From 214a333e2d25d78082c2a5e6d3783ca9702c14a5 Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Tue, 11 Jun 2024 14:44:54 -0700 Subject: [PATCH] Block Tesseract 5.4.0 --- src/ocrmypdf/builtin_plugins/tesseract_ocr.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/src/ocrmypdf/builtin_plugins/tesseract_ocr.py b/src/ocrmypdf/builtin_plugins/tesseract_ocr.py index ae0f0763..a54052c5 100644 --- a/src/ocrmypdf/builtin_plugins/tesseract_ocr.py +++ b/src/ocrmypdf/builtin_plugins/tesseract_ocr.py @@ -14,7 +14,7 @@ from ocrmypdf import hookimpl from ocrmypdf._exec import tesseract from ocrmypdf._jobcontext import PageContext from ocrmypdf.cli import numeric, str_to_int -from ocrmypdf.exceptions import BadArgsError +from ocrmypdf.exceptions import BadArgsError, MissingDependencyError from ocrmypdf.helpers import clamp from ocrmypdf.imageops import calculate_downsample, downsample_image from ocrmypdf.pluginspec import OcrEngine @@ -145,6 +145,12 @@ def check_options(options): need_version='4.1.1', # Ubuntu 22.04 version (also 20.04) version_parser=tesseract.TesseractVersion, ) + tess_version = tesseract.version() + if tess_version == tesseract.TesseractVersion('5.4.0'): + raise MissingDependencyError( + "Tesseract 5.4.0 is not supported due to regressions in this version. " + "Please upgrade to a newer or supported older version." + ) # Decide on what renderer to use if options.pdf_renderer == 'auto':