nv_ingest.extraction_workflows.pptx package#

Submodules#

nv_ingest.extraction_workflows.pptx.pptx_helper module#

nv_ingest.extraction_workflows.pptx.pptx_helper.escape_text(text)[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.format_text( text: str, bold: bool = False, italic: bool = False, underline: bool = False, ) → str[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.get_bbox( presentation_object: Presentation | None = None, shape_object: Slide | None = None, text_depth: TextTypeEnum | None = None, )[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.get_hyperlink(text, url)[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.is_accent(font)[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.is_list_block(shape)[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.is_strong(font)[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.is_subtitle(shape)[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.is_title(shape)[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.is_underlined(font)[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.process_subtitle(shape)[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.process_title(shape)[source]#

nv_ingest.extraction_workflows.pptx.pptx_helper.python_pptx(

pptx_stream,

extract_text: bool,

extract_images: bool,

extract_tables: bool,

extract_charts: bool,

**kwargs,

)[source]#: Helper function to use python-pptx to extract text from a bytestream PPTX, while deferring image classification into tables/charts if requested.

nv_ingest.extraction_workflows.pptx.pptx_helper.ungroup_shapes(shapes)[source]#

Module contents#

nv_ingest.extraction_workflows.pptx.python_pptx(

pptx_stream,

extract_text: bool,

extract_images: bool,

extract_tables: bool,

extract_charts: bool,

**kwargs,

)[source]#: Helper function to use python-pptx to extract text from a bytestream PPTX, while deferring image classification into tables/charts if requested.