mkdocs2confluence 0.7.1__tar.gz → 0.7.4__tar.gz

{mkdocs2confluence-0.7.1/src/mkdocs2confluence.egg-info → mkdocs2confluence-0.7.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mkdocs2confluence
-Version: 0.7.1
+Version: 0.7.4
 Summary: Publish MkDocs Material pages to Confluence Cloud — admonitions, Mermaid diagrams, tabs, page properties and more
 Author: Anders Hybertz
 License: GPL-3.0-or-later

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mkdocs2confluence"
-version = "0.7.1"
+version = "0.7.4"
 description = "Publish MkDocs Material pages to Confluence Cloud — admonitions, Mermaid diagrams, tabs, page properties and more"
 readme = "README.md"
 license = { text = "GPL-3.0-or-later" }

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4/src/mkdocs2confluence.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mkdocs2confluence
-Version: 0.7.1
+Version: 0.7.4
 Summary: Publish MkDocs Material pages to Confluence Cloud — admonitions, Mermaid diagrams, tabs, page properties and more
 Author: Anders Hybertz
 License: GPL-3.0-or-later

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/src/mkdocs_to_confluence/emitter/xhtml.py

@@ -48,6 +48,7 @@ from mkdocs_to_confluence.ir.nodes import (
     OrderedList,
     Paragraph,
     RawHTML,
+    RawInlineHtml,
     Section,
     StrikethroughNode,
     SubscriptNode,
@@ -613,6 +614,8 @@ def _emit_inline(node: IRNode) -> str:
     if isinstance(node, InlineHtmlNode):
         open_tag, close_tag = _INLINE_HTML_MAP.get(node.tag, ("<span>", "</span>"))
         return f"{open_tag}{_emit_inlines(node.children)}{close_tag}"
+    if isinstance(node, RawInlineHtml):
+        return node.html_str
     # Fallback: emit unknown inline nodes as escaped repr
     return html.escape(repr(node))
 

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/src/mkdocs_to_confluence/ir/__init__.py

@@ -44,6 +44,7 @@ from mkdocs_to_confluence.ir.nodes import (
     OrderedList,
     Paragraph,
     RawHTML,
+    RawInlineHtml,
     # Block nodes
     Section,
     StrikethroughNode,
@@ -81,6 +82,7 @@ __all__ = [
     "ImageNode",
     "LineBreakNode",
     "InlineHtmlNode",
+    "RawInlineHtml",
     "InsertNode",
     # Block
     "Section",

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/src/mkdocs_to_confluence/ir/nodes.py

@@ -125,6 +125,18 @@ class InlineHtmlNode(IRNode):
     children: tuple[IRNode, ...]
 
 
+@dataclass(frozen=True)
+class RawInlineHtml(IRNode):
+    """A raw inline HTML element passed through verbatim.
+
+    Used for ``<span class="...">``, ``<abbr>``, and other inline HTML that has
+    no semantic IR equivalent.  The emitter outputs ``html_str`` unchanged; PDF
+    and browser-preview renderers handle it natively.
+    """
+
+    html_str: str
+
+
 @dataclass(frozen=True)
 class ImageNode(IRNode):
     """An image reference.

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/src/mkdocs_to_confluence/parser/markdown.py

@@ -49,6 +49,7 @@ a proper library (e.g. ``markdown-it-py``) later without touching the IR.
 from __future__ import annotations
 
 import contextlib
+import html
 import re
 from dataclasses import dataclass, field
 from typing import Union
@@ -79,6 +80,7 @@ from mkdocs_to_confluence.ir.nodes import (
     MermaidDiagram,
     OrderedList,
     Paragraph,
+    RawInlineHtml,
     Section,
     StrikethroughNode,
     SubscriptNode,
@@ -784,7 +786,7 @@ def _scan_inline(text: str, fn_map: dict[str, int] | None = None) -> list[IRNode
     def flush() -> None:
         nonlocal buf
         if buf:
-            nodes.append(TextNode(text=buf))
+            nodes.append(TextNode(text=html.unescape(buf)))
             buf = ""
 
     while i < n:
@@ -962,6 +964,16 @@ def _scan_inline(text: str, fn_map: dict[str, int] | None = None) -> list[IRNode
                     i = close_idx + len(close)
                     continue
 
+            # Generic inline HTML with attributes (e.g. <span class="...">) — pass through verbatim
+            generic_m = re.match(
+                r"<([a-z][a-z0-9]*)\b[^>]*>.*?</\1>", text[i:], re.DOTALL | re.IGNORECASE
+            )
+            if generic_m:
+                flush()
+                nodes.append(RawInlineHtml(html_str=generic_m.group(0)))
+                i += len(generic_m.group(0))
+                continue
+
         # Bare URL autolink: https:// or http://
         if text[i : i + 4] in ("http", "ftp:"):
             url_m = re.match(r"(https?://|ftp://)[^\s<>\[\]\"']+", text[i:])

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/src/mkdocs_to_confluence/pdf/render.py

@@ -20,7 +20,7 @@ from mkdocs_to_confluence.preview.render import render_html
 _PDF_CSS = """
 @page {
   size: A4 portrait;
-  margin: 25mm 20mm 25mm 20mm;
+  margin: 18mm 15mm 18mm 20mm;
   @bottom-center {
     content: counter(page);
     font-size: 9pt;
@@ -115,7 +115,10 @@ body {
 /* ── Chapters ── */
 article {
   page-break-before: always;
-  string-set: section-title attr(data-title);
+}
+.pdf-chapter-title {
+  display: none;
+  string-set: section-title content();
 }
 article h1 { font-size: 18pt; color: #0052cc; margin-top: 0; }
 article h2 { font-size: 13pt; color: #0052cc; }
@@ -249,7 +252,7 @@ def build_pdf_html(
 
     # Chapters
     chapter_html = "".join(
-        '<article id="{anchor}" data-title="{title}">\n{body}\n</article>\n'.format(
+        '<article id="{anchor}">\n<span class="pdf-chapter-title">{title}</span>\n{body}\n</article>\n'.format(
             anchor=_anchor(title),
             title=_html.escape(title),
             body=render_html(xhtml),

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/src/mkdocs_to_confluence/preprocess/icons.py

@@ -24,6 +24,60 @@ _ICON_RE = re.compile(
     r":(?:material|fontawesome|octicons|simple|twemoji)-[a-z0-9-]+:"
 )
 
+# Matches bare GitHub/Python-Markdown emoji shortcodes: :rotating_light:, :wrench: etc.
+# Requires at least one underscore or is a known single-word name.
+# Must not overlap with _ICON_RE (those all contain a hyphenated prefix).
+_STANDARD_EMOJI_RE = re.compile(r":([a-z][a-z0-9_]*):")
+
+# Bare emoji shortcode → BMP Unicode symbol (or "" to strip silently).
+# BMP-only where a reasonable equivalent exists; supplementary-plane emoji
+# are excluded to preserve MySQL utf8 Confluence compatibility.
+_STANDARD_EMOJI_MAP: dict[str, str] = {
+    # Alerts / status
+    "warning": "⚠",                # U+26A0
+    "rotating_light": "⚠",         # U+26A0  (🚨 U+1F6A8 is supplementary)
+    "octagonal_sign": "⛔",         # U+26D4
+    "no_entry": "⛔",               # U+26D4
+    "no_entry_sign": "⛔",
+    "stop_sign": "⛔",
+    "information_source": "ℹ",     # U+2139
+    # Checkmarks / marks
+    "white_check_mark": "✓",       # U+2713  (✅ supplementary)
+    "heavy_check_mark": "✓",       # U+2713
+    "x": "✗",                      # U+2717  (❌ supplementary)
+    "heavy_multiplication_x": "✗",
+    # Objects — tools
+    "wrench": "⚙",                 # U+2699  (🔧 supplementary)
+    "gear": "⚙",                   # U+2699
+    "hammer": "",                   # 🔨 supplementary, no BMP equiv — strip
+    "hammer_and_wrench": "",
+    # Work / business
+    "briefcase": "",                # 💼 supplementary — strip
+    # Nature / miscellaneous
+    "star": "★",                   # U+2605
+    "star2": "★",
+    "rocket": "",                   # 🚀 supplementary — strip
+    "construction": "",             # 🚧 supplementary — strip
+    "tada": "",
+    "trophy": "",
+    "thinking": "",
+    "smile": "",
+    "laughing": "",
+    "heart": "♥",                  # U+2665
+    "fire": "",                     # 🔥 supplementary — strip
+    "zap": "",                      # ⚡ U+26A1 BMP
+    "bulb": "",
+    "computer": "",
+    "notebook": "",
+    "memo": "",
+    "clipboard": "",
+    "link": "",
+    "label": "",
+    "bookmark": "",
+    "chart_with_upwards_trend": "",
+    "bar_chart": "",
+}
+
 # Keyword → symbol.  Keys must be lowercase single words (icon name segments).
 # ALL values must be BMP characters (U+0000–U+FFFF) or "" (strip silently).
 # Ordered so earlier, more-specific entries take priority where ambiguous.
@@ -175,6 +229,19 @@ def _resolve(parts: list[str]) -> str:
     return ""
 
 
+def _replace_standard_emoji(text: str) -> str:
+    """Replace standard emoji shortcodes (e.g. ``:rotating_light:``) with BMP symbols."""
+
+    def _replace(m: re.Match[str]) -> str:
+        name = m.group(1)
+        if name in _STANDARD_EMOJI_MAP:
+            return _STANDARD_EMOJI_MAP[name]
+        # Unknown shortcode — leave it intact (may be valid Markdown syntax).
+        return m.group(0)
+
+    return _STANDARD_EMOJI_RE.sub(_replace, text)
+
+
 def strip_icon_shortcodes(text: str) -> str:
     """Replace icon shortcodes with emoji or strip them silently.
 
@@ -194,4 +261,4 @@ def strip_icon_shortcodes(text: str) -> str:
         parts = name.split("-")
         return _resolve(parts)
 
-    return _ICON_RE.sub(_replace, text)
+    return _ICON_RE.sub(_replace, _replace_standard_emoji(text))

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/src/mkdocs_to_confluence/preview/render.py

@@ -72,7 +72,8 @@ _AC_ANCHOR_ATTR_RE = re.compile(r'ac:anchor="(?P<anchor>[^"]*)"')
 
 
 def _params(macro_body: str) -> dict[str, str]:
-    return {m.group(1): m.group(2) for m in _PARAM_RE.finditer(macro_body)}
+    # Values are XML text content (e.g. "&amp;" for "&"); unescape to plain text.
+    return {m.group(1): _html.unescape(m.group(2)) for m in _PARAM_RE.finditer(macro_body)}
 
 
 def _cdata(macro_body: str) -> str:

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/tests/test_icons.py

@@ -157,3 +157,49 @@ class TestInlineReplacement:
     def test_no_icons_unchanged(self) -> None:
         text = "No icons here, just plain text."
         assert strip_icon_shortcodes(text) == text
+
+
+class TestStandardEmoji:
+    """Tests for bare emoji shortcodes like :rotating_light:."""
+
+    def test_rotating_light_maps_to_warning(self) -> None:
+        assert strip_icon_shortcodes(":rotating_light:") == "⚠"
+
+    def test_octagonal_sign_maps_to_no_entry(self) -> None:
+        assert strip_icon_shortcodes(":octagonal_sign:") == "⛔"
+
+    def test_wrench_maps_to_gear(self) -> None:
+        assert strip_icon_shortcodes(":wrench:") == "⚙"
+
+    def test_information_source_maps_to_info(self) -> None:
+        assert strip_icon_shortcodes(":information_source:") == "ℹ"
+
+    def test_white_check_mark_maps_to_check(self) -> None:
+        assert strip_icon_shortcodes(":white_check_mark:") == "✓"
+
+    def test_x_maps_to_cross(self) -> None:
+        assert strip_icon_shortcodes(":x:") == "✗"
+
+    def test_briefcase_stripped(self) -> None:
+        assert strip_icon_shortcodes(":briefcase:") == ""
+
+    def test_unknown_shortcode_unchanged(self) -> None:
+        assert strip_icon_shortcodes(":unknown_emoji_xyz:") == ":unknown_emoji_xyz:"
+
+    def test_emoji_in_sentence(self) -> None:
+        result = strip_icon_shortcodes("Status: :white_check_mark: Done")
+        assert result == "Status: ✓ Done"
+
+    def test_material_icon_not_double_processed(self) -> None:
+        # :material-check-circle: should still go through the prefixed path
+        result = strip_icon_shortcodes(":material-check-circle:")
+        assert result == "✓"
+
+    def test_all_standard_emoji_values_are_bmp(self) -> None:
+        from mkdocs_to_confluence.preprocess.icons import _STANDARD_EMOJI_MAP
+        for name, symbol in _STANDARD_EMOJI_MAP.items():
+            for ch in symbol:
+                assert ord(ch) <= 0xFFFF, (
+                    f"_STANDARD_EMOJI_MAP[{name!r}] contains supplementary-plane "
+                    f"character U+{ord(ch):04X} — use BMP or empty string"
+                )

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/tests/test_parser.py

@@ -1181,6 +1181,25 @@ class TestInlineHtmlParsing:
         raw = "".join(n.text for n in para.children if isinstance(n, TextNode))
         assert "<mark>" in raw
 
+    def test_span_with_class_produces_raw_inline_html(self) -> None:
+        from mkdocs_to_confluence.ir import RawInlineHtml
+        para = first(parse('Text <span class="crit-level">C0</span> end\n'), Paragraph)
+        node = next(n for n in para.children if isinstance(n, RawInlineHtml))
+        assert node.html_str == '<span class="crit-level">C0</span>'
+
+    def test_span_without_attrs_not_treated_as_raw(self) -> None:
+        # Plain <span> (no attributes) is not in the known-tag list either,
+        # so it falls through to generic handler.
+        from mkdocs_to_confluence.ir import RawInlineHtml
+        para = first(parse("<span>plain</span>\n"), Paragraph)
+        assert any(isinstance(n, RawInlineHtml) for n in para.children)
+
+    def test_raw_inline_html_emitted_verbatim(self) -> None:
+        from mkdocs_to_confluence.emitter.xhtml import emit
+        nodes = parse('| Col |\n|-----|\n| <span class="hl">X</span> |\n')
+        xhtml = emit(nodes)
+        assert '<span class="hl">X</span>' in xhtml
+
 
 class TestKeyboardKeys:
     def test_single_key(self) -> None:

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/tests/test_pdf.py

@@ -166,6 +166,11 @@ class TestWritePdf:
 class TestPdfCli:
     """Tests for the `pdf` subcommand in cli.py."""
 
+    @pytest.fixture(autouse=True)
+    def _skip_macos_reexec(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        """Suppress the macOS DYLD re-exec so tests don't try to exec pytest."""
+        monkeypatch.setenv("_MK2CONF_DYLD_SET", "1")
+
     def _run(self, argv: list[str], config_path: Path) -> None:
         from mkdocs_to_confluence.cli import main
         main(["--"] + argv if argv[0].startswith("-") else argv)

{mkdocs2confluence-0.7.1 → mkdocs2confluence-0.7.4}/tests/test_preview.py

@@ -87,6 +87,17 @@ class TestRenderHtml:
         assert "Show more" in out
         assert "hidden content" in out
 
+    def test_expand_title_with_ampersand_not_double_escaped(self) -> None:
+        xhtml = (
+            '<ac:structured-macro ac:name="expand">'
+            '<ac:parameter ac:name="title">Architecture &amp; Resilience</ac:parameter>'
+            "<ac:rich-text-body><p>content</p></ac:rich-text-body>"
+            "</ac:structured-macro>"
+        )
+        out = render_html(xhtml)
+        assert "Architecture &amp; Resilience" in out
+        assert "&amp;amp;" not in out
+
     def test_nested_code_inside_warning(self) -> None:
         xhtml = (
             '<ac:structured-macro ac:name="warning">'