refactor: #85 T5 extrait le domaine search vers backend/routers + executor partage (comportement inchange)
This commit is contained in:
+22
-470
@@ -8,9 +8,7 @@ import secrets
|
||||
import shutil
|
||||
import string
|
||||
import urllib.request
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from contextlib import asynccontextmanager
|
||||
from functools import partial
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
from urllib.parse import quote
|
||||
@@ -45,7 +43,6 @@ from backend.indexer import (
|
||||
handle_file_move,
|
||||
index,
|
||||
parse_markdown_file,
|
||||
reload_index,
|
||||
remove_single_file,
|
||||
remove_vault_from_index,
|
||||
update_single_file,
|
||||
@@ -76,7 +73,6 @@ from backend.schemas import (
|
||||
DiagnosticsResponse,
|
||||
PdfInfoResponse,
|
||||
RecentResponse,
|
||||
ReplaceResponse,
|
||||
SavedSearch,
|
||||
StatusResponse,
|
||||
VaultActionResponse,
|
||||
@@ -87,14 +83,11 @@ from backend.schemas import (
|
||||
)
|
||||
from backend.search import (
|
||||
init_inverted_index,
|
||||
suggest_tags,
|
||||
suggest_titles,
|
||||
)
|
||||
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.files import read_raw_file
|
||||
from backend.services.graph import get_graph as service_get_graph
|
||||
from backend.services.mutations import (
|
||||
batch_upload_files as service_batch_upload_files,
|
||||
)
|
||||
@@ -125,13 +118,8 @@ from backend.services.mutations import (
|
||||
from backend.services.mutations import (
|
||||
rename_file as service_rename_file,
|
||||
)
|
||||
from backend.services.mutations import (
|
||||
replace_in_files as service_replace_in_files,
|
||||
)
|
||||
from backend.services.recent import humanize_mtime, list_recent
|
||||
from backend.services.sanitizer import sanitize_html
|
||||
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.services.vaults import (
|
||||
browse_directory,
|
||||
list_accessible_vaults,
|
||||
@@ -234,154 +222,8 @@ class FileDeleteResponse(BaseModel):
|
||||
path: str = Field(description="Relative file path within the vault")
|
||||
|
||||
|
||||
class SearchResultItem(BaseModel):
|
||||
"""A single search result."""
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Relative file path")
|
||||
title: str = Field(description="File title")
|
||||
tags: list[str] = Field(description="File tags")
|
||||
score: int = Field(description="Relevance score")
|
||||
snippet: str = Field(description="Content excerpt with highlights")
|
||||
modified: str = Field(description="ISO 8601 modification timestamp")
|
||||
|
||||
|
||||
class SearchResponse(BaseModel):
|
||||
"""Full-text search response with optional pagination."""
|
||||
query: str = Field(description="Original search query")
|
||||
vault_filter: str = Field(description="Vault filter applied ('all' or vault name)")
|
||||
tag_filter: str | None = Field(default=None, description="Tag filter applied")
|
||||
count: int = Field(description="Number of results in this response")
|
||||
total: int = Field(default=0, description="Total results before pagination")
|
||||
offset: int = Field(default=0, description="Current pagination offset")
|
||||
limit: int = Field(default=200, description="Page size")
|
||||
results: list[SearchResultItem] = Field(description="Search result items")
|
||||
|
||||
|
||||
class TagsResponse(BaseModel):
|
||||
"""Tag aggregation response."""
|
||||
vault_filter: str | None = Field(default=None, description="Vault filter applied")
|
||||
tags: dict[str, int] = Field(description="Tag name → count mapping")
|
||||
|
||||
|
||||
class TreeSearchResult(BaseModel):
|
||||
"""A single tree search result item."""
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Full relative path")
|
||||
name: str = Field(description="File or directory name")
|
||||
type: str = Field(description="'file' or 'directory'")
|
||||
matched_path: str = Field(description="Path segment that matched the query")
|
||||
|
||||
|
||||
class TreeSearchResponse(BaseModel):
|
||||
"""Tree search response with matching paths."""
|
||||
query: str = Field(description="Search query")
|
||||
vault_filter: str = Field(description="Vault filter applied")
|
||||
results: list[TreeSearchResult] = Field(description="Matching files and directories")
|
||||
|
||||
|
||||
class VaultPathEntry(BaseModel):
|
||||
"""A single indexed path (file or directory) in a vault."""
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Full relative path")
|
||||
name: str = Field(description="File or directory name")
|
||||
type: str = Field(description="'file' or 'directory'")
|
||||
|
||||
|
||||
class VaultPathsResponse(BaseModel):
|
||||
"""Flat list of every indexed path in a vault (capped)."""
|
||||
vault: str = Field(description="Vault name")
|
||||
count: int = Field(description="Number of returned entries")
|
||||
results: list[VaultPathEntry] = Field(description="Indexed files and directories")
|
||||
|
||||
|
||||
class AdvancedSearchResultItem(BaseModel):
|
||||
"""A single advanced search result with highlighted snippet."""
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Relative file path")
|
||||
title: str = Field(description="File title")
|
||||
tags: list[str] = Field(description="File tags")
|
||||
score: float = Field(description="TF-IDF relevance score (or fused RRF score in semantic mode)")
|
||||
semantic_score: float = Field(default=0.0, description="Cosine similarity from the semantic index (0 when unavailable)")
|
||||
snippet: str = Field(description="Content excerpt with <mark> highlights")
|
||||
modified: str = Field(description="ISO 8601 modification timestamp")
|
||||
extension: str = Field(default="", description="File extension")
|
||||
|
||||
|
||||
class SearchFacets(BaseModel):
|
||||
"""Faceted counts for search results."""
|
||||
tags: dict[str, int] = Field(default_factory=dict)
|
||||
vaults: dict[str, int] = Field(default_factory=dict)
|
||||
|
||||
|
||||
class AdvancedSearchResponse(BaseModel):
|
||||
"""Advanced search response with TF-IDF scoring, facets, and pagination."""
|
||||
results: list[AdvancedSearchResultItem] = Field(description="Search results")
|
||||
total: int = Field(description="Total number of matching results")
|
||||
offset: int = Field(description="Current pagination offset")
|
||||
limit: int = Field(description="Page size")
|
||||
facets: SearchFacets = Field(description="Faceted counts by tag and vault")
|
||||
query_time_ms: float = Field(default=0, description="Server-side query time in milliseconds")
|
||||
semantic_available: bool = Field(default=False, description="True when the semantic (embedding) index is ready")
|
||||
|
||||
|
||||
class TitleSuggestion(BaseModel):
|
||||
"""A file title suggestion for autocomplete."""
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Relative file path")
|
||||
title: str = Field(description="File title")
|
||||
|
||||
|
||||
class SuggestResponse(BaseModel):
|
||||
"""Autocomplete suggestions for file titles."""
|
||||
query: str = Field(description="Original query string")
|
||||
suggestions: list[TitleSuggestion] = Field(description="Matching file suggestions")
|
||||
|
||||
|
||||
class TagSuggestion(BaseModel):
|
||||
"""A tag suggestion for autocomplete."""
|
||||
tag: str = Field(description="Tag name")
|
||||
count: int = Field(description="Number of files with this tag")
|
||||
|
||||
|
||||
class TagSuggestResponse(BaseModel):
|
||||
"""Autocomplete suggestions for tags."""
|
||||
query: str = Field(description="Original query string")
|
||||
suggestions: list[TagSuggestion] = Field(description="Matching tag suggestions")
|
||||
|
||||
|
||||
class GraphNode(BaseModel):
|
||||
"""A single node in the graph view."""
|
||||
id: str = Field(description="Unique node identifier")
|
||||
name: str = Field(description="Display name")
|
||||
type: str = Field(description="'vault', 'directory', or 'file'")
|
||||
path: str = Field(description="Relative path within vault")
|
||||
size: int = Field(default=0, description="File size in bytes")
|
||||
tags: list[str] = Field(default_factory=list, description="Tags from frontmatter")
|
||||
incoming_count: int = Field(default=0, description="Number of incoming wikilinks")
|
||||
outgoing_count: int = Field(default=0, description="Number of outgoing wikilinks")
|
||||
|
||||
|
||||
class GraphEdge(BaseModel):
|
||||
"""An edge between two nodes in the graph view."""
|
||||
source: str = Field(description="Source node ID")
|
||||
target: str = Field(description="Target node ID")
|
||||
relation: str = Field(description="'parent', 'wikilink', or 'backlink'")
|
||||
|
||||
|
||||
class GraphResponse(BaseModel):
|
||||
"""Graph data for a vault or directory."""
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Root path for the graph")
|
||||
scope: str = Field(default="directory", description="'directory' or 'full'")
|
||||
nodes: list[GraphNode] = Field(description="Graph nodes (files and directories)")
|
||||
edges: list[GraphEdge] = Field(description="Graph edges (parent and wikilink relations)")
|
||||
|
||||
|
||||
class ReloadResponse(BaseModel):
|
||||
"""Index reload confirmation with per-vault stats."""
|
||||
status: str = Field(description="Reload status ('ok' or 'error')")
|
||||
vaults: dict[str, Any] = Field(description="Per-vault file counts after reload")
|
||||
|
||||
# Search / suggest / graph models : voir backend.schemas (#85 T5)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class DirectoryCreateRequest(BaseModel):
|
||||
"""Request to create a new directory."""
|
||||
@@ -503,6 +345,11 @@ class DiffRequest(BaseModel):
|
||||
# ---------------------------------------------------------------------------
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
from backend.search_executor import (
|
||||
get_search_executor,
|
||||
init_search_executor,
|
||||
shutdown_search_executor,
|
||||
)
|
||||
from backend.sse import sse_manager
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -510,9 +357,7 @@ from backend.sse import sse_manager
|
||||
# ---------------------------------------------------------------------------
|
||||
from backend.watcher import VaultWatcher
|
||||
|
||||
# Thread pool for offloading CPU-bound search from the event loop.
|
||||
# Sized to 2 workers so concurrent searches don't starve other requests.
|
||||
_search_executor: ThreadPoolExecutor | None = None
|
||||
# File watcher handle (the search thread pool lives in backend.search_executor).
|
||||
_vault_watcher: VaultWatcher | None = None
|
||||
|
||||
|
||||
@@ -694,8 +539,10 @@ def _guard_insecure_auth() -> None:
|
||||
@asynccontextmanager
|
||||
async def lifespan(app: FastAPI):
|
||||
"""Application lifespan: build index on startup, cleanup on shutdown."""
|
||||
global _search_executor, _vault_watcher
|
||||
_search_executor = ThreadPoolExecutor(max_workers=2, thread_name_prefix="search")
|
||||
global _vault_watcher
|
||||
# Thread pool for offloading CPU-bound search from the event loop.
|
||||
# Sized to 2 workers so concurrent searches don't starve other requests.
|
||||
init_search_executor()
|
||||
|
||||
# BUG-037: refuse to expose an unauthenticated instance on a public bind.
|
||||
_guard_insecure_auth()
|
||||
@@ -716,9 +563,9 @@ async def lifespan(app: FastAPI):
|
||||
# The inverted index rebuild is CPU-bound (tokenization, indexing) and
|
||||
# would freeze HTTP responses if run in the async event loop.
|
||||
loop = asyncio.get_running_loop()
|
||||
await loop.run_in_executor(_search_executor, init_inverted_index)
|
||||
await loop.run_in_executor(get_search_executor(), init_inverted_index)
|
||||
# Build the semantic (embedding) index in the same background thread pool.
|
||||
await loop.run_in_executor(_search_executor, init_semantic_index)
|
||||
await loop.run_in_executor(get_search_executor(), init_semantic_index)
|
||||
|
||||
# BUG-040: extract the PDF text deferred during the scan now that the
|
||||
# index and inverted index are queryable (keeps startup non-blocking).
|
||||
@@ -774,8 +621,7 @@ async def lifespan(app: FastAPI):
|
||||
if _vault_watcher:
|
||||
await _vault_watcher.stop()
|
||||
_vault_watcher = None
|
||||
_search_executor.shutdown(wait=False)
|
||||
_search_executor = None
|
||||
shutdown_search_executor()
|
||||
|
||||
|
||||
from backend.version import get_version
|
||||
@@ -872,6 +718,7 @@ from backend.bookslm_routes import router as bookslm_router
|
||||
from backend.export import ExportError, export_epub, export_html, export_md_bundle
|
||||
from backend.routers.backups import router as backups_router
|
||||
from backend.routers.health import router as health_router
|
||||
from backend.routers.search import router as search_router
|
||||
from backend.routers.sharing import router as sharing_router
|
||||
from backend.routers.webhooks import router as webhooks_router
|
||||
from backend.saved_searches import delete_saved, get_saved, save_search
|
||||
@@ -884,6 +731,7 @@ app.include_router(ai_router)
|
||||
app.include_router(bookslm_router)
|
||||
app.include_router(skills_router)
|
||||
app.include_router(health_router) # ROADMAP #85 T1 — System / health
|
||||
app.include_router(search_router) # ROADMAP #85 T5 — Search
|
||||
app.include_router(backups_router) # ROADMAP #85 T4 — Backups
|
||||
app.include_router(webhooks_router) # ROADMAP #85 T2 — Webhooks
|
||||
app.include_router(sharing_router) # ROADMAP #85 T3 — Sharing
|
||||
@@ -2577,305 +2425,9 @@ async def api_pdf_info(
|
||||
}
|
||||
|
||||
|
||||
@app.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(
|
||||
_search_executor,
|
||||
partial(search_vaults, q, vault, tag, limit, offset),
|
||||
)
|
||||
|
||||
|
||||
@app.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)}
|
||||
|
||||
|
||||
@app.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)
|
||||
|
||||
|
||||
@app.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)
|
||||
|
||||
|
||||
@app.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(_search_executor, search_fn)
|
||||
except ValueError as e:
|
||||
raise HTTPException(400, str(e)) from e
|
||||
|
||||
|
||||
@app.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
|
||||
|
||||
|
||||
@app.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}
|
||||
|
||||
|
||||
@app.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}
|
||||
|
||||
|
||||
@app.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}
|
||||
|
||||
|
||||
@app.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)
|
||||
|
||||
|
||||
@app.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))
|
||||
# ---------------------------------------------------------------------------
|
||||
# Search / suggest / graph / index-reload : voir backend.routers.search (#85 T5)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -3769,8 +3321,8 @@ async def api_diagnostics(current_user=Depends(require_admin)):
|
||||
},
|
||||
"config": _load_config(),
|
||||
"search_executor": {
|
||||
"active": _search_executor is not None,
|
||||
"max_workers": _search_executor._max_workers if _search_executor else 0,
|
||||
"active": get_search_executor() is not None,
|
||||
"max_workers": get_search_executor()._max_workers if get_search_executor() else 0,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,353 @@
|
||||
"""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))
|
||||
@@ -214,6 +214,178 @@ class RestoreResponse(BaseModel):
|
||||
current_backed_up: int | None = Field(default=None, description="Timestamp of the backup created from the current version before restore, if any")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Search / suggest / graph (#85 — extrait de backend.main, inchangé)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class SearchResultItem(BaseModel):
|
||||
"""A single search result."""
|
||||
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Relative file path")
|
||||
title: str = Field(description="File title")
|
||||
tags: list[str] = Field(description="File tags")
|
||||
score: int = Field(description="Relevance score")
|
||||
snippet: str = Field(description="Content excerpt with highlights")
|
||||
modified: str = Field(description="ISO 8601 modification timestamp")
|
||||
|
||||
|
||||
class SearchResponse(BaseModel):
|
||||
"""Full-text search response with optional pagination."""
|
||||
|
||||
query: str = Field(description="Original search query")
|
||||
vault_filter: str = Field(description="Vault filter applied ('all' or vault name)")
|
||||
tag_filter: str | None = Field(default=None, description="Tag filter applied")
|
||||
count: int = Field(description="Number of results in this response")
|
||||
total: int = Field(default=0, description="Total results before pagination")
|
||||
offset: int = Field(default=0, description="Current pagination offset")
|
||||
limit: int = Field(default=200, description="Page size")
|
||||
results: list[SearchResultItem] = Field(description="Search result items")
|
||||
|
||||
|
||||
class TagsResponse(BaseModel):
|
||||
"""Tag aggregation response."""
|
||||
|
||||
vault_filter: str | None = Field(default=None, description="Vault filter applied")
|
||||
tags: dict[str, int] = Field(description="Tag name → count mapping")
|
||||
|
||||
|
||||
class TreeSearchResult(BaseModel):
|
||||
"""A single tree search result item."""
|
||||
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Full relative path")
|
||||
name: str = Field(description="File or directory name")
|
||||
type: str = Field(description="'file' or 'directory'")
|
||||
matched_path: str = Field(description="Path segment that matched the query")
|
||||
|
||||
|
||||
class TreeSearchResponse(BaseModel):
|
||||
"""Tree search response with matching paths."""
|
||||
|
||||
query: str = Field(description="Search query")
|
||||
vault_filter: str = Field(description="Vault filter applied")
|
||||
results: list[TreeSearchResult] = Field(description="Matching files and directories")
|
||||
|
||||
|
||||
class VaultPathEntry(BaseModel):
|
||||
"""A single indexed path (file or directory) in a vault."""
|
||||
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Full relative path")
|
||||
name: str = Field(description="File or directory name")
|
||||
type: str = Field(description="'file' or 'directory'")
|
||||
|
||||
|
||||
class VaultPathsResponse(BaseModel):
|
||||
"""Flat list of every indexed path in a vault (capped)."""
|
||||
|
||||
vault: str = Field(description="Vault name")
|
||||
count: int = Field(description="Number of returned entries")
|
||||
results: list[VaultPathEntry] = Field(description="Indexed files and directories")
|
||||
|
||||
|
||||
class AdvancedSearchResultItem(BaseModel):
|
||||
"""A single advanced search result with highlighted snippet."""
|
||||
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Relative file path")
|
||||
title: str = Field(description="File title")
|
||||
tags: list[str] = Field(description="File tags")
|
||||
score: float = Field(description="TF-IDF relevance score (or fused RRF score in semantic mode)")
|
||||
semantic_score: float = Field(default=0.0, description="Cosine similarity from the semantic index (0 when unavailable)")
|
||||
snippet: str = Field(description="Content excerpt with <mark> highlights")
|
||||
modified: str = Field(description="ISO 8601 modification timestamp")
|
||||
extension: str = Field(default="", description="File extension")
|
||||
|
||||
|
||||
class SearchFacets(BaseModel):
|
||||
"""Faceted counts for search results."""
|
||||
|
||||
tags: dict[str, int] = Field(default_factory=dict)
|
||||
vaults: dict[str, int] = Field(default_factory=dict)
|
||||
|
||||
|
||||
class AdvancedSearchResponse(BaseModel):
|
||||
"""Advanced search response with TF-IDF scoring, facets, and pagination."""
|
||||
|
||||
results: list[AdvancedSearchResultItem] = Field(description="Search results")
|
||||
total: int = Field(description="Total number of matching results")
|
||||
offset: int = Field(description="Current pagination offset")
|
||||
limit: int = Field(description="Page size")
|
||||
facets: SearchFacets = Field(description="Faceted counts by tag and vault")
|
||||
query_time_ms: float = Field(default=0, description="Server-side query time in milliseconds")
|
||||
semantic_available: bool = Field(default=False, description="True when the semantic (embedding) index is ready")
|
||||
|
||||
|
||||
class TitleSuggestion(BaseModel):
|
||||
"""A file title suggestion for autocomplete."""
|
||||
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Relative file path")
|
||||
title: str = Field(description="File title")
|
||||
|
||||
|
||||
class SuggestResponse(BaseModel):
|
||||
"""Autocomplete suggestions for file titles."""
|
||||
|
||||
query: str = Field(description="Original query string")
|
||||
suggestions: list[TitleSuggestion] = Field(description="Matching file suggestions")
|
||||
|
||||
|
||||
class TagSuggestion(BaseModel):
|
||||
"""A tag suggestion for autocomplete."""
|
||||
|
||||
tag: str = Field(description="Tag name")
|
||||
count: int = Field(description="Number of files with this tag")
|
||||
|
||||
|
||||
class TagSuggestResponse(BaseModel):
|
||||
"""Autocomplete suggestions for tags."""
|
||||
|
||||
query: str = Field(description="Original query string")
|
||||
suggestions: list[TagSuggestion] = Field(description="Matching tag suggestions")
|
||||
|
||||
|
||||
class GraphNode(BaseModel):
|
||||
"""A single node in the graph view."""
|
||||
|
||||
id: str = Field(description="Unique node identifier")
|
||||
name: str = Field(description="Display name")
|
||||
type: str = Field(description="'vault', 'directory', or 'file'")
|
||||
path: str = Field(description="Relative path within vault")
|
||||
size: int = Field(default=0, description="File size in bytes")
|
||||
tags: list[str] = Field(default_factory=list, description="Tags from frontmatter")
|
||||
incoming_count: int = Field(default=0, description="Number of incoming wikilinks")
|
||||
outgoing_count: int = Field(default=0, description="Number of outgoing wikilinks")
|
||||
|
||||
|
||||
class GraphEdge(BaseModel):
|
||||
"""An edge between two nodes in the graph view."""
|
||||
|
||||
source: str = Field(description="Source node ID")
|
||||
target: str = Field(description="Target node ID")
|
||||
relation: str = Field(description="'parent', 'wikilink', or 'backlink'")
|
||||
|
||||
|
||||
class GraphResponse(BaseModel):
|
||||
"""Graph data for a vault or directory."""
|
||||
|
||||
vault: str = Field(description="Vault name")
|
||||
path: str = Field(description="Root path for the graph")
|
||||
scope: str = Field(default="directory", description="'directory' or 'full'")
|
||||
nodes: list[GraphNode] = Field(description="Graph nodes (files and directories)")
|
||||
edges: list[GraphEdge] = Field(description="Graph edges (parent and wikilink relations)")
|
||||
|
||||
|
||||
class ReloadResponse(BaseModel):
|
||||
"""Index reload confirmation with per-vault stats."""
|
||||
|
||||
status: str = Field(description="Reload status ('ok' or 'error')")
|
||||
vaults: dict[str, Any] = Field(description="Per-vault file counts after reload")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# PDF
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
"""Shared thread pool for CPU-bound search (ROADMAP #85, tranche 5).
|
||||
|
||||
Holder extrait de :mod:`backend.main` sans changement de comportement :
|
||||
un seul pool (2 workers, préfixe ``"search"``) créé au démarrage et arrêté
|
||||
à l'extinction par le lifespan de ``main``. Les routers et les endpoints
|
||||
restants y accèdent via :func:`get_search_executor` au lieu du global de
|
||||
``main`` (plus d'import circulaire potentiel).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
|
||||
_executor: ThreadPoolExecutor | None = None
|
||||
|
||||
|
||||
def init_search_executor(max_workers: int = 2) -> ThreadPoolExecutor:
|
||||
"""Create (or reuse) the shared search thread pool."""
|
||||
global _executor
|
||||
if _executor is None:
|
||||
_executor = ThreadPoolExecutor(max_workers=max_workers, thread_name_prefix="search")
|
||||
return _executor
|
||||
|
||||
|
||||
def shutdown_search_executor() -> None:
|
||||
"""Stop the shared search thread pool (best-effort, non-blocking)."""
|
||||
global _executor
|
||||
if _executor is not None:
|
||||
_executor.shutdown(wait=False)
|
||||
_executor = None
|
||||
|
||||
|
||||
def get_search_executor() -> ThreadPoolExecutor | None:
|
||||
"""Return the shared search thread pool (``None`` before startup)."""
|
||||
return _executor
|
||||
Reference in New Issue
Block a user