From 7234dc3a42d2a9be41174ec49638e90671fe3486 Mon Sep 17 00:00:00 2001
From: Nikos Livathinos <nli@zurich.ibm.com>
Date: Mon, 11 Nov 2024 14:10:56 +0100
Subject: [PATCH] feat: Introduce the force-ocr cmd parameter in docling cli.
 Add the full_page_ocr.py example in mkdocs

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
---
 docling/cli/main.py            | 13 ++++++++++---
 docs/examples/full_page_ocr.py |  1 -
 mkdocs.yml                     |  1 +
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/docling/cli/main.py b/docling/cli/main.py
index 35ae01df..60a3c296 100644
--- a/docling/cli/main.py
+++ b/docling/cli/main.py
@@ -153,6 +153,13 @@ def convert(
             ..., help="If enabled, the bitmap content will be processed using OCR."
         ),
     ] = True,
+    force_ocr: Annotated[
+        bool,
+        typer.Option(
+            ...,
+            help="Replace any existing text with OCR generated text over the full content.",
+        ),
+    ] = False,
     ocr_engine: Annotated[
         OcrEngine, typer.Option(..., help="The OCR engine to use.")
     ] = OcrEngine.EASYOCR,
@@ -219,11 +226,11 @@ def convert(
 
     match ocr_engine:
         case OcrEngine.EASYOCR:
-            ocr_options: OcrOptions = EasyOcrOptions()
+            ocr_options: OcrOptions = EasyOcrOptions(force_full_page_ocr=force_ocr)
         case OcrEngine.TESSERACT_CLI:
-            ocr_options = TesseractCliOcrOptions()
+            ocr_options = TesseractCliOcrOptions(force_full_page_ocr=force_ocr)
         case OcrEngine.TESSERACT:
-            ocr_options = TesseractOcrOptions()
+            ocr_options = TesseractOcrOptions(force_full_page_ocr=force_ocr)
         case _:
             raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}")
 
diff --git a/docs/examples/full_page_ocr.py b/docs/examples/full_page_ocr.py
index 0a61507e..35c2ba6b 100644
--- a/docs/examples/full_page_ocr.py
+++ b/docs/examples/full_page_ocr.py
@@ -29,7 +29,6 @@ def main():
         format_options={
             InputFormat.PDF: PdfFormatOption(
                 pipeline_options=pipeline_options,
-                backend=DoclingParseDocumentBackend,
             )
         }
     )
diff --git a/mkdocs.yml b/mkdocs.yml
index 1fef4428..9ca6fdeb 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -69,6 +69,7 @@ nav:
       - "Figure enrichment": examples/develop_picture_enrichment.py
       - "Table export": examples/export_tables.py
       - "Multimodal export": examples/export_multimodal.py
+      - "Force full page OCR": examples/full_page_ocr.py
     - RAG / QA:
       - "RAG with LlamaIndex 🦙": examples/rag_llamaindex.ipynb
       - "RAG with LangChain 🦜🔗": examples/rag_langchain.ipynb