From 781991b6bf935aef80ae7a6ba3931b2bd62be0ab Mon Sep 17 00:00:00 2001
From: EliotJones <elioty@hotmail.co.uk>
Date: Sun, 6 Jul 2025 17:56:59 -0500
Subject: [PATCH] fix #670 by ignoring duplicate endstream definitions

when parsing a stream object with multiple endstream tokens
the last parsed token was selected instead of the actual stream
token so instead we just skip all following tokens if the first
is a stream and the following tokens are `endstream` operators
only
---
 src/UglyToad.PdfPig/Tokenization/Scanner/PdfTokenScanner.cs | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/src/UglyToad.PdfPig/Tokenization/Scanner/PdfTokenScanner.cs b/src/UglyToad.PdfPig/Tokenization/Scanner/PdfTokenScanner.cs
index 4bfd802d..e9e408fd 100644
--- a/src/UglyToad.PdfPig/Tokenization/Scanner/PdfTokenScanner.cs
+++ b/src/UglyToad.PdfPig/Tokenization/Scanner/PdfTokenScanner.cs
@@ -268,6 +268,12 @@
                     {
                         token = trimmedDuplicatedEndTokens[0];
                     }
+                    else if (readTokens[0] is StreamToken str
+                             && readTokens.Skip(1).All(x => x is OperatorToken op && op.Equals(OperatorToken.EndStream)))
+                    {
+                        // If a stream token is followed by "endstream" operator tokens just skip the following duplicated tokens.
+                        token = str;
+                    }
                     else
                     {
                         token = readTokens[readTokens.Count - 1];