ELFObjectWriter: deduplicate suffices in strtab

We already do this for shstrtab, so might as well do it for strtab. This
extracts the string table building code into a separate class. The idea
is to use it for other object formats too.

I mostly wanted to do this for the general principle, but it does save a
little bit on object file size. I tried this on a clang bootstrap and
saved 0.54% on the sum of object file sizes (1.14 MB out of 212 MB for
a release build).

Differential Revision: http://reviews.llvm.org/D3533

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207670 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 59 insertions, 0 deletions

diff --git a/include/llvm/Object/StringTableBuilder.h b/include/llvm/Object/StringTableBuilder.h
new file mode 100644
index 0000000000..c61e216bdf
--- /dev/null
+++ b/include/llvm/Object/StringTableBuilder.h
@@ -0,0 +1,59 @@
+//===-- StringTableBuilder.h - String table building utility ------*- C++ -*-=//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_OBJECT_STRINGTABLE_BUILDER_H
+#define LLVM_OBJECT_STRINGTABLE_BUILDER_H
+
+#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/StringMap.h"
+#include <cassert>
+
+namespace llvm {
+
+/// \brief Utility for building string tables with deduplicated suffixes.
+class StringTableBuilder {
+  SmallString<256> StringTable;
+  StringMap<size_t> StringIndexMap;
+
+public:
+  /// \brief Add a string to the builder. Returns a StringRef to the internal
+  /// copy of s. Can only be used before the table is finalized.
+  StringRef add(StringRef s) {
+    assert(!isFinalized());
+    return StringIndexMap.GetOrCreateValue(s, 0).getKey();
+  }
+
+  /// \brief Analyze the strings and build the final table. No more strings can
+  /// be added after this point.
+  void finalize();
+
+  /// \brief Retrieve the string table data. Can only be used after the table
+  /// is finalized.
+  StringRef data() {
+    assert(isFinalized());
+    return StringTable;
+  }
+
+  /// \brief Get the offest of a string in the string table. Can only be used
+  /// after the table is finalized.
+  size_t getOffset(StringRef s) {
+    assert(isFinalized());
+    assert(StringIndexMap.count(s) && "String is not in table!");
+    return StringIndexMap[s];
+  }
+
+private:
+  bool isFinalized() {
+    return !StringTable.empty();
+  }
+};
+
+} // end llvm namespace
+
+#endif