Merge pull request #102 from microsoft/bump_version

Bump version.

.dockerignore

@@ -0,0 +1 @@
+*

.gitattributes

@@ -0,0 +1 @@
+tests/test_files/** linguist-vendored

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.13-alpine
+
+USER root
+
+# Runtime dependency
+RUN apk add --no-cache ffmpeg
+
+RUN pip install markitdown
+
+# Default USERID and GROUPID
+ARG USERID=10000
+ARG GROUPID=10000
+
+USER $USERID:$GROUPID
+
+ENTRYPOINT [ "markitdown" ]

README.md

@@ -1,5 +1,7 @@
 # MarkItDown
 
+[![PyPI](https://img.shields.io/pypi/v/markitdown.svg)](https://pypi.org/project/markitdown/)
+
 The MarkItDown library is a utility tool for converting various files to Markdown (e.g., for indexing, text analysis, etc.)
 
 It presently supports:
@@ -12,7 +14,23 @@ It presently supports:
 - Audio (EXIF metadata, and speech transcription)
 - HTML (special handling of Wikipedia, etc.)
 - Various other text-based formats (csv, json, xml, etc.)
+- ZIP (Iterates over contents and converts each file)
 
+# Installation
+
+You can install `markitdown` using pip:
+
+```python
+pip install markitdown
+```
+
+or from the source
+
+```sh
+pip install -e .
+```
+
+# Usage
 The API is simple:
 
 ```python
@@ -23,6 +41,44 @@ result = markitdown.convert("test.xlsx")
 print(result.text_content)
 ```
 
+To use this as a command-line utility, install it and then run it like this:
+
+```bash
+markitdown path-to-file.pdf
+```
+
+This will output Markdown to standard output. You can save it like this:
+
+```bash
+markitdown path-to-file.pdf > document.md
+```
+
+You can pipe content to standard input by omitting the argument:
+
+```bash
+cat path-to-file.pdf | markitdown
+```
+
+You can also configure markitdown to use Large Language Models to describe images. To do so you must provide `llm_client` and `llm_model` parameters to MarkItDown object, according to your specific client.
+
+
+```python
+from markitdown import MarkItDown
+from openai import OpenAI
+
+client = OpenAI()
+md = MarkItDown(llm_client=client, llm_model="gpt-4o")
+result = md.convert("example.jpg")
+print(result.text_content)
+```
+
+You can also use the project as Docker Image:
+
+```sh
+docker build -t markitdown:latest .
+docker run --rm -i markitdown:latest < ~/your-file.pdf > output.md
+```
+
 ## Contributing
 
 This project welcomes contributions and suggestions.  Most contributions require you to agree to a
@@ -37,6 +93,24 @@ This project has adopted the [Microsoft Open Source Code of Conduct](https://ope
 For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
 contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.
 
+### Running Tests
+
+To run tests, install `hatch` using `pip` or other methods as described [here](https://hatch.pypa.io/dev/install).
+
+```sh
+pip install hatch
+hatch shell
+hatch test
+```
+
+### Running Pre-commit Checks
+
+Please run the pre-commit checks before submitting a PR.
+
+```sh
+pre-commit run --all-files
+```
+
 ## Trademarks
 
 This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft 

pyproject.toml

@@ -38,7 +38,8 @@ dependencies = [
   "youtube-transcript-api",
   "SpeechRecognition",
   "pathvalidate",
-  "pygithub"
+  "charset-normalizer",
+  "openai",
 ]
 
 [project.urls]
@@ -77,3 +78,6 @@ exclude_lines = [
   "if __name__ == .__main__.:",
   "if TYPE_CHECKING:",
 ]
+
+[tool.hatch.build.targets.sdist]
+only-include = ["src/markitdown"]

src/markitdown/__about__.py

@@ -1,4 +1,4 @@
 # SPDX-FileCopyrightText: 2024-present Adam Fourney <adamfo@microsoft.com>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.1a1"
+__version__ = "0.0.1a3"

src/markitdown/__main__.py

@@ -2,21 +2,15 @@
 #
 # SPDX-License-Identifier: MIT
 import sys
+import argparse
 from ._markitdown import MarkItDown
 
 
 def main():
-    if len(sys.argv) == 1:
+    parser = argparse.ArgumentParser(
-        markitdown = MarkItDown()
+        description="Convert various file formats to markdown.",
-        result = markitdown.convert_stream(sys.stdin.buffer)
+        formatter_class=argparse.RawDescriptionHelpFormatter,
-        print(result.text_content)
+        usage="""
-    elif len(sys.argv) == 2:
-        markitdown = MarkItDown()
-        result = markitdown.convert(sys.argv[1])
-        print(result.text_content)
-    else:
-        sys.stderr.write(
-            """
 SYNTAX: 
     
     markitdown <OPTIONAL: FILENAME>
@@ -33,9 +27,20 @@ EXAMPLE:
     OR 
 
     markitdown < example.pdf
-""".strip()
+""".strip(),
-            + "\n"
+    )
-        )
+
+    parser.add_argument("filename", nargs="?")
+    args = parser.parse_args()
+
+    if args.filename is None:
+        markitdown = MarkItDown()
+        result = markitdown.convert_stream(sys.stdin.buffer)
+        print(result.text_content)
+    else:
+        markitdown = MarkItDown()
+        result = markitdown.convert(args.filename)
+        print(result.text_content)
 
 
 if __name__ == "__main__":

src/markitdown/_markitdown.py

@@ -12,8 +12,10 @@ import subprocess
 import sys
 import tempfile
 import traceback
+import zipfile
 from typing import Any, Dict, List, Optional, Union
 from urllib.parse import parse_qs, quote, unquote, urlparse, urlunparse
+from warnings import warn, resetwarnings, catch_warnings
 
 import mammoth
 import markdownify
@@ -26,15 +28,24 @@ import pptx
 import puremagic
 import requests
 from bs4 import BeautifulSoup
+from charset_normalizer import from_path
 
 # Optional Transcription support
 try:
-    import pydub
+    # Using warnings' catch_warnings to catch
+    # pydub's warning of ffmpeg or avconv missing
+    with catch_warnings(record=True) as w:
+        import pydub
+
+        if w:
+            raise ModuleNotFoundError
     import speech_recognition as sr
 
     IS_AUDIO_TRANSCRIPTION_CAPABLE = True
 except ModuleNotFoundError:
     pass
+finally:
+    resetwarnings()
 
 # Optional YouTube transcription support
 try:
@@ -44,14 +55,6 @@ try:
 except ModuleNotFoundError:
     pass
 
-# Optional GitHub issue support
-try:
-    from github import Github
-
-    IS_GITHUB_ISSUE_CAPABLE = True
-except ModuleNotFoundError:
-    IS_GITHUB_ISSUE_CAPABLE = False
-
 
 class _CustomMarkdownify(markdownify.MarkdownConverter):
     """
@@ -169,9 +172,7 @@ class PlainTextConverter(DocumentConverter):
         elif "text/" not in content_type.lower():
             return None
 
-        text_content = ""
+        text_content = str(from_path(local_path).best())
-        with open(local_path, "rt", encoding="utf-8") as fh:
-            text_content = fh.read()
         return DocumentConverterResult(
             title=None,
             text_content=text_content,
@@ -352,8 +353,11 @@ class YouTubeConverter(DocumentConverter):
                 assert isinstance(params["v"][0], str)
                 video_id = str(params["v"][0])
                 try:
+                    youtube_transcript_languages = kwargs.get(
+                        "youtube_transcript_languages", ("en",)
+                    )
                     # Must be a single transcript.
-                    transcript = YouTubeTranscriptApi.get_transcript(video_id)  # type: ignore
+                    transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=youtube_transcript_languages)  # type: ignore
                     transcript_text = " ".join([part["text"] for part in transcript])  # type: ignore
                     # Alternative formatting:
                     # formatter = TextFormatter()
@@ -500,7 +504,9 @@ class DocxConverter(HtmlConverter):
 
         result = None
         with open(local_path, "rb") as docx_file:
-            result = mammoth.convert_to_html(docx_file)
+            style_map = kwargs.get("style_map", None)
+
+            result = mammoth.convert_to_html(docx_file, style_map=style_map)
             html_content = result.value
             result = self._convert(html_content)
 
@@ -590,6 +596,10 @@ class PptxConverter(HtmlConverter):
                         "\n" + self._convert(html_table).text_content.strip() + "\n"
                     )
 
+                # Charts
+                if shape.has_chart:
+                    md_content += self._convert_chart_to_markdown(shape.chart)
+
                 # Text areas
                 elif shape.has_text_frame:
                     if shape == title:
@@ -624,6 +634,29 @@ class PptxConverter(HtmlConverter):
             return True
         return False
 
+    def _convert_chart_to_markdown(self, chart):
+        md = "\n\n### Chart"
+        if chart.has_title:
+            md += f": {chart.chart_title.text_frame.text}"
+        md += "\n\n"
+        data = []
+        category_names = [c.label for c in chart.plots[0].categories]
+        series_names = [s.name for s in chart.series]
+        data.append(["Category"] + series_names)
+
+        for idx, category in enumerate(category_names):
+            row = [category]
+            for series in chart.series:
+                row.append(series.values[idx])
+            data.append(row)
+
+        markdown_table = []
+        for row in data:
+            markdown_table.append("| " + " | ".join(map(str, row)) + " |")
+        header = markdown_table[0]
+        separator = "|" + "|".join(["---"] * len(data[0])) + "|"
+        return md + "\n".join([header, separator] + markdown_table[1:])
+
 
 class MediaConverter(DocumentConverter):
     """
@@ -762,7 +795,7 @@ class Mp3Converter(WavConverter):
 
 class ImageConverter(MediaConverter):
     """
-    Converts images to markdown via extraction of metadata (if `exiftool` is installed), OCR (if `easyocr` is installed), and description via a multimodal LLM (if an mlm_client is configured).
+    Converts images to markdown via extraction of metadata (if `exiftool` is installed), OCR (if `easyocr` is installed), and description via a multimodal LLM (if an llm_client is configured).
     """
 
     def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
@@ -792,17 +825,17 @@ class ImageConverter(MediaConverter):
                     md_content += f"{f}: {metadata[f]}\n"
 
         # Try describing the image with GPTV
-        mlm_client = kwargs.get("mlm_client")
+        llm_client = kwargs.get("llm_client")
-        mlm_model = kwargs.get("mlm_model")
+        llm_model = kwargs.get("llm_model")
-        if mlm_client is not None and mlm_model is not None:
+        if llm_client is not None and llm_model is not None:
             md_content += (
                 "\n# Description:\n"
-                + self._get_mlm_description(
+                + self._get_llm_description(
                     local_path,
                     extension,
-                    mlm_client,
+                    llm_client,
-                    mlm_model,
+                    llm_model,
-                    prompt=kwargs.get("mlm_prompt"),
+                    prompt=kwargs.get("llm_prompt"),
                 ).strip()
                 + "\n"
             )
@@ -812,12 +845,10 @@ class ImageConverter(MediaConverter):
             text_content=md_content,
         )
 
-    def _get_mlm_description(self, local_path, extension, client, model, prompt=None):
+    def _get_llm_description(self, local_path, extension, client, model, prompt=None):
         if prompt is None or prompt.strip() == "":
             prompt = "Write a detailed caption for this image."
 
-        sys.stderr.write(f"MLM Prompt:\n{prompt}\n")
-
         data_uri = ""
         with open(local_path, "rb") as image_file:
             content_type, encoding = mimetypes.guess_type("_dummy" + extension)
@@ -845,126 +876,122 @@ class ImageConverter(MediaConverter):
         return response.choices[0].message.content
 
 
-class GitHubIssueConverter(DocumentConverter):
+class ZipConverter(DocumentConverter):
-    """Converts GitHub issues and pull requests to Markdown."""
+    """Converts ZIP files to markdown by extracting and converting all contained files.
 
-    def convert(self, github_url, github_token) -> Union[None, DocumentConverterResult]:
+    The converter extracts the ZIP contents to a temporary directory, processes each file
-        # Bail if not a valid GitHub issue or pull request URL
+    using appropriate converters based on file extensions, and then combines the results
-        if github_url:
+    into a single markdown document. The temporary directory is cleaned up after processing.
-            parsed_url = urlparse(github_url)
-            path_parts = parsed_url.path.strip("/").split("/")
-            if len(path_parts) < 4 or path_parts[2] not in ["issues", "pull"]:
-                return None
 
-            if not github_token:
+    Example output format:
-                raise ValueError(
+    ```markdown
-                    "GitHub token is not set. Cannot convert GitHub issue or pull request."
+    Content from the zip file `example.zip`:
-                )
 
-            if path_parts[2] == "issues":
+    ## File: docs/readme.txt
-                return self._convert_github_issue(github_url, github_token)
-            elif path_parts[2] == "pull":
-                return self._convert_github_pr(github_url, github_token)
 
-        return None
+    This is the content of readme.txt
+    Multiple lines are preserved
 
-    def _convert_github_issue(
+    ## File: images/example.jpg
-        self, issue_url: str, github_token: str
+
-    ) -> DocumentConverterResult:
+    ImageSize: 1920x1080
-        """
+    DateTimeOriginal: 2024-02-15 14:30:00
-        Convert a GitHub issue to a markdown document.
+    Description: A beautiful landscape photo
-        Args:
+
-            issue_url (str): The URL of the GitHub issue to convert.
+    ## File: data/report.xlsx
-            github_token (str): A GitHub token with access to the repository.
+
-        Returns:
+    ## Sheet1
-            DocumentConverterResult: The result containing the issue title and markdown content.
+    | Column1 | Column2 | Column3 |
-        Raises:
+    |---------|---------|---------|
-            ImportError: If the PyGithub library is not installed.
+    | data1   | data2   | data3   |
-            ValueError: If the provided URL is not a valid GitHub issue URL.
+    | data4   | data5   | data6   |
-        """
+    ```
-        if not IS_GITHUB_ISSUE_CAPABLE:
+
-            raise ImportError(
+    Key features:
-                "PyGithub is not installed. Please install it to use this feature."
+    - Maintains original file structure in headings
+    - Processes nested files recursively
+    - Uses appropriate converters for each file type
+    - Preserves formatting of converted content
+    - Cleans up temporary files after processing
+    """
+
+    def convert(
+        self, local_path: str, **kwargs: Any
+    ) -> Union[None, DocumentConverterResult]:
+        # Bail if not a ZIP
+        extension = kwargs.get("file_extension", "")
+        if extension.lower() != ".zip":
+            return None
+
+        # Get parent converters list if available
+        parent_converters = kwargs.get("_parent_converters", [])
+        if not parent_converters:
+            return DocumentConverterResult(
+                title=None,
+                text_content=f"[ERROR] No converters available to process zip contents from: {local_path}",
             )
 
-        # Parse the issue URL
+        extracted_zip_folder_name = (
-        parsed_url = urlparse(issue_url)
+            f"extracted_{os.path.basename(local_path).replace('.zip', '_zip')}"
-        path_parts = parsed_url.path.strip("/").split("/")
-        if len(path_parts) < 4 or path_parts[2] != "issues":
-            raise ValueError("Invalid GitHub issue URL")
-
-        owner, repo, _, issue_number = path_parts[:4]
-
-        # Authenticate with GitHub
-        g = Github(github_token)
-        repo = g.get_repo(f"{owner}/{repo}")
-        issue = repo.get_issue(int(issue_number))
-
-        # Convert issue details to markdown
-        markdown_content = f"# {issue.title}\n\n{issue.body}\n\n"
-        markdown_content += f"**State:** {issue.state}\n"
-        markdown_content += f"**Created at:** {issue.created_at}\n"
-        markdown_content += f"**Updated at:** {issue.updated_at}\n"
-        markdown_content += f"**Comments:**\n"
-
-        for comment in issue.get_comments():
-            markdown_content += (
-                f"- {comment.user.login} ({comment.created_at}): {comment.body}\n"
-            )
-
-        return DocumentConverterResult(
-            title=issue.title,
-            text_content=markdown_content,
         )
-
+        new_folder = os.path.normpath(
-    def _convert_github_pr(
+            os.path.join(os.path.dirname(local_path), extracted_zip_folder_name)
-        self, pr_url: str, github_token: str
-    ) -> DocumentConverterResult:
-        """
-        Convert a GitHub pull request to a markdown document.
-        Args:
-            pr_url (str): The URL of the GitHub pull request to convert.
-            github_token (str): A GitHub token with access to the repository.
-        Returns:
-            DocumentConverterResult: The result containing the pull request title and markdown content.
-        Raises:
-            ImportError: If the PyGithub library is not installed.
-            ValueError: If the provided URL is not a valid GitHub pull request URL.
-        """
-        if not IS_GITHUB_ISSUE_CAPABLE:
-            raise ImportError(
-                "PyGithub is not installed. Please install it to use this feature."
-            )
-
-        # Parse the pull request URL
-        parsed_url = urlparse(pr_url)
-        path_parts = parsed_url.path.strip("/").split("/")
-        if len(path_parts) < 4 or path_parts[2] != "pull":
-            raise ValueError("Invalid GitHub pull request URL")
-
-        owner, repo, _, pr_number = path_parts[:4]
-
-        # Authenticate with GitHub
-        g = Github(github_token)
-        repo = g.get_repo(f"{owner}/{repo}")
-        pr = repo.get_pull(int(pr_number))
-
-        # Convert pull request details to markdown
-        markdown_content = f"# {pr.title}\n\n{pr.body}\n\n"
-        markdown_content += f"**State:** {pr.state}\n"
-        markdown_content += f"**Created at:** {pr.created_at}\n"
-        markdown_content += f"**Updated at:** {pr.updated_at}\n"
-        markdown_content += f"**Comments:**\n"
-
-        for comment in pr.get_issue_comments():
-            markdown_content += (
-                f"- {comment.user.login} ({comment.created_at}): {comment.body}\n"
-            )
-
-        return DocumentConverterResult(
-            title=pr.title,
-            text_content=markdown_content,
         )
+        md_content = f"Content from the zip file `{os.path.basename(local_path)}`:\n\n"
+
+        # Safety check for path traversal
+        if not new_folder.startswith(os.path.dirname(local_path)):
+            return DocumentConverterResult(
+                title=None, text_content=f"[ERROR] Invalid zip file path: {local_path}"
+            )
+
+        try:
+            # Extract the zip file
+            with zipfile.ZipFile(local_path, "r") as zipObj:
+                zipObj.extractall(path=new_folder)
+
+            # Process each extracted file
+            for root, dirs, files in os.walk(new_folder):
+                for name in files:
+                    file_path = os.path.join(root, name)
+                    relative_path = os.path.relpath(file_path, new_folder)
+
+                    # Get file extension
+                    _, file_extension = os.path.splitext(name)
+
+                    # Update kwargs for the file
+                    file_kwargs = kwargs.copy()
+                    file_kwargs["file_extension"] = file_extension
+                    file_kwargs["_parent_converters"] = parent_converters
+
+                    # Try converting the file using available converters
+                    for converter in parent_converters:
+                        # Skip the zip converter to avoid infinite recursion
+                        if isinstance(converter, ZipConverter):
+                            continue
+
+                        result = converter.convert(file_path, **file_kwargs)
+                        if result is not None:
+                            md_content += f"\n## File: {relative_path}\n\n"
+                            md_content += result.text_content + "\n\n"
+                            break
+
+            # Clean up extracted files if specified
+            if kwargs.get("cleanup_extracted", True):
+                shutil.rmtree(new_folder)
+
+            return DocumentConverterResult(title=None, text_content=md_content.strip())
+
+        except zipfile.BadZipFile:
+            return DocumentConverterResult(
+                title=None,
+                text_content=f"[ERROR] Invalid or corrupted zip file: {local_path}",
+            )
+        except Exception as e:
+            return DocumentConverterResult(
+                title=None,
+                text_content=f"[ERROR] Failed to process zip file {local_path}: {str(e)}",
+            )
 
 
 class FileConversionException(BaseException):
@@ -982,16 +1009,50 @@ class MarkItDown:
     def __init__(
         self,
         requests_session: Optional[requests.Session] = None,
+        llm_client: Optional[Any] = None,
+        llm_model: Optional[str] = None,
+        style_map: Optional[str] = None,
+        # Deprecated
         mlm_client: Optional[Any] = None,
-        mlm_model: Optional[Any] = None,
+        mlm_model: Optional[str] = None,
     ):
         if requests_session is None:
             self._requests_session = requests.Session()
         else:
             self._requests_session = requests_session
 
-        self._mlm_client = mlm_client
+        # Handle deprecation notices
-        self._mlm_model = mlm_model
+        #############################
+        if mlm_client is not None:
+            if llm_client is None:
+                warn(
+                    "'mlm_client' is deprecated, and was renamed 'llm_client'.",
+                    DeprecationWarning,
+                )
+                llm_client = mlm_client
+                mlm_client = None
+            else:
+                raise ValueError(
+                    "'mlm_client' is deprecated, and was renamed 'llm_client'. Do not use both at the same time. Just use 'llm_client' instead."
+                )
+
+        if mlm_model is not None:
+            if llm_model is None:
+                warn(
+                    "'mlm_model' is deprecated, and was renamed 'llm_model'.",
+                    DeprecationWarning,
+                )
+                llm_model = mlm_model
+                mlm_model = None
+            else:
+                raise ValueError(
+                    "'mlm_model' is deprecated, and was renamed 'llm_model'. Do not use both at the same time. Just use 'llm_model' instead."
+                )
+        #############################
+
+        self._llm_client = llm_client
+        self._llm_model = llm_model
+        self._style_map = style_map
 
         self._page_converters: List[DocumentConverter] = []
 
@@ -1010,6 +1071,7 @@ class MarkItDown:
         self.register_page_converter(Mp3Converter())
         self.register_page_converter(ImageConverter())
         self.register_page_converter(PdfConverter())
+        self.register_page_converter(ZipConverter())
 
     def convert(
         self, source: Union[str, requests.Response], **kwargs: Any
@@ -1019,6 +1081,7 @@ class MarkItDown:
             - source: can be a string representing a path or url, or a requests.response object
             - extension: specifies the file extension to use when interpreting the file. If None, infer from source (path, uri, content-type, etc.)
         """
+
         # Local path or url
         if isinstance(source, str):
             if (
@@ -1033,28 +1096,6 @@ class MarkItDown:
         elif isinstance(source, requests.Response):
             return self.convert_response(source, **kwargs)
 
-    def convert_url(
-        self, url: str, **kwargs: Any
-    ) -> DocumentConverterResult:  # TODO: fix kwargs type
-        # Handle GitHub issue and pull request URLs directly
-        parsed_url = urlparse(url)
-        if parsed_url.hostname == "github.com" and any(
-            x in parsed_url.path for x in ["/issues/", "/pull/"]
-        ):
-            github_token = kwargs.get("github_token", os.getenv("GITHUB_TOKEN"))
-            if not github_token:
-                raise ValueError(
-                    "GitHub token is required for GitHub issue or pull request conversion."
-                )
-            return GitHubIssueConverter().convert(
-                github_url=url, github_token=github_token
-            )
-
-        # Send a HTTP request to the URL
-        response = self._requests_session.get(url, stream=True)
-        response.raise_for_status()
-        return self.convert_response(response, **kwargs)
-
     def convert_local(
         self, path: str, **kwargs: Any
     ) -> DocumentConverterResult:  # TODO: deal with kwargs
@@ -1109,6 +1150,14 @@ class MarkItDown:
 
         return result
 
+    def convert_url(
+        self, url: str, **kwargs: Any
+    ) -> DocumentConverterResult:  # TODO: fix kwargs type
+        # Send a HTTP request to the URL
+        response = self._requests_session.get(url, stream=True)
+        response.raise_for_status()
+        return self.convert_response(response, **kwargs)
+
     def convert_response(
         self, response: requests.Response, **kwargs: Any
     ) -> DocumentConverterResult:  # TODO fix kwargs type
@@ -1146,7 +1195,7 @@ class MarkItDown:
                 self._append_ext(extensions, g)
 
             # Convert
-            result = self._convert(temp_path, extensions, url=response.url)
+            result = self._convert(temp_path, extensions, url=response.url, **kwargs)
         # Clean up
         finally:
             try:
@@ -1173,11 +1222,17 @@ class MarkItDown:
                     _kwargs.update({"file_extension": ext})
 
                 # Copy any additional global options
-                if "mlm_client" not in _kwargs and self._mlm_client is not None:
+                if "llm_client" not in _kwargs and self._llm_client is not None:
-                    _kwargs["mlm_client"] = self._mlm_client
+                    _kwargs["llm_client"] = self._llm_client
 
-                if "mlm_model" not in _kwargs and self._mlm_model is not None:
+                if "llm_model" not in _kwargs and self._llm_model is not None:
-                    _kwargs["mlm_model"] = self._mlm_model
+                    _kwargs["llm_model"] = self._llm_model
+
+                # Add the list of converters for nested processing
+                _kwargs["_parent_converters"] = self._page_converters
+
+                if "style_map" not in _kwargs and self._style_map is not None:
+                    _kwargs["style_map"] = self._style_map
 
                 # If we hit an error log it and keep trying
                 try:
@@ -1214,8 +1269,7 @@ class MarkItDown:
         if ext == "":
             return
         # if ext not in extensions:
-        if True:
+        extensions.append(ext)
-            extensions.append(ext)
 
     def _guess_ext_magic(self, path):
         """Use puremagic (a Python implementation of libmagic) to guess a file's extension based on the first few bytes."""

tests/test_files/test_mskanji.csv

@@ -0,0 +1,4 @@
+<EFBFBD><EFBFBD><EFBFBD>O,<EFBFBD>N<EFBFBD><EFBFBD>,<EFBFBD>Z<EFBFBD><EFBFBD>
+<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Y,30,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>
+<EFBFBD>O<EFBFBD>؉p<EFBFBD>q,25,<EFBFBD><EFBFBD><EFBFBD><EFBFBD>
+<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>~,35,<EFBFBD><EFBFBD><EFBFBD>É<EFBFBD>

tests/test_markitdown.py

@@ -6,11 +6,23 @@ import shutil
 import pytest
 import requests
 
+from warnings import catch_warnings, resetwarnings
+
 from markitdown import MarkItDown
 
 skip_remote = (
     True if os.environ.get("GITHUB_ACTIONS") else False
 )  # Don't run these tests in CI
+
+
+# Don't run the llm tests without a key and the client library
+skip_llm = False if os.environ.get("OPENAI_API_KEY") else True
+try:
+    import openai
+except ModuleNotFoundError:
+    skip_llm = True
+
+# Skip exiftool tests if not installed
 skip_exiftool = shutil.which("exiftool") is None
 
 TEST_FILES_DIR = os.path.join(os.path.dirname(__file__), "test_files")
@@ -51,12 +63,25 @@ DOCX_TEST_STRINGS = [
     "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation",
 ]
 
+DOCX_COMMENT_TEST_STRINGS = [
+    "314b0a30-5b04-470b-b9f7-eed2c2bec74a",
+    "49e168b7-d2ae-407f-a055-2167576f39a1",
+    "## d666f1f7-46cb-42bd-9a39-9a39cf2a509f",
+    "# Abstract",
+    "# Introduction",
+    "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation",
+    "This is a test comment. 12df-321a",
+    "Yet another comment in the doc. 55yiyi-asd09",
+]
+
 PPTX_TEST_STRINGS = [
     "2cdda5c8-e50e-4db4-b5f0-9722a649f455",
     "04191ea8-5c73-4215-a1d3-1cfb43aaaf12",
     "44bf7d06-5e7a-4a40-a2e1-a2e42ef28c8a",
     "1b92870d-e3b5-4e65-8153-919f4ff45592",
     "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation",
+    "a3f6004b-6f4f-4ea8-bee3-3741f4dc385f",  # chart title
+    "2003",  # chart value
 ]
 
 BLOG_TEST_URL = "https://microsoft.github.io/autogen/blog/2023/04/21/LLM-tuning-math"
@@ -87,9 +112,16 @@ SERP_TEST_EXCLUDES = [
     "data:image/svg+xml,%3Csvg%20width%3D",
 ]
 
-GITHUB_ISSUE_URL = "https://github.com/microsoft/autogen/issues/1421"
+CSV_CP932_TEST_STRINGS = [
-GITHUB_PR_URL = "https://github.com/microsoft/autogen/pull/194"
+    "名前,年齢,住所",
-GITHUB_TOKEN = os.environ.get("GITHUB_TOKEN", "")
+    "佐藤太郎,30,東京",
+    "三木英子,25,大阪",
+    "髙橋淳,35,名古屋",
+]
+
+LLM_TEST_STRINGS = [
+    "5bda1dd6",
+]
 
 
 @pytest.mark.skipif(
@@ -134,6 +166,24 @@ def test_markitdown_local() -> None:
         text_content = result.text_content.replace("\\", "")
         assert test_string in text_content
 
+    # Test DOCX processing, with comments
+    result = markitdown.convert(
+        os.path.join(TEST_FILES_DIR, "test_with_comment.docx"),
+        style_map="comment-reference => ",
+    )
+    for test_string in DOCX_COMMENT_TEST_STRINGS:
+        text_content = result.text_content.replace("\\", "")
+        assert test_string in text_content
+
+    # Test DOCX processing, with comments and setting style_map on init
+    markitdown_with_style_map = MarkItDown(style_map="comment-reference => ")
+    result = markitdown_with_style_map.convert(
+        os.path.join(TEST_FILES_DIR, "test_with_comment.docx")
+    )
+    for test_string in DOCX_COMMENT_TEST_STRINGS:
+        text_content = result.text_content.replace("\\", "")
+        assert test_string in text_content
+
     # Test PPTX processing
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.pptx"))
     for test_string in PPTX_TEST_STRINGS:
@@ -148,6 +198,12 @@ def test_markitdown_local() -> None:
         text_content = result.text_content.replace("\\", "")
         assert test_string in text_content
 
+    # Test ZIP file processing
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_files.zip"))
+    for test_string in DOCX_TEST_STRINGS:
+        text_content = result.text_content.replace("\\", "")
+        assert test_string in text_content
+
     # Test Wikipedia processing
     result = markitdown.convert(
         os.path.join(TEST_FILES_DIR, "test_wikipedia.html"), url=WIKIPEDIA_TEST_URL
@@ -168,6 +224,12 @@ def test_markitdown_local() -> None:
     for test_string in SERP_TEST_STRINGS:
         assert test_string in text_content
 
+    ## Test non-UTF-8 encoding
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_mskanji.csv"))
+    text_content = result.text_content.replace("\\", "")
+    for test_string in CSV_CP932_TEST_STRINGS:
+        assert test_string in text_content
+
 
 @pytest.mark.skipif(
     skip_exiftool,
@@ -183,28 +245,57 @@ def test_markitdown_exiftool() -> None:
         assert target in result.text_content
 
 
-@pytest.mark.skipif(
+def test_markitdown_deprecation() -> None:
-    not GITHUB_TOKEN,
+    try:
-    reason="GitHub token not provided",
+        with catch_warnings(record=True) as w:
-)
+            test_client = object()
-def test_markitdown_github_issue() -> None:
+            markitdown = MarkItDown(mlm_client=test_client)
-    markitdown = MarkItDown()
+            assert len(w) == 1
-    result = markitdown.convert(GITHUB_ISSUE_URL, github_token=GITHUB_TOKEN)
+            assert w[0].category is DeprecationWarning
-    print(result.text_content)
+            assert markitdown._llm_client == test_client
-    assert "User-Defined Functions" in result.text_content
+    finally:
-    assert "closed" in result.text_content
+        resetwarnings()
-    assert "Comments:" in result.text_content
+
+    try:
+        with catch_warnings(record=True) as w:
+            markitdown = MarkItDown(mlm_model="gpt-4o")
+            assert len(w) == 1
+            assert w[0].category is DeprecationWarning
+            assert markitdown._llm_model == "gpt-4o"
+    finally:
+        resetwarnings()
+
+    try:
+        test_client = object()
+        markitdown = MarkItDown(mlm_client=test_client, llm_client=test_client)
+        assert False
+    except ValueError:
+        pass
+
+    try:
+        markitdown = MarkItDown(mlm_model="gpt-4o", llm_model="gpt-4o")
+        assert False
+    except ValueError:
+        pass
 
 
 @pytest.mark.skipif(
-    not GITHUB_TOKEN,
+    skip_llm,
-    reason="GitHub token not provided",
+    reason="do not run llm tests without a key",
 )
-def test_markitdown_github_pr() -> None:
+def test_markitdown_llm() -> None:
-    markitdown = MarkItDown()
+    client = openai.OpenAI()
-    result = markitdown.convert(GITHUB_PR_URL, github_token=GITHUB_TOKEN)
+    markitdown = MarkItDown(llm_client=client, llm_model="gpt-4o")
-    print(result.text_content)
+
-    assert "faq" in result.text_content
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_llm.jpg"))
+
+    for test_string in LLM_TEST_STRINGS:
+        assert test_string in result.text_content
+
+    # This is not super precise. It would also accept "red square", "blue circle",
+    # "the square is not blue", etc. But it's sufficient for this test.
+    for test_string in ["red", "circle", "blue", "square"]:
+        assert test_string in result.text_content.lower()
 
 
 if __name__ == "__main__":
@@ -212,5 +303,5 @@ if __name__ == "__main__":
     test_markitdown_remote()
     test_markitdown_local()
     test_markitdown_exiftool()
-    test_markitdown_github_issue()
+    test_markitdown_deprecation()
-    test_markitdown_github_pr()
+    test_markitdown_llm()