def strip_invisible_text(pdf, page):
stream = []
in_text_obj = False
render_mode = 0
text_objects = []
rich_page = Page(page)
rich_page.contents_coalesce()
for operands, operator in parse_content_stream(page, ''):
if not in_text_obj:
if operator == Operator('BT'):
in_text_obj = True
render_mode = 0
text_objects.append((operands, operator))
else:
stream.append((operands, operator))
else:
if operator == Operator('Tr'):
render_mode = operands[0]
text_objects.append((operands, operator))
if operator == Operator('ET'):
in_text_obj = False
if render_mode != 3:
stream.extend(text_objects)
text_objects.clear()
content_stream = unparse_content_stream(stream)
page.Contents = Stream(pdf, content_stream)
def test_externalize(resources):
with Pdf.open(resources / 'image-mono-inline.pdf') as p:
page = Page(p.pages[0])
page.contents_coalesce()
assert b'BI' in page.obj.Contents.read_bytes(), "no inline image"
assert Name.XObject not in page.obj.Resources, "expected no xobjs"
page.externalize_inline_images()
assert Name.XObject in page.obj.Resources, "image not created"
pdfimagexobj = next(iter(p.pages[0].images.values()))
assert pdfimagexobj.Subtype == Name.Image
assert page.label == '1'