mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Rename docling backend to v4

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-03-14 12:35:06 +01:00
parent b77f73beec
commit af18215714
9 changed files with 25 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docling/backend/docling_parse_v3_backend.py → docling/backend/docling_parse_v4_backend.py
View File

@ -20,7 +20,7 @@ if TYPE_CHECKING:
_log = logging.getLogger(__name__)
class DoclingParseV3PageBackend(PdfPageBackend):
class DoclingParseV4PageBackend(PdfPageBackend):
def __init__(self, parsed_page: SegmentedPdfPage, page_obj: PdfPage):
self._ppage = page_obj
self._dpage = parsed_page
@ -144,7 +144,7 @@ class DoclingParseV3PageBackend(PdfPageBackend):
self._dpage = None
class DoclingParseV3DocumentBackend(PdfDocumentBackend):
class DoclingParseV4DocumentBackend(PdfDocumentBackend):
def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
super().__init__(in_doc, path_or_stream)
@ -171,8 +171,8 @@ class DoclingParseV3DocumentBackend(PdfDocumentBackend):
def load_page(
self, page_no: int, create_words: bool = True, create_textlines: bool = True
) -> DoclingParseV3PageBackend:
return DoclingParseV3PageBackend(
) -> DoclingParseV4PageBackend:
return DoclingParseV4PageBackend(
self.dp_doc.get_page(
page_no + 1,
create_words=create_words,

6
docling/cli/main.py
View File

@ -15,7 +15,7 @@ from docling_core.utils.file import resolve_source_to_path
from pydantic import TypeAdapter
from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
from docling.backend.docling_parse_v3_backend import DoclingParseV3DocumentBackend
from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
from docling.backend.pdf_backend import PdfDocumentBackend
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
from docling.datamodel.base_models import (
@ -416,8 +416,8 @@ def convert(
backend = DoclingParseV2DocumentBackend
elif pdf_backend == PdfBackend.DLPARSE_V2:
backend = DoclingParseV2DocumentBackend
elif pdf_backend == PdfBackend.DLPARSE_V3:
backend = DoclingParseV3DocumentBackend # type: ignore
elif pdf_backend == PdfBackend.DLPARSE_V4:
backend = DoclingParseV4DocumentBackend # type: ignore
elif pdf_backend == PdfBackend.PYPDFIUM2:
backend = PyPdfiumDocumentBackend # type: ignore
else:

2
docling/datamodel/pipeline_options.py
View File

@ -301,7 +301,7 @@ class PdfBackend(str, Enum):
PYPDFIUM2 = "pypdfium2"
DLPARSE_V1 = "dlparse_v1"
DLPARSE_V2 = "dlparse_v2"
DLPARSE_V3 = "dlparse_v3"
DLPARSE_V4 = "dlparse_v4"
# Define an enum for the ocr engines

4
docs/examples/batch_convert.py
View File

@ -7,7 +7,7 @@ from typing import Iterable
import yaml
from docling_core.types.doc import ImageRefMode
from docling.backend.docling_parse_v3_backend import DoclingParseV3DocumentBackend
from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
from docling.datamodel.base_models import ConversionStatus, InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PdfPipelineOptions
@ -145,7 +145,7 @@ def main():
doc_converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=pipeline_options, backend=DoclingParseV3DocumentBackend
pipeline_options=pipeline_options, backend=DoclingParseV4DocumentBackend
)
}
)

14
tests/test_backend_docling_parse_v3.py → tests/test_backend_docling_parse_v4.py
View File

@ -2,9 +2,9 @@ from pathlib import Path
import pytest
from docling.backend.docling_parse_v3_backend import (
DoclingParseV3DocumentBackend,
DoclingParseV3PageBackend,
from docling.backend.docling_parse_v4_backend import (
DoclingParseV4DocumentBackend,
DoclingParseV4PageBackend,
)
from docling.datamodel.base_models import BoundingBox, InputFormat
from docling.datamodel.document import InputDocument
@ -19,7 +19,7 @@ def _get_backend(pdf_doc):
in_doc = InputDocument(
path_or_stream=pdf_doc,
format=InputFormat.PDF,
backend=DoclingParseV3DocumentBackend,
backend=DoclingParseV4DocumentBackend,
)
doc_backend = in_doc._backend
@ -34,7 +34,7 @@ def test_text_cell_counts():
for page_index in range(0, doc_backend.page_count()):
last_cell_count = None
for i in range(10):
page_backend: DoclingParseV3PageBackend = doc_backend.load_page(0)
page_backend: DoclingParseV4PageBackend = doc_backend.load_page(0)
cells = list(page_backend.get_text_cells())
if last_cell_count is None:
@ -49,7 +49,7 @@ def test_text_cell_counts():
def test_get_text_from_rect(test_doc_path):
doc_backend = _get_backend(test_doc_path)
page_backend: DoclingParseV3PageBackend = doc_backend.load_page(0)
page_backend: DoclingParseV4PageBackend = doc_backend.load_page(0)
# Get the title text of the DocLayNet paper
textpiece = page_backend.get_text_in_rect(
@ -62,7 +62,7 @@ def test_get_text_from_rect(test_doc_path):
def test_crop_page_image(test_doc_path):
doc_backend = _get_backend(test_doc_path)
page_backend: DoclingParseV3PageBackend = doc_backend.load_page(0)
page_backend: DoclingParseV4PageBackend = doc_backend.load_page(0)
# Crop out "Figure 1" from the DocLayNet paper
im = page_backend.get_page_image(

4
tests/test_e2e_conversion.py
View File

@ -1,6 +1,6 @@
from pathlib import Path
from docling.backend.docling_parse_v3_backend import DoclingParseV3DocumentBackend
from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import AcceleratorDevice, PdfPipelineOptions
@ -34,7 +34,7 @@ def get_converter():
converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=pipeline_options, backend=DoclingParseV3DocumentBackend
pipeline_options=pipeline_options, backend=DoclingParseV4DocumentBackend
)
}
)

4
tests/test_e2e_ocr_conversion.py
View File

@ -2,7 +2,7 @@ import sys
from pathlib import Path
from typing import List
from docling.backend.docling_parse_v3_backend import DoclingParseV3DocumentBackend
from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import (
@ -45,7 +45,7 @@ def get_converter(ocr_options: OcrOptions):
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=pipeline_options,
backend=DoclingParseV3DocumentBackend,
backend=DoclingParseV4DocumentBackend,
)
}
)

4
tests/test_interfaces.py
View File

@ -3,7 +3,7 @@ from pathlib import Path
import pytest
from docling.backend.docling_parse_v3_backend import DoclingParseV3DocumentBackend
from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
from docling.datamodel.base_models import DocumentStream, InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
@ -31,7 +31,7 @@ def converter():
converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=pipeline_options, backend=DoclingParseV3DocumentBackend
pipeline_options=pipeline_options, backend=DoclingParseV4DocumentBackend
)
}
)

4
tests/test_options.py
View File

@ -3,7 +3,7 @@ from pathlib import Path
import pytest
from docling.backend.docling_parse_v3_backend import DoclingParseV3DocumentBackend
from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
from docling.datamodel.base_models import ConversionStatus, InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import (
@ -33,7 +33,7 @@ def get_converters_with_table_options():
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=pipeline_options,
backend=DoclingParseV3DocumentBackend,
backend=DoclingParseV4DocumentBackend,
)
}
)