path: root/lib/AST/CommentLexer.cpp

#include "clang/AST/CommentLexer.h"
#include "clang/AST/CommentCommandTraits.h"
#include "clang/Basic/ConvertUTF.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

StringRef Lexer::resolveHTMLNamedCharacterReference(StringRef Name) const {
  return llvm::StringSwitch<StringRef>(Name)
      .Case("amp", "&")
      .Case("lt", "<")
      .Case("gt", ">")
      .Case("quot", "\"")
      .Case("apos", "\'")
      .Default("");
}

StringRef Lexer::resolveHTMLDecimalCharacterReference(StringRef Name) const {
  unsigned CodePoint = 0;
  for (unsigned i = 0, e = Name.size(); i != e; ++i) {
    assert(isHTMLDecimalCharacterReferenceCharacter(Name[i]));
    CodePoint *= 10;
    CodePoint += Name[i] - '0';
  }

  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 = 0;
  for (unsigned i = 0, e = Name.size(); i != e; ++i) {
    CodePoint *= 16;
    const char C = Name[i];
    assert(isHTMLHexCharacterReferenceCharacter(C));
    if (C >= '0' && C <= '9')
      CodePoint += Name[i] - '0';
    else if (C >= 'a' && C <= 'f')
      CodePoint += Name[i] - 'a' + 10;
    else
      CodePoint += Name[i] - 'A' + 10;
  }

  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();
}

void Lexer::skipLineStartingDecorations() {
  // This function should be called only for C comments
  assert(CommentState == LCS_InsideCComment);

  if (BufferPtr == CommentEnd)
    return;

  switch (*BufferPtr) {
  case ' ':
  case '\t':
  case '\f':
  case '\v': {
    const char *NewBufferPtr = BufferPtr;
    NewBufferPtr++;
    if (NewBufferPtr == CommentEnd)
      return;

    char C = *NewBufferPtr;
    while (C == ' ' || C == '\t' || C == '\f' || C == '\v') {
      NewBufferPtr++;
      if (NewBufferPtr == CommentEnd)
        return;
      C = *NewBufferPtr;
    }
    if (C == '*')
      BufferPtr = NewBufferPtr + 1;
    break;
  }
  case '*':
    BufferPtr++;
    break;
  }
}

namespace {
/// Returns pointer to the first newline character in the string.
const char *findNewline(const char *BufferPtr, const char *BufferEnd) {
  for ( ; BufferPtr != BufferEnd; ++BufferPtr) {
    const char C = *BufferPtr;
    if (C == '\n' || C == '\r')
      return BufferPtr;
  }
  return BufferEnd;
}

const char *skipNewline(const char *BufferPtr, const char *BufferEnd) {
  if (BufferPtr == BufferEnd)