Skip to content

feature: FileByteType #162

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
maxbreuker wants to merge 5 commits into
base: main
Choose a base branch
from
Open

feature: FileByteType #162

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
981c973
feat: FileByteType validation mode
maxbreuker Feb 18, 2026
67eaea1
feat: relax PDF EOF validation via FileByteType
maxbreuker Feb 18, 2026
dd5dbbd
test: adjust Validator unit tests for FileByteType
maxbreuker Feb 18, 2026
6a702fb
test: add PDF unit tests for strict vs relaxed validation
maxbreuker Feb 18, 2026
02834a7
docs: update README and bump package version
maxbreuker Feb 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
65 changes: 64 additions & 1 deletion MagicBytesValidator.Tests/Models/FileByteFilterMatches.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,69 @@ public void Should_not_match_pdf()
Assert.False(pdf.Matches(pdfTestData));
}

[Fact]
public void Should_match_pdf_with_trailing_bytes_in_default_mode()
{
var pdf = new Pdf();

var pdfTestData = "%PDF-\n%%EOF\nTRAILING"u8.ToArray();

Assert.True(pdf.Matches(pdfTestData, FileByteType.Lazy));
}

[Fact]
public void Should_not_match_pdf_with_trailing_bytes_in_strict_mode()
{
var pdf = new Pdf();

var pdfTestData = "%PDF-\n%%EOF\nTRAILING"u8.ToArray();

Assert.False(pdf.Matches(pdfTestData, FileByteType.Strict));
}

[Fact]
public void Should_not_match_pdf_when_eof_is_not_within_last_1024_bytes_in_default_mode()
{
var pdf = new Pdf();

var prefix = "%PDF-\n"u8.ToArray();
var eof = "%%EOF\n"u8.ToArray();

// put EOF early, then add >1024 bytes afterwards so it falls outside the last 1024 bytes
var trailing = new byte[1100];
for (var i = 0; i < trailing.Length; i++)
{
trailing[i] = (byte)'A';
}

var pdfTestData = prefix
.Concat(eof)
.Concat(trailing)
.ToArray();

Assert.False(pdf.Matches(pdfTestData, FileByteType.Lazy));
}

[Fact]
public void Should_match_pdf_when_eof_marker_is_present_in_default_mode()
{
var pdf = new Pdf();

var pdfTestData = "%PDF-\n...%%EOF...TAIL"u8.ToArray();

Assert.True(pdf.Matches(pdfTestData, FileByteType.Lazy));
}

[Fact]
public void Should_match_pdf_in_strict_mode_when_eof_is_at_end()
{
var pdf = new Pdf();

var pdfTestData = "%PDF-\n%%EOF"u8.ToArray();

Assert.True(pdf.Matches(pdfTestData, FileByteType.Strict));
}

[Fact]
public void Should_match_ppt()
{
Expand Down Expand Up @@ -144,4 +207,4 @@ public void Should_match_heic()

Assert.True(heic.Matches(testStream));
}
}
}
2 changes: 1 addition & 1 deletion MagicBytesValidator.Tests/ValidatorIsValidAsync.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,4 +72,4 @@ public async Task Should_fail_incorrect_magicByte_sequence()
// Assert
Assert.False(invalidMagicByte);
}
}
}
43 changes: 25 additions & 18 deletions MagicBytesValidator/Formats/Pdf.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,21 +4,28 @@ namespace MagicBytesValidator.Formats;
/// <see href="https://www.garykessler.net/library/file_sigs.html"/>
public class Pdf : FileByteFilter
{
public Pdf() : base(
["application/pdf"],
["pdf"]
)
{
StartsWith([0x25, 0x50, 0x44, 0x46, 0x2D])
.EndsWithAnyOf(
[
[0x25, 0x25, 0x45, 0x4F, 0x46],
[0x0A, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0A],
[0x0A, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0A, 0x20],
[0x0D, 0x0A, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0D, 0x0A],
[0x0D, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0D], /* looks strange, but garykessler says so. */
[0x0D, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0A],
[0x0A, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0D, 0x0A],
]);
}
}
public Pdf() : base(
["application/pdf"],
["pdf"]
)
{
StartsWith([0x25, 0x50, 0x44, 0x46, 0x2D]); // %PDF-

EndsWithAnyOf(
[
[0x25, 0x25, 0x45, 0x4F, 0x46],
[0x0A, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0A],
[0x0A, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0A, 0x20],
[0x0D, 0x0A, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0D, 0x0A],
[0x0D, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0D], // garykessler variant
[0x0D, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0A],
[0x0A, 0x25, 0x25, 0x45, 0x4F, 0x46, 0x0D, 0x0A]
], FileByteType.Strict);

TailContains(
1024,
[0x25, 0x25, 0x45, 0x4F, 0x46], // %%EOF
FileByteType.Lazy
);
}
}
4 changes: 2 additions & 2 deletions MagicBytesValidator/MagicBytesValidator.csproj
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
<PackageId>MagicBytesValidator</PackageId>
<Title>traperto GmbH</Title>
<Description>Validate files based on mime types, file extensions and magic byte sequences.</Description>
<Version>2.1.6</Version>
<Version>2.2.0</Version>
<Authors>Members of traperto GmbH</Authors>
<PackageProjectUrl>https://github.com/Traperto/magic-bytes-validator/blob/main/README.md</PackageProjectUrl>
<PackageTags>mime mimetype mimetypes magic magicbyte magicbytes extension extensions file
Expand All @@ -17,7 +17,7 @@
<Company>traperto GmbH</Company>

<PackageLicenseExpression>MIT</PackageLicenseExpression>

<GeneratePackageOnBuild>true</GeneratePackageOnBuild>
</PropertyGroup>

Expand Down
Loading