refactor: #85 T6a extrait lecture fichiers vers backend/routers (comportement inchange)

backend/routers/files_read.py

@@ -0,0 +1,525 @@
+"""File browsing & reading endpoints (ROADMAP #85, tranche 6a).
+
+Handlers déplacés depuis :mod:`backend.main` sans changement de
+comportement : mêmes chemins (``/api/browse/*``, ``/api/file/*`` en
+lecture), mêmes modèles de réponse (déménagés dans
+:mod:`backend.schemas`), mêmes dépendances d'authentification.
+
+Adaptations strictement équivalentes :
+- ``_resolve_safe_path`` → :mod:`backend.services.paths` (pass-through).
+- ``_render_markdown`` reste dans ``main`` (import différé, extraction
+  prévue dans une tranche ultérieure).
+- ``_content_disposition`` / ``_media_max_inline_bytes`` / ``EXT_TO_LANG``
+  ont déménagé : helpers partagés dans :mod:`backend.routers.helpers`
+  (``EXT_TO_LANG`` n'était utilisé que par la vue fichier).
+"""
+
+import html as html_mod
+import logging
+from pathlib import Path
+from urllib.parse import quote
+
+from fastapi import APIRouter, Depends, HTTPException, Query
+from fastapi.responses import FileResponse
+
+from backend.auth.middleware import check_vault_access, require_auth
+from backend.history import record_open
+from backend.indexer import (
+    _extract_tags,
+    get_backlinks,
+    get_vault_data,
+    parse_markdown_file,
+)
+from backend.media_types import is_audio, is_image, is_video, media_mime_type
+from backend.routers.helpers import media_max_inline_bytes
+from backend.schemas import (
+    BacklinksResponse,
+    BrowseResponse,
+    FileContentResponse,
+    FileRawResponse,
+)
+from backend.services.files import read_raw_file
+from backend.services.paths import resolve_safe_path
+from backend.services.vaults import browse_directory
+
+logger = logging.getLogger("obsigate")
+
+# Map file extensions to highlight.js language hints
+EXT_TO_LANG = {
+    ".py": "python", ".js": "javascript", ".ts": "typescript",
+    ".jsx": "jsx", ".tsx": "tsx", ".sh": "bash", ".bash": "bash",
+    ".zsh": "bash", ".fish": "fish", ".bat": "batch", ".cmd": "batch",
+    ".ps1": "powershell", ".json": "json", ".yaml": "yaml", ".yml": "yaml",
+    ".toml": "toml", ".xml": "xml", ".csv": "plaintext",
+    ".cfg": "ini", ".ini": "ini", ".conf": "ini", ".env": "bash",
+    ".html": "html", ".css": "css", ".scss": "scss", ".less": "less",
+    ".java": "java", ".c": "c", ".cpp": "cpp", ".h": "c", ".hpp": "cpp",
+    ".cs": "csharp", ".go": "go", ".rs": "rust", ".rb": "ruby",
+    ".php": "php", ".sql": "sql", ".r": "r", ".swift": "swift",
+    ".kt": "kotlin", ".txt": "plaintext", ".log": "plaintext",
+    ".lua": "lua", ".pl": "perl", ".pm": "perl", ".ex": "elixir", ".exs": "elixir",
+    ".dart": "dart", ".tf": "haskell", ".gradle": "groovy", ".groovy": "groovy",
+    ".graphql": "graphql", ".gql": "graphql", ".prisma": "sql", ".proto": "c",
+    ".vb": "basic", ".asm": "x86asm", ".s": "armasm",
+    ".vue": "xml", ".svelte": "xml", ".astro": "xml",
+    ".properties": "ini", ".service": "ini", ".hosts": "ini",
+    ".ksh": "bash", ".dockerfile": "dockerfile",
+    ".makefile": "makefile", ".cmake": "cmake",
+}
+
+router = APIRouter(tags=["files"])
+
+
+@router.get("/api/browse/{vault_name}", response_model=BrowseResponse)
+async def api_browse(vault_name: str, path: str = "", current_user=Depends(require_auth)):
+    """Browse directories and files in a vault at a given path level.
+
+    Returns sorted entries (directories first, then files) with metadata.
+    Hidden files/directories (starting with ``"."`` ) are excluded.
+
+    Args:
+        vault_name: Name of the vault to browse.
+        path: Relative directory path within the vault (empty = root).
+
+    Returns:
+        ``BrowseResponse`` with vault name, path, and item list.
+    """
+    if not check_vault_access(vault_name, current_user):
+        raise HTTPException(status_code=403, detail=f"Accès refusé à la vault '{vault_name}'")
+    return browse_directory(vault_name, path)
+
+
+@router.get("/api/file/{vault_name}/raw", response_model=FileRawResponse)
+async def api_file_raw(vault_name: str, path: str = Query(..., description="Relative path to file"), current_user=Depends(require_auth)):
+    """Return raw file content as plain text.
+
+    Args:
+        vault_name: Name of the vault.
+        path: Relative file path within the vault.
+
+    Returns:
+        ``FileRawResponse`` with vault, path, and raw text content.
+    """
+    if not check_vault_access(vault_name, current_user):
+        raise HTTPException(status_code=403, detail=f"Accès refusé à la vault '{vault_name}'")
+    return read_raw_file(vault_name, path)
+
+
+@router.get("/api/file/{vault_name}/download", response_class=FileResponse)
+async def api_file_download(vault_name: str, path: str = Query(..., description="Relative path to file"), current_user=Depends(require_auth)):
+    """Download a file as an attachment.
+
+    Args:
+        vault_name: Name of the vault.
+        path: Relative file path within the vault.
+
+    Returns:
+        ``FileResponse`` with ``application/octet-stream`` content-type.
+    """
+    if not check_vault_access(vault_name, current_user):
+        raise HTTPException(status_code=403, detail=f"Accès refusé à la vault '{vault_name}'")
+    vault_data = get_vault_data(vault_name)
+    if not vault_data:
+        raise HTTPException(status_code=404, detail=f"Vault '{vault_name}' not found")
+
+    vault_root = Path(vault_data["path"])
+    file_path = resolve_safe_path(vault_root, path)
+
+    if not file_path.exists() or not file_path.is_file():
+        raise HTTPException(status_code=404, detail=f"File not found: {path}")
+
+    # Record history
+    record_open(current_user.get("username"), vault_name, path)
+
+    return FileResponse(
+        path=str(file_path),
+        filename=file_path.name,
+        media_type="application/octet-stream",
+    )
+
+
+@router.get("/api/file/{vault_name}/backlinks", response_model=BacklinksResponse)
+async def api_file_backlinks(
+    vault_name: str,
+    path: str = Query(..., description="Relative path to file"),
+    current_user=Depends(require_auth),
+):
+    """Get backlinks (files linking to this file via wikilinks).
+
+    Returns a list of files that contain `[[wikilinks]]` pointing
+    to the requested file, across all accessible vaults.
+
+    Args:
+        vault_name: Name of the vault containing the target file.
+        path: Relative path of the target file within the vault.
+
+    Returns:
+        ``{"vault": str, "path": str, "backlinks": [...]}``
+    """
+    if not check_vault_access(vault_name, current_user):
+        raise HTTPException(status_code=403, detail=f"Accès refusé à la vault '{vault_name}'")
+    vault_data = get_vault_data(vault_name)
+    if not vault_data:
+        raise HTTPException(status_code=404, detail=f"Vault '{vault_name}' not found")
+
+    user_vaults = current_user.get("_token_vaults") or current_user.get("vaults", [])
+    backlinks = get_backlinks(vault_name, path)
+
+    # Filter by user-accessible vaults
+    if "*" not in user_vaults:
+        backlinks = [b for b in backlinks if b["vault"] in user_vaults]
+
+    return {
+        "vault": vault_name,
+        "path": path,
+        "backlinks": backlinks,
+        "total": len(backlinks),
+    }
+
+
+@router.get("/api/file/{vault_name}", response_model=FileContentResponse)
+async def api_file(vault_name: str, path: str = Query(..., description="Relative path to file"), current_user=Depends(require_auth)):
+    """Return rendered HTML and metadata for a file.
+
+    Markdown files are parsed for frontmatter, rendered with wikilink
+    support, and returned with extracted tags. Other supported file
+    types are syntax-highlighted as code blocks.
+
+    Args:
+        vault_name: Name of the vault.
+        path: Relative file path within the vault.
+
+    Returns:
+        ``FileContentResponse`` with HTML, metadata, and tags.
+    """
+    from backend.main import _render_markdown  # différé : évite l'import circulaire (#85)
+
+    if not check_vault_access(vault_name, current_user):
+        raise HTTPException(status_code=403, detail=f"Accès refusé à la vault '{vault_name}'")
+    vault_data = get_vault_data(vault_name)
+    if not vault_data:
+        raise HTTPException(status_code=404, detail=f"Vault '{vault_name}' not found")
+
+    vault_root = Path(vault_data["path"])
+    file_path = resolve_safe_path(vault_root, path)
+
+    if not file_path.exists() or not file_path.is_file():
+        raise HTTPException(status_code=404, detail=f"File not found: {path}")
+
+    # Record history
+    record_open(current_user.get("username"), vault_name, path, title=file_path.name)
+
+    ext = file_path.suffix.lower()
+
+    # === PDF: special handling before read_text (binary file) ===
+    if ext == ".pdf":
+        try:
+            from backend.pdf_reader import extract_pdf_metadata, extract_pdf_text, extract_pdf_toc
+            pdf_text = extract_pdf_text(file_path, max_chars=100000)
+            pdf_meta = extract_pdf_metadata(file_path)
+            pdf_toc = extract_pdf_toc(file_path)
+            size = file_path.stat().st_size
+            return {
+                "vault": vault_name,
+                "path": path,
+                "title": pdf_meta.get("title") or file_path.name,
+                "tags": [],
+                "frontmatter": {},
+                "html": f"<div class='pdf-viewer'><p>PDF — {pdf_meta.get('pages', '?')} pages</p><pre>{pdf_text[:5000]}</pre></div>",
+                "raw_length": size,
+                "extension": ext,
+                "is_markdown": False,
+                "is_pdf": True,
+                "unsupported": False,
+                "pdf_metadata": pdf_meta,
+                "pdf_toc": pdf_toc,
+                "size_bytes": size,
+            }
+        except Exception as e:
+            logger.error(f"PDF read error for {path}: {e}")
+            raise HTTPException(status_code=500, detail=f"Error reading PDF: {e!s}")
+
+    # === Excel .xlsx: render sheets as HTML tables (binary, before read_text) ===
+    if ext == ".xlsx":
+        try:
+            from backend.xlsx_reader import render_sheets
+
+            sheets = render_sheets(file_path)
+            size = file_path.stat().st_size
+            return {
+                "vault": vault_name,
+                "path": path,
+                "title": file_path.name,
+                "tags": [],
+                "frontmatter": {},
+                "html": sheets[0]["html"] if sheets else "",
+                "raw_length": size,
+                "extension": ext,
+                "is_markdown": False,
+                "is_xlsx": True,
+                "xlsx_sheets": sheets,
+                "unsupported": False,
+                "size_bytes": size,
+            }
+        except Exception as e:
+            logger.error(f"XLSX read error for {path}: {e}")
+            raise HTTPException(status_code=500, detail=f"Error reading XLSX: {e!s}")
+
+    # === Images: return as viewable image ===
+    if is_image(ext):
+        size = file_path.stat().st_size
+        mime = media_mime_type(str(file_path))
+        # #108-B1 — the raw endpoint returns JSON (FileRawResponse), so the
+        # standalone <img> must point to /api/image, which serves the bytes
+        # with the right MIME type. Paths are URL-encoded (accents, spaces).
+        img_url = f"/api/image/{quote(vault_name, safe='')}?path={quote(path, safe='')}"
+        html = (
+            f'<div class="image-viewer">'
+            f'<img src="{img_url}" '
+            f'alt="{html_mod.escape(file_path.name, quote=True)}" '
+            f'style="max-width:100%;max-height:80vh;object-fit:contain" />'
+            f'</div>'
+        )
+        return {
+            "vault": vault_name,
+            "path": path,
+            "title": file_path.name,
+            "tags": [],
+            "frontmatter": {},
+            "html": html,
+            "raw_length": size,
+            "extension": ext,
+            "is_markdown": False,
+            "is_image": True,
+            "image_mime": mime,
+            "size_bytes": size,
+        }
+
+    # === Audio / Video: HTML5 players streamed from /api/media (roadmap #109) ===
+    if is_audio(ext) or is_video(ext):
+        size = file_path.stat().st_size
+        mime = media_mime_type(str(file_path))
+        media_kind = "audio" if is_audio(ext) else "video"
+
+        # #109-A3 — beyond the inline limit the viewer falls back to download
+        # (a single uvicorn worker must not be pinned by multi-GB media).
+        if size > media_max_inline_bytes():
+            return {
+                "vault": vault_name,
+                "path": path,
+                "title": file_path.name,
+                "tags": [],
+                "frontmatter": {},
+                "html": "",
+                "raw_length": size,
+                "extension": ext,
+                "is_markdown": False,
+                "unsupported": True,
+                "media_too_large": True,
+                "size_bytes": size,
+            }
+
+        # #109-A2 — byte-range endpoint: enables scrub and is required by Safari.
+        stream_url = f"/api/media/{quote(vault_name, safe='')}?path={quote(path, safe='')}"
+        if media_kind == "audio":
+            html = (
+                f'<div class="audio-viewer">'
+                f'<audio controls preload="metadata" src="{stream_url}"></audio>'
+                f'</div>'
+            )
+        else:
+            html = (
+                f'<div class="video-viewer">'
+                f'<video controls playsinline preload="metadata" src="{stream_url}"></video>'
+                f'</div>'
+            )
+        return {
+            "vault": vault_name,
+            "path": path,
+            "title": file_path.name,
+            "tags": [],
+            "frontmatter": {},
+            "html": html,
+            "raw_length": size,
+            "extension": ext,
+            "is_markdown": False,
+            "is_audio": media_kind == "audio",
+            "is_video": media_kind == "video",
+            "media_mime": mime,
+            "stream_url": stream_url,
+            "size_bytes": size,
+        }
+
+    try:
+        raw = file_path.read_text(encoding="utf-8", errors="replace")
+    except PermissionError as e:
+        logger.error(f"Permission denied reading file {path}: {e}")
+        raise HTTPException(status_code=403, detail=f"Permission denied: cannot read file {path}")
+    except UnicodeDecodeError:
+        # Binary / unsupported file — return structured info with download option
+        size = file_path.stat().st_size
+        return {
+            "vault": vault_name,
+            "path": path,
+            "title": file_path.name,
+            "tags": [],
+            "frontmatter": {},
+            "html": "",
+            "raw_length": size,
+            "extension": ext,
+            "is_markdown": False,
+            "unsupported": True,
+            "size_bytes": size,
+        }
+    except Exception as e:
+        logger.error(f"Unexpected error reading file {path}: {e}")
+        raise HTTPException(status_code=500, detail=f"Error reading file: {e!s}")
+
+    # === CSV: render as HTML table ===
+    if ext == ".csv":
+        import csv
+        import io as csv_io
+        reader = csv.reader(csv_io.StringIO(raw))
+        rows = list(reader)
+        if not rows:
+            html = "<p><em>Fichier CSV vide</em></p>"
+        else:
+            headers = rows[0]
+            data_rows = rows[1:]
+            html = '<div class="csv-table-wrapper"><table class="csv-table"><thead><tr>'
+            for h in headers:
+                html += f"<th>{h}</th>"
+            html += "</tr></thead><tbody>"
+            for row in data_rows:
+                html += "<tr>"
+                for cell in row:
+                    html += f"<td>{cell}</td>"
+                html += "</tr>"
+            html += "</tbody></table></div>"
+        return {
+            "vault": vault_name, "path": path,
+            "title": file_path.name, "tags": [], "frontmatter": {},
+            "html": html, "raw_length": len(raw), "extension": ext,
+            "is_markdown": False, "is_csv": True,
+        }
+
+    # === JSON: syntax-highlighted display ===
+    if ext == ".json":
+        import json as json_mod
+        try:
+            parsed = json_mod.loads(raw)
+            formatted = json_mod.dumps(parsed, indent=2, ensure_ascii=False)
+        except json_mod.JSONDecodeError:
+            formatted = raw
+        html = f"<pre class='json-viewer'><code>{html_mod.escape(formatted)}</code></pre>"
+        return {
+            "vault": vault_name, "path": path,
+            "title": file_path.name, "tags": [], "frontmatter": {},
+            "html": html, "raw_length": len(raw), "extension": ext,
+            "is_markdown": False, "is_json": True,
+        }
+
+    # === Excalidraw .excalidraw.md (Obsidian plugin format) ===
+    if path.lower().endswith(".excalidraw.md"):
+        import re as re_mod
+        raw_lower = file_path.read_text(encoding="utf-8", errors="replace")
+        # Check for excalidraw-plugin in frontmatter or body
+        if "excalidraw-plugin:" in raw_lower:
+            # Extract compressed JSON block
+            match = re_mod.search(r'```compressed-json\n(.*?)\n```', raw_lower, re_mod.DOTALL)
+            if match:
+                compressed = match.group(1).strip()
+                return {
+                    "vault": vault_name, "path": path,
+                    "title": file_path.name.replace(".excalidraw.md", ""),
+                    "tags": [], "frontmatter": {},
+                    "html": "", "raw_length": len(raw_lower),
+                    "extension": ".excalidraw.md",
+                    "is_markdown": False,
+                    "is_excalidraw": True,
+                    "excalidraw_data_compressed": compressed,
+                }
+        # Fallback: treat as regular markdown
+        raw = raw_lower
+    if ext == ".excalidraw":
+        import json as json_mod
+        try:
+            parsed = json_mod.loads(raw)
+        except json_mod.JSONDecodeError:
+            parsed = None
+        if parsed and parsed.get("type") == "excalidraw":
+            return {
+                "vault": vault_name,
+                "path": path,
+                "title": parsed.get("appState", {}).get("name") or file_path.name,
+                "tags": [],
+                "frontmatter": {},
+                "html": "",
+                "raw_length": len(raw),
+                "extension": ext,
+                "is_markdown": False,
+                "is_excalidraw": True,
+                "excalidraw_data": {
+                    "elements": parsed.get("elements", []),
+                    "appState": parsed.get("appState", {}),
+                    "files": parsed.get("files", {}),
+                },
+            }
+        else:
+            # Not a valid Excalidraw file — fall through to text viewer
+            pass
+
+    # === Plain text / other readable files ===
+    TEXT_EXTENSIONS = {".txt", ".log", ".yml", ".yaml", ".toml", ".ini", ".cfg",
+                       ".sh", ".bash", ".py", ".js", ".ts", ".html", ".css",
+                       ".xml", ".rst", ".tex", ".sql", ".conf", ".env"}
+    if ext in TEXT_EXTENSIONS or ext == ".md":
+        pass  # handled below or by markdown section
+
+    if ext == ".md":
+        post = parse_markdown_file(raw)
+
+        # Extract metadata using shared indexer logic
+        tags = _extract_tags(post)
+
+        title = post.metadata.get("title", file_path.stem.replace("-", " ").replace("_", " "))
+        html_content = _render_markdown(post.content, vault_name, file_path)
+
+        return {
+            "vault": vault_name,
+            "path": path,
+            "title": str(title),
+            "tags": tags,
+            "frontmatter": dict(post.metadata) if post.metadata else {},
+            "html": html_content,
+            "raw_length": len(raw),
+            "extension": ext,
+            "is_markdown": True,
+        }
+    else:
+        # Non-markdown: wrap in syntax-highlighted code block
+        lang = EXT_TO_LANG.get(ext, "")
+        if not lang:
+            # Fichiers sans extension usuels (Dockerfile, Makefile, etc.)
+            NAME_TO_LANG = {
+                "dockerfile": "dockerfile", "makefile": "makefile",
+                "cmakelists.txt": "cmake", "jenkinsfile": "groovy",
+                "vagrantfile": "ruby", "rakefile": "ruby", "gemfile": "ruby",
+                "procfile": "plaintext", "bashrc": "bash", "bash_profile": "bash",
+                "zshrc": "bash", "profile": "bash", "gitignore": "plaintext",
+            }
+            lang = NAME_TO_LANG.get(file_path.name.lower(), "plaintext")
+        escaped = html_mod.escape(raw)
+        html_content = f'<pre><code class="language-{lang}">{escaped}</code></pre>'
+
+        return {
+            "vault": vault_name,
+            "path": path,
+            "title": file_path.name,
+            "tags": [],
+            "frontmatter": {},
+            "html": html_content,
+            "raw_length": len(raw),
+            "extension": ext,
+            "is_markdown": False,
+        }

backend/routers/helpers.py

@@ -0,0 +1,51 @@
+"""Shared helpers for the file routers (ROADMAP #85, tranche 6a).
+
+Petites fonctions pures extraites de :mod:`backend.main` sans changement
+de comportement. Regroupées ici car utilisées par plusieurs routers
+(``files_read`` aujourd'hui, ``files_media`` / mutations ensuite) :
+- :func:`content_disposition` — aussi utilisée par ``_stream_file_with_range``
+  (resté dans ``main`` jusqu'à la tranche media).
+- :func:`media_max_inline_bytes` — aussi utilisée par ``/api/media``.
+"""
+
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+
+def content_disposition(disposition: str, filename: str) -> str:
+    """Build a header-safe Content-Disposition value.
+
+    HTTP header values must be ASCII. Unicode filenames are sent per
+    RFC 5987 via ``filename*`` (percent-encoded UTF-8) with a pure-ASCII
+    ``filename`` fallback. This avoids a UnicodeDecodeError / HTTP 500 when
+    the filename contains accented characters (e.g. 'Bière blonde…pdf').
+    """
+    from urllib.parse import quote
+    ascii_name = "".join(c for c in filename if c.isascii() and (c.isalnum() or c in " _-.")).strip() or "file"
+    ext = Path(filename).suffix
+    if ext and not Path(ascii_name).suffix:
+        ascii_name = ascii_name + ext
+    return f"{disposition}; filename=\"{ascii_name}\"; filename*=UTF-8''{quote(filename)}"
+
+
+def media_max_inline_bytes() -> int:
+    """Maximum size (bytes) for inline audio/video playback (roadmap #109-A3).
+
+    Configurable via ``OBSIGATE_MEDIA_MAX_INLINE_MB`` (default 500 MB). Files
+    above the limit are not streamed in the viewer (the UI falls back to the
+    download button), which keeps a single uvicorn worker from being pinned by
+    multi-gigabyte media. Invalid or non-positive values fall back to default.
+    """
+    default_mb = 500
+    raw = os.environ.get("OBSIGATE_MEDIA_MAX_INLINE_MB", "").strip()
+    if not raw:
+        return default_mb * 1024 * 1024
+    try:
+        mb = float(raw)
+    except ValueError:
+        return default_mb * 1024 * 1024
+    if mb <= 0:
+        return default_mb * 1024 * 1024
+    return int(mb * 1024 * 1024)