Add advanced TF-IDF search with autocomplete, query operators, facets, pagination, and accent normalization

backend/main.py

@@ -25,7 +25,7 @@ from backend.indexer import (
     _extract_tags,
     SUPPORTED_EXTENSIONS,
 )
-from backend.search import search, get_all_tags
+from backend.search import search, get_all_tags, advanced_search, suggest_titles, suggest_tags
 from backend.image_processor import preprocess_images
 from backend.attachment_indexer import rescan_vault_attachments, get_attachment_stats
 
@@ -141,6 +141,57 @@ class TreeSearchResponse(BaseModel):
     results: List[TreeSearchResult]
 
 
+class AdvancedSearchResultItem(BaseModel):
+    """A single advanced search result with highlighted snippet."""
+    vault: str
+    path: str
+    title: str
+    tags: List[str]
+    score: float
+    snippet: str
+    modified: str
+
+
+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]
+    total: int
+    offset: int
+    limit: int
+    facets: SearchFacets
+
+
+class TitleSuggestion(BaseModel):
+    """A file title suggestion for autocomplete."""
+    vault: str
+    path: str
+    title: str
+
+
+class SuggestResponse(BaseModel):
+    """Autocomplete suggestions for file titles."""
+    query: str
+    suggestions: List[TitleSuggestion]
+
+
+class TagSuggestion(BaseModel):
+    """A tag suggestion for autocomplete."""
+    tag: str
+    count: int
+
+
+class TagSuggestResponse(BaseModel):
+    """Autocomplete suggestions for tags."""
+    query: str
+    suggestions: List[TagSuggestion]
+
+
 class ReloadResponse(BaseModel):
     """Index reload confirmation with per-vault stats."""
     status: str
@@ -711,6 +762,84 @@ async def api_tree_search(
     return {"query": q, "vault_filter": vault, "results": results}
 
 
+@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: operators)"),
+    vault: str = Query("all", description="Vault filter"),
+    tag: Optional[str] = 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'"),
+):
+    """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
+    - Remaining text is scored using TF-IDF with accent normalization.
+
+    Results include ``<mark>``-highlighted snippets and faceted tag/vault counts.
+
+    Args:
+        q: Query string with optional operators.
+        vault: Vault name or ``"all"``.
+        tag: Extra comma-separated tag names to require.
+        limit: Max results per page (1–200).
+        offset: Pagination offset.
+        sort: ``"relevance"`` (TF-IDF) or ``"modified"`` (date).
+
+    Returns:
+        ``AdvancedSearchResponse`` with scored results, facets, and pagination info.
+    """
+    return advanced_search(q, vault_filter=vault, tag_filter=tag, limit=limit, offset=offset, sort_by=sort)
+
+
+@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"),
+):
+    """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"),
+):
+    """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():
     """Force a full re-index of all configured vaults.