mirror/OCRmyPDF
1
0
Fork 0
mirror of https://github.com/ocrmypdf/OCRmyPDF.git synced 2026-01-31 17:32:44 -05:00
Code Issues Packages Projects Releases Wiki Activity

Use context managers to ensure Pillow images are closed

Browse Source
This commit is contained in:
James R. Barlow
2019-09-03 17:19:12 -07:00
parent c8d6ea6b10
commit feff1e38bb
8 changed files with 45 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/ocrmypdf/_pipeline.py
View File

@@ -54,9 +54,9 @@ def triage_image_file(input_file, output_file, options, log):
# Recover the original filename
log.error(str(e).replace(input_file, options.input_file))
raise UnsupportedImageFormatError() from e
else:
log.info("Input file is an image")
with im:
log.info("Input file is an image")
if 'dpi' in im.info:
if im.info['dpi'] <= (96, 96) and not options.image_dpi:
log.info("Image size: (%d, %d)" % im.size)
@@ -89,7 +89,6 @@ def triage_image_file(input_file, output_file, options, log):
elif im.mode == 'CMYK':
log.info('Input CMYK image has no ICC profile, not usable')
raise UnsupportedImageFormatError()
im.close()
try:
log.info("Image seems valid. Try converting to PDF...")

3
src/ocrmypdf/exec/pngquant.py
View File

@@ -40,8 +40,7 @@ def available():
def quantize(input_file, output_file, quality_min, quality_max):
if input_file.endswith('.jpg'):
im = Image.open(input_file)
with NamedTemporaryFile(suffix='.png') as tmp:
with Image.open(input_file) as im, NamedTemporaryFile(suffix='.png') as tmp:
im.save(tmp)
args = [
'pngquant',

4
src/ocrmypdf/exec/tesseract.py
View File

@@ -233,8 +233,8 @@ def _generate_null_hocr(output_hocr, output_sidecar, image):
the same size as the input image."""
from PIL import Image
im = Image.open(image)
w, h = im.size
with Image.open(image) as im:
w, h = im.size
with open(output_hocr, 'w', encoding="utf-8") as f:
f.write(HOCR_TEMPLATE.format(w, h))

43
src/ocrmypdf/exec/unpaper.py
View File

@@ -42,33 +42,30 @@ def run(input_file, output_file, dpi, log, mode_args):
SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
im = Image.open(input_file)
if im.mode not in SUFFIXES.keys():
log.info("Converting image to other colorspace")
with TemporaryDirectory() as tmpdir, Image.open(input_file) as im:
if im.mode not in SUFFIXES.keys():
log.info("Converting image to other colorspace")
try:
if im.mode == 'P' and len(im.getcolors()) == 2:
im = im.convert(mode='1')
else:
im = im.convert(mode='RGB')
except IOError as e:
im.close()
raise MissingDependencyError(
"Could not convert image with type " + im.mode
) from e
try:
if im.mode == 'P' and len(im.getcolors()) == 2:
im = im.convert(mode='1')
else:
im = im.convert(mode='RGB')
except IOError as e:
im.close()
suffix = SUFFIXES[im.mode]
except KeyError:
raise MissingDependencyError(
"Could not convert image with type " + im.mode
"Failed to convert image to a supported format."
) from e
try:
suffix = SUFFIXES[im.mode]
except KeyError:
im.close()
raise MissingDependencyError(
"Failed to convert image to a supported format."
) from e
with TemporaryDirectory() as tmpdir:
input_pnm = os.path.join(tmpdir, f'input{suffix}')
output_pnm = os.path.join(tmpdir, f'output{suffix}')
im.save(input_pnm, format='PPM')
im.close()
# To prevent any shenanigans from accepting arbitrary parameters in
# --unpaper-args, we:
@@ -95,10 +92,12 @@ def run(input_file, output_file, dpi, log, mode_args):
log.debug(proc.stdout)
# unpaper sets dpi to 72; fix this
try:
Image.open(output_pnm).save(output_file, dpi=(dpi, dpi))
with Image.open(output_pnm) as imout:
imout.save(output_file, dpi=(dpi, dpi))
except (FileNotFoundError, OSError):
raise SubprocessOutputError(
"unpaper: failed to produce the expected output file. Called with: "
"unpaper: failed to produce the expected output file. "
+ " Called with: "
+ str(args_unpaper)
) from None

3
tests/test_lept.py
View File

@@ -38,7 +38,8 @@ def test_colormap_backgroundnorm(resources):
def crom_pix(resources):
pix = lept.Pix.open(resources / 'crom.png')
im = Image.open(resources / 'crom.png')
return pix, im
yield pix, im
im.close()
def test_pix_basic(crom_pix):

10
tests/test_main.py
View File

@@ -118,8 +118,8 @@ def test_deskew(spoof_tesseract_noop, resources, outdir):
def test_remove_background(spoof_tesseract_noop, resources, outdir):
# Ensure the input image does not contain pure white/black
im = Image.open(resources / 'congress.jpg')
assert im.getextrema() != ((0, 255), (0, 255), (0, 255))
with Image.open(resources / 'congress.jpg') as im:
assert im.getextrema() != ((0, 255), (0, 255), (0, 255))
output_pdf = check_ocrmypdf(
resources / 'congress.jpg',
@@ -145,8 +145,8 @@ def test_remove_background(spoof_tesseract_noop, resources, outdir):
)
# The output image should contain pure white and black
im = Image.open(output_png)
assert im.getextrema() == ((0, 255), (0, 255), (0, 255))
with Image.open(output_png) as im:
assert im.getextrema() == ((0, 255), (0, 255), (0, 255))
# This will run 5 * 2 * 2 = 20 test cases
@@ -792,6 +792,7 @@ def test_compression_preserved(
assert pdfimage.color == Colorspace.rgb, "Colorspace changed"
elif im.mode.startswith('L'):
assert pdfimage.color == Colorspace.gray, "Colorspace changed"
im.close()
@pytest.mark.parametrize(
@@ -853,6 +854,7 @@ def test_compression_changed(
assert pdfimage.color == Colorspace.rgb, "Colorspace changed"
elif im.mode.startswith('L'):
assert pdfimage.color == Colorspace.gray, "Colorspace changed"
im.close()
def test_sidecar_pagecount(spoof_tesseract_cache, resources, outpdf):

12
tests/test_optimize.py
View File

@@ -51,8 +51,8 @@ def test_mono_not_inverted(resources, outdir):
log=logging.getLogger(name='test_mono_not_inverted'),
)
im = Image.open(fspath(outdir / 'im.png'))
assert im.getpixel((0, 0)) == 255, "Expected white background"
with Image.open(fspath(outdir / 'im.png')) as im:
assert im.getpixel((0, 0)) == 255, "Expected white background"
@pytest.mark.skipif(not pngquant.available(), reason='need pngquant')
@@ -110,10 +110,10 @@ def test_flate_to_jbig2(resources, outdir, spoof_tesseract_noop):
# 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
im = Image.open(fspath(resources / 'typewriter.png'))
assert im.mode in ('1', 'P')
im = im.convert('L')
im.save(fspath(outdir / 'type8.png'))
with Image.open(fspath(resources / 'typewriter.png')) as im:
assert im.mode in ('1', 'P')
im = im.convert('L')
im.save(fspath(outdir / 'type8.png'))
check_ocrmypdf(
outdir / 'type8.png',

10
tests/test_rotation.py
View File

@@ -224,12 +224,12 @@ def test_rotate_deskew_timeout(resources, outdir):
@pytest.mark.parametrize('image_angle', (0, 90, 180, 270))
def test_rotate_page_level(image_angle, page_angle, resources, outdir):
def make_rotate_test(prefix, image_angle, page_angle):
im = Image.open(fspath(resources / 'typewriter.png'))
if image_angle != 0:
ccw_angle = -image_angle % 360
im = im.transpose(getattr(Image, f'ROTATE_{ccw_angle}'))
memimg = BytesIO()
im.save(memimg, format='PNG')
with Image.open(fspath(resources / 'typewriter.png')) as im:
if image_angle != 0:
ccw_angle = -image_angle % 360
im = im.transpose(getattr(Image, f'ROTATE_{ccw_angle}'))
im.save(memimg, format='PNG')
memimg.seek(0)
mempdf = BytesIO()
img2pdf.convert(