mirror of
https://github.com/ocrmypdf/OCRmyPDF.git
synced 2025-11-04 03:40:19 +00:00
tests: split out stdin/stdout tests
This commit is contained in:
James R. Barlow
parent
7bfcd0a9d5
commit
a1a7b973e9
@ -1,4 +1,4 @@
|
||||
# © 2015-17 James R. Barlow: github.com/jbarlow83
|
||||
# © 2015-19 James R. Barlow: github.com/jbarlow83
|
||||
#
|
||||
# This file is part of OCRmyPDF.
|
||||
#
|
||||
@ -18,10 +18,9 @@
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import sys
|
||||
from math import isclose
|
||||
from pathlib import Path
|
||||
from subprocess import DEVNULL, PIPE, run, Popen
|
||||
from subprocess import PIPE, run
|
||||
|
||||
import PIL
|
||||
import pytest
|
||||
@ -84,11 +83,6 @@ def spoof_no_tess_gs_raster_fail(tmp_path_factory):
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture(scope='session')
|
||||
def spoof_tess_bad_utf8(tmp_path_factory):
|
||||
return spoof(tmp_path_factory, tesseract='tesseract_badutf8.py')
|
||||
|
||||
|
||||
def test_quick(spoof_tesseract_cache, resources, outpdf):
|
||||
check_ocrmypdf(resources / 'ccitt.pdf', outpdf, env=spoof_tesseract_cache)
|
||||
|
||||
@ -550,68 +544,6 @@ def test_jbig2_passthrough(spoof_tesseract_cache, resources, outpdf):
|
||||
assert out_pageinfo[0].images[0].enc == Encoding.jbig2
|
||||
|
||||
|
||||
def test_stdin(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
|
||||
input_file = str(resources / 'francais.pdf')
|
||||
output_file = str(outpdf)
|
||||
|
||||
# Runs: ocrmypdf - output.pdf < testfile.pdf
|
||||
with open(input_file, 'rb') as input_stream:
|
||||
p_args = ocrmypdf_exec + ['-', output_file]
|
||||
p = run(
|
||||
p_args,
|
||||
stdout=PIPE,
|
||||
stderr=PIPE,
|
||||
stdin=input_stream,
|
||||
env=spoof_tesseract_noop,
|
||||
)
|
||||
assert p.returncode == ExitCode.ok
|
||||
|
||||
|
||||
def test_stdout(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
|
||||
input_file = str(resources / 'francais.pdf')
|
||||
output_file = str(outpdf)
|
||||
|
||||
# Runs: ocrmypdf francais.pdf - > test_stdout.pdf
|
||||
with open(output_file, 'wb') as output_stream:
|
||||
p_args = ocrmypdf_exec + [input_file, '-']
|
||||
p = run(
|
||||
p_args,
|
||||
stdout=output_stream,
|
||||
stderr=PIPE,
|
||||
stdin=DEVNULL,
|
||||
env=spoof_tesseract_noop,
|
||||
)
|
||||
assert p.returncode == ExitCode.ok
|
||||
|
||||
assert qpdf.check(output_file, log=None)
|
||||
|
||||
|
||||
@pytest.mark.skipif(
|
||||
sys.version_info[0:3] >= (3, 6, 4), reason="issue fixed in Python 3.6.4"
|
||||
)
|
||||
def test_closed_streams(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
|
||||
input_file = str(resources / 'francais.pdf')
|
||||
output_file = str(outpdf)
|
||||
|
||||
def evil_closer():
|
||||
os.close(0)
|
||||
os.close(1)
|
||||
|
||||
p_args = ocrmypdf_exec + [input_file, output_file]
|
||||
p = Popen( # pylint: disable=subprocess-popen-preexec-fn
|
||||
p_args,
|
||||
close_fds=True,
|
||||
stdout=None,
|
||||
stderr=PIPE,
|
||||
stdin=None,
|
||||
env=spoof_tesseract_noop,
|
||||
preexec_fn=evil_closer,
|
||||
)
|
||||
out, err = p.communicate()
|
||||
print(err.decode())
|
||||
assert p.returncode == ExitCode.ok
|
||||
|
||||
|
||||
def test_masks(spoof_tesseract_noop, resources, outpdf):
|
||||
assert (
|
||||
ocrmypdf.ocr(
|
||||
@ -993,36 +925,6 @@ def test_pdfa_n(spoof_tesseract_cache, pdfa_level, resources, outpdf):
|
||||
assert pdfa_info['conformance'] == f'PDF/A-{pdfa_level}B'
|
||||
|
||||
|
||||
@pytest.mark.skipif(sys.version_info >= (3, 7, 0), reason='better utf-8')
|
||||
@pytest.mark.skipif(
|
||||
Path('/etc/alpine-release').exists(), reason="invalid test on alpine"
|
||||
)
|
||||
def test_bad_locale():
|
||||
env = os.environ.copy()
|
||||
env['LC_ALL'] = 'C'
|
||||
|
||||
p, out, err = run_ocrmypdf('a', 'b', env=env)
|
||||
assert out == '', "stdout not clean"
|
||||
assert p.returncode != 0
|
||||
assert 'configured to use ASCII as encoding' in err, "should whine"
|
||||
|
||||
|
||||
@pytest.mark.parametrize('renderer', RENDERERS)
|
||||
def test_bad_utf8(spoof_tess_bad_utf8, renderer, resources, no_outpdf):
|
||||
p, out, err = run_ocrmypdf(
|
||||
resources / 'ccitt.pdf',
|
||||
no_outpdf,
|
||||
'--pdf-renderer',
|
||||
renderer,
|
||||
env=spoof_tess_bad_utf8,
|
||||
)
|
||||
|
||||
assert out == '', "stdout not clean"
|
||||
assert p.returncode != 0
|
||||
assert 'not utf-8' in err, "should whine about utf-8"
|
||||
assert '\\x96' in err, 'should repeat backslash encoded output'
|
||||
|
||||
|
||||
@pytest.mark.skipif(
|
||||
PIL.__version__ < '5.0.0', reason="Pillow < 5.0.0 doesn't raise the exception"
|
||||
)
|
||||
@ -1051,14 +953,6 @@ def test_text_curves(spoof_tesseract_noop, resources, outpdf):
|
||||
assert len(info.pages[0].images) != 0, "force did not rasterize"
|
||||
|
||||
|
||||
def test_dev_null(spoof_tesseract_noop, resources):
|
||||
p, out, err = run_ocrmypdf(
|
||||
resources / 'trivial.pdf', os.devnull, '--force-ocr', env=spoof_tesseract_noop
|
||||
)
|
||||
assert p.returncode == 0, "could not send output to /dev/null"
|
||||
assert len(out) == 0, "wrote to stdout"
|
||||
|
||||
|
||||
def test_output_is_dir(spoof_tesseract_noop, resources, outdir):
|
||||
p, out, err = run_ocrmypdf(
|
||||
resources / 'trivial.pdf', outdir, '--force-ocr', env=spoof_tesseract_noop
|
||||
|
||||
137
tests/test_stdio.py
Normal file
137
tests/test_stdio.py
Normal file
@ -0,0 +1,137 @@
|
||||
# © 2019 James R. Barlow: github.com/jbarlow83
|
||||
#
|
||||
# This file is part of OCRmyPDF.
|
||||
#
|
||||
# OCRmyPDF is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# OCRmyPDF is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with OCRmyPDF. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from subprocess import DEVNULL, PIPE, run, Popen
|
||||
|
||||
import pytest
|
||||
|
||||
from ocrmypdf.exceptions import ExitCode
|
||||
from ocrmypdf.exec import qpdf
|
||||
|
||||
# pytest.helpers is dynamic
|
||||
# pylint: disable=no-member,redefined-outer-name
|
||||
|
||||
run_ocrmypdf = pytest.helpers.run_ocrmypdf
|
||||
spoof = pytest.helpers.spoof
|
||||
|
||||
|
||||
@pytest.fixture(scope='session')
|
||||
def spoof_tess_bad_utf8(tmp_path_factory):
|
||||
return spoof(tmp_path_factory, tesseract='tesseract_badutf8.py')
|
||||
|
||||
|
||||
def test_stdin(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
|
||||
input_file = str(resources / 'francais.pdf')
|
||||
output_file = str(outpdf)
|
||||
|
||||
# Runs: ocrmypdf - output.pdf < testfile.pdf
|
||||
with open(input_file, 'rb') as input_stream:
|
||||
p_args = ocrmypdf_exec + ['-', output_file]
|
||||
p = run(
|
||||
p_args,
|
||||
stdout=PIPE,
|
||||
stderr=PIPE,
|
||||
stdin=input_stream,
|
||||
env=spoof_tesseract_noop,
|
||||
)
|
||||
assert p.returncode == ExitCode.ok
|
||||
|
||||
|
||||
def test_stdout(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
|
||||
input_file = str(resources / 'francais.pdf')
|
||||
output_file = str(outpdf)
|
||||
|
||||
# Runs: ocrmypdf francais.pdf - > test_stdout.pdf
|
||||
with open(output_file, 'wb') as output_stream:
|
||||
p_args = ocrmypdf_exec + [input_file, '-']
|
||||
p = run(
|
||||
p_args,
|
||||
stdout=output_stream,
|
||||
stderr=PIPE,
|
||||
stdin=DEVNULL,
|
||||
env=spoof_tesseract_noop,
|
||||
)
|
||||
assert p.returncode == ExitCode.ok
|
||||
|
||||
assert qpdf.check(output_file, log=None)
|
||||
|
||||
|
||||
@pytest.mark.skipif(
|
||||
sys.version_info[0:3] >= (3, 6, 4), reason="issue fixed in Python 3.6.4"
|
||||
)
|
||||
def test_closed_streams(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
|
||||
input_file = str(resources / 'francais.pdf')
|
||||
output_file = str(outpdf)
|
||||
|
||||
def evil_closer():
|
||||
os.close(0)
|
||||
os.close(1)
|
||||
|
||||
p_args = ocrmypdf_exec + [input_file, output_file]
|
||||
p = Popen( # pylint: disable=subprocess-popen-preexec-fn
|
||||
p_args,
|
||||
close_fds=True,
|
||||
stdout=None,
|
||||
stderr=PIPE,
|
||||
stdin=None,
|
||||
env=spoof_tesseract_noop,
|
||||
preexec_fn=evil_closer,
|
||||
)
|
||||
out, err = p.communicate()
|
||||
print(err.decode())
|
||||
assert p.returncode == ExitCode.ok
|
||||
|
||||
|
||||
@pytest.mark.skipif(sys.version_info >= (3, 7, 0), reason='better utf-8')
|
||||
@pytest.mark.skipif(
|
||||
Path('/etc/alpine-release').exists(), reason="invalid test on alpine"
|
||||
)
|
||||
def test_bad_locale():
|
||||
env = os.environ.copy()
|
||||
env['LC_ALL'] = 'C'
|
||||
|
||||
p, out, err = run_ocrmypdf('a', 'b', env=env)
|
||||
assert out == '', "stdout not clean"
|
||||
assert p.returncode != 0
|
||||
assert 'configured to use ASCII as encoding' in err, "should whine"
|
||||
|
||||
|
||||
@pytest.mark.parametrize('renderer', ['hocr', 'sandwich'])
|
||||
def test_bad_utf8(spoof_tess_bad_utf8, renderer, resources, no_outpdf):
|
||||
p, out, err = run_ocrmypdf(
|
||||
resources / 'ccitt.pdf',
|
||||
no_outpdf,
|
||||
'--pdf-renderer',
|
||||
renderer,
|
||||
env=spoof_tess_bad_utf8,
|
||||
)
|
||||
|
||||
assert out == '', "stdout not clean"
|
||||
assert p.returncode != 0
|
||||
assert 'not utf-8' in err, "should whine about utf-8"
|
||||
assert '\\x96' in err, 'should repeat backslash encoded output'
|
||||
|
||||
|
||||
def test_dev_null(spoof_tesseract_noop, resources):
|
||||
p, out, err = run_ocrmypdf(
|
||||
resources / 'trivial.pdf', os.devnull, '--force-ocr', env=spoof_tesseract_noop
|
||||
)
|
||||
assert p.returncode == 0, "could not send output to /dev/null"
|
||||
assert len(out) == 0, "wrote to stdout"
|
||||
Loading…
x
Reference in New Issue
Block a user