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_ParseName():
p = pdf_parser.ParseName()
assert p.parse(b"asa") is None
assert p.parse(b"/Matt asa") == (pdf.PDFName("Matt"), 5)
assert p.parse(b"/Matt") == (pdf.PDFName("Matt"), 5)
assert p.parse(b"/Matt#20 asa") == (pdf.PDFName("Matt "), 8)
assert p.parse(b"/Matt/Bob") == (pdf.PDFName("Matt"), 5)
def test_DocumentCatalog():
pages = pdf.PDFObjectId(5, 2)
root = pdf_write.DocumentCatalog(pages)
dic = root.object().data
assert set(bytes(x) for x in dic) == {b"/Type", b"/Pages"}
assert dic[pdf.PDFName("Type")] == pdf.PDFName("Catalog")
assert bytes(dic[pdf.PDFName("Pages")]) == b"5 2 R"
def test_ArrayConsumer():
p = pdf_parser.ParseArray()
c = p.consumer()
assert isinstance(c, pdf_parser.ArrayConsumer)
c.consume(pdf.PDFName("Matt"))
assert c.end(b"123.2") is None
assert c.end(b"]ahsgas") == 1
assert c.build() == pdf.PDFArray([pdf.PDFName("Matt")])
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_DictionaryConsumer():
p = pdf_parser.ParseDictionary()
c = p.consumer()
assert isinstance(c, pdf_parser.DictionaryConsumer)
assert c.end(b"ajsdga") is None
assert c.end(b">>ahsga") == 2
c.consume(pdf.PDFName("Mat"))
c.consume(pdf.PDFObjectId(12, 0))
d = c.build()
assert bytes(d[pdf.PDFName("Mat")]) == b"12 0 R"
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_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_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_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_PDFName():
x = pdf.PDFName(b"Bob")
assert x.name == b"Bob"
assert repr(x) == "PDFName(b'Bob')"
assert x == pdf.PDFName(b"Bob")
assert x == pdf.PDFName("Bob")
assert bytes(x) == b"/Bob"
with pytest.raises(ValueError):
x = pdf.PDFName("ahdga\x00")
bytes(x)
x = pdf.PDFName(b"Bob\n T\xee")
assert bytes(x) == b"/Bob#0A#20T#EE"
assert len({pdf.PDFName("Masa"), pdf.PDFName("Masa")})
def test_Page(page1):
page = page1
page.parent = pdf.PDFObjectId(2, 5)
dic = page.object().data
assert set(bytes(x) for x in dic) == {
b"/Type", b"/Parent", b"/Resources", b"/MediaBox", b"/Contents"
}
assert dic[pdf.PDFName("Type")] == pdf.PDFName("Page")
assert bytes(dic[pdf.PDFName("Parent")]) == b"2 5 R"
assert bytes(dic[pdf.PDFName("Resources")]) == b"<</Matt 7>>"
assert bytes(dic[pdf.PDFName("MediaBox")]) == b"[0 1 20 50]"
assert bytes(dic[pdf.PDFName("Contents")]) == b"3 2 R"
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 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_read_object_1(pdf1):
p = pdf_read.PDF(pdf1)
objs = p.object_at(10)
assert len(objs) == 1
assert objs[0][pdf.PDFName("Pages")] == pdf.PDFObjectId(2, 0)
assert objs[0][pdf.PDFName("Type")] == pdf.PDFName("Catalog")
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_InfoObject():
io = pdf_write.InfoObject("My Title")
dic = io.object().data
assert set(bytes(x) for x in dic) == {b"/Title", b"/CreationDate"}
assert dic[pdf.PDFName("Title")] == pdf.PDFString("My Title")
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)