fix: make enum serializable with human-readable value (#555)

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2024-12-10 13:12:44 +01:00
committed by GitHub
parent eb30c4f763
commit a7df337654
3 changed files with 34 additions and 28 deletions

View File

@@ -27,8 +27,10 @@ from docling.datamodel.base_models import (
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import (
EasyOcrOptions,
OcrEngine,
OcrMacOptions,
OcrOptions,
PdfBackend,
PdfPipelineOptions,
RapidOcrOptions,
TableFormerMode,
@@ -68,22 +70,6 @@ def version_callback(value: bool):
raise typer.Exit()
# Define an enum for the backend options
class PdfBackend(str, Enum):
PYPDFIUM2 = "pypdfium2"
DLPARSE_V1 = "dlparse_v1"
DLPARSE_V2 = "dlparse_v2"
# Define an enum for the ocr engines
class OcrEngine(str, Enum):
EASYOCR = "easyocr"
TESSERACT_CLI = "tesseract_cli"
TESSERACT = "tesseract"
OCRMAC = "ocrmac"
RAPIDOCR = "rapidocr"
def export_documents(
conv_results: Iterable[ConversionResult],
output_dir: Path,