Comment parsing: resolve more named character references

This reimplements r173850 with a better approach:
(1) use a TableGen-generated matcher instead of doing a linear search;
(2) avoid allocations for new strings by converting code points to string
    iterals with TableGen.


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@173931 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 93 insertions, 0 deletions

diff --git a/utils/TableGen/CMakeLists.txt b/utils/TableGen/CMakeLists.txt
index 534ac9af77..a858a214b0 100644
--- a/utils/TableGen/CMakeLists.txt
+++ b/utils/TableGen/CMakeLists.txt
@@ -4,6 +4,7 @@ add_tablegen(clang-tblgen CLANG
   ClangASTNodesEmitter.cpp
   ClangAttrEmitter.cpp
   ClangCommentCommandInfoEmitter.cpp
+  ClangCommentHTMLNamedCharacterReferenceEmitter.cpp
   ClangCommentHTMLTagsEmitter.cpp
   ClangDiagnosticsEmitter.cpp
   ClangSACheckersEmitter.cpp
diff --git a/utils/TableGen/ClangCommentHTMLNamedCharacterReferenceEmitter.cpp b/utils/TableGen/ClangCommentHTMLNamedCharacterReferenceEmitter.cpp
new file mode 100644
index 0000000000..3afe2b73f0
--- /dev/null
+++ b/utils/TableGen/ClangCommentHTMLNamedCharacterReferenceEmitter.cpp
@@ -0,0 +1,83 @@
+//===--- ClangCommentHTMLNamedCharacterReferenceEmitter.cpp -----------------=//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This tablegen backend emits an fficient function to translate HTML named
+// character references to UTF-8 sequences.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/ADT/SmallString.h"
+#include "llvm/Support/ConvertUTF.h"
+#include "llvm/TableGen/Error.h"
+#include "llvm/TableGen/Record.h"
+#include "llvm/TableGen/StringMatcher.h"
+#include <vector>
+
+using namespace llvm;
+
+/// \brief Convert a code point to the corresponding UTF-8 sequence represented
+/// as a C string literal.
+///
+/// \returns true on success.
+static bool translateCodePointToUTF8(unsigned CodePoint,
+                                     SmallVectorImpl<char> &CLiteral) {
+  char Translated[UNI_MAX_UTF8_BYTES_PER_CODE_POINT];
+  char *TranslatedPtr = Translated;
+  if (!ConvertCodePointToUTF8(CodePoint, TranslatedPtr))
+    return false;
+
+  StringRef UTF8(Translated, TranslatedPtr - Translated);
+
+  raw_svector_ostream OS(CLiteral);
+  OS << "\"";
+  for (size_t i = 0, e = UTF8.size(); i != e; ++i) {
+    OS << "\\x";
+    OS.write_hex(static_cast<unsigned char>(UTF8[i]));
+  }
+  OS << "\"";
+
+  return true;
+}
+
+namespace clang {
+void EmitClangCommentHTMLNamedCharacterReferences(RecordKeeper &Records,
+                                                  raw_ostream &OS) {
+  std::vector<Record *> Tags = Records.getAllDerivedDefinitions("NCR");
+  std::vector<StringMatcher::StringPair> NameToUTF8;
+  SmallString<32> CLiteral;
+  for (std::vector<Record *>::iterator I = Tags.begin(), E = Tags.end();
+       I != E; ++I) {
+    Record &Tag = **I;
+    std::string Spelling = Tag.getValueAsString("Spelling");
+    uint64_t CodePoint = Tag.getValueAsInt("CodePoint");
+    CLiteral.clear();
+    CLiteral.append("return ");
+    if (!translateCodePointToUTF8(CodePoint, CLiteral)) {
+      SrcMgr.PrintMessage(Tag.getLoc().front(),
+                          SourceMgr::DK_Error,
+                          Twine("invalid code point"));
+      continue;
+    }
+    CLiteral.append(";");
+
+    StringMatcher::StringPair Match(Spelling, CLiteral.str());
+    NameToUTF8.push_back(Match);
+  }
+
+  OS << "// This file is generated by TableGen.  Do not edit.\n\n";
+
+  OS << "StringRef translateHTMLNamedCharacterReferenceToUTF8(\n"
+        "                                             StringRef Name) {\n";
+  StringMatcher("Name", NameToUTF8, OS).Emit();
+  OS << "  return StringRef();\n"
+     << "}\n\n";
+}
+
+} // end namespace clang
+
diff --git a/utils/TableGen/TableGen.cpp b/utils/TableGen/TableGen.cpp
index 8af6598cd0..4097339b9a 100644
--- a/utils/TableGen/TableGen.cpp
+++ b/utils/TableGen/TableGen.cpp
@@ -44,6 +44,7 @@ enum ActionType {
   GenClangSACheckers,
   GenClangCommentHTMLTags,
   GenClangCommentHTMLTagsProperties,
+  GenClangCommentHTMLNamedCharacterReferences,
   GenClangCommentCommandInfo,
   GenOptParserDefs, GenOptParserImpl,
   GenArmNeon,
@@ -111,6 +112,10 @@ namespace {
                                "gen-clang-comment-html-tags-properties",
                                "Generate efficient matchers for HTML tag "
                                "properties"),
+                    clEnumValN(GenClangCommentHTMLNamedCharacterReferences,
+                               "gen-clang-comment-html-named-character-references",
+                               "Generate function to translate named character "
+                               "references to UTF-8 sequences"),
                     clEnumValN(GenClangCommentCommandInfo,
                                "gen-clang-comment-command-info",
                                "Generate list of commands that are used in "
@@ -194,6 +199,9 @@ bool ClangTableGenMain(raw_ostream &OS, RecordKeeper &Records) {
   case GenClangCommentHTMLTagsProperties:
     EmitClangCommentHTMLTagsProperties(Records, OS);
     break;
+  case GenClangCommentHTMLNamedCharacterReferences:
+    EmitClangCommentHTMLNamedCharacterReferences(Records, OS);
+    break;
   case GenClangCommentCommandInfo:
     EmitClangCommentCommandInfo(Records, OS);
     break;
diff --git a/utils/TableGen/TableGenBackends.h b/utils/TableGen/TableGenBackends.h
index 637e54c01b..3bc4c906c0 100644
--- a/utils/TableGen/TableGenBackends.h
+++ b/utils/TableGen/TableGenBackends.h
@@ -51,6 +51,7 @@ void EmitClangSACheckers(RecordKeeper &Records, raw_ostream &OS);
 
 void EmitClangCommentHTMLTags(RecordKeeper &Records, raw_ostream &OS);
 void EmitClangCommentHTMLTagsProperties(RecordKeeper &Records, raw_ostream &OS);
+void EmitClangCommentHTMLNamedCharacterReferences(RecordKeeper &Records, raw_ostream &OS);
 
 void EmitClangCommentCommandInfo(RecordKeeper &Records, raw_ostream &OS);