path: root/lib/AST/CommentLexer.cpp

#include "clang/AST/CommentLexer.h"
#include "clang/AST/CommentCommandTraits.h"
#include "clang/Basic/ConvertUTF.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/ErrorHandling.h"

namespace clang {
namespace comments {

void Token::dump(const Lexer &L, const SourceManager &SM) const {
  llvm::errs() << "comments::Token Kind=" << Kind << " ";
  Loc.dump(SM);
  llvm::errs() << " " << Length << " \"" << L.getSpelling(*this, SM) << "\"\n";
}

namespace {
bool isHTMLNamedCharacterReferenceCharacter(char C) {
  return (C >= 'a' && C <= 'z') ||
         (C >= 'A' && C <= 'Z');
}

bool isHTMLDecimalCharacterReferenceCharacter(char C) {
  return C >= '0' && C <= '9';
}

bool isHTMLHexCharacterReferenceCharacter(char C) {
  return (C >= '0' && C <= '9') ||
         (C >= 'a' && C <= 'f') ||
         (C >= 'A' && C <= 'F');
}

#include "clang/AST/CommentHTMLTags.inc"

} // unnamed namespace

static unsigned getCodePoint(StringRef Name) {
  unsigned CodePoint = 0;
  for (unsigned i = 0, e = Name.size(); i != e; ++i) {
    CodePoint *= 16;
    const char C = Name[i];
    assert(isHTMLHexCharacterReferenceCharacter(C));
    CodePoint += llvm::hexDigitValue(C);
  }
  return CodePoint;
}

StringRef Lexer::helperResolveHTMLHexCharacterReference(unsigned CodePoint) const {
  char *Resolved = Allocator.Allocate<char>(UNI_MAX_UTF8_BYTES_PER_CODE_POINT);
  char *ResolvedPtr = Resolved;
  if (ConvertCodePointToUTF8(CodePoint, ResolvedPtr))
    return StringRef(Resolved, ResolvedPtr - Resolved);
  else
    return StringRef();
}
  
StringRef Lexer::resolveHTMLHexCharacterReference(StringRef Name) const {
  unsigned CodePoint = getCodePoint(Name);
  return helperResolveHTMLHexCharacterReference(CodePoint);
}

StringRef Lexer::resolveHTMLNamedCharacterReference(StringRef Name) const {
  return llvm::StringSwitch<StringRef>(Name)
      .Case("amp", "&")
      .Case("lt", "<")
      .Case("gt", ">")
      .Case("quot", "\"")
      .Case("apos", "\'")
      .Default("");
}
  
StringRef Lexer::HTMLDoxygenCharacterReference(StringRef Name) const {
  return llvm::StringSwitch<StringRef>(Name)
  .Case("copy", helperResolveHTMLHexCharacterReference(0x000A9))
  .Case("trade",        helperResolveHTMLHexCharacterReference(0x02122))
  .Case("reg",  helperResolveHTMLHexCharacterReference(0x000AE))
  .Case("lt",   helperResolveHTMLHexCharacterReference(0x0003C))
  .Case("gt",   helperResolveHTMLHexCharacterReference(0x0003C))
  .Case("amp",  helperResolveHTMLHexCharacterReference(0x00026))
  .Case("apos", helperResolveHTMLHexCharacterReference(0x00027))
  .Case("quot", helperResolveHTMLHexCharacterReference(0x00022))
  .Case("lsquo",        helperResolveHTMLHexCharacterReference(0x02018))
  .Case("rsquo",        helperResolveHTMLHexCharacterReference(0x02019))
  .Case("ldquo",        helperResolveHTMLHexCharacterReference(0x0201C))
  .Case("rdquo",        helperResolveHTMLHexCharacterReference(0x0201D))
  .Case("ndash",        helperResolveHTMLHexCharacterReference(0x02013))
  .Case("mdash",        helperResolveHTMLHexCharacterReference(0x02014))
  .Case("Auml", helperResolveHTMLHexCharacterReference(0x000C4))
  .Case("Euml", helperResolveHTMLHexCharacterReference(0x000CB))
  .Case("Iuml", helperResolveHTMLHexCharacterReference(0x000CF))
  .Case("Ouml", helperResolveHTMLHexCharacterReference(0x000D6))
  .Case("Uuml", helperResolveHTMLHexCharacterReference(0x000DC))
  .Case("Yuml", helperResolveHTMLHexCharacterReference(0x00178))
  .Case("auml", helperResolveHTMLHexCharacterReference(0x000E4))
  .Case("euml",<