mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-13 07:08:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add image format support to PdfBackend

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2024-10-11 16:47:15 +02:00
parent d0fccb9342
commit 6efcf0a5a5
12 changed files with 110 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
examples/run_with_formats.py
View File

@@ -21,57 +21,34 @@ input_paths = [
Path("tests/data/word_sample.docx"),
Path("tests/data/lorem_ipsum.docx"),
Path("tests/data/powerpoint_sample.pptx"),
Path("tests/data/2305.03393v1-pg9-img.png"),
Path("tests/data/2206.01062.pdf"),
# Path("tests/data/2305.03393v1-pg9-img.png"),
]
## for defaults use:
# doc_converter = DocumentConverter()
## to customize use:
doc_converter = DocumentConverter( # all of the below is optional, has internal defaults.
formats=[
InputFormat.PDF,
# InputFormat.IMAGE,
InputFormat.DOCX,
InputFormat.HTML,
InputFormat.PPTX,
], # whitelist formats, other files are ignored.
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_cls=StandardPdfModelPipeline, backend=PyPdfiumDocumentBackend
), # PdfFormatOption(backend=PyPdfiumDocumentBackend),
InputFormat.DOCX: WordFormatOption(
pipeline_cls=SimpleModelPipeline # , backend=MsWordDocumentBackend
),
# InputFormat.IMAGE: PdfFormatOption(),
},
doc_converter = (
DocumentConverter( # all of the below is optional, has internal defaults.
formats=[
InputFormat.PDF,
InputFormat.IMAGE,
InputFormat.DOCX,
InputFormat.HTML,
InputFormat.PPTX,
], # whitelist formats, non-matching files are ignored.
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_cls=StandardPdfModelPipeline, backend=PyPdfiumDocumentBackend
),
InputFormat.DOCX: WordFormatOption(
pipeline_cls=SimpleModelPipeline # , backend=MsWordDocumentBackend
),
},
)
)
doc_converter = DocumentConverter( # all of the below is optional, has internal defaults.
pdf=None,
docx=WordFormatOption(
pipeline_cls=SimpleModelPipeline # , backend=MsWordDocumentBackend
),
formats=[
InputFormat.PDF,
# InputFormat.IMAGE,
InputFormat.DOCX,
InputFormat.HTML,
InputFormat.PPTX,
], # whitelist formats, other files are ignored.
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_cls=StandardPdfModelPipeline, backend=PyPdfiumDocumentBackend
), # PdfFormatOption(backend=PyPdfiumDocumentBackend),
InputFormat.DOCX: WordFormatOption(
pipeline_cls=SimpleModelPipeline # , backend=MsWordDocumentBackend
),
# InputFormat.IMAGE: PdfFormatOption(),
},
)
conv_results = doc_converter.convert_all(input_paths)
for res in conv_results: