From 45853505bb64d9d20c8a169236f93f0a03f14514 Mon Sep 17 00:00:00 2001 From: Zhedong Cen Date: Thu, 27 Jun 2024 14:37:58 +0800 Subject: [PATCH] Fix occasional errors in pdf table recognition (#1277) ### What problem does this PR solve? Fix occasional errors in pdf table recognition ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --- deepdoc/parser/pdf_parser.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deepdoc/parser/pdf_parser.py b/deepdoc/parser/pdf_parser.py index ecfef8107..5bb9bffac 100644 --- a/deepdoc/parser/pdf_parser.py +++ b/deepdoc/parser/pdf_parser.py @@ -952,7 +952,7 @@ class RAGFlowPdfParser: fnm, str) else pdfplumber.open(BytesIO(fnm)) self.page_images = [p.to_image(resolution=72 * zoomin).annotated for i, p in enumerate(self.pdf.pages[page_from:page_to])] - self.page_chars = [[c for c in page.chars if self._has_color(c)] for page in + self.page_chars = [[{**c, 'top': max(0, c['top'] - 10), 'bottom': max(0, c['bottom'] - 10)} for c in page.chars if self._has_color(c)] for page in self.pdf.pages[page_from:page_to]] self.total_page = len(self.pdf.pages) except Exception as e: