ObsiGate/backend/routers/search.py

"""Search, suggest, graph & index-reload endpoints (ROADMAP #85, tranche 5).

Handlers déplacés depuis :mod:`backend.main` sans changement de
comportement : mêmes chemins, mêmes modèles de réponse (déménagés dans
:mod:`backend.schemas`), mêmes dépendances d'authentification. La logique
métier vit déjà dans :mod:`backend.services.search`,
:mod:`backend.search`, :mod:`backend.services.graph` et
:mod:`backend.services.mutations`.

Adaptations strictement équivalentes :
- Le pool ``_search_executor`` de ``main`` vit désormais dans
  :mod:`backend.search_executor` (même dimensionnement, même cycle de vie
  géré par le lifespan de ``main``) : accès via
  :func:`get_search_executor`.
"""

import asyncio
import logging
from functools import partial
from pathlib import Path

from fastapi import APIRouter, Body, Depends, HTTPException, Query

from backend.audit import log_file_save
from backend.auth.middleware import check_vault_access, require_admin, require_auth
from backend.indexer import get_vault_data, reload_index, update_single_file
from backend.schemas import (
    AdvancedSearchResponse,
    GraphResponse,
    ReloadResponse,
    ReplaceResponse,
    SearchResponse,
    SuggestResponse,
    TagsResponse,
    TagSuggestResponse,
    TreeSearchResponse,
    VaultPathsResponse,
    VaultStatsResponse,
)
from backend.search import suggest_tags, suggest_titles
from backend.search_executor import get_search_executor
from backend.services.graph import get_graph as service_get_graph
from backend.services.mutations import (
    replace_in_files as service_replace_in_files,
)
from backend.services.search import advanced_search_vaults, list_paths, search_paths, search_vaults
from backend.services.search import list_tags as service_list_tags
from backend.sse import sse_manager

logger = logging.getLogger("obsigate")

router = APIRouter(tags=["search"])


@router.get("/api/search", response_model=SearchResponse)
async def api_search(
    q: str = Query("", description="Search query"),
    vault: str = Query("all", description="Vault filter"),
    tag: str | None = Query(None, description="Tag filter"),
    limit: int = Query(50, ge=1, le=200, description="Results per page"),
    offset: int = Query(0, ge=0, description="Pagination offset"),
    current_user=Depends(require_auth),
):
    """Full-text search across vaults with relevance scoring.

    Supports combining free-text queries with tag filters.
    Results are ranked by a multi-factor scoring algorithm.
    Pagination via ``limit`` and ``offset`` (defaults preserve backward compat).

    Args:
        q: Free-text search string.
        vault: Vault name or ``"all"`` to search everywhere.
        tag: Comma-separated tag names to require.
        limit: Max results per page (1–200).
        offset: Pagination offset.

    Returns:
        ``SearchResponse`` with ranked results and snippets.
    """
    loop = asyncio.get_event_loop()
    # Fetch the full result set (capped at DEFAULT_SEARCH_LIMIT internally) and
    # paginate in the shared service so routes and tools share the same logic.
    return await loop.run_in_executor(
        get_search_executor(),
        partial(search_vaults, q, vault, tag, limit, offset),
    )


@router.get("/api/tags", response_model=TagsResponse)
async def api_tags(vault: str | None = Query(None, description="Vault filter"), current_user=Depends(require_auth)):
    """Return all unique tags with occurrence counts.

    Args:
        vault: Optional vault name to restrict tag aggregation.

    Returns:
        ``TagsResponse`` with tags sorted by descending count.
    """
    return {"vault_filter": vault, "tags": service_list_tags(vault)}


@router.get("/api/tree-search", response_model=TreeSearchResponse)
async def api_tree_search(
    q: str = Query("", description="Search query"),
    vault: str = Query("all", description="Vault filter"),
    current_user=Depends(require_auth),
):
    """Search for files and directories in the tree structure using pre-built index.

    Uses the in-memory path index for instant filtering without filesystem access.

    Args:
        q: Search string to match against file/directory paths.
        vault: Vault name or "all" to search everywhere.

    Returns:
        ``TreeSearchResponse`` with matching paths.
    """
    return search_paths(q, vault)


@router.get("/api/vault/{vault_name}/paths", response_model=VaultPathsResponse)
async def api_vault_paths(
    vault_name: str,
    limit: int = Query(5000, ge=1, le=20000, description="Maximum number of indexed paths to return"),
    current_user=Depends(require_auth),
):
    """Return a flat list of every indexed file and directory in a vault.

    Used by the AI assistant ``@`` mention menu to filter paths instantly on
    the client (one request instead of one per keystroke).

    Args:
        vault_name: Name of the vault.
        limit: Maximum number of entries returned.

    Returns:
        ``VaultPathsResponse`` with the vault's indexed paths.
    """
    if not check_vault_access(vault_name, current_user):
        raise HTTPException(status_code=403, detail=f"Accès refusé à la vault '{vault_name}'")
    return list_paths(vault_name, limit=limit)


@router.get("/api/search/advanced", response_model=AdvancedSearchResponse)
async def api_advanced_search(
    q: str = Query("", description="Advanced search query (supports tag:, vault:, title:, path:, ext: operators)"),
    vault: str = Query("all", description="Vault filter"),
    tag: str | None = Query(None, description="Comma-separated tag filter"),
    limit: int = Query(50, ge=1, le=200, description="Results per page"),
    offset: int = Query(0, ge=0, description="Pagination offset"),
    sort: str = Query("relevance", description="Sort by 'relevance' or 'modified'"),
    case_sensitive: bool = Query(False, description="Match case"),
    whole_word: bool = Query(False, description="Match whole words only"),
    regex: bool = Query(False, description="Treat query as regex"),
    include_paths: str | None = Query(None, description="Comma-separated glob patterns to include"),
    exclude_paths: str | None = Query(None, description="Comma-separated glob patterns to exclude"),
    created: str | None = Query(None, description="Created date filter (>date, <date, date..date)"),
    modified: str | None = Query(None, description="Modified date filter (>date, <date, date..date, <Nd)"),
    size: str | None = Query(None, description="Size filter (>size, <size, size..size, e.g. >1MB, <10KB)"),
    semantic: bool = Query(False, description="Fuse TF-IDF with semantic embeddings (RRF)"),
    current_user=Depends(require_auth),
):
    """Advanced full-text search with TF-IDF scoring, facets, and pagination.

    Supports advanced query operators:
    - ``tag:<name>`` or ``#<name>`` — filter by tag
    - ``vault:<name>`` — filter by vault
    - ``title:<text>`` — filter by title substring
    - ``path:<text>`` — filter by path substring
    - ``ext:<type>`` — filter by file extension
    - ``created:>2024-01-01`` — filter by creation date
    - ``modified:<7d`` or ``modified:2024-01-01..2024-06-01`` — filter by modification date
    - ``size:>1MB`` or ``size:100KB..1MB`` — filter by file size
    - Remaining text is scored using TF-IDF with accent normalization.
    - Toggles: case_sensitive, whole_word, regex
    - Path filters: include_paths, exclude_paths (glob patterns)
    - ``semantic=true`` — fuse the TF-IDF ranking with the semantic (embedding)
      ranking via Reciprocal Rank Fusion and expose ``semantic_score`` per result.

    Results include ``<mark>``-highlighted snippets and faceted tag/vault counts.
    """
    loop = asyncio.get_event_loop()
    search_fn = partial(advanced_search_vaults, q, vault=vault, tag=tag,
                limit=limit, offset=offset, sort=sort,
                case_sensitive=case_sensitive, whole_word=whole_word, regex=regex,
                include_paths=include_paths, exclude_paths=exclude_paths,
                created=created, modified=modified, size=size, semantic=semantic)
    try:
        return await loop.run_in_executor(get_search_executor(), search_fn)
    except ValueError as e:
        raise HTTPException(400, str(e)) from e


@router.post("/api/search/replace", response_model=ReplaceResponse)
async def api_search_replace(
    body: dict = Body(...),
    current_user=Depends(require_auth),
):
    """Find and replace across vault files."""
    query = body.get("query", "")
    replacement = body.get("replacement", "")
    vault_filter = body.get("vault", "all")
    case_sensitive = body.get("case_sensitive", False)
    whole_word = body.get("whole_word", False)
    regex_mode = body.get("regex", False)
    include_paths = body.get("include_paths")
    exclude_paths = body.get("exclude_paths")
    replace_all = body.get("replace_all", False)
    dry_run = body.get("dry_run", not replace_all)

    if not query:
        raise HTTPException(400, "Query is required")

    result = service_replace_in_files(
        query,
        replacement,
        vault=vault_filter,
        case_sensitive=case_sensitive,
        whole_word=whole_word,
        regex=regex_mode,
        include_paths=include_paths,
        exclude_paths=exclude_paths,
        replace_all=replace_all,
        dry_run=dry_run,
        is_vault_allowed=lambda v: check_vault_access(v, current_user),
    )

    if dry_run:
        return result

    # Side effects for applied replacements (audit + incremental index).
    for match in result.get("replaced", []):
        log_file_save(current_user["username"], match["vault"], match["path"], match.get("size", 0))
        vault_data = get_vault_data(match["vault"])
        if vault_data:
            abs_path = str(Path(vault_data["path"]) / match["path"])
            await update_single_file(match["vault"], abs_path)

    return result


@router.get("/api/suggest", response_model=SuggestResponse)
async def api_suggest(
    q: str = Query("", description="Prefix to search for in file titles"),
    vault: str = Query("all", description="Vault filter"),
    limit: int = Query(10, ge=1, le=50, description="Max suggestions"),
    current_user=Depends(require_auth),
):
    """Suggest file titles matching a prefix (accent-insensitive).

    Used for autocomplete in the search input.

    Args:
        q: User-typed prefix (minimum 2 characters).
        vault: Vault name or ``"all"``.
        limit: Max number of suggestions.

    Returns:
        ``SuggestResponse`` with matching file title suggestions.
    """
    suggestions = suggest_titles(q, vault_filter=vault, limit=limit)
    return {"query": q, "suggestions": suggestions}


@router.get("/api/tags/suggest", response_model=TagSuggestResponse)
async def api_tags_suggest(
    q: str = Query("", description="Prefix to search for in tags"),
    vault: str = Query("all", description="Vault filter"),
    limit: int = Query(10, ge=1, le=50, description="Max suggestions"),
    current_user=Depends(require_auth),
):
    """Suggest tags matching a prefix (accent-insensitive).

    Used for autocomplete when typing ``tag:`` or ``#`` in the search input.

    Args:
        q: User-typed prefix (with or without ``#``, minimum 2 characters).
        vault: Vault name or ``"all"``.
        limit: Max number of suggestions.

    Returns:
        ``TagSuggestResponse`` with matching tag suggestions and counts.
    """
    suggestions = suggest_tags(q, vault_filter=vault, limit=limit)
    return {"query": q, "suggestions": suggestions}


@router.get("/api/index/reload", response_model=ReloadResponse)
async def api_reload(current_user=Depends(require_admin)):
    """Force a full re-index of all configured vaults.

    Returns:
        ``ReloadResponse`` with per-vault file and tag counts.
    """
    stats = await reload_index()
    await sse_manager.broadcast("index_reloaded", {
        "vaults": list(stats.keys()),
        "stats": stats,
    })
    return {"status": "ok", "vaults": stats}


@router.get("/api/graph/{vault_name}", response_model=GraphResponse)
async def api_graph(
    vault_name: str,
    path: str = Query("", description="Relative path to focus on"),
    depth: int = Query(1, ge=0, le=3, description="How many levels deep to expand"),
    scope: str = Query("directory", description="'directory' (default) or 'full' for entire vault"),
    tag: str = Query("", description="Filter: only show files with this tag"),
    current_user=Depends(require_auth),
):
    """Return graph data (nodes and edges) for a vault or directory.

    Nodes represent files and directories. Edges represent parent-child
    relationships and wikilinks between markdown files.

    Args:
        vault_name: Name of the vault.
        path: Relative directory path to focus on (empty = root).
        depth: Expansion depth (0 = only direct children, 1-3 = deeper).
        scope: 'directory' for subtree, 'full' for entire vault.
        tag: Optional tag filter (only files with this tag appear).

    Returns:
        ``GraphResponse`` with nodes and edges.
    """
    if not check_vault_access(vault_name, current_user):
        raise HTTPException(status_code=403, detail=f"Accès refusé à la vault '{vault_name}'")

    return service_get_graph(vault_name, path=path, depth=depth, scope=scope, tag=tag)


@router.get("/api/index/reload/{vault_name}", response_model=VaultStatsResponse)
async def api_reload_vault(vault_name: str, current_user=Depends(require_admin)):
    """Force a re-index of a single vault.

    Args:
        vault_name: Name of the vault to reindex.

    Returns:
        Dict with vault statistics.
    """
    try:
        from backend.indexer import reload_single_vault
        stats = await reload_single_vault(vault_name)
        await sse_manager.broadcast("vault_reloaded", {
            "vault": vault_name,
            "stats": stats,
        })
        return {"status": "ok", "vault": vault_name, "stats": stats}
    except ValueError as e:
        raise HTTPException(status_code=404, detail=str(e))