From 09064e8e70a0549147db172eb5b122e50479fd36 Mon Sep 17 00:00:00 2001
From: Johannes Schauer Marin Rodrigues <josch@mister-muffin.de>
Date: Tue, 8 Aug 2023 07:40:38 +0200
Subject: [PATCH] jp2: rudimentary support for raw jpeg2000 without jp2 boxes

---
 src/img2pdf.py |  8 ++++----
 src/jp2.py     | 46 ++++++++++++++++++++++++++++++++++++++--------
 2 files changed, 42 insertions(+), 12 deletions(-)

diff --git a/src/img2pdf.py b/src/img2pdf.py
index 904b647..68e94f4 100755
--- a/src/img2pdf.py
+++ b/src/img2pdf.py
@@ -37,7 +37,7 @@ if hasattr(GifImagePlugin, "LoadingStrategy"):
 # TiffImagePlugin.DEBUG = True
 from PIL.ExifTags import TAGS
 from datetime import datetime, timezone
-from jp2 import parsejp2
+import jp2
 from enum import Enum
 from io import BytesIO
 import logging
@@ -1301,7 +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, channels, bpp = parsejp2(rawdata)
+        imgwidthpx, imgheightpx, ics, hdpi, vdpi, channels, bpp = jp2.parse(rawdata)
 
         if hdpi is None:
             hdpi = default_dpi
@@ -1843,7 +1843,7 @@ def read_images(
         cleanup()
         depth = 8
         if imgformat == ImageFormat.JPEG2000:
-            _, _, _, _, _, _, depth = parsejp2(rawdata)
+            *_, depth = jp2.parse(rawdata)
         return [
             (
                 color,
@@ -2241,7 +2241,7 @@ def read_images(
                     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. Computing a separate "
                     "soft mask (/SMask) image to store transparency in PDF."
diff --git a/src/jp2.py b/src/jp2.py
index d305d38..44d3e21 100644
--- a/src/jp2.py
+++ b/src/jp2.py
@@ -38,7 +38,7 @@ def getBox(data, byteStart, noBytes):
 
 def parse_ihdr(data):
     height, width, channels, bpp = struct.unpack(">IIHB", data[:11])
-    return width, height, channels, bpp+1
+    return width, height, channels, bpp + 1
 
 
 def parse_colr(data):
@@ -58,8 +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
-    vdpi = ((vnum / vden) * (10 ** vexp) * 100) / 2.54
+    hdpi = ((hnum / hden) * (10**hexp) * 100) / 2.54
+    vdpi = ((vnum / vden) * (10**vexp) * 100) / 2.54
     return hdpi, vdpi
 
 
@@ -101,7 +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, channels, bpp = parse_jp2h(boxContents)
+            width, height, colorspace, hdpi, vdpi, channels, bpp = parse_jp2h(
+                boxContents
+            )
             break
         byteStart = byteEnd
     if not width:
@@ -114,10 +116,38 @@ def parsejp2(data):
     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())
-    sys.stdout.write("width = %d" % width)
-    sys.stdout.write("height = %d" % height)
-    sys.stdout.write("colorspace = %s" % colorspace)
+    width, height, colorspace, hdpi, vdpi, channels, bpp = parse(
+        open(sys.argv[1], "rb").read()
+    )
+    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)