mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-11 14:18:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: allow computing page images on-demand with scale and cache them (#36)

Browse Source 
* feat: allow computing page images on-demand and cache them

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* feat: expose scale for export of page images and document elements

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* fix comment

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2024-08-20 13:27:19 +02:00
committed by GitHub
parent c253dd743a
commit 78347bf679
9 changed files with 104 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
docling/document_converter.py
View File

@@ -188,10 +188,8 @@ class DocumentConverter:
# Free up mem resources before moving on with next batch
# Remove page images (can be disabled)
if not self.assemble_options.keep_page_images:
assembled_page.image = (
None # Comment this if you want to visualize page images
)
if self.assemble_options.images_scale is None:
assembled_page._image_cache = {}
# Unload backend
assembled_page._backend.unload()
@@ -231,7 +229,15 @@ class DocumentConverter:
# Generate the page image and store it in the page object
def populate_page_images(self, doc: InputDocument, page: Page) -> Page:
page.image = page._backend.get_page_image()
# default scale
page.get_image(scale=1.0)
# user requested scales
if self.assemble_options.images_scale is not None:
page._default_image_scale = self.assemble_options.images_scale
page.get_image(
scale=self.assemble_options.images_scale
) # this will trigger storing the image in the internal cache
return page
@@ -247,7 +253,7 @@ class DocumentConverter:
draw.rectangle([(x0, y0), (x1, y1)], outline="red")
image.show()
# draw_text_boxes(page.image, cells)
# draw_text_boxes(page.get_image(scale=1.0), cells)
return page