def test_encryption(name, requres_pycryptodome):
inputfile = os.path.join(RESOURCE_ROOT, "encryption", name)
if requres_pycryptodome and not HAS_PYCRYPTODOME:
with pytest.raises(DependencyError) as exc:
ipdf = PyPDF2.PdfReader(inputfile)
ipdf.decrypt("asdfzxcv")
dd = dict(ipdf.metadata)
assert exc.value.args[
0] == "PyCryptodome is required for AES algorithm"
return
else:
ipdf = PyPDF2.PdfReader(inputfile)
if inputfile.endswith("unencrypted.pdf"):
assert not ipdf.is_encrypted
else:
assert ipdf.is_encrypted
ipdf.decrypt("asdfzxcv")
assert len(ipdf.pages) == 1
dd = dict(ipdf.metadata)
# remove empty value entry
dd = {x[0]: x[1] for x in dd.items() if x[1]}
assert dd == {
"/Author": "cheng",
"/CreationDate": "D:20220414132421+05'24'",
"/Creator": "WPS Writer",
"/ModDate": "D:20220414132421+05'24'",
"/SourceModified": "D:20220414132421+05'24'",
"/Trapped": "/False",
}
def merge():
pdf_path = os.path.join(RESOURCE_ROOT, "crazyones.pdf")
outline = os.path.join(RESOURCE_ROOT, "pdflatex-outline.pdf")
pdf_forms = os.path.join(RESOURCE_ROOT, "pdflatex-forms.pdf")
pdf_pw = os.path.join(RESOURCE_ROOT, "libreoffice-writer-password.pdf")
file_merger = PyPDF2.PdfMerger()
# string path:
file_merger.append(pdf_path)
file_merger.append(outline)
file_merger.append(pdf_path, pages=PyPDF2.pagerange.PageRange(slice(0, 0)))
file_merger.append(pdf_forms)
# Merging an encrypted file
reader = PyPDF2.PdfReader(pdf_pw)
reader.decrypt("openpassword")
file_merger.append(reader)
# PdfReader object:
file_merger.append(PyPDF2.PdfReader(pdf_path, "rb"), bookmark=True)
# File handle
with open(pdf_path, "rb") as fh:
file_merger.append(fh)
bookmark = file_merger.add_bookmark("A bookmark", 0)
file_merger.add_bookmark("deeper", 0, parent=bookmark)
file_merger.add_metadata({"author": "Martin Thoma"})
file_merger.add_named_destination("title", 0)
file_merger.set_page_layout("/SinglePage")
file_merger.set_page_mode("/UseThumbs")
tmp_path = "dont_commit_merged.pdf"
file_merger.write(tmp_path)
file_merger.close()
# Check if bookmarks are correct
reader = PyPDF2.PdfReader(tmp_path)
assert [
el.title for el in reader._get_outlines()
if isinstance(el, Destination)
] == [
"A bookmark",
"Foo",
"Bar",
"Baz",
"Foo",
"Bar",
"Baz",
"Foo",
"Bar",
"Baz",
"True",
]
# Clean up
os.remove(tmp_path)
def test_both_password(name, user_passwd, owner_passwd):
from PyPDF2 import PasswordType
inputfile = os.path.join(RESOURCE_ROOT, "encryption", name)
ipdf = PyPDF2.PdfReader(inputfile)
assert ipdf.is_encrypted
assert ipdf.decrypt(user_passwd) == PasswordType.USER_PASSWORD
assert ipdf.decrypt(owner_passwd) == PasswordType.OWNER_PASSWORD
assert len(ipdf.pages) == 1
def test_get_page_of_encrypted_file_new_algorithm(pdffile, password):
"""
Check if we can read a page of an encrypted file.
This is a regression test for issue 327:
IndexError for get_page() of decrypted file
"""
path = os.path.join(RESOURCE_ROOT, pdffile)
PyPDF2.PdfReader(path, password=password).pages[0]
def test_encryption_merge(names):
pdf_merger = PyPDF2.PdfMerger()
files = [os.path.join(RESOURCE_ROOT, "encryption", x) for x in names]
pdfs = [PyPDF2.PdfReader(x) for x in files]
for pdf in pdfs:
if pdf.is_encrypted:
pdf.decrypt("asdfzxcv")
pdf_merger.append(pdf)
# no need to write to file
pdf_merger.close()
def test_merge():
pdf_path = os.path.join(RESOURCE_ROOT, "crazyones.pdf")
outline = os.path.join(RESOURCE_ROOT, "pdflatex-outline.pdf")
pdf_forms = os.path.join(RESOURCE_ROOT, "pdflatex-forms.pdf")
pdf_pw = os.path.join(RESOURCE_ROOT, "libreoffice-writer-password.pdf")
merger = PyPDF2.PdfMerger()
# string path:
merger.append(pdf_path)
merger.append(outline)
merger.append(pdf_path, pages=PyPDF2.pagerange.PageRange(slice(0, 0)))
merger.append(pdf_forms)
merger.merge(0, pdf_path, import_bookmarks=False)
# Merging an encrypted file
reader = PyPDF2.PdfReader(pdf_pw)
reader.decrypt("openpassword")
merger.append(reader)
# PdfReader object:
merger.append(PyPDF2.PdfReader(pdf_path), bookmark="foo")
# File handle
with open(pdf_path, "rb") as fh:
merger.append(fh)
bookmark = merger.add_bookmark("A bookmark", 0)
bm2 = merger.add_bookmark("deeper",
0,
parent=bookmark,
italic=True,
bold=True)
merger.add_bookmark("Let's see", 2, bm2, (255, 255, 0), True, True,
"/FitBV", 12)
merger.add_bookmark("The XYZ fit", 0, bookmark, (255, 0, 15), True, True,
"/XYZ", 10, 20, 3)
merger.add_bookmark("The FitH fit", 0, bookmark, (255, 0, 15), True, True,
"/FitH", 10)
merger.add_bookmark("The FitV fit", 0, bookmark, (255, 0, 15), True, True,
"/FitV", 10)
merger.add_bookmark("The FitR fit", 0, bookmark, (255, 0, 15), True, True,
"/FitR", 10, 20, 30, 40)
merger.add_bookmark("The FitB fit", 0, bookmark, (255, 0, 15), True, True,
"/FitB")
merger.add_bookmark("The FitBH fit", 0, bookmark, (255, 0, 15), True, True,
"/FitBH", 10)
merger.add_bookmark("The FitBV fit", 0, bookmark, (255, 0, 15), True, True,
"/FitBV", 10)
found_bm = merger.find_bookmark("nothing here")
assert found_bm is None
found_bm = merger.find_bookmark("foo")
assert found_bm == [9]
merger.add_metadata({"author": "Martin Thoma"})
merger.add_named_destination("title", 0)
merger.set_page_layout("/SinglePage")
merger.set_page_mode("/UseThumbs")
tmp_path = "dont_commit_merged.pdf"
merger.write(tmp_path)
merger.close()
# Check if bookmarks are correct
reader = PyPDF2.PdfReader(tmp_path)
assert [
el.title for el in reader._get_outlines()
if isinstance(el, Destination)
] == [
"A bookmark",
"Foo",
"Bar",
"Baz",
"Foo",
"Bar",
"Baz",
"Foo",
"Bar",
"Baz",
"foo",
]
# TODO: There seem to be no destinations for those links?
# Clean up
os.remove(tmp_path)
