[Remarks] Add string deduplication using a string table

* Add support for uniquing strings in the remark streamer and emitting the string table in the remarks section.

* Add parsing support for the string table in the RemarkParser.

From this remark:

```
--- !Missed
Pass:     inline
Name:     NoDefinition
DebugLoc: { File: 'test-suite/SingleSource/UnitTests/2002-04-17-PrintfChar.c',
            Line: 7, Column: 3 }
Function: printArgsNoRet
Args:
  - Callee:   printf
  - String:   ' will not be inlined into '
  - Caller:   printArgsNoRet
    DebugLoc: { File: 'test-suite/SingleSource/UnitTests/2002-04-17-PrintfChar.c',
                Line: 6, Column: 0 }
  - String:   ' because its definition is unavailable'
...
```

to:

```
--- !Missed
Pass: 0
Name: 1
DebugLoc: { File: 3, Line: 7, Column: 3 }
Function: 2
Args:
  - Callee:   4
  - String:   5
  - Caller:   2
    DebugLoc: { File: 3, Line: 6, Column: 0 }
  - String:   6
...
```

And the string table in the .remarks/__remarks section containing:

```
inline\0NoDefinition\0printArgsNoRet\0
test-suite/SingleSource/UnitTests/2002-04-17-PrintfChar.c\0printf\0
will not be inlined into \0 because its definition is unavailable\0
```

This is mostly supposed to be used for testing purposes, but it gives us
a 2x reduction in the remark size, and is an incremental change for the
updates to the remarks file format.

Differential Revision: https://reviews.llvm.org/D60227

llvm-svn: 359050

3 files changed, 142 insertions, 0 deletions

diff --git a/llvm/unittests/Remarks/CMakeLists.txt b/llvm/unittests/Remarks/CMakeLists.txt
index b7d22b694ef..d74960e0558 100644
--- a/llvm/unittests/Remarks/CMakeLists.txt
+++ b/llvm/unittests/Remarks/CMakeLists.txt
@@ -4,5 +4,6 @@ set(LLVM_LINK_COMPONENTS
   )
 
 add_llvm_unittest(RemarksTests
+  RemarksStrTabParsingTest.cpp
   YAMLRemarksParsingTest.cpp
   )
diff --git a/llvm/unittests/Remarks/RemarksStrTabParsingTest.cpp b/llvm/unittests/Remarks/RemarksStrTabParsingTest.cpp
new file mode 100644
index 00000000000..f1e9eb86840
--- /dev/null
+++ b/llvm/unittests/Remarks/RemarksStrTabParsingTest.cpp
@@ -0,0 +1,39 @@
+//===- unittest/Support/RemarksStrTabParsingTest.cpp - StrTab tests -------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Remarks/Remark.h"
+#include "llvm/Remarks/RemarkParser.h"
+#include "gtest/gtest.h"
+
+using namespace llvm;
+
+TEST(RemarksStrTab, ParsingEmpty) {
+  StringRef Empty("", 0);
+  remarks::ParsedStringTable StrTab(Empty);
+  Expected<StringRef> Nothing = StrTab[0];
+  EXPECT_FALSE(static_cast<bool>(Nothing));
+  EXPECT_EQ(toString(Nothing.takeError()),
+            "String with index 0 is out of bounds (size = 0).");
+}
+
+TEST(RemarksStrTab, ParsingGood) {
+  StringRef Strings("str1\0str2\0str3\0str4", 20);
+  remarks::ParsedStringTable StrTab(Strings);
+  Expected<StringRef> Result = StrTab[0];
+  EXPECT_TRUE(static_cast<bool>(Result));
+  EXPECT_EQ(*Result, "str1");
+  Result = StrTab[1];
+  EXPECT_TRUE(static_cast<bool>(Result));
+  EXPECT_EQ(*Result, "str2");
+  Result = StrTab[2];
+  EXPECT_TRUE(static_cast<bool>(Result));
+  EXPECT_EQ(*Result, "str3");
+  Result = StrTab[3];
+  EXPECT_TRUE(static_cast<bool>(Result));
+  EXPECT_EQ(*Result, "str4");
+}
diff --git a/llvm/unittests/Remarks/YAMLRemarksParsingTest.cpp b/llvm/unittests/Remarks/YAMLRemarksParsingTest.cpp
index 36dbb0c9518..1a6267c9785 100644
--- a/llvm/unittests/Remarks/YAMLRemarksParsingTest.cpp
+++ b/llvm/unittests/Remarks/YAMLRemarksParsingTest.cpp
@@ -492,3 +492,105 @@ TEST(YAMLRemarks, ContentsCAPI) {
   EXPECT_FALSE(LLVMRemarkParserHasError(Parser));
   LLVMRemarkParserDispose(Parser);
 }
+
+TEST(YAMLRemarks, ContentsStrTab) {
+  StringRef Buf = "\n"
+                  "--- !Missed\n"
+                  "Pass: 0\n"
+                  "Name: 1\n"
+                  "DebugLoc: { File: 2, Line: 3, Column: 12 }\n"
+                  "Function: 3\n"
+                  "Hotness: 4\n"
+                  "Args:\n"
+                  "  - Callee: 5\n"
+                  "  - String: 7\n"
+                  "  - Caller: 3\n"
+                  "    DebugLoc: { File: 2, Line: 2, Column: 0 }\n"
+                  "  - String: 8\n"
+                  "\n";
+
+  StringRef StrTabBuf =
+      StringRef("inline\0NoDefinition\0file.c\0foo\0Callee\0bar\0String\0 "
+                "will not be inlined into \0 because its definition is "
+                "unavailable",
+                115);
+
+  remarks::Parser Parser(Buf, StrTabBuf);
+  Expected<const remarks::Remark *> RemarkOrErr = Parser.getNext();
+  EXPECT_FALSE(errorToBool(RemarkOrErr.takeError()));
+  EXPECT_TRUE(*RemarkOrErr != nullptr);
+
+  const remarks::Remark &Remark = **RemarkOrErr;
+  EXPECT_EQ(Remark.RemarkType, remarks::Type::Missed);
+  EXPECT_EQ(checkStr(Remark.PassName, 6), "inline");
+  EXPECT_EQ(checkStr(Remark.RemarkName, 12), "NoDefinition");
+  EXPECT_EQ(checkStr(Remark.FunctionName, 3), "foo");
+  EXPECT_TRUE(Remark.Loc);
+  const remarks::RemarkLocation &RL = *Remark.Loc;
+  EXPECT_EQ(checkStr(RL.SourceFilePath, 6), "file.c");
+  EXPECT_EQ(RL.SourceLine, 3U);
+  EXPECT_EQ(RL.SourceColumn, 12U);
+  EXPECT_TRUE(Remark.Hotness);
+  EXPECT_EQ(*Remark.Hotness, 4U);
+  EXPECT_EQ(Remark.Args.size(), 4U);
+
+  unsigned ArgID = 0;
+  for (const remarks::Argument &Arg : Remark.Args) {
+    switch (ArgID) {
+    case 0:
+      EXPECT_EQ(checkStr(Arg.Key, 6), "Callee");
+      EXPECT_EQ(checkStr(Arg.Val, 3), "bar");
+      EXPECT_FALSE(Arg.Loc);
+      break;
+    case 1:
+      EXPECT_EQ(checkStr(Arg.Key, 6), "String");
+      EXPECT_EQ(checkStr(Arg.Val, 26), " will not be inlined into ");
+      EXPECT_FALSE(Arg.Loc);
+      break;
+    case 2: {
+      EXPECT_EQ(checkStr(Arg.Key, 6), "Caller");
+      EXPECT_EQ(checkStr(Arg.Val, 3), "foo");
+      EXPECT_TRUE(Arg.Loc);
+      const remarks::RemarkLocation &RL = *Arg.Loc;
+      EXPECT_EQ(checkStr(RL.SourceFilePath, 6), "file.c");
+      EXPECT_EQ(RL.SourceLine, 2U);
+      EXPECT_EQ(RL.SourceColumn, 0U);
+      break;
+    }
+    case 3:
+      EXPECT_EQ(checkStr(Arg.Key, 6), "String");
+      EXPECT_EQ(checkStr(Arg.Val, 38),
+                " because its definition is unavailable");
+      EXPECT_FALSE(Arg.Loc);
+      break;
+    default:
+      break;
+    }
+    ++ArgID;
+  }
+
+  RemarkOrErr = Parser.getNext();
+  EXPECT_FALSE(errorToBool(RemarkOrErr.takeError()));
+  EXPECT_EQ(*RemarkOrErr, nullptr);
+}
+
+TEST(YAMLRemarks, ParsingBadStringTableIndex) {
+  StringRef Buf = "\n"
+                  "--- !Missed\n"
+                  "Pass: 50\n"
+                  "\n";
+
+  StringRef StrTabBuf = StringRef("inline");
+
+  remarks::Parser Parser(Buf, StrTabBuf);
+  Expected<const remarks::Remark *> Remark = Parser.getNext();
+  EXPECT_FALSE(Remark); // Expect an error here.
+
+  std::string ErrorStr;
+  raw_string_ostream Stream(ErrorStr);
+  handleAllErrors(Remark.takeError(),
+                  [&](const ErrorInfoBase &EIB) { EIB.log(Stream); });
+  EXPECT_TRUE(
+      StringRef(Stream.str())
+          .contains("String with index 50 is out of bounds (size = 1)."));
+}