[Draft] Exploring ways to allow Optional dependencies

packages/markitdown/pyproject.toml

@@ -26,10 +26,8 @@ classifiers = [
 dependencies = [
   "beautifulsoup4",
   "requests",
-  "mammoth",
   "markdownify~=0.14.1",
   "numpy",
-  "python-pptx",
   "pandas",
   "openpyxl",
   "xlrd",
@@ -46,6 +44,14 @@ dependencies = [
   "azure-identity"
 ]
 
+[project.optional-dependencies]
+all = [
+  "python-pptx",
+  "mammoth"
+]
+pptx = ["python-pptx"]
+docx = ["mammoth"]
+
 [project.urls]
 Documentation = "https://github.com/microsoft/markitdown#readme"
 Issues = "https://github.com/microsoft/markitdown/issues"
@@ -57,6 +63,12 @@ path = "src/markitdown/__about__.py"
 [project.scripts]
 markitdown = "markitdown.__main__:main"
 
+[tool.hatch.envs.default]
+features = ["all"]
+
+[tool.hatch.envs.hatch-test]
+features = ["all"]
+
 [tool.hatch.envs.types]
 extra-dependencies = [
   "mypy>=1.0.0",

packages/markitdown/src/markitdown/__init__.py

@@ -6,7 +6,7 @@
 from ._markitdown import MarkItDown
 from ._exceptions import (
     MarkItDownException,
-    ConverterPrerequisiteException,
+    MissingDependencyException,
     FailedConversionAttempt,
     FileConversionException,
     UnsupportedFormatException,
@@ -19,7 +19,7 @@
     "DocumentConverter",
     "DocumentConverterResult",
     "MarkItDownException",
-    "ConverterPrerequisiteException",
+    "MissingDependencyException",
     "FailedConversionAttempt",
     "FileConversionException",
     "UnsupportedFormatException",

packages/markitdown/src/markitdown/_exceptions.py

@@ -9,15 +9,16 @@ class MarkItDownException(Exception):
     pass
 
 
-class ConverterPrerequisiteException(MarkItDownException):
+class MissingDependencyException(MarkItDownException):
     """
-    Thrown when instantiating a DocumentConverter in cases where
-    a required library or dependency is not installed, an API key
-    is not set, or some other prerequisite is not met.
-
-    This is not necessarily a fatal error. If thrown during
-    MarkItDown's plugin loading phase, the converter will simply be
-    skipped, and a warning will be issued.
+    Converters shipped with MarkItDown may depend on optional
+    dependencies. This exception is thrown when a converter's
+    convert() method is called, but the required dependency is not
+    installed. This is not necessarily a fatal error, as the converter
+    will simply be skipped (an error will bubble up only if no other
+    suitable converter is found).
+
+    Error messages should clearly indicate which dependency is missing.
     """
 
     pass

packages/markitdown/src/markitdown/_markitdown.py

@@ -42,7 +42,6 @@
 from ._exceptions import (
     FileConversionException,
     UnsupportedFormatException,
-    ConverterPrerequisiteException,
     FailedConversionAttempt,
 )
 

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

@@ -1,13 +1,23 @@
-from typing import Union
+import sys
 
-import mammoth
+from typing import Union
 
 from ._base import (
     DocumentConverterResult,
 )
 
 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 @@ def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
         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)

packages/markitdown/src/markitdown/converters/_pptx_converter.py

@@ -1,12 +1,22 @@
 import base64
-import pptx
 import re
 import html
+import sys
 
 from typing import Union
 
 from ._base import DocumentConverterResult, 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 pptx
+except ImportError:
+    # Preserve the error and stack trace for later
+    _dependency_exc_info = sys.exc_info()
 
 
 class PptxConverter(HtmlConverter):
@@ -54,9 +64,21 @@ def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
         if extension.lower() != ".pptx":
             return None
 
-        md_content = ""
+        # Load the dependencies
+        if _dependency_exc_info is not None:
+            raise MissingDependencyException(
+                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]
+* pip install markitdown[pptx, docx, ...]
+* etc."""
+            ) from _dependency_exc_info[1].with_traceback(
+                _dependency_exc_info[2]
+            )  # Restore the original traceback
 
         presentation = pptx.Presentation(local_path)
+        md_content = ""
         slide_num = 0
         for slide in presentation.slides:
             slide_num += 1