use resolution (DPI) from EXIF first, if not found or invalid, then use info from Pillow image

Closes: #181

CHANGES.rst

@@ -2,6 +2,22 @@
 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)
 ------------------
 

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 ...

setup.py

@@ -1,7 +1,7 @@
 import sys
 from setuptools import setup
 
-VERSION = "0.4.4"
+VERSION = "0.5.1"
 
 INSTALL_REQUIRES = (
     "Pillow",

src/img2pdf.py

@@ -22,7 +22,7 @@ import sys
 import os
 import zlib
 import argparse
-from PIL import Image, TiffImagePlugin, GifImagePlugin, ImageCms
+from PIL import Image, TiffImagePlugin, GifImagePlugin, ImageCms, ExifTags
 
 if hasattr(GifImagePlugin, "LoadingStrategy"):
     # Pillow 9.0.0 started emitting all frames but the first as RGB instead of
@@ -62,7 +62,7 @@ try:
 except ImportError:
     have_pikepdf = False
 
-__version__ = "0.4.4"
+__version__ = "0.5.1"
 default_dpi = 96.0
 papersizes = {
     "letter": "8.5inx11in",
@@ -1298,6 +1298,7 @@ class pdfdoc(object):
 def get_imgmetadata(
     imgdata, imgformat, default_dpi, colorspace, rawdata=None, rotreq=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
         # handle JPEG2000 files
@@ -1311,7 +1312,37 @@ def get_imgmetadata(
     else:
         imgwidthpx, imgheightpx = imgdata.size
 
-        ndpi = imgdata.info.get("dpi", (default_dpi, default_dpi))
+        ndpi = None
+        # For JPEG images with both EXIF tags and JFIF tags, Pillow seems reading image resolution from JFIF.
+        # However, "Preview" on Mac and "Photos" on Windows read the resolution from EXIF.
+        # We try to read the value from EXIF first
+        exif = imgdata.getexif()
+        if exif:
+            exif_res_unit = exif.get(ExifTags.Base.ResolutionUnit)
+            exif_x_res = exif.get(ExifTags.Base.XResolution)
+            exif_y_res = exif.get(ExifTags.Base.YResolution)
+            if exif_x_res and exif_y_res:
+                if (exif_res_unit == 3): # cm
+                    ndpi = (exif_x_res * 2.54, exif_y_res * 2.54)
+                else:
+                    ndpi = (exif_x_res, exif_y_res)
+
+        # if no DPI from EXIF, get it from `info`
+        if ndpi is None:
+            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
@@ -1489,10 +1520,8 @@ def get_imgmetadata(
         with io.BytesIO(iccp) as f:
             prf = ImageCms.ImageCmsProfile(f)
 
-        if prf.profile.xcolor_space not in ('GRAY'):
+        if prf.profile.xcolor_space not in ("GRAY"):
-            logger.warning(
+            logger.warning("Ignoring non-GRAY ICC profile in Grayscale JPG")
-                "Ignoring non-GRAY ICC profile in Grayscale JPG"
-            )
             iccp = None
 
     logger.debug("width x height = %dpx x %dpx", imgwidthpx, imgheightpx)
@@ -3816,13 +3845,30 @@ def gui():
     app.mainloop()
 
 
+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 os.path.exists(profile):
+        if not os.path.exists(profile):
+            continue
+        if not file_is_icc(profile):
+            continue
         return profile
     return "/usr/share/color/icc/sRGB.icc"
 
@@ -4094,11 +4140,23 @@ RGB.""",
         % Image.MAX_IMAGE_PIXELS,
     )
 
+    if sys.platform == "win32":
+        # on Windows, there are no default paths to search for an ICC profile
+        # so make the argument required instead of optional
+        outargs.add_argument(
+            "--pdfa",
+            type=validate_icc,
+            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 "