From aba7a47b20148b880856c03cad0ad4f2ca9a8f86 Mon Sep 17 00:00:00 2001 From: chenrui7 Date: Thu, 29 Jan 2026 11:24:34 +0800 Subject: [PATCH] fix(parser): resolve chunk index mismatch in logs --- docreader/parser/base_parser.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docreader/parser/base_parser.py b/docreader/parser/base_parser.py index 30033987..eadd28e3 100644 --- a/docreader/parser/base_parser.py +++ b/docreader/parser/base_parser.py @@ -683,7 +683,7 @@ class BaseParser(ABC): Returns: List of image information """ - logger.info(f"Extracting image information from Chunk #{chunk.seq}") + logger.info(f"Extracting image information from Chunk #{chunk.seq + 1}") text = chunk.content # Regex to extract image information from text, @@ -692,7 +692,7 @@ class BaseParser(ABC): # Extract image information img_matches = list(re.finditer(img_pattern, text)) - logger.info(f"Chunk #{chunk.seq} found {len(img_matches)} images") + logger.info(f"Chunk #{chunk.seq + 1} found {len(img_matches)} images") images_info = [] for match_idx, match in enumerate(img_matches): @@ -711,9 +711,9 @@ class BaseParser(ABC): images_info.append(image_info) logger.info( - f"Image in Chunk #{chunk.seq} {match_idx + 1}: URL={img_url[:50]}..." + f"Image in Chunk #{chunk.seq + 1} {match_idx + 1}: URL={img_url[:50]}..." if len(img_url) > 50 - else f"Image in Chunk #{chunk.seq} {match_idx + 1}: URL={img_url}" + else f"Image in Chunk #{chunk.seq + 1} {match_idx + 1}: URL={img_url}" ) return images_info