def test_convert_to_square_resolution(renderer, spoof_tesseract_cache,
resources, outpdf):
from math import isclose
# Confirm input image is non-square resolution
in_pageinfo = pdf_get_all_pageinfo(str(resources / 'aspect.pdf'))
assert in_pageinfo[0]['xres'] != in_pageinfo[0]['yres']
# --force-ocr requires means forced conversion to square resolution
check_ocrmypdf(resources / 'aspect.pdf',
outpdf,
'--force-ocr',
'--pdf-renderer',
renderer,
env=spoof_tesseract_cache)
out_pageinfo = pdf_get_all_pageinfo(str(outpdf))
in_p0, out_p0 = in_pageinfo[0], out_pageinfo[0]
# Resolution show now be equal
assert out_p0['xres'] == out_p0['yres']
# Page size should match input page size
assert isclose(in_p0['width_inches'], out_p0['width_inches'])
assert isclose(in_p0['height_inches'], out_p0['height_inches'])
# Because we rasterized the page to produce a new image, it should occupy
# the entire page
out_im_w = out_p0['images'][0]['width'] / out_p0['images'][0]['dpi_w']
out_im_h = out_p0['images'][0]['height'] / out_p0['images'][0]['dpi_h']
assert isclose(out_p0['width_inches'], out_im_w)
assert isclose(out_p0['height_inches'], out_im_h)
def test_rotated_skew_timeout():
"""This document contains an image that is rotated 90 into place with a
/Rotate tag and intentionally skewed by altering the transformation matrix.
This tests for a bug where the combinatino of preprocessing and a tesseract
timeout produced a page whose dimensions did not match the original's.
"""
input_file = _infile('rotated_skew.pdf')
in_pageinfo = pdf_get_all_pageinfo(input_file)[0]
assert in_pageinfo['height_pixels'] < in_pageinfo['width_pixels'], \
"Expected the input page to be landscape"
assert in_pageinfo['rotate'] == 90, "Expected a rotated page"
out = check_ocrmypdf(
'rotated_skew.pdf', 'test_rotated_skew.pdf',
'--pdf-renderer', 'hocr',
'--deskew', '--tesseract-timeout', '0')
out_pageinfo = pdf_get_all_pageinfo(out)[0]
assert out_pageinfo['height_pixels'] > out_pageinfo['width_pixels'], \
"Expected the output page to be portrait"
assert out_pageinfo['rotate'] == 0, \
"Expected no page rotation for output"
assert in_pageinfo['width_pixels'] == out_pageinfo['height_pixels'] and \
in_pageinfo['height_pixels'] == out_pageinfo['width_pixels'], \
"Expected page rotation to be baked in"
def test_rotated_skew_timeout(resources, outpdf):
"""This document contains an image that is rotated 90 into place with a
/Rotate tag and intentionally skewed by altering the transformation matrix.
This tests for a bug where the combinatino of preprocessing and a tesseract
timeout produced a page whose dimensions did not match the original's.
"""
input_file = str(resources / 'rotated_skew.pdf')
in_pageinfo = pdf_get_all_pageinfo(input_file)[0]
assert in_pageinfo['height_pixels'] < in_pageinfo['width_pixels'], \
"Expected the input page to be landscape"
assert in_pageinfo['rotate'] == 90, "Expected a rotated page"
out = check_ocrmypdf(input_file, outpdf, '--pdf-renderer', 'hocr',
'--deskew', '--tesseract-timeout', '0')
out_pageinfo = pdf_get_all_pageinfo(str(out))[0]
assert out_pageinfo['height_pixels'] > out_pageinfo['width_pixels'], \
"Expected the output page to be portrait"
assert out_pageinfo['rotate'] == 0, \
"Expected no page rotation for output"
assert in_pageinfo['width_pixels'] == out_pageinfo['height_pixels'] and \
in_pageinfo['height_pixels'] == out_pageinfo['width_pixels'], \
"Expected page rotation to be baked in"
def test_non_square_resolution(renderer, spoof_tesseract_cache):
# Confirm input image is non-square resolution
in_pageinfo = pdf_get_all_pageinfo(_infile('aspect.pdf'))
assert in_pageinfo[0]['xres'] != in_pageinfo[0]['yres']
out = 'aspect_%s.pdf' % renderer
check_ocrmypdf(
'aspect.pdf', out,
'--pdf-renderer', renderer, env=spoof_tesseract_cache)
out_pageinfo = pdf_get_all_pageinfo(_outfile(out))
# Confirm resolution was kept the same
assert in_pageinfo[0]['xres'] == out_pageinfo[0]['xres']
assert in_pageinfo[0]['yres'] == out_pageinfo[0]['yres']
def test_non_square_resolution(renderer, spoof_tesseract_cache):
# Confirm input image is non-square resolution
in_pageinfo = pdf_get_all_pageinfo(_infile('aspect.pdf'))
assert in_pageinfo[0]['xres'] != in_pageinfo[0]['yres']
out = 'aspect_%s.pdf' % renderer
check_ocrmypdf(
'aspect.pdf', out,
'--pdf-renderer', renderer, env=spoof_tesseract_cache)
out_pageinfo = pdf_get_all_pageinfo(_outfile(out))
# Confirm resolution was kept the same
assert in_pageinfo[0]['xres'] == out_pageinfo[0]['xres']
assert in_pageinfo[0]['yres'] == out_pageinfo[0]['yres']
def test_single_page_inline_image():
filename = os.path.join(TEST_OUTPUT, 'image-mono-inline.pdf')
pdf = Canvas(filename, pagesize=(8 * 72, 6 * 72))
with NamedTemporaryFile() as im_tmp:
im = Image.new('1', (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(im_tmp.name, format='PNG')
# Draw image in a 72x72 pt or 1"x1" area
pdf.drawInlineImage(im_tmp.name, 0, 0, width=72, height=72)
pdf.showPage()
pdf.save()
with pytest.raises(NotImplementedError):
pageinfo.pdf_get_all_pageinfo(filename)
def test_non_square_resolution(renderer, spoof_tesseract_cache,
resources, outpdf):
# Confirm input image is non-square resolution
in_pageinfo = pdf_get_all_pageinfo(str(resources / 'aspect.pdf'))
assert in_pageinfo[0]['xres'] != in_pageinfo[0]['yres']
check_ocrmypdf(
resources / 'aspect.pdf', outpdf,
'--pdf-renderer', renderer, env=spoof_tesseract_cache)
out_pageinfo = pdf_get_all_pageinfo(str(outpdf))
# Confirm resolution was kept the same
assert in_pageinfo[0]['xres'] == out_pageinfo[0]['xres']
assert in_pageinfo[0]['yres'] == out_pageinfo[0]['yres']
def test_single_page_inline_image():
filename = os.path.join(TEST_OUTPUT, "image-mono-inline.pdf")
pdf = Canvas(filename, pagesize=(8 * 72, 6 * 72))
with NamedTemporaryFile() as im_tmp:
im = Image.new("1", (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(im_tmp.name, format="PNG")
# Draw image in a 72x72 pt or 1"x1" area
pdf.drawInlineImage(im_tmp.name, 0, 0, width=72, height=72)
pdf.showPage()
pdf.save()
with pytest.raises(NotImplementedError):
pageinfo.pdf_get_all_pageinfo(filename)
def test_single_page_image():
filename = os.path.join(TEST_OUTPUT, 'image-mono.pdf')
pdf = Canvas(filename, pagesize=(72, 72))
with NamedTemporaryFile() as im_tmp:
im = Image.new('1', (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(im_tmp.name, format='PNG')
# Draw image in a 72x72 pt or 1"x1" area
pdf.drawImage(im_tmp.name, 0, 0, width=72, height=72)
pdf.showPage()
pdf.save()
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
assert len(pdfinfo) == 1
page = pdfinfo[0]
assert not page['has_text']
assert len(page['images']) == 1
pdfimage = page['images'][0]
assert pdfimage['width'] == 8
# assert pdfimage['color'] == 'gray'
# While unexpected, this is correct
# PDF spec says /FlateDecode image must have /BitsPerComponent 8
# So mono images get upgraded to 8-bit
assert pdfimage['bpc'] == 8
# DPI in a 1"x1" is the image width
assert pdfimage['dpi_w'] == 8
assert pdfimage['dpi_h'] == 8
def test_force_ocr(spoof_tesseract_cache):
out = check_ocrmypdf('graph_ocred.pdf',
'test_force.pdf',
'-f',
env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(out)
assert pdfinfo[0]['has_text']
def test_single_page_image():
filename = os.path.join(TEST_OUTPUT, 'image-mono.pdf')
with NamedTemporaryFile() as im_tmp:
im = Image.new('1', (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(im_tmp.name, format='PNG')
pdf_bytes = img2pdf.convert([im_tmp.name], dpi=8)
with open(filename, 'wb') as pdf:
pdf.write(pdf_bytes)
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
assert len(pdfinfo) == 1
page = pdfinfo[0]
assert not page['has_text']
assert len(page['images']) == 1
pdfimage = page['images'][0]
assert pdfimage['width'] == 8
assert pdfimage['color'] == 'gray'
# While unexpected, this is correct
# PDF spec says /FlateDecode image must have /BitsPerComponent 8
# So mono images get upgraded to 8-bit
assert pdfimage['bpc'] == 8
# DPI in a 1"x1" is the image width
assert pdfimage['dpi_w'] == 8
assert pdfimage['dpi_h'] == 8
def test_single_page_image():
filename = os.path.join(TEST_OUTPUT, 'image-mono.pdf')
with NamedTemporaryFile() as im_tmp:
im = Image.new('1', (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(im_tmp.name, format='PNG')
pdf_bytes = img2pdf.convert([im_tmp.name], dpi=8)
with open(filename, 'wb') as pdf:
pdf.write(pdf_bytes)
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
assert len(pdfinfo) == 1
page = pdfinfo[0]
assert not page['has_text']
assert len(page['images']) == 1
pdfimage = page['images'][0]
assert pdfimage['width'] == 8
assert pdfimage['color'] == 'gray'
# While unexpected, this is correct
# PDF spec says /FlateDecode image must have /BitsPerComponent 8
# So mono images get upgraded to 8-bit
assert pdfimage['bpc'] == 8
# DPI in a 1"x1" is the image width
assert pdfimage['dpi_w'] == 8
assert pdfimage['dpi_h'] == 8
def test_jpeg():
filename = resource_filename(req, 'tests/resources/c02-22.pdf')
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
pdfimage = pdfinfo[0]['images'][0]
assert pdfimage['enc'] == 'jpeg'
def test_jpeg():
filename = resource_filename(req, "tests/resources/c02-22.pdf")
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
pdfimage = pdfinfo[0]["images"][0]
assert pdfimage["enc"] == "jpeg"
def test_single_page_image():
filename = os.path.join(TEST_OUTPUT, "image-mono.pdf")
with NamedTemporaryFile() as im_tmp:
im = Image.new("1", (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(im_tmp.name, format="PNG")
pdf_bytes = img2pdf.convert([im_tmp.name], dpi=8)
with open(filename, "wb") as pdf:
pdf.write(pdf_bytes)
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
assert len(pdfinfo) == 1
page = pdfinfo[0]
assert not page["has_text"]
assert len(page["images"]) == 1
pdfimage = page["images"][0]
assert pdfimage["width"] == 8
assert pdfimage["color"] == "gray"
# While unexpected, this is correct
# PDF spec says /FlateDecode image must have /BitsPerComponent 8
# So mono images get upgraded to 8-bit
assert pdfimage["bpc"] == 8
# DPI in a 1"x1" is the image width
assert pdfimage["dpi_w"] == 8
assert pdfimage["dpi_h"] == 8
def test_jpeg():
filename = resource_filename(req, 'tests/resources/c02-22.pdf')
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
pdfimage = pdfinfo[0]['images'][0]
assert pdfimage['enc'] == 'jpeg'
def test_jpeg():
filename = _make_input('c02-22.pdf')
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
pdfimage = pdfinfo[0]['images'][0]
assert pdfimage['enc'] == 'jpeg'
def test_force_ocr(spoof_tesseract_cache, resources, outpdf):
out = check_ocrmypdf(resources / 'graph_ocred.pdf',
outpdf,
'-f',
env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(out)
assert pdfinfo[0]['has_text']
def test_single_page_image(outdir):
filename = outdir / 'image-mono.pdf'
im_tmp = outdir / 'tmp.png'
im = Image.new('1', (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(str(im_tmp), format='PNG')
imgsize = ((img2pdf.ImgSize.dpi, 8), (img2pdf.ImgSize.dpi, 8))
layout_fun = img2pdf.get_layout_fun(None, imgsize, None, None, None)
im_bytes = im_tmp.read_bytes()
pdf_bytes = img2pdf.convert(im_bytes,
producer="img2pdf",
with_pdfrw=False,
layout_fun=layout_fun)
filename.write_bytes(pdf_bytes)
pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
assert len(pdfinfo) == 1
page = pdfinfo[0]
assert not page['has_text']
assert len(page['images']) == 1
pdfimage = page['images'][0]
assert pdfimage['width'] == 8
assert pdfimage['color'] == 'gray'
# DPI in a 1"x1" is the image width
assert abs(pdfimage['dpi_w'] - 8) < 1e-5
assert abs(pdfimage['dpi_h'] - 8) < 1e-5
def test_skip_big(spoof_tesseract_cache):
out = check_ocrmypdf('enormous.pdf',
'test_enormous.pdf',
'--skip-big',
'10',
env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(out)
assert not pdfinfo[0]['has_text']
def test_jpeg(resources, outdir):
filename = resources / 'c02-22.pdf'
pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
pdfimage = pdfinfo[0]['images'][0]
assert pdfimage['enc'] == 'jpeg'
assert (pdfimage['dpi_w'] - 150) < 1e-5
def test_skip_big(spoof_tesseract_cache, resources, outpdf):
out = check_ocrmypdf(resources / 'enormous.pdf',
outpdf,
'--skip-big',
'10',
env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(str(out))
assert not pdfinfo[0]['has_text']
def test_jpeg():
filename = _make_input('c02-22.pdf')
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
pdfimage = pdfinfo[0]['images'][0]
assert pdfimage['enc'] == 'jpeg'
assert (pdfimage['dpi_w'] - 150) < 1e-5
def test_jbig2_passthrough(spoof_tesseract_cache, resources, outpdf):
out = check_ocrmypdf(
resources / 'jbig2.pdf', outpdf,
'--output-type', 'pdf',
'--pdf-renderer', 'hocr',
env=spoof_tesseract_cache)
out_pageinfo = pdf_get_all_pageinfo(str(out))
assert out_pageinfo[0]['images'][0]['enc'] == 'jbig2'
def check_oversample(renderer):
oversampled_pdf = check_ocrmypdf(
'skew.pdf', 'test_oversample_%s.pdf' % renderer, '--oversample', '300',
'--pdf-renderer', renderer)
pdfinfo = pdf_get_all_pageinfo(oversampled_pdf)
print(pdfinfo[0]['xres'])
assert abs(pdfinfo[0]['xres'] - 300) < 1
def test_jbig2_passthrough(spoof_tesseract_cache):
out = check_ocrmypdf(
'jbig2.pdf', 'jbig2_out.pdf',
'--output-type', 'pdf',
'--pdf-renderer', 'hocr',
env=spoof_tesseract_cache)
out_pageinfo = pdf_get_all_pageinfo(out)
assert out_pageinfo[0]['images'][0]['enc'] == 'jbig2'
def test_jbig2_passthrough(spoof_tesseract_cache):
out = check_ocrmypdf(
'jbig2.pdf', 'jbig2_out.pdf',
'--output-type', 'pdf',
'--pdf-renderer', 'hocr',
env=spoof_tesseract_cache)
out_pageinfo = pdf_get_all_pageinfo(out)
assert out_pageinfo[0]['images'][0]['enc'] == 'jbig2'
def test_oversample(spoof_tesseract_cache, renderer):
oversampled_pdf = check_ocrmypdf(
'skew.pdf', 'test_oversample_%s.pdf' % renderer, '--oversample', '350',
'-f',
'--pdf-renderer', renderer, env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(oversampled_pdf)
print(pdfinfo[0]['xres'])
assert abs(pdfinfo[0]['xres'] - 350) < 1
def test_oversample(spoof_tesseract_cache, renderer):
oversampled_pdf = check_ocrmypdf(
'skew.pdf', 'test_oversample_%s.pdf' % renderer, '--oversample', '350',
'-f',
'--pdf-renderer', renderer, env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(oversampled_pdf)
print(pdfinfo[0]['xres'])
assert abs(pdfinfo[0]['xres'] - 350) < 1
def test_oversample(spoof_tesseract_cache, renderer, resources, outpdf):
oversampled_pdf = check_ocrmypdf(
resources / 'skew.pdf', outpdf, '--oversample', '350',
'-f',
'--pdf-renderer', renderer, env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(str(oversampled_pdf))
print(pdfinfo[0]['xres'])
assert abs(pdfinfo[0]['xres'] - 350) < 1
def check_oversample(renderer):
oversampled_pdf = check_ocrmypdf('skew.pdf',
'test_oversample_%s.pdf' % renderer,
'--oversample', '300', '--pdf-renderer',
renderer)
pdfinfo = pdf_get_all_pageinfo(oversampled_pdf)
print(pdfinfo[0]['xres'])
assert abs(pdfinfo[0]['xres'] - 300) < 1
def test_very_high_dpi(spoof_tesseract_cache, resources, outpdf):
"Checks for a Decimal quantize error with high DPI, etc"
check_ocrmypdf(resources / '2400dpi.pdf',
outpdf,
env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(outpdf)
image = pdfinfo[0]['images'][0]
assert image['dpi_w'] == image['dpi_h']
assert image['dpi_w'] == 2400
def test_skip_pages_does_not_replicate(
ensure_tess4, resources, basename, outdir):
infile = resources / basename
outpdf = outdir / basename
check_ocrmypdf(
infile,
outpdf, '--pdf-renderer', 'tess4', '--force-ocr',
'--tesseract-timeout', '0',
env=ensure_tess4
)
info_in = pageinfo.pdf_get_all_pageinfo(str(infile))
info = pageinfo.pdf_get_all_pageinfo(str(outpdf))
for page in info:
assert len(page['images']) == 1, "skipped page was replicated"
for n in range(len(info_in)):
assert info[n]['width_inches'] == info_in[n]['width_inches']
def test_content_preservation(ensure_tess4, resources, outpdf):
infile = resources / 'masks.pdf'
check_ocrmypdf(
infile,
outpdf, '--pdf-renderer', 'tess4', '--tesseract-timeout', '0',
env=ensure_tess4
)
info = pageinfo.pdf_get_all_pageinfo(str(outpdf))
page = info[0]
assert len(page['images']) > 1, "masked were rasterized"
def test_single_page_text():
filename = os.path.join(TEST_OUTPUT, "text.pdf")
pdf = Canvas(filename, pagesize=(8 * 72, 6 * 72))
text = pdf.beginText()
text.setFont("Helvetica", 12)
text.setTextOrigin(1 * 72, 3 * 72)
text.textLine("Methink'st thou art a general offence and every" " man should beat thee.")
pdf.drawText(text)
pdf.showPage()
pdf.save()
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
assert len(pdfinfo) == 1
page = pdfinfo[0]
assert page["has_text"]
assert len(page["images"]) == 0
def test_single_page_inline_image():
filename = os.path.join(TEST_OUTPUT, 'image-mono-inline.pdf')
pdf = Canvas(filename, pagesize=(8*72, 6*72))
with NamedTemporaryFile() as im_tmp:
im = Image.new('1', (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(im_tmp.name, format='PNG')
# Draw image in a 72x72 pt or 1"x1" area
pdf.drawInlineImage(im_tmp.name, 0, 0, width=72, height=72)
pdf.showPage()
pdf.save()
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
print(pdfinfo)
pdfimage = pdfinfo[0]['images'][0]
assert (pdfimage['dpi_w'] - 8) < 1e-5
assert pdfimage['color'] != '-'
assert pdfimage['width'] == 8
def test_sidecar_pagecount(spoof_tesseract_cache, resources, outpdf):
sidecar = outpdf + '.txt'
check_ocrmypdf(resources / 'multipage.pdf',
outpdf,
'--skip-text',
'--sidecar',
sidecar,
env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(str(resources / 'multipage.pdf'))
num_pages = len(pdfinfo)
with open(sidecar, 'r') as f:
ocr_text = f.read()
# There should a formfeed between each pair of pages, so the count of
# formfeeds is the page count less one
assert ocr_text.count('\f') == num_pages - 1, \
"Sidecar page count does not match PDF page count"
def test_single_page_inline_image(outdir):
filename = outdir / 'image-mono-inline.pdf'
pdf = Canvas(str(filename), pagesize=(8 * 72, 6 * 72))
with NamedTemporaryFile() as im_tmp:
im = Image.new('1', (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(im_tmp.name, format='PNG')
# Draw image in a 72x72 pt or 1"x1" area
pdf.drawInlineImage(im_tmp.name, 0, 0, width=72, height=72)
pdf.showPage()
pdf.save()
pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
print(pdfinfo)
pdfimage = pdfinfo[0]['images'][0]
assert (pdfimage['dpi_w'] - 8) < 1e-5
assert pdfimage['color'] != '-'
assert pdfimage['width'] == 8
def test_single_page_text(outdir):
filename = outdir / 'text.pdf'
pdf = Canvas(str(filename), pagesize=(8 * 72, 6 * 72))
text = pdf.beginText()
text.setFont('Helvetica', 12)
text.setTextOrigin(1 * 72, 3 * 72)
text.textLine("Methink'st thou art a general offence and every"
" man should beat thee.")
pdf.drawText(text)
pdf.showPage()
pdf.save()
pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
assert len(pdfinfo) == 1
page = pdfinfo[0]
assert page['has_text']
assert len(page['images']) == 0
def test_single_page_image():
filename = os.path.join(TEST_OUTPUT, 'image-mono.pdf')
with NamedTemporaryFile(mode='wb+', suffix='.png') as im_tmp:
im = Image.new('1', (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(im_tmp.name, format='PNG')
imgsize = ((img2pdf.ImgSize.dpi, 8), (img2pdf.ImgSize.dpi, 8))
layout_fun = img2pdf.get_layout_fun(None, imgsize, None, None, None)
im_tmp.seek(0)
im_bytes = im_tmp.read()
pdf_bytes = img2pdf.convert(im_bytes,
producer="img2pdf",
with_pdfrw=False,
layout_fun=layout_fun)
with open(filename, 'wb') as pdf:
pdf.write(pdf_bytes)
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
assert len(pdfinfo) == 1
page = pdfinfo[0]
assert not page['has_text']
assert len(page['images']) == 1
pdfimage = page['images'][0]
assert pdfimage['width'] == 8
assert pdfimage['color'] == 'gray'
# While unexpected, this is correct
# PDF spec says /FlateDecode image must have /BitsPerComponent 8
# So mono images get upgraded to 8-bit
assert pdfimage['bpc'] == 8
# DPI in a 1"x1" is the image width
assert abs(pdfimage['dpi_w'] - 8) < 1e-5
assert abs(pdfimage['dpi_h'] - 8) < 1e-5
def test_single_page_image():
filename = os.path.join(TEST_OUTPUT, 'image-mono.pdf')
with NamedTemporaryFile(mode='wb+', suffix='.png') as im_tmp:
im = Image.new('1', (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
im.save(im_tmp.name, format='PNG')
imgsize = ((img2pdf.ImgSize.dpi, 8), (img2pdf.ImgSize.dpi, 8))
layout_fun = img2pdf.get_layout_fun(None, imgsize, None, None, None)
im_tmp.seek(0)
im_bytes = im_tmp.read()
pdf_bytes = img2pdf.convert(
im_bytes, producer="img2pdf", with_pdfrw=False,
layout_fun=layout_fun)
with open(filename, 'wb') as pdf:
pdf.write(pdf_bytes)
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
assert len(pdfinfo) == 1
page = pdfinfo[0]
assert not page['has_text']
assert len(page['images']) == 1
pdfimage = page['images'][0]
assert pdfimage['width'] == 8
assert pdfimage['color'] == 'gray'
# While unexpected, this is correct
# PDF spec says /FlateDecode image must have /BitsPerComponent 8
# So mono images get upgraded to 8-bit
assert pdfimage['bpc'] == 8
# DPI in a 1"x1" is the image width
assert pdfimage['dpi_w'] == 8
assert pdfimage['dpi_h'] == 8
def test_compression_preserved(spoof_tesseract_noop, ocrmypdf_exec, resources,
image, outpdf):
from PIL import Image
input_file = str(resources / image)
output_file = str(outpdf)
im = Image.open(input_file)
# Runs: ocrmypdf - output.pdf < testfile
with open(input_file, 'rb') as input_stream:
p_args = ocrmypdf_exec + [
'--image-dpi', '150', '--output-type', 'pdf', '-', output_file
]
p = Popen(p_args,
close_fds=True,
stdout=PIPE,
stderr=PIPE,
stdin=input_stream,
env=spoof_tesseract_noop)
out, err = p.communicate()
assert p.returncode == ExitCode.ok
pdfinfo = pdf_get_all_pageinfo(output_file)
pdfimage = pdfinfo[0]['images'][0]
if input_file.endswith('.png'):
assert pdfimage['enc'] != 'jpeg', \
"Lossless compression changed to lossy!"
elif input_file.endswith('.jpg'):
assert pdfimage['enc'] == 'jpeg', \
"Lossy compression changed to lossless!"
if im.mode.startswith('RGB') or im.mode.startswith('BGR'):
assert pdfimage['color'] == 'rgb', \
"Colorspace changed"
elif im.mode.startswith('L'):
assert pdfimage['color'] == 'gray', \
"Colorspace changed"
def first_page_dimensions(pdf):
from ocrmypdf import pageinfo
info = pageinfo.pdf_get_all_pageinfo(str(pdf))
page0 = info[0]
return (page0['width_inches'], page0['height_inches'])
def test_skip_big(spoof_tesseract_cache):
out = check_ocrmypdf('enormous.pdf', 'test_enormous.pdf',
'--skip-big', '10', env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(out)
assert not pdfinfo[0]['has_text']
def test_ocr_timeout(renderer):
out = check_ocrmypdf('skew.pdf', 'test_timeout_%s.pdf' % renderer,
'--tesseract-timeout', '1.0')
pdfinfo = pdf_get_all_pageinfo(out)
assert not pdfinfo[0]['has_text']
def test_force_ocr(spoof_tesseract_cache):
out = check_ocrmypdf('graph_ocred.pdf', 'test_force.pdf', '-f',
env=spoof_tesseract_cache)
pdfinfo = pdf_get_all_pageinfo(out)
assert pdfinfo[0]['has_text']
def test_force_ocr():
out = check_ocrmypdf('graph_ocred.pdf', 'test_force.pdf', '-f')
pdfinfo = pdf_get_all_pageinfo(out)
assert pdfinfo[0]['has_text']
def test_skip_big():
out = check_ocrmypdf('enormous.pdf', 'test_enormous.pdf',
'--skip-big', '10')
pdfinfo = pdf_get_all_pageinfo(out)
assert pdfinfo[0]['has_text'] == False
def test_form_xobject(resources):
filename = resources / 'formxobject.pdf'
pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
pdfimage = pdfinfo[0]['images'][0]
assert pdfimage['width'] == 50
def test_no_contents(resources):
filename = resources / 'no_contents.pdf'
pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
assert len(pdfinfo[0]['images']) == 0
assert pdfinfo[0]['has_text'] == False
