fix: JSONConverter raises KeyError on ByteStream sources without file_path

haystack/components/converters/json.py

@@ -191,7 +191,7 @@ def _get_content_and_meta(self, source: ByteStream) -> list[tuple[str, dict[str,
         except UnicodeError as exc:
             logger.warning(
                 "Failed to extract text from {source}. Skipping it. Error: {error}",
-                source=source.meta["file_path"],
+                source=source.meta.get("file_path", "unknown"),
                 error=exc,
             )
             return []
@@ -204,7 +204,7 @@ def _get_content_and_meta(self, source: ByteStream) -> list[tuple[str, dict[str,
             except Exception as exc:
                 logger.warning(
                     "Failed to extract text from {source}. Skipping it. Error: {error}",
-                    source=source.meta["file_path"],
+                    source=source.meta.get("file_path", "unknown"),
                     error=exc,
                 )
                 return []
@@ -216,7 +216,7 @@ def _get_content_and_meta(self, source: ByteStream) -> list[tuple[str, dict[str,
             except json.JSONDecodeError as exc:
                 logger.warning(
                     "Failed to extract text from {source}. Skipping it. Error: {error}",
-                    source=source.meta["file_path"],
+                    source=source.meta.get("file_path", "unknown"),
                     error=exc,
                 )
                 return []

releasenotes/notes/fix-json-converter-bytestream-keyerror-9c55c4ccd0ccca4c.yaml

@@ -0,0 +1,9 @@
+---
+fixes:
+  - |
+    Fixed ``JSONConverter`` raising a ``KeyError`` instead of logging its
+    intended "Failed to extract text, skipping it" warning when a source is a
+    ``ByteStream`` without a ``file_path`` in its ``meta`` (for example
+    ``ByteStream.from_string(...)``, the exact usage shown in the component's
+    own docstring examples). Affected error paths: invalid UTF-8 content, a
+    ``jq_schema`` filter that fails to apply, and malformed JSON content.

test/components/converters/test_json.py

@@ -275,6 +275,51 @@ def test_run_with_malformed_json_and_content_key(tmpdir, caplog):
     assert result == {"documents": []}
 
 
+def test_run_with_bad_filter_and_bytestream_without_file_path(caplog):
+    """A bare ByteStream source (no 'file_path' in its meta) must not raise a KeyError."""
+    source = ByteStream(data=json.dumps(test_data[0]).encode("utf-8"))
+    converter = JSONConverter(".laureates | .motivation")
+
+    caplog.clear()
+    with caplog.at_level(logging.WARNING):
+        result = converter.run(sources=[source])
+
+    records = caplog.records
+    assert len(records) == 1
+    assert records[0].msg.startswith("Failed to extract text from unknown. Skipping it. Error:")
+    assert result == {"documents": []}
+
+
+def test_run_with_bad_encoding_and_bytestream_without_file_path(caplog):
+    """A bare ByteStream source (no 'file_path' in its meta) must not raise a KeyError."""
+    source = ByteStream(data=json.dumps(test_data[0]).encode("utf-16"))
+    converter = JSONConverter(".laureates")
+
+    caplog.clear()
+    with caplog.at_level(logging.WARNING):
+        result = converter.run(sources=[source])
+
+    records = caplog.records
+    assert len(records) == 1
+    assert records[0].msg.startswith("Failed to extract text from unknown. Skipping it. Error:")
+    assert result == {"documents": []}
+
+
+def test_run_with_malformed_json_and_bytestream_without_file_path(caplog):
+    """A bare ByteStream source (no 'file_path' in its meta) must not raise a KeyError."""
+    source = ByteStream(data=b"This is not valid JSON.")
+    converter = JSONConverter(content_key="motivation")
+
+    caplog.clear()
+    with caplog.at_level(logging.WARNING):
+        result = converter.run(sources=[source])
+
+    records = caplog.records
+    assert len(records) == 1
+    assert records[0].msg.startswith("Failed to extract text from unknown. Skipping it. Error:")
+    assert result == {"documents": []}
+
+
 def test_run_with_single_meta(tmpdir):
     first_test_file = Path(tmpdir / "first_test_file.json")
     second_test_file = Path(tmpdir / "second_test_file.json")