feat: update parser with bytesio interface and set as new default bac…

…kend (#32) * update parser with bytesio interface Signed-off-by: Michele Dolfi <[email protected]> * change default backend Signed-off-by: Michele Dolfi <[email protected]> * update DEFAULT_BACKEND Signed-off-by: Michele Dolfi <[email protected]> --------- Signed-off-by: Michele Dolfi <[email protected]>
DS4SD · Aug 14, 2024 · 90dd676 · 90dd676
1 parent 61be78a
commit 90dd676
Show file tree

Hide file tree

Showing 4 changed files with 86 additions and 32 deletions.
diff --git a/docling/backend/docling_parse_backend.py b/docling/backend/docling_parse_backend.py
@@ -150,10 +150,11 @@ def __init__(self, path_or_stream: Union[BytesIO, Path]):
         super().__init__(path_or_stream)
         self._pdoc = pdfium.PdfDocument(path_or_stream)
         # Parsing cells with docling_parser call
-        if isinstance(path_or_stream, BytesIO):
-            raise NotImplemented("This backend does not support byte streams yet.")
         parser = pdf_parser()
-        self._parser_doc = parser.find_cells(str(path_or_stream))
+        if isinstance(path_or_stream, BytesIO):
+            self._parser_doc = parser.find_cells_from_bytesio(path_or_stream)
+        else:
+            self._parser_doc = parser.find_cells(str(path_or_stream))
 
     def page_count(self) -> int:
         return len(self._parser_doc["pages"])

diff --git a/docling/datamodel/document.py b/docling/datamodel/document.py
@@ -14,7 +14,7 @@
 from pydantic import BaseModel
 
 from docling.backend.abstract_backend import PdfDocumentBackend
-from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
+from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.datamodel.base_models import (
     AssembledUnit,
     ConversionStatus,
@@ -64,7 +64,7 @@ def __init__(
         path_or_stream: Union[BytesIO, Path],
         filename: Optional[str] = None,
         limits: Optional[DocumentLimits] = None,
-        pdf_backend=PyPdfiumDocumentBackend,
+        pdf_backend=DoclingParseDocumentBackend,
     ):
         super().__init__()
 
@@ -308,7 +308,7 @@ class DocumentConversionInput(BaseModel):
     _path_or_stream_iterator: Iterable[Union[Path, DocumentStream]] = None
     limits: Optional[DocumentLimits] = DocumentLimits()
 
-    DEFAULT_BACKEND: ClassVar = PyPdfiumDocumentBackend
+    DEFAULT_BACKEND: ClassVar = DoclingParseDocumentBackend
 
     def docs(
         self, pdf_backend: Optional[Type[PdfDocumentBackend]] = None

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -32,7 +32,7 @@ pydantic-settings = "^2.3.0"
 huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = { version = "^1.7", optional = true }
-docling-parse = "^0.0.1"
+docling-parse = "^0.2.0"
 certifi = ">=2024.7.4"
 
 [tool.poetry.group.dev.dependencies]