//===--- PPDirectives.cpp - Directive Handling for Preprocessor -----------===//

//

// 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

//

//===----------------------------------------------------------------------===//

///

/// \file

/// Implements # directive processing for the Preprocessor.

///

//===----------------------------------------------------------------------===//

#include "clang/Basic/CharInfo.h"

#include "clang/Basic/DirectoryEntry.h"

#include "clang/Basic/FileManager.h"

#include "clang/Basic/IdentifierTable.h"

#include "clang/Basic/LangOptions.h"

#include "clang/Basic/Module.h"

#include "clang/Basic/SourceLocation.h"

#include "clang/Basic/SourceManager.h"

#include "clang/Basic/TokenKinds.h"

#include "clang/Lex/CodeCompletionHandler.h"

#include "clang/Lex/HeaderSearch.h"

#include "clang/Lex/HeaderSearchOptions.h"

#include "clang/Lex/LexDiagnostic.h"

#include "clang/Lex/LiteralSupport.h"

#include "clang/Lex/MacroInfo.h"

#include "clang/Lex/ModuleLoader.h"

#include "clang/Lex/ModuleMap.h"

#include "clang/Lex/PPCallbacks.h"

#include "clang/Lex/Pragma.h"

#include "clang/Lex/Preprocessor.h"

#include "clang/Lex/PreprocessorOptions.h"

#include "clang/Lex/Token.h"

#include "clang/Lex/VariadicMacroSupport.h"

#include "llvm/ADT/ArrayRef.h"

#include "llvm/ADT/STLExtras.h"

#include "llvm/ADT/ScopeExit.h"

#include "llvm/ADT/SmallString.h"

#include "llvm/ADT/SmallVector.h"

#include "llvm/ADT/StringRef.h"

#include "llvm/ADT/StringSwitch.h"

#include "llvm/Support/AlignOf.h"

#include "llvm/Support/ErrorHandling.h"

#include "llvm/Support/Path.h"

#include "llvm/Support/SaveAndRestore.h"

#include <algorithm>

#include <cassert>

#include <cstring>

#include <new>

#include <optional>

#include <string>

#include <utility>

using namespace clang;

//===----------------------------------------------------------------------===//

// Utility Methods for Preprocessor Directive Handling.

//===----------------------------------------------------------------------===//

MacroInfo *Preprocessor::AllocateMacroInfo(SourceLocation L) {

  static_assert(std::is_trivially_destructible_v<MacroInfo>, "");

  return new (BP) MacroInfo(L);

}

DefMacroDirective *Preprocessor::AllocateDefMacroDirective(MacroInfo *MI,

                                                           SourceLocation Loc) {

  return new (BP) DefMacroDirective(MI, Loc);

}

UndefMacroDirective *

Preprocessor::AllocateUndefMacroDirective(SourceLocation UndefLoc) {

  return new (BP) UndefMacroDirective(UndefLoc);

}

VisibilityMacroDirective *

Preprocessor::AllocateVisibilityMacroDirective(SourceLocation Loc,

                                               bool isPublic) {

  return new (BP) VisibilityMacroDirective(Loc, isPublic);

}

/// Read and discard all tokens remaining on the current line until

/// the tok::eod token is found.

SourceRange Preprocessor::DiscardUntilEndOfDirective() {

  Token Tmp;

  SourceRange Res;

  LexUnexpandedToken(Tmp);

  Res.setBegin(Tmp.getLocation());

  while (Tmp.isNot(tok::eod)) {

    assert(Tmp.isNot(tok::eof) && "EOF seen while discarding directive tokens");

    LexUnexpandedToken(Tmp);

  }

  Res.setEnd(Tmp.getLocation());

  return Res;

}

/// Enumerates possible cases of #define/#undef a reserved identifier.

enum MacroDiag {

  MD_NoWarn,        //> Not a reserved identifier

  MD_KeywordDef,    //> Macro hides keyword, enabled by default

  MD_ReservedMacro  //> #define of #undef reserved id, disabled by default

};

/// Enumerates possible %select values for the pp_err_elif_after_else and

/// pp_err_elif_without_if diagnostics.

enum PPElifDiag {

  PED_Elif,

  PED_Elifdef,

  PED_Elifndef

};

static bool isFeatureTestMacro(StringRef MacroName) {

  // list from:

  // * https://gcc.gnu.org/onlinedocs/libstdc++/manual/using_macros.html

  // * https://docs.microsoft.com/en-us/cpp/c-runtime-library/security-features-in-the-crt?view=msvc-160

  // * man 7 feature_test_macros

  // The list must be sorted for correct binary search.

  static constexpr StringRef ReservedMacro[] = {

      "_ATFILE_SOURCE",

      "_BSD_SOURCE",

      "_CRT_NONSTDC_NO_WARNINGS",

      "_CRT_SECURE_CPP_OVERLOAD_STANDARD_NAMES",

      "_CRT_SECURE_NO_WARNINGS",

      "_FILE_OFFSET_BITS",

      "_FORTIFY_SOURCE",

      "_GLIBCXX_ASSERTIONS",

      "_GLIBCXX_CONCEPT_CHECKS",

      "_GLIBCXX_DEBUG",

      "_GLIBCXX_DEBUG_PEDANTIC",

      "_GLIBCXX_PARALLEL",

      "_GLIBCXX_PARALLEL_ASSERTIONS",

      "_GLIBCXX_SANITIZE_VECTOR",

      "_GLIBCXX_USE_CXX11_ABI",

      "_GLIBCXX_USE_DEPRECATED",

      "_GNU_SOURCE",

      "_ISOC11_SOURCE",

      "_ISOC95_SOURCE",

      "_ISOC99_SOURCE",

      "_LARGEFILE64_SOURCE",

      "_POSIX_C_SOURCE",

      "_REENTRANT",

      "_SVID_SOURCE",

      "_THREAD_SAFE",

      "_XOPEN_SOURCE",

      "_XOPEN_SOURCE_EXTENDED",

      "__STDCPP_WANT_MATH_SPEC_FUNCS__",

      "__STDC_FORMAT_MACROS",

  };

  return std::binary_search(std::begin(ReservedMacro), std::end(ReservedMacro),

                            MacroName);

}

static bool isLanguageDefinedBuiltin(const SourceManager &SourceMgr,

                                     const MacroInfo *MI,

                                     const StringRef MacroName) {

  // If this is a macro with special handling (like __LINE__) then it's language

  // defined.

  if (MI->isBuiltinMacro())

    return true;

  // Builtin macros are defined in the builtin file

  if (!SourceMgr.isWrittenInBuiltinFile(MI->getDefinitionLoc()))

    return false;

  // C defines macros starting with __STDC, and C++ defines macros starting with

  // __STDCPP

  if (MacroName.starts_with("__STDC"))

    return true;

  // C++ defines the __cplusplus macro

  if (MacroName == "__cplusplus")

    return true;

  // C++ defines various feature-test macros starting with __cpp

  if (MacroName.starts_with("__cpp"))

    return true;

  // Anything else isn't language-defined

  return false;

}

static MacroDiag shouldWarnOnMacroDef(Preprocessor &PP, IdentifierInfo *II) {

  const LangOptions &Lang = PP.getLangOpts();

  StringRef Text = II->getName();

  if (isReservedInAllContexts(II->isReserved(Lang)))

    return isFeatureTestMacro(Text) ? MD_NoWarn : MD_ReservedMacro;

  if (II->isKeyword(Lang))

    return MD_KeywordDef;

  if (Lang.CPlusPlus11 && (Text.equals("override") || Text.equals("final")))

    return MD_KeywordDef;

  return MD_NoWarn;

}

static MacroDiag shouldWarnOnMacroUndef(Preprocessor &PP, IdentifierInfo *II) {

  const LangOptions &Lang = PP.getLangOpts();

  // Do not warn on keyword undef.  It is generally harmless and widely used.

  if (isReservedInAllContexts(II->isReserved(Lang)))

    return MD_ReservedMacro;

  return MD_NoWarn;

}

// Return true if we want to issue a diagnostic by default if we

// encounter this name in a #include with the wrong case. For now,

// this includes the standard C and C++ headers, Posix headers,

// and Boost headers. Improper case for these #includes is a

// potential portability issue.

static bool warnByDefaultOnWrongCase(StringRef Include) {

  // If the first component of the path is "boost", treat this like a standard header

  // for the purposes of diagnostics.

  if (::llvm::sys::path::begin(Include)->equals_insensitive("boost"))

    return true;

  // "condition_variable" is the longest standard header name at 18 characters.

  // If the include file name is longer than that, it can't be a standard header.

  static const size_t MaxStdHeaderNameLen = 18u;

  if (Include.size() > MaxStdHeaderNameLen)

    return false;

  // Lowercase and normalize the search string.

  SmallString<32> LowerInclude{Include};

  for (char &Ch : LowerInclude) {

    // In the ASCII range?

    if (static_cast<unsigned char>(Ch) > 0x7f)

      return false; // Can't be a standard header

    // ASCII lowercase:

    if (Ch >= 'A' && Ch <= 'Z')

      Ch += 'a' - 'A';

    // Normalize path separators for comparison purposes.

    else if (::llvm::sys::path::is_separator(Ch))

      Ch = '/';

  }

  // The standard C/C++ and Posix headers

  return llvm::StringSwitch<bool>(LowerInclude)

    // C library headers

    .Cases("assert.h", "complex.h", "ctype.h", "errno.h", "fenv.h", true)

    .Cases("float.h", "inttypes.h", "iso646.h", "limits.h", "locale.h", true)

    .Cases("math.h", "setjmp.h", "signal.h", "stdalign.h", "stdarg.h", true)

    .Cases("stdatomic.h", "stdbool.h", "stdckdint.h", "stddef.h", true)

    .Cases("stdint.h", "stdio.h", "stdlib.h", "stdnoreturn.h", true)

    .Cases("string.h", "tgmath.h", "threads.h", "time.h", "uchar.h", true)

    .Cases("wchar.h", "wctype.h", true)

    // C++ headers for C library facilities

    .Cases("cassert", "ccomplex", "cctype", "cerrno", "cfenv", true)

    .Cases("cfloat", "cinttypes", "ciso646", "climits", "clocale", true)

    .Cases("cmath", "csetjmp", "csignal", "cstdalign", "cstdarg", true)

    .Cases("cstdbool", "cstddef", "cstdint", "cstdio", "cstdlib", true)

    .Cases("cstring", "ctgmath", "ctime", "cuchar", "cwchar", true)

    .Case("cwctype", true)

    // C++ library headers

    .Cases("algorithm", "fstream", "list", "regex", "thread", true)

    .Cases("array", "functional", "locale", "scoped_allocator", "tuple", true)

    .Cases("atomic", "future", "map", "set", "type_traits", true)

    .Cases("bitset", "initializer_list", "memory", "shared_mutex", "typeindex", true)

    .Cases("chrono", "iomanip", "mutex", "sstream", "typeinfo", true)

    .Cases("codecvt", "ios", "new", "stack", "unordered_map", true)

    .Cases("complex", "iosfwd", "numeric", "stdexcept", "unordered_set", true)

    .Cases("condition_variable", "iostream", "ostream", "streambuf", "utility", true)

    .Cases("deque", "istream", "queue", "string", "valarray", true)

    .Cases("exception", "iterator", "random", "strstream", "vector", true)

    .Cases("forward_list", "limits", "ratio", "system_error", true)

    // POSIX headers (which aren't also C headers)

    .Cases("aio.h", "arpa/inet.h", "cpio.h", "dirent.h", "dlfcn.h", true)

    .Cases("fcntl.h", "fmtmsg.h", "fnmatch.h", "ftw.h", "glob.h", true)

    .Cases("grp.h", "iconv.h", "langinfo.h", "libgen.h", "monetary.h", true)

    .Cases("mqueue.h", "ndbm.h", "net/if.h", "netdb.h", "netinet/in.h", true)

    .Cases("netinet/tcp.h", "nl_types.h", "poll.h", "pthread.h", "pwd.h", true)

    .Cases("regex.h", "sched.h", "search.h", "semaphore.h", "spawn.h", true)

    .Cases("strings.h", "stropts.h", "sys/ipc.h", "sys/mman.h", "sys/msg.h", true)

    .Cases("sys/resource.h", "sys/select.h",  "sys/sem.h", "sys/shm.h", "sys/socket.h", true)

    .Cases("sys/stat.h", "sys/statvfs.h", "sys/time.h", "sys/times.h", "sys/types.h", true)

    .Cases("sys/uio.h", "sys/un.h", "sys/utsname.h", "sys/wait.h", "syslog.h", true)

    .Cases("tar.h", "termios.h", "trace.h", "ulimit.h", true)

    .Cases("unistd.h", "utime.h", "utmpx.h", "wordexp.h", true)

    .Default(false);

}

/// Find a similar string in `Candidates`.

///

/// \param LHS a string for a similar string in `Candidates`

///

/// \param Candidates the candidates to find a similar string.

///

/// \returns a similar string if exists. If no similar string exists,

/// returns std::nullopt.

static std::optional<StringRef>

findSimilarStr(StringRef LHS, const std::vector<StringRef> &Candidates) {

  // We need to check if `Candidates` has the exact case-insensitive string

  // because the Levenshtein distance match does not care about it.

  for (StringRef C : Candidates) {

    if (LHS.equals_insensitive(C)) {

      return C;

    }

  }

  // Keep going with the Levenshtein distance match.

  // If the LHS size is less than 3, use the LHS size minus 1 and if not,

  // use the LHS size divided by 3.

  size_t Length = LHS.size();

  size_t MaxDist = Length < 3 ? Length - 1 : Length / 3;

  std::optional<std::pair<StringRef, size_t>> SimilarStr;

  for (StringRef C : Candidates) {

    size_t CurDist = LHS.edit_distance(C, true);

    if (CurDist <= MaxDist) {

      if (!SimilarStr) {

        // The first similar string found.

        SimilarStr = {C, CurDist};

      } else if (CurDist < SimilarStr->second) {

        // More similar string found.

        SimilarStr = {C, CurDist};

      }

    }

  }

  if (SimilarStr) {

    return SimilarStr->first;

  } else {

    return std::nullopt;

  }

}

bool Preprocessor::CheckMacroName(Token &MacroNameTok, MacroUse isDefineUndef,

                                  bool *ShadowFlag) {

  // Missing macro name?

  if (MacroNameTok.is(tok::eod))

    return Diag(MacroNameTok, diag::err_pp_missing_macro_name);

  IdentifierInfo *II = MacroNameTok.getIdentifierInfo();

  if (!II)

    return Diag(MacroNameTok, diag::err_pp_macro_not_identifier);

  if (II->isCPlusPlusOperatorKeyword()) {

    // C++ 2.5p2: Alternative tokens behave the same as its primary token

    // except for their spellings.

    Diag(MacroNameTok, getLangOpts().MicrosoftExt

                           ? diag::ext_pp_operator_used_as_macro_name

                           : diag::err_pp_operator_used_as_macro_name)

        << II << MacroNameTok.getKind();

    // Allow #defining |and| and friends for Microsoft compatibility or

    // recovery when legacy C headers are included in C++.

  }

  if ((isDefineUndef != MU_Other) && II->getPPKeywordID() == tok::pp_defined) {

    // Error if defining "defined": C99 6.10.8/4, C++ [cpp.predefined]p4.

    return Diag(MacroNameTok, diag::err_defined_macro_name);

  }

  // If defining/undefining reserved identifier or a keyword, we need to issue

  // a warning.

  SourceLocation MacroNameLoc = MacroNameTok.getLocation();

  if (ShadowFlag)

    *ShadowFlag = false;

  if (!SourceMgr.isInSystemHeader(MacroNameLoc) &&

      (SourceMgr.getBufferName(MacroNameLoc) != "<built-in>")) {

    MacroDiag D = MD_NoWarn;

    if (isDefineUndef == MU_Define) {

      D = shouldWarnOnMacroDef(*this, II);

    }

    else if (isDefineUndef == MU_Undef)

      D = shouldWarnOnMacroUndef(*this, II);

    if (D == MD_KeywordDef) {

      // We do not want to warn on some patterns widely used in configuration

      // scripts.  This requires analyzing next tokens, so do not issue warnings

      // now, only inform caller.

      if (ShadowFlag)

        *ShadowFlag = true;

    }

    if (D == MD_ReservedMacro)

      Diag(MacroNameTok, diag::warn_pp_macro_is_reserved_id);

  }

  // Okay, we got a good identifier.

  return false;

}

/// Lex and validate a macro name, which occurs after a

/// \#define or \#undef.

///

/// This sets the token kind to eod and discards the rest of the macro line if

/// the macro name is invalid.

///

/// \param MacroNameTok Token that is expected to be a macro name.

/// \param isDefineUndef Context in which macro is used.

/// \param ShadowFlag Points to a flag that is set if macro shadows a keyword.

void Preprocessor::ReadMacroName(Token &MacroNameTok, MacroUse isDefineUndef,

                                 bool *ShadowFlag) {

  // Read the token, don't allow macro expansion on it.

  LexUnexpandedToken(MacroNameTok);

  if (MacroNameTok.is(tok::code_completion)) {

    if (CodeComplete)

      CodeComplete->CodeCompleteMacroName(isDefineUndef == MU_Define);

    setCodeCompletionReached();

    LexUnexpandedToken(MacroNameTok);

  }

  if (!CheckMacroName(MacroNameTok, isDefineUndef, ShadowFlag))

    return;

  // Invalid macro name, read and discard the rest of the line and set the

  // token kind to tok::eod if necessary.

  if (MacroNameTok.isNot(tok::eod)) {

    MacroNameTok.setKind(tok::eod);

    DiscardUntilEndOfDirective();

  }

}

/// Ensure that the next token is a tok::eod token.

///

/// If not, emit a diagnostic and consume up until the eod.  If EnableMacros is

/// true, then we consider macros that expand to zero tokens as being ok.

///

/// Returns the location of the end of the directive.

SourceLocation Preprocessor::CheckEndOfDirective(const char *DirType,

                                                 bool EnableMacros) {

  Token Tmp;

  // Lex unexpanded tokens for most directives: macros might expand to zero

  // tokens, causing us to miss diagnosing invalid lines.  Some directives (like

  // #line) allow empty macros.

  if (EnableMacros)

    Lex(Tmp);

  else

    LexUnexpandedToken(Tmp);

  // There should be no tokens after the directive, but we allow them as an

  // extension.

  while (Tmp.is(tok::comment))  // Skip comments in -C mode.

    LexUnexpandedToken(Tmp);

  if (Tmp.is(tok::eod))

    return Tmp.getLocation();

  // Add a fixit in GNU/C99/C++ mode.  Don't offer a fixit for strict-C89,

  // or if this is a macro-style preprocessing directive, because it is more

  // trouble than it is worth to insert /**/ and check that there is no /**/

  // in the range also.

  FixItHint Hint;

  if ((LangOpts.GNUMode || LangOpts.C99 || LangOpts.CPlusPlus) &&

      !CurTokenLexer)

    Hint = FixItHint::CreateInsertion(Tmp.getLocation(),"//");

  Diag(Tmp, diag::ext_pp_extra_tokens_at_eol) << DirType << Hint;

  return DiscardUntilEndOfDirective().getEnd();

}

void Preprocessor::SuggestTypoedDirective(const Token &Tok,

                                          StringRef Directive) const {

  // If this is a `.S` file, treat unknown # directives as non-preprocessor

  // directives.

  if (getLangOpts().AsmPreprocessor) return;

  std::vector<StringRef> Candidates = {

      "if", "ifdef", "ifndef", "elif", "else", "endif"

  };

  if (LangOpts.C23 || LangOpts.CPlusPlus23)

    Candidates.insert(Candidates.end(), {"elifdef", "elifndef"});

  if (std::optional<StringRef> Sugg = findSimilarStr(Directive, Candidates)) {

    // Directive cannot be coming from macro.

    assert(Tok.getLocation().isFileID());

    CharSourceRange DirectiveRange = CharSourceRange::getCharRange(

        Tok.getLocation(),

        Tok.getLocation().getLocWithOffset(Directive.size()));

    StringRef SuggValue = *Sugg;

    auto Hint = FixItHint::CreateReplacement(DirectiveRange, SuggValue);

    Diag(Tok, diag::warn_pp_invalid_directive) << 1 << SuggValue << Hint;

  }

}

/// SkipExcludedConditionalBlock - We just read a \#if or related directive and

/// decided that the subsequent tokens are in the \#if'd out portion of the

/// file.  Lex the rest of the file, until we see an \#endif.  If

/// FoundNonSkipPortion is true, then we have already emitted code for part of

/// this \#if directive, so \#else/\#elif blocks should never be entered.

/// If ElseOk is true, then \#else directives are ok, if not, then we have

/// already seen one so a \#else directive is a duplicate.  When this returns,

/// the caller can lex the first valid token.

void Preprocessor::SkipExcludedConditionalBlock(SourceLocation HashTokenLoc,

                                                SourceLocation IfTokenLoc,

                                                bool FoundNonSkipPortion,

                                                bool FoundElse,

                                                SourceLocation ElseLoc) {

  // In SkippingRangeStateTy we are depending on SkipExcludedConditionalBlock()

  // not getting called recursively by storing the RecordedSkippedRanges

  // DenseMap lookup pointer (field SkipRangePtr). SkippingRangeStateTy expects

  // that RecordedSkippedRanges won't get modified and SkipRangePtr won't be

  // invalidated. If this changes and there is a need to call

  // SkipExcludedConditionalBlock() recursively, SkippingRangeStateTy should

  // change to do a second lookup in endLexPass function instead of reusing the

  // lookup pointer.

  assert(!SkippingExcludedConditionalBlock &&

         "calling SkipExcludedConditionalBlock recursively");

  llvm::SaveAndRestore SARSkipping(SkippingExcludedConditionalBlock, true);

  ++NumSkipped;

  assert(!CurTokenLexer && "Conditional PP block cannot appear in a macro!");

  assert(CurPPLexer && "Conditional PP block must be in a file!");

  assert(CurLexer && "Conditional PP block but no current lexer set!");

  if (PreambleConditionalStack.reachedEOFWhileSkipping())

    PreambleConditionalStack.clearSkipInfo();

  else

    CurPPLexer->pushConditionalLevel(IfTokenLoc, /*isSkipping*/ false,

                                     FoundNonSkipPortion, FoundElse);

  // Enter raw mode to disable identifier lookup (and thus macro expansion),

  // disabling warnings, etc.

  CurPPLexer->LexingRawMode = true;

  Token Tok;

  SourceLocation endLoc;

  /// Keeps track and caches skipped ranges and also retrieves a prior skipped

  /// range if the same block is re-visited.

  struct SkippingRangeStateTy {

    Preprocessor &PP;

    const char *BeginPtr = nullptr;

    unsigned *SkipRangePtr = nullptr;

    SkippingRangeStateTy(Preprocessor &PP) : PP(PP) {}

    void beginLexPass() {

      if (BeginPtr)

        return; // continue skipping a block.

      // Initiate a skipping block and adjust the lexer if we already skipped it

      // before.

      BeginPtr = PP.CurLexer->getBufferLocation();

      SkipRangePtr = &PP.RecordedSkippedRanges[BeginPtr];

      if (*SkipRangePtr) {

        PP.CurLexer->seek(PP.CurLexer->getCurrentBufferOffset() + *SkipRangePtr,

                          /*IsAtStartOfLine*/ true);

      }

    }

    void endLexPass(const char *Hashptr) {

      if (!BeginPtr) {

        // Not doing normal lexing.

        assert(PP.CurLexer->isDependencyDirectivesLexer());

        return;

      }

      // Finished skipping a block, record the range if it's first time visited.

      if (!*SkipRangePtr) {

        *SkipRangePtr = Hashptr - BeginPtr;

      }

      assert(*SkipRangePtr == Hashptr - BeginPtr);

      BeginPtr = nullptr;

      SkipRangePtr = nullptr;

    }

  } SkippingRangeState(*this);

  while (true) {

    if (CurLexer->isDependencyDirectivesLexer()) {

      CurLexer->LexDependencyDirectiveTokenWhileSkipping(Tok);

    } else {

      SkippingRangeState.beginLexPass();

      while (true) {

        CurLexer->Lex(Tok);

        if (Tok.is(tok::code_completion)) {

          setCodeCompletionReached();

          if (CodeComplete)

            CodeComplete->CodeCompleteInConditionalExclusion();

          continue;

        }

        // If this is the end of the buffer, we have an error.

        if (Tok.is(tok::eof)) {

          // We don't emit errors for unterminated conditionals here,

          // Lexer::LexEndOfFile can do that properly.

          // Just return and let the caller lex after this #include.

          if (PreambleConditionalStack.isRecording())

            PreambleConditionalStack.SkipInfo.emplace(HashTokenLoc, IfTokenLoc,

                                                      FoundNonSkipPortion,

                                                      FoundElse, ElseLoc);

          break;

        }

        // If this token is not a preprocessor directive, just skip it.

        if (Tok.isNot(tok::hash) || !Tok.isAtStartOfLine())

          continue;

        break;

      }

    }

    if (Tok.is(tok::eof))

      break;

    // We just parsed a # character at the start of a line, so we're in

    // directive mode.  Tell the lexer this so any newlines we see will be

    // converted into an EOD token (this terminates the macro).

    CurPPLexer->ParsingPreprocessorDirective = true;

    if (CurLexer) CurLexer->SetKeepWhitespaceMode(false);

    assert(Tok.is(tok::hash));

    const char *Hashptr = CurLexer->getBufferLocation() - Tok.getLength();

    assert(CurLexer->getSourceLocation(Hashptr) == Tok.getLocation());

    // Read the next token, the directive flavor.

    LexUnexpandedToken(Tok);

    // If this isn't an identifier directive (e.g. is "# 1\n" or "#\n", or

    // something bogus), skip it.

    if (Tok.isNot(tok::raw_identifier)) {

      CurPPLexer->ParsingPreprocessorDirective = false;

      // Restore comment saving mode.

      if (CurLexer) CurLexer->resetExtendedTokenMode();

      continue;

    }

    // If the first letter isn't i or e, it isn't intesting to us.  We know that

    // this is safe in the face of spelling differences, because there is no way

    // to spell an i/e in a strange way that is another letter.  Skipping this

    // allows us to avoid looking up the identifier info for #define/#undef and

    // other common directives.

    StringRef RI = Tok.getRawIdentifier();

    char FirstChar = RI[0];

    if (FirstChar >= 'a' && FirstChar <= 'z' &&

        FirstChar != 'i' && FirstChar != 'e') {

      CurPPLexer->ParsingPreprocessorDirective = false;

      // Restore comment saving mode.

      if (CurLexer) CurLexer->resetExtendedTokenMode();

      continue;

    }

    // Get the identifier name without trigraphs or embedded newlines.  Note

    // that we can't use Tok.getIdentifierInfo() because its lookup is disabled

    // when skipping.

    char DirectiveBuf[20];

    StringRef Directive;

    if (!Tok.needsCleaning() && RI.size() < 20) {

      Directive = RI;

    } else {

      std::string DirectiveStr = getSpelling(Tok);

      size_t IdLen = DirectiveStr.size();

      if (IdLen >= 20) {

        CurPPLexer->ParsingPreprocessorDirective = false;

        // Restore comment saving mode.

        if (CurLexer) CurLexer->resetExtendedTokenMode();

        continue;

      }

      memcpy(DirectiveBuf, &DirectiveStr[0], IdLen);

      Directive = StringRef(DirectiveBuf, IdLen);

    }

    if (Directive.starts_with("if")) {

      StringRef Sub = Directive.substr(2);

      if (Sub.empty() ||   // "if"

          Sub == "def" ||   // "ifdef"

          Sub == "ndef") {  // "ifndef"

        // We know the entire #if/#ifdef/#ifndef block will be skipped, don't

        // bother parsing the condition.

        DiscardUntilEndOfDirective();

        CurPPLexer->pushConditionalLevel(Tok.getLocation(), /*wasskipping*/true,

                                       /*foundnonskip*/false,

                                       /*foundelse*/false);

      } else {

        SuggestTypoedDirective(Tok, Directive);

      }

    } else if (Directive[0] == 'e') {

      StringRef Sub = Directive.substr(1);

      if (Sub == "ndif") {  // "endif"

        PPConditionalInfo CondInfo;

        CondInfo.WasSkipping = true; // Silence bogus warning.

        bool InCond = CurPPLexer->popConditionalLevel(CondInfo);

        (void)InCond;  // Silence warning in no-asserts mode.

        assert(!InCond && "Can't be skipping if not in a conditional!");

        // If we popped the outermost skipping block, we're done skipping!

        if (!CondInfo.WasSkipping) {

          SkippingRangeState.endLexPass(Hashptr);

          // Restore the value of LexingRawMode so that trailing comments

          // are handled correctly, if we've reached the outermost block.

          CurPPLexer->LexingRawMode = false;

          endLoc = CheckEndOfDirective("endif");

          CurPPLexer->LexingRawMode = true;

          if (Callbacks)

            Callbacks->Endif(Tok.getLocation(), CondInfo.IfLoc);

          break;

        } else {

          DiscardUntilEndOfDirective();

        }

      } else if (Sub == "lse") { // "else".

        // #else directive in a skipping conditional.  If not in some other

        // skipping conditional, and if #else hasn't already been seen, enter it

        // as a non-skipping conditional.

        PPConditionalInfo &CondInfo = CurPPLexer->peekConditionalLevel();

        if (!CondInfo.WasSkipping)

          SkippingRangeState.endLexPass(Hashptr);

        // If this is a #else with a #else before it, report the error.

        if (CondInfo.FoundElse)

          Diag(Tok, diag::pp_err_else_after_else);

        // Note that we've seen a #else in this conditional.

        CondInfo.FoundElse = true;

        // If the conditional is at the top level, and the #if block wasn't

        // entered, enter the #else block now.

        if (!CondInfo.WasSkipping && !CondInfo.FoundNonSkip) {

          CondInfo.FoundNonSkip = true;

          // Restore the value of LexingRawMode so that trailing comments

          // are handled correctly.

          CurPPLexer->LexingRawMode = false;

          endLoc = CheckEndOfDirective("else");

          CurPPLexer->LexingRawMode = true;

          if (Callbacks)

            Callbacks->Else(Tok.getLocation(), CondInfo.IfLoc);

          break;

        } else {

          DiscardUntilEndOfDirective();  // C99 6.10p4.

        }

      } else if (Sub == "lif") {  // "elif".

        PPConditionalInfo &CondInfo = CurPPLexer->peekConditionalLevel();

        if (!CondInfo.WasSkipping)

          SkippingRangeState.endLexPass(Hashptr);

        // If this is a #elif with a #else before it, report the error.

        if (CondInfo.FoundElse)

          Diag(Tok, diag::pp_err_elif_after_else) << PED_Elif;

        // If this is in a skipping block or if we're already handled this #if

        // block, don't bother parsing the condition.

        if (CondInfo.WasSkipping || CondInfo.FoundNonSkip) {

          // FIXME: We should probably do at least some minimal parsing of the

          // condition to verify that it is well-formed. The current state

          // allows #elif* directives with completely malformed (or missing)

          // conditions.

          DiscardUntilEndOfDirective();

        } else {

          // Restore the value of LexingRawMode so that identifiers are

          // looked up, etc, inside the #elif expression.

          assert(CurPPLexer->LexingRawMode && "We have to be skipping here!");

          CurPPLexer->LexingRawMode = false;

          IdentifierInfo *IfNDefMacro = nullptr;

          DirectiveEvalResult DER = EvaluateDirectiveExpression(IfNDefMacro);

          // Stop if Lexer became invalid after hitting code completion token.

          if (!CurPPLexer)

            return;

          const bool CondValue = DER.Conditional;

          CurPPLexer->LexingRawMode = true;

          if (Callbacks) {

            Callbacks->Elif(

                Tok.getLocation(), DER.ExprRange,

                (CondValue ? PPCallbacks::CVK_True : PPCallbacks::CVK_False),

                CondInfo.IfLoc);

          }

          // If this condition is true, enter it!

          if (CondValue) {

            CondInfo.FoundNonSkip = true;

            break;

          }

        }

      } else if (Sub == "lifdef" ||  // "elifdef"

                 Sub == "lifndef") { // "elifndef"

        bool IsElifDef = Sub == "lifdef";

        PPConditionalInfo &CondInfo = CurPPLexer->peekConditionalLevel();

        Token DirectiveToken = Tok;

        if (!CondInfo.WasSkipping)

          SkippingRangeState.endLexPass(Hashptr);

        // Warn if using `#elifdef` & `#elifndef` in not C23 & C++23 mode even

        // if this branch is in a skipping block.

        unsigned DiagID;

        if (LangOpts.CPlusPlus)

          DiagID = LangOpts.CPlusPlus23 ? diag::warn_cxx23_compat_pp_directive

                                        : diag::ext_cxx23_pp_directive;

        else

          DiagID = LangOpts.C23 ? diag::warn_c23_compat_pp_directive

                                : diag::ext_c23_pp_directive;

        Diag(Tok, DiagID) << (IsElifDef ? PED_Elifdef : PED_Elifndef);

        // If this is a #elif with a #else before it, report the error.

        if (CondInfo.FoundElse)

          Diag(Tok, diag::pp_err_elif_after_else)

              << (IsElifDef ? PED_Elifdef : PED_Elifndef);

        // If this is in a skipping block or if we're already handled this #if

        // block, don't bother parsing the condition.

        if (CondInfo.WasSkipping || CondInfo.FoundNonSkip) {

          // FIXME: We should probably do at least some minimal parsing of the

          // condition to verify that it is well-formed. The current state

          // allows #elif* directives with completely malformed (or missing)

          // conditions.

          DiscardUntilEndOfDirective();

        } else {

          // Restore the value of LexingRawMode so that identifiers are

          // looked up, etc, inside the #elif[n]def expression.

          assert(CurPPLexer->LexingRawMode && "We have to be skipping here!");

          CurPPLexer->LexingRawMode = false;

          Token MacroNameTok;

          ReadMacroName(MacroNameTok);

          CurPPLexer->LexingRawMode = true;

          // If the macro name token is tok::eod, there was an error that was

          // already reported.

          if (MacroNameTok.is(tok::eod)) {

            // Skip code until we get to #endif.  This helps with recovery by

            // not emitting an error when the #endif is reached.

            continue;

          }

          emitMacroExpansionWarnings(MacroNameTok);

          CheckEndOfDirective(IsElifDef ? "elifdef" : "elifndef");

          IdentifierInfo *MII = MacroNameTok.getIdentifierInfo();

          auto MD = getMacroDefinition(MII);

          MacroInfo *MI = MD.getMacroInfo();

          if (Callbacks) {

            if (IsElifDef) {

              Callbacks->Elifdef(DirectiveToken.getLocation(), MacroNameTok,

                                 MD);

            } else {

              Callbacks->Elifndef(DirectiveToken.getLocation(), MacroNameTok,

                                  MD);

            }

          }

          // If this condition is true, enter it!

          if (static_cast<bool>(MI) == IsElifDef) {

            CondInfo.FoundNonSkip = true;

            break;

          }

        }

      } else {

        SuggestTypoedDirective(Tok, Directive);

      }

    } else {

      SuggestTypoedDirective(Tok, Directive);

    }

    CurPPLexer->ParsingPreprocessorDirective = false;

    // Restore comment saving mode.

    if (CurLexer) CurLexer->resetExtendedTokenMode();

  }

  // Finally, if we are out of the conditional (saw an #endif or ran off the end

  // of the file, just stop skipping and return to lexing whatever came after

  // the #if block.

  CurPPLexer->LexingRawMode = false;

  // The last skipped range isn't actually skipped yet if it's truncated

  // by the end of the preamble; we'll resume parsing after the preamble.

  if (Callbacks && (Tok.isNot(tok::eof) || !isRecordingPreamble()))

    Callbacks->SourceRangeSkipped(

        SourceRange(HashTokenLoc, endLoc.isValid()

                                      ? endLoc

                                      : CurPPLexer->getSourceLocation()),

        Tok.getLocation());

}

Module *Preprocessor::getModuleForLocation(SourceLocation Loc,

                                           bool AllowTextual) {

  if (!SourceMgr.isInMainFile(Loc)) {

    // Try to determine the module of the include directive.

    // FIXME: Look into directly passing the FileEntry from LookupFile instead.

    FileID IDOfIncl = SourceMgr.getFileID(SourceMgr.getExpansionLoc(Loc));

    if (auto EntryOfIncl = SourceMgr.getFileEntryRefForID(IDOfIncl)) {

      // The include comes from an included file.

      return HeaderInfo.getModuleMap()

          .findModuleForHeader(*EntryOfIncl, AllowTextual)

          .getModule();

    }

  }

  // This is either in the main file or not in a file at all. It belongs

  // to the current module, if there is one.

  return getLangOpts().CurrentModule.empty()

             ? nullptr

             : HeaderInfo.lookupModule(getLangOpts().CurrentModule, Loc);

}

OptionalFileEntryRef

Preprocessor::getHeaderToIncludeForDiagnostics(SourceLocation IncLoc,

                                               SourceLocation Loc) {

  Module *IncM = getModuleForLocation(

      IncLoc, LangOpts.ModulesValidateTextualHeaderIncludes);

  // Walk up through the include stack, looking through textual headers of M

  // until we hit a non-textual header that we can #include. (We assume textual

  // headers of a module with non-textual headers aren't meant to be used to

  // import entities from the module.)

  auto &SM = getSourceManager();

  while (!Loc.isInvalid() && !SM.isInMainFile(Loc)) {

    auto ID = SM.getFileID(SM.getExpansionLoc(Loc));

    auto FE = SM.getFileEntryRefForID(ID);

    if (!FE)

      break;

    // We want to find all possible modules that might contain this header, so

    // search all enclosing directories for module maps and load them.

    HeaderInfo.hasModuleMap(FE->getName(), /*Root*/ nullptr,

                            SourceMgr.isInSystemHeader(Loc));

    bool InPrivateHeader = false;

    for (auto Header : HeaderInfo.findAllModulesForHeader(*FE)) {

      if (!Header.isAccessibleFrom(IncM)) {

        // It's in a private header; we can't #include it.

        // FIXME: If there's a public header in some module that re-exports it,

        // then we could suggest including that, but it's not clear that's the

        // expected way to make this entity visible.

        InPrivateHeader = true;

        continue;

      }

      // Don't suggest explicitly excluded headers.

      if (Header.getRole() == ModuleMap::ExcludedHeader)