Rebased branch on latest main. changes for CodeItem

DS4SD · Jan 15, 2025 · dd6e609 · dd6e609
1 parent 412e4c9
commit dd6e609
Show file tree

Hide file tree

Showing 10 changed files with 336 additions and 474 deletions.
diff --git a/docling/backend/asciidoc_backend.py b/docling/backend/asciidoc_backend.py
@@ -24,7 +24,6 @@
 
 
 class AsciiDocBackend(DeclarativeDocumentBackend):
-
     def __init__(self, in_doc: InputDocument, path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
 

diff --git a/docling/backend/md_backend.py b/docling/backend/md_backend.py
@@ -27,7 +27,6 @@
 
 
 class MarkdownDocumentBackend(DeclarativeDocumentBackend):
-
     def shorten_underscore_sequences(self, markdown_text, max_length=10):
         # This regex will match any sequence of underscores
         pattern = r"_+"

diff --git a/docling/backend/msexcel_backend.py b/docling/backend/msexcel_backend.py
@@ -44,7 +44,6 @@ class ExcelTable(BaseModel):
 
 
 class MsExcelDocumentBackend(DeclarativeDocumentBackend):
-
     def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
 

diff --git a/docling/backend/msword_backend.py b/docling/backend/msword_backend.py
@@ -26,7 +26,6 @@
 
 
 class MsWordDocumentBackend(DeclarativeDocumentBackend):
-
     def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
         self.XML_KEY = (

diff --git a/docling/backend/pdf_backend.py b/docling/backend/pdf_backend.py
@@ -12,7 +12,6 @@
 
 
 class PdfPageBackend(ABC):
-
     @abstractmethod
     def get_text_in_rect(self, bbox: BoundingBox) -> str:
         pass
@@ -45,7 +44,6 @@ def unload(self):
 
 
 class PdfDocumentBackend(PaginatedDocumentBackend):
-
     def __init__(self, in_doc: InputDocument, path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
 

diff --git a/docling/models/tesseract_ocr_cli_model.py b/docling/models/tesseract_ocr_cli_model.py
@@ -20,7 +20,6 @@
 
 
 class TesseractOcrCliModel(BaseOcrModel):
-
     def __init__(self, enabled: bool, options: TesseractCliOcrOptions):
         super().__init__(enabled=enabled, options=options)
         self.options: TesseractCliOcrOptions

diff --git a/docs/examples/develop_code_equation_enrichment.py b/docs/examples/develop_code_equation_enrichment.py
diff --git a/docs/examples/develop_picture_enrichment.py b/docs/examples/develop_picture_enrichment.py
@@ -22,7 +22,6 @@ class ExamplePictureClassifierPipelineOptions(PdfPipelineOptions):
 
 
 class ExamplePictureClassifierEnrichmentModel(BaseEnrichmentModel):
-
     def __init__(self, enabled: bool):
         self.enabled = enabled
 
@@ -54,7 +53,6 @@ def __call__(
 
 
 class ExamplePictureClassifierPipeline(StandardPdfPipeline):
-
     def __init__(self, pipeline_options: ExamplePictureClassifierPipelineOptions):
         super().__init__(pipeline_options)
         self.pipeline_options: ExamplePictureClassifierPipeline
Original file line number	Diff line number	Diff line change
Expand Up		@@ -24,7 +24,6 @@


		class AsciiDocBackend(DeclarativeDocumentBackend):

		def __init__(self, in_doc: InputDocument, path_or_stream: Union[BytesIO, Path]):
		super().__init__(in_doc, path_or_stream)

Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -44,7 +44,6 @@ class ExcelTable(BaseModel):


		class MsExcelDocumentBackend(DeclarativeDocumentBackend):

		def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
		super().__init__(in_doc, path_or_stream)

Expand Down