def _chop_images(self):
pages_count = len(self._flattened_pages)
for i in range(pages_count):
page = self._flattened_pages[i]
bytes_data: bytes = page[_k.CONTENT].get_data()
parts = _pattern_space.split(bytes_data)
the_image = page[_k.RESOURCES][b'/XObject'][_get_image_name_from(parts)]
_u.debug(parts, len(page[_k.RESOURCES][b'/XObject']), the_image)
image_data = the_image.get_data()
# _u.debug(the_image, len(image_data))
if b'/Subtype' in the_image and the_image[b'/Subtype'] == b'/Image':
(
width, height, compressed_length, compressed_data,
) = _im.chop_off_image_empty_edges(the_image, image_data, i + 1)
the_image[NameObject(b'/Length')] = NumberObject(compressed_length)
the_image[NameObject(b'/Width')] = NumberObject(width)
the_image[NameObject(b'/Height')] = NumberObject(height)
the_image._bytes_data = compressed_data
# We might need to insert this matrix in the below line: 1 0 0 1 0 100 cm
page[_k.CONTENT].set_data(
b'q ' + _u.s2b(str(width)) + b' 0 0 ' + _u.s2b(str(height)) + b' 0 0 cm ' + parts[-5] + b' Do Q'
)
page[_k.MEDIA_BOX][2] = NumberObject(width)
page[_k.MEDIA_BOX][3] = NumberObject(height)
_u.debug(
'Chopped empty edges for {:4}/{} image.'.format(i + 1, pages_count),
page[_k.MEDIA_BOX], page[_k.MEDIA_BOX][2:], parts, width, height,
page[_k.CONTENT].get_data(),
)
else:
_u.debug(image_data)
pass
def _write_cross_reference_table(self, stream, object_positions):
xref_location = stream.tell()
stream.write(b'xref\n')
stream.write(_u.s2b(f'0 {len(self._objects) + 1}\n'))
stream.write(b'0000000000 00000 f \n')
for offset in object_positions:
stream.write(_u.s2b(f'{offset:010d} 00000 n \n'))
_u.debug('Wrote cross reference table.')
return xref_location
def _write_objects_to(self, stream):
_u.debug('Writing objects...')
objects_count = len(self._objects)
object_positions = []
stream.write(b'%PDF-1.3\n')
for i in range(objects_count):
idnum = (i + 1)
obj = self._objects[i]
# _u.debug('idnum: [{:4}]'.format(idnum), '| type:', type(obj).__name__, '| obj:', obj)
# if b'/Type' in obj:
# _u.debug('type:', obj[b'/Type'], '| obj:', obj)
object_positions.append(stream.tell())
stream.write(_u.s2b(f'{idnum} 0 obj\n'))
key = None
if (self._encrypt is not None) and (not (idnum == self._encrypt.idnum)):
pack1 = _s.pack("<i", i + 1)[:3]
pack2 = _s.pack("<i", 0)[:2]
key = _u.encrypt(self._encrypt_key, pack1, pack2)
if is_plain_object(obj):
obj.write_to_stream(stream)
else:
obj.write_to_stream(stream, key)
stream.write(b'\nendobj\n')
_u.debug('Wrote {:4}/{} objects.'.format(i + 1, objects_count))
return object_positions
def write_to_stream(self, stream, encryption_key):
# Try to write the string out as a PDFDocEncoding encoded string. It's
# nicer to look at in the PDF file. Sadly, we take a performance hit
# here for trying...
try:
byte_arr = _u.encode_pdf_doc_encoding(self)
except UnicodeEncodeError:
byte_arr = codecs.BOM_UTF16_BE + self.encode(_u.ENCODING_UTF16BE)
if encryption_key:
byte_arr = _u.rc4_encrypt(encryption_key, byte_arr)
obj = ByteStringObject(byte_arr)
obj.write_to_stream(stream, None)
else:
stream.write(b'(')
for c in byte_arr:
if not c.isalnum() and not c == ' ':
stream.write(_u.s2b("\\%03o" % ord(c)))
else:
stream.write(_u.s2b(c))
stream.write(b')')
def write_to(self, stream):
"""
Writes the collection of pages added to this object out as a PDF file.
Stability: Added in v1.0, will exist for all v1.x releases.
stream - An object to write the file to. The object must support
the write method, and the tell method, similar to a file object.
"""
# _u.debug(self.get_pages_count())
# _u.debug(len(self._objects))
external_reference_map = self._build_external_reference_map()
# _u.debug(len(self._objects))
self._scan_indirect_references(external_reference_map, self._root, [])
# _u.debug(len(self._objects))
# Begin writing:
object_positions = self._write_objects_to(stream)
xref_location = self._write_cross_reference_table(stream, object_positions)
self._write_trailer_to(stream)
stream.write(_u.s2b(f'\nstartxref\n{xref_location}\n%%%%EOF\n'))
def write_to_stream(self, stream):
stream.write(_u.s2b(repr(self)))