Skip to content

Add branching and specific SharpCompress calls for solid vs non-solid archives in order to extract solid archives properly. #375

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

Merged
mnadareski merged 6 commits into from
Jul 12, 2025
Merged

Add branching and specific SharpCompress calls for solid vs non-solid archives in order to extract solid archives properly. #375

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
ecd99b1
Add branching for solid vs non-solid archives in order to extract sol…
HeroponRikiBestest Jul 12, 2025
26c1e88
Change comments on sevenzip, reuse archive-level solid flag for rar
HeroponRikiBestest Jul 12, 2025
df38bf3
Fully simplify identifying if archive is solid.
HeroponRikiBestest Jul 12, 2025
eca101b
Finish implementing first round of feedback.
HeroponRikiBestest Jul 12, 2025
6460684
Fix second round of formatting issues.
HeroponRikiBestest Jul 12, 2025
c37dbc7
Final formatting fixes.
HeroponRikiBestest Jul 12, 2025
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
102 changes: 72 additions & 30 deletions BinaryObjectScanner/FileType/RAR.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
#if NET462_OR_GREATER || NETCOREAPP
using SharpCompress.Archives;
using SharpCompress.Archives.Rar;
using SharpCompress.Common;
using SharpCompress.Readers;
#endif

Expand Down Expand Up @@ -51,36 +52,11 @@ public bool Extract(Stream? stream, string file, string outDir, bool lookForHead
if (!rarFile.IsComplete)
return false;

foreach (var entry in rarFile.Entries)
{
try
{
// If the entry is a directory
if (entry.IsDirectory)
continue;

// If the entry has an invalid key
if (entry.Key == null)
continue;

// If we have a partial entry due to an incomplete multi-part archive, skip it
if (!entry.IsComplete)
continue;

string tempFile = Path.Combine(outDir, entry.Key);
var directoryName = Path.GetDirectoryName(tempFile);
if (directoryName != null && !Directory.Exists(directoryName))
Directory.CreateDirectory(directoryName);

entry.WriteToFile(tempFile);
}
catch (Exception ex)
{
if (includeDebug) Console.WriteLine(ex);
}
}
if (rarFile.IsSolid)
return ExtractSolid(rarFile, outDir, includeDebug);
else
return ExtractNonSolid(rarFile, outDir, includeDebug);

return true;
}
catch (Exception ex)
{
Expand All @@ -91,5 +67,71 @@ public bool Extract(Stream? stream, string file, string outDir, bool lookForHead
return false;
#endif
}

#if NET462_OR_GREATER || NETCOREAPP

/// <summary>
/// Extraction method for non-solid archives. This iterates over each entry in the archive to extract every
/// file individually, in order to extract all valid files from the archive.
/// </summary>
private bool ExtractNonSolid(RarArchive rarFile, string outDir, bool includeDebug)
{
foreach (var entry in rarFile.Entries)
{
try
{
// If the entry is a directory
if (entry.IsDirectory)
continue;

// If the entry has an invalid key
if (entry.Key == null)
continue;

// If we have a partial entry due to an incomplete multi-part archive, skip it
if (!entry.IsComplete)
continue;

string tempFile = Path.Combine(outDir, entry.Key);
var directoryName = Path.GetDirectoryName(tempFile);
if (directoryName != null && !Directory.Exists(directoryName))
Directory.CreateDirectory(directoryName);

entry.WriteToFile(tempFile);
}
catch (Exception ex)
{
if (includeDebug) Console.WriteLine(ex);
}
}
return true;
}

/// <summary>
/// Extraction method for solid archives. Uses ExtractAllEntries because extraction for solid archives must be
/// done sequentially, and files beyond a corrupted point in a solid archive will be unreadable anyways.
/// </summary>
private bool ExtractSolid(RarArchive rarFile, string outDir, bool includeDebug)
{
try
{
if (!Directory.Exists(outDir))
Directory.CreateDirectory(outDir);

rarFile.WriteToDirectory(outDir, new ExtractionOptions()
{
ExtractFullPath = true,
Overwrite = true,
});

}
catch (Exception ex)
{
if (includeDebug) Console.WriteLine(ex);
}

return true;
}
#endif
}
}
}
102 changes: 72 additions & 30 deletions BinaryObjectScanner/FileType/SevenZip.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
#if NET462_OR_GREATER || NETCOREAPP
using SharpCompress.Archives;
using SharpCompress.Archives.SevenZip;
using SharpCompress.Common;
using SharpCompress.Readers;
#endif

Expand Down Expand Up @@ -43,50 +44,91 @@ public bool Extract(Stream? stream, string file, string outDir, bool lookForHead
{
var readerOptions = new ReaderOptions() { LookForHeader = lookForHeader };
var sevenZip = SevenZipArchive.Open(stream, readerOptions);

// Try to read the file path if no entries are found
if (sevenZip.Entries.Count == 0 && !string.IsNullOrEmpty(file) && File.Exists(file))
sevenZip = SevenZipArchive.Open(file, readerOptions);

foreach (var entry in sevenZip.Entries)
// Currently doesn't flag solid 7z archives with only 1 solid block as solid, but practically speaking
// this is not much of a concern.
if (sevenZip.IsSolid)
return ExtractSolid(sevenZip, outDir, includeDebug);
else
return ExtractNonSolid(sevenZip, outDir, includeDebug);

}
catch (Exception ex)
{
if (includeDebug) Console.WriteLine(ex);
return false;
}
#else
return false;
#endif
}

#if NET462_OR_GREATER || NETCOREAPP
/// <summary>
/// Extraction method for non-solid archives. This iterates over each entry in the archive to extract every
/// file individually, in order to extract all valid files from the archive.
/// </summary>
private bool ExtractNonSolid(SevenZipArchive sevenZip, string outDir, bool includeDebug)
{
foreach (var entry in sevenZip.Entries)
{
try
{
try
{
// If the entry is a directory
if (entry.IsDirectory)
continue;
// If the entry is a directory
if (entry.IsDirectory)
continue;

// If the entry has an invalid key
if (entry.Key == null)
continue;
// If the entry has an invalid key
if (entry.Key == null)
continue;

// If we have a partial entry due to an incomplete multi-part archive, skip it
if (!entry.IsComplete)
continue;
// If we have a partial entry due to an incomplete multi-part archive, skip it
if (!entry.IsComplete)
continue;

string tempFile = Path.Combine(outDir, entry.Key);
var directoryName = Path.GetDirectoryName(tempFile);
if (directoryName != null && !Directory.Exists(directoryName))
Directory.CreateDirectory(directoryName);
string tempFile = Path.Combine(outDir, entry.Key);
var directoryName = Path.GetDirectoryName(tempFile);
if (directoryName != null && !Directory.Exists(directoryName))
Directory.CreateDirectory(directoryName);

entry.WriteToFile(tempFile);
}
catch (Exception ex)
{
if (includeDebug) Console.WriteLine(ex);
}
entry.WriteToFile(tempFile);
}
catch (Exception ex)
{
if (includeDebug) Console.WriteLine(ex);
}

return true;
}
return true;
}

/// <summary>
/// Extraction method for solid archives. Uses ExtractAllEntries because extraction for solid archives must be
/// done sequentially, and files beyond a corrupted point in a solid archive will be unreadable anyways.
/// </summary>
private bool ExtractSolid(SevenZipArchive sevenZip, string outDir, bool includeDebug)
{
try
{
if (!Directory.Exists(outDir))
Directory.CreateDirectory(outDir);

sevenZip.WriteToDirectory(outDir, new ExtractionOptions()
{
ExtractFullPath = true,
Overwrite = true,
});

}
catch (Exception ex)
{
if (includeDebug) Console.WriteLine(ex);
return false;
}
#else
return false;
#endif

return true;
}
#endif
}
}
}
Loading