NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Handle no result from RapidOcr reader (#558)

Browse Source 
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
This commit is contained in:
Christoph Auer 2024-12-10 16:25:05 +01:00 committed by GitHub
parent d0c9e8e508
commit f45499ce93
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
docling/models/rapid_ocr_model.py
View File

@ -118,24 +118,25 @@ class RapidOcrModel(BaseOcrModel):
del high_res_image
del im
cells = [
OcrCell(
id=ix,
text=line[1],
confidence=line[2],
bbox=BoundingBox.from_tuple(
coord=(
(line[0][0][0] / self.scale) + ocr_rect.l,
(line[0][0][1] / self.scale) + ocr_rect.t,
(line[0][2][0] / self.scale) + ocr_rect.l,
(line[0][2][1] / self.scale) + ocr_rect.t,
if result is not None:
cells = [
OcrCell(
id=ix,
text=line[1],
confidence=line[2],
bbox=BoundingBox.from_tuple(
coord=(
(line[0][0][0] / self.scale) + ocr_rect.l,
(line[0][0][1] / self.scale) + ocr_rect.t,
(line[0][2][0] / self.scale) + ocr_rect.l,
(line[0][2][1] / self.scale) + ocr_rect.t,
),
origin=CoordOrigin.TOPLEFT,
),
origin=CoordOrigin.TOPLEFT,
),
)
for ix, line in enumerate(result)
]
all_ocr_cells.extend(cells)
)
for ix, line in enumerate(result)
]
all_ocr_cells.extend(cells)
# Post-process the cells
page.cells = self.post_process_cells(all_ocr_cells, page.cells)