feat: document extractor chardet encoding (#20269)

Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-27 13:27:46 +08:00
parent 756f35f480
commit 9c9d3d7bd0
2 changed files with 63 additions and 11 deletions
--- a/api/tests/unit_tests/core/workflow/nodes/test_document_extractor_node.py
+++ b/api/tests/unit_tests/core/workflow/nodes/test_document_extractor_node.py
@@ -150,7 +150,7 @@ def test_extract_text_from_plain_text_non_utf8():
        temp_file.write(non_utf8_content)
        temp_file.seek(0)
        text = _extract_text_from_plain_text(temp_file.read())
-    assert text == "Hello, world."
+    assert text == "Hello, world©."


@patch("pypdfium2.PdfDocument")