[Support/TarWriter] - Don't allow TarWriter to add the same file more than once.

This is for PR35460.

Currently when LLD adds files to TarWriter it may pass the same file
multiple times. For example it happens for clang reproduce file which specifies
archive (.a) files more than once in command line. 
Patch makes TarWriter to ignore files with the same path, so it will
add only the first one to archive.

Differential revision: https://reviews.llvm.org/D40606

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319750 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Support/TarWriter.h

@@ -11,6 +11,7 @@
 #define LLVM_SUPPORT_TAR_WRITER_H
 
 #include "llvm/ADT/StringRef.h"
+#include "llvm/ADT/StringSet.h"
 #include "llvm/Support/Error.h"
 #include "llvm/Support/raw_ostream.h"
 
@@ -26,6 +27,7 @@ private:
   TarWriter(int FD, StringRef BaseDir);
   raw_fd_ostream OS;
   std::string BaseDir;
+  StringSet<> Files;
 };
 }
 

lib/Support/TarWriter.cpp

@@ -173,6 +173,10 @@ void TarWriter::append(StringRef Path, StringRef Data) {
   // Write Path and Data.
   std::string Fullpath = BaseDir + "/" + sys::path::convert_to_slash(Path);
 
+  // We do not want to include the same file more than once.
+  if (!Files.insert(Fullpath).second)
+    return;
+
   StringRef Prefix;
   StringRef Name;
   if (splitUstar(Fullpath, Prefix, Name)) {

unittests/Support/TarWriterTest.cpp

@@ -120,4 +120,60 @@ TEST_F(TarWriterTest, Pax) {
   StringRef Pax = StringRef((char *)(Buf.data() + 512), 512);
   EXPECT_TRUE(Pax.startswith("211 path=/" + std::string(200, 'x')));
 }
+
+TEST_F(TarWriterTest, SingleFile) {
+  SmallString<128> Path;
+  std::error_code EC =
+      sys::fs::createTemporaryFile("TarWriterTest", "tar", Path);
+  EXPECT_FALSE((bool)EC);
+
+  Expected<std::unique_ptr<TarWriter>> TarOrErr = TarWriter::create(Path, "");
+  EXPECT_TRUE((bool)TarOrErr);
+  std::unique_ptr<TarWriter> Tar = std::move(*TarOrErr);
+  Tar->append("FooPath", "foo");
+  Tar.reset();
+
+  uint64_t TarSize;
+  EC = sys::fs::file_size(Path, TarSize);
+  EXPECT_FALSE((bool)EC);
+  EXPECT_EQ(TarSize, 2048);
+}
+
+TEST_F(TarWriterTest, NoDuplicate) {
+  SmallString<128> Path;
+  std::error_code EC =
+      sys::fs::createTemporaryFile("TarWriterTest", "tar", Path);
+  EXPECT_FALSE((bool)EC);
+
+  Expected<std::unique_ptr<TarWriter>> TarOrErr = TarWriter::create(Path, "");
+  EXPECT_TRUE((bool)TarOrErr);
+  std::unique_ptr<TarWriter> Tar = std::move(*TarOrErr);
+  Tar->append("FooPath", "foo");
+  Tar->append("BarPath", "bar");
+  Tar.reset();
+
+  uint64_t TarSize;
+  EC = sys::fs::file_size(Path, TarSize);
+  EXPECT_FALSE((bool)EC);
+  EXPECT_EQ(TarSize, 3072);
+}
+
+TEST_F(TarWriterTest, Duplicate) {
+  SmallString<128> Path;
+  std::error_code EC =
+      sys::fs::createTemporaryFile("TarWriterTest", "tar", Path);
+  EXPECT_FALSE((bool)EC);
+
+  Expected<std::unique_ptr<TarWriter>> TarOrErr = TarWriter::create(Path, "");
+  EXPECT_TRUE((bool)TarOrErr);
+  std::unique_ptr<TarWriter> Tar = std::move(*TarOrErr);
+  Tar->append("FooPath", "foo");
+  Tar->append("FooPath", "bar");
+  Tar.reset();
+
+  uint64_t TarSize;
+  EC = sys::fs::file_size(Path, TarSize);
+  EXPECT_FALSE((bool)EC);
+  EXPECT_EQ(TarSize, 2048);
 }
+} // namespace