From ca391f4908f44f301de54a97057f0b809f5ce66c Mon Sep 17 00:00:00 2001 From: Qiefan Jiang Date: Tue, 1 Jul 2025 19:38:29 +0800 Subject: [PATCH 1/2] feat(msexcel): ignore invisible sheet --- docling/backend/msexcel_backend.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/docling/backend/msexcel_backend.py b/docling/backend/msexcel_backend.py index 0ae90831..e8ff911a 100644 --- a/docling/backend/msexcel_backend.py +++ b/docling/backend/msexcel_backend.py @@ -186,9 +186,12 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentBacken if self.workbook is not None: # Iterate over all sheets for sheet_name in self.workbook.sheetnames: + sheet = self.workbook[sheet_name] + if sheet.sheet_state != Worksheet.SHEETSTATE_VISIBLE: + _log.info(f"Ignore invisible sheet: {sheet_name}") + continue _log.info(f"Processing sheet: {sheet_name}") - sheet = self.workbook[sheet_name] page_no = self.workbook.index(sheet) + 1 # do not rely on sheet.max_column, sheet.max_row if there are images page = doc.add_page(page_no=page_no, size=Size(width=0, height=0)) From d90442488cceda746396ac31bed1e2e243073e1b Mon Sep 17 00:00:00 2001 From: Qiefan Jiang Date: Tue, 1 Jul 2025 19:45:43 +0800 Subject: [PATCH 2/2] DCO Remediation Commit for Qiefan Jiang I, Qiefan Jiang , hereby add my Signed-off-by to this commit: ca391f4908f44f301de54a97057f0b809f5ce66c Signed-off-by: Qiefan Jiang