From 21b3a7a77d81e1b2c699e91d8061356776e443e7 Mon Sep 17 00:00:00 2001
From: Sebastian Petrescu <sebastian@runningwolf.com>
Date: Tue, 28 Jul 2026 10:27:02 +0300
Subject: [PATCH] feat(md2doc): table, pre, blockquote, hr renderers

---
 md2doc.py                   | 65 ++++++++++++++++++++++++++++++++
 tests/test_md2doc_blocks.py | 74 +++++++++++++++++++++++++++++++++++++
 2 files changed, 139 insertions(+)
 create mode 100644 tests/test_md2doc_blocks.py

diff --git a/md2doc.py b/md2doc.py
index e6c62db..c3f6fbc 100644
--- a/md2doc.py
+++ b/md2doc.py
@@ -365,6 +365,71 @@ def _render_list(doc, node, style: dict, level: int = 0, num_state: dict = None)
             _render_list(doc, nested, style=style, level=level + 1, num_state=num_state)
 
 
+def _render_table(doc, node, style: dict):
+    """Render <table> with header row shading."""
+    header_fill = style.get("table_header_fill", "1e3a8a")
+
+    rows = node.find_all("tr")
+    if not rows:
+        return
+
+    cols = max(len(row.find_all(["th", "td"])) for row in rows)
+    table = doc.add_table(rows=len(rows), cols=cols)
+    table.style = 'Table Grid'
+
+    for i, row in enumerate(rows):
+        cells = row.find_all(["th", "td"])
+        is_header = row.parent.name == "thead" or any(c.name == "th" for c in cells)
+        for j, cell in enumerate(cells):
+            if j >= cols:
+                break
+            tc = table.rows[i].cells[j]
+            tc.text = cell.get_text(strip=True)
+            if is_header:
+                add_cell_shading(tc, fill=header_fill)
+
+
+def _render_pre(doc, node, style: dict):
+    """Render <pre> (code block) — shaded background + monospace font.
+
+    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). Trailing empty line from markdown's final \\n is dropped.
+    """
+    code_fill = style.get("code_fill", "f7f8fa")
+    text = node.get_text()
+    lines = text.split("\n")
+    while lines and lines[-1] == "":
+        lines.pop()
+
+    p = doc.add_paragraph()
+    for i, line in enumerate(lines):
+        if i > 0:
+            p.add_run().add_break()
+        run = p.add_run(line)
+        run.font.name = "Menlo"
+        run.font.size = Pt(8)
+    add_paragraph_shading(p, fill=code_fill)
+
+
+def _render_blockquote(doc, node, style: dict):
+    """Render <blockquote> — left indent + italic + shading."""
+    quote_fill = style.get("blockquote_fill", "f7f8fa")
+    text = node.get_text(strip=True)
+
+    p = doc.add_paragraph()
+    p.paragraph_format.left_indent = Cm(1)
+    run = p.add_run(text)
+    run.italic = True
+    add_paragraph_shading(p, fill=quote_fill)
+
+
+def _render_hr(doc, node, style: dict):
+    """Render <hr> as empty paragraph with bottom border."""
+    p = doc.add_paragraph()
+    add_paragraph_bottom_border(p, color="d8d8d8", size="6")
+
+
 def convert_md_to_doc(md_file: Path, output_file: Path, style: str = "elegant") -> Path:
     """Convert a single markdown file to DOCX.
 
diff --git a/tests/test_md2doc_blocks.py b/tests/test_md2doc_blocks.py
new file mode 100644
index 0000000..9d37725
--- /dev/null
+++ b/tests/test_md2doc_blocks.py
@@ -0,0 +1,74 @@
+"""Tests for block-level element renderers."""
+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_table, _render_pre, _render_blockquote, _render_hr
+
+W_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+
+def get_doc_xml(doc):
+    tmp = Path(__file__).parent / "_tmp_blocks.docx"
+    doc.save(tmp)
+    try:
+        with zipfile.ZipFile(tmp) as z:
+            return ET.fromstring(z.read("word/document.xml"))
+    finally:
+        tmp.unlink()
+
+
+def test_table_renders_with_header_shading():
+    html = """
+    <table>
+      <thead><tr><th>Name</th><th>Value</th></tr></thead>
+      <tbody>
+        <tr><td>A</td><td>1</td></tr>
+      </tbody>
+    </table>
+    """
+    doc = Document()
+    node = BeautifulSoup(html, "html.parser").find("table")
+    _render_table(doc, node, style=STYLES["elegant"])
+    root = get_doc_xml(doc)
+    trs = list(root.iter(f"{{{W_NS}}}tr"))
+    assert len(trs) == 2
+    shds = list(root.iter(f"{{{W_NS}}}shd"))
+    assert len(shds) >= 2  # at least 2 header cells
+
+
+def test_pre_renders_with_shading():
+    html = '<pre><code>print("hello")</code></pre>'
+    doc = Document()
+    node = BeautifulSoup(html, "html.parser").find("pre")
+    _render_pre(doc, node, style=STYLES["elegant"])
+    root = get_doc_xml(doc)
+    shds = list(root.iter(f"{{{W_NS}}}shd"))
+    assert len(shds) >= 1
+    texts = [t.text for t in root.iter(f"{{{W_NS}}}t")]
+    assert any('print' in t for t in texts)
+
+
+def test_blockquote_renders_with_indent_and_italic():
+    html = "<blockquote>A quoted passage</blockquote>"
+    doc = Document()
+    node = BeautifulSoup(html, "html.parser").find("blockquote")
+    _render_blockquote(doc, node, style=STYLES["elegant"])
+    root = get_doc_xml(doc)
+    italic_el = list(root.iter(f"{{{W_NS}}}i"))
+    assert len(italic_el) >= 1
+    indents = list(root.iter(f"{{{W_NS}}}ind"))
+    assert len(indents) >= 1
+
+
+def test_hr_renders_as_paragraph_with_bottom_border():
+    html = "<hr/>"
+    doc = Document()
+    node = BeautifulSoup(html, "html.parser").find("hr")
+    _render_hr(doc, node, style=STYLES["elegant"])
+    root = get_doc_xml(doc)
+    bottoms = list(root.iter(f"{{{W_NS}}}bottom"))
+    assert len(bottoms) >= 1