luciano/markitdown
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

switch openpyxl for calamine

Browse source
This commit is contained in:
yeungadrian 2024-12-30 22:24:50 +00:00
parent 125e206047
commit 328c67cdaf
6 changed files with 21 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
pyproject.toml
View file

@ -29,9 +29,9 @@ dependencies = [
"mammoth",
"markdownify",
"numpy",
"python-calamine",
"python-pptx",
"pandas",
"openpyxl",
"pdfminer.six",
"puremagic",
"pydub",

10
src/markitdown/_markitdown.py
View file

@ -713,18 +713,18 @@ class DocxConverter(HtmlConverter):
return result
class XlsxConverter(HtmlConverter):
class ExcelConverter(HtmlConverter):
"""
Converts XLSX files to Markdown, with each sheet presented as a separate Markdown table.
Converts excel files to Markdown, with each sheet presented as a separate Markdown table.
"""
def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
# Bail if not a XLSX
extension = kwargs.get("file_extension", "")
if extension.lower() != ".xlsx":
if extension.lower() not in [".xlsx", ".xls", ".xlsm", ".xlsb"]:
return None
sheets = pd.read_excel(local_path, sheet_name=None)
sheets = pd.read_excel(local_path, sheet_name=None, engine="calamine")
md_content = ""
for s in sheets:
md_content += f"## {s}\n"
@ -1277,7 +1277,7 @@ class MarkItDown:
self.register_page_converter(YouTubeConverter())
self.register_page_converter(BingSerpConverter())
self.register_page_converter(DocxConverter())
self.register_page_converter(XlsxConverter())
self.register_page_converter(ExcelConverter())
self.register_page_converter(PptxConverter())
self.register_page_converter(WavConverter())
self.register_page_converter(Mp3Converter())

BIN
tests/test_files/test.xls vendored Normal file
View file

Binary file not shown.

BIN
tests/test_files/test.xlsb vendored Normal file
View file

Binary file not shown.

BIN
tests/test_files/test.xlsm vendored Normal file
View file

Binary file not shown.

18
tests/test_markitdown.py
View file

@ -48,7 +48,7 @@ YOUTUBE_TEST_STRINGS = [
"the model we're going to be using today is GPT 3.5 turbo", # From the transcript
]
XLSX_TEST_STRINGS = [
EXCEL_TEST_STRINGS = [
"## 09060124-b5e7-4717-9d07-3c046eb",
"6ff4173b-42a5-4784-9b19-f49caff4d93d",
"affc7dad-52dc-4b98-9b5d-51e65d8a8ad0",
@ -174,7 +174,19 @@ def test_markitdown_local() -> None:
# Test XLSX processing
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsx"))
validate_strings(result, XLSX_TEST_STRINGS)
validate_strings(result, EXCEL_TEST_STRINGS)
# Test XLS processing
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xls"))
validate_strings(result, EXCEL_TEST_STRINGS)
# Test XLSM processing
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsm"))
validate_strings(result, EXCEL_TEST_STRINGS)
# Test XLSB processing
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsb"))
validate_strings(result, EXCEL_TEST_STRINGS)
# Test DOCX processing
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.docx"))
@ -206,7 +218,7 @@ def test_markitdown_local() -> None:
# Test ZIP file processing
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_files.zip"))
validate_strings(result, XLSX_TEST_STRINGS)
validate_strings(result, EXCEL_TEST_STRINGS)
# Test Wikipedia processing
result = markitdown.convert(