menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Abolish spoof_tesseract_noop

Browse Source
This commit is contained in:
James R. Barlow
2020-06-01 03:07:53 -07:00
parent 2b23f7ec73
commit 1598f2f0e5
12 changed files with 234 additions and 282 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ocrmypdf/api.py
+1 -1
View File
@@ -143,7 +143,7 @@ def create_options(
# These arguments with special handling for which we bypass
# argparse
if arg in {'tesseract_env', 'progress_bar'}:
if arg in {'tesseract_env', 'progress_bar', 'plugins'}:
deferred.append((arg, val))
continue
tests/conftest.py
+2 -7
View File
@@ -169,11 +169,6 @@ def spoof(tmp_path_factory, **kwargs):
return env
@pytest.fixture
def spoof_tesseract_noop(tmp_path_factory):
return spoof(tmp_path_factory, tesseract='tesseract_noop.py')
@pytest.fixture
def spoof_tesseract_cache(tmp_path_factory):
if running_in_docker():
@@ -222,7 +217,7 @@ def check_ocrmypdf(input_file, output_file, *args, env=None):
if env:
first = env['_OCRMYPDF_TEST_PATH'].split(os.pathsep)[0]
if 'tesseract_noop' in first:
options.plugins = ['tests/plugins/tesseract_noop.py']
raise ValueError('noop')
else:
options.tesseract_env = env
options.tesseract_env['_OCRMYPDF_TEST_INFILE'] = os.fspath(input_file)
@@ -250,7 +245,7 @@ def run_ocrmypdf_api(input_file, output_file, *args, env=None):
try:
first = env['_OCRMYPDF_TEST_PATH'].split(os.pathsep)[0]
if 'tesseract_noop' in first:
options.plugins = ['tests/plugins/tesseract_noop.py']
raise ValueError('noop')
else:
options.tesseract_env = env.copy()
options.tesseract_env['_OCRMYPDF_TEST_INFILE'] = os.fspath(input_file)
tests/spoof/tesseract_noop.py
-134
View File
@@ -1,134 +0,0 @@
#!/usr/bin/env python3
# © 2016 James R. Barlow: github.com/jbarlow83
#
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the
# "Software"), to deal in the Software without restriction, including
# without limitation the rights to use, copy, modify, merge, publish,
# distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so, subject to
# the following conditions:
#
# The above copyright notice and this permission notice shall be included
# in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
"""Tesseract no-op spoof
To quickly run tests where getting OCR output is not necessary.
In 'hocr' mode, create a .hocr file that specifies no text found.
In 'pdf' mode, convert the image to PDF using another program.
In orientation check mode, report the orientation is upright.
"""
import sys
from pathlib import Path
import img2pdf
import pikepdf
from PIL import Image
VERSION_STRING = '''tesseract 4.0.0
leptonica-1.77.0
libjpeg 9c : libpng 1.6.35 : libtiff 4.0.10 : zlib 1.2.11 : libopenjp2 2.3.0
Found AVX2
Found AVX
Found SSE
SPOOFED
'''
HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<title></title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name='ocr-system' content='tesseract 4.0.0' />
<meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
</head>
<body>
<div class='ocr_page' id='page_1' title='image "x.tif"; bbox 0 0 {0} {1}; ppageno 0'>
<div class='ocr_carea' id='block_1_1' title="bbox 0 1 {0} {1}">
<p class='ocr_par' dir='ltr' id='par_1' title="bbox 0 1 {0} {1}">
<span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}"><span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
</span>
</p>
</div>
</div>
</body>
</html>'''
def main():
if sys.argv[1] == '--version':
print(VERSION_STRING, file=sys.stderr)
sys.exit(0)
elif sys.argv[1] == '--list-langs':
print('List of available languages (1):\neng', file=sys.stderr)
sys.exit(0)
elif sys.argv[-2] == '--print-parameters':
print("Some parameters", file=sys.stderr)
print("textonly_pdf\t1\tSome help text")
sys.exit(0)
elif sys.argv[-2] == 'hocr':
inputf = sys.argv[-4]
output = sys.argv[-3]
with Image.open(inputf) as im, open(
output + '.hocr', 'w', encoding='utf-8'
) as f:
w, h = im.size
f.write(HOCR_TEMPLATE.format(str(w), str(h)))
with open(output + '.txt', 'w') as f:
f.write('')
elif sys.argv[-2] == 'pdf':
if 'textonly_pdf=1' in sys.argv:
inputf = sys.argv[-4]
output = sys.argv[-3]
with Image.open(inputf) as im:
dpi = im.info['dpi']
pagesize = im.size[0] / dpi[0], im.size[1] / dpi[1]
ptsize = pagesize[0] * 72, pagesize[1] * 72
pdf_out = pikepdf.new()
pdf_out.add_blank_page(page_size=ptsize)
pdf_out.save(Path(output).with_suffix('.pdf'), static_id=True)
Path(output).with_suffix('.txt').write_text('')
else:
inputf = sys.argv[-4]
output = sys.argv[-3]
pdf_bytes = img2pdf.convert([inputf], dpi=300)
with open(output + '.pdf', 'wb') as f:
f.write(pdf_bytes)
with open(output + '.txt', 'w') as f:
f.write('')
elif sys.argv[-1] == 'stdout':
inputf = sys.argv[-2]
print(
"""Orientation: 0
Orientation in degrees: 0
Orientation confidence: 100.00
Script: 1
Script confidence: 100.00""",
file=sys.stderr,
)
else:
print("Spoof doesn't understand arguments", file=sys.stderr)
print(sys.argv, file=sys.stderr)
sys.exit(1)
sys.exit(0)
if __name__ == '__main__':
main()
tests/test_acroform.py
+2 -2
View File
@@ -35,8 +35,8 @@ def test_acroform_and_redo(acroform, caplog, no_outpdf):
assert '--redo-ocr is not currently possible' in caplog.text
def test_acroform_message(acroform, caplog, spoof_tesseract_noop, outpdf):
def test_acroform_message(acroform, caplog, outpdf):
caplog.set_level(logging.INFO)
check_ocrmypdf(acroform, outpdf, env=spoof_tesseract_noop)
check_ocrmypdf(acroform, outpdf, '--plugin', 'tests/plugins/tesseract_noop.py')
assert 'fillable form' in caplog.text
assert '--force-ocr' in caplog.text
tests/test_ghostscript.py
+34 -24
View File
@@ -33,31 +33,23 @@ spoof = pytest.helpers.spoof
@pytest.fixture
def spoof_no_tess_gs_render_fail(tmp_path_factory):
return spoof(
tmp_path_factory, tesseract='tesseract_noop.py', gs='gs_render_failure.py'
)
def spoof_gs_render_fail(tmp_path_factory):
return spoof(tmp_path_factory, gs='gs_render_failure.py')
@pytest.fixture
def spoof_no_tess_gs_raster_fail(tmp_path_factory):
return spoof(
tmp_path_factory, tesseract='tesseract_noop.py', gs='gs_raster_failure.py'
)
def spoof_gs_raster_fail(tmp_path_factory):
return spoof(tmp_path_factory, gs='gs_raster_failure.py')
@pytest.fixture
def spoof_no_tess_no_pdfa(tmp_path_factory):
return spoof(
tmp_path_factory, tesseract='tesseract_noop.py', gs='gs_pdfa_failure.py'
)
def spoof_no_pdfa(tmp_path_factory):
return spoof(tmp_path_factory, gs='gs_pdfa_failure.py')
@pytest.fixture
def spoof_no_tess_pdfa_warning(tmp_path_factory):
return spoof(
tmp_path_factory, tesseract='tesseract_noop.py', gs='gs_feature_elision.py'
)
def spoof_pdfa_warning(tmp_path_factory):
return spoof(tmp_path_factory, gs='gs_feature_elision.py')
@pytest.fixture
@@ -114,30 +106,48 @@ def test_rasterize_rotated(francais, outdir, caplog):
assert im.info['dpi'] == (forced_dpi[1], forced_dpi[0])
def test_gs_render_failure(spoof_no_tess_gs_render_fail, resources, outpdf):
def test_gs_render_failure(spoof_gs_render_fail, resources, outpdf):
p, out, err = run_ocrmypdf(
resources / 'blank.pdf', outpdf, env=spoof_no_tess_gs_render_fail
resources / 'blank.pdf',
outpdf,
'--plugin',
'tests/plugins/tesseract_noop.py',
env=spoof_gs_render_fail,
)
assert 'Casper is not a friendly ghost' in err
assert p.returncode == ExitCode.child_process_error
def test_gs_raster_failure(spoof_no_tess_gs_raster_fail, resources, outpdf):
def test_gs_raster_failure(spoof_gs_raster_fail, resources, outpdf):
p, out, err = run_ocrmypdf(
resources / 'francais.pdf', outpdf, env=spoof_no_tess_gs_raster_fail
resources / 'francais.pdf',
outpdf,
'--plugin',
'tests/plugins/tesseract_noop.py',
env=spoof_gs_raster_fail,
)
assert 'Ghost story archive not found' in err
assert p.returncode == ExitCode.child_process_error
def test_ghostscript_pdfa_failure(spoof_no_tess_no_pdfa, resources, outpdf):
def test_ghostscript_pdfa_failure(spoof_no_pdfa, resources, outpdf):
p, out, err = run_ocrmypdf(
resources / 'francais.pdf', outpdf, env=spoof_no_tess_no_pdfa
resources / 'francais.pdf',
outpdf,
'--plugin',
'tests/plugins/tesseract_noop.py',
env=spoof_no_pdfa,
)
assert (
p.returncode == ExitCode.pdfa_conversion_failed
), "Unexpected return when PDF/A fails"
def test_ghostscript_feature_elision(spoof_no_tess_pdfa_warning, resources, outpdf):
check_ocrmypdf(resources / 'francais.pdf', outpdf, env=spoof_no_tess_pdfa_warning)
def test_ghostscript_feature_elision(spoof_pdfa_warning, resources, outpdf):
check_ocrmypdf(
resources / 'francais.pdf',
outpdf,
'--plugin',
'tests/plugins/tesseract_noop.py',
env=spoof_pdfa_warning,
)
tests/test_image_input.py
+10 -4
View File
@@ -33,9 +33,14 @@ def baiona(resources):
return Image.open(resources / 'baiona_gray.png')
def test_image_to_pdf(spoof_tesseract_noop, resources, outpdf):
def test_image_to_pdf(resources, outpdf):
check_ocrmypdf(
resources / 'crom.png', outpdf, '--image-dpi', '200', env=spoof_tesseract_noop
resources / 'crom.png',
outpdf,
'--image-dpi',
'200',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
@@ -77,7 +82,7 @@ def test_img2pdf_fails(resources, no_outpdf):
assert rc == ocrmypdf.ExitCode.input_file
def test_jpeg_in_jpeg_out(resources, outpdf, spoof_tesseract_noop):
def test_jpeg_in_jpeg_out(resources, outpdf):
check_ocrmypdf(
resources / 'congress.jpg',
outpdf,
@@ -86,7 +91,8 @@ def test_jpeg_in_jpeg_out(resources, outpdf, spoof_tesseract_noop):
'--output-type',
'pdf', # specifically check pdf because Ghostscript may convert to JPEG
'--remove-background',
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
with pikepdf.open(outpdf) as pdf:
assert next(pdf.pages[0].images.values()).Filter == pikepdf.Name.DCTDecode
tests/test_main.py
+85 -46
View File
@@ -111,7 +111,7 @@ def test_redo_ocr(resources, outpdf):
), "Expected text to be different after re-OCR"
def test_argsfile(spoof_tesseract_noop, resources, outdir):
def test_argsfile(resources, outdir):
path_argsfile = outdir / 'test_argsfile.txt'
with open(str(path_argsfile), 'w') as argsfile:
print(
@@ -119,15 +119,14 @@ def test_argsfile(spoof_tesseract_noop, resources, outdir):
'ArgsFile Test',
'--author',
'Test Cases',
'--plugin',
'tests/plugins/tesseract_noop.py',
sep='\n',
end='\n',
file=argsfile,
)
check_ocrmypdf(
resources / 'graph.pdf',
path_argsfile,
'@' + str(outdir / 'test_argsfile.txt'),
env=spoof_tesseract_noop,
resources / 'graph.pdf', path_argsfile, '@' + str(outdir / 'test_argsfile.txt')
)
@@ -239,23 +238,27 @@ def test_klingon(resources, outpdf):
assert p.returncode == ExitCode.missing_dependency
def test_missing_docinfo(spoof_tesseract_noop, resources, outpdf):
def test_missing_docinfo(resources, outpdf):
result = run_ocrmypdf_api(
resources / 'missing_docinfo.pdf',
outpdf,
'-l',
'eng',
'--skip-text',
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert result == ExitCode.ok
def test_uppercase_extension(spoof_tesseract_noop, resources, outdir):
def test_uppercase_extension(resources, outdir):
shutil.copy(str(resources / "skew.pdf"), str(outdir / "UPPERCASE.PDF"))
check_ocrmypdf(
outdir / "UPPERCASE.PDF", outdir / "UPPERCASE_OUT.PDF", env=spoof_tesseract_noop
outdir / "UPPERCASE.PDF",
outdir / "UPPERCASE_OUT.PDF",
'--plugin',
'tests/plugins/tesseract_noop.py',
)
@@ -349,9 +352,12 @@ def test_tesseract_image_too_big(
)
def test_algo4(resources, spoof_tesseract_noop, outpdf):
def test_algo4(resources, outpdf):
p, _, _ = run_ocrmypdf(
resources / 'encrypted_algo4.pdf', outpdf, env=spoof_tesseract_noop
resources / 'encrypted_algo4.pdf',
outpdf,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert p.returncode == ExitCode.encrypted_pdf
@@ -370,17 +376,19 @@ def test_jbig2_passthrough(spoof_tesseract_cache, resources, outpdf):
assert out_pageinfo[0].images[0].enc == Encoding.jbig2
def test_masks(spoof_tesseract_noop, resources, outpdf):
def test_masks(resources, outpdf):
assert (
ocrmypdf.ocr(
resources / 'masks.pdf', outpdf, tesseract_env=spoof_tesseract_noop
resources / 'masks.pdf', outpdf, plugins=['tests/plugins/tesseract_noop.py']
)
== ExitCode.ok
)
def test_linearized_pdf_and_indirect_object(spoof_tesseract_noop, resources, outpdf):
check_ocrmypdf(resources / 'epson.pdf', outpdf, env=spoof_tesseract_noop)
def test_linearized_pdf_and_indirect_object(resources, outpdf):
check_ocrmypdf(
resources / 'epson.pdf', outpdf, '--plugin', 'tests/plugins/tesseract_noop.py'
)
def test_very_high_dpi(spoof_tesseract_cache, resources, outpdf):
@@ -393,20 +401,27 @@ def test_very_high_dpi(spoof_tesseract_cache, resources, outpdf):
assert isclose(image.dpi.x, 2400)
def test_overlay(spoof_tesseract_noop, resources, outpdf):
def test_overlay(resources, outpdf):
check_ocrmypdf(
resources / 'overlay.pdf', outpdf, '--skip-text', env=spoof_tesseract_noop
resources / 'overlay.pdf',
outpdf,
'--skip-text',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
def test_destination_not_writable(spoof_tesseract_noop, resources, outdir):
def test_destination_not_writable(resources, outdir):
if os.name != 'nt' and (os.getuid() == 0 or os.geteuid() == 0):
pytest.xfail(reason="root can write to anything")
protected_file = outdir / 'protected.pdf'
protected_file.touch()
protected_file.chmod(0o400) # Read-only
p, _out, _err = run_ocrmypdf(
resources / 'jbig2.pdf', protected_file, env=spoof_tesseract_noop
resources / 'jbig2.pdf',
protected_file,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert p.returncode == ExitCode.file_access_error, "Expected error"
@@ -479,9 +494,13 @@ def test_user_words_ocr(resources, outdir):
)
def test_form_xobject(spoof_tesseract_noop, resources, outpdf):
def test_form_xobject(resources, outpdf):
check_ocrmypdf(
resources / 'formxobject.pdf', outpdf, '--force-ocr', env=spoof_tesseract_noop
resources / 'formxobject.pdf',
outpdf,
'--force-ocr',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
@@ -513,14 +532,15 @@ def test_pagesize_consistency(renderer, resources, outpdf):
assert isclose(before_dims[1], after_dims[1], rel_tol=1e-4)
def test_skip_big_with_no_images(spoof_tesseract_noop, resources, outpdf):
def test_skip_big_with_no_images(resources, outpdf):
check_ocrmypdf(
resources / 'blank.pdf',
outpdf,
'--skip-big',
'5',
'--force-ocr',
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
@@ -528,18 +548,20 @@ def test_skip_big_with_no_images(spoof_tesseract_noop, resources, outpdf):
'8.0.0' <= pikepdf.__libqpdf_version__ <= '8.0.1',
reason="libqpdf regression on pages with no contents",
)
def test_no_contents(spoof_tesseract_noop, resources, outpdf):
def test_no_contents(resources, outpdf):
check_ocrmypdf(
resources / 'no_contents.pdf', outpdf, '--force-ocr', env=spoof_tesseract_noop
resources / 'no_contents.pdf',
outpdf,
'--force-ocr',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
@pytest.mark.parametrize(
'image', ['baiona.png', 'baiona_gray.png', 'baiona_alpha.png', 'congress.jpg']
)
def test_compression_preserved(
spoof_tesseract_noop, ocrmypdf_exec, resources, image, outpdf
):
def test_compression_preserved(ocrmypdf_exec, resources, image, outpdf):
input_file = str(resources / image)
output_file = str(outpdf)
@@ -553,6 +575,8 @@ def test_compression_preserved(
'150',
'--output-type',
'pdf',
'--plugin',
'tests/plugins/tesseract_noop.py',
'-',
output_file,
]
@@ -562,7 +586,6 @@ def test_compression_preserved(
stderr=PIPE,
stdin=input_stream,
universal_newlines=True,
env=spoof_tesseract_noop,
check=False,
)
@@ -596,9 +619,7 @@ def test_compression_preserved(
('congress.jpg', 'lossless'),
],
)
def test_compression_changed(
spoof_tesseract_noop, ocrmypdf_exec, resources, image, compression, outpdf
):
def test_compression_changed(ocrmypdf_exec, resources, image, compression, outpdf):
input_file = str(resources / image)
output_file = str(outpdf)
@@ -615,6 +636,8 @@ def test_compression_changed(
'0',
'--pdfa-image-compression',
compression,
'--plugin',
'tests/plugins/tesseract_noop.py',
'-',
output_file,
]
@@ -624,7 +647,6 @@ def test_compression_changed(
stderr=PIPE,
stdin=input_stream,
universal_newlines=True,
env=spoof_tesseract_noop,
check=False,
)
assert p.returncode == ExitCode.ok, p.stderr
@@ -717,35 +739,52 @@ def test_decompression_bomb(resources, outpdf):
assert p.returncode == 0
def test_text_curves(spoof_tesseract_noop, resources, outpdf):
def test_text_curves(resources, outpdf):
with patch('ocrmypdf._pipeline.VECTOR_PAGE_DPI', 100):
check_ocrmypdf(resources / 'vector.pdf', outpdf, env=spoof_tesseract_noop)
check_ocrmypdf(
resources / 'vector.pdf',
outpdf,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
info = PdfInfo(outpdf)
assert len(info.pages[0].images) == 0, "added images to the vector PDF"
check_ocrmypdf(
resources / 'vector.pdf', outpdf, '--force-ocr', env=spoof_tesseract_noop
resources / 'vector.pdf',
outpdf,
'--force-ocr',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
info = PdfInfo(outpdf)
assert len(info.pages[0].images) != 0, "force did not rasterize"
def test_output_is_dir(spoof_tesseract_noop, resources, outdir):
def test_output_is_dir(resources, outdir):
p, _out, err = run_ocrmypdf(
resources / 'trivial.pdf', outdir, '--force-ocr', env=spoof_tesseract_noop
resources / 'trivial.pdf',
outdir,
'--force-ocr',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert p.returncode == ExitCode.file_access_error
assert 'is not a writable file' in err
@pytest.mark.skipif(os.name == 'nt', reason="symlink needs admin permissions")
def test_output_is_symlink(spoof_tesseract_noop, resources, outdir):
def test_output_is_symlink(resources, outdir):
sym = Path(outdir / 'this_is_a_symlink')
sym.symlink_to(outdir / 'out.pdf')
p, _out, err = run_ocrmypdf(
resources / 'trivial.pdf', sym, '--force-ocr', env=spoof_tesseract_noop
resources / 'trivial.pdf',
sym,
'--force-ocr',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert p.returncode == ExitCode.ok, err
assert (outdir / 'out.pdf').stat().st_size > 0, 'target file not created'
@@ -781,9 +820,7 @@ def test_version_check():
[0.0, 1, 'pdf', True],
],
)
def test_fast_web_view(
spoof_tesseract_noop, resources, outpdf, threshold, optimize, output_type, expected
):
def test_fast_web_view(resources, outpdf, threshold, optimize, output_type, expected):
check_ocrmypdf(
resources / 'trivial.pdf',
outpdf,
@@ -793,18 +830,20 @@ def test_fast_web_view(
optimize,
'--output-type',
output_type,
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
with pikepdf.open(outpdf) as pdf:
assert pdf.is_linearized == expected
def test_image_dpi_not_image(caplog, spoof_tesseract_noop, resources, outpdf):
def test_image_dpi_not_image(caplog, resources, outpdf):
check_ocrmypdf(
resources / 'trivial.pdf',
outpdf,
'--image-dpi',
'100',
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert '--image-dpi is being ignored' in caplog.text
tests/test_metadata.py
+33 -18
View File
@@ -51,7 +51,7 @@ spoof = pytest.helpers.spoof
@pytest.mark.parametrize("output_type", ['pdfa', 'pdf'])
def test_preserve_metadata(spoof_tesseract_noop, output_type, resources, outpdf):
def test_preserve_metadata(output_type, resources, outpdf):
pdf_before = pikepdf.open(resources / 'graph.pdf')
output = check_ocrmypdf(
@@ -59,7 +59,8 @@ def test_preserve_metadata(spoof_tesseract_noop, output_type, resources, outpdf)
outpdf,
'--output-type',
output_type,
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
pdf_after = pikepdf.open(output)
@@ -72,7 +73,7 @@ def test_preserve_metadata(spoof_tesseract_noop, output_type, resources, outpdf)
@pytest.mark.parametrize("output_type", ['pdfa', 'pdf'])
def test_override_metadata(spoof_tesseract_noop, output_type, resources, outpdf):
def test_override_metadata(output_type, resources, outpdf):
input_file = resources / 'c02-22.pdf'
german = 'Du siehst den Wald vor lauter Bäumen nicht.'
chinese = '孔子'
@@ -86,7 +87,8 @@ def test_override_metadata(spoof_tesseract_noop, output_type, resources, outpdf)
chinese,
'--output-type',
output_type,
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert p.returncode == ExitCode.ok, err
@@ -106,7 +108,7 @@ def test_override_metadata(spoof_tesseract_noop, output_type, resources, outpdf)
assert pdfa_info['output'] == output_type
def test_high_unicode(spoof_tesseract_noop, resources, no_outpdf):
def test_high_unicode(resources, no_outpdf):
# Ghostscript doesn't support high Unicode, so neither do we, to be
# safe
@@ -120,7 +122,8 @@ def test_high_unicode(spoof_tesseract_noop, resources, no_outpdf):
high_unicode,
'--output-type',
'pdfa',
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert p.returncode == ExitCode.bad_args, err
@@ -129,9 +132,7 @@ def test_high_unicode(spoof_tesseract_noop, resources, no_outpdf):
@pytest.mark.skipif(not fitz, reason="test uses fitz")
@pytest.mark.parametrize('ocr_option', ['--skip-text', '--force-ocr'])
@pytest.mark.parametrize('output_type', ['pdf', 'pdfa'])
def test_bookmarks_preserved(
spoof_tesseract_noop, output_type, ocr_option, resources, outpdf
):
def test_bookmarks_preserved(output_type, ocr_option, resources, outpdf):
input_file = resources / 'toc.pdf'
before_toc = fitz.Document(str(input_file)).getToC()
@@ -141,7 +142,8 @@ def test_bookmarks_preserved(
ocr_option,
'--output-type',
output_type,
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
after_toc = fitz.Document(str(outpdf)).getToC()
@@ -156,13 +158,16 @@ def seconds_between_dates(date1, date2):
@pytest.mark.parametrize('infile', ['trivial.pdf', 'jbig2.pdf'])
@pytest.mark.parametrize('output_type', ['pdf', 'pdfa'])
def test_creation_date_preserved(
spoof_tesseract_noop, output_type, resources, infile, outpdf
):
def test_creation_date_preserved(output_type, resources, infile, outpdf):
input_file = resources / infile
check_ocrmypdf(
input_file, outpdf, '--output-type', output_type, env=spoof_tesseract_noop
input_file,
outpdf,
'--output-type',
output_type,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
pdf_before = pikepdf.open(input_file)
@@ -185,7 +190,7 @@ def test_creation_date_preserved(
@pytest.mark.parametrize('output_type', ['pdf', 'pdfa'])
def test_xml_metadata_preserved(spoof_tesseract_noop, output_type, resources, outpdf):
def test_xml_metadata_preserved(output_type, resources, outpdf):
input_file = resources / 'graph.pdf'
try:
@@ -196,7 +201,12 @@ def test_xml_metadata_preserved(spoof_tesseract_noop, output_type, resources, ou
before = file_to_dict(str(input_file))
check_ocrmypdf(
input_file, outpdf, '--output-type', output_type, env=spoof_tesseract_noop
input_file,
outpdf,
'--output-type',
output_type,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
after = file_to_dict(str(outpdf))
@@ -274,9 +284,14 @@ def test_srgb_in_unicode_path(tmp_path):
generate_pdfa_ps(dstdir / 'out.ps')
def test_kodak_toc(resources, outpdf, spoof_tesseract_noop):
def test_kodak_toc(resources, outpdf):
_output = check_ocrmypdf(
resources / 'kcs.pdf', outpdf, '--output-type', 'pdf', env=spoof_tesseract_noop
resources / 'kcs.pdf',
outpdf,
'--output-type',
'pdf',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
p = pikepdf.open(outpdf)
tests/test_optimize.py
+10 -6
View File
@@ -54,7 +54,7 @@ def test_mono_not_inverted(resources, outdir):
@pytest.mark.skipif(not pngquant.available(), reason='need pngquant')
def test_jpg_png_params(resources, outpdf, spoof_tesseract_noop):
def test_jpg_png_params(resources, outpdf):
check_ocrmypdf(
resources / 'crom.png',
outpdf,
@@ -66,13 +66,14 @@ def test_jpg_png_params(resources, outpdf, spoof_tesseract_noop):
'50',
'--png-quality',
'20',
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
@pytest.mark.skipif(not jbig2enc.available(), reason='need jbig2enc')
@pytest.mark.parametrize('lossy', [False, True])
def test_jbig2_lossy(lossy, resources, outpdf, spoof_tesseract_noop):
def test_jbig2_lossy(lossy, resources, outpdf):
args = [
resources / 'ccitt.pdf',
outpdf,
@@ -84,11 +85,13 @@ def test_jbig2_lossy(lossy, resources, outpdf, spoof_tesseract_noop):
'50',
'--png-quality',
'20',
'--plugin',
'tests/plugins/tesseract_noop.py',
]
if lossy:
args.append('--jbig2-lossy')
check_ocrmypdf(*args, env=spoof_tesseract_noop)
check_ocrmypdf(*args)
pdf = pikepdf.open(outpdf)
pim = pikepdf.PdfImage(next(iter(pdf.pages[0].images.values())))
@@ -104,7 +107,7 @@ def test_jbig2_lossy(lossy, resources, outpdf, spoof_tesseract_noop):
not jbig2enc.available() or not pngquant.available(),
reason='need jbig2enc and pngquant',
)
def test_flate_to_jbig2(resources, outdir, spoof_tesseract_noop):
def test_flate_to_jbig2(resources, outdir):
# This test requires an image that pngquant is capable of converting to
# to 1bpp - so use an existing 1bpp image, convert up, confirm it can
# convert down
@@ -122,7 +125,8 @@ def test_flate_to_jbig2(resources, outdir, spoof_tesseract_noop):
'50',
'--optimize',
'3',
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
pdf = pikepdf.open(outdir / 'out.pdf')
tests/test_preprocessing.py
+9 -7
View File
@@ -15,7 +15,6 @@
# You should have received a copy of the GNU General Public License
# along with OCRmyPDF. If not, see <http://www.gnu.org/licenses/>.
import logging
from math import isclose
import pytest
@@ -38,16 +37,18 @@ spoof = pytest.helpers.spoof
RENDERERS = ['hocr', 'sandwich']
def test_deskew(spoof_tesseract_noop, resources, outdir):
def test_deskew(resources, outdir):
# Run with deskew
deskewed_pdf = check_ocrmypdf(
resources / 'skew.pdf', outdir / 'skew.pdf', '-d', env=spoof_tesseract_noop
resources / 'skew.pdf',
outdir / 'skew.pdf',
'-d',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
# Now render as an image again and use Leptonica to find the skew angle
# to confirm that it was deskewed
log = logging.getLogger()
deskewed_png = outdir / 'deskewed.png'
ghostscript.rasterize_pdf(
@@ -65,7 +66,7 @@ def test_deskew(spoof_tesseract_noop, resources, outdir):
assert -0.5 < skew_angle < 0.5, "Deskewing failed"
def test_remove_background(spoof_tesseract_noop, resources, outdir):
def test_remove_background(resources, outdir):
# Ensure the input image does not contain pure white/black
with Image.open(resources / 'congress.jpg') as im:
assert im.getextrema() != ((0, 255), (0, 255), (0, 255))
@@ -76,7 +77,8 @@ def test_remove_background(spoof_tesseract_noop, resources, outdir):
'--remove-background',
'--image-dpi',
'150',
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
output_png = outdir / 'remove_bg.png'
tests/test_stdio.py
+31 -25
View File
@@ -38,25 +38,24 @@ 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):
def test_stdin(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,
)
p_args = ocrmypdf_exec + [
'-',
output_file,
'--plugin',
'tests/plugins/tesseract_noop.py',
]
p = run(p_args, stdout=PIPE, stderr=PIPE, stdin=input_stream)
assert p.returncode == ExitCode.ok
def test_stdout(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
if 'COV_CORE_DATAFILE' in spoof_tesseract_noop:
def test_stdout(ocrmypdf_exec, resources, outpdf):
if 'COV_CORE_DATAFILE' in os.environ:
pytest.skip(msg="Coverage uses stdout")
input_file = str(resources / 'francais.pdf')
@@ -64,14 +63,13 @@ def test_stdout(spoof_tesseract_noop, ocrmypdf_exec, resources, 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,
)
p_args = ocrmypdf_exec + [
input_file,
'-',
'--plugin',
'tests/plugins/tesseract_noop.py',
]
p = run(p_args, stdout=output_stream, stderr=PIPE, stdin=DEVNULL)
assert p.returncode == ExitCode.ok
assert check_pdf(output_file)
@@ -81,7 +79,7 @@ def test_stdout(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
sys.version_info[0:3] >= (3, 6, 4), reason="issue fixed in Python 3.6.4"
)
@pytest.mark.skipif(os.name == 'nt', reason="POSIX problem")
def test_closed_streams(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
def test_closed_streams(ocrmypdf_exec, resources, outpdf):
input_file = str(resources / 'francais.pdf')
output_file = str(outpdf)
@@ -89,14 +87,18 @@ def test_closed_streams(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
os.close(0)
os.close(1)
p_args = ocrmypdf_exec + [input_file, output_file]
p_args = ocrmypdf_exec + [
input_file,
output_file,
'--plugin',
'tests/plugins/tesseract_noop.py',
]
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()
@@ -123,12 +125,16 @@ def test_bad_locale():
os.name == 'nt' and sys.version_info < (3, 8),
reason="Windows does not like this; not sure how to fix",
)
def test_dev_null(spoof_tesseract_noop, resources):
if 'COV_CORE_DATAFILE' in spoof_tesseract_noop:
def test_dev_null(resources):
if 'COV_CORE_DATAFILE' in os.environ:
pytest.skip(msg="Coverage uses stdout")
p, out, err = run_ocrmypdf(
resources / 'trivial.pdf', os.devnull, '--force-ocr', env=spoof_tesseract_noop
resources / 'trivial.pdf',
os.devnull,
'--force-ocr',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert p.returncode == 0, "could not send output to /dev/null"
assert len(out) == 0, "wrote to stdout"
tests/test_unpaper.py
+17 -8
View File
@@ -60,45 +60,54 @@ def test_old_unpaper(spoof_unpaper_oldversion, resources, no_outpdf):
@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
def test_clean(spoof_tesseract_noop, resources, outpdf):
check_ocrmypdf(resources / "skew.pdf", outpdf, "-c", env=spoof_tesseract_noop)
def test_clean(resources, outpdf):
check_ocrmypdf(
resources / "skew.pdf",
outpdf,
"-c",
'--plugin',
'tests/plugins/tesseract_noop.py',
)
@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
def test_unpaper_args_valid(spoof_tesseract_noop, resources, outpdf):
def test_unpaper_args_valid(resources, outpdf):
check_ocrmypdf(
resources / "skew.pdf",
outpdf,
"-c",
"--unpaper-args",
"--layout double", # Spaces required here
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
def test_unpaper_args_invalid_filename(spoof_tesseract_noop, resources, outpdf):
def test_unpaper_args_invalid_filename(resources, outpdf):
p, out, err = run_ocrmypdf(
resources / "skew.pdf",
outpdf,
"-c",
"--unpaper-args",
"/etc/passwd",
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert "No filenames allowed" in err
assert p.returncode == ExitCode.bad_args
@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
def test_unpaper_args_invalid(spoof_tesseract_noop, resources, outpdf):
def test_unpaper_args_invalid(resources, outpdf):
p, out, err = run_ocrmypdf(
resources / "skew.pdf",
outpdf,
"-c",
"--unpaper-args",
"unpaper is not going to like these arguments",
env=spoof_tesseract_noop,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
# Can't tell difference between unpaper choking on bad arguments or some
# other unpaper failure