From 8e3f096bc5805c58c9049c18d20f0b89cbf72db6 Mon Sep 17 00:00:00 2001
From: Scott O'Neil <v-scottoneil@microsoft.com>
Date: Wed, 24 Jan 2024 14:26:04 -0800
Subject: [PATCH 1/2] yar

---
 src/Sarif/ZipArchiveArtifact.cs               | 25 +++++++++++++------
 .../ArtifactProviderTests.cs                  | 16 +++++++-----
 2 files changed, 27 insertions(+), 14 deletions(-)

diff --git a/src/Sarif/ZipArchiveArtifact.cs b/src/Sarif/ZipArchiveArtifact.cs
index 26b9da28e..fb39a4d54 100644
--- a/src/Sarif/ZipArchiveArtifact.cs
+++ b/src/Sarif/ZipArchiveArtifact.cs
@@ -34,8 +34,8 @@ public bool IsBinary
         {
             get
             {
-                string extension = Path.GetExtension(Uri.ToString());
-                return this.binaryExtensions.Contains(extension);
+                GetArtifactData();
+                return this.bytes != null;
             }
         }
 
@@ -91,8 +91,20 @@ public byte[] Bytes
                 {
                     if (this.contents == null && this.bytes == null)
                     {
-                        string extension = Path.GetExtension(Uri.ToString());
-                        if (this.binaryExtensions.Contains(extension))
+                        const int PeekWindowBytes = 1024;
+                        var peekable = new PeekableStream(this.Stream, PeekWindowBytes);
+
+                        byte[] header = new byte[PeekWindowBytes];
+                        int length = this.Stream.Read(header, 0, header.Length);
+                        bool isText = FileEncoding.IsTextualData(header, 0, length);
+
+                        peekable.Rewind();
+
+                        if (isText)
+                        {
+                            this.contents = new StreamReader(Stream).ReadToEnd();
+                        }
+                        else
                         {
                             // The underlying System.IO.Compression.DeflateStream throws on reads to get_Length.
                             using var ms = new MemoryStream((int)SizeInBytes.Value);
@@ -113,12 +125,9 @@ public byte[] Bytes
                                 ms.Read(this.bytes, 0, this.bytes.Length);
                             }
                         }
-                        else
-                        {
-                            this.contents = new StreamReader(Stream).ReadToEnd();
-                        }
                     }
                 }
+
                 this.entry = null;
             }
 
diff --git a/src/Test.UnitTests.Sarif/ArtifactProviderTests.cs b/src/Test.UnitTests.Sarif/ArtifactProviderTests.cs
index 0916c47fc..b8faa0bd5 100644
--- a/src/Test.UnitTests.Sarif/ArtifactProviderTests.cs
+++ b/src/Test.UnitTests.Sarif/ArtifactProviderTests.cs
@@ -6,7 +6,6 @@
 using System.IO;
 using System.IO.Compression;
 using System.Linq;
-using System.Text;
 
 using FluentAssertions;
 
@@ -32,14 +31,19 @@ public void MultithreadedZipArchiveArtifactProvider_RetrieveSizeInBytesBeforeRet
         [Fact]
         public void MultithreadedZipArchiveArtifactProvider_RetrieveSizeInBytesBeforeRetrievingBytes()
         {
-            string entryContents = $"{Guid.NewGuid()}";
+            string filePath = this.GetType().Assembly.Location;
+            using FileStream reader = File.OpenRead(filePath);
+
+            int headerSize = 1024;
+            byte[] data = new byte[headerSize];
+            reader.Read(data, 0, data.Length);
 
-            // Note that even thought we populate an archive with text contents, the extension
-            // of the archive entry indicates a binary file. So we expect binary data on expansion.
-            ZipArchive zip = CreateZipArchiveWithTextContents("test.exe", entryContents);
+            // Note that even thought we populate an archive with binary contents, the extension
+            // of the archive entry indicates a text file. We still expect binary data on expansion.
+            ZipArchive zip = CreateZipArchiveWithBinaryContents("test.txt", data);
             var artifactProvider = new MultithreadedZipArchiveArtifactProvider(zip, FileSystem.Instance);
 
-            ValidateBinaryContents(artifactProvider.Artifacts, Encoding.UTF8.GetBytes(entryContents));
+            ValidateBinaryContents(artifactProvider.Artifacts, data);
         }
 
         [Fact]

From c4de01e54d81d139f9233b9be2da221b9aa53d8f Mon Sep 17 00:00:00 2001
From: Scott O'Neil <v-scottoneil@microsoft.com>
Date: Wed, 31 Jan 2024 16:23:06 -0800
Subject: [PATCH 2/2] release notes

---
 ReleaseHistory.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/ReleaseHistory.md b/ReleaseHistory.md
index 49815dd3f..be6b1c9e1 100644
--- a/ReleaseHistory.md
+++ b/ReleaseHistory.md
@@ -8,6 +8,7 @@
 * BUG: Update `Stack.Create` method to populate missing `PhysicalLocation` instances when stack frames reference relative file paths.
 * BUG: Fix `UnsupportedOperationException` in `ZipArchiveArtifact`.
 * NEW: Add `IsBinary` property to `IEnumeratedArtifact` and implement the property in `ZipArchiveArtifact`.
+* NEW: Switch to content-based `IsBinary` categorization for `ZipArchiveArtifact`s.
 * PRF: Change default `max-file-size-in-kb` parameter to 10 megabytes.
 * PRF: Add support for efficiently peeking into non-seekable streams for binary/text categorization.
 * NEW: Add a new `--timeout-in-seconds` parameter to `AnalyzeOptionsBase`, which will override the `TimeoutInMilliseconds` property in `AnalyzeContextBase`.