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

refactor: fix type of tesseractocr options (#140)

Browse Source 
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
This commit is contained in:
Michele Dolfi 2024-10-14 08:40:22 +02:00 committed by GitHub
parent 4672b24c1a
commit 2b1e72d327
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docling/models/tesseract_ocr_model.py
View File

@ -4,16 +4,16 @@ from typing import Iterable
import numpy import numpy
from docling.datamodel.base_models import BoundingBox, CoordOrigin, OcrCell, Page from docling.datamodel.base_models import BoundingBox, CoordOrigin, OcrCell, Page
from docling.datamodel.pipeline_options import TesseractCliOcrOptions from docling.datamodel.pipeline_options import TesseractOcrOptions
from docling.models.base_ocr_model import BaseOcrModel from docling.models.base_ocr_model import BaseOcrModel
_log = logging.getLogger(__name__) _log = logging.getLogger(__name__)
class TesseractOcrModel(BaseOcrModel): class TesseractOcrModel(BaseOcrModel):
def __init__(self, enabled: bool, options: TesseractCliOcrOptions): def __init__(self, enabled: bool, options: TesseractOcrOptions):
super().__init__(enabled=enabled, options=options) super().__init__(enabled=enabled, options=options)
self.options: TesseractCliOcrOptions self.options: TesseractOcrOptions
self.scale = 3 # multiplier for 72 dpi == 216 dpi. self.scale = 3 # multiplier for 72 dpi == 216 dpi.
self.reader = None self.reader = None