mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-31 22:44:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor EXCEL to XLSX

Browse Source 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
Peter Staar 2024-11-16 08:05:30 +01:00
parent bc31f2a973
commit c9c4810c25
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docling/backend/msexcel_backend.py
View File

@ -67,7 +67,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
@classmethod @classmethod
def supported_formats(cls) -> Set[InputFormat]: def supported_formats(cls) -> Set[InputFormat]:
return {InputFormat.EXCEL} return {InputFormat.XLSX}
def convert(self) -> DoclingDocument: def convert(self) -> DoclingDocument:
# Parses the DOCX into a structured document model. # Parses the DOCX into a structured document model.
@ -76,7 +76,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
origin = DocumentOrigin( origin = DocumentOrigin(
filename=self.file.name or "file", filename=self.file.name or "file",
mimetype="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", mimetype="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
binary_hash=self.document_hash, binary_hash=self.document_hash,
) )

2
docling/document_converter.py
View File

@ -86,7 +86,7 @@ class ImageFormatOption(FormatOption):
_format_to_default_options = { _format_to_default_options = {
InputFormat.EXCEL: FormatOption( InputFormat.XLSX: FormatOption(
pipeline_cls=SimplePipeline, backend=MsExcelDocumentBackend pipeline_cls=SimplePipeline, backend=MsExcelDocumentBackend
), ),
InputFormat.DOCX: FormatOption( InputFormat.DOCX: FormatOption(