[Support] Add a UniqueStringSaver: like StringSaver, but deduplicating.

sam-mccall · sam-mccall · commit 4bb7883d097f · 2018-07-23T10:44:40.000Z
Summary: Clarify contract of StringSaver (it null-terminates, callers rely on it). Reviewers: hokein Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D49596 llvm-svn: 337677
diff --git a/llvm/include/llvm/Support/StringSaver.h b/llvm/include/llvm/Support/StringSaver.h
@@ -10,23 +10,49 @@
 #ifndef LLVM_SUPPORT_STRINGSAVER_H
 #define LLVM_SUPPORT_STRINGSAVER_H
 
+#include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/Support/Allocator.h"
 
 namespace llvm {
 
-/// Saves strings in the inheritor's stable storage and returns a
+/// Saves strings in the provided stable storage and returns a
 /// StringRef with a stable character pointer.
 class StringSaver final {
   BumpPtrAllocator &Alloc;
 
 public:
   StringSaver(BumpPtrAllocator &Alloc) : Alloc(Alloc) {}
+
+  // All returned strings are null-terminated: *save(S).end() == 0.
   StringRef save(const char *S) { return save(StringRef(S)); }
   StringRef save(StringRef S);
   StringRef save(const Twine &S) { return save(StringRef(S.str())); }
   StringRef save(const std::string &S) { return save(StringRef(S)); }
 };
+
+/// Saves strings in the provided stable storage and returns a StringRef with a
+/// stable character pointer. Saving the same string yields the same StringRef.
+///
+/// Compared to StringSaver, it does more work but avoids saving the same string
+/// multiple times.
+///
+/// Compared to StringPool, it performs fewer allocations but doesn't support
+/// refcounting/deletion.
+class UniqueStringSaver final {
+  StringSaver Strings;
+  llvm::DenseSet<llvm::StringRef> Unique;
+
+public:
+  UniqueStringSaver(BumpPtrAllocator &Alloc) : Strings(Alloc) {}
+
+  // All returned strings are null-terminated: *save(S).end() == 0.
+  StringRef save(const char *S) { return save(StringRef(S)); }
+  StringRef save(StringRef S);
+  StringRef save(const Twine &S) { return save(StringRef(S.str())); }
+  StringRef save(const std::string &S) { return save(StringRef(S)); }
+};
+
 }
 #endif
diff --git a/llvm/lib/Support/StringSaver.cpp b/llvm/lib/Support/StringSaver.cpp
@@ -17,3 +17,10 @@ StringRef StringSaver::save(StringRef S) {
   P[S.size()] = '\0';
   return StringRef(P, S.size());
 }
+
+StringRef UniqueStringSaver::save(StringRef S) {
+  auto R = Unique.insert(S);
+  if (R.second)                 // cache miss, need to actually save the string
+    *R.first = Strings.save(S); // safe replacement with equal value
+  return *R.first;
+}
