mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(TesserOcrModel): Refactor code to catch exception in case of import error

Browse Source 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
This commit is contained in:
Nikos Livathinos 2024-10-03 14:23:07 +02:00
parent 81d176cd3d
commit 1d4517ffb4
1 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
docling/models/tesserocr_model.py
View File

@ -2,8 +2,6 @@ import logging
from typing import Iterable
import numpy
import tesserocr
from tesserocr import OEM, PSM, RIL, PyTessBaseAPI
from docling.datamodel.base_models import BoundingBox, CoordOrigin, OcrCell, Page
from docling.datamodel.pipeline_options import TesseractOcrOptions
@ -21,12 +19,22 @@ class TesserOcrModel(BaseOcrModel):
self.reader = None
if self.enabled:
try:
import tesserocr
except ImportError:
msg = (
"TesserOCR is not installed."
"Please install it via `pip install easyocr` to use this OCR engine."
)
raise ImportError(msg)
# Initialize the tesseractAPI
lang = "+".join(self.options.lang)
_log.debug("Initializing TesserOCR: %s", tesserocr.tesseract_version())
self.reader = PyTessBaseAPI(
lang=lang, psm=PSM.AUTO, init=True, oem=OEM.DEFAULT
self.reader = tesserocr.PyTessBaseAPI(
lang=lang, psm=tesserocr.PSM.AUTO, init=True, oem=tesserocr.OEM.DEFAULT
)
self.reader_RIL = tesserocr.RIL.TEXTLINE
def __del__(self):
if self.reader is not None:
@ -51,7 +59,7 @@ class TesserOcrModel(BaseOcrModel):
# Retrieve text snippets with their bounding boxes
self.reader.SetImage(high_res_image)
boxes = self.reader.GetComponentImages(RIL.TEXTLINE, True)
boxes = self.reader.GetComponentImages(self.reader_RIL.TEXTLINE, True)
cells = []
for ix, (im, box, _, _) in enumerate(boxes):