release version 0.5.1

Closes: #181

.mailmap

@@ -0,0 +1,3 @@
+Johannes Schauer Marin Rodrigues <josch@mister-muffin.de>
+Johannes Schauer Marin Rodrigues <josch@mister-muffin.de> <j.schauer@email.de>
+Johannes Schauer Marin Rodrigues <josch@mister-muffin.de> <josch@pyneo.org>

CHANGES.rst

@@ -2,6 +2,29 @@
 CHANGES
 =======
 
+0.5.1 (2023-11-26)
+------------------
+
+ - no default ICC profile location for PDF/A-1b on Windows
+ - workaround for PNG input without dpi units but non-square dpi aspect ratio
+
+0.5.0 (2023-10-28)
+------------------
+
+ - support MIFF for 16 bit CMYK input
+ - accept pathlib.Path objects as input
+ - don't store RGB ICC profiles from bilevel or grayscale TIFF, PNG and JPEG
+ - thumbnails are no longer included by default and --include-thumbnails has to
+   be used if you want them
+ - support for pikepdf (>= 6.2.0)
+
+0.4.4 (2022-04-07)
+------------------
+
+ - --viewer-page-layout support for twopageright and twopageleft
+ - Add B and JB paper sizes
+ - support for pikepdf (>= 5.0.0) and Pillow (>= 9.1.0)
+
 0.4.3 (2021-10-24)
 ------------------
 

HACKING

@@ -27,6 +27,41 @@ Making a new release
 
  - Build and upload to pypi:
 
-    $ rm dist/*
+    $ rm -rf dist/*
     $ python3 setup.py sdist
-    $ twine upload --sign dist/*
+    $ twine upload dist/*
+
+Using debbisect to find regressions
+-----------------------------------
+
+    $ debbisect --cache=./cache  --depends="git,ca-certificates,python3,
+           ghostscript,imagemagick,mupdf-tools,poppler-utils,python3-pil,
+           python3-pytest,python3-numpy,python3-scipy,python3-pikepdf" \
+      --verbose  2023-09-16 2023-10-24 \
+      'chroot "$1" sh -c "
+           git clone https://gitlab.mister-muffin.de/josch/img2pdf.git
+           && cd img2pdf
+           && pytest 'src/img2pdf_test.py::test_jpg_2000_rgba8[internal]"'
+
+Using debbisect cache
+---------------------
+
+    $ mmdebstrap --variant=apt --aptopt='Acquire::Check-Valid-Until "false"' \
+          --include=git,ca-certificates,python3,ghostscript,imagemagick \
+          --include=mupdf-tools,poppler-utils,python3-pil,python3-pytest \
+          --include=python3-numpy,python3-scipy,python3-pikepdf \
+          --hook-dir=/usr/share/mmdebstrap/hooks/file-mirror-automount \
+          --setup-hook='mkdir -p "$1/home/josch/git/devscripts/cache/pool/"' \
+          --setup-hook='mount -o ro,bind /home/josch/git/devscripts/cache/pool/ "$1/home/josch/git/devscripts/cache/pool/"' \
+          --chrooted-customize-hook=bash
+          unstable /dev/null
+          file:///home/josch/git/devscripts/cache/archive/debian/20231022T090139Z/
+
+Bisecting imagemagick
+---------------------
+
+    $ git clean -fdx && git reset --hard
+    $ ./configure --prefix=$(pwd)/prefix
+    $ make -j$(nproc)
+    $ make install
+    $ LD_LIBRARY_PATH=$(pwd)/prefix/lib prefix/bin/compare ...

README.md

@@ -27,15 +27,15 @@ software, because the raw pixel data never has to be loaded into memory.
 The following table shows how img2pdf handles different input depending on the
 input file format and image color space.
 
-| Format               | Colorspace                     | Result        |
+| Format                                | Colorspace                     | Result        |
-| -------------------- | ------------------------------ | ------------- |
+| ------------------------------------- | ------------------------------ | ------------- |
-| JPEG                 | any                            | direct        |
+| JPEG                                  | any                            | direct        |
-| JPEG2000             | any                            | direct        |
+| JPEG2000                              | any                            | direct        |
-| PNG (non-interlaced) | any                            | direct        |
+| PNG (non-interlaced, no transparency) | any                            | direct        |
-| TIFF (CCITT Group 4) | monochrome                     | direct        |
+| TIFF (CCITT Group 4)                  | monochrome                     | direct        |
-| any                  | any except CMYK and monochrome | PNG Paeth     |
+| any                                   | any except CMYK and monochrome | PNG Paeth     |
-| any                  | monochrome                     | CCITT Group 4 |
+| any                                   | monochrome                     | CCITT Group 4 |
-| any                  | CMYK                           | flate         |
+| any                                   | CMYK                           | flate         |
 
 For JPEG, JPEG2000, non-interlaced PNG and TIFF images with CCITT Group 4
 encoded data, img2pdf directly embeds the image data into the PDF without
@@ -72,11 +72,6 @@ Bugs
    when embedded into the PDF cannot be read by the Adobe Acrobat Reader,
    please contact me.
 
- - I have not yet figured out how to determine the colorspace of JPEG2000
-   files.  Therefore JPEG2000 files use DeviceRGB by default. For JPEG2000
-   files with other colorspaces, you must explicitly specify it using the
-   `--colorspace` option.
-
  - An error is produced if the input image is broken. This commonly happens if
    the input image has an invalid EXIF Orientation value of zero. Even though
    only nine different values from 1 to 9 are permitted, Anroid phones and
@@ -122,10 +117,9 @@ You can then test the converter using:
 
 	$ ve/bin/img2pdf -o test.pdf src/tests/test.jpg
 
-For Microsoft Windows users, PyInstaller based .exe files are produced by
+If you don't want to setup Python on Windows, then head to the
-appveyor. If you don't want to install Python before using img2pdf you can head
+[releases](/josch/img2pdf/releases) section and download the latest
-to appveyor and click on "Artifacts" to download the latest version:
+`img2pdf.exe`.
-https://ci.appveyor.com/project/josch/img2pdf
 
 GUI
 ---
@@ -152,6 +146,10 @@ The package can also be used as a library:
 	with open("name.pdf","wb") as f1, open("test.jpg") as f2:
 		f1.write(img2pdf.convert(f2))
 
+	# opening using pathlib
+	with open("name.pdf","wb") as f:
+		f.write(img2pdf.convert(pathlib.Path('test.jpg')))
+
 	# using in-memory image data
 	with open("name.pdf","wb") as f:
 		f.write(img2pdf.convert("\x89PNG...")
@@ -194,6 +192,11 @@ The package can also be used as a library:
 	with open("name.pdf","wb") as f:
 		f.write(img2pdf.convert(glob.glob("/path/to/*.jpg")))
 
+	# convert all files matching a glob using pathlib.Path
+	from pathlib import Path
+	with open("name.pdf","wb") as f:
+		f.write(img2pdf.convert(*Path("/path").glob("**/*.jpg")))
+
 	# ignore invalid rotation values in the input images
 	with open("name.pdf","wb") as f:
 		f.write(img2pdf.convert('test.jpg'), rotation=img2pdf.Rotation.ifvalid)
@@ -305,3 +308,14 @@ Tesseract might not do a lossless conversion. For example it converts CMYK
 input to RGB and removes the alpha channel from images with transparency. For
 multipage TIFF or animated GIF, it will only convert the first frame.
 
+Comparison to econvert from ExactImage
+--------------------------------------
+
+Like pdflatex and podofoimg2pf, econvert is able to embed JPEG images into PDF
+directly without re-encoding but when given other file formats, it stores them
+just using flate compressen, which unnecessarily increases the filesize.
+Furthermore, it throws an error with CMYK TIF input. It also doesn't store CMYK
+jpeg files as CMYK but converts them to RGB, so it's not lossless. When trying
+to feed it 16bit files, it errors out with Unhandled bps/spp combination. It
+also seems to choose JPEG encoding when using it on some file types (like
+palette images) making it again not lossless for that input as well.

appveyor.yml

@@ -26,7 +26,8 @@ build: off
 
 after_test:
   - "%PYTHON%\\python.exe setup.py bdist_wheel"
-  - "%PYTHON%\\python.exe -m PyInstaller --clean --onefile --noconsole src/img2pdf.py"
+  - "%PYTHON%\\python.exe -m PyInstaller --clean --onefile --console --nowindowed --name img2pdf src/img2pdf.py"
+  #- "%PYTHON%\\python.exe -m PyInstaller --clean --onefile --noconsole --windowed --name img2pdf_windowed src/img2pdf.py"
 
 artifacts:
   - path: dist\*

setup.py

@@ -1,7 +1,7 @@
 import sys
 from setuptools import setup
 
-VERSION = "0.4.3"
+VERSION = "0.5.1"
 
 INSTALL_REQUIRES = (
     "Pillow",

src/img2pdf.py

@@ -22,12 +22,22 @@ import sys
 import os
 import zlib
 import argparse
-from PIL import Image, TiffImagePlugin
+from PIL import Image, TiffImagePlugin, GifImagePlugin, ImageCms
+
+if hasattr(GifImagePlugin, "LoadingStrategy"):
+    # Pillow 9.0.0 started emitting all frames but the first as RGB instead of
+    # P to make sure that more than 256 colors can be represented. But palette
+    # images compress far better than RGB images in PDF so we instruct Pillow
+    # to only emit RGB frames if the palette differs and return P otherwise.
+    # This works since Pillow 9.1.0.
+    GifImagePlugin.LOADING_STRATEGY = (
+        GifImagePlugin.LoadingStrategy.RGB_AFTER_DIFFERENT_PALETTE_ONLY
+    )
 
 # TiffImagePlugin.DEBUG = True
 from PIL.ExifTags import TAGS
-from datetime import datetime
+from datetime import datetime, timezone
-from jp2 import parsejp2
+import jp2
 from enum import Enum
 from io import BytesIO
 import logging
@@ -35,6 +45,8 @@ import struct
 import platform
 import hashlib
 from itertools import chain
+import re
+import io
 
 logger = logging.getLogger(__name__)
 
@@ -50,7 +62,7 @@ try:
 except ImportError:
     have_pikepdf = False
 
-__version__ = "0.4.3"
+__version__ = "0.5.1"
 default_dpi = 96.0
 papersizes = {
     "letter": "8.5inx11in",
@@ -115,11 +127,16 @@ PageOrientation = Enum("PageOrientation", "portrait landscape")
 
 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")
 
-PageLayout = Enum("PageLayout", "single onecolumn twocolumnright twocolumnleft twopageright twopageleft")
+PageLayout = Enum(
+    "PageLayout",
+    "single onecolumn twocolumnright twocolumnleft twopageright twopageleft",
+)
 
 Magnification = Enum("Magnification", "fit fith fitbh")
 
@@ -417,6 +434,28 @@ class ExifOrientationError(Exception):
     pass
 
 
+# temporary change the attribute of an object using a context manager
+class temp_attr:
+    def __init__(self, obj, field, value):
+        self.obj = obj
+        self.field = field
+        self.value = value
+
+    def __enter__(self):
+        self.exists = False
+        if hasattr(self.obj, self.field):
+            self.exists = True
+            self.old_value = getattr(self.obj, self.field)
+        logger.debug(f"setting {self.obj}.{self.field} = {self.value}")
+        setattr(self.obj, self.field, self.value)
+
+    def __exit__(self, exctype, excinst, exctb):
+        if self.exists:
+            setattr(self.obj, self.field, self.old_value)
+        else:
+            delattr(self.obj, self.field)
+
+
 # without pdfrw this function is a no-op
 def my_convert_load(string):
     return string
@@ -683,7 +722,7 @@ class pdfdoc(object):
             self.writer.docinfo = PdfDict(indirect=True)
 
         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"]:
             v = locals()[k.lower()]
@@ -693,7 +732,7 @@ class pdfdoc(object):
                 v = PdfString.encode(v)
             self.writer.docinfo[getattr(PdfName, k)] = v
 
-        now = datetime.now()
+        now = datetime.now().astimezone()
         for k in ["CreationDate", "ModDate"]:
             v = locals()[k.lower()]
             if v is None and nodate:
@@ -713,7 +752,7 @@ class pdfdoc(object):
                 )
 
         def datetime_to_xmpdate(dt):
-            return dt.strftime("%Y-%m-%dT%H:%M:%SZ")
+            return dt.astimezone(tz=timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
 
         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'>
@@ -788,8 +827,10 @@ class pdfdoc(object):
         artborder=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:
@@ -813,7 +854,13 @@ class pdfdoc(object):
         if color == Colorspace["1"] or color == Colorspace.L or color == Colorspace.LA:
             colorspace = PdfName.DeviceGray
         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"]:
             colorspace = PdfName.DeviceCMYK
         elif color == Colorspace.P:
@@ -884,7 +931,8 @@ class pdfdoc(object):
         image[PdfName.Filter] = ofilter
         image[PdfName.Width] = imgwidthpx
         image[PdfName.Height] = imgheightpx
-        image[PdfName.ColorSpace] = colorspace
+        if colorspace is not None:
+            image[PdfName.ColorSpace] = colorspace
         image[PdfName.BitsPerComponent] = depth
 
         smask = None
@@ -1134,9 +1182,17 @@ class pdfdoc(object):
                 [initial_page, PdfName.XYZ, NullObject, NullObject, 0]
             )
 
-        # the /OpenAction array must contain the page as an indirect object
+        # The /OpenAction array must contain the page as an indirect object.
+        # This changed some time after 4.2.0 and on or before 5.0.0 and current
+        # versions require to use .obj or otherwise we get:
+        #   TypeError: Can't convert ObjectHelper (or subclass) to Object
+        #   implicitly. Use .obj to get access the underlying object.
+        # See https://github.com/pikepdf/pikepdf/issues/313 for details.
         if self.engine == Engine.pikepdf:
-            initial_page = self.writer.make_indirect(initial_page)
+            if isinstance(initial_page, pikepdf.Page):
+                initial_page = self.writer.make_indirect(initial_page.obj)
+            else:
+                initial_page = self.writer.make_indirect(initial_page)
 
         if self.magnification == Magnification.fit:
             catalog[PdfName.OpenAction] = PdfArray([initial_page, PdfName.Fit])
@@ -1213,8 +1269,11 @@ class pdfdoc(object):
 
         # now write out the PDF
         if self.engine == Engine.pikepdf:
+            kwargs = {}
+            if pikepdf.__version__ >= "6.2.0":
+                kwargs["deterministic_id"] = True
             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:
             self.writer.trailer.Info = self.writer.docinfo
@@ -1242,7 +1301,7 @@ def get_imgmetadata(
     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
         # handle JPEG2000 files
-        imgwidthpx, imgheightpx, ics, hdpi, vdpi = parsejp2(rawdata)
+        imgwidthpx, imgheightpx, ics, hdpi, vdpi, channels, bpp = jp2.parse(rawdata)
 
         if hdpi is None:
             hdpi = default_dpi
@@ -1252,7 +1311,19 @@ def get_imgmetadata(
     else:
         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
         # not be an integer but a float. To make the behaviour of
         # img2pdf the same between python2 and python3, we convert that
@@ -1262,7 +1333,7 @@ def get_imgmetadata(
         ics = imgdata.mode
 
     # 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
     ):
         # Must check the IHDR chunk for the bit depth, because PIL would lossily
@@ -1272,6 +1343,10 @@ def get_imgmetadata(
             if depth > 8:
                 logger.warning("Image with transparency and a bit depth of %d." % depth)
                 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(
                     "Refusing to work with multiple >8bit channels."
                 )
@@ -1382,6 +1457,53 @@ def get_imgmetadata(
     iccp = None
     if "icc_profile" in imgdata.info:
         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 = %dpx x %dpx", imgwidthpx, imgheightpx)
 
@@ -1438,27 +1560,29 @@ def transcode_monochrome(imgdata):
     # into putting everything into a single strip. Thanks to Andrew Murray for
     # the hack.
     #
-    # This can be dropped once this gets merged:
+    # Since version 8.4.0 Pillow allows us to modify the strip size explicitly
-    # https://github.com/python-pillow/Pillow/pull/5744
+    tmp_strip_size = (imgdata.size[0] + 7) // 8 * imgdata.size[1]
-    pillow__getitem__ = TiffImagePlugin.ImageFileDirectory_v2.__getitem__
+    if hasattr(TiffImagePlugin, "STRIP_SIZE"):
+        # we are using Pillow 8.4.0 or later
+        with temp_attr(TiffImagePlugin, "STRIP_SIZE", tmp_strip_size):
+            im.save(newimgio, format="TIFF", compression="group4")
+    else:
+        # only needed for Pillow 8.3.x but works for versions before that as
+        # well
+        pillow__getitem__ = TiffImagePlugin.ImageFileDirectory_v2.__getitem__
 
-    def __getitem__(self, tag):
+        def __getitem__(self, tag):
-        overrides = {
+            overrides = {
-            TiffImagePlugin.ROWSPERSTRIP: imgdata.size[1],
+                TiffImagePlugin.ROWSPERSTRIP: imgdata.size[1],
-            TiffImagePlugin.STRIPBYTECOUNTS: [
+                TiffImagePlugin.STRIPBYTECOUNTS: [tmp_strip_size],
-                (imgdata.size[0] + 7) // 8 * imgdata.size[1]
+                TiffImagePlugin.STRIPOFFSETS: [0],
-            ],
+            }
-            TiffImagePlugin.STRIPOFFSETS: [0],
+            return overrides.get(tag, pillow__getitem__(self, tag))
-        }
-        return overrides.get(tag, pillow__getitem__(self, tag))
 
-    # use try/finally to make sure that __getitem__ is reset even if save()
+        with temp_attr(
-    # raises an exception
+            TiffImagePlugin.ImageFileDirectory_v2, "__getitem__", __getitem__
-    try:
+        ):
-        TiffImagePlugin.ImageFileDirectory_v2.__getitem__ = __getitem__
+            im.save(newimgio, format="TIFF", compression="group4")
-        im.save(newimgio, format="TIFF", compression="group4")
-    finally:
-        TiffImagePlugin.ImageFileDirectory_v2.__getitem__ = pillow__getitem__
 
     # Open new image in memory
     newimgio.seek(0)
@@ -1488,7 +1612,204 @@ def parse_png(rawdata):
     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.seek(0)
     imgdata = None
@@ -1496,13 +1817,19 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
         imgdata = Image.open(im)
     except IOError as e:
         # 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(
                 "cannot read input image (not jpeg2000). "
                 "PIL: error reading image: %s" % e
             )
-        # image is jpeg2000
-        imgformat = ImageFormat.JPEG2000
     else:
         logger.debug("PIL format = %s", imgdata.format)
         imgformat = None
@@ -1536,10 +1863,13 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
             raise JpegColorspaceError("jpeg can't be monochrome")
         if color == Colorspace["P"]:
             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")
         logger.debug("read_images() embeds a JPEG")
         cleanup()
+        depth = 8
+        if imgformat == ImageFormat.JPEG2000:
+            *_, depth = jp2.parse(rawdata)
         return [
             (
                 color,
@@ -1551,7 +1881,7 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
                 imgheightpx,
                 [],
                 False,
-                8,
+                depth,
                 rotation,
                 iccp,
             )
@@ -1568,6 +1898,77 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
     if imgformat == ImageFormat.MPO:
         result = []
         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(
             imgdata._MpoImageFile__mpoffsets, imgdata.mpinfo[0xB002]
         ):
@@ -1665,6 +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
     # supports multiple frames (like TIFF or GIF), so we need a loop to
     # iterate through all frames of the image.
@@ -1830,7 +2234,16 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
                 )
             )
         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
                 or color == Colorspace.LA
                 or color == Colorspace.PA
@@ -1844,25 +2257,21 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
                     newcolor = color
                     l, a = newimg.split()
                     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:
                     newcolor = Colorspace.RGBA
                     r, g, b, a = newimg.convert(mode="RGBA").split()
                     newimg = Image.merge("RGB", (r, g, b))
 
-                smaskidat, _, _ = to_png_data(a)
+                smaskidat, *_ = to_png_data(a)
                 logger.warning(
-                    "Image contains an alpha channel which will be stored "
+                    "Image contains an alpha channel. Computing a separate "
-                    "as a separate soft mask (/SMask) image 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:
                 newcolor = color
                 smaskidat = None
@@ -2204,7 +2613,6 @@ def find_scale(pagewidth, pageheight):
 # as a binary string representing the image content or as filenames to the
 # images.
 def convert(*images, **kwargs):
-
     _default_kwargs = dict(
         engine=None,
         title=None,
@@ -2234,6 +2642,7 @@ def convert(*images, **kwargs):
         artborder=None,
         pdfa=None,
         rotation=None,
+        include_thumbnails=False,
     )
     for kwname, default in _default_kwargs.items():
         if kwname not in kwargs:
@@ -2277,11 +2686,16 @@ def convert(*images, **kwargs):
     for img in images:
         # img is allowed to be a path, a binary string representing image data
         # 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)):
-                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
             # it as a file name
             try:
@@ -2299,6 +2713,10 @@ def convert(*images, **kwargs):
                 rawdata = f.read()
                 f.close()
 
+        # md5 = hashlib.md5(rawdata).hexdigest()
+        # with open("./testdata/" + md5, "wb") as f:
+        #    f.write(rawdata)
+
         for (
             color,
             ndpi,
@@ -2317,6 +2735,7 @@ def convert(*images, **kwargs):
             kwargs["colorspace"],
             kwargs["first_frame_only"],
             kwargs["rotation"],
+            kwargs["include_thumbnails"],
         ):
             pagewidth, pageheight, imgwidthpdf, imgheightpdf = kwargs["layout_fun"](
                 imgwidthpx, imgheightpx, ndpi
@@ -2692,7 +3111,7 @@ def valid_date(string):
     else:
         try:
             return parser.parse(string)
-        except TypeError:
+        except:
             pass
     # as a last resort, try the local date utility
     try:
@@ -2705,7 +3124,7 @@ def valid_date(string):
         except subprocess.CalledProcessError:
             pass
         else:
-            return datetime.utcfromtimestamp(int(utime))
+            return datetime.fromtimestamp(int(utime))
     raise argparse.ArgumentTypeError("cannot parse date: %s" % string)
 
 
@@ -3407,7 +3826,35 @@ def gui():
     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 = ""
     for k, v in sorted(papersizes.items()):
         rendered_papersizes += "    %-8s %s\n" % (papernames[k], v)
@@ -3448,7 +3895,9 @@ Paper sizes:
   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
   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
 
@@ -3515,7 +3964,7 @@ Examples:
   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.
 
-    $ img2pdf --output out.pdf --pagesize A4^T --border 2cm:2.5cm *.jpg
+    $ img2pdf --output out.pdf --pagesize "A4^T" --border 2cm:2.5cm *.jpg
 
   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.
@@ -3650,6 +4099,17 @@ RGB.""",
         "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(
         "--pillow-limit-break",
         action="store_true",
@@ -3661,14 +4121,29 @@ RGB.""",
         % 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(
         title="Image and page size and layout arguments",
@@ -3957,8 +4432,11 @@ and left/right, respectively. It is not possible to specify asymmetric borders.
         action="store_true",
         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:
         logging.basicConfig(level=logging.DEBUG)
@@ -3982,7 +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:
         # if no positional arguments were supplied, read a single image from
         # 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:
             images = [sys.stdin.buffer.read()]
         except KeyboardInterrupt:
@@ -4043,6 +4525,7 @@ and left/right, respectively. It is not possible to specify asymmetric borders.
             artborder=args.art_border,
             pdfa=args.pdfa,
             rotation=args.rotation,
+            include_thumbnails=args.include_thumbnails,
         )
     except Exception as e:
         logger.error("error: " + str(e))

src/jp2.py

@@ -37,9 +37,8 @@ def getBox(data, byteStart, noBytes):
 
 
 def parse_ihdr(data):
-    height = struct.unpack(">I", data[0:4])[0]
+    height, width, channels, bpp = struct.unpack(">IIHB", data[:11])
-    width = struct.unpack(">I", data[4:8])[0]
+    return width, height, channels, bpp + 1
-    return width, height
 
 
 def parse_colr(data):
@@ -59,8 +58,8 @@ def parse_colr(data):
 
 def parse_resc(data):
     hnum, hden, vnum, vden, hexp, vexp = struct.unpack(">HHHHBB", data)
-    hdpi = ((hnum / hden) * (10 ** hexp) * 100) / 2.54
+    hdpi = ((hnum / hden) * (10**hexp) * 100) / 2.54
-    vdpi = ((vnum / vden) * (10 ** vexp) * 100) / 2.54
+    vdpi = ((vnum / vden) * (10**vexp) * 100) / 2.54
     return hdpi, vdpi
 
 
@@ -85,13 +84,13 @@ def parse_jp2h(data):
     while byteStart < noBytes and boxLengthValue != 0:
         boxLengthValue, boxType, byteEnd, boxContents = getBox(data, byteStart, noBytes)
         if boxType == b"ihdr":
-            width, height = parse_ihdr(boxContents)
+            width, height, channels, bpp = parse_ihdr(boxContents)
         elif boxType == b"colr":
             colorspace = parse_colr(boxContents)
         elif boxType == b"res ":
             hdpi, vdpi = parse_res(boxContents)
         byteStart = byteEnd
-    return (width, height, colorspace, hdpi, vdpi)
+    return (width, height, colorspace, hdpi, vdpi, channels, bpp)
 
 
 def parsejp2(data):
@@ -102,7 +101,9 @@ def parsejp2(data):
     while byteStart < noBytes and boxLengthValue != 0:
         boxLengthValue, boxType, byteEnd, boxContents = getBox(data, byteStart, noBytes)
         if boxType == b"jp2h":
-            width, height, colorspace, hdpi, vdpi = parse_jp2h(boxContents)
+            width, height, colorspace, hdpi, vdpi, channels, bpp = parse_jp2h(
+                boxContents
+            )
             break
         byteStart = byteEnd
     if not width:
@@ -112,13 +113,41 @@ def parsejp2(data):
     if not colorspace:
         raise Exception("no colorspace in jp2 header")
     # retrieving the dpi is optional so we do not error out if not present
-    return (width, height, colorspace, hdpi, vdpi)
+    return (width, height, colorspace, hdpi, vdpi, channels, bpp)
+
+
+def parsej2k(data):
+    lsiz, rsiz, xsiz, ysiz, xosiz, yosiz, _, _, _, _, csiz = struct.unpack(
+        ">HHIIIIIIIIH", data[4:42]
+    )
+    ssiz = [None] * csiz
+    xrsiz = [None] * csiz
+    yrsiz = [None] * csiz
+    for i in range(csiz):
+        ssiz[i], xrsiz[i], yrsiz[i] = struct.unpack(
+            "BBB", data[42 + 3 * i : 42 + 3 * (i + 1)]
+        )
+    assert ssiz == [7, 7, 7]
+    return xsiz - xosiz, ysiz - yosiz, None, None, None, csiz, 8
+
+
+def parse(data):
+    if data[:4] == b"\xff\x4f\xff\x51":
+        return parsej2k(data)
+    else:
+        return parsejp2(data)
 
 
 if __name__ == "__main__":
     import sys
 
-    width, height, colorspace = parsejp2(open(sys.argv[1]).read())
+    width, height, colorspace, hdpi, vdpi, channels, bpp = parse(
-    sys.stdout.write("width = %d" % width)
+        open(sys.argv[1], "rb").read()
-    sys.stdout.write("height = %d" % height)
+    )
-    sys.stdout.write("colorspace = %s" % colorspace)
+    print("width = %d" % width)
+    print("height = %d" % height)
+    print("colorspace = %s" % colorspace)
+    print("hdpi = %s" % hdpi)
+    print("vdpi = %s" % vdpi)
+    print("channels = %s" % channels)
+    print("bpp = %s" % bpp)