def test_skip_pages_does_not_replicate(resources, basename, outdir):
infile = resources / basename
outpdf = outdir / basename
check_ocrmypdf(
infile,
outpdf,
'--pdf-renderer',
'sandwich',
'--force-ocr',
'--tesseract-timeout',
'0',
)
info_in = pdfinfo.PdfInfo(infile)
info = pdfinfo.PdfInfo(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_pages_issue700(monkeypatch, resources):
def get_no_pages(*args, **kwargs):
return iter([])
monkeypatch.setattr(PDFPage, 'get_pages', get_no_pages)
with pytest.raises(InputFileError, match="pdfminer"):
pdfinfo.PdfInfo(
resources / 'cardinal.pdf',
detailed_analysis=True,
progbar=False,
max_workers=1,
)
def test_content_preservation(ensure_tess4, resources, outpdf):
infile = resources / 'masks.pdf'
check_ocrmypdf(infile,
outpdf,
'--pdf-renderer',
'sandwich',
'--tesseract-timeout',
'0',
env=ensure_tess4)
info = pdfinfo.PdfInfo(outpdf)
page = info[0]
assert len(page.images) > 1, "masks were rasterized"
def test_single_page_inline_image(eight_by_eight, outdir):
filename = outdir / 'image-mono-inline.pdf'
pdf = Canvas(str(filename), pagesize=(8 * 72, 6 * 72))
# Draw image in a 72x72 pt or 1"x1" area
pdf.drawInlineImage(eight_by_eight, 0, 0, width=72, height=72)
pdf.showPage()
pdf.save()
info = pdfinfo.PdfInfo(filename)
print(info)
pdfimage = info[0].images[0]
assert isclose(pdfimage.dpi.x, 8)
assert pdfimage.color == Colorspace.gray
assert pdfimage.width == 8
def test_image_scale0(resources, outpdf):
with pikepdf.open(resources / 'cmyk.pdf') as cmyk:
xobj = pikepdf.Page(cmyk.pages[0]).as_form_xobject()
p = pikepdf.Pdf.new()
p.add_blank_page(page_size=(72, 72))
objname = pikepdf.Page(p.pages[0]).add_resource(
p.copy_foreign(xobj), pikepdf.Name.XObject, pikepdf.Name.Im0)
print(objname)
p.pages[0].Contents = pikepdf.Stream(
p, b"q 0 0 0 0 0 0 cm %s Do Q" % bytes(objname))
p.save(outpdf)
pi = pdfinfo.PdfInfo(outpdf,
detailed_analysis=True,
progbar=False,
max_workers=1)
assert not pi.pages[0]._images[0].dpi.is_finite
assert pi.pages[0].dpi == Resolution(0, 0)
def test_single_page_inline_image(outdir):
filename = outdir / 'image-mono-inline.pdf'
pdf = Canvas(str(filename), pagesize=(8 * 72, 6 * 72))
im = Image.new('1', (8, 8), 0)
for n in range(8):
im.putpixel((n, n), 1)
# Draw image in a 72x72 pt or 1"x1" area
pdf.drawInlineImage(im, 0, 0, width=72, height=72)
pdf.showPage()
pdf.save()
info = pdfinfo.PdfInfo(filename)
print(info)
pdfimage = info[0].images[0]
assert isclose(pdfimage.dpi.x, 8)
assert pdfimage.color == Colorspace.gray
assert pdfimage.width == 8
def test_dpi_needed(image, text, vector, result, rgb_image, outdir):
c = Canvas(str(outdir / 'dpi.pdf'), pagesize=(5 * inch, 5 * inch))
if image:
c.drawImage(rgb_image, 1 * inch, 1 * inch, width=1 * inch, height=1 * inch)
if text:
c.drawString(1 * inch, 4 * inch, "Actual text")
if vector:
c.ellipse(3 * inch, 3 * inch, 4 * inch, 4 * inch)
c.showPage()
c.save()
mock = Mock()
mock.oversample = DUMMY_OVERSAMPLE_RESOLUTION[0]
pi = pdfinfo.PdfInfo(outdir / 'dpi.pdf')
assert _pipeline.get_canvas_square_dpi(pi[0], mock) == result
assert _pipeline.get_page_square_dpi(pi[0], mock) == result
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()
info = pdfinfo.PdfInfo(filename)
assert len(info) == 1
page = info[0]
assert page.has_text
assert len(page.images) == 0
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()
pdf = pdfinfo.PdfInfo(filename)
print(pdf)
pdfimage = pdf[0].images[0]
assert isclose(pdfimage.xres, 8)
assert pdfimage.color == Colorspace.rgb # reportlab produces color image
assert pdfimage.width == 8
def first_page_dimensions(pdf):
from ocrmypdf import pdfinfo
info = pdfinfo.PdfInfo(pdf)
page0 = info[0]
return (page0.width_inches, page0.height_inches)
def test_vector(resources):
filename = resources / 'vector.pdf'
pdf = pdfinfo.PdfInfo(filename)
assert pdf[0].has_vector
assert not pdf[0].has_text
def test_ocr_detection(resources):
filename = resources / 'graph_ocred.pdf'
pdf = pdfinfo.PdfInfo(filename)
assert not pdf[0].has_vector
assert pdf[0].has_text
def test_oversized_page(resources):
pdf = pdfinfo.PdfInfo(resources / 'poster.pdf')
image = pdf[0].images[0]
assert image.width * image.xres > 200, "this is supposed to be oversized"
def test_no_contents(resources):
filename = resources / 'no_contents.pdf'
pdf = pdfinfo.PdfInfo(filename)
assert len(pdf[0].images) == 0
assert pdf[0].has_text == False
def test_form_xobject(resources):
filename = resources / 'formxobject.pdf'
pdf = pdfinfo.PdfInfo(filename)
pdfimage = pdf[0].images[0]
assert pdfimage.width == 50
def first_page_dimensions(pdf):
info = pdfinfo.PdfInfo(pdf)
page0 = info[0]
return (page0.width_inches, page0.height_inches)
def test_corrupt_font_detection(resources, testfile):
filename = resources / testfile
pdf = pdfinfo.PdfInfo(filename, detailed_analysis=True)
assert pdf[0].has_corrupt_text
