NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(cli): expose debug options (#467)

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2024-11-29 13:25:58 +01:00 committed by GitHub
parent af63818df5
commit dd8de46267
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
docling/cli/main.py
View File

@ -32,6 +32,7 @@ from docling.datamodel.pipeline_options import (
TesseractCliOcrOptions, TesseractCliOcrOptions,
TesseractOcrOptions, TesseractOcrOptions,
) )
from docling.datamodel.settings import settings
from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|torch") warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|torch")
@ -212,6 +213,24 @@ def convert(
help="Set the verbosity level. -v for info logging, -vv for debug logging.", help="Set the verbosity level. -v for info logging, -vv for debug logging.",
), ),
] = 0, ] = 0,
debug_visualize_cells: Annotated[
bool,
typer.Option(..., help="Enable debug output which visualizes the PDF cells"),
] = False,
debug_visualize_ocr: Annotated[
bool,
typer.Option(..., help="Enable debug output which visualizes the OCR cells"),
] = False,
debug_visualize_layout: Annotated[
bool,
typer.Option(
..., help="Enable debug output which visualizes the layour clusters"
),
] = False,
debug_visualize_tables: Annotated[
bool,
typer.Option(..., help="Enable debug output which visualizes the table cells"),
] = False,
version: Annotated[ version: Annotated[
Optional[bool], Optional[bool],
typer.Option( typer.Option(
@ -229,6 +248,11 @@ def convert(
elif verbose == 2: elif verbose == 2:
logging.basicConfig(level=logging.DEBUG) logging.basicConfig(level=logging.DEBUG)
settings.debug.visualize_cells = debug_visualize_cells
settings.debug.visualize_layout = debug_visualize_layout
settings.debug.visualize_tables = debug_visualize_tables
settings.debug.visualize_ocr = debug_visualize_ocr
if from_formats is None: if from_formats is None:
from_formats = [e for e in InputFormat] from_formats = [e for e in InputFormat]