Skip to content

RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.

Fix email and presentation parsers treating an empty upload as a missing binary (#18712)

Yash Raj Pandeyb003502917b2
diff --git a/rag/app/email.py b/rag/app/email.py
index 90c926e62e..bde97b207c 100644
--- a/rag/app/email.py
+++ b/rag/app/email.py
@@ -51,7 +51,7 @@ def chunk(
main_res = []
attachment_res = []
- if binary:
+ if binary is not None:
with io.BytesIO(binary) as buffer:
msg = BytesParser(policy=policy.default).parse(buffer)
else:
diff --git a/rag/app/presentation.py b/rag/app/presentation.py
index ef2c77fe75..b8f2c668f0 100644
--- a/rag/app/presentation.py
+++ b/rag/app/presentation.py
@@ -40,7 +40,7 @@ class Pdf(PdfParser):
def __call__(self, filename, binary=None, from_page=0, to_page=MAXIMUM_PAGE_NUMBER, zoomin=3, callback=None, **kwargs):
# 1. OCR
callback(msg="OCR started")
- self.__images__(filename if not binary else binary, zoomin, from_page, to_page, callback)
+ self.__images__(filename if binary is None else binary, zoomin, from_page, to_page, callback)
# 2. Layout Analysis
callback(msg="Layout Analysis")
@@ -118,7 +118,7 @@ class Pdf(PdfParser):
class PlainPdf(PlainParser):
def __call__(self, filename, binary=None, from_page=0, to_page=MAXIMUM_PAGE_NUMBER, callback=None, **kwargs):
- self.pdf = pdf2_read(filename if not binary else BytesIO(binary))
+ self.pdf = pdf2_read(filename if binary is None else BytesIO(binary))
page_txt = []
for page in self.pdf.pages[from_page:to_page]:
page_txt.append(page.extract_text())
@@ -141,7 +141,7 @@ def chunk(filename, binary=None, from_page=0, to_page=MAXIMUM_PAGE_NUMBER, lang=
if re.search(r"\.pptx?$", filename, re.IGNORECASE):
try:
ppt_parser = RAGFlowPptParser()
- for pn, txt in enumerate(ppt_parser(filename if not binary else binary, from_page, MAXIMUM_PAGE_NUMBER, callback)):
+ for pn, txt in enumerate(ppt_parser(filename if binary is None else binary, from_page, MAXIMUM_PAGE_NUMBER, callback)):
d = copy.deepcopy(doc)
pn += from_page
d["doc_type_kwd"] = "image"
@@ -165,7 +165,7 @@ def chunk(filename, binary=None, from_page=0, to_page=MAXIMUM_PAGE_NUMBER, lang=
logging.warning(f"{error_msg} for {filename}.")
raise NotImplementedError(error_msg)
- if binary:
+ if binary is not None:
binary_data = binary
else:
with open(filename, "rb") as f:
diff --git a/test/unit_test/rag/app/test_email_empty_binary.py b/test/unit_test/rag/app/test_email_empty_binary.py
new file mode 100644
index 0000000000..ae8a0587c3
--- /dev/null
+++ b/test/unit_test/rag/app/test_email_empty_binary.py
@@ -0,0 +1,35 @@
+#
+# Copyright 2026 The InfiniFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from __future__ import annotations
+
+import pytest
+
+from rag.app import email
+
+
[email protected](autouse=True)
+def _stub_rag_tokenizer(monkeypatch):
+ def fake_tokenize(text):
+ return str(text)
+
+ monkeypatch.setattr("rag.nlp.rag_tokenizer.tokenize", fake_tokenize)
+ monkeypatch.setattr("rag.nlp.rag_tokenizer.fine_grained_tokenize", fake_tokenize)
+
+
+def test_empty_binary_does_not_open_display_name():
+ email.chunk("message.eml", binary=b"", callback=lambda *a, **k: None)