From 923d3fbcae4a0b7ac789dbaf0ec120ebacac6455 Mon Sep 17 00:00:00 2001 From: Kenny Zhang Date: Tue, 11 Feb 2025 16:51:15 -0500 Subject: [PATCH] fixed analysis features bug for docx --- .../src/markitdown/converters/_doc_intel_converter.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py b/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py index 55973a7..faf26e7 100644 --- a/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py +++ b/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py @@ -61,8 +61,8 @@ class DocumentIntelligenceConverter(DocumentConverter): with open(local_path, "rb") as f: file_bytes = f.read() - # Certain document analysis features are not availiable for filetypes (.xlsx, .pptx, .html) - if extension.lower() in [".xlsx", ".pptx", ".html"]: + # Certain document analysis features are not availiable for office filetypes (.xlsx, .pptx, .html, .docx) + if extension.lower() in [".xlsx", ".pptx", ".html", ".docx"]: analysis_features = [] else: analysis_features = [