize(text: str) -> str:
    return "\n".join(out)


+# ---------------------------------------------------------------------------
+# XML manipulation helpers
+# Spec ref: docs/specs/2026-07-27-md2doc-design.md §4.1 — verified empirically
+# that python-docx 1.2 has no public API for borders/shading/numbering, so
+# we manipulate the OOXML directly via OxmlElement.
+# ---------------------------------------------------------------------------
+
+
+def add_paragraph_bottom_border(paragraph, color: str = "000000", size: str = "6"):
+    """Attach a bottom border to a paragraph (e.g., Heading 1 underline).
+
+    Spec §4.1 H1: SURVIVED — verified via XML inspection.
+    """
+    pPr = paragraph._p.get_or_add_pPr()
+    pBdr = pPr.find(qn('w:pBdr'))
+    if pBdr is None:
+        pBdr = OxmlElement('w:pBdr')
+        pPr.append(pBdr)
+    bottom = OxmlElement('w:bottom')
+    bottom.set(qn('w:val'), 'single')
+    bottom.set(qn('w:sz'), size)
+    bottom.set(qn('w:space'), '1')
+    bottom.set(qn('w:color'), color)
+    pBdr.append(bottom)
+
+
+def add_paragraph_shading(paragraph, fill: str):
+    """Apply background shading to a paragraph (code, blockquote).
+
+    Spec §4.1 H2: SURVIVED.
+    """
+    pPr = paragraph._p.get_or_add_pPr()
+    shd = OxmlElement('w:shd')
+    shd.set(qn('w:val'), 'clear')
+    shd.set(qn('w:color'), 'auto')
+    shd.set(qn('w:fill'), fill)
+    pPr.append(shd)
+
+
+def add_cell_shading(cell, fill: str):
+    """Apply background shading to a table cell (header row).
+
+    Spec §4.1 H4: SURVIVED. Inserts w:shd inside w:tcPr.
+    """
+    tcPr = cell._tc.get_or_add_tcPr()
+    shd = OxmlElement('w:shd')
+    shd.set(qn('w:val'), 'clear')
+    shd.set(qn('w:color'), 'auto')
+    shd.set(qn('w:fill'), fill)
+    tcPr.append(shd)
+
+
+def register_multilevel_numbering(doc, levels: int = 3, kind: str = "bullet") -> int:
+    """Register a multi-level numbering definition in the document.
+
+    Returns the numId to reference from paragraphs.
+
+    Spec §4.1 H3 Route B: SURVIVED at XML level. Mandatory because style-name
+    approach ('List Bullet 2') produces flat lists in Word (single-level
+    abstractNums in default template).
+
+    Args:
+        doc: python-docx Document
+        levels: number of nesting levels to define (1=flat, 3=three levels deep)
+        kind: 'bullet' or 'decimal' for numbered lists
+    """
+    numbering = doc.part.numbering_part.element
+
+    existing_abstract_ids = [
+        int(an.get(qn('w:abstractNumId')))
+        for an in numbering.findall(qn('w:abstractNum'))
+    ]
+    abstract_num_id = max(existing_abstract_ids, default=-1) + 1
+
+    abstract_num = OxmlElement('w:abstractNum')
+    abstract_num.set(qn('w:abstractNumId'), str(abstract_num_id))
+
+    multi_level = OxmlElement('w:multiLevelType')
+    multi_level.set(qn('w:val'), 'hybridMultilevel')
+    abstract_num.append(multi_level)
+
+    for ilvl in range(levels):
+        lvl = OxmlElement('w:lvl')
+        lvl.set(qn('w:ilvl'), str(ilvl))
+        lvl.set(qn('w:tplc'), '0409000F' if kind == "bullet" else '04070001')
+
+        start = OxmlElement('w:start')
+        start.set(qn('w:val'), '1')
+        lvl.append(start)
+
+        numFmt = OxmlElement('w:numFmt')
+        numFmt.set(qn('w:val'), 'bullet' if kind == "bullet" else 'decimal')
+        lvl.append(numFmt)
+
+        lvl_text = OxmlElement('w:lvlText')
+        lvl_text.set(qn('w:val'), '•' if kind == "bullet" else f'%{ilvl + 1}.')
+        lvl.append(lvl_text)
+
+        lvl_jc = OxmlElement('w:lvlJc')
+        lvl_jc.set(qn('w:val'), 'left')
+        lvl.append(lvl_jc)
+
+        pPr = OxmlElement('w:pPr')
+        ind = OxmlElement('w:ind')
+        ind.set(qn('w:left'), str(720 * (ilvl + 1)))
+        ind.set(qn('w:hanging'), '360')
+        pPr.append(ind)
+        lvl.append(pPr)
+
+        abstract_num.append(lvl)
+
+    numbering.insert(0, abstract_num)
+
+    existing_num_ids = [
+        int(n.get(qn('w:numId')))
+        for n in numbering.findall(qn('w:num'))
+    ]
+    num_id = max(existing_num_ids, default=0) + 1
+
+    num = OxmlElement('w:num')
+    num.set(qn('w:numId'), str(num_id))
+    abstract_ref = OxmlElement('w:abstractNumId')
+    abstract_ref.set(qn('w:val'), str(abstract_num_id))
+    num.append(abstract_ref)
+    numbering.append(num)
+
+    return num_id
+
+
+def attach_list_numbering(paragraph, num_id: int, ilvl: int):
+    """Attach numbering to a paragraph at the given indent level.
+
+    Spec §4.1 H3 Route B. Must be paired with register_multilevel_numbering.
+    """
+    pPr = paragraph._p.get_or_add_pPr()
+    existing = pPr.find(qn('w:numPr'))
+    if existing is not None:
+        pPr.remove(existing)
+    numPr = OxmlElement('w:numPr')
+    ilvl_el = OxmlElement('w:ilvl')
+    ilvl_el.set(qn('w:val'), str(ilvl))
+    numId_el = OxmlElement('w:numId')
+    numId_el.set(qn('w:val'), str(num_id))
+    numPr.append(ilvl_el)
+    numPr.append(numId_el)
+    pPr.append(numPr)
+
+
 def convert_md_to_doc(md_file: Path, output_file: Path, style: str = "elegant") -> Path:
    """Convert a single markdown file to DOCX.

@@ -0,0 +1,138 @@
+"""Tests for XML helper functions — borders, shading, numbering.
+
+These prove the EFFECT (XML structure lands in the right place), not the call.
+Each test unzips the docx and inspects word/document.xml directly.
+"""
+import zipfile
+import xml.etree.ElementTree as ET
+from pathlib import Path
+
+import pytest
+from docx import Document
+from docx.oxml import OxmlElement
+
+from md2doc import (
+    add_paragraph_bottom_border,
+    add_paragraph_shading,
+    add_cell_shading,
+    attach_list_numbering,
+    register_multilevel_numbering,
+)
+
+W_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+
+def get_doc_xml(doc):
+    tmp = Path(__file__).parent / "_tmp_helper_test.docx"
+    doc.save(tmp)
+    try:
+        with zipfile.ZipFile(tmp) as z:
+            xml_bytes = z.read("word/document.xml")
+        return ET.fromstring(xml_bytes)
+    finally:
+        tmp.unlink()
+
+
+def find_all(root, tag):
+    return root.findall(f".//{{{W_NS}}}{tag}")
+
+
+def test_add_paragraph_bottom_border_inserts_pBdr():
+    """H1: paragraph bottom border lands inside w:pPr as w:pBdr/w:bottom."""
+    doc = Document()
+    p = doc.add_paragraph()
+    add_paragraph_bottom_border(p, color="000000", size="12")
+    root = get_doc_xml(doc)
+    pBdr = find_all(root, "pBdr")
+    bottom = find_all(root, "bottom")
+    assert len(pBdr) >= 1, "w:pBdr missing"
+    assert len(bottom) >= 1, "w:bottom missing"
+    b = bottom[0]
+    assert b.get(f"{{{W_NS}}}color") == "000000"
+    assert b.get(f"{{{W_NS}}}sz") == "12"
+    assert b.get(f"{{{W_NS}}}val") == "single"
+
+
+def test_add_paragraph_shading_inserts_shd():
+    """H2: paragraph shading w:shd lands inside w:pPr with correct fill."""
+    doc = Document()
+    p = doc.add_paragraph()
+    add_paragraph_shading(p, fill="D9D9D9")
+    root = get_doc_xml(doc)
+    shd = find_all(root, "shd")
+    assert len(shd) >= 1, "w:shd missing"
+    assert shd[0].get(f"{{{W_NS}}}fill") == "D9D9D9"
+    assert shd[0].get(f"{{{W_NS}}}val") == "clear"
+
+
+def test_add_cell_shading_inserts_shd_in_tcPr():
+    """H4: cell shading w:shd lands inside w:tcPr."""
+    doc = Document()
+    table = doc.add_table(rows=2, cols=2)
+    cell = table.rows[0].cells[0]
+    add_cell_shading(cell, fill="4472C4")
+    root = get_doc_xml(doc)
+    tcPr_list = find_all(root, "tcPr")
+    shd_in_tc = [tc.find(f"{{{W_NS}}}shd") for tc in tcPr_list
+                 if tc.find(f"{{{W_NS}}}shd") is not None]
+    assert len(shd_in_tc) >= 1, "w:shd missing from w:tcPr"
+    assert shd_in_tc[0].get(f"{{{W_NS}}}fill") == "4472C4"
+
+
+def test_register_multilevel_numbering_creates_abstractNum_with_3_levels():
+    """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.
+    """
+    doc = Document()
+    num_id = register_multilevel_numbering(doc, levels=3, kind="bullet")
+    assert isinstance(num_id, int)
+
+    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)
+
+        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)"
+
+        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")
+
+        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()
+
+
+def test_attach_list_numbering_sets_numPr_with_ilvl():
+    """H3 Route B: paragraph gets w:numPr with w:ilvl and w:numId."""
+    doc = Document()
+    num_id = register_multilevel_numbering(doc, levels=3, kind="bullet")
+    p = doc.add_paragraph("nested item")
+    attach_list_numbering(p, num_id=num_id, ilvl=1)
+    root = get_doc_xml(doc)
+    numPr = find_all(root, "numPr")
+    ilvl = find_all(root, "ilvl")
+    numId_xml = find_all(root, "numId")
+    assert len(numPr) >= 1, "w:numPr missing"
+    assert len(ilvl) >= 1, "w:ilvl missing"
+    assert ilvl[0].get(f"{{{W_NS}}}val") == "1"
+    assert len(numId_xml) >= 1, "w:numId missing"