From 7d61c3769f3bb596027c3ca51a3f757684e073dd Mon Sep 17 00:00:00 2001
From: stumpylog <797416+stumpylog@users.noreply.github.com>
Date: Thu, 20 Aug 2026 11:56:42 -0700
Subject: [PATCH] test(search): assert the empty highlight query matches
 nothing

test_empty_query_returns_empty_query and test_all_operators_returns_empty_query
asserted isinstance(result, tantivy.Query), which parse_simple_text_highlight_query
cannot fail to satisfy: it either returns a Query or raises. Replacing its
`return tantivy.Query.empty_query()` with `all_query()` left both green, so
the contract they were named for -- highlight nothing, rather than highlight
every document -- was unpinned.

They now count hits against an index holding one document. A third test
asserts a real token matches that document, so an empty corpus cannot make
the other two pass for a match-everything query.

Under the empty_query -> all_query mutation both new tests fail; before this
change the mutation killed nothing.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---
 src/documents/tests/search/test_query.py | 46 +++++++++++++++++++-----
 1 file changed, 38 insertions(+), 8 deletions(-)

diff --git a/src/documents/tests/search/test_query.py b/src/documents/tests/search/test_query.py
index caa35f365..8b2962542 100644
--- a/src/documents/tests/search/test_query.py
+++ b/src/documents/tests/search/test_query.py
@@ -34,6 +34,27 @@ def query_index() -> tantivy.Index:
     return idx
 
 
+@pytest.fixture(scope="module")
+def populated_index() -> tantivy.Index:
+    """An index holding one document, so a query matching nothing is
+    distinguishable from one matching everything."""
+    idx = tantivy.Index(build_schema(), path=None)
+    register_tokenizers(idx, "")
+    writer = idx.writer()
+    doc = tantivy.Document()
+    doc.add_unsigned("id", 1)
+    doc.add_text("content", "needle in indexed content")
+    writer.add_document(doc)
+    writer.commit()
+    idx.reload()
+    return idx
+
+
+def _highlight_hit_count(index: tantivy.Index, raw_query: str) -> int:
+    query = parse_simple_text_highlight_query(index, raw_query)
+    return index.searcher().search(query, limit=1).count
+
+
 class TestParseUserQuery:
     """parse_user_query runs the full preprocessing pipeline."""
 
@@ -166,16 +187,25 @@ class TestParseSimpleTextHighlightQuery:
             tantivy.Query,
         )
 
-    def test_empty_query_returns_empty_query(self, query_index: tantivy.Index) -> None:
-        result = parse_simple_text_highlight_query(query_index, "")
-        assert isinstance(result, tantivy.Query)
-
-    def test_all_operators_returns_empty_query(
+    def test_a_real_token_matches_the_corpus(
         self,
-        query_index: tantivy.Index,
+        populated_index: tantivy.Index,
     ) -> None:
-        result = parse_simple_text_highlight_query(query_index, "- +")
-        assert isinstance(result, tantivy.Query)
+        """Without this, an empty corpus would make the two assertions below
+        pass for a query that matches every document."""
+        assert _highlight_hit_count(populated_index, "needle") == 1
+
+    def test_empty_query_matches_no_document(
+        self,
+        populated_index: tantivy.Index,
+    ) -> None:
+        assert _highlight_hit_count(populated_index, "") == 0
+
+    def test_all_operators_query_matches_no_document(
+        self,
+        populated_index: tantivy.Index,
+    ) -> None:
+        assert _highlight_hit_count(populated_index, "- +") == 0
 
 
 class TestPermissionFilter: