Fix SevenZipReader to iterate entries as contiguous streams

Co-authored-by: adamhathcock <527620+adamhathcock@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-01-27 17:01:18 +00:00
parent 72eaf66f05
commit db2f5c9cb9
3 changed files with 79 additions and 11 deletions

View File

@@ -216,6 +216,9 @@ public class SevenZipArchive : AbstractArchive<SevenZipArchiveEntry, SevenZipVol
{
private readonly SevenZipArchive _archive;
private SevenZipEntry? _currentEntry;
private Stream? _currentFolderStream;
private CFolder? _currentFolder;
private int _currentFolderIndex = -1;
internal SevenZipReader(ReaderOptions readerOptions, SevenZipArchive archive)
: base(readerOptions, ArchiveType.SevenZip) => this._archive = archive;
@@ -231,9 +234,10 @@ public class SevenZipArchive : AbstractArchive<SevenZipArchiveEntry, SevenZipVol
_currentEntry = dir;
yield return dir;
}
// For non-directory entries, yield them without creating shared streams
// Each call to GetEntryStream() will create a fresh decompression stream
// to avoid state corruption issues with async operations
// For solid archives (entries in the same folder share a compressed stream),
// we must iterate entries sequentially and maintain the folder stream state
// across entries in the same folder to avoid recreating the decompression
// stream for each file, which breaks contiguous streaming.
foreach (var entry in entries.Where(x => !x.IsDirectory))
{
_currentEntry = entry;
@@ -243,19 +247,47 @@ public class SevenZipArchive : AbstractArchive<SevenZipArchiveEntry, SevenZipVol
protected override EntryStream GetEntryStream()
{
// Create a fresh decompression stream for each file (no state sharing).
// However, the LZMA decoder has bugs in its async implementation that cause
// state corruption even on fresh streams. The SyncOnlyStream wrapper
// works around these bugs by forcing async operations to use sync equivalents.
//
// TODO: Fix the LZMA decoder async bugs (in LzmaStream, Decoder, OutWindow)
// so this wrapper is no longer necessary.
var entry = _currentEntry.NotNull("currentEntry is not null");
if (entry.IsDirectory)
{
return CreateEntryStream(Stream.Null);
}
return CreateEntryStream(new SyncOnlyStream(entry.FilePart.GetCompressedStream()));
var folder = entry.FilePart.Folder;
// Check if we're starting a new folder - dispose old folder stream if needed
if (folder != _currentFolder)
{
_currentFolderStream?.Dispose();
_currentFolderStream = null;
_currentFolder = folder;
_currentFolderIndex = _archive._database!._folders.IndexOf(folder!);
}
// Create the folder stream once per folder
if (_currentFolderStream is null)
{
_currentFolderStream = _archive._database!.GetFolderStream(
_archive.Volumes.Single().Stream,
folder!,
_archive._database.PasswordProvider
);
}
// Wrap with SyncOnlyStream to work around LZMA async bugs
// Return a ReadOnlySubStream that reads from the shared folder stream
return CreateEntryStream(
new SyncOnlyStream(
new ReadOnlySubStream(_currentFolderStream, entry.Size, leaveOpen: true)
)
);
}
public override void Dispose()
{
_currentFolderStream?.Dispose();
_currentFolderStream = null;
base.Dispose();
}
}

View File

@@ -251,4 +251,28 @@ public class SevenZipArchiveTests : ArchiveTests
);
Assert.False(nonSolidArchive.IsSolid);
}
[Fact]
public void SevenZipArchive_Solid_ExtractAllEntries_Contiguous()
{
// This test verifies that solid archives iterate entries as contiguous streams
// rather than recreating the decompression stream for each entry
var testArchive = Path.Combine(TEST_ARCHIVES_PATH, "7Zip.solid.7z");
using var archive = SevenZipArchive.Open(testArchive);
Assert.True(archive.IsSolid);
using var reader = archive.ExtractAllEntries();
while (reader.MoveToNextEntry())
{
if (!reader.Entry.IsDirectory)
{
reader.WriteEntryToDirectory(
SCRATCH_FILES_PATH,
new ExtractionOptions { ExtractFullPath = true, Overwrite = true }
);
}
}
VerifyFiles();
}
}

View File

@@ -29,6 +29,12 @@
"Microsoft.NETFramework.ReferenceAssemblies.net48": "1.0.3"
}
},
"Mono.Posix.NETStandard": {
"type": "Direct",
"requested": "[1.0.0, )",
"resolved": "1.0.0",
"contentHash": "vSN/L1uaVwKsiLa95bYu2SGkF0iY3xMblTfxc8alSziPuVfJpj3geVqHGAA75J7cZkMuKpFVikz82Lo6y6LLdA=="
},
"xunit": {
"type": "Direct",
"requested": "[2.9.3, )",
@@ -216,6 +222,12 @@
"Microsoft.NETFramework.ReferenceAssemblies.net461": "1.0.3"
}
},
"Mono.Posix.NETStandard": {
"type": "Direct",
"requested": "[1.0.0, )",
"resolved": "1.0.0",
"contentHash": "vSN/L1uaVwKsiLa95bYu2SGkF0iY3xMblTfxc8alSziPuVfJpj3geVqHGAA75J7cZkMuKpFVikz82Lo6y6LLdA=="
},
"xunit": {
"type": "Direct",
"requested": "[2.9.3, )",