refactor: #85 T9 extrait realtime et render vers modules dedies (comportement inchange)

backend/render.py

@@ -0,0 +1,207 @@
+"""Markdown rendering pipeline (ROADMAP #85, tranche 9).
+
+Helpers extraits de :mod:`backend.main` sans changement de comportement :
+slugification des headings, IDs d'ancrage, rendu mistune singleton,
+wikilinks, normalisation des sauts de ligne et pipeline complet
+:func:`_render_markdown` (rendu + sanitizer XSS BUG-021).
+
+Les noms gardent leur préfixe ``_`` d'origine pour un déplacement
+strictement verbatim (tests et routers pointent ici désormais).
+"""
+
+from __future__ import annotations
+
+import html as html_mod
+import re
+import unicodedata
+from pathlib import Path
+
+import mistune
+
+from backend.image_processor import preprocess_images
+from backend.indexer import find_file_in_index, get_vault_data
+from backend.secret_redactor import redact_file_content
+from backend.services.sanitizer import sanitize_html
+
+
+def _heading_slugify(text: str) -> str:
+    """Generate a URL-safe slug from heading text.
+
+    Matches the JavaScript slugify algorithm exactly using
+    Unicode-aware character classification:
+    1. Strip HTML tags (e.g. wikilink spans rendered inside headings)
+    2. Decode HTML entities (e.g. ``&`` → ``&``)
+    3. Lowercase
+    4. NFD normalize + strip combining marks
+    5. Keep only Unicode letters, numbers, spaces, hyphens
+    6. Replace spaces with hyphens, collapse multiple hyphens
+
+    Args:
+        text: The heading text content (may contain inline HTML).
+
+    Returns:
+        A URL-safe slug string.
+    """
+    # Strip any inline HTML so it does not pollute the slug
+    text = re.sub(r"<[^>]+>", "", text)
+    # Decode HTML entities so &amp; becomes & before slugification
+    text = html_mod.unescape(text)
+    text = text.lower()
+    text = unicodedata.normalize("NFD", text)
+    text = "".join(ch for ch in text if not unicodedata.combining(ch))
+    # Unicode-aware: keep letters (L*), numbers (N*), spaces, and hyphens
+    cleaned = []
+    for ch in text:
+        cat = unicodedata.category(ch)
+        if cat.startswith('L') or cat.startswith('N') or ch in (' ', '-'):
+            cleaned.append(ch)
+    text = "".join(cleaned)
+    text = re.sub(r"\s+", "-", text)
+    text = re.sub(r"-+", "-", text)
+    result = text.strip("-")
+    return result if result else "heading"
+
+
+def _add_heading_ids(html: str) -> str:
+    """Post-process rendered HTML to add IDs to heading tags.
+
+    Adds an ``id`` attribute to every ``<h1>`` through ``<h6>`` tag
+    using a slug generated from the heading's text content.
+    Duplicate slugs get a ``-2``, ``-3``, etc. suffix.
+
+    Args:
+        html: Rendered HTML string.
+
+    Returns:
+        HTML with heading IDs injected.
+    """
+    used_ids: dict[str, int] = {}
+
+    def _replace_heading(match):
+        tag = match.group(1)
+        content = match.group(2)
+        slug = _heading_slugify(content)
+        count = used_ids.get(slug, 0)
+        used_ids[slug] = count + 1
+        if count > 0:
+            slug = f"{slug}-{count + 1}"
+        return f'<{tag} id="{slug}">{content}</{tag}>'
+
+    # Match h1-h6 tags with text content (no existing id attribute)
+    return re.sub(
+        r'<(h[1-6])>([^<]*(?:<(?!/?h[1-6])[^<]*)*)</h[1-6]>',
+        _replace_heading,
+        html,
+    )
+
+
+# Cached mistune renderer — avoids re-creating on every request
+_markdown_renderer = mistune.create_markdown(
+    escape=False,
+    plugins=["table", "strikethrough", "footnotes", "task_lists"],
+)
+
+
+def _convert_wikilinks(content: str, current_vault: str) -> str:
+    """Convert ``[[wikilinks]]`` and ``[[target|display]]`` to clickable HTML.
+
+    Supports:
+    - Internal file links: ``[[My Note]]`` / ``[[My Note|display]]``
+    - Same-document anchors: ``[[#Heading]]`` / ``[[#Heading|display]]``
+
+    Resolved file links get a ``data-vault`` / ``data-path`` attribute pair.
+    Anchor links target the slugified heading ID in the current document.
+    Unresolved links are rendered as ``<span class="wikilink-missing">``.
+
+    Args:
+        content: Markdown string potentially containing wikilinks.
+        current_vault: Active vault name for resolution priority.
+
+    Returns:
+        Markdown string with wikilinks replaced by HTML anchors.
+    """
+    def _replace(match):
+        target = match.group(1).strip()
+        display = match.group(2).strip() if match.group(2) else target
+
+        # Same-document anchor link: [[#Heading|display]]
+        if target.startswith("#"):
+            anchor_text = target[1:].strip()
+            anchor_slug = _heading_slugify(anchor_text)
+            link_display = display if display != target else anchor_text
+            return f'<a class="wikilink-anchor" href="#{anchor_slug}">{link_display}</a>'
+
+        found = find_file_in_index(target, current_vault)
+        if found:
+            return (
+                f'<a class="wikilink" href="#" '
+                f'data-vault="{found["vault"]}" '
+                f'data-path="{found["path"]}">{display}</a>'
+            )
+        return f'<span class="wikilink-missing">{display}</span>'
+
+    pattern = r'\[\[([^\]|]+)(?:\|([^\]]+))?\]\]'
+    return re.sub(pattern, _replace, content)
+
+
+def _normalize_line_breaks(text: str) -> str:
+    """Convert single newlines to hard breaks (matching Obsidian default behavior).
+
+    In standard Markdown, a single ``\\n`` is a "soft break" — it renders as a space,
+    not a visible line break.  Obsidian defaults to treating single newlines as hard
+    breaks (equivalent to ``<br>``).  This function pre-processes the Markdown source
+    so that mistune renders standalone lines on separate rows, while still honouring
+    blank lines as paragraph separators.
+
+    Fenced code blocks (`` ``` ``) are left untouched so their internal newlines are
+    preserved verbatim.
+    """
+    parts = re.split(r"(```[\s\S]*?```)", text)
+    for i, part in enumerate(parts):
+        if part.startswith("```"):
+            continue  # Protect fenced code blocks
+        # Single \n (not preceded or followed by another \n) → two spaces + \n
+        parts[i] = re.sub(r"(?<!\n)\n(?!\n)", "  \n", part)
+    return "".join(parts)
+
+
+def _render_markdown(raw_md: str, vault_name: str, current_file_path: Path | None = None) -> str:
+    """Render a markdown string to HTML with wikilink and image support.
+
+    Uses the cached singleton mistune renderer for performance.
+
+    Args:
+        raw_md: Raw markdown text (frontmatter already stripped).
+        vault_name: Current vault for wikilink resolution context.
+        current_file_path: Absolute path to the current markdown file.
+
+    Returns:
+        HTML string.
+    """
+    # Get vault data for image resolution
+    vault_data = get_vault_data(vault_name)
+    vault_root = Path(vault_data["path"]) if vault_data else None
+    attachments_path = vault_data.get("config", {}).get("attachmentsPath") if vault_data else None
+
+    # Redact secrets before rendering (P0 security)
+    raw_md = redact_file_content(raw_md, str(current_file_path) if current_file_path else "")
+
+    # Preprocess images first
+    if vault_root:
+        raw_md = preprocess_images(raw_md, vault_name, vault_root, current_file_path, attachments_path)
+
+    # Convert wikilinks
+    converted = _convert_wikilinks(raw_md, vault_name)
+
+    # Normalize line breaks to match Obsidian behavior (single \n → hard break)
+    converted = _normalize_line_breaks(converted)
+
+    rendered = _markdown_renderer(converted)
+
+    # Add heading IDs for TOC navigation
+    rendered = _add_heading_ids(rendered)
+
+    # Sanitize: raw HTML in vault content must never reach the DOM (BUG-021).
+    rendered = sanitize_html(rendered)
+
+    return rendered