From be11210ae9d600f7d8148bf4098cb487571a707c Mon Sep 17 00:00:00 2001
From: Maksym Lysak <mly@zurich.ibm.com>
Date: Thu, 13 Feb 2025 10:29:37 +0100
Subject: [PATCH] Removed special html code wrapping when exporting to docling
 document, cleaned up comments

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
---
 docling/pipeline/vlm_pipeline.py | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/docling/pipeline/vlm_pipeline.py b/docling/pipeline/vlm_pipeline.py
index 53c10e42c..fd6e9dfce 100644
--- a/docling/pipeline/vlm_pipeline.py
+++ b/docling/pipeline/vlm_pipeline.py
@@ -110,13 +110,6 @@ def __init__(self, pipeline_options: VlmPipelineOptions):
             "code": "lightblue",
         }
 
-        """
-        if pipeline_options.artifacts_path is None:
-            self.artifacts_path = self.download_models_hf()
-        else:
-            self.artifacts_path = Path(pipeline_options.artifacts_path)
-        """
-
         self.keep_images = (
             self.pipeline_options.generate_page_images
             or self.pipeline_options.generate_picture_images
@@ -447,9 +440,6 @@ def parse_table_content(otsl_content: str) -> TableData:
                         text_content = extract_text_from_backend(page, bbox)
                     else:
                         text_content = extract_inner_text(full_chunk)
-                    # If it's code, wrap it with <pre><code> tags
-                    if doc_label == DocItemLabel.CODE:
-                        text_content = f"<pre><code>{text_content}</code></pre>"
                     doc.add_text(
                         label=doc_label,
                         text=text_content,
@@ -472,6 +462,3 @@ def get_default_options(cls) -> PdfPipelineOptions:
     @classmethod
     def is_backend_supported(cls, backend: AbstractDocumentBackend):
         return isinstance(backend, PdfDocumentBackend)
-
-    # def _turn_tags_into_doc(self, document_tags):
-    #     return DoclingDocument()