From c3aa8053c0e20b3eb0df4eace62528062fdc01a5 Mon Sep 17 00:00:00 2001 From: Yash Raj Pandey <55940078+devYRPauli@users.noreply.github.com> Date: Wed, 29 Jul 2026 05:01:07 -0400 Subject: [PATCH] Fix tag CSV parser ignoring the documented TAB delimiter (#17496) --- rag/app/tag.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/rag/app/tag.py b/rag/app/tag.py index 656226a792..da7b4bda24 100644 --- a/rag/app/tag.py +++ b/rag/app/tag.py @@ -92,11 +92,12 @@ def chunk(filename, binary=None, lang="Chinese", callback=None, **kwargs): callback(0.1, "Start to parse.") txt = get_text(filename, binary) lines = txt.split("\n") + delimiter = "\t" if any("\t" in line for line in lines) else "," fails = [] content = "" res = [] - reader = csv.reader((line + "\n" for line in lines)) + reader = csv.reader((line + "\n" for line in lines), delimiter=delimiter) prev_line_num = 0 # line_num tracks the physical span when quoted fields cross lines.