refactor: #85 T9 extrait realtime et render vers modules dedies (comportement inchange)
This commit is contained in:
+9
-305
@@ -1,27 +1,19 @@
|
||||
import asyncio
|
||||
import html as html_mod
|
||||
import json as _json
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import secrets
|
||||
import string
|
||||
from contextlib import asynccontextmanager
|
||||
from pathlib import Path
|
||||
|
||||
import mistune
|
||||
from fastapi import Depends, FastAPI, HTTPException, Request, WebSocket
|
||||
from fastapi.responses import FileResponse, HTMLResponse, JSONResponse, StreamingResponse
|
||||
from fastapi import Depends, FastAPI, HTTPException, Request
|
||||
from fastapi.responses import FileResponse, HTMLResponse, JSONResponse
|
||||
from fastapi.staticfiles import StaticFiles
|
||||
from pydantic import BaseModel, Field
|
||||
from starlette.middleware.base import BaseHTTPMiddleware
|
||||
|
||||
from backend.collab import authenticate_websocket, collab_manager
|
||||
from backend.image_processor import preprocess_images
|
||||
from backend.collab import collab_manager
|
||||
from backend.indexer import (
|
||||
build_index,
|
||||
find_file_in_index,
|
||||
get_vault_data,
|
||||
handle_file_move,
|
||||
remove_single_file,
|
||||
update_single_file,
|
||||
@@ -38,7 +30,6 @@ from backend.search import (
|
||||
from backend.semantic_search import init_semantic_index
|
||||
from backend.services.backups import get_backup_dir as service_get_backup_dir
|
||||
from backend.services.errors import ServiceError
|
||||
from backend.services.sanitizer import sanitize_html
|
||||
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
@@ -48,33 +39,10 @@ logger = logging.getLogger("obsigate")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Pydantic response models : voir backend.schemas (vaults/history : #85 T8)
|
||||
# Pydantic models : voir backend.schemas (#85 T5→T9)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
# Filesystem mutation + search / suggest / graph models : voir backend.schemas (#85 T5, T6b)
|
||||
|
||||
class BackupEntry(BaseModel):
|
||||
"""A single backup version of a file."""
|
||||
timestamp: int = Field(description="Unix timestamp of when the backup was created")
|
||||
datetime: str = Field(description="ISO 8601 datetime string")
|
||||
size: int = Field(description="File size in bytes")
|
||||
filename: str = Field(description="Backup filename on disk")
|
||||
|
||||
|
||||
class BackupListResponse(BaseModel):
|
||||
"""Response listing all available backups for a file."""
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Relative file path")
|
||||
backups: list[BackupEntry] = Field(description="Available backups, newest first")
|
||||
|
||||
|
||||
class DiffRequest(BaseModel):
|
||||
"""Request parameters for generating a diff."""
|
||||
version: int = Field(description="Timestamp of the backup version to compare")
|
||||
compare_with: int | None = Field(default=None, description="Timestamp of another backup version. If omitted, compares with the current file.")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# SSE Manager — voir backend.sse (ROADMAP #85 T4, instance partagée)
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -432,9 +400,7 @@ app.add_middleware(SecurityHeadersMiddleware)
|
||||
# Multi-format export (HTML / MD bundle / ePub) — voir backend.routers.files_media (#85 T6c).
|
||||
from backend.ai_routes import router as ai_router
|
||||
from backend.auth.middleware import (
|
||||
check_vault_access,
|
||||
require_admin,
|
||||
require_auth,
|
||||
)
|
||||
from backend.auth.router import router as auth_router
|
||||
from backend.bookslm_routes import router as bookslm_router
|
||||
@@ -447,11 +413,11 @@ from backend.routers.files_read import router as files_read_router
|
||||
from backend.routers.files_write import router as files_write_router
|
||||
from backend.routers.health import router as health_router
|
||||
from backend.routers.history import router as history_router
|
||||
from backend.routers.realtime import router as realtime_router
|
||||
from backend.routers.search import router as search_router
|
||||
from backend.routers.sharing import router as sharing_router
|
||||
from backend.routers.vaults import router as vaults_router
|
||||
from backend.routers.webhooks import router as webhooks_router
|
||||
from backend.secret_redactor import redact_file_content
|
||||
from backend.skills_routes import router as skills_router
|
||||
|
||||
app.include_router(auth_router)
|
||||
@@ -460,6 +426,7 @@ app.include_router(bookslm_router)
|
||||
app.include_router(skills_router)
|
||||
app.include_router(health_router) # ROADMAP #85 T1 — System / health
|
||||
app.include_router(history_router) # ROADMAP #85 T8 — History
|
||||
app.include_router(realtime_router) # ROADMAP #85 T9 — SSE + collab WS
|
||||
app.include_router(search_router) # ROADMAP #85 T5 — Search
|
||||
app.include_router(backups_router) # ROADMAP #85 T4 — Backups
|
||||
app.include_router(conflicts_router) # ROADMAP #85 T8 — Conflicts
|
||||
@@ -569,193 +536,9 @@ def _check_vault_writable(vault_root: Path) -> bool:
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Markdown rendering helpers (singleton renderer)
|
||||
# Markdown rendering helpers : voir backend.render (#85 T9)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
import unicodedata
|
||||
|
||||
|
||||
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 & 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
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -826,51 +609,9 @@ def _get_backup_dir(vault_name: str, relative_path: str) -> Path:
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# SSE endpoint — Server-Sent Events stream
|
||||
# SSE endpoint : voir backend.routers.realtime (#85 T9)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@app.get(
|
||||
"/api/events",
|
||||
response_class=StreamingResponse,
|
||||
responses={200: {"content": {"text/event-stream": {}}, "description": "Server-Sent Events stream"}},
|
||||
)
|
||||
async def api_events(current_user=Depends(require_auth)):
|
||||
"""SSE stream for real-time index update notifications.
|
||||
|
||||
Sends keepalive comments every 30s. Events:
|
||||
- ``index_updated``: partial index change (file create/modify/delete/move)
|
||||
- ``index_reloaded``: full re-index completed
|
||||
- ``vault_added``: new vault added dynamically
|
||||
- ``vault_removed``: vault removed dynamically
|
||||
"""
|
||||
queue = await sse_manager.connect()
|
||||
|
||||
async def event_generator():
|
||||
try:
|
||||
# Send initial connection event
|
||||
yield f"event: connected\ndata: {_json.dumps({'sse_clients': sse_manager.client_count})}\n\n"
|
||||
while True:
|
||||
try:
|
||||
msg = await asyncio.wait_for(queue.get(), timeout=30.0)
|
||||
yield f"event: {msg['event']}\ndata: {msg['data']}\n\n"
|
||||
except asyncio.TimeoutError:
|
||||
# Keepalive comment
|
||||
yield ": keepalive\n\n"
|
||||
except asyncio.CancelledError:
|
||||
break
|
||||
finally:
|
||||
sse_manager.disconnect(queue)
|
||||
|
||||
return StreamingResponse(
|
||||
event_generator(),
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive",
|
||||
"X-Accel-Buffering": "no",
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Dynamic vault management endpoints : voir backend.routers.vaults (#85 T8)
|
||||
@@ -940,46 +681,9 @@ async def api_events(current_user=Depends(require_auth)):
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Real-time collaboration — WebSocket endpoint (ROADMAP #62)
|
||||
# Real-time collaboration — WebSocket endpoint : voir backend.routers.realtime (#85 T9, ROADMAP #62)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@app.websocket("/ws/collab/{vault_name}/{path:path}")
|
||||
async def collab_websocket(websocket: WebSocket, vault_name: str, path: str):
|
||||
"""Real-time collaborative editing over WebSocket (ROADMAP #62).
|
||||
|
||||
One *room* is created per ``vault::path``; all clients editing the same
|
||||
file share Yjs/CRDT updates, awareness (cursors/selection) and a debounced
|
||||
server-side persistence of the markdown content.
|
||||
|
||||
Authentication is performed manually (FastAPI ``Depends`` do not run for
|
||||
WebSocket routes) and vault access is enforced per connection.
|
||||
"""
|
||||
from backend.services.errors import ServiceError
|
||||
from backend.services.vaults import get_vault_root
|
||||
|
||||
user = authenticate_websocket(websocket)
|
||||
if user is None:
|
||||
await websocket.close(code=4401)
|
||||
return
|
||||
|
||||
if not check_vault_access(vault_name, user):
|
||||
await websocket.close(code=4403)
|
||||
return
|
||||
|
||||
try:
|
||||
vault_root = get_vault_root(vault_name)
|
||||
file_path = _resolve_safe_path(vault_root, path)
|
||||
except ServiceError:
|
||||
await websocket.close(code=4404)
|
||||
return
|
||||
|
||||
if not file_path.exists() or not file_path.is_file():
|
||||
await websocket.close(code=4404)
|
||||
return
|
||||
|
||||
await websocket.accept()
|
||||
await collab_manager.connect(websocket, vault_name, path, file_path, user)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Static files & SPA fallback
|
||||
|
||||
Reference in New Issue
Block a user