From 98698a64ce24a1d74957a4b59aef1797f2f239bf Mon Sep 17 00:00:00 2001
From: Adam Fourney <adamfo@microsoft.com>
Date: Fri, 28 Feb 2025 17:06:59 -0800
Subject: [PATCH] Added .docx to optional dependencies

---
 packages/markitdown/pyproject.toml            |  7 +++--
 .../markitdown/converters/_docx_converter.py  | 27 +++++++++++++++++--
 .../markitdown/converters/_pptx_converter.py  |  2 +-
 3 files changed, 31 insertions(+), 5 deletions(-)

diff --git a/packages/markitdown/pyproject.toml b/packages/markitdown/pyproject.toml
index 3343eae..5e56642 100644
--- a/packages/markitdown/pyproject.toml
+++ b/packages/markitdown/pyproject.toml
@@ -26,7 +26,6 @@ classifiers = [
 dependencies = [
   "beautifulsoup4",
   "requests",
-  "mammoth",
   "markdownify~=0.14.1",
   "numpy",
   "pandas",
@@ -46,8 +45,12 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
-all = ["python-pptx"]
+all = [
+  "python-pptx",
+  "mammoth"
+]
 pptx = ["python-pptx"]
+docx = ["mammoth"]
 
 [project.urls]
 Documentation = "https://github.com/microsoft/markitdown#readme"
diff --git a/packages/markitdown/src/markitdown/converters/_docx_converter.py b/packages/markitdown/src/markitdown/converters/_docx_converter.py
index 8515f6d..b68500f 100644
--- a/packages/markitdown/src/markitdown/converters/_docx_converter.py
+++ b/packages/markitdown/src/markitdown/converters/_docx_converter.py
@@ -1,6 +1,6 @@
-from typing import Union
+import sys
 
-import mammoth
+from typing import Union
 
 from ._base import (
     DocumentConverterResult,
@@ -8,6 +8,16 @@ from ._base import (
 
 from ._base import DocumentConverter
 from ._html_converter import HtmlConverter
+from .._exceptions import MissingDependencyException
+
+# Try loading optional (but in this case, required) dependencies
+# Save reporting of any exceptions for later
+_dependency_exc_info = None
+try:
+    import mammoth
+except ImportError:
+    # Preserve the error and stack trace for later
+    _dependency_exc_info = sys.exc_info()
 
 
 class DocxConverter(HtmlConverter):
@@ -26,6 +36,19 @@ class DocxConverter(HtmlConverter):
         if extension.lower() != ".docx":
             return None
 
+        # Load the dependencies
+        if _dependency_exc_info is not None:
+            raise MissingDependencyException(
+                f"""{type(self).__name__} recognized the input as a potential .docx file, but the dependencies needed to read .docx files have not been installed. To resolve this error, include the optional dependency [docx] or [all] when installing MarkItDown. For example:
+
+* pip install markitdown[docx]
+* pip install markitdown[all]
+* pip install markitdown[pptx, docx, ...]
+* etc."""
+            ) from _dependency_exc_info[1].with_traceback(
+                _dependency_exc_info[2]
+            )  # Restore the original traceback
+
         result = None
         with open(local_path, "rb") as docx_file:
             style_map = kwargs.get("style_map", None)
diff --git a/packages/markitdown/src/markitdown/converters/_pptx_converter.py b/packages/markitdown/src/markitdown/converters/_pptx_converter.py
index 34d4fbd..7d72c1b 100644
--- a/packages/markitdown/src/markitdown/converters/_pptx_converter.py
+++ b/packages/markitdown/src/markitdown/converters/_pptx_converter.py
@@ -67,7 +67,7 @@ class PptxConverter(HtmlConverter):
         # Load the dependencies
         if _dependency_exc_info is not None:
             raise MissingDependencyException(
-                f"""{type(self).__name__} recognized the input as a .pptx file, but the dependencies needed to read .pptx files have not been installed. To resolve this error, include the optional dependency [pptx] or [all] when installing MarkItDown. For example:
+                f"""{type(self).__name__} recognized the input as a potential .pptx file, but the dependencies needed to read .pptx files have not been installed. To resolve this error, include the optional dependency [pptx] or [all] when installing MarkItDown. For example:
 
 * pip install markitdown[pptx]
 * pip install markitdown[all]