Add support for JPEG2000 image encoding

CHANGELOG.md

@@ -10,6 +10,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ### Fixed
 - Hande decompression error due to CRC checksum error ([#637](https://github.com/pdfminer/pdfminer.six/pull/637))
+- Add handling of JPXDecode filter to enable extraction of images for some pdfs ([#645](https://github.com/pdfminer/pdfminer.six/pull/645))
 
 ## [20211012]
 

pdfminer/image.py

@@ -9,7 +9,8 @@ from .layout import LTImage
 from .pdfcolor import LITERAL_DEVICE_CMYK
 from .pdfcolor import LITERAL_DEVICE_GRAY
 from .pdfcolor import LITERAL_DEVICE_RGB
-from .pdftypes import LITERALS_DCT_DECODE, LITERALS_JBIG2_DECODE
+from .pdftypes import LITERALS_DCT_DECODE, LITERALS_JBIG2_DECODE, \
+    LITERALS_JPX_DECODE
 
 
 def align32(x: int) -> int:
@@ -99,6 +100,16 @@ class ImageWriter:
                 i.save(fp, 'JPEG')
             else:
                 fp.write(raw_data)
+        elif ext == '.jp2':
+            # if we just write the raw data, most image programs
+            # that I have tried cannot open the file. However,
+            # open and saving with PIL produces a file that
+            # seems to be easily opened by other programs
+            from PIL import Image
+            raw_data = image.stream.get_rawdata()
+            ifp = BytesIO(raw_data)
+            i = Image.open(ifp)
+            i.save(fp, 'JPEG2000')
         elif is_jbig2:
             input_stream = BytesIO()
             input_stream.write(image.stream.get_data())
@@ -156,6 +167,8 @@ class ImageWriter:
         filters = image.stream.get_filters()
         if len(filters) == 1 and filters[0][0] in LITERALS_DCT_DECODE:
             ext = '.jpg'
+        elif len(filters) == 1 and filters[0][0] in LITERALS_JPX_DECODE:
+            ext = '.jp2'
         elif is_jbig2:
             ext = '.jb2'
         elif (image.bits == 1 or

pdfminer/pdftypes.py

@@ -34,6 +34,7 @@ LITERALS_RUNLENGTH_DECODE = (LIT('RunLengthDecode'), LIT('RL'))
 LITERALS_CCITTFAX_DECODE = (LIT('CCITTFaxDecode'), LIT('CCF'))
 LITERALS_DCT_DECODE = (LIT('DCTDecode'), LIT('DCT'))
 LITERALS_JBIG2_DECODE = (LIT('JBIG2Decode'),)
+LITERALS_JPX_DECODE = (LIT('JPXDecode'),)
 
 
 if sys.version_info >= (3, 8):
@@ -358,6 +359,8 @@ class PDFStream(PDFObject):
                 pass
             elif f in LITERALS_JBIG2_DECODE:
                 pass
+            elif f in LITERALS_JPX_DECODE:
+                pass
             elif f == LITERAL_CRYPT:
                 # not yet..
                 raise PDFNotImplementedError('/Crypt filter is unsupported')