Add simple text search mode and API param

src/documents/search/_backend.py

@@ -7,6 +7,7 @@ from collections import Counter
 from dataclasses import dataclass
 from datetime import UTC
 from datetime import datetime
+from enum import StrEnum
 from typing import TYPE_CHECKING
 from typing import Self
 from typing import TypedDict
@@ -20,6 +21,7 @@ from django.utils.timezone import get_current_timezone
 from guardian.shortcuts import get_users_with_perms
 
 from documents.search._query import build_permission_filter
+from documents.search._query import parse_simple_text_query
 from documents.search._query import parse_user_query
 from documents.search._schema import _write_sentinels
 from documents.search._schema import build_schema
@@ -45,6 +47,11 @@ _AUTOCOMPLETE_REGEX_TIMEOUT = 1.0  # seconds; guards against ReDoS on untrusted
 T = TypeVar("T")
 
 
+class SearchMode(StrEnum):
+    QUERY = "query"
+    TEXT = "text"
+
+
 def _ascii_fold(s: str) -> str:
     """
     Normalize unicode to ASCII equivalent characters for search consistency.
@@ -433,6 +440,7 @@ class TantivyBackend:
         sort_field: str | None,
         *,
         sort_reverse: bool,
+        search_mode: SearchMode = SearchMode.QUERY,
     ) -> SearchResults:
         """
         Execute a search query against the document index.
@@ -441,20 +449,28 @@ class TantivyBackend:
         permission filtering before executing against Tantivy. Supports both
         relevance-based and field-based sorting.
 
+        QUERY search mode supports natural date keywords, field filters, etc.
+        TEXT search mode treats the query as plain text to search for in title and content
+
         Args:
-            query: User's search query (supports natural date keywords, field filters)
+            query: User's search query
             user: User for permission filtering (None for superuser/no filtering)
             page: Page number (1-indexed) for pagination
             page_size: Number of results per page
             sort_field: Field to sort by (None for relevance ranking)
             sort_reverse: Whether to reverse the sort order
+            search_mode: "query" for advanced Tantivy syntax, "text" for
+                plain-text search over title and content only
 
         Returns:
             SearchResults with hits, total count, and processed query
         """
         self._ensure_open()
         tz = get_current_timezone()
-        user_query = parse_user_query(self._index, query, tz)
+        if search_mode is SearchMode.TEXT:
+            user_query = parse_simple_text_query(self._index, query)
+        else:
+            user_query = parse_user_query(self._index, query, tz)
 
         # Apply permission filter if user is not None (not superuser)
         if user is not None:

src/documents/search/_query.py

@@ -51,6 +51,7 @@ _WHOOSH_REL_RANGE_RE = regex.compile(
 )
 # Whoosh-style 8-digit date: field:YYYYMMDD — field-aware so timezone can be applied correctly
 _DATE8_RE = regex.compile(r"(?P<field>\w+):(?P<date8>\d{8})\b")
+_SIMPLE_QUERY_SPECIAL_CHARS_RE = regex.compile(r'([+\-!(){}\[\]^"~*?:\\/])')
 
 
 def _fmt(dt: datetime) -> str:
@@ -436,6 +437,7 @@ DEFAULT_SEARCH_FIELDS = [
     "document_type",
     "tag",
 ]
+SIMPLE_SEARCH_FIELDS = ["title", "content"]
 _FIELD_BOOSTS = {"title": 2.0}
 
 
@@ -495,3 +497,28 @@ def parse_user_query(
         )
 
     return exact
+
+
+def parse_simple_text_query(
+    index: tantivy.Index,
+    raw_query: str,
+) -> tantivy.Query:
+    """
+    Parse a plain-text query using Tantivy's default parser over title/content.
+
+    Query string is escaped and normalized to be treated as "simple" text query.
+    """
+    # strips special characters that would be interpreted as syntax by the parser
+    query_str = regex.sub(
+        _SIMPLE_QUERY_SPECIAL_CHARS_RE,
+        r"\\\1",
+        raw_query,
+        timeout=_REGEX_TIMEOUT,
+    )
+    # collapse multiple spaces to a single space for cleaner parsing (and to prevent ReDoS on excessive whitespace)
+    query_str = regex.sub(r" {2,}", " ", query_str, timeout=_REGEX_TIMEOUT).strip()
+    return index.parse_query(
+        query_str,
+        SIMPLE_SEARCH_FIELDS,
+        field_boosts=_FIELD_BOOSTS,
+    )

src/documents/views.py

@@ -1995,6 +1995,12 @@ class ChatStreamingView(GenericAPIView):
     list=extend_schema(
         description="Document views including search",
         parameters=[
+            OpenApiParameter(
+                name="text",
+                type=OpenApiTypes.STR,
+                location=OpenApiParameter.QUERY,
+                description="Simple text search query string",
+            ),
             OpenApiParameter(
                 name="query",
                 type=OpenApiTypes.STR,
@@ -2033,7 +2039,8 @@ class UnifiedSearchViewSet(DocumentViewSet):
 
     def _is_search_request(self):
         return (
-            "query" in self.request.query_params
+            "text" in self.request.query_params
+            or "query" in self.request.query_params
             or "more_like_id" in self.request.query_params
         )
 
@@ -2043,6 +2050,7 @@ class UnifiedSearchViewSet(DocumentViewSet):
 
         from documents.search import TantivyRelevanceList
         from documents.search import get_backend
+        from documents.search._backend import SearchMode
 
         try:
             backend = get_backend()
@@ -2051,8 +2059,15 @@ class UnifiedSearchViewSet(DocumentViewSet):
 
             user = None if request.user.is_superuser else request.user
 
-            if "query" in request.query_params:
-                query_str = request.query_params["query"]
+            if "text" in request.query_params or "query" in request.query_params:
+                search_mode = (
+                    SearchMode.TEXT
+                    if "text" in request.query_params
+                    else SearchMode.QUERY
+                )
+                query_str = (
+                    request.query_params.get("text") or request.query_params["query"]
+                )
                 results = backend.search(
                     query_str,
                     user=user,
@@ -2060,6 +2075,7 @@ class UnifiedSearchViewSet(DocumentViewSet):
                     page_size=10000,
                     sort_field=None,
                     sort_reverse=False,
+                    search_mode=search_mode,
                 )
             else:
                 # more_like_id — validate permission on the seed document first