From 1caebaefb55a6c30505d5d2fa47b5c86e6509f77 Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Sun, 25 Mar 2018 21:38:20 -0700 Subject: [PATCH] tesseract: Fix FileExistsError on if output file was created at timeout --- src/ocrmypdf/exec/tesseract.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/src/ocrmypdf/exec/tesseract.py b/src/ocrmypdf/exec/tesseract.py index a9034464..db4ca66b 100644 --- a/src/ocrmypdf/exec/tesseract.py +++ b/src/ocrmypdf/exec/tesseract.py @@ -22,9 +22,11 @@ import shutil from functools import lru_cache from collections import namedtuple from textwrap import dedent -import PyPDF2 as pypdf from subprocess import PIPE, CalledProcessError, \ TimeoutExpired, check_output, STDOUT +from contextlib import suppress + +import PyPDF2 as pypdf from ..exceptions import MissingDependencyError, TesseractConfigError from ..helpers import page_number @@ -281,6 +283,8 @@ def use_skip_page(text_only, skip_pdf, output_pdf, output_text): f.write('[skipped page]') if not text_only: + with suppress(FileNotFoundError): + os.remove(output_pdf) # In case it was partially created os.symlink(skip_pdf, output_pdf) return