@ -22,7 +22,7 @@ import sys
import os
import os
import zlib
import zlib
import argparse
import argparse
from PIL import Image , TiffImagePlugin , GifImagePlugin
from PIL import Image , TiffImagePlugin , GifImagePlugin , ImageCms
if hasattr ( GifImagePlugin , " LoadingStrategy " ) :
if hasattr ( GifImagePlugin , " LoadingStrategy " ) :
# Pillow 9.0.0 started emitting all frames but the first as RGB instead of
# Pillow 9.0.0 started emitting all frames but the first as RGB instead of
@ -36,8 +36,8 @@ if hasattr(GifImagePlugin, "LoadingStrategy"):
# TiffImagePlugin.DEBUG = True
# TiffImagePlugin.DEBUG = True
from PIL . ExifTags import TAGS
from PIL . ExifTags import TAGS
from datetime import datetime
from datetime import datetime , timezone
from jp2 import parse jp2
import jp2
from enum import Enum
from enum import Enum
from io import BytesIO
from io import BytesIO
import logging
import logging
@ -45,6 +45,8 @@ import struct
import platform
import platform
import hashlib
import hashlib
from itertools import chain
from itertools import chain
import re
import io
logger = logging . getLogger ( __name__ )
logger = logging . getLogger ( __name__ )
@ -60,7 +62,7 @@ try:
except ImportError :
except ImportError :
have_pikepdf = False
have_pikepdf = False
__version__ = " 0. 4.4 "
__version__ = " 0. 5.1 "
default_dpi = 96.0
default_dpi = 96.0
papersizes = {
papersizes = {
" letter " : " 8.5inx11in " ,
" letter " : " 8.5inx11in " ,
@ -125,7 +127,9 @@ PageOrientation = Enum("PageOrientation", "portrait landscape")
Colorspace = Enum ( " Colorspace " , " RGB RGBA L LA 1 CMYK CMYK;I P PA other " )
Colorspace = Enum ( " Colorspace " , " RGB RGBA L LA 1 CMYK CMYK;I P PA other " )
ImageFormat = Enum ( " ImageFormat " , " JPEG JPEG2000 CCITTGroup4 PNG GIF TIFF MPO other " )
ImageFormat = Enum (
" ImageFormat " , " JPEG JPEG2000 CCITTGroup4 PNG GIF TIFF MPO MIFF other "
)
PageMode = Enum ( " PageMode " , " none outlines thumbs " )
PageMode = Enum ( " PageMode " , " none outlines thumbs " )
@ -442,7 +446,7 @@ class temp_attr:
if hasattr ( self . obj , self . field ) :
if hasattr ( self . obj , self . field ) :
self . exists = True
self . exists = True
self . old_value = getattr ( self . obj , self . field )
self . old_value = getattr ( self . obj , self . field )
print ( f " setting { self . obj } . { self . field } = { self . value } " )
logger . debug ( f " setting { self . obj } . { self . field } = { self . value } " )
setattr ( self . obj , self . field , self . value )
setattr ( self . obj , self . field , self . value )
def __exit__ ( self , exctype , excinst , exctb ) :
def __exit__ ( self , exctype , excinst , exctb ) :
@ -718,7 +722,7 @@ class pdfdoc(object):
self . writer . docinfo = PdfDict ( indirect = True )
self . writer . docinfo = PdfDict ( indirect = True )
def datetime_to_pdfdate ( dt ) :
def datetime_to_pdfdate ( dt ) :
return dt . strftime( " % Y % m %d % H % M % SZ " )
return dt . astimezone( tz = timezone . utc ) . strftime( " % Y % m %d % H % M % SZ " )
for k in [ " Title " , " Author " , " Creator " , " Producer " , " Subject " ] :
for k in [ " Title " , " Author " , " Creator " , " Producer " , " Subject " ] :
v = locals ( ) [ k . lower ( ) ]
v = locals ( ) [ k . lower ( ) ]
@ -728,7 +732,7 @@ class pdfdoc(object):
v = PdfString . encode ( v )
v = PdfString . encode ( v )
self . writer . docinfo [ getattr ( PdfName , k ) ] = v
self . writer . docinfo [ getattr ( PdfName , k ) ] = v
now = datetime . now ( )
now = datetime . now ( ) . astimezone ( )
for k in [ " CreationDate " , " ModDate " ] :
for k in [ " CreationDate " , " ModDate " ] :
v = locals ( ) [ k . lower ( ) ]
v = locals ( ) [ k . lower ( ) ]
if v is None and nodate :
if v is None and nodate :
@ -748,7 +752,7 @@ class pdfdoc(object):
)
)
def datetime_to_xmpdate ( dt ) :
def datetime_to_xmpdate ( dt ) :
return dt . strftime( " % Y- % m- %d T % H: % M: % SZ " )
return dt . astimezone( tz = timezone . utc ) . strftime( " % Y- % m- %d T % H: % M: % SZ " )
self . xmp = b """ <?xpacket begin= ' \xef \xbb \xbf ' id= ' W5M0MpCehiHzreSzNTczkc9d ' ?>
self . xmp = b """ <?xpacket begin= ' \xef \xbb \xbf ' id= ' W5M0MpCehiHzreSzNTczkc9d ' ?>
< x : xmpmeta xmlns : x = ' adobe:ns:meta/ ' x : xmptk = ' XMP toolkit 2.9.1-13, framework 1.6 ' >
< x : xmpmeta xmlns : x = ' adobe:ns:meta/ ' x : xmptk = ' XMP toolkit 2.9.1-13, framework 1.6 ' >
@ -823,8 +827,10 @@ class pdfdoc(object):
artborder = None ,
artborder = None ,
iccp = None ,
iccp = None ,
) :
) :
assert ( color != Colorspace . RGBA and color != Colorspace . LA ) or (
assert (
imgformat == ImageFormat . PNG and smaskdata is not None
color not in [ Colorspace . RGBA , Colorspace . LA ]
or ( imgformat == ImageFormat . PNG and smaskdata is not None )
or imgformat == ImageFormat . JPEG2000
)
)
if self . engine == Engine . pikepdf :
if self . engine == Engine . pikepdf :
@ -848,7 +854,13 @@ class pdfdoc(object):
if color == Colorspace [ " 1 " ] or color == Colorspace . L or color == Colorspace . LA :
if color == Colorspace [ " 1 " ] or color == Colorspace . L or color == Colorspace . LA :
colorspace = PdfName . DeviceGray
colorspace = PdfName . DeviceGray
elif color == Colorspace . RGB or color == Colorspace . RGBA :
elif color == Colorspace . RGB or color == Colorspace . RGBA :
colorspace = PdfName . DeviceRGB
if color == Colorspace . RGBA and imgformat == ImageFormat . JPEG2000 :
# there is no DeviceRGBA and for JPXDecode it is okay to have
# no colorspace as the pdf reader is supposed to get this info
# from the jpeg2000 payload itself
colorspace = None
else :
colorspace = PdfName . DeviceRGB
elif color == Colorspace . CMYK or color == Colorspace [ " CMYK;I " ] :
elif color == Colorspace . CMYK or color == Colorspace [ " CMYK;I " ] :
colorspace = PdfName . DeviceCMYK
colorspace = PdfName . DeviceCMYK
elif color == Colorspace . P :
elif color == Colorspace . P :
@ -919,7 +931,8 @@ class pdfdoc(object):
image [ PdfName . Filter ] = ofilter
image [ PdfName . Filter ] = ofilter
image [ PdfName . Width ] = imgwidthpx
image [ PdfName . Width ] = imgwidthpx
image [ PdfName . Height ] = imgheightpx
image [ PdfName . Height ] = imgheightpx
image [ PdfName . ColorSpace ] = colorspace
if colorspace is not None :
image [ PdfName . ColorSpace ] = colorspace
image [ PdfName . BitsPerComponent ] = depth
image [ PdfName . BitsPerComponent ] = depth
smask = None
smask = None
@ -1256,8 +1269,11 @@ class pdfdoc(object):
# now write out the PDF
# now write out the PDF
if self . engine == Engine . pikepdf :
if self . engine == Engine . pikepdf :
kwargs = { }
if pikepdf . __version__ > = " 6.2.0 " :
kwargs [ " deterministic_id " ] = True
self . writer . save (
self . writer . save (
outputstream , min_version = self . output_version , linearize = True
outputstream , min_version = self . output_version , linearize = True , * * kwargs
)
)
elif self . engine == Engine . pdfrw :
elif self . engine == Engine . pdfrw :
self . writer . trailer . Info = self . writer . docinfo
self . writer . trailer . Info = self . writer . docinfo
@ -1285,7 +1301,7 @@ def get_imgmetadata(
if imgformat == ImageFormat . JPEG2000 and rawdata is not None and imgdata is None :
if imgformat == ImageFormat . JPEG2000 and rawdata is not None and imgdata is None :
# this codepath gets called if the PIL installation is not able to
# this codepath gets called if the PIL installation is not able to
# handle JPEG2000 files
# handle JPEG2000 files
imgwidthpx , imgheightpx , ics , hdpi , vdpi = parsejp2 ( rawdata )
imgwidthpx , imgheightpx , ics , hdpi , vdpi , channels , bpp = jp2. parse( rawdata )
if hdpi is None :
if hdpi is None :
hdpi = default_dpi
hdpi = default_dpi
@ -1295,7 +1311,19 @@ def get_imgmetadata(
else :
else :
imgwidthpx , imgheightpx = imgdata . size
imgwidthpx , imgheightpx = imgdata . size
ndpi = imgdata . info . get ( " dpi " , ( default_dpi , default_dpi ) )
ndpi = imgdata . info . get ( " dpi " )
if ndpi is None :
# the PNG plugin of PIL adds the undocumented "aspect" field instead of
# the "dpi" field if the PNG pHYs chunk unit is not set to meters
if imgformat == ImageFormat . PNG and imgdata . info . get ( " aspect " ) is not None :
aspect = imgdata . info [ " aspect " ]
# make sure not to go below the default dpi
if aspect [ 0 ] > aspect [ 1 ] :
ndpi = ( default_dpi * aspect [ 0 ] / aspect [ 1 ] , default_dpi )
else :
ndpi = ( default_dpi , default_dpi * aspect [ 1 ] / aspect [ 0 ] )
else :
ndpi = ( default_dpi , default_dpi )
# In python3, the returned dpi value for some tiff images will
# In python3, the returned dpi value for some tiff images will
# not be an integer but a float. To make the behaviour of
# not be an integer but a float. To make the behaviour of
# img2pdf the same between python2 and python3, we convert that
# img2pdf the same between python2 and python3, we convert that
@ -1305,7 +1333,7 @@ def get_imgmetadata(
ics = imgdata . mode
ics = imgdata . mode
# GIF and PNG files with transparency are supported
# GIF and PNG files with transparency are supported
if ( imgformat == ImageFormat . PNG or imgformat == ImageFormat . GIF ) and (
if imgformat in [ ImageFormat . PNG , ImageFormat . GIF , ImageFormat . JPEG2000 ] and (
ics in [ " RGBA " , " LA " ] or " transparency " in imgdata . info
ics in [ " RGBA " , " LA " ] or " transparency " in imgdata . info
) :
) :
# Must check the IHDR chunk for the bit depth, because PIL would lossily
# Must check the IHDR chunk for the bit depth, because PIL would lossily
@ -1315,6 +1343,10 @@ def get_imgmetadata(
if depth > 8 :
if depth > 8 :
logger . warning ( " Image with transparency and a bit depth of %d . " % depth )
logger . warning ( " Image with transparency and a bit depth of %d . " % depth )
logger . warning ( " This is unsupported due to PIL limitations. " )
logger . warning ( " This is unsupported due to PIL limitations. " )
logger . warning (
" If you accept a lossy conversion, you can manually convert "
" your images to 8 bit using `convert -depth 8` from imagemagick "
)
raise AlphaChannelError (
raise AlphaChannelError (
" Refusing to work with multiple >8bit channels. "
" Refusing to work with multiple >8bit channels. "
)
)
@ -1425,6 +1457,53 @@ def get_imgmetadata(
iccp = None
iccp = None
if " icc_profile " in imgdata . info :
if " icc_profile " in imgdata . info :
iccp = imgdata . info . get ( " icc_profile " )
iccp = imgdata . info . get ( " icc_profile " )
# GIMP saves bilevel TIFF images and palette PNG images with only black and
# white in the palette with an RGB ICC profile which is useless
# https://gitlab.gnome.org/GNOME/gimp/-/issues/3438
# and produces an error in Adobe Acrobat, so we ignore it with a warning.
# imagemagick also used to (wrongly) include an RGB ICC profile for bilevel
# images: https://github.com/ImageMagick/ImageMagick/issues/2070
if iccp is not None and (
( color == Colorspace [ " 1 " ] and imgformat == ImageFormat . TIFF )
or (
imgformat == ImageFormat . PNG
and color == Colorspace . P
and rawdata is not None
and parse_png ( rawdata ) [ 1 ]
in [ b " \x00 \x00 \x00 \xff \xff \xff " , b " \xff \xff \xff \x00 \x00 \x00 " ]
)
) :
with io . BytesIO ( iccp ) as f :
prf = ImageCms . ImageCmsProfile ( f )
if (
prf . profile . model == " sRGB "
and prf . profile . manufacturer == " GIMP "
and prf . profile . profile_description == " GIMP built-in sRGB "
) :
if imgformat == ImageFormat . TIFF :
logger . warning (
" Ignoring RGB ICC profile in bilevel TIFF produced by GIMP. "
)
elif imgformat == ImageFormat . PNG :
logger . warning (
" Ignoring RGB ICC profile in 2-color palette PNG produced by GIMP. "
)
logger . warning ( " https://gitlab.gnome.org/GNOME/gimp/-/issues/3438 " )
iccp = None
# SmartAlbums old version (found 2.2.6) exports JPG with only 1 compone
# with an RGB ICC profile which is useless.
# This produces an error in Adobe Acrobat, so we ignore it with a warning.
# Update: Found another case, the JPG is created by Adobe PhotoShop, so we
# don't check software anymore.
if iccp is not None and (
( color == Colorspace [ " L " ] and imgformat == ImageFormat . JPEG )
) :
with io . BytesIO ( iccp ) as f :
prf = ImageCms . ImageCmsProfile ( f )
if prf . profile . xcolor_space not in ( " GRAY " ) :
logger . warning ( " Ignoring non-GRAY ICC profile in Grayscale JPG " )
iccp = None
logger . debug ( " width x height = %d px x %d px " , imgwidthpx , imgheightpx )
logger . debug ( " width x height = %d px x %d px " , imgwidthpx , imgheightpx )
@ -1533,7 +1612,204 @@ def parse_png(rawdata):
return pngidat , palette
return pngidat , palette
def read_images ( rawdata , colorspace , first_frame_only = False , rot = None ) :
miff_re = re . compile (
r """
[ ^ \x00 - \x20 \x7f - \x9f ] # the field name must not start with a control char or space
[ ^ = ] + # the field name can even contain spaces
= # field name and value are separated by an equal sign
( ? :
[ ^ \x00 - \x20 \x7f - \x9f { } ] # either chars that are not braces and not control chars
| { [ ^ } ] * } # or any kind of char surrounded by braces
) + """ ,
re . VERBOSE ,
)
# https://imagemagick.org/script/miff.php
# turn off black formatting until python 3.10 is available on more platforms
# and we can use match/case
# fmt: off
def parse_miff ( data ) :
results = [ ]
header , rest = data . split ( b " : \x1a " , 1 )
header = header . decode ( " ISO-8859-1 " )
assert header . lower ( ) . startswith ( " id=imagemagick " )
hdata = { }
for i , line in enumerate ( re . findall ( miff_re , header ) ) :
if not line :
continue
k , v = line . split ( " = " , 1 )
if i == 0 :
assert k . lower ( ) == " id "
assert v . lower ( ) == " imagemagick "
#match k.lower():
# case "class":
if k . lower ( ) == " class " :
#match v:
# case "DirectClass" | "PseudoClass":
if v in [ " DirectClass " , " PseudoClass " ] :
hdata [ " class " ] = v
# case _:
else :
print ( " cannot understand class " , v )
# case "colorspace":
elif k . lower ( ) == " colorspace " :
# theoretically RGBA and CMYKA should be supported as well
# please teach me how to create such a MIFF file
#match v:
# case "sRGB" | "CMYK" | "Gray":
if v in [ " sRGB " , " CMYK " , " Gray " ] :
hdata [ " colorspace " ] = v
# case _:
else :
print ( " cannot understand colorspace " , v )
# case "depth":
elif k . lower ( ) == " depth " :
#match v:
# case "8" | "16" | "32":
if v in [ " 8 " , " 16 " , " 32 " ] :
hdata [ " depth " ] = int ( v )
# case _:
else :
print ( " cannot understand depth " , v )
# case "colors":
elif k . lower ( ) == " colors " :
hdata [ " colors " ] = int ( v )
# case "matte":
elif k . lower ( ) == " matte " :
#match v:
# case "True":
if v == " True " :
hdata [ " matte " ] = True
# case "False":
elif v == " False " :
hdata [ " matte " ] = False
# case _:
else :
print ( " cannot understand matte " , v )
# case "columns" | "rows":
elif k . lower ( ) in [ " columns " , " rows " ] :
hdata [ k . lower ( ) ] = int ( v )
# case "compression":
elif k . lower ( ) == " compression " :
print ( " compression not yet supported " )
# case "profile":
elif k . lower ( ) == " profile " :
assert v in [ " icc " , " exif " ]
hdata [ " profile " ] = v
# case "resolution":
elif k . lower ( ) == " resolution " :
dpix , dpiy = v . split ( " x " , 1 )
hdata [ " resolution " ] = ( float ( dpix ) , float ( dpiy ) )
assert " depth " in hdata
assert " columns " in hdata
assert " rows " in hdata
#match hdata["class"]:
# case "DirectClass":
if hdata [ " class " ] == " DirectClass " :
if " colors " in hdata :
assert hdata [ " colors " ] == 0
#match hdata["colorspace"]:
# case "sRGB":
if hdata [ " colorspace " ] == " sRGB " :
numchannels = 3
colorspace = Colorspace . RGB
# case "CMYK":
elif hdata [ " colorspace " ] == " CMYK " :
numchannels = 4
colorspace = Colorspace . CMYK
# case "Gray":
elif hdata [ " colorspace " ] == " Gray " :
numchannels = 1
colorspace = Colorspace . L
if hdata . get ( " matte " ) :
numchannels + = 1
if hdata . get ( " profile " ) :
# there is no key encoding the length of icc or exif data
# according to the docs, the profile-icc key is supposed to do this
print ( " FAIL: exif " )
else :
lenimgdata = (
hdata [ " depth " ] / / 8 * numchannels * hdata [ " columns " ] * hdata [ " rows " ]
)
assert len ( rest ) > = lenimgdata , (
len ( rest ) ,
hdata [ " depth " ] ,
numchannels ,
hdata [ " columns " ] ,
hdata [ " rows " ] ,
lenimgdata ,
)
if colorspace == Colorspace . RGB and hdata [ " depth " ] == 8 :
newimg = Image . frombytes ( " RGB " , ( hdata [ " columns " ] , hdata [ " rows " ] ) , rest [ : lenimgdata ] )
imgdata , palette , depth = to_png_data ( newimg )
assert palette == b " "
assert depth == hdata [ " depth " ]
imgfmt = ImageFormat . PNG
else :
imgdata = zlib . compress ( rest [ : lenimgdata ] )
imgfmt = ImageFormat . MIFF
results . append (
(
colorspace ,
hdata . get ( " resolution " ) or ( default_dpi , default_dpi ) ,
imgfmt ,
imgdata ,
None , # smask
hdata [ " columns " ] ,
hdata [ " rows " ] ,
[ ] , # palette
False , # inverted
hdata [ " depth " ] ,
0 , # rotation
None , # icc profile
)
)
if len ( rest ) > lenimgdata :
# another image is here
assert rest [ lenimgdata : ] [ : 14 ] . lower ( ) == b " id=imagemagick "
results . extend ( parse_miff ( rest [ lenimgdata : ] ) )
# case "PseudoClass":
elif hdata [ " class " ] == " PseudoClass " :
assert " colors " in hdata
if hdata . get ( " matte " ) :
numchannels = 2
else :
numchannels = 1
lenpal = 3 * hdata [ " colors " ] * hdata [ " depth " ] / / 8
lenimgdata = numchannels * hdata [ " rows " ] * hdata [ " columns " ]
assert len ( rest ) > = lenpal + lenimgdata , ( len ( rest ) , lenpal , lenimgdata )
results . append (
(
Colorspace . RGB ,
hdata . get ( " resolution " ) or ( default_dpi , default_dpi ) ,
ImageFormat . MIFF ,
zlib . compress ( rest [ lenpal : lenpal + lenimgdata ] ) ,
None , # FIXME: allow alpha channel smask
hdata [ " columns " ] ,
hdata [ " rows " ] ,
rest [ : lenpal ] , # palette
False , # inverted
hdata [ " depth " ] ,
0 , # rotation
None , # icc profile
)
)
if len ( rest ) > lenpal + lenimgdata :
# another image is here
assert rest [ lenpal + lenimgdata : ] [ : 14 ] . lower ( ) == b " id=imagemagick " , (
len ( rest ) ,
lenpal ,
lenimgdata ,
)
results . extend ( parse_miff ( rest [ lenpal + lenimgdata : ] ) )
return results
# fmt: on
def read_images (
rawdata , colorspace , first_frame_only = False , rot = None , include_thumbnails = False
) :
im = BytesIO ( rawdata )
im = BytesIO ( rawdata )
im . seek ( 0 )
im . seek ( 0 )
imgdata = None
imgdata = None
@ -1541,13 +1817,19 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
imgdata = Image . open ( im )
imgdata = Image . open ( im )
except IOError as e :
except IOError as e :
# test if it is a jpeg2000 image
# test if it is a jpeg2000 image
if rawdata [ : 12 ] != b " \x00 \x00 \x00 \x0C \x6A \x50 \x20 \x20 \x0D \x0A \x87 \x0A " :
if rawdata [ : 12 ] == b " \x00 \x00 \x00 \x0C \x6A \x50 \x20 \x20 \x0D \x0A \x87 \x0A " :
# image is jpeg2000
imgformat = ImageFormat . JPEG2000
if rawdata [ : 14 ] . lower ( ) == b " id=imagemagick " :
# image is in MIFF format
# this is useful for 16 bit CMYK because PNG cannot do CMYK and thus
# we need PIL but PIL cannot do 16 bit
imgformat = ImageFormat . MIFF
else :
raise ImageOpenError (
raise ImageOpenError (
" cannot read input image (not jpeg2000). "
" cannot read input image (not jpeg2000). "
" PIL: error reading image: %s " % e
" PIL: error reading image: %s " % e
)
)
# image is jpeg2000
imgformat = ImageFormat . JPEG2000
else :
else :
logger . debug ( " PIL format = %s " , imgdata . format )
logger . debug ( " PIL format = %s " , imgdata . format )
imgformat = None
imgformat = None
@ -1581,10 +1863,13 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
raise JpegColorspaceError ( " jpeg can ' t be monochrome " )
raise JpegColorspaceError ( " jpeg can ' t be monochrome " )
if color == Colorspace [ " P " ] :
if color == Colorspace [ " P " ] :
raise JpegColorspaceError ( " jpeg can ' t have a color palette " )
raise JpegColorspaceError ( " jpeg can ' t have a color palette " )
if color == Colorspace [ " RGBA " ] :
if color == Colorspace [ " RGBA " ] and imgformat != ImageFormat . JPEG2000 :
raise JpegColorspaceError ( " jpeg can ' t have an alpha channel " )
raise JpegColorspaceError ( " jpeg can ' t have an alpha channel " )
logger . debug ( " read_images() embeds a JPEG " )
logger . debug ( " read_images() embeds a JPEG " )
cleanup ( )
cleanup ( )
depth = 8
if imgformat == ImageFormat . JPEG2000 :
* _ , depth = jp2 . parse ( rawdata )
return [
return [
(
(
color ,
color ,
@ -1596,7 +1881,7 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
imgheightpx ,
imgheightpx ,
[ ] ,
[ ] ,
False ,
False ,
8 ,
depth ,
rotation ,
rotation ,
iccp ,
iccp ,
)
)
@ -1613,6 +1898,77 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
if imgformat == ImageFormat . MPO :
if imgformat == ImageFormat . MPO :
result = [ ]
result = [ ]
img_page_count = 0
img_page_count = 0
assert len ( imgdata . _MpoImageFile__mpoffsets ) == len ( imgdata . mpinfo [ 0xB002 ] )
num_frames = len ( imgdata . mpinfo [ 0xB002 ] )
# An MPO file can be a main image together with one or more thumbnails
# if that is the case, then we only include all frames if the
# --include-thumbnails option is given. If it is not, such an MPO file
# will be embedded as is, so including its thumbnails but showing up
# as a single image page in the resulting PDF.
num_main_frames = 0
num_thumbnail_frames = 0
for i , mpent in enumerate ( imgdata . mpinfo [ 0xB002 ] ) :
# check only the first frame for being the main image
if (
i == 0
and mpent [ " Attribute " ] [ " DependentParentImageFlag " ]
and not mpent [ " Attribute " ] [ " DependentChildImageFlag " ]
and mpent [ " Attribute " ] [ " RepresentativeImageFlag " ]
and mpent [ " Attribute " ] [ " MPType " ] == " Baseline MP Primary Image "
) :
num_main_frames + = 1
elif (
not mpent [ " Attribute " ] [ " DependentParentImageFlag " ]
and mpent [ " Attribute " ] [ " DependentChildImageFlag " ]
and not mpent [ " Attribute " ] [ " RepresentativeImageFlag " ]
and mpent [ " Attribute " ] [ " MPType " ]
in [
" Large Thumbnail (VGA Equivalent) " ,
" Large Thumbnail (Full HD Equivalent) " ,
]
) :
num_thumbnail_frames + = 1
logger . debug ( f " number of frames: { num_frames } " )
logger . debug ( f " number of main frames: { num_main_frames } " )
logger . debug ( f " number of thumbnail frames: { num_thumbnail_frames } " )
# this MPO file is a main image plus zero or more thumbnails
# embed as-is unless the --include-thumbnails option was given
if num_frames == 1 or (
not include_thumbnails
and num_main_frames == 1
and num_thumbnail_frames + 1 == num_frames
) :
color , ndpi , imgwidthpx , imgheightpx , rotation , iccp = get_imgmetadata (
imgdata , imgformat , default_dpi , colorspace , rawdata , rot
)
if color == Colorspace [ " 1 " ] :
raise JpegColorspaceError ( " jpeg can ' t be monochrome " )
if color == Colorspace [ " P " ] :
raise JpegColorspaceError ( " jpeg can ' t have a color palette " )
if color == Colorspace [ " RGBA " ] :
raise JpegColorspaceError ( " jpeg can ' t have an alpha channel " )
logger . debug ( " read_images() embeds an MPO verbatim " )
cleanup ( )
return [
(
color ,
ndpi ,
ImageFormat . JPEG ,
rawdata ,
None ,
imgwidthpx ,
imgheightpx ,
[ ] ,
False ,
8 ,
rotation ,
iccp ,
)
]
# If the control flow reaches here, the MPO has more than a single
# frame but was not detected to be a main image followed by multiple
# thumbnails. We thus treat this MPO as we do other multi-frame images
# and include all its frames as individual pages.
for offset , mpent in zip (
for offset , mpent in zip (
imgdata . _MpoImageFile__mpoffsets , imgdata . mpinfo [ 0xB002 ]
imgdata . _MpoImageFile__mpoffsets , imgdata . mpinfo [ 0xB002 ]
) :
) :
@ -1710,6 +2066,9 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
)
)
]
]
if imgformat == ImageFormat . MIFF :
return parse_miff ( rawdata )
# If our input is not JPEG or PNG, then we might have a format that
# If our input is not JPEG or PNG, then we might have a format that
# supports multiple frames (like TIFF or GIF), so we need a loop to
# supports multiple frames (like TIFF or GIF), so we need a loop to
# iterate through all frames of the image.
# iterate through all frames of the image.
@ -1875,7 +2234,16 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
)
)
)
)
else :
else :
if (
if color in [ Colorspace . P , Colorspace . PA ] and iccp is not None :
# PDF does not support palette images with icc profile
if color == Colorspace . P :
newcolor = Colorspace . RGB
newimg = newimg . convert ( mode = " RGB " )
elif color == Colorspace . PA :
newcolor = Colorspace . RGBA
newimg = newimg . convert ( mode = " RGBA " )
smaskidat = None
elif (
color == Colorspace . RGBA
color == Colorspace . RGBA
or color == Colorspace . LA
or color == Colorspace . LA
or color == Colorspace . PA
or color == Colorspace . PA
@ -1889,25 +2257,21 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
newcolor = color
newcolor = color
l , a = newimg . split ( )
l , a = newimg . split ( )
newimg = l
newimg = l
elif color == Colorspace . PA or (
color == Colorspace . P and " transparency " in newimg . info
) :
newcolor = color
a = newimg . convert ( mode = " RGBA " ) . split ( ) [ - 1 ]
else :
else :
newcolor = Colorspace . RGBA
newcolor = Colorspace . RGBA
r , g , b , a = newimg . convert ( mode = " RGBA " ) . split ( )
r , g , b , a = newimg . convert ( mode = " RGBA " ) . split ( )
newimg = Image . merge ( " RGB " , ( r , g , b ) )
newimg = Image . merge ( " RGB " , ( r , g , b ) )
smaskidat , _ , _ = to_png_data ( a )
smaskidat , * _ = to_png_data ( a )
logger . warning (
logger . warning (
" Image contains an alpha channel. Computing a separate "
" Image contains an alpha channel. Computing a separate "
" soft mask (/SMask) image to store transparency in PDF. "
" soft mask (/SMask) image to store transparency in PDF. "
)
)
elif color in [ Colorspace . P , Colorspace . PA ] and iccp is not None :
# PDF does not support palette images with icc profile
if color == Colorspace . P :
newcolor = Colorspace . RGB
newimg = newimg . convert ( mode = " RGB " )
elif color == Colorspace . PA :
newcolor = Colorspace . RGBA
newimg = newimg . convert ( mode = " RGBA " )
smaskidat = None
else :
else :
newcolor = color
newcolor = color
smaskidat = None
smaskidat = None
@ -2249,7 +2613,6 @@ def find_scale(pagewidth, pageheight):
# as a binary string representing the image content or as filenames to the
# as a binary string representing the image content or as filenames to the
# images.
# images.
def convert ( * images , * * kwargs ) :
def convert ( * images , * * kwargs ) :
_default_kwargs = dict (
_default_kwargs = dict (
engine = None ,
engine = None ,
title = None ,
title = None ,
@ -2279,6 +2642,7 @@ def convert(*images, **kwargs):
artborder = None ,
artborder = None ,
pdfa = None ,
pdfa = None ,
rotation = None ,
rotation = None ,
include_thumbnails = False ,
)
)
for kwname , default in _default_kwargs . items ( ) :
for kwname , default in _default_kwargs . items ( ) :
if kwname not in kwargs :
if kwname not in kwargs :
@ -2322,11 +2686,16 @@ def convert(*images, **kwargs):
for img in images :
for img in images :
# img is allowed to be a path, a binary string representing image data
# img is allowed to be a path, a binary string representing image data
# or a file-like object (really anything that implements read())
# or a file-like object (really anything that implements read())
try :
# or a pathlib.Path object (really anything that implements read_bytes())
rawdata = img . read ( )
rawdata = None
except AttributeError :
for fun in " read " , " read_bytes " :
try :
rawdata = getattr ( img , fun ) ( )
except AttributeError :
pass
if rawdata is None :
if not isinstance ( img , ( str , bytes ) ) :
if not isinstance ( img , ( str , bytes ) ) :
raise TypeError ( " Neither implements read() nor is str or bytes " )
raise TypeError ( " Neither read(), read_bytes () nor is str or bytes" )
# the thing doesn't have a read() function, so try if we can treat
# the thing doesn't have a read() function, so try if we can treat
# it as a file name
# it as a file name
try :
try :
@ -2344,6 +2713,10 @@ def convert(*images, **kwargs):
rawdata = f . read ( )
rawdata = f . read ( )
f . close ( )
f . close ( )
# md5 = hashlib.md5(rawdata).hexdigest()
# with open("./testdata/" + md5, "wb") as f:
# f.write(rawdata)
for (
for (
color ,
color ,
ndpi ,
ndpi ,
@ -2362,6 +2735,7 @@ def convert(*images, **kwargs):
kwargs [ " colorspace " ] ,
kwargs [ " colorspace " ] ,
kwargs [ " first_frame_only " ] ,
kwargs [ " first_frame_only " ] ,
kwargs [ " rotation " ] ,
kwargs [ " rotation " ] ,
kwargs [ " include_thumbnails " ] ,
) :
) :
pagewidth , pageheight , imgwidthpdf , imgheightpdf = kwargs [ " layout_fun " ] (
pagewidth , pageheight , imgwidthpdf , imgheightpdf = kwargs [ " layout_fun " ] (
imgwidthpx , imgheightpx , ndpi
imgwidthpx , imgheightpx , ndpi
@ -2737,7 +3111,7 @@ def valid_date(string):
else :
else :
try :
try :
return parser . parse ( string )
return parser . parse ( string )
except TypeError :
except :
pass
pass
# as a last resort, try the local date utility
# as a last resort, try the local date utility
try :
try :
@ -2750,7 +3124,7 @@ def valid_date(string):
except subprocess . CalledProcessError :
except subprocess . CalledProcessError :
pass
pass
else :
else :
return datetime . utc fromtimestamp( int ( utime ) )
return datetime . fromtimestamp( int ( utime ) )
raise argparse . ArgumentTypeError ( " cannot parse date: %s " % string )
raise argparse . ArgumentTypeError ( " cannot parse date: %s " % string )
@ -3452,7 +3826,35 @@ def gui():
app . mainloop ( )
app . mainloop ( )
def main ( argv = sys . argv ) :
def file_is_icc ( fname ) :
with open ( fname , " rb " ) as f :
data = f . read ( 40 )
if len ( data ) < 40 :
return False
return data [ 36 : ] == b " acsp "
def validate_icc ( fname ) :
if not file_is_icc ( fname ) :
raise argparse . ArgumentTypeError ( ' " %s " is not an ICC profile ' % fname )
return fname
def get_default_icc_profile ( ) :
for profile in [
" /usr/share/color/icc/sRGB.icc " ,
" /usr/share/color/icc/OpenICC/sRGB.icc " ,
" /usr/share/color/icc/colord/sRGB.icc " ,
] :
if not os . path . exists ( profile ) :
continue
if not file_is_icc ( profile ) :
continue
return profile
return " /usr/share/color/icc/sRGB.icc "
def get_main_parser ( ) :
rendered_papersizes = " "
rendered_papersizes = " "
for k , v in sorted ( papersizes . items ( ) ) :
for k , v in sorted ( papersizes . items ( ) ) :
rendered_papersizes + = " %-8s %s \n " % ( papernames [ k ] , v )
rendered_papersizes + = " %-8s %s \n " % ( papernames [ k ] , v )
@ -3493,7 +3895,9 @@ Paper sizes:
the value in the second column has the same effect as giving the short hand
the value in the second column has the same effect as giving the short hand
in the first column . Appending ^ T ( a caret / circumflex followed by the letter
in the first column . Appending ^ T ( a caret / circumflex followed by the letter
T ) turns the paper size from portrait into landscape . The postfix thus
T ) turns the paper size from portrait into landscape . The postfix thus
symbolizes the transpose . The values are case insensitive .
symbolizes the transpose . Note that on Windows cmd . exe the caret symbol is
the escape character , so you need to put quotes around the option value .
The values are case insensitive .
% s
% s
@ -3560,7 +3964,7 @@ Examples:
while preserving its aspect ratio and a print border of 2 cm on the top and
while preserving its aspect ratio and a print border of 2 cm on the top and
bottom and 2.5 cm on the left and right hand side .
bottom and 2.5 cm on the left and right hand side .
$ img2pdf - - output out . pdf - - pagesize A4 ^ T - - border 2 cm : 2.5 cm * . jpg
$ img2pdf - - output out . pdf - - pagesize " A4^T " - - border 2 cm : 2.5 cm * . jpg
On each A4 page , fit images into a 10 cm times 15 cm rectangle but keep the
On each A4 page , fit images into a 10 cm times 15 cm rectangle but keep the
original image size if the image is smaller than that .
original image size if the image is smaller than that .
@ -3695,6 +4099,17 @@ RGB.""",
" input image be converted into a page in the resulting PDF. " ,
" input image be converted into a page in the resulting PDF. " ,
)
)
outargs . add_argument (
" --include-thumbnails " ,
action = " store_true " ,
help = " Some multi-frame formats like MPO carry a main image and "
" one or more scaled-down copies of the main image (thumbnails). "
" In such a case, img2pdf will only include the main image and "
" not create additional pages for each of the thumbnails. If this "
" option is set, img2pdf will instead create one page per frame and "
" thus store each thumbnail on its own page. " ,
)
outargs . add_argument (
outargs . add_argument (
" --pillow-limit-break " ,
" --pillow-limit-break " ,
action = " store_true " ,
action = " store_true " ,
@ -3706,14 +4121,29 @@ RGB.""",
% Image . MAX_IMAGE_PIXELS ,
% Image . MAX_IMAGE_PIXELS ,
)
)
outargs . add_argument (
if sys . platform == " win32 " :
" --pdfa " ,
# on Windows, there are no default paths to search for an ICC profile
nargs = " ? " ,
# so make the argument required instead of optional
const = " /usr/share/color/icc/sRGB.icc " ,
outargs . add_argument (
default = None ,
" --pdfa " ,
help = " Output a PDF/A-1b compliant document. By default, this will "
type = validate_icc ,
" embed /usr/share/color/icc/sRGB.icc as the color profile. " ,
help = " Output a PDF/A-1b compliant document. The argument to this "
)
" option is the path to the ICC profile that will be embedded into "
" the resulting PDF. " ,
)
else :
outargs . add_argument (
" --pdfa " ,
nargs = " ? " ,
const = get_default_icc_profile ( ) ,
default = None ,
type = validate_icc ,
help = " Output a PDF/A-1b compliant document. By default, this will "
" embed either /usr/share/color/icc/sRGB.icc, "
" /usr/share/color/icc/OpenICC/sRGB.icc or "
" /usr/share/color/icc/colord/sRGB.icc as the color profile, whichever "
" is found to exist first. " ,
)
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 " ,
@ -4002,8 +4432,11 @@ and left/right, respectively. It is not possible to specify asymmetric borders.
action = " store_true " ,
action = " store_true " ,
help = " Instruct the PDF viewer to open the PDF in fullscreen mode " ,
help = " Instruct the PDF viewer to open the PDF in fullscreen mode " ,
)
)
return parser
args = parser . parse_args ( argv [ 1 : ] )
def main ( argv = sys . argv ) :
args = get_main_parser ( ) . parse_args ( argv [ 1 : ] )
if args . verbose :
if args . verbose :
logging . basicConfig ( level = logging . DEBUG )
logging . basicConfig ( level = logging . DEBUG )
@ -4027,7 +4460,11 @@ and left/right, respectively. It is not possible to specify asymmetric borders.
elif len ( args . images ) == 0 and len ( args . from_file ) == 0 :
elif len ( args . images ) == 0 and len ( args . from_file ) == 0 :
# if no positional arguments were supplied, read a single image from
# if no positional arguments were supplied, read a single image from
# standard input
# standard input
logger . info ( " reading image from standard input " )
print (
" Reading image from standard input... \n "
" Re-run with -h or --help for usage information. " ,
file = sys . stderr ,
)
try :
try :
images = [ sys . stdin . buffer . read ( ) ]
images = [ sys . stdin . buffer . read ( ) ]
except KeyboardInterrupt :
except KeyboardInterrupt :
@ -4088,6 +4525,7 @@ and left/right, respectively. It is not possible to specify asymmetric borders.
artborder = args . art_border ,
artborder = args . art_border ,
pdfa = args . pdfa ,
pdfa = args . pdfa ,
rotation = args . rotation ,
rotation = args . rotation ,
include_thumbnails = args . include_thumbnails ,
)
)
except Exception as e :
except Exception as e :
logger . error ( " error: " + str ( e ) )
logger . error ( " error: " + str ( e ) )