From eedf73e73eb0be2a2e2cc54e21e8235b47016006 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <jim@purplerock.ca>
Date: Thu, 21 Jul 2016 16:33:26 -0700
Subject: [PATCH] Add test cases for CCITT G4

---
 src/tests/__init__.py         |  43 +++++++++++++++++++++++++++++++++-
 src/tests/input/mono.png      | Bin 0 -> 444 bytes
 src/tests/output/mono.png.pdf | Bin 0 -> 1005 bytes
 3 files changed, 42 insertions(+), 1 deletion(-)
 create mode 100644 src/tests/input/mono.png
 create mode 100644 src/tests/output/mono.png.pdf

diff --git a/src/tests/__init__.py b/src/tests/__init__.py
index b668054..6b468aa 100644
--- a/src/tests/__init__.py
+++ b/src/tests/__init__.py
@@ -4,6 +4,8 @@ import os
 import img2pdf
 import zlib
 from PIL import Image
+from io import BytesIO
+import struct
 
 HERE = os.path.dirname(__file__)
 
@@ -396,6 +398,28 @@ layout_test_cases = [
 ]
 
 
+def tiff_header_for_ccitt(width, height, img_size, ccitt_group=4):
+    # Quick and dirty TIFF header builder from
+    # https://stackoverflow.com/questions/2641770/extracting-image-from-pdf-with-ccittfaxdecode-filter
+    tiff_header_struct = '<' + '2s' + 'h' + 'l' + 'h' + 'hhll' * 8 + 'h'
+    return struct.pack(
+        tiff_header_struct,
+        b'II',  # Byte order indication: Little indian
+        42,  # Version number (always 42)
+        8,  # Offset to first IFD
+        8,  # Number of tags in IFD
+        256, 4, 1, width,  # ImageWidth, LONG, 1, width
+        257, 4, 1, height,  # ImageLength, LONG, 1, lenght
+        258, 3, 1, 1,  # BitsPerSample, SHORT, 1, 1
+        259, 3, 1, ccitt_group,  # Compression, SHORT, 1, 4 = CCITT Group 4
+        262, 3, 1, 1,  # Threshholding, SHORT, 1, 0 = WhiteIsZero
+        273, 4, 1, struct.calcsize(tiff_header_struct),  # StripOffsets, LONG, 1, len of header
+        278, 4, 1, height,  # RowsPerStrip, LONG, 1, lenght
+        279, 4, 1, img_size,  # StripByteCounts, LONG, 1, size of image
+        0  # last IFD
+        )
+
+
 def test_suite():
     class TestImg2Pdf(unittest.TestCase):
         pass
@@ -485,7 +509,8 @@ def test_suite():
             # test if the filter is valid:
             self.assertIn(
                 imgprops.Filter, [[PdfName.DCTDecode], [PdfName.JPXDecode],
-                                  [PdfName.FlateDecode]])
+                                  [PdfName.FlateDecode],
+                                  [PdfName.CCITTFaxDecode]])
             # test if the colorspace is valid
             self.assertIn(
                 imgprops.ColorSpace, [PdfName.DeviceGray, PdfName.DeviceRGB,
@@ -500,6 +525,22 @@ def test_suite():
                 self.assertEqual(
                     x.Root.Pages.Kids[0].Resources.XObject.Im0.stream,
                     convert_load(orig_imgdata))
+            elif imgprops.Filter == [PdfName.CCITTFaxDecode]:
+                tiff_header = tiff_header_for_ccitt(
+                    int(imgprops.Width), int(imgprops.Height),
+                    int(imgprops.Length), 4)
+                imgio = BytesIO()
+                imgio.write(tiff_header)
+                imgio.write(convert_store(
+                    x.Root.Pages.Kids[0].Resources.XObject.Im0.stream))
+                imgio.seek(0)
+                im = Image.open(imgio)
+                self.assertEqual(im.tobytes(), orig_img.tobytes())
+                try:
+                    im.close()
+                except AttributeError:
+                    pass
+
             elif imgprops.Filter == [PdfName.FlateDecode]:
                 # otherwise, the data is flate encoded and has to be equal to
                 # the pixel data of the input image
diff --git a/src/tests/input/mono.png b/src/tests/input/mono.png
new file mode 100644
index 0000000000000000000000000000000000000000..59b17ad025a5f769412b50a731b70e11a44a5956
GIT binary patch
literal 444
zcmeAS@N?(olHy`uVBq!ia0vp^#XxMp2qYM|zEpGqDVB6cUq=Rpjs4tz5?O(Kg=CK)
zUj~LMH3o);76yi2K%s^g3=E|P3=FRl7#OT(FffQ0%-I!a1C(G&@^*J&V7%KUyadSO
zEbxc~8qX~Z!i)^F=12eq*-JcqUD+Qn3NTq|EGf)=02J!-ba4#PIDhuiL0%?B0oDuq
zA8v5>ULfMNQADHn2%Ao#_kqd93N_Q$1lon0PP|;--gw4f!5rTIuU6Z~Fid|qW7@p9
zyoMd~wjIuyCw{5v>zA^eM?x!~rEhy_$K7lkR{W}K^Nz%+zxKv&bv!F_HFXnf>EBiF
zYZo==U;cgc`9}Nj4IR1vFJ1Kc_wxR`>&zR|e6GA(wG<Q%k|nMYCC>S|xv6<249-QV
zi6yBi3gww484B*6z5(HleBwYwsvt!vKq;$aunGnv14A=i14CUyvk(I#D^m+A69ZiX
m3o8SId1|{|Q8eV{r(~v8;@0rKn)xSC1B0ilpUXO@geCy>)t2r6

literal 0
HcmV?d00001

diff --git a/src/tests/output/mono.png.pdf b/src/tests/output/mono.png.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..67ed8a843f06ffb77f12fba0a4a05dcd61906227
GIT binary patch
literal 1005
zcmZ{j&ubGw6vsUjg~5V{o;=ux5^0cTe<a(rQey4KXsESmQm|MAH@lN`Yj!8jPBitB
zi--p=9=!MB**~Frk*bJ-|A1Ig5WEybi?-W0o202!-(`mP>pSl=Gl^m@KdPnDB=KqE
z-3Ow93aqkBCMFb%Q(Jf}$k~FzNba1jYGbOYYnox08SQ!!lo{s!FGv8CB4=*Xp&Uj$
zzos|bDyS(vr6sdjLIYQ-=zX=KU85nS(NO|rex*S{v20=2S*@QgqrJniW*|TVW!iH?
zSj@<}8@<A~SHDaK_sRl60}+DJ5t^Z{XHT&fEUM_h(I9gc+Z1h%S-sPgXvmt}p&<^1
zToz_4%hVBaTkusFlby0?`_=p6Qm89_g$6aT1etM+h63sO<TgRgl!}IFDvEdae=Uwr
zVx=4-bCO)Qw#!iJcLk<A5f&-8nBQQ5902)Ptj>73VLJ#kNAGwJy~OPmxp$aLaZq25
zwTQz^)otfiA=E(drlim6O+N@@D9SX9Vy_ar8{!$WSwxig>Vk4vs#sQGem-xvIxR7F
znR>M)ftjFmXVz35lyb8o;)^Z#c-b9X@}2a6D%U(0`5=)#pwp|ZWE5>4*?6+$zBzV(
z^;P=U?DmP_^~#qQlNZ)2(Q5SV{ErCjcl+m`M?>$Awr{>3-hSAA`(UB{`S{$9b+!F5
z`W~&xlxXYl#?xr9{q^PA<AF2V&o+m4PM(UM4;-32NVUajm8f76c{d${F~dk3P#xU!
z;d6;Y5bXIh{U1IP-?_AXdAe>M@THA|d6~?3KTmMmt0Q#zI}1UT;r+(nrNo#3`IqqP
Yl)ZZt%ow1}MLdQ%u8~CI;%uJm0#KJS{r~^~

literal 0
HcmV?d00001