josch/img2pdf
3
6
Fork 10
Code Issues 22 Pull requests 5 Projects Releases 3 Wiki Activity

make pep8 compliant

Browse source
This commit is contained in:
Johannes 'josch' Schauer 2018-08-01 22:28:44 +02:00
parent 9395b6fbbe
commit 198c98a5f9
Signed by: josch
GPG key ID: F2CBA5C78FBD83E1
2 changed files with 48 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
src/img2pdf.py
View file

@ -277,7 +277,8 @@ if PY3:
@classmethod @classmethod
def encode(cls, string, hextype=False): def encode(cls, string, hextype=False):
if hextype: if hextype:
return b'< ' + b' '.join(("%06x"%c).encode('ascii') for c in string) + b' >' return b'< ' + b' '.join(
("%06x" % c).encode('ascii') for c in string) + b' >'
else: else:
try: try:
string = string.encode('ascii') string = string.encode('ascii')
@ -292,7 +293,8 @@ else:
@classmethod @classmethod
def encode(cls, string, hextype=False): def encode(cls, string, hextype=False):
if hextype: if hextype:
return b'< ' + b' '.join(("%06x"%c).encode('ascii') for c in string) + b' >' return b'< ' + b' '.join(
("%06x" % c).encode('ascii') for c in string) + b' >'
else: else:
# This mimics exactely to what pdfrw does. # This mimics exactely to what pdfrw does.
string = string.replace(b'\\', b'\\\\') string = string.replace(b'\\', b'\\\\')
@ -393,8 +395,11 @@ class pdfdoc(object):
colorspace = PdfName.DeviceCMYK colorspace = PdfName.DeviceCMYK
elif color == Colorspace.P: elif color == Colorspace.P:
if self.with_pdfrw: if self.with_pdfrw:
raise Exception("pdfrw does not support hex strings for palette image input, re-run with --without-pdfrw") raise Exception("pdfrw does not support hex strings for "
colorspace = [ PdfName.Indexed, PdfName.DeviceRGB, len(palette)-1, PdfString.encode(palette, hextype=True)] "palette image input, re-run with "
"--without-pdfrw")
colorspace = [PdfName.Indexed, PdfName.DeviceRGB, len(palette)-1,
PdfString.encode(palette, hextype=True)]
else: else:
raise UnsupportedColorspaceError("unsupported color space: %s" raise UnsupportedColorspaceError("unsupported color space: %s"
% color.name) % color.name)
@ -453,7 +458,7 @@ class pdfdoc(object):
elif imgformat is ImageFormat.PNG: elif imgformat is ImageFormat.PNG:
decodeparms = PdfDict() decodeparms = PdfDict()
decodeparms[PdfName.Predictor] = 15 decodeparms[PdfName.Predictor] = 15
if color in [ Colorspace.P, Colorspace['1'], Colorspace.L ]: if color in [Colorspace.P, Colorspace['1'], Colorspace.L]:
decodeparms[PdfName.Colors] = 1 decodeparms[PdfName.Colors] = 1
else: else:
decodeparms[PdfName.Colors] = 3 decodeparms[PdfName.Colors] = 3
@ -647,13 +652,14 @@ def get_imgmetadata(imgdata, imgformat, default_dpi, colorspace, rawdata=None):
ics = imgdata.mode ics = imgdata.mode
if ics in ["LA", "PA", "RGBA"]: if ics in ["LA", "PA", "RGBA"]:
logging.warning("Image contains transparency which cannot be retained in PDF.") logging.warning("Image contains transparency which cannot be retained "
"in PDF.")
logging.warning("img2pdf will not perform a lossy operation.") logging.warning("img2pdf will not perform a lossy operation.")
logging.warning("You can remove the alpha channel using imagemagick:") logging.warning("You can remove the alpha channel using imagemagick:")
logging.warning(" $ convert input.png -background white -alpha remove -alpha off output.png") logging.warning(" $ convert input.png -background white -alpha "
"remove -alpha off output.png")
raise Exception("Refusing to work on images with alpha channel") raise Exception("Refusing to work on images with alpha channel")
# Since commit 07a96209597c5e8dfe785c757d7051ce67a980fb or release 4.1.0 # Since commit 07a96209597c5e8dfe785c757d7051ce67a980fb or release 4.1.0
# Pillow retrieves the DPI from EXIF if it cannot find the DPI in the JPEG # Pillow retrieves the DPI from EXIF if it cannot find the DPI in the JPEG
# header. In that case it can happen that the horizontal and vertical DPI # header. In that case it can happen that the horizontal and vertical DPI
@ -694,7 +700,8 @@ def ccitt_payload_location_from_pil(img):
# If Pillow is passed an invalid compression argument it will ignore it; # If Pillow is passed an invalid compression argument it will ignore it;
# make sure the image actually got compressed. # make sure the image actually got compressed.
if img.info['compression'] != 'group4': if img.info['compression'] != 'group4':
raise ValueError("Image not compressed with CCITT Group 4 but with: %s" % img.info['compression']) raise ValueError("Image not compressed with CCITT Group 4 but with: %s"
% img.info['compression'])
# Read the TIFF tags to find the offset(s) of the compressed data strips. # Read the TIFF tags to find the offset(s) of the compressed data strips.
strip_offsets = img.tag_v2[TiffImagePlugin.STRIPOFFSETS] strip_offsets = img.tag_v2[TiffImagePlugin.STRIPOFFSETS]
@ -747,18 +754,20 @@ def parse_png(rawdata):
# once we can require Python >= 3.2 we can use int.from_bytes() instead # once we can require Python >= 3.2 we can use int.from_bytes() instead
n, = struct.unpack('>I', rawdata[i-8:i-4]) n, = struct.unpack('>I', rawdata[i-8:i-4])
if i + n > len(rawdata): if i + n > len(rawdata):
raise Exception("invalid png: %d %d %d"%(i, n, len(rawdata))) raise Exception("invalid png: %d %d %d" % (i, n, len(rawdata)))
if rawdata[i-4:i] == b"IDAT": if rawdata[i-4:i] == b"IDAT":
pngidat += rawdata[i:i+n] pngidat += rawdata[i:i+n]
elif rawdata[i-4:i] == b"PLTE": elif rawdata[i-4:i] == b"PLTE":
for j in range(i, i+n, 3): for j in range(i, i+n, 3):
# with int.from_bytes() we would not have to prepend extra zeroes # with int.from_bytes() we would not have to prepend extra
# zeroes
color, = struct.unpack('>I', b'\x00'+rawdata[j:j+3]) color, = struct.unpack('>I', b'\x00'+rawdata[j:j+3])
palette.append(color) palette.append(color)
i += n i += n
i += 12 i += 12
return pngidat, palette return pngidat, palette
def read_images(rawdata, colorspace, first_frame_only=False): def read_images(rawdata, colorspace, first_frame_only=False):
im = BytesIO(rawdata) im = BytesIO(rawdata)
im.seek(0) im.seek(0)
@ -796,7 +805,8 @@ def read_images(rawdata, colorspace, first_frame_only=False):
if color == Colorspace['RGBA']: if color == Colorspace['RGBA']:
raise JpegColorspaceError("jpeg can't have an alpha channel") raise JpegColorspaceError("jpeg can't have an alpha channel")
im.close() im.close()
return [(color, ndpi, imgformat, rawdata, imgwidthpx, imgheightpx, [], False)] return [(color, ndpi, imgformat, rawdata, imgwidthpx, imgheightpx, [],
False)]
# We can directly embed the IDAT chunk of PNG images if the PNG is not # We can directly embed the IDAT chunk of PNG images if the PNG is not
# interlaced # interlaced
@ -810,26 +820,29 @@ def read_images(rawdata, colorspace, first_frame_only=False):
imgdata, imgformat, default_dpi, colorspace, rawdata) imgdata, imgformat, default_dpi, colorspace, rawdata)
pngidat, palette = parse_png(rawdata) pngidat, palette = parse_png(rawdata)
im.close() im.close()
return [(color, ndpi, imgformat, pngidat, imgwidthpx, imgheightpx, palette, False)] return [(color, ndpi, imgformat, pngidat, imgwidthpx, imgheightpx,
palette, False)]
# We can directly copy the data out of a CCITT Group 4 encoded TIFF, if it # We can directly copy the data out of a CCITT Group 4 encoded TIFF, if it
# only contains a single strip # only contains a single strip
if imgformat == ImageFormat.TIFF \ if imgformat == ImageFormat.TIFF \
and imgdata.info['compression'] == "group4" \ and imgdata.info['compression'] == "group4" \
and len(imgdata.tag_v2[TiffImagePlugin.STRIPOFFSETS]) == 1: and len(imgdata.tag_v2[TiffImagePlugin.STRIPOFFSETS]) == 1:
photo = imgdata.tag_v2[TiffImagePlugin.PHOTOMETRIC_INTERPRETATION] photo = imgdata.tag_v2[TiffImagePlugin.PHOTOMETRIC_INTERPRETATION]
inverted = False inverted = False
if photo == 0: if photo == 0:
inverted = True inverted = True
elif photo != 1: elif photo != 1:
raise ValueError("unsupported photometric interpretation for group4 tiff: %d" % photo) raise ValueError("unsupported photometric interpretation for "
"group4 tiff: %d" % photo)
color, ndpi, imgwidthpx, imgheightpx = get_imgmetadata( color, ndpi, imgwidthpx, imgheightpx = get_imgmetadata(
imgdata, imgformat, default_dpi, colorspace, rawdata) imgdata, imgformat, default_dpi, colorspace, rawdata)
offset, length = ccitt_payload_location_from_pil(imgdata) offset, length = ccitt_payload_location_from_pil(imgdata)
im.seek(offset) im.seek(offset)
rawdata = im.read(length) rawdata = im.read(length)
im.close() im.close()
return [(color, ndpi, ImageFormat.CCITTGroup4, rawdata, imgwidthpx, imgheightpx, [], inverted)] return [(color, ndpi, ImageFormat.CCITTGroup4, rawdata, imgwidthpx,
imgheightpx, [], inverted)]
# Everything else has to be encoded # Everything else has to be encoded
@ -869,7 +882,8 @@ def read_images(rawdata, colorspace, first_frame_only=False):
logging.debug("Colorspace is OK: %s", color) logging.debug("Colorspace is OK: %s", color)
newimg = imgdata newimg = imgdata
else: else:
raise ValueError("unknown or unsupported colorspace: %s" % color.name) raise ValueError("unknown or unsupported colorspace: %s"
% color.name)
# the PNG format does not support CMYK, so we fall back to normal # the PNG format does not support CMYK, so we fall back to normal
# compression # compression
if color in [Colorspace.CMYK, Colorspace["CMYK;I"]]: if color in [Colorspace.CMYK, Colorspace["CMYK;I"]]:
@ -1194,7 +1208,7 @@ def convert(*images, **kwargs):
try: try:
with open(img, "rb") as f: with open(img, "rb") as f:
rawdata = f.read() rawdata = f.read()
except: except Exception:
# whatever the exception is (string could contain NUL # whatever the exception is (string could contain NUL
# characters or the path could just not exist) it's not a file # characters or the path could just not exist) it's not a file
# name so we now try treating it as raw image content # name so we now try treating it as raw image content
@ -1698,7 +1712,7 @@ RGB.''')
"to prevent decompression bomb denial of service attacks. If " "to prevent decompression bomb denial of service attacks. If "
"your input image contains more pixels than that, use this " "your input image contains more pixels than that, use this "
"option to disable this safety measure during this run of img2pdf" "option to disable this safety measure during this run of img2pdf"
%Image.MAX_IMAGE_PIXELS) % Image.MAX_IMAGE_PIXELS)
sizeargs = parser.add_argument_group( sizeargs = parser.add_argument_group(
title='Image and page size and layout arguments', title='Image and page size and layout arguments',

22
src/tests/__init__.py
View file

@ -592,13 +592,17 @@ def test_suite():
if imgprops.DecodeParms: if imgprops.DecodeParms:
if orig_img.format == 'PNG': if orig_img.format == 'PNG':
pngidat, palette = img2pdf.parse_png(orig_imgdata) pngidat, palette = img2pdf.parse_png(orig_imgdata)
elif orig_img.format == 'TIFF' and orig_img.info['compression'] == "group4": elif orig_img.format == 'TIFF' \
offset, length = img2pdf.ccitt_payload_location_from_pil(orig_img) and orig_img.info['compression'] == "group4":
offset, length = \
img2pdf.ccitt_payload_location_from_pil(
orig_img)
pngidat = orig_imgdata[offset:offset+length] pngidat = orig_imgdata[offset:offset+length]
else: else:
pngbuffer = BytesIO() pngbuffer = BytesIO()
orig_img.save(pngbuffer, format="png") orig_img.save(pngbuffer, format="png")
pngidat, palette = img2pdf.parse_png(pngbuffer.getvalue()) pngidat, palette = img2pdf.parse_png(
pngbuffer.getvalue())
self.assertEqual(zlib.decompress(pngidat), imgdata) self.assertEqual(zlib.decompress(pngidat), imgdata)
else: else:
colorspace = imgprops.ColorSpace colorspace = imgprops.ColorSpace
@ -610,17 +614,19 @@ def test_suite():
colorspace = 'CMYK' colorspace = 'CMYK'
else: else:
raise Exception("invalid colorspace") raise Exception("invalid colorspace")
im = Image.frombytes(colorspace, (int(imgprops.Width), im = Image.frombytes(colorspace,
int(imgprops.Height)), (int(imgprops.Width),
int(imgprops.Height)),
imgdata) imgdata)
if orig_img.mode == '1': if orig_img.mode == '1':
self.assertEqual(im.tobytes(), self.assertEqual(im.tobytes(),
orig_img.convert("L").tobytes()) orig_img.convert("L").tobytes())
elif orig_img.mode not in ("RGB", "L", "CMYK", "CMYK;I"): elif orig_img.mode not in ("RGB", "L", "CMYK",
"CMYK;I"):
self.assertEqual(im.tobytes(), self.assertEqual(im.tobytes(),
orig_img.convert("RGB").tobytes()) orig_img.convert("RGB").tobytes())
# the python-pil version 2.3.0-1ubuntu3 in Ubuntu does not # the python-pil version 2.3.0-1ubuntu3 in Ubuntu does
# have the close() method # not have the close() method
try: try:
im.close() im.close()
except AttributeError: except AttributeError: