feat(md2doc): heading and paragraph renderers with inline formatting

2026-07-28 10:24:12 +03:00
parent 322eaad887
commit 36b6a16fd8
2 changed files with 200 additions and 0 deletions
@@ -232,6 +232,97 @@ def attach_list_numbering(paragraph, num_id: int, ilvl: int):
    pPr.append(numPr)


+# ---------------------------------------------------------------------------
+# Element renderers (walk BeautifulSoup DOM → emit docx elements)
+# ---------------------------------------------------------------------------
+
+
+def _warn_skip_image(node):
+    """Warn to stderr when an <img> is encountered (out of scope per spec §10).
+
+    Defined early so _render_paragraph (used in Task 4) and convert_md_to_doc
+    (Task 7) can both reference it without forward-declaration issues.
+    """
+    src = node.get("src", "(no src)")
+    print(f"Warning: image skipped (out of scope): {src}", file=sys.stderr)
+
+
+def _add_run_shading(run, fill: str):
+    """Apply background shading to a run (for inline <code> highlight).
+
+    Inserts w:shd inside w:rPr.
+    """
+    rPr = run._r.get_or_add_rPr()
+    shd = OxmlElement('w:shd')
+    shd.set(qn('w:val'), 'clear')
+    shd.set(qn('w:color'), 'auto')
+    shd.set(qn('w:fill'), fill)
+    rPr.append(shd)
+
+
+def _render_heading(doc, node, level: int, style: dict):
+    """Render <h1>-<h4> as Word Heading paragraphs.
+
+    H1 also gets a bottom paragraph border (per md2pdf pattern).
+    Applies COMMON['keep_with_next_headings'] so headings don't orphan at page bottom.
+    Applies COMMON['page_break_before_h1'] if True (style-overridable).
+    """
+    text = node.get_text(strip=True)
+    p = doc.add_heading(level=level)
+    p.add_run(text)
+
+    # Apply style-specific color
+    color_hex = style.get("heading_color", "000000")
+    for run in p.runs:
+        run.font.color.rgb = RGBColor.from_string(color_hex)
+
+    # Wire COMMON config: keep heading with next paragraph
+    if COMMON.get("keep_with_next_headings", True):
+        p.paragraph_format.keep_with_next = True
+
+    # H1 page-break-before if style overrides COMMON default
+    if level == 1 and style.get("page_break_before_h1", COMMON.get("page_break_before_h1", False)):
+        p.paragraph_format.page_break_before = True
+
+    if level == 1:
+        add_paragraph_bottom_border(p, color=color_hex, size="12")
+
+
+def _render_paragraph(doc, node, style: dict):
+    """Render <p> as a Word paragraph, preserving inline formatting (strong, em, code, a).
+
+    Also handles <img> children — prints stderr warning and skips (spec §10).
+    """
+    p = doc.add_paragraph()
+    code_fill = style.get("code_fill", "f5f5f5")
+
+    def _add_runs(element):
+        for child in element.children:
+            if isinstance(child, str):
+                p.add_run(child)
+            elif child.name == "strong" or child.name == "b":
+                r = p.add_run(child.get_text())
+                r.bold = True
+            elif child.name == "em" or child.name == "i":
+                r = p.add_run(child.get_text())
+                r.italic = True
+            elif child.name == "code":
+                r = p.add_run(child.get_text())
+                r.font.name = "Menlo"
+                _add_run_shading(r, fill=code_fill)
+            elif child.name == "a":
+                r = p.add_run(child.get_text())
+                r.underline = True
+                r.font.color.rgb = RGBColor.from_string(style.get("link_color", "0000EE"))
+            elif child.name == "img":
+                _warn_skip_image(child)
+            else:
+                # Unknown inline — recurse
+                _add_runs(child)
+
+    _add_runs(node)
+
+
 def convert_md_to_doc(md_file: Path, output_file: Path, style: str = "elegant") -> Path:
    """Convert a single markdown file to DOCX.

@@ -0,0 +1,109 @@
+"""Tests for heading and paragraph renderers — verify the EFFECT (text + style land)."""
+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_heading, _render_paragraph
+
+W_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+
+def get_doc_xml(doc):
+    tmp = Path(__file__).parent / "_tmp_render.docx"
+    doc.save(tmp)
+    try:
+        with zipfile.ZipFile(tmp) as z:
+            return ET.fromstring(z.read("word/document.xml"))
+    finally:
+        tmp.unlink()
+
+
+def test_render_h1_uses_heading1_style_and_text():
+    doc = Document()
+    style = STYLES["elegant"]
+    node = BeautifulSoup("<h1>My Title</h1>", "html.parser").find("h1")
+    _render_heading(doc, node, level=1, style=style)
+    root = get_doc_xml(doc)
+    pStyles = [p.text for p in root.iter(f"{{{W_NS}}}pStyle")]
+    assert "Heading1" in pStyles
+    texts = [t.text for t in root.iter(f"{{{W_NS}}}t")]
+    assert "My Title" in texts
+
+
+def test_render_h1_has_bottom_border():
+    doc = Document()
+    style = STYLES["elegant"]
+    node = BeautifulSoup("<h1>Title</h1>", "html.parser").find("h1")
+    _render_heading(doc, node, level=1, style=style)
+    root = get_doc_xml(doc)
+    bottoms = list(root.iter(f"{{{W_NS}}}bottom"))
+    assert len(bottoms) >= 1, "h1 should have bottom border"
+
+
+def test_render_h1_applies_style_heading_color():
+    """Heading color should come from STYLES[style]['heading_color']."""
+    doc = Document()
+    style = STYLES["report"]
+    node = BeautifulSoup("<h1>Title</h1>", "html.parser").find("h1")
+    _render_heading(doc, node, level=1, style=style)
+    root = get_doc_xml(doc)
+    colors = [c.get(f"{{{W_NS}}}val") for c in root.iter(f"{{{W_NS}}}color")]
+    assert "1e3a8a" in colors, f"expected heading color 1e3a8a from 'report' style, got {colors}"
+
+
+def test_render_heading_applies_keep_with_next():
+    """COMMON['keep_with_next_headings'] should set paragraph_format.keep_with_next=True."""
+    doc = Document()
+    style = STYLES["elegant"]
+    node = BeautifulSoup("<h2>Section</h2>", "html.parser").find("h2")
+    _render_heading(doc, node, level=2, style=style)
+    root = get_doc_xml(doc)
+    keep_next = list(root.iter(f"{{{W_NS}}}keepNext"))
+    assert len(keep_next) >= 1, "expected w:keepNext for heading"
+
+
+def test_render_h2_no_bottom_border():
+    """Only h1 gets border; h2/h3/h4 don't."""
+    doc = Document()
+    style = STYLES["elegant"]
+    node = BeautifulSoup("<h2>Subtitle</h2>", "html.parser").find("h2")
+    _render_heading(doc, node, level=2, style=style)
+    root = get_doc_xml(doc)
+    bottoms = list(root.iter(f"{{{W_NS}}}bottom"))
+    assert len(bottoms) == 0
+
+
+def test_render_paragraph_emits_text():
+    doc = Document()
+    style = STYLES["elegant"]
+    node = BeautifulSoup("<p>Hello world</p>", "html.parser").find("p")
+    _render_paragraph(doc, node, style=style)
+    root = get_doc_xml(doc)
+    texts = [t.text for t in root.iter(f"{{{W_NS}}}t")]
+    assert "Hello world" in texts
+
+
+def test_render_paragraph_handles_bold_inline():
+    doc = Document()
+    style = STYLES["elegant"]
+    node = BeautifulSoup("<p>This is <strong>bold</strong> text</p>", "html.parser").find("p")
+    _render_paragraph(doc, node, style=style)
+    root = get_doc_xml(doc)
+    b_el = list(root.iter(f"{{{W_NS}}}b"))
+    assert len(b_el) >= 1
+
+
+def test_render_paragraph_handles_inline_code_with_shading():
+    """Inline <code> should have monospace font AND run-level shading."""
+    doc = Document()
+    style = STYLES["elegant"]
+    node = BeautifulSoup("<p>See <code>foo()</code> here</p>", "html.parser").find("p")
+    _render_paragraph(doc, node, style=style)
+    root = get_doc_xml(doc)
+    rPr_list = list(root.iter(f"{{{W_NS}}}rPr"))
+    shd_in_runs = [r.find(f"{{{W_NS}}}shd") for r in rPr_list
+                   if r.find(f"{{{W_NS}}}shd") is not None]
+    assert len(shd_in_runs) >= 1, "expected w:shd inside a w:rPr for inline code"