From dd8de462676993b81926610fd573d51d3272cbaf Mon Sep 17 00:00:00 2001 From: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Date: Fri, 29 Nov 2024 13:25:58 +0100 Subject: [PATCH] fix(cli): expose debug options (#467) Signed-off-by: Michele Dolfi --- docling/cli/main.py | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/docling/cli/main.py b/docling/cli/main.py index d6f51b74..ac8b19aa 100644 --- a/docling/cli/main.py +++ b/docling/cli/main.py @@ -32,6 +32,7 @@ TesseractCliOcrOptions, TesseractOcrOptions, ) +from docling.datamodel.settings import settings from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption 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.", ), ] = 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[ Optional[bool], typer.Option( @@ -229,6 +248,11 @@ def convert( elif verbose == 2: 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: from_formats = [e for e in InputFormat]