def test_ImageDictionary():
im = pdf_write.ImageDictionary(width=1024,
height=768,
colour_space=pdf_write.ColourSpaceRGB(),
bits=8)
im.add_filtered_data("FlateDecode", b"1234", {"Predictor": 5})
im.add_dictionary_entry("matt", 7)
obj = im.object()
dic = obj.data
assert set(bytes(x) for x in dic) == {
b"/Subtype", b"/Filter", b"/Width", b"/Height", b"/ColorSpace",
b"/BitsPerComponent", b"/Length", b"/Interpolate", b"/DecodeParms",
b"/matt"
}
assert dic[pdf.PDFName("Subtype")] == pdf.PDFName("Image")
assert dic[pdf.PDFName("Filter")] == pdf.PDFName("FlateDecode")
assert dic[pdf.PDFName("Width")] == pdf.PDFNumeric(1024)
assert dic[pdf.PDFName("Height")] == pdf.PDFNumeric(768)
assert dic[pdf.PDFName("ColorSpace")] == pdf.PDFName("DeviceRGB")
assert dic[pdf.PDFName("BitsPerComponent")] == pdf.PDFNumeric(8)
assert dic[pdf.PDFName("Length")] == pdf.PDFNumeric(4)
assert dic[pdf.PDFName("Interpolate")] == pdf.PDFBoolean(True)
assert dic[pdf.PDFName("matt")] == pdf.PDFNumeric(7)
assert bytes(dic[pdf.PDFName("DecodeParms")]) == b"<</Predictor 5>>"
assert obj.data.stream_contents == b"1234"
def test_NumericParser():
p = pdf_parser.NumericParser()
assert p.parse(b"Bob") is None
assert p.parse(b"1521/T asa") == (pdf.PDFNumeric(1521), 4)
assert p.parse(b"-.002/T asa") == (pdf.PDFNumeric(-0.002), 5)
with pytest.raises(pdf_parser.ParseError):
p.parse(b"+121.261.1622 ahsga")
with pytest.raises(pdf_parser.ParseError):
p.parse(b"1521a")
def test_PDFSimpleDict():
d = pdf.PDFSimpleDict()
d["Filter"] = "FlateDecode"
d["BitsPerComponent"] = 8
d["Interpolate"] = True
d["matt"] = 1.23
dd = d.to_dict()
assert dd[pdf.PDFName("Filter")] == pdf.PDFName("FlateDecode")
assert dd[pdf.PDFName("BitsPerComponent")] == pdf.PDFNumeric(8)
assert dd[pdf.PDFName("Interpolate")] == pdf.PDFBoolean(True)
assert dd[pdf.PDFName("matt")] == pdf.PDFNumeric(1.23)
def test_PDFStream():
x = pdf.PDFStream([(pdf.PDFName("Length"), pdf.PDFNumeric(10))],
b"abcdfgiqsp")
assert x.stream_contents == b"abcdfgiqsp"
assert repr(
x
) == "PDFDictionary({PDFName(b'Length'): PDFNumeric(10)}, stream length=10)"
assert bytes(x) == b"<</Length 10>>\nstream\nabcdfgiqsp\nendstream"
y = pdf.PDFStream([(pdf.PDFName("Length"), pdf.PDFNumeric(10))],
b"abcdfgiqsp")
assert x == y
def test_PDFArray():
x = pdf.PDFArray()
with pytest.raises(IndexError):
x[0]
assert repr(x) == "PDFArray([])"
assert bytes(x) == b"[]"
assert x == pdf.PDFArray()
x = pdf.PDFArray([pdf.PDFName("Matt"), pdf.PDFNumeric(12.2)])
assert repr(x) == "PDFArray([PDFName(b'Matt'), PDFNumeric(12.2)])"
assert bytes(x) == b"[/Matt 12.2]"
assert x == pdf.PDFArray([pdf.PDFName("Matt"), pdf.PDFNumeric(12.2)])
def test_PDFDictionary():
x = pdf.PDFDictionary()
with pytest.raises(KeyError):
x[pdf.PDFName("Mat")]
assert repr(x) == "PDFDictionary({})"
assert bytes(x) == b"<<>>"
x = pdf.PDFDictionary([(pdf.PDFName("Bob"), pdf.PDFNumeric(12))])
assert x[pdf.PDFName("Bob")] == pdf.PDFNumeric(12)
assert repr(x) == "PDFDictionary({PDFName(b'Bob'): PDFNumeric(12)})"
assert bytes(x) == b"<</Bob 12>>"
x[pdf.PDFName("Bob")] = pdf.PDFNumeric(1)
assert bytes(x) == b"<</Bob 1>>"
def test_PDFWriter(test_output_dir):
pw = pdf_write.PDFWriter()
font = pdf.PDFSimpleDict()
font["Type"] = "Font"
font["Subtype"] = "Type1"
font["Name"] = "F1"
font["BaseFont"] = "Helvetica"
font["Encoding"] = "MaxRomanEncoding"
font = pw.add_pdf_object(font.to_dict())
resources = pdf.PDFSimpleDict()
proc_set = pw.add_pdf_object(pdf_write.ProcedureSet().object())
resources["ProcSet"] = proc_set
resources["Font"] = pdf.PDFDictionary([(pdf.PDFName("F1"), font)])
resources = resources.to_dict()
data = b"BT\n/F1 24 Tf\n100 100 Td\n(Hello World) Tj\nET"
contents = pdf.PDFStream(
[(pdf.PDFName("Length"), pdf.PDFNumeric(len(data)))], data)
contents = pw.add_pdf_object(contents)
page = pdf_write.Page(pdf_write.Rectangle(0, 0, 612, 792), resources,
contents)
pw.add_page(page)
with open(os.path.join(test_output_dir, "text.pdf"), "wb") as f:
f.write(bytes(pw))
def test_PDFObject():
obj = pdf.PDFObject(pdf.PDFNumeric(12.3), 1, 5)
assert obj.number == 1
assert obj.generation == 5
assert obj.data == pdf.PDFNumeric(12.3)
assert repr(obj) == "PDFObject(1, 5)"
assert bytes(obj) == b"1 5 R"
obj = pdf.PDFObject(None, None, 5)
with pytest.raises(ValueError):
bytes(obj)
obj.number = 1
assert bytes(obj) == b"1 5 R"
obj = pdf.PDFObject(None, 1, None)
with pytest.raises(ValueError):
bytes(obj)
obj.generation = 5
assert bytes(obj) == b"1 5 R"
def test_read_full_object(pdf1):
p = pdf_read.PDF(pdf1)
loc = p.object_lookup[pdf_read.PDFObjectId(5, 0)]
obj = p.full_object_at(loc)
assert repr(obj) == "PDFNumeric(33)"
loc = p.object_lookup[pdf_read.PDFObjectId(4, 0)]
obj = p.full_object_at(loc)
assert obj[pdf.PDFName("Length")] == pdf.PDFNumeric(33)
assert obj.stream_contents.startswith(b"q\n1637")
def test_PageTree(page1):
pt = pdf_write.PageTree()
pt.add_page(page1)
pt_obj = pt.object()
dic = pt_obj.data
assert set(bytes(x) for x in dic) == {b"/Type", b"/Kids", b"/Count"}
assert dic[pdf.PDFName("Type")] == pdf.PDFName("Pages")
assert dic[pdf.PDFName("Kids")][0].number == None
assert dic[pdf.PDFName("Count")] == pdf.PDFNumeric(1)
assert page1.parent is pt_obj
page1.object().number = 5
assert dic[pdf.PDFName("Kids")][0].number == 5
def test_PDFParser_1():
f = io.BytesIO(
b"\n<</Linearized 1/L 10171355/O 1489/E 14578/N 480/T 10169091/H [ 470 1215]>>\n"
)
p = pdf_parser.PDFParser(f)
got = list(p)
assert len(got) == 1
got = got[0]
assert got[pdf.PDFName("Linearized")] == pdf.PDFNumeric(1)
assert got[pdf.PDFName("L")] == pdf.PDFNumeric(10171355)
assert got[pdf.PDFName("O")] == pdf.PDFNumeric(1489)
assert got[pdf.PDFName("E")] == pdf.PDFNumeric(14578)
assert got[pdf.PDFName("N")] == pdf.PDFNumeric(480)
assert got[pdf.PDFName("T")] == pdf.PDFNumeric(10169091)
assert got[pdf.PDFName("H")] == pdf.PDFArray(
[pdf.PDFNumeric(470), pdf.PDFNumeric(1215)])
keys = []
for x in got:
assert isinstance(x, pdf.PDFName)
keys.append(x.name)
assert set(keys) == {b"Linearized", b"L", b"O", b"E", b"N", b"T", b"H"}
def page1():
mediabox = pdf_write.Rectangle(0, 1, 20, 50)
resources = pdf.PDFDictionary([(pdf.PDFName("Matt"), pdf.PDFNumeric(7))])
contents = pdf.PDFObjectId(3, 2)
return pdf_write.Page(mediabox, resources, contents)
def test_Rectangle():
rect = pdf_write.Rectangle(5, 7, 50, 70)
assert rect() == pdf.PDFArray([pdf.PDFNumeric(x) for x in [5, 7, 50, 70]])
rect = pdf_write.Rectangle(xmin=5, ymin=7, xmax=50, ymax=70)
assert rect() == pdf.PDFArray([pdf.PDFNumeric(x) for x in [5, 7, 50, 70]])
def test_trailer(pdf1):
p = pdf_read.PDF(pdf1)
assert p.trailer[pdf.PDFName("Size")] == pdf.PDFNumeric(18)
assert pdf.PDFName("Info") in p.trailer
assert pdf.PDFName("Root") in p.trailer
def test_PDFNumeric():
x = pdf.PDFNumeric(5)
assert x.value == 5
assert int(x) == 5
assert float(x) == 5.0
assert repr(x) == "PDFNumeric(5)"
assert bytes(x) == b"5"
assert x == pdf.PDFNumeric("5")
x = pdf.PDFNumeric(5.2)
assert x.value == pytest.approx(5.2)
assert int(x) == 5
assert float(x) == pytest.approx(5.2)
assert repr(x) == "PDFNumeric(5.2)"
assert bytes(x) == b"5.2"
assert x == pdf.PDFNumeric("5.2")
x = pdf.PDFNumeric("+7")
assert x.value == 7
assert isinstance(x.value, int)
x = pdf.PDFNumeric("-7")
assert x.value == -7
assert isinstance(x.value, int)
x = pdf.PDFNumeric("+7.523")
assert x.value == pytest.approx(7.523)
assert x == pdf.PDFNumeric(7.523)
with pytest.raises(ValueError):
pdf.PDFNumeric("a6sa")
assert len({pdf.PDFNumeric(12), pdf.PDFNumeric(12)}) == 1