From ebdd71ce68e20d0e41a7cce0c324db23d04445b4 Mon Sep 17 00:00:00 2001 From: Jason Lee Date: Mon, 29 Jul 2024 09:43:05 +0800 Subject: [PATCH] fix: When parsing the bold content in PDF, the result is duplicated. (#1729) ### What problem does this PR solve? _fix: When parsing the bold content in PDF, the result is duplicated._ the detail: [When using OCR to recognize Chinese titles, the structure appears to be duplicated](https://github.com/infiniflow/ragflow/issues/1718) ### 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 4c04d9e4b..31a132adf 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, '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.page_chars = [[{**c, 'top': max(0, c['top'] - 10), 'bottom': max(0, c['bottom'] - 10)} for c in page.dedupe_chars().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: