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

fix(tesserocr): Raise Exception if tesserocr has not loaded any languages (#279)

Browse Source 
fix(TesseractOcrModel): Raise Exception if tesserocr has not loaded any languages. Provide a descriptive error message.

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
This commit is contained in:
Nikos Livathinos 2024-11-08 13:03:09 +01:00 committed by GitHub
parent 6c22cba0a7
commit 704d792a79
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 19 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
docling/models/tesseract_ocr_model.py
View File

@ -22,25 +22,37 @@ class TesseractOcrModel(BaseOcrModel):
self.reader = None
if self.enabled:
setup_errmsg = (
install_errmsg = (
"tesserocr is not correctly installed. "
"Please install it via `pip install tesserocr` to use this OCR engine. "
"Note that tesserocr might have to be manually compiled for working with"
"Note that tesserocr might have to be manually compiled for working with "
"your Tesseract installation. The Docling documentation provides examples for it. "
"Alternatively, Docling has support for other OCR engines. See the documentation."
"Alternatively, Docling has support for other OCR engines. See the documentation: "
"https://ds4sd.github.io/docling/installation/"
)
missing_langs_errmsg = (
"tesserocr is not correctly configured. No language models have been detected. "
"Please ensure that the TESSDATA_PREFIX envvar points to tesseract languages dir. "
"You can find more information how to setup other OCR engines in Docling "
"documentation: "
"https://ds4sd.github.io/docling/installation/"
)
try:
import tesserocr
except ImportError:
raise ImportError(setup_errmsg)
raise ImportError(install_errmsg)
try:
tesseract_version = tesserocr.tesseract_version()
_log.debug("Initializing TesserOCR: %s", tesseract_version)
except:
raise ImportError(setup_errmsg)
raise ImportError(install_errmsg)
_, tesserocr_languages = tesserocr.get_languages()
if not tesserocr_languages:
raise ImportError(missing_langs_errmsg)
# Initialize the tesseractAPI
_log.debug("Initializing TesserOCR: %s", tesseract_version)
lang = "+".join(self.options.lang)
if self.options.path is not None:
self.reader = tesserocr.PyTessBaseAPI(