From 97eeed5f325d15ab3f1bc65e6a4f146c4e7e0680 Mon Sep 17 00:00:00 2001
From: KennyZhang1 <90438893+KennyZhang1@users.noreply.github.com>
Date: Tue, 11 Feb 2025 19:01:46 -0500
Subject: [PATCH] Doc Intelligence fixes for refactored code (#325)

* added priority flag to doc intel converter constructor
* fixed analysis features bug for docx
---
 .../src/markitdown/converters/_doc_intel_converter.py       | 6 ++++--
 1 file changed, 4 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 835345a..ed8aabf 100644
--- a/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py
+++ b/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py
@@ -1,4 +1,5 @@
 from typing import Any, Union
+import re
 
 # Azure imports
 from azure.ai.documentintelligence import DocumentIntelligenceClient
@@ -36,6 +37,7 @@ class DocumentIntelligenceConverter(DocumentConverter):
             api_version=self.api_version,
             credential=DefaultAzureCredential(),
         )
+        self._priority = priority
 
     def convert(
         self, local_path: str, **kwargs: Any
@@ -62,8 +64,8 @@ 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 = [