TAR: added zstd, lzma (xz) and bzip3 support

src/plugins/tar/beta.txt

@@ -55,3 +55,7 @@ version 3.30: (2009.02.28) J.Patera
   -CDecompressFile::Rewind() did not update StreamPos -> CPIO (e_OldASCII)
    archives could not open
   -GZIP: files longer than 4 GB before compression complained about premature EOF
+
+version 3.40: (2021.11.12) Vilo
+  +LZMA: Added support for .XZ archives
+  +ZSTD: Added support for .ZST archives

src/plugins/tar/bzip/bunzip.cpp

@@ -103,7 +103,7 @@ CBZip::DecompressBlock(unsigned short needed)
       return FALSE;
     }
     BZStream->next_in = (char *)DataStart;
-    BZStream->avail_in = (unsigned int)(DataEnd - DataStart);
+    BZStream->avail_in = GetUnreadInputBufferSize();
     BZStream->next_out = (char *)ExtrEnd;
     BZStream->avail_out = BUFSIZE - (unsigned int)(ExtrEnd - Window);
     ret = BZ2_bzDecompress(BZStream);

src/plugins/tar/deb/deb.cpp

@@ -96,15 +96,16 @@ CDEBArchive::CDEBArchive(const char* fileName, CSalamanderForOperationsAbstract*
     pos += sizeof(ARBlock);
 
     // Open the fist subarchive
-    controlArchive = new CArchive(fileName, salamander, pos, CQuadWord(SubArchiveSize, 0));
-    if (!controlArchive->IsOk())
+    CArchive *archive = new CArchive(fileName, salamander, pos, CQuadWord(SubArchiveSize, 0));
+    if (!archive->IsOk())
     {
-        delete controlArchive;
-        controlArchive = NULL;
+        delete archive;
+        archive = NULL;
         return;
     }
     // We are happy if at least one subarchive was recognized
-    bOK = TRUE;
+    if (AssignArchive(ARBlock.FileName, archive))
+        bOK = TRUE;
 
     // Skip the subarchive and read the 3rd and last subarchive
     if (SubArchiveSize & 1)
@@ -127,12 +128,15 @@ CDEBArchive::CDEBArchive(const char* fileName, CSalamanderForOperationsAbstract*
         return;
     }
     sscanf(ARBlock.FileSize, "%u", &SubArchiveSize);
-    dataArchive = new CArchive(fileName, salamander, pos + sizeof(ARBlock), CQuadWord(0, 0));
-    if (!dataArchive->IsOk())
+    pos += sizeof(ARBlock);
+    archive = new CArchive(fileName, salamander, pos, CQuadWord(SubArchiveSize, 0));
+    if (!archive->IsOk())
     {
-        delete dataArchive;
-        dataArchive = NULL;
+        delete archive;
+        archive = NULL;
     }
+    if (AssignArchive(ARBlock.FileName, archive))
+        bOK = TRUE;
     CloseHandle(file);
 }
 
@@ -315,3 +319,21 @@ BOOL CDEBArchive::UnpackWholeArchive(const char* mask, const char* targetPath)
     }
     return ret;
 }
+
+BOOL CDEBArchive::AssignArchive(const char* archName, CArchive* archive)
+{
+    if (!controlArchive && !strncmp(archName, DEB_STREAM_NAME_CONTROL".", sizeof(DEB_STREAM_NAME_CONTROL".") - 1))
+    {
+        controlArchive = archive;
+        return TRUE;
+    }
+    else if (!dataArchive && !strncmp(archName, DEB_STREAM_NAME_DATA".", sizeof(DEB_STREAM_NAME_DATA".") - 1))
+    {
+        dataArchive = archive;
+        return TRUE;
+    }
+
+    // archiv se uz nebude pouzivat
+    delete archive;
+    return FALSE;
+}

src/plugins/tar/deb/deb.h

@@ -41,4 +41,7 @@ class CDEBArchive : public CArchiveAbstract
     BOOL UnpackWholeArchive(const char* mask, const char* targetPath);
 
     BOOL IsOk() { return bOK; };
+
+  private:
+    BOOL AssignArchive(const char *archName, CArchive *archive);
 };

src/plugins/tar/fileio.cpp

@@ -12,6 +12,8 @@
 #include "compress/compress.h"
 #include "rpm/rpm.h"
 #include "lzh/lzh.h"
+#include "lzma/unlzma.h"
+#include "zstd/unzstd.h"
 
 #include "tar.rh"
 #include "tar.rh2"
@@ -97,14 +99,26 @@ CDecompressFile::CreateInstance(LPCTSTR fileName, DWORD inputOffset, CQuadWord i
                 archive = new CBZip(fileName, file, buffer, inputOffset, read, inputSize);
                 if (archive != NULL && !archive->IsOk() && archive->GetErrorCode() == 0)
                 {
-                    // neni to compress, zkusime lzh
+                    // neni to bzip, zkusime lzh
                     delete archive;
                     archive = new CLZH(fileName, file, buffer, read);
                     if (archive != NULL && !archive->IsOk() && archive->GetErrorCode() == 0)
                     {
-                        // neni to kompresene, berem zakladni tridu
+                        // neni to lzh, zkusime lzma
                         delete archive;
-                        archive = new CDecompressFile(fileName, file, buffer, inputOffset, read, inputSize);
+                        archive = new CLZMa(fileName, file, buffer, inputOffset, read, inputSize);
+                        if (archive != NULL && !archive->IsOk() && archive->GetErrorCode() == 0)
+                        {
+                            // neni to lzma, zkusime zstd
+                            delete archive;
+                            archive = new CZStd(fileName, file, buffer, inputOffset, read, inputSize);
+                            if (archive != NULL && !archive->IsOk() && archive->GetErrorCode() == 0)
+                            {
+                                // neni to kompresene, berem zakladni tridu
+                                delete archive;
+                                archive = new CDecompressFile(fileName, file, buffer, inputOffset, read, inputSize);
+                            }
+                        }
                     }
                 }
             }
@@ -129,8 +143,9 @@ CDecompressFile::CreateInstance(LPCTSTR fileName, DWORD inputOffset, CQuadWord i
 }
 
 // class constructor
-CDecompressFile::CDecompressFile(const char* filename, HANDLE file, unsigned char* buffer, unsigned long start, unsigned long read, CQuadWord inputSize) : FileName(filename), File(file), Buffer(buffer), DataStart(buffer), DataEnd(buffer + read),
-                                                                                                                                                           OldName(NULL), Ok(TRUE), StreamPos(start, 0), ErrorCode(0), LastError(0), FreeBufAndFile(TRUE)
+CDecompressFile::CDecompressFile(const char* filename, HANDLE file, unsigned char* buffer, unsigned long start, unsigned long read, CQuadWord inputSize) :
+    FileName(filename), File(file), Buffer(buffer), DataStart(buffer), DataEnd(buffer + read),
+    OldName(NULL), Ok(TRUE), InputPos(0, 0), StreamPos(start, 0), ErrorCode(0), LastError(0), FreeBufAndFile(TRUE)
 {
     CALL_STACK_MESSAGE3("CDecompressFile::CDecompressFile(%s, , %u)", filename, read);
 
@@ -204,9 +219,9 @@ CDecompressFile::FReadBlock(unsigned int number)
     {
         DWORD read = (DWORD)(Buffer + BUFSIZE - DataEnd);
 
-        if (StreamPos.Value + read > InputSize.Value)
+        if (InputPos.Value + read > InputSize.Value)
         {
-            read = (DWORD)(InputSize.Value - StreamPos.Value);
+            read = (DWORD)(InputSize.Value - InputPos.Value);
         }
 
         if (!ReadFile(File, DataEnd, read, &read, NULL))
@@ -230,6 +245,7 @@ CDecompressFile::FReadBlock(unsigned int number)
     // upravime ukazatele
     DataStart += number;
     StreamPos += CQuadWord(number, 0);
+    InputPos = min(InputPos + CQuadWord(number, 0), InputSize);
     // a vratime vysledek
     return ret;
 }
@@ -274,6 +290,7 @@ CDecompressFile::FReadByte()
     }
     // upravime ukazatele
     ++StreamPos;
+    InputPos = min(++InputPos, InputSize);
     return *(DataStart++);
 }
 
@@ -313,6 +330,7 @@ void CDecompressFile::Rewind(unsigned short size)
     {
         DataStart -= size;
         StreamPos.Value -= size;
+        InputPos.Value -= size;
     }
     else
     {
@@ -347,7 +365,8 @@ void CDecompressFile::GetFileInfo(FILETIME& lastWrite, CQuadWord& fileSize, DWOR
 //  CZippedFile
 //
 
-CZippedFile::CZippedFile(const char* filename, HANDLE file, unsigned char* buffer, unsigned long start, unsigned long read, CQuadWord inputSize) : CDecompressFile(filename, file, buffer, start, read, inputSize), Window(NULL), ExtrStart(NULL), ExtrEnd(NULL)
+CZippedFile::CZippedFile(const char* filename, HANDLE file, unsigned char* buffer, unsigned long start, unsigned long read, CQuadWord inputSize) :
+    CDecompressFile(filename, file, buffer, start, read, inputSize), Window(NULL), ExtrStart(NULL), ExtrEnd(NULL)
 {
     // pokud neprosel konstruktor parenta, balime to rovnou
     if (!Ok)

src/plugins/tar/fileio.h

@@ -20,19 +20,23 @@ class CDecompressFile
     virtual BOOL BuggySize() { return FALSE; }
 
     // vraci, v jakem jsme stavu
-    BOOL IsOk() { return Ok; }
+    BOOL IsOk() const { return Ok; }
     // pokud nastala chyba, vraci jeji kod
-    const unsigned int GetErrorCode() { return ErrorCode; }
+    unsigned int GetErrorCode() const { return ErrorCode; }
     // pokud nastala systemova chyba (I/O etc.) vraci blizsi urceni (::GetLastError())
-    const DWORD GetLastErr() { return LastError; }
+    DWORD GetLastErr() const { return LastError; }
+    // vraci velikost bufferu s neprectenymi datami
+    size_t GetUnreadInputBufferSize() const { return min(size_t(DataEnd - DataStart), (InputSize - InputPos).LoDWord); }
     // vraci velikost archivu na disku
-    CQuadWord GetStreamSize() { return InputSize; }
+    CQuadWord GetStreamSize() const { return InputSize; }
+    // vraci soucasnou pozici v aktualnim souboru v archivu na disku
+    CQuadWord GetInputPos() const { return InputPos; }
     // vraci soucasnou pozici v archivu na disku
-    CQuadWord GetStreamPos() { return StreamPos; }
+    CQuadWord GetStreamPos() const { return StreamPos; }
     // vrati puvodni nazev souboru, ktery byl v archivu (nazev taru v gzipu apod.)
     const char* GetOldName();
     // vrati nazev souboru, se kterym pracuje (jmeno archivu)
-    const char* GetArchiveName() { return FileName; }
+    const char* GetArchiveName() const { return FileName; }
 
     // vrati cast nebo cely posledni precteny blok k dalsimu pouziti
     virtual void Rewind(unsigned short size);
@@ -53,7 +57,8 @@ class CDecompressFile
     unsigned int ErrorCode;   // pokud nastala chyba, tady je uvedeno, jaka
     const char* FileName;     // nazev archivu, nad kterym pracujem
     char* OldName;            // puvodni nazev souboru pred zapakovanim
-    CQuadWord InputSize;      // velikost archivu
+    CQuadWord InputSize;      // velikost archivu (parcialni)
+    CQuadWord InputPos;       // pozice v archivu (parcialni)
     CQuadWord StreamPos;      // pozice v archivu (pro progress)
     HANDLE File;              // otevreny archiv
     DWORD LastError;          // pokud byla chyba systemu (I/O...), tady je blizsi urceni

src/plugins/tar/lzma/liblzma-port.txt

@@ -0,0 +1,11 @@
+a minimalistic lzma library port
+================================
+
+source: https://tukaani.org/xz/
+version: 5.4.4
+license: public domain
+
+the port contains:
+- library sources \src\common and \src\liblzma
+- MSVC project file liblzma.vcxproj and config.h, taken from \windows\vz2019 and modified,
+- license and readme files

src/plugins/tar/lzma/liblzma/AUTHORS

@@ -0,0 +1,39 @@
+
+Authors of XZ Utils
+===================
+
+    XZ Utils is developed and maintained by Lasse Collin
+    <lasse.collin@tukaani.org> and Jia Tan <jiat0218@gmail.com>.
+
+    Major parts of liblzma are based on code written by Igor Pavlov,
+    specifically the LZMA SDK <https://7-zip.org/sdk.html>. Without
+    this code, XZ Utils wouldn't exist.
+
+    The SHA-256 implementation in liblzma is based on the code found from
+    7-Zip <https://7-zip.org/>, which has a modified version of the SHA-256
+    code found from Crypto++ <https://www.cryptopp.com/>. The SHA-256 code
+    in Crypto++ was written by Kevin Springle and Wei Dai.
+
+    Some scripts have been adapted from gzip. The original versions
+    were written by Jean-loup Gailly, Charles Levert, and Paul Eggert.
+    Andrew Dudman helped adapting the scripts and their man pages for
+    XZ Utils.
+
+    The initial version of the threaded .xz decompressor was written
+    by Sebastian Andrzej Siewior.
+
+    The initial version of the .lz (lzip) decoder was written
+    by Michał Górny.
+
+    CLMUL-accelerated CRC code was contributed by Ilya Kurdyukov.
+
+    Other authors:
+      - Jonathan Nieder
+      - Joachim Henke
+
+    The GNU Autotools-based build system contains files from many authors,
+    which I'm not trying to list here.
+
+    Several people have contributed fixes or reported bugs. Most of them
+    are mentioned in the file THANKS.
+

src/plugins/tar/lzma/liblzma/COPYING

@@ -0,0 +1,65 @@
+
+XZ Utils Licensing
+==================
+
+    Different licenses apply to different files in this package. Here
+    is a rough summary of which licenses apply to which parts of this
+    package (but check the individual files to be sure!):
+
+      - liblzma is in the public domain.
+
+      - xz, xzdec, and lzmadec command line tools are in the public
+        domain unless GNU getopt_long had to be compiled and linked
+        in from the lib directory. The getopt_long code is under
+        GNU LGPLv2.1+.
+
+      - The scripts to grep, diff, and view compressed files have been
+        adapted from gzip. These scripts and their documentation are
+        under GNU GPLv2+.
+
+      - All the documentation in the doc directory and most of the
+        XZ Utils specific documentation files in other directories
+        are in the public domain.
+
+      - Translated messages are in the public domain.
+
+      - The build system contains public domain files, and files that
+        are under GNU GPLv2+ or GNU GPLv3+. None of these files end up
+        in the binaries being built.
+
+      - Test files and test code in the tests directory, and debugging
+        utilities in the debug directory are in the public domain.
+
+      - The extra directory may contain public domain files, and files
+        that are under various free software licenses.
+
+    You can do whatever you want with the files that have been put into
+    the public domain. If you find public domain legally problematic,
+    take the previous sentence as a license grant. If you still find
+    the lack of copyright legally problematic, you have too many
+    lawyers.
+
+    As usual, this software is provided "as is", without any warranty.
+
+    If you copy significant amounts of public domain code from XZ Utils
+    into your project, acknowledging this somewhere in your software is
+    polite (especially if it is proprietary, non-free software), but
+    naturally it is not legally required. Here is an example of a good
+    notice to put into "about box" or into documentation:
+
+        This software includes code from XZ Utils <https://tukaani.org/xz/>.
+
+    The following license texts are included in the following files:
+      - COPYING.LGPLv2.1: GNU Lesser General Public License version 2.1
+      - COPYING.GPLv2: GNU General Public License version 2
+      - COPYING.GPLv3: GNU General Public License version 3
+
+    Note that the toolchain (compiler, linker etc.) may add some code
+    pieces that are copyrighted. Thus, it is possible that e.g. liblzma
+    binary wouldn't actually be in the public domain in its entirety
+    even though it contains no copyrighted code from the XZ Utils source
+    package.
+
+    If you have questions, don't hesitate to ask the author(s) for more
+    information.
+