Skip to content

fix: handle BadZipFile for corrupted media in PPTX converter #1670

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
octo-patch wants to merge 1 commit into
base: main
Choose a base branch
from
+43 −28
Open

fix: handle BadZipFile for corrupted media in PPTX converter #1670

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
71 changes: 43 additions & 28 deletions packages/markitdown/src/markitdown/converters/_pptx_converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,11 @@
import sys
import base64
import logging
import os
import io
import re
import html
import zipfile

from typing import BinaryIO, Any
from operator import attrgetter
Expand Down Expand Up @@ -102,31 +104,37 @@ def get_shape_content(shape, **kwargs):
llm_client = kwargs.get("llm_client")
llm_model = kwargs.get("llm_model")
if llm_client is not None and llm_model is not None:
# Prepare a file_stream and stream_info for the image data
image_filename = shape.image.filename
image_extension = None
if image_filename:
image_extension = os.path.splitext(image_filename)[1]
image_stream_info = StreamInfo(
mimetype=shape.image.content_type,
extension=image_extension,
filename=image_filename,
)

image_stream = io.BytesIO(shape.image.blob)

# Caption the image
try:
llm_description = llm_caption(
image_stream,
image_stream_info,
client=llm_client,
model=llm_model,
prompt=kwargs.get("llm_prompt"),
# Prepare a file_stream and stream_info for the image data
image_filename = shape.image.filename
image_extension = None
if image_filename:
image_extension = os.path.splitext(image_filename)[1]
image_stream_info = StreamInfo(
mimetype=shape.image.content_type,
extension=image_extension,
filename=image_filename,
)

image_stream = io.BytesIO(shape.image.blob)

# Caption the image
try:
llm_description = llm_caption(
image_stream,
image_stream_info,
client=llm_client,
model=llm_model,
prompt=kwargs.get("llm_prompt"),
)
except Exception:
# Unable to generate a description
pass
except (zipfile.BadZipFile, Exception):
# Unable to read media file (e.g., corrupted CRC)
logging.warning(
f"Unable to read media for shape '{shape.name}': skipping image content."
)
except Exception:
# Unable to generate a description
pass

# Also grab any description embedded in the deck
try:
Expand All @@ -136,16 +144,23 @@ def get_shape_content(shape, **kwargs):
pass

# Prepare the alt, escaping any special characters
alt_text = "\n".join([llm_description, alt_text]) or shape.name
alt_text = "\n".join(filter(None, [llm_description, alt_text])) or shape.name
alt_text = re.sub(r"[\r\n\[\]]", " ", alt_text)
alt_text = re.sub(r"\s+", " ", alt_text).strip()

# If keep_data_uris is True, use base64 encoding for images
if kwargs.get("keep_data_uris", False):
blob = shape.image.blob
content_type = shape.image.content_type or "image/png"
b64_string = base64.b64encode(blob).decode("utf-8")
md_content += f"\n![{alt_text}](data:{content_type};base64,{b64_string})\n"
try:
blob = shape.image.blob
content_type = shape.image.content_type or "image/png"
b64_string = base64.b64encode(blob).decode("utf-8")
md_content += f"\n![{alt_text}](data:{content_type};base64,{b64_string})\n"
except (zipfile.BadZipFile, Exception):
logging.warning(
f"Unable to read image data for shape '{shape.name}': using placeholder."
)
filename = re.sub(r"\W", "", shape.name) + ".jpg"
md_content += "\n![" + alt_text + "](" + filename + ")\n"
else:
# A placeholder name
filename = re.sub(r"\W", "", shape.name) + ".jpg"
Expand Down