Resolved an issue with linked images in docx [mammoth] (#1405)

packages/markitdown/pyproject.toml

@@ -36,7 +36,7 @@ dependencies = [
 [project.optional-dependencies]
 all = [
   "python-pptx",
-  "mammoth",
+  "mammoth~=1.10.0",
   "pandas",
   "openpyxl",
   "xlrd",

packages/markitdown/src/markitdown/__about__.py

@@ -1,4 +1,4 @@
 # SPDX-FileCopyrightText: 2024-present Adam Fourney <adamfo@microsoft.com>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.1.2"
+__version__ = "0.1.3"

packages/markitdown/src/markitdown/converters/_docx_converter.py

@@ -1,4 +1,6 @@
 import sys
+import io
+from warnings import warn
 
 from typing import BinaryIO, Any
 
@@ -13,6 +15,14 @@ from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
 _dependency_exc_info = None
 try:
     import mammoth
+    import mammoth.docx.files
+
+    def mammoth_files_open(self, uri):
+        warn("DOCX: processing of r:link resources (e.g., linked images) is disabled.")
+        return io.BytesIO(b"")
+
+    mammoth.docx.files.Files.open = mammoth_files_open
+
 except ImportError:
     # Preserve the error and stack trace for later
     _dependency_exc_info = sys.exc_info()