Python tool for converting files and office documents to Markdown.
Chore: Make linter happy (#1256)
t3tracb421cf9eae0
diff --git a/packages/markitdown-mcp/src/markitdown_mcp/__main__.py b/packages/markitdown-mcp/src/markitdown_mcp/__main__.pyindex 32b75273..9e404ab2 100644--- a/packages/markitdown-mcp/src/markitdown_mcp/__main__.py+++ b/packages/markitdown-mcp/src/markitdown_mcp/__main__.py@@ -1,5 +1,4 @@import sys-from typing import Anyfrom mcp.server.fastmcp import FastMCPfrom starlette.applications import Starlettefrom mcp.server.sse import SseServerTransportdiff --git a/packages/markitdown-sample-plugin/tests/test_sample_plugin.py b/packages/markitdown-sample-plugin/tests/test_sample_plugin.pyindex 6d0102dc..69682474 100644--- a/packages/markitdown-sample-plugin/tests/test_sample_plugin.py+++ b/packages/markitdown-sample-plugin/tests/test_sample_plugin.py@@ -1,6 +1,5 @@#!/usr/bin/env python3 -m pytestimport os-import pytestfrom markitdown import MarkItDown, StreamInfofrom markitdown_sample_plugin import RtfConverterdiff --git a/packages/markitdown/src/markitdown/__main__.py b/packages/markitdown/src/markitdown/__main__.pyindex cfb1c6e8..6085ad6b 100644--- a/packages/markitdown/src/markitdown/__main__.py+++ b/packages/markitdown/src/markitdown/__main__.py@@ -4,7 +4,6 @@import argparseimport sysimport codecs-import localefrom textwrap import dedentfrom importlib.metadata import entry_pointsfrom .__about__ import __version__@@ -34,13 +33,13 @@ def main():ORmarkitdown < example.pdf-+OR to save to a file use-+markitdown example.pdf -o example.md-+OR-+markitdown example.pdf > example.md""").strip(),diff --git a/packages/markitdown/src/markitdown/_base_converter.py b/packages/markitdown/src/markitdown/_base_converter.pyindex 2f0ca9dd..a6f2a2d9 100644--- a/packages/markitdown/src/markitdown/_base_converter.py+++ b/packages/markitdown/src/markitdown/_base_converter.py@@ -1,7 +1,4 @@-import os-import tempfile-from warnings import warn-from typing import Any, Union, BinaryIO, Optional, List+from typing import Any, BinaryIO, Optionalfrom ._stream_info import StreamInfodiff --git a/packages/markitdown/src/markitdown/_markitdown.py b/packages/markitdown/src/markitdown/_markitdown.pyindex 682902b4..52a5e28f 100644--- a/packages/markitdown/src/markitdown/_markitdown.py+++ b/packages/markitdown/src/markitdown/_markitdown.py@@ -1,11 +1,8 @@-import copyimport mimetypesimport osimport reimport sysimport shutil-import tempfile-import warningsimport tracebackimport iofrom dataclasses import dataclass@@ -547,7 +544,7 @@ class MarkItDown:# Sanity check -- make sure the cur_pos is still the sameassert (cur_pos == file_stream.tell()- ), f"File stream position should NOT change between guess iterations"+ ), "File stream position should NOT change between guess iterations"_kwargs = {k: v for k, v in kwargs.items()}@@ -614,7 +611,7 @@ class MarkItDown:# Nothing can handle it!raise UnsupportedFormatException(- f"Could not convert stream to Markdown. No converter attempted a conversion, suggesting that the filetype is simply not supported."+ "Could not convert stream to Markdown. No converter attempted a conversion, suggesting that the filetype is simply not supported.")def register_page_converter(self, converter: DocumentConverter) -> None:diff --git a/packages/markitdown/src/markitdown/converter_utils/docx/math/omml.py b/packages/markitdown/src/markitdown/converter_utils/docx/math/omml.pyindex 012b95df..dfa734cd 100644--- a/packages/markitdown/src/markitdown/converter_utils/docx/math/omml.py+++ b/packages/markitdown/src/markitdown/converter_utils/docx/math/omml.py@@ -272,7 +272,7 @@ class oMath2Latex(Tag2Method):if FUNC.get(t):latex_chars.append(FUNC[t])else:- raise NotImplemented("Not support func %s" % t)+ raise NotImplementedError("Not support func %s" % t)else:latex_chars.append(t)t = BLANK.join(latex_chars)@@ -316,7 +316,7 @@ class oMath2Latex(Tag2Method):t_dict = self.process_children_dict(elm, include=("e", "lim"))latex_s = LIM_FUNC.get(t_dict["e"])if not latex_s:- raise NotImplemented("Not support lim %s" % t_dict["e"])+ raise NotImplementedError("Not support lim %s" % t_dict["e"])else:return latex_s.format(lim=t_dict.get("lim"))diff --git a/packages/markitdown/src/markitdown/converter_utils/docx/pre_process.py b/packages/markitdown/src/markitdown/converter_utils/docx/pre_process.pyindex 78552bc0..d6fa8db6 100644--- a/packages/markitdown/src/markitdown/converter_utils/docx/pre_process.py+++ b/packages/markitdown/src/markitdown/converter_utils/docx/pre_process.py@@ -147,7 +147,7 @@ def pre_process_docx(input_docx: BinaryIO) -> BinaryIO:updated_content = _pre_process_math(content)# In the future, if there are more pre-processing steps, they can be added herezip_output.writestr(name, updated_content)- except:+ except Exception:# If there is an error in processing the content, write the original contentzip_output.writestr(name, content)else:diff --git a/packages/markitdown/src/markitdown/converters/_audio_converter.py b/packages/markitdown/src/markitdown/converters/_audio_converter.pyindex 845ad5de..3d96b53c 100644--- a/packages/markitdown/src/markitdown/converters/_audio_converter.py+++ b/packages/markitdown/src/markitdown/converters/_audio_converter.py@@ -1,5 +1,4 @@-import io-from typing import Any, BinaryIO, Optional+from typing import Any, BinaryIOfrom ._exiftool import exiftool_metadatafrom ._transcribe_audio import transcribe_audiodiff --git a/packages/markitdown/src/markitdown/converters/_bing_serp_converter.py b/packages/markitdown/src/markitdown/converters/_bing_serp_converter.pyindex f65b85fe..6a383487 100644--- a/packages/markitdown/src/markitdown/converters/_bing_serp_converter.py+++ b/packages/markitdown/src/markitdown/converters/_bing_serp_converter.py@@ -1,9 +1,8 @@-import ioimport reimport base64import binasciifrom urllib.parse import parse_qs, urlparse-from typing import Any, BinaryIO, Optional+from typing import Any, BinaryIOfrom bs4 import BeautifulSoupfrom .._base_converter import DocumentConverter, DocumentConverterResultdiff --git a/packages/markitdown/src/markitdown/converters/_csv_converter.py b/packages/markitdown/src/markitdown/converters/_csv_converter.pyindex 7162889d..7e9631e1 100644--- a/packages/markitdown/src/markitdown/converters/_csv_converter.py+++ b/packages/markitdown/src/markitdown/converters/_csv_converter.py@@ -1,9 +1,7 @@-import sysimport csvimport iofrom typing import BinaryIO, Anyfrom charset_normalizer import from_bytes-from ._html_converter import HtmlConverterfrom .._base_converter import DocumentConverter, DocumentConverterResultfrom .._stream_info import StreamInfodiff --git a/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py b/packages/markitdown/src/markitdown/converters/_doc_intel_converter.pyindex d2dce917..ba66b5b5 100644--- a/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py+++ b/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py@@ -1,13 +1,12 @@import sysimport reimport os-from typing import BinaryIO, Any, List, Optional, Union+from typing import BinaryIO, Any, Listfrom enum import Enum-from ._html_converter import HtmlConverterfrom .._base_converter import DocumentConverter, DocumentConverterResultfrom .._stream_info import StreamInfo-from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE+from .._exceptions import MissingDependencyException# Try loading optional (but in this case, required) dependencies# Save reporting of any exceptions for laterdiff --git a/packages/markitdown/src/markitdown/converters/_docx_converter.py b/packages/markitdown/src/markitdown/converters/_docx_converter.pyindex b3206952..69c1ea83 100644--- a/packages/markitdown/src/markitdown/converters/_docx_converter.py+++ b/packages/markitdown/src/markitdown/converters/_docx_converter.py@@ -4,7 +4,7 @@ from typing import BinaryIO, Anyfrom ._html_converter import HtmlConverterfrom ..converter_utils.docx.pre_process import pre_process_docx-from .._base_converter import DocumentConverter, DocumentConverterResult+from .._base_converter import DocumentConverterResultfrom .._stream_info import StreamInfofrom .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGEdiff --git a/packages/markitdown/src/markitdown/converters/_epub_converter.py b/packages/markitdown/src/markitdown/converters/_epub_converter.pyindex 73f2955f..3be65b01 100644--- a/packages/markitdown/src/markitdown/converters/_epub_converter.py+++ b/packages/markitdown/src/markitdown/converters/_epub_converter.py@@ -6,7 +6,7 @@ from xml.dom.minidom import Documentfrom typing import BinaryIO, Any, Dict, Listfrom ._html_converter import HtmlConverter-from .._base_converter import DocumentConverter, DocumentConverterResult+from .._base_converter import DocumentConverterResultfrom .._stream_info import StreamInfoACCEPTED_MIME_TYPE_PREFIXES = [diff --git a/packages/markitdown/src/markitdown/converters/_exiftool.py b/packages/markitdown/src/markitdown/converters/_exiftool.pyindex 43c100fa..1af155f2 100644--- a/packages/markitdown/src/markitdown/converters/_exiftool.py+++ b/packages/markitdown/src/markitdown/converters/_exiftool.py@@ -1,10 +1,6 @@import jsonimport subprocessimport locale-import sys-import shutil-import os-import warningsfrom typing import BinaryIO, Any, Uniondiff --git a/packages/markitdown/src/markitdown/converters/_ipynb_converter.py b/packages/markitdown/src/markitdown/converters/_ipynb_converter.pyindex f8ba1933..b15e77aa 100644--- a/packages/markitdown/src/markitdown/converters/_ipynb_converter.py+++ b/packages/markitdown/src/markitdown/converters/_ipynb_converter.py@@ -50,8 +50,6 @@ class IpynbConverter(DocumentConverter):**kwargs: Any, # Options to pass to the converter) -> DocumentConverterResult:# Parse and convert the notebook- result = None-encoding = stream_info.charset or "utf-8"notebook_content = file_stream.read().decode(encoding=encoding)return self._convert(json.loads(notebook_content))diff --git a/packages/markitdown/src/markitdown/converters/_llm_caption.py b/packages/markitdown/src/markitdown/converters/_llm_caption.pyindex b851dc8d..004a47ae 100644--- a/packages/markitdown/src/markitdown/converters/_llm_caption.py+++ b/packages/markitdown/src/markitdown/converters/_llm_caption.py@@ -1,4 +1,4 @@-from typing import BinaryIO, Any, Union+from typing import BinaryIO, Unionimport base64import mimetypesfrom .._stream_info import StreamInfodiff --git a/packages/markitdown/src/markitdown/converters/_pdf_converter.py b/packages/markitdown/src/markitdown/converters/_pdf_converter.pyindex 4586ef1d..63162d52 100644--- a/packages/markitdown/src/markitdown/converters/_pdf_converter.py+++ b/packages/markitdown/src/markitdown/converters/_pdf_converter.py@@ -4,7 +4,6 @@ import iofrom typing import BinaryIO, Any-from ._html_converter import HtmlConverterfrom .._base_converter import DocumentConverter, DocumentConverterResultfrom .._stream_info import StreamInfofrom .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGEdiff --git a/packages/markitdown/src/markitdown/converters/_plain_text_converter.py b/packages/markitdown/src/markitdown/converters/_plain_text_converter.pyindex 2e104051..6f1306fe 100644--- a/packages/markitdown/src/markitdown/converters/_plain_text_converter.py+++ b/packages/markitdown/src/markitdown/converters/_plain_text_converter.py@@ -9,7 +9,7 @@ from .._stream_info import StreamInfo# Save reporting of any exceptions for later_dependency_exc_info = Nonetry:- import mammoth+ import mammoth # noqa: F401except ImportError:# Preserve the error and stack trace for later_dependency_exc_info = sys.exc_info()diff --git a/packages/markitdown/src/markitdown/converters/_wikipedia_converter.py b/packages/markitdown/src/markitdown/converters/_wikipedia_converter.pyindex c0f7e0e4..c2001865 100644--- a/packages/markitdown/src/markitdown/converters/_wikipedia_converter.py+++ b/packages/markitdown/src/markitdown/converters/_wikipedia_converter.py@@ -1,7 +1,6 @@-import ioimport reimport bs4-from typing import Any, BinaryIO, Optional+from typing import Any, BinaryIOfrom .._base_converter import DocumentConverter, DocumentConverterResultfrom .._stream_info import StreamInfodiff --git a/packages/markitdown/src/markitdown/converters/_xlsx_converter.py b/packages/markitdown/src/markitdown/converters/_xlsx_converter.pyindex 28f73a0d..4186ec77 100644--- a/packages/markitdown/src/markitdown/converters/_xlsx_converter.py+++ b/packages/markitdown/src/markitdown/converters/_xlsx_converter.py@@ -10,14 +10,14 @@ from .._stream_info import StreamInfo_xlsx_dependency_exc_info = Nonetry:import pandas as pd- import openpyxl+ import openpyxl # noqa: F401except ImportError:_xlsx_dependency_exc_info = sys.exc_info()_xls_dependency_exc_info = Nonetry:- import pandas as pd- import xlrd+ import pandas as pd # noqa: F811+ import xlrd # noqa: F401except ImportError:_xls_dependency_exc_info = sys.exc_info()diff --git a/packages/markitdown/src/markitdown/converters/_youtube_converter.py b/packages/markitdown/src/markitdown/converters/_youtube_converter.pyindex b5a014c3..e08c4cb7 100644--- a/packages/markitdown/src/markitdown/converters/_youtube_converter.py+++ b/packages/markitdown/src/markitdown/converters/_youtube_converter.py@@ -1,10 +1,8 @@-import sysimport jsonimport time-import ioimport reimport bs4-from typing import Any, BinaryIO, Optional, Dict, List, Union+from typing import Any, BinaryIO, Dict, List, Unionfrom urllib.parse import parse_qs, urlparse, unquotefrom .._base_converter import DocumentConverter, DocumentConverterResultdiff --git a/packages/markitdown/src/markitdown/converters/_zip_converter.py b/packages/markitdown/src/markitdown/converters/_zip_converter.pyindex cb1a7e6f..f87e6c89 100644--- a/packages/markitdown/src/markitdown/converters/_zip_converter.py+++ b/packages/markitdown/src/markitdown/converters/_zip_converter.py@@ -1,4 +1,3 @@-import sysimport zipfileimport ioimport osdiff --git a/packages/markitdown/tests/test_cli_misc.py b/packages/markitdown/tests/test_cli_misc.pyindex 345d5cc3..cf6c9ccc 100644--- a/packages/markitdown/tests/test_cli_misc.py+++ b/packages/markitdown/tests/test_cli_misc.py@@ -1,6 +1,5 @@#!/usr/bin/env python3 -m pytestimport subprocess-import pytestfrom markitdown import __version__# This file contains CLI tests that are not directly tested by the FileTestVectors.@@ -24,8 +23,8 @@ def test_invalid_flag() -> None:assert result.returncode != 0, f"CLI exited with error: {result.stderr}"assert ("unrecognized arguments" in result.stderr- ), f"Expected 'unrecognized arguments' to appear in STDERR"- assert "SYNTAX" in result.stderr, f"Expected 'SYNTAX' to appear in STDERR"+ ), "Expected 'unrecognized arguments' to appear in STDERR"+ assert "SYNTAX" in result.stderr, "Expected 'SYNTAX' to appear in STDERR"if __name__ == "__main__":diff --git a/packages/markitdown/tests/test_cli_vectors.py b/packages/markitdown/tests/test_cli_vectors.pyindex 60304821..5add530b 100644--- a/packages/markitdown/tests/test_cli_vectors.py+++ b/packages/markitdown/tests/test_cli_vectors.py@@ -19,13 +19,6 @@ else:FileTestVector,)-from markitdown import (- MarkItDown,- UnsupportedFormatException,- FileConversionException,- StreamInfo,-)-skip_remote = (True if os.environ.get("GITHUB_ACTIONS") else False) # Don't run these tests in CI@@ -140,8 +133,6 @@ def test_convert_url(shared_tmp_dir, test_vector):"""Test the conversion of a stream with no stream info."""# Note: tmp_dir is not used here, but is needed to match the signature- markitdown = MarkItDown()-time.sleep(1) # Ensure we don't hit rate limitsresult = subprocess.run(["python", "-m", "markitdown", TEST_FILES_URL + "/" + test_vector.filename],@@ -191,7 +182,6 @@ def test_output_to_file_with_data_uris(shared_tmp_dir, test_vector) -> None:if __name__ == "__main__":- import sysimport tempfile"""Runs this file's tests from the command line."""diff --git a/packages/markitdown/tests/test_module_misc.py b/packages/markitdown/tests/test_module_misc.pyindex 1819183e..447e28ab 100644--- a/packages/markitdown/tests/test_module_misc.py+++ b/packages/markitdown/tests/test_module_misc.py@@ -3,7 +3,6 @@ import ioimport osimport reimport shutil-import openaiimport pytestfrom markitdown._uri_utils import parse_data_uri, file_uri_to_path@@ -253,8 +252,6 @@ def test_file_uris() -> None:def test_docx_comments() -> None:- markitdown = MarkItDown()-# Test DOCX processing, with comments and setting style_map on initmarkitdown_with_style_map = MarkItDown(style_map="comment-reference => ")result = markitdown_with_style_map.convert(diff --git a/packages/markitdown/tests/test_module_vectors.py b/packages/markitdown/tests/test_module_vectors.pyindex 98fd0c7a..d6d9d680 100644--- a/packages/markitdown/tests/test_module_vectors.py+++ b/packages/markitdown/tests/test_module_vectors.py@@ -2,7 +2,6 @@import osimport timeimport pytest-import codecsimport base64from pathlib import Path@@ -14,8 +13,6 @@ else:from markitdown import (MarkItDown,- UnsupportedFormatException,- FileConversionException,StreamInfo,)@@ -203,8 +200,6 @@ def test_convert_stream_keep_data_uris(test_vector):if __name__ == "__main__":- import sys-"""Runs this file's tests from the command line."""# General tests