feat: adding HTML export to DoclingDocument, adding export of images …

…in png with links to Markdown & HTML (#69) Signed-off-by: Peter Staar <[email protected]> Signed-off-by: Christoph Auer <[email protected]> Signed-off-by: Michele Dolfi <[email protected]> Co-authored-by: Christoph Auer <[email protected]> Co-authored-by: Michele Dolfi <[email protected]>
DS4SD · Nov 27, 2024 · ef49fd3 · ef49fd3
1 parent b32c4cc
commit ef49fd3
Show file tree

Hide file tree

Showing 37 changed files with 4,779 additions and 453 deletions.
diff --git a/.gitignore b/.gitignore
@@ -3,6 +3,12 @@ node_modules/
 .idea/
 *~
 *.DS_Store
+test/data/constructed_images*
+test/data/doc/constructed_doc*.html
+test/data/doc/constructed_doc*.yaml
+test/data/doc/constructed_doc*.json
+test/data/doc/constructed_doc*.dt
+test/data/doc/constructed_doc*.md
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

diff --git a/docling_core/types/doc/base.py b/docling_core/types/doc/base.py
@@ -10,8 +10,9 @@
 class ImageRefMode(str, Enum):
     """ImageRefMode."""
 
-    PLACEHOLDER = "placeholder"
-    EMBEDDED = "embedded"
+    PLACEHOLDER = "placeholder"  # just a place-holder
+    EMBEDDED = "embedded"  # embed the image as a base64
+    REFERENCED = "referenced"  # reference the image via uri
 
 
 class CoordOrigin(str, Enum):