def test_xref_stream_parse_width_value_default_ix2():
# no tail part
encoded_entries = [
"0000000000",
"0100000011",
]
xref_data = b''.join(binascii.unhexlify(entr) for entr in encoded_entries)
stream_obj = generic.StreamObject(
dict_data={
generic.pdf_name('/W'): generic.ArrayObject(list(
map(generic.NumberObject, [1, 4, 0])
)),
generic.pdf_name('/Size'): 2
},
stream_data=xref_data
)
expected_out = [
XRefEntry(
xref_type=XRefType.FREE, location=None, idnum=0, generation=0
),
XRefEntry(xref_type=XRefType.STANDARD, location=0x11, idnum=1),
]
actual_out = list(parse_xref_stream(stream_obj))
assert actual_out == expected_out
def test_xref_stream_parse_entry_types():
encoded_entries = [
"0000000000ffff", # free
"01000000110000", # regular objects
"01000000840000",
"01000000bc0005",
"01000001b40000",
"01000002990000",
"02000000030001", # object in stream
"03deadbeef1337", # undefined (should be ignored)
"02000000030002", # object in stream
"ffcafebabe0007", # another undefined one
]
xref_data = b''.join(binascii.unhexlify(entr) for entr in encoded_entries)
stream_obj = generic.StreamObject(
dict_data={
generic.pdf_name('/W'): generic.ArrayObject(list(
map(generic.NumberObject, [1, 4, 2])
)),
generic.pdf_name('/Size'): 10
},
stream_data=xref_data
)
expected_out = [
XRefEntry(
xref_type=XRefType.FREE, location=None, idnum=0, generation=0xffff
),
XRefEntry(xref_type=XRefType.STANDARD, location=0x11, idnum=1),
XRefEntry(xref_type=XRefType.STANDARD, location=0x84, idnum=2),
XRefEntry(
xref_type=XRefType.STANDARD, location=0xbc, idnum=3, generation=5
),
XRefEntry(xref_type=XRefType.STANDARD, location=0x1b4, idnum=4),
XRefEntry(xref_type=XRefType.STANDARD, location=0x299, idnum=5),
XRefEntry(
xref_type=XRefType.IN_OBJ_STREAM,
location=ObjStreamRef(3, 1), idnum=6
),
XRefEntry(
xref_type=XRefType.IN_OBJ_STREAM,
location=ObjStreamRef(3, 2),
idnum=8 # idnum jump because of undefined entry
),
]
actual_out = list(parse_xref_stream(stream_obj))
assert actual_out == expected_out
def test_premature_xref_stream_end():
encoded_entries = ["000000ffff", "0100110000"]
xref_data = b''.join(binascii.unhexlify(entr) for entr in encoded_entries)
stream_obj = generic.StreamObject(
dict_data={
generic.pdf_name('/W'): generic.ArrayObject(list(
map(generic.NumberObject, [1, 2, 2])
)),
generic.pdf_name('/Size'): 3 # one too many
},
stream_data=xref_data
)
with pytest.raises(misc.PdfReadError, match='incomplete entry'):
list(parse_xref_stream(stream_obj))
def test_xref_stream_trailing_data():
encoded_entries = [
"0000000000ffff", # free
"01000000110000",
"deadbeef"
]
xref_data = b''.join(binascii.unhexlify(entr) for entr in encoded_entries)
stream_obj = generic.StreamObject(
dict_data={
generic.pdf_name('/W'): generic.ArrayObject(list(
map(generic.NumberObject, [1, 4, 2])
)),
generic.pdf_name('/Size'): 2
},
stream_data=xref_data
)
with pytest.raises(misc.PdfReadError, match='Trailing'):
list(parse_xref_stream(stream_obj))