LibPDF+LibGfx: Pass jbig2-filtered data to JBIG2ImageDecoderPlugin

Except for /JBIG2Globals, which we bail out on for now. In my 1000
files, 13 use JBIG2, and of those, 2 use JBIG2Globals (0000372.pdf e.g.
page 11 and 0000857.pdf e.g. page 1), and only one (the latter) of the
two uses the same JBIG2Globals stream for more than a single image.

JBIG2ImageDecoderPlugin cannot decode the data yet, so no behavior
change, but with `#define JBIG2_DEBUG 1` at the top of that file,
it now prints segment header info for PDFs containing JBIG2 data :^)

Userland/Libraries/LibGfx/ImageFormats/JBIG2Loader.cpp

@@ -180,7 +180,10 @@ static ErrorOr<SegmentHeader> decode_segment_header(SeekableStream& stream)
 
 static ErrorOr<void> decode_segment_headers(JBIG2LoadingContext& context)
 {
-    FixedMemoryStream stream(context.data.slice(sizeof(id_string) + sizeof(u8) + (context.number_of_pages.has_value() ? sizeof(u32) : 0)));
+    ReadonlyBytes data = context.data;
+    if (context.organization != Organization::Embedded)
+        data = data.slice(sizeof(id_string) + sizeof(u8) + (context.number_of_pages.has_value() ? sizeof(u32) : 0));
+    FixedMemoryStream stream(data);
     while (!stream.is_eof()) {
         auto segment_header = TRY(decode_segment_header(stream));
         if (context.organization != Organization::RandomAccess) {
@@ -232,4 +235,12 @@ ErrorOr<ImageFrameDescriptor> JBIG2ImageDecoderPlugin::frame(size_t index, Optio
     return Error::from_string_literal("JBIG2ImageDecoderPlugin: Draw the rest of the owl");
 }
 
+ErrorOr<ByteBuffer> JBIG2ImageDecoderPlugin::decode_embedded(ReadonlyBytes data)
+{
+    auto plugin = TRY(adopt_nonnull_own_or_enomem(new (nothrow) JBIG2ImageDecoderPlugin(data)));
+    plugin->m_context->organization = Organization::Embedded;
+    TRY(decode_segment_headers(*plugin->m_context));
+    return Error::from_string_literal("JBIG2ImageDecoderPlugin: Cannot decode embedded JBIG2 yet");
+}
+
 }

Userland/Libraries/LibGfx/ImageFormats/JBIG2Loader.h

@@ -25,6 +25,8 @@ public:
 
     virtual ErrorOr<ImageFrameDescriptor> frame(size_t index, Optional<IntSize> ideal_size = {}) override;
 
+    static ErrorOr<ByteBuffer> decode_embedded(ReadonlyBytes);
+
 private:
     JBIG2ImageDecoderPlugin(ReadonlyBytes);
 

Userland/Libraries/LibPDF/CommonNames.h

@@ -112,6 +112,7 @@
     X(Info)                       \
     X(Intent)                     \
     X(JBIG2Decode)                \
+    X(JBIG2Globals)               \
     X(JPXDecode)                  \
     X(K)                          \
     X(Keywords)                   \

Userland/Libraries/LibPDF/Filter.cpp

@@ -10,6 +10,7 @@
 #include <LibCompress/LZWDecoder.h>
 #include <LibCompress/PackBitsDecoder.h>
 #include <LibGfx/ImageFormats/CCITTDecoder.h>
+#include <LibGfx/ImageFormats/JBIG2Loader.h>
 #include <LibGfx/ImageFormats/JPEGLoader.h>
 #include <LibGfx/ImageFormats/PNGLoader.h>
 #include <LibPDF/CommonNames.h>
@@ -33,7 +34,7 @@ PDFErrorOr<ByteBuffer> Filter::decode(ReadonlyBytes bytes, DeprecatedFlyString c
     if (encoding_type == CommonNames::CCITTFaxDecode)
         return decode_ccitt(bytes, decode_parms);
     if (encoding_type == CommonNames::JBIG2Decode)
-        return decode_jbig2(bytes);
+        return decode_jbig2(bytes, decode_parms);
     if (encoding_type == CommonNames::DCTDecode)
         return decode_dct(bytes);
     if (encoding_type == CommonNames::JPXDecode)
@@ -333,9 +334,15 @@ PDFErrorOr<ByteBuffer> Filter::decode_ccitt(ReadonlyBytes bytes, RefPtr<DictObje
     return decoded;
 }
 
-PDFErrorOr<ByteBuffer> Filter::decode_jbig2(ReadonlyBytes)
+PDFErrorOr<ByteBuffer> Filter::decode_jbig2(ReadonlyBytes bytes, RefPtr<DictObject> decode_parms)
 {
-    return Error::rendering_unsupported_error("JBIG2 Filter is unsupported");
+    // 3.3.6 JBIG2Decode Filter
+    if (decode_parms) {
+        if (decode_parms->contains(CommonNames::JBIG2Globals))
+            return Error::rendering_unsupported_error("JBIG2Globals is not yet supported");
+    }
+
+    return TRY(Gfx::JBIG2ImageDecoderPlugin::decode_embedded(bytes));
 }
 
 PDFErrorOr<ByteBuffer> Filter::decode_dct(ReadonlyBytes bytes)

Userland/Libraries/LibPDF/Filter.h

@@ -26,7 +26,7 @@ private:
     static PDFErrorOr<ByteBuffer> decode_flate(ReadonlyBytes bytes, RefPtr<DictObject> decode_parms);
     static PDFErrorOr<ByteBuffer> decode_run_length(ReadonlyBytes bytes);
     static PDFErrorOr<ByteBuffer> decode_ccitt(ReadonlyBytes bytes, RefPtr<DictObject> decode_parms);
-    static PDFErrorOr<ByteBuffer> decode_jbig2(ReadonlyBytes bytes);
+    static PDFErrorOr<ByteBuffer> decode_jbig2(ReadonlyBytes bytes, RefPtr<DictObject> decode_parms);
     static PDFErrorOr<ByteBuffer> decode_dct(ReadonlyBytes bytes);
     static PDFErrorOr<ByteBuffer> decode_jpx(ReadonlyBytes bytes);
     static PDFErrorOr<ByteBuffer> decode_crypt(ReadonlyBytes bytes);