fix: raise FilterError on unknown metadata filter operators (#11795)

Co-authored-by: David S. Batista <dsbatista@gmail.com>

Author: immuhammadfurqan

haystack/utils/filters.py

@@ -173,6 +173,9 @@ def _logic_condition(condition: dict[str, Any], document: Document | ByteStream)
         msg = f"'conditions' key missing in {condition}"
         raise FilterError(msg)
     operator: str = condition["operator"]
+    if operator not in LOGICAL_OPERATORS:
+        msg = f"Unknown logical operator '{operator}'. Valid operators are: {sorted(LOGICAL_OPERATORS)}"
+        raise FilterError(msg)
     conditions: list[dict[str, Any]] = condition["conditions"]
     return LOGICAL_OPERATORS[operator](document=document, conditions=conditions)
 
@@ -214,5 +217,8 @@ def _comparison_condition(condition: dict[str, Any], document: Document | ByteSt
     else:
         document_value = getattr(document, field)
     operator: str = condition["operator"]
+    if operator not in COMPARISON_OPERATORS:
+        msg = f"Unknown comparison operator '{operator}'. Valid operators are: {sorted(COMPARISON_OPERATORS)}"
+        raise FilterError(msg)
     filter_value: Any = condition["value"]
     return COMPARISON_OPERATORS[operator](filter_value=filter_value, value=document_value)

releasenotes/notes/filter-unknown-operator-error-8df4039c0db976ff.yaml

@@ -0,0 +1,8 @@
+---
+fixes:
+  - |
+    Metadata filters that use an unsupported operator now raise a clear ``FilterError``
+    that lists the valid operators, instead of a cryptic ``KeyError``. For example, a
+    typo such as ``{"field": "meta.year", "operator": "gt", "value": 2000}`` (instead of
+    ``">"``) previously surfaced as ``KeyError: 'gt'``. This applies to both comparison
+    operators and logical operators (``AND``, ``OR``, ``NOT``).

test/utils/test_filters.py

@@ -566,6 +566,23 @@ def test_document_matches_filter(filters, document, expected_result):
     pytest.param({"operator": "==", "value": "test"}, id="Missing condition field key"),
     pytest.param({"field": "meta.name", "value": "test"}, id="Missing condition operator key"),
     pytest.param({"field": "meta.name", "operator": "=="}, id="Missing condition value key"),
+    # Unknown operators
+    pytest.param({"field": "meta.page", "operator": "gt", "value": 10}, id="Unknown comparison operator"),
+    pytest.param(
+        {"operator": "XOR", "conditions": [{"field": "meta.page", "operator": "==", "value": 10}]},
+        id="Unknown logical operator",
+    ),
+    pytest.param(
+        {
+            "operator": "AND",
+            "conditions": [{"operator": "XOR", "conditions": [{"field": "meta.page", "operator": "==", "value": 10}]}],
+        },
+        id="Unknown nested logical operator",
+    ),
+    pytest.param(
+        {"operator": "and", "conditions": [{"field": "meta.page", "operator": "==", "value": 10}]},
+        id="Lowercase logical operator",
+    ),
 ]
 
 
@@ -574,3 +591,38 @@ def test_document_matches_filter_raises_error(filters):
     with pytest.raises(FilterError):
         document = Document(meta={"page": 10})
         document_matches_filter(filters, document)
+
+
+@pytest.mark.parametrize(
+    "filters,expected_message",
+    [
+        pytest.param(
+            {"field": "meta.page", "operator": "gt", "value": 10},
+            "Unknown comparison operator 'gt'",
+            id="Unknown comparison operator",
+        ),
+        pytest.param(
+            {"operator": "XOR", "conditions": [{"field": "meta.page", "operator": "==", "value": 10}]},
+            "Unknown logical operator 'XOR'",
+            id="Unknown logical operator",
+        ),
+        pytest.param(
+            {
+                "operator": "AND",
+                "conditions": [
+                    {"operator": "XOR", "conditions": [{"field": "meta.page", "operator": "==", "value": 10}]}
+                ],
+            },
+            "Unknown logical operator 'XOR'",
+            id="Unknown nested logical operator",
+        ),
+        pytest.param(
+            {"operator": "and", "conditions": [{"field": "meta.page", "operator": "==", "value": 10}]},
+            "Unknown logical operator 'and'",
+            id="Lowercase logical operator",
+        ),
+    ],
+)
+def test_document_matches_filter_unknown_operator_error_message(filters, expected_message):
+    with pytest.raises(FilterError, match=expected_message):
+        document_matches_filter(filters, Document(meta={"page": 10}))