From 482c1b59c800e651e676acd8b0fcddeb862e31af Mon Sep 17 00:00:00 2001 From: Zhichang Yu Date: Fri, 22 Nov 2024 11:05:06 +0800 Subject: [PATCH] Check tika.parser return result (#3564) ### What problem does this PR solve? Check tika.parser return result. Close #3229 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) Co-authored-by: Yingfeng --- rag/app/naive.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/rag/app/naive.py b/rag/app/naive.py index dfaef0bec..2628fd546 100644 --- a/rag/app/naive.py +++ b/rag/app/naive.py @@ -263,9 +263,14 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, callback(0.1, "Start to parse.") binary = BytesIO(binary) doc_parsed = parser.from_buffer(binary) - sections = doc_parsed['content'].split('\n') - sections = [(_, "") for _ in sections if _] - callback(0.8, "Finish parsing.") + if doc_parsed.get('content', None) is not None: + sections = doc_parsed['content'].split('\n') + sections = [(_, "") for _ in sections if _] + callback(0.8, "Finish parsing.") + else: + callback(0.8, f"tika.parser got empty content from {filename}.") + logging.warning(f"tika.parser got empty content from {filename}.") + return [] else: raise NotImplementedError(