Prevent use of —pdf-renderer tess4 on tesseract 3

This commit is contained in:
James R. Barlow
2017-02-06 13:49:43 -08:00
parent 5b8d88af4c
commit a0657ad937
3 changed files with 32 additions and 9 deletions
+4
View File
@@ -333,6 +333,10 @@ def check_options_advanced(options, log):
if options.tesseract_oem and not tesseract.v4():
log.warning(
"--tesseract-oem requires Tesseract 4.x -- argument ignored")
if options.pdf_renderer == 'tess4' and not tesseract.has_textonly_pdf():
raise MissingDependencyError(
"--pdf-renderer tess4 requires Tesseract 4.x "
"commit 3d9fb3b or later")
def check_options(options, log):
+28
View File
@@ -0,0 +1,28 @@
#!/usr/bin/env python3
# © 2017 James R. Barlow: github.com/jbarlow83
import pytest
from ocrmypdf.exceptions import ExitCode
from ocrmypdf.exec import tesseract
# Skip all tests in this file if not tesseract 3
pytestmark = pytest.mark.skipif(tesseract.v4(),
reason="tesseract 3.x required")
def test_textonly_pdf_on_tess3(resources, no_outpdf):
p, _, _ = pytest.helpers.run_ocrmypdf(
resources / 'linn.pdf',
no_outpdf, '--pdf-renderer', 'tess4')
assert p.returncode == ExitCode.missing_dependency
def test_oem_on_tess3(resources, no_outpdf):
p, _, err = pytest.helpers.run_ocrmypdf(
resources / 'aspect.pdf',
no_outpdf, '--tesseract-oem', '1')
assert p.returncode == ExitCode.ok
assert 'argument ignored' in err
-9
View File
@@ -1,17 +1,8 @@
#!/usr/bin/env python3
# © 2017 James R. Barlow: github.com/jbarlow83
from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
import os
import shutil
from contextlib import suppress
import sys
import pytest
from ocrmypdf.pageinfo import pdf_get_all_pageinfo
import PyPDF2 as pypdf
from ocrmypdf.exceptions import ExitCode
from ocrmypdf import leptonica
from ocrmypdf.pdfa import file_claims_pdfa
from ocrmypdf.exec import tesseract