From 88c52a15237e30bd3d8be6d5221a10da589ca4db Mon Sep 17 00:00:00 2001
From: Calixte Denizet <calixte.denizet@gmail.com>
Date: Fri, 5 Jun 2026 16:31:11 +0200
Subject: [PATCH] Strip the JBIG2 file header from JBIG2Decode streams

It's rendering correctly in Acrobat and PdfBox.
---
 src/core/jbig2_stream.js        |  24 ++++++++++++++++++++++--
 test/pdfs/.gitignore            |   1 +
 test/pdfs/jbig2_file_header.pdf | Bin 0 -> 774 bytes
 test/test_manifest.json         |   7 +++++++
 4 files changed, 30 insertions(+), 2 deletions(-)
 create mode 100644 test/pdfs/jbig2_file_header.pdf

diff --git a/src/core/jbig2_stream.js b/src/core/jbig2_stream.js
index e94c1edb1..3b16f8674 100644
--- a/src/core/jbig2_stream.js
+++ b/src/core/jbig2_stream.js
@@ -51,17 +51,37 @@ class Jbig2Stream extends DecodeStream {
     return true;
   }
 
+  // The JBIG2 file header is defined in ITU-T T.88, Annex D.4:
+  // https://www.itu.int/rec/T-REC-T.88
+  static stripFileHeader(bytes) {
+    if (
+      bytes.length >= 9 &&
+      bytes[0] === 0x97 &&
+      bytes[1] === 0x4a &&
+      bytes[2] === 0x42 &&
+      bytes[3] === 0x32 &&
+      bytes[4] === 0x0d &&
+      bytes[5] === 0x0a &&
+      bytes[6] === 0x1a &&
+      bytes[7] === 0x0a
+    ) {
+      const headerLength = (bytes[8] & 2) === 0 ? 13 : 9;
+      return bytes.subarray(headerLength);
+    }
+    return bytes;
+  }
+
   async decodeImage(bytes, length, _decoderOptions) {
     if (this.eof) {
       return this.buffer;
     }
-    bytes ||= this.bytes;
+    bytes = Jbig2Stream.stripFileHeader(bytes || this.bytes);
 
     let globals = null;
     if (this.params instanceof Dict) {
       const globalsStream = this.params.get("JBIG2Globals");
       if (globalsStream instanceof BaseStream) {
-        globals = globalsStream.getBytes();
+        globals = Jbig2Stream.stripFileHeader(globalsStream.getBytes());
       }
     }
     this.buffer = await JBig2CCITTFaxImage.instance.decode(
diff --git a/test/pdfs/.gitignore b/test/pdfs/.gitignore
index 9db3f6b26..8bb7acc70 100644
--- a/test/pdfs/.gitignore
+++ b/test/pdfs/.gitignore
@@ -930,3 +930,4 @@
 !90ms_rksj_h_sample.pdf
 !issue21346.pdf
 !cidfont_cmap_overflow.pdf
+!jbig2_file_header.pdf
diff --git a/test/pdfs/jbig2_file_header.pdf b/test/pdfs/jbig2_file_header.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..99fff7640ef03a356e7adc28c91130a2b9933799
GIT binary patch
literal 774
zcmZWn&2G~`5O!NmD<P1$aVUEU7X<5duvJTy4@sJmQq+(Xfm9WBV^33;*c;Xx)N-K`
z9FRD2Kz#sCaO6EWaN>jnkAX;--I$~bV~sujc7DE{nM%9Syv^_Ur1JCE*KdSVm&)ET
zSzl+nr$b<Mp~XP<SzGj>pdOxfqKH7A7$@_4(b+n&`)N|_RgLF9tIJWYDW8WJd@%%*
zD?m4!ojrgg6*YOX=b|h3)@T^)vknw;q+%$L*OQ&zF~l0JR_4;Xrci`}wQ`MV3hGax
ze=Lp1#gb(_>yCQbT(Onm-Pq$a(MP5py9a6iNMl*dIFPD46fv*{yhvl%RN|D?QeCt`
z)nzu6x#7)OGaYD9Y^&DV^coP$1lTs@eUq@d7Da_tATsh{tL9xM*U6IOI7S`Uey*W)
zhI)W%#hy7!H|=SJ&>89hYAGv|Ka=J0c>L+<#+U8yyO&n4ykC7id1arg&(7h^+mDaV
zf8YA??#ARZhAi`GH8fYMQ`5AjBvp>m^sH=B$=nNP#Gl(an0bT&zFZn-)Hc5%>BIkX
zohUdYE)9q~6B_t_)u)GahH<QDgywTBz}yQM=eUsznCBsj1<dE+9Mejq15jp(yXi}y
a0qaPKb3*23dkZa;wj})!_r9{R)BFqF)X}W~

literal 0
HcmV?d00001

diff --git a/test/test_manifest.json b/test/test_manifest.json
index 2824af541..e64216b03 100644
--- a/test/test_manifest.json
+++ b/test/test_manifest.json
@@ -14357,5 +14357,12 @@
     "md5": "8ce57e23b42b3232b0f2060bdd2c8b2a",
     "rounds": 1,
     "type": "eq"
+  },
+  {
+    "id": "jbig2_file_header",
+    "file": "pdfs/jbig2_file_header.pdf",
+    "md5": "702be2459f9bdbe93338ab3a584babc4",
+    "rounds": 1,
+    "type": "eq"
   }
 ]