Convert creation/modification dates to UTC (fixes #155)

Ensure that timezones are correctly interpreted in the input by calling
`.astimezone()` as appropriate on datetime objects, and store the
resulting date fields as UTC.

One could argue that datetimes in the local timezone be stored in the
PDF, but then the date string handling becomes more complicated; the PDF
and XMP date specs both use the `Z` suffix to indicate UTC time, but
other +/- offsets require different syntax between the two specs.

src/img2pdf.py

@@ -22,7 +22,7 @@ import sys
 import os
 import zlib
 import argparse
-from PIL import Image, TiffImagePlugin, GifImagePlugin
+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
@@ -36,7 +36,7 @@ if hasattr(GifImagePlugin, "LoadingStrategy"):
 
 # TiffImagePlugin.DEBUG = True
 from PIL.ExifTags import TAGS
-from datetime import datetime
+from datetime import datetime, timezone
 from jp2 import parsejp2
 from enum import Enum
 from io import BytesIO
@@ -46,6 +46,7 @@ import platform
 import hashlib
 from itertools import chain
 import re
+import io
 
 logger = logging.getLogger(__name__)
 
@@ -721,7 +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()]
@@ -731,7 +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:
@@ -751,7 +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'>
@@ -1431,6 +1432,21 @@ def get_imgmetadata(
     iccp = None
     if "icc_profile" in imgdata.info:
         iccp = imgdata.info.get("icc_profile")
+    # GIMP saves bilevel tiff images with an RGB ICC profile which is useless
+    # 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:
+        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"
+        ):
+            logger.warning("Ignoring RGB ICC profile in bilevel TIFF produced by GIMP.")
+            logger.warning("https://gitlab.gnome.org/GNOME/gimp/-/issues/3438")
+            iccp = None
 
     logger.debug("width x height = %dpx x %dpx", imgwidthpx, imgheightpx)
 
@@ -2085,7 +2101,16 @@ 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
@@ -2099,6 +2124,11 @@ 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()
@@ -2109,15 +2139,6 @@ def read_images(rawdata, colorspace, first_frame_only=False, rot=None):
                     "Image contains an alpha channel. Computing a separate "
                     "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
@@ -3711,7 +3732,9 @@ 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
 
@@ -3778,7 +3801,7 @@ 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.
@@ -4248,7 +4271,7 @@ and left/right, respectively. It is not possible to specify asymmetric borders.
         print(
             "Reading image from standard input...\n"
             "Re-run with -h or --help for usage information.",
-            file=sys.stderr
+            file=sys.stderr,
         )
         try:
             images = [sys.stdin.buffer.read()]

src/img2pdf_test.py

@@ -4276,9 +4276,10 @@ def gif_transparent_pdf(tmp_path_factory, gif_transparent_img, request):
             == b"q\n45.0000 0 0 45.0000 0.0000 0.0000 cm\n/Im0 Do\nQ"
         )
         assert p.pages[0].Resources.XObject.Im0.BitsPerComponent == 8
-        assert p.pages[0].Resources.XObject.Im0.ColorSpace == "/DeviceRGB"
+        assert p.pages[0].Resources.XObject.Im0.ColorSpace[0] == "/Indexed"
+        assert p.pages[0].Resources.XObject.Im0.ColorSpace[1] == "/DeviceRGB"
         assert p.pages[0].Resources.XObject.Im0.DecodeParms.BitsPerComponent == 8
-        assert p.pages[0].Resources.XObject.Im0.DecodeParms.Colors == 3
+        assert p.pages[0].Resources.XObject.Im0.DecodeParms.Colors == 1
         assert p.pages[0].Resources.XObject.Im0.DecodeParms.Predictor == 15
         assert p.pages[0].Resources.XObject.Im0.Filter == "/FlateDecode"
         assert p.pages[0].Resources.XObject.Im0.Height == 60