SourceCode.cpp 40.1 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131
//===--- SourceCode.h - Manipulating source code as strings -----*- C++ -*-===//
//
// 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 "SourceCode.h"

#include "Context.h"
#include "FuzzyMatch.h"
#include "Logger.h"
#include "Protocol.h"
#include "refactor/Tweak.h"
#include "clang/AST/ASTContext.h"
#include "clang/Basic/LangOptions.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Basic/TokenKinds.h"
#include "clang/Driver/Types.h"
#include "clang/Format/Format.h"
#include "clang/Lex/Lexer.h"
#include "clang/Lex/Preprocessor.h"
#include "clang/Lex/Token.h"
#include "clang/Tooling/Core/Replacement.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/None.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Errc.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/LineIterator.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/SHA1.h"
#include "llvm/Support/VirtualFileSystem.h"
#include "llvm/Support/xxhash.h"
#include <algorithm>
#include <cstddef>
#include <string>
#include <vector>

namespace clang {
namespace clangd {

// Here be dragons. LSP positions use columns measured in *UTF-16 code units*!
// Clangd uses UTF-8 and byte-offsets internally, so conversion is nontrivial.

// Iterates over unicode codepoints in the (UTF-8) string. For each,
// invokes CB(UTF-8 length, UTF-16 length), and breaks if it returns true.
// Returns true if CB returned true, false if we hit the end of string.
template <typename Callback>
static bool iterateCodepoints(llvm::StringRef U8, const Callback &CB) {
  // A codepoint takes two UTF-16 code unit if it's astral (outside BMP).
  // Astral codepoints are encoded as 4 bytes in UTF-8, starting with 11110xxx.
  for (size_t I = 0; I < U8.size();) {
    unsigned char C = static_cast<unsigned char>(U8[I]);
    if (LLVM_LIKELY(!(C & 0x80))) { // ASCII character.
      if (CB(1, 1))
        return true;
      ++I;
      continue;
    }
    // This convenient property of UTF-8 holds for all non-ASCII characters.
    size_t UTF8Length = llvm::countLeadingOnes(C);
    // 0xxx is ASCII, handled above. 10xxx is a trailing byte, invalid here.
    // 11111xxx is not valid UTF-8 at all. Assert because it's probably our bug.
    assert((UTF8Length >= 2 && UTF8Length <= 4) &&
           "Invalid UTF-8, or transcoding bug?");
    I += UTF8Length; // Skip over all trailing bytes.
    // A codepoint takes two UTF-16 code unit if it's astral (outside BMP).
    // Astral codepoints are encoded as 4 bytes in UTF-8 (11110xxx ...)
    if (CB(UTF8Length, UTF8Length == 4 ? 2 : 1))
      return true;
  }
  return false;
}

// Returns the byte offset into the string that is an offset of \p Units in
// the specified encoding.
// Conceptually, this converts to the encoding, truncates to CodeUnits,
// converts back to UTF-8, and returns the length in bytes.
static size_t measureUnits(llvm::StringRef U8, int Units, OffsetEncoding Enc,
                           bool &Valid) {
  Valid = Units >= 0;
  if (Units <= 0)
    return 0;
  size_t Result = 0;
  switch (Enc) {
  case OffsetEncoding::UTF8:
    Result = Units;
    break;
  case OffsetEncoding::UTF16:
    Valid = iterateCodepoints(U8, [&](int U8Len, int U16Len) {
      Result += U8Len;
      Units -= U16Len;
      return Units <= 0;
    });
    if (Units < 0) // Offset in the middle of a surrogate pair.
      Valid = false;
    break;
  case OffsetEncoding::UTF32:
    Valid = iterateCodepoints(U8, [&](int U8Len, int U16Len) {
      Result += U8Len;
      Units--;
      return Units <= 0;
    });
    break;
  case OffsetEncoding::UnsupportedEncoding:
    llvm_unreachable("unsupported encoding");
  }
  // Don't return an out-of-range index if we overran.
  if (Result > U8.size()) {
    Valid = false;
    return U8.size();
  }
  return Result;
}

Key<OffsetEncoding> kCurrentOffsetEncoding;
static OffsetEncoding lspEncoding() {
  auto *Enc = Context::current().get(kCurrentOffsetEncoding);
  return Enc ? *Enc : OffsetEncoding::UTF16;
}

// Like most strings in clangd, the input is UTF-8 encoded.
size_t lspLength(llvm::StringRef Code) {
  size_t Count = 0;
  switch (lspEncoding()) {
  case OffsetEncoding::UTF8:
    Count = Code.size();
    break;
  case OffsetEncoding::UTF16:
    iterateCodepoints(Code, [&](int U8Len, int U16Len) {
      Count += U16Len;
      return false;
    });
    break;
  case OffsetEncoding::UTF32:
    iterateCodepoints(Code, [&](int U8Len, int U16Len) {
      ++Count;
      return false;
    });
    break;
  case OffsetEncoding::UnsupportedEncoding:
    llvm_unreachable("unsupported encoding");
  }
  return Count;
}

llvm::Expected<size_t> positionToOffset(llvm::StringRef Code, Position P,
                                        bool AllowColumnsBeyondLineLength) {
  if (P.line < 0)
    return llvm::make_error<llvm::StringError>(
        llvm::formatv("Line value can't be negative ({0})", P.line),
        llvm::errc::invalid_argument);
  if (P.character < 0)
    return llvm::make_error<llvm::StringError>(
        llvm::formatv("Character value can't be negative ({0})", P.character),
        llvm::errc::invalid_argument);
  size_t StartOfLine = 0;
  for (int I = 0; I != P.line; ++I) {
    size_t NextNL = Code.find('\n', StartOfLine);
    if (NextNL == llvm::StringRef::npos)
      return llvm::make_error<llvm::StringError>(
          llvm::formatv("Line value is out of range ({0})", P.line),
          llvm::errc::invalid_argument);
    StartOfLine = NextNL + 1;
  }
  StringRef Line =
      Code.substr(StartOfLine).take_until([](char C) { return C == '\n'; });

  // P.character may be in UTF-16, transcode if necessary.
  bool Valid;
  size_t ByteInLine = measureUnits(Line, P.character, lspEncoding(), Valid);
  if (!Valid && !AllowColumnsBeyondLineLength)
    return llvm::make_error<llvm::StringError>(
        llvm::formatv("{0} offset {1} is invalid for line {2}", lspEncoding(),
                      P.character, P.line),
        llvm::errc::invalid_argument);
  return StartOfLine + ByteInLine;
}

Position offsetToPosition(llvm::StringRef Code, size_t Offset) {
  Offset = std::min(Code.size(), Offset);
  llvm::StringRef Before = Code.substr(0, Offset);
  int Lines = Before.count('\n');
  size_t PrevNL = Before.rfind('\n');
  size_t StartOfLine = (PrevNL == llvm::StringRef::npos) ? 0 : (PrevNL + 1);
  Position Pos;
  Pos.line = Lines;
  Pos.character = lspLength(Before.substr(StartOfLine));
  return Pos;
}

Position sourceLocToPosition(const SourceManager &SM, SourceLocation Loc) {
  // We use the SourceManager's line tables, but its column number is in bytes.
  FileID FID;
  unsigned Offset;
  std::tie(FID, Offset) = SM.getDecomposedSpellingLoc(Loc);
  Position P;
  P.line = static_cast<int>(SM.getLineNumber(FID, Offset)) - 1;
  bool Invalid = false;
  llvm::StringRef Code = SM.getBufferData(FID, &Invalid);
  if (!Invalid) {
    auto ColumnInBytes = SM.getColumnNumber(FID, Offset) - 1;
    auto LineSoFar = Code.substr(Offset - ColumnInBytes, ColumnInBytes);
    P.character = lspLength(LineSoFar);
  }
  return P;
}

bool isSpelledInSource(SourceLocation Loc, const SourceManager &SM) {
  if (Loc.isMacroID()) {
    std::string PrintLoc = SM.getSpellingLoc(Loc).printToString(SM);
    if (llvm::StringRef(PrintLoc).startswith("<scratch") ||
        llvm::StringRef(PrintLoc).startswith("<command line>"))
      return false;
  }
  return true;
}

llvm::Optional<Range> getTokenRange(const SourceManager &SM,
                                    const LangOptions &LangOpts,
                                    SourceLocation TokLoc) {
  if (!TokLoc.isValid())
    return llvm::None;
  SourceLocation End = Lexer::getLocForEndOfToken(TokLoc, 0, SM, LangOpts);
  if (!End.isValid())
    return llvm::None;
  return halfOpenToRange(SM, CharSourceRange::getCharRange(TokLoc, End));
}

namespace {

enum TokenFlavor { Identifier, Operator, Whitespace, Other };

bool isOverloadedOperator(const Token &Tok) {
  switch (Tok.getKind()) {
#define OVERLOADED_OPERATOR(Name, Spelling, Token, Unary, Binary, MemOnly)     \
  case tok::Token:
#define OVERLOADED_OPERATOR_MULTI(Name, Spelling, Unary, Binary, MemOnly)
#include "clang/Basic/OperatorKinds.def"
    return true;

  default:
    break;
  }
  return false;
}

TokenFlavor getTokenFlavor(SourceLocation Loc, const SourceManager &SM,
                           const LangOptions &LangOpts) {
  Token Tok;
  Tok.setKind(tok::NUM_TOKENS);
  if (Lexer::getRawToken(Loc, Tok, SM, LangOpts,
                         /*IgnoreWhiteSpace*/ false))
    return Other;

  // getRawToken will return false without setting Tok when the token is
  // whitespace, so if the flag is not set, we are sure this is a whitespace.
  if (Tok.is(tok::TokenKind::NUM_TOKENS))
    return Whitespace;
  if (Tok.is(tok::TokenKind::raw_identifier))
    return Identifier;
  if (isOverloadedOperator(Tok))
    return Operator;
  return Other;
}

} // namespace

SourceLocation getBeginningOfIdentifier(const Position &Pos,
                                        const SourceManager &SM,
                                        const LangOptions &LangOpts) {
  FileID FID = SM.getMainFileID();
  auto Offset = positionToOffset(SM.getBufferData(FID), Pos);
  if (!Offset) {
    log("getBeginningOfIdentifier: {0}", Offset.takeError());
    return SourceLocation();
  }

  // GetBeginningOfToken(InputLoc) is almost what we want, but does the wrong
  // thing if the cursor is at the end of the token (identifier or operator).
  // The cases are:
  //   1) at the beginning of the token
  //   2) at the middle of the token
  //   3) at the end of the token
  //   4) anywhere outside the identifier or operator
  // To distinguish all cases, we lex both at the
  // GetBeginningOfToken(InputLoc-1) and GetBeginningOfToken(InputLoc), for
  // cases 1 and 4, we just return the original location.
  SourceLocation InputLoc = SM.getComposedLoc(FID, *Offset);
  if (*Offset == 0) // Case 1 or 4.
    return InputLoc;
  SourceLocation Before = SM.getComposedLoc(FID, *Offset - 1);
  SourceLocation BeforeTokBeginning =
      Lexer::GetBeginningOfToken(Before, SM, LangOpts);
  TokenFlavor BeforeKind = getTokenFlavor(BeforeTokBeginning, SM, LangOpts);

  SourceLocation CurrentTokBeginning =
      Lexer::GetBeginningOfToken(InputLoc, SM, LangOpts);
  TokenFlavor CurrentKind = getTokenFlavor(CurrentTokBeginning, SM, LangOpts);

  // At the middle of the token.
  if (BeforeTokBeginning == CurrentTokBeginning) {
    // For interesting token, we return the beginning of the token.
    if (CurrentKind == Identifier || CurrentKind == Operator)
      return CurrentTokBeginning;
    // otherwise, we return the original loc.
    return InputLoc;
  }

  // Whitespace is not interesting.
  if (BeforeKind == Whitespace)
    return CurrentTokBeginning;
  if (CurrentKind == Whitespace)
    return BeforeTokBeginning;

  // The cursor is at the token boundary, e.g. "Before^Current", we prefer
  // identifiers to other tokens.
  if (CurrentKind == Identifier)
    return CurrentTokBeginning;
  if (BeforeKind == Identifier)
    return BeforeTokBeginning;
  // Then prefer overloaded operators to other tokens.
  if (CurrentKind == Operator)
    return CurrentTokBeginning;
  if (BeforeKind == Operator)
    return BeforeTokBeginning;

  // Non-interesting case, we just return the original location.
  return InputLoc;
}

bool isValidFileRange(const SourceManager &Mgr, SourceRange R) {
  if (!R.getBegin().isValid() || !R.getEnd().isValid())
    return false;

  FileID BeginFID;
  size_t BeginOffset = 0;
  std::tie(BeginFID, BeginOffset) = Mgr.getDecomposedLoc(R.getBegin());

  FileID EndFID;
  size_t EndOffset = 0;
  std::tie(EndFID, EndOffset) = Mgr.getDecomposedLoc(R.getEnd());

  return BeginFID.isValid() && BeginFID == EndFID && BeginOffset <= EndOffset;
}

bool halfOpenRangeContains(const SourceManager &Mgr, SourceRange R,
                           SourceLocation L) {
  assert(isValidFileRange(Mgr, R));

  FileID BeginFID;
  size_t BeginOffset = 0;
  std::tie(BeginFID, BeginOffset) = Mgr.getDecomposedLoc(R.getBegin());
  size_t EndOffset = Mgr.getFileOffset(R.getEnd());

  FileID LFid;
  size_t LOffset;
  std::tie(LFid, LOffset) = Mgr.getDecomposedLoc(L);
  return BeginFID == LFid && BeginOffset <= LOffset && LOffset < EndOffset;
}

bool halfOpenRangeTouches(const SourceManager &Mgr, SourceRange R,
                          SourceLocation L) {
  return L == R.getEnd() || halfOpenRangeContains(Mgr, R, L);
}

SourceLocation includeHashLoc(FileID IncludedFile, const SourceManager &SM) {
  assert(SM.getLocForEndOfFile(IncludedFile).isFileID());
  FileID IncludingFile;
  unsigned Offset;
  std::tie(IncludingFile, Offset) =
      SM.getDecomposedExpansionLoc(SM.getIncludeLoc(IncludedFile));
  bool Invalid = false;
  llvm::StringRef Buf = SM.getBufferData(IncludingFile, &Invalid);
  if (Invalid)
    return SourceLocation();
  // Now buf is "...\n#include <foo>\n..."
  // and Offset points here:   ^
  // Rewind to the preceding # on the line.
  assert(Offset < Buf.size());
  for (;; --Offset) {
    if (Buf[Offset] == '#')
      return SM.getComposedLoc(IncludingFile, Offset);
    if (Buf[Offset] == '\n' || Offset == 0) // no hash, what's going on?
      return SourceLocation();
  }
}

static unsigned getTokenLengthAtLoc(SourceLocation Loc, const SourceManager &SM,
                                    const LangOptions &LangOpts) {
  Token TheTok;
  if (Lexer::getRawToken(Loc, TheTok, SM, LangOpts))
    return 0;
  // FIXME: Here we check whether the token at the location is a greatergreater
  // (>>) token and consider it as a single greater (>). This is to get it
  // working for templates but it isn't correct for the right shift operator. We
  // can avoid this by using half open char ranges in getFileRange() but getting
  // token ending is not well supported in macroIDs.
  if (TheTok.is(tok::greatergreater))
    return 1;
  return TheTok.getLength();
}

// Returns location of the last character of the token at a given loc
static SourceLocation getLocForTokenEnd(SourceLocation BeginLoc,
                                        const SourceManager &SM,
                                        const LangOptions &LangOpts) {
  unsigned Len = getTokenLengthAtLoc(BeginLoc, SM, LangOpts);
  return BeginLoc.getLocWithOffset(Len ? Len - 1 : 0);
}

// Returns location of the starting of the token at a given EndLoc
static SourceLocation getLocForTokenBegin(SourceLocation EndLoc,
                                          const SourceManager &SM,
                                          const LangOptions &LangOpts) {
  return EndLoc.getLocWithOffset(
      -(signed)getTokenLengthAtLoc(EndLoc, SM, LangOpts));
}

// Converts a char source range to a token range.
static SourceRange toTokenRange(CharSourceRange Range, const SourceManager &SM,
                                const LangOptions &LangOpts) {
  if (!Range.isTokenRange())
    Range.setEnd(getLocForTokenBegin(Range.getEnd(), SM, LangOpts));
  return Range.getAsRange();
}
// Returns the union of two token ranges.
// To find the maximum of the Ends of the ranges, we compare the location of the
// last character of the token.
static SourceRange unionTokenRange(SourceRange R1, SourceRange R2,
                                   const SourceManager &SM,
                                   const LangOptions &LangOpts) {
  SourceLocation Begin =
      SM.isBeforeInTranslationUnit(R1.getBegin(), R2.getBegin())
          ? R1.getBegin()
          : R2.getBegin();
  SourceLocation End =
      SM.isBeforeInTranslationUnit(getLocForTokenEnd(R1.getEnd(), SM, LangOpts),
                                   getLocForTokenEnd(R2.getEnd(), SM, LangOpts))
          ? R2.getEnd()
          : R1.getEnd();
  return SourceRange(Begin, End);
}

// Given a range whose endpoints may be in different expansions or files,
// tries to find a range within a common file by following up the expansion and
// include location in each.
static SourceRange rangeInCommonFile(SourceRange R, const SourceManager &SM,
                                     const LangOptions &LangOpts) {
  // Fast path for most common cases.
  if (SM.isWrittenInSameFile(R.getBegin(), R.getEnd()))
    return R;
  // Record the stack of expansion locations for the beginning, keyed by FileID.
  llvm::DenseMap<FileID, SourceLocation> BeginExpansions;
  for (SourceLocation Begin = R.getBegin(); Begin.isValid();
       Begin = Begin.isFileID()
                   ? includeHashLoc(SM.getFileID(Begin), SM)
                   : SM.getImmediateExpansionRange(Begin).getBegin()) {
    BeginExpansions[SM.getFileID(Begin)] = Begin;
  }
  // Move up the stack of expansion locations for the end until we find the
  // location in BeginExpansions with that has the same file id.
  for (SourceLocation End = R.getEnd(); End.isValid();
       End = End.isFileID() ? includeHashLoc(SM.getFileID(End), SM)
                            : toTokenRange(SM.getImmediateExpansionRange(End),
                                           SM, LangOpts)
                                  .getEnd()) {
    auto It = BeginExpansions.find(SM.getFileID(End));
    if (It != BeginExpansions.end()) {
      if (SM.getFileOffset(It->second) > SM.getFileOffset(End))
        return SourceLocation();
      return {It->second, End};
    }
  }
  return SourceRange();
}

// Find an expansion range (not necessarily immediate) the ends of which are in
// the same file id.
static SourceRange
getExpansionTokenRangeInSameFile(SourceLocation Loc, const SourceManager &SM,
                                 const LangOptions &LangOpts) {
  return rangeInCommonFile(
      toTokenRange(SM.getImmediateExpansionRange(Loc), SM, LangOpts), SM,
      LangOpts);
}

// Returns the file range for a given Location as a Token Range
// This is quite similar to getFileLoc in SourceManager as both use
// getImmediateExpansionRange and getImmediateSpellingLoc (for macro IDs).
// However:
// - We want to maintain the full range information as we move from one file to
//   the next. getFileLoc only uses the BeginLoc of getImmediateExpansionRange.
// - We want to split '>>' tokens as the lexer parses the '>>' in nested
//   template instantiations as a '>>' instead of two '>'s.
// There is also getExpansionRange but it simply calls
// getImmediateExpansionRange on the begin and ends separately which is wrong.
static SourceRange getTokenFileRange(SourceLocation Loc,
                                     const SourceManager &SM,
                                     const LangOptions &LangOpts) {
  SourceRange FileRange = Loc;
  while (!FileRange.getBegin().isFileID()) {
    if (SM.isMacroArgExpansion(FileRange.getBegin())) {
      FileRange = unionTokenRange(
          SM.getImmediateSpellingLoc(FileRange.getBegin()),
          SM.getImmediateSpellingLoc(FileRange.getEnd()), SM, LangOpts);
      assert(SM.isWrittenInSameFile(FileRange.getBegin(), FileRange.getEnd()));
    } else {
      SourceRange ExpansionRangeForBegin =
          getExpansionTokenRangeInSameFile(FileRange.getBegin(), SM, LangOpts);
      SourceRange ExpansionRangeForEnd =
          getExpansionTokenRangeInSameFile(FileRange.getEnd(), SM, LangOpts);
      if (ExpansionRangeForBegin.isInvalid() ||
          ExpansionRangeForEnd.isInvalid())
        return SourceRange();
      assert(SM.isWrittenInSameFile(ExpansionRangeForBegin.getBegin(),
                                    ExpansionRangeForEnd.getBegin()) &&
             "Both Expansion ranges should be in same file.");
      FileRange = unionTokenRange(ExpansionRangeForBegin, ExpansionRangeForEnd,
                                  SM, LangOpts);
    }
  }
  return FileRange;
}

bool isInsideMainFile(SourceLocation Loc, const SourceManager &SM) {
  return Loc.isValid() && SM.isWrittenInMainFile(SM.getExpansionLoc(Loc));
}

llvm::Optional<SourceRange> toHalfOpenFileRange(const SourceManager &SM,
                                                const LangOptions &LangOpts,
                                                SourceRange R) {
  SourceRange R1 = getTokenFileRange(R.getBegin(), SM, LangOpts);
  if (!isValidFileRange(SM, R1))
    return llvm::None;

  SourceRange R2 = getTokenFileRange(R.getEnd(), SM, LangOpts);
  if (!isValidFileRange(SM, R2))
    return llvm::None;

  SourceRange Result =
      rangeInCommonFile(unionTokenRange(R1, R2, SM, LangOpts), SM, LangOpts);
  unsigned TokLen = getTokenLengthAtLoc(Result.getEnd(), SM, LangOpts);
  // Convert from closed token range to half-open (char) range
  Result.setEnd(Result.getEnd().getLocWithOffset(TokLen));
  if (!isValidFileRange(SM, Result))
    return llvm::None;

  return Result;
}

llvm::StringRef toSourceCode(const SourceManager &SM, SourceRange R) {
  assert(isValidFileRange(SM, R));
  bool Invalid = false;
  auto *Buf = SM.getBuffer(SM.getFileID(R.getBegin()), &Invalid);
  assert(!Invalid);

  size_t BeginOffset = SM.getFileOffset(R.getBegin());
  size_t EndOffset = SM.getFileOffset(R.getEnd());
  return Buf->getBuffer().substr(BeginOffset, EndOffset - BeginOffset);
}

llvm::Expected<SourceLocation> sourceLocationInMainFile(const SourceManager &SM,
                                                        Position P) {
  llvm::StringRef Code = SM.getBuffer(SM.getMainFileID())->getBuffer();
  auto Offset =
      positionToOffset(Code, P, /*AllowColumnBeyondLineLength=*/false);
  if (!Offset)
    return Offset.takeError();
  return SM.getLocForStartOfFile(SM.getMainFileID()).getLocWithOffset(*Offset);
}

Range halfOpenToRange(const SourceManager &SM, CharSourceRange R) {
  // Clang is 1-based, LSP uses 0-based indexes.
  Position Begin = sourceLocToPosition(SM, R.getBegin());
  Position End = sourceLocToPosition(SM, R.getEnd());

  return {Begin, End};
}

std::pair<size_t, size_t> offsetToClangLineColumn(llvm::StringRef Code,
                                                  size_t Offset) {
  Offset = std::min(Code.size(), Offset);
  llvm::StringRef Before = Code.substr(0, Offset);
  int Lines = Before.count('\n');
  size_t PrevNL = Before.rfind('\n');
  size_t StartOfLine = (PrevNL == llvm::StringRef::npos) ? 0 : (PrevNL + 1);
  return {Lines + 1, Offset - StartOfLine + 1};
}

std::pair<StringRef, StringRef> splitQualifiedName(StringRef QName) {
  size_t Pos = QName.rfind("::");
  if (Pos == llvm::StringRef::npos)
    return {llvm::StringRef(), QName};
  return {QName.substr(0, Pos + 2), QName.substr(Pos + 2)};
}

TextEdit replacementToEdit(llvm::StringRef Code,
                           const tooling::Replacement &R) {
  Range ReplacementRange = {
      offsetToPosition(Code, R.getOffset()),
      offsetToPosition(Code, R.getOffset() + R.getLength())};
  return {ReplacementRange, R.getReplacementText()};
}

std::vector<TextEdit> replacementsToEdits(llvm::StringRef Code,
                                          const tooling::Replacements &Repls) {
  std::vector<TextEdit> Edits;
  for (const auto &R : Repls)
    Edits.push_back(replacementToEdit(Code, R));
  return Edits;
}

llvm::Optional<std::string> getCanonicalPath(const FileEntry *F,
                                             const SourceManager &SourceMgr) {
  if (!F)
    return None;

  llvm::SmallString<128> FilePath = F->getName();
  if (!llvm::sys::path::is_absolute(FilePath)) {
    if (auto EC =
            SourceMgr.getFileManager().getVirtualFileSystem().makeAbsolute(
                FilePath)) {
      elog("Could not turn relative path '{0}' to absolute: {1}", FilePath,
           EC.message());
      return None;
    }
  }

  // Handle the symbolic link path case where the current working directory
  // (getCurrentWorkingDirectory) is a symlink. We always want to the real
  // file path (instead of the symlink path) for the  C++ symbols.
  //
  // Consider the following example:
  //
  //   src dir: /project/src/foo.h
  //   current working directory (symlink): /tmp/build -> /project/src/
  //
  //  The file path of Symbol is "/project/src/foo.h" instead of
  //  "/tmp/build/foo.h"
  if (auto Dir = SourceMgr.getFileManager().getDirectory(
          llvm::sys::path::parent_path(FilePath))) {
    llvm::SmallString<128> RealPath;
    llvm::StringRef DirName = SourceMgr.getFileManager().getCanonicalName(*Dir);
    llvm::sys::path::append(RealPath, DirName,
                            llvm::sys::path::filename(FilePath));
    return RealPath.str().str();
  }

  return FilePath.str().str();
}

TextEdit toTextEdit(const FixItHint &FixIt, const SourceManager &M,
                    const LangOptions &L) {
  TextEdit Result;
  Result.range =
      halfOpenToRange(M, Lexer::makeFileCharRange(FixIt.RemoveRange, M, L));
  Result.newText = FixIt.CodeToInsert;
  return Result;
}

bool isRangeConsecutive(const Range &Left, const Range &Right) {
  return Left.end.line == Right.start.line &&
         Left.end.character == Right.start.character;
}

FileDigest digest(llvm::StringRef Content) {
  uint64_t Hash{llvm::xxHash64(Content)};
  FileDigest Result;
  for (unsigned I = 0; I < Result.size(); ++I) {
    Result[I] = uint8_t(Hash);
    Hash >>= 8;
  }
  return Result;
}

llvm::Optional<FileDigest> digestFile(const SourceManager &SM, FileID FID) {
  bool Invalid = false;
  llvm::StringRef Content = SM.getBufferData(FID, &Invalid);
  if (Invalid)
    return None;
  return digest(Content);
}

format::FormatStyle getFormatStyleForFile(llvm::StringRef File,
                                          llvm::StringRef Content,
                                          llvm::vfs::FileSystem *FS) {
  auto Style = format::getStyle(format::DefaultFormatStyle, File,
                                format::DefaultFallbackStyle, Content, FS);
  if (!Style) {
    log("getStyle() failed for file {0}: {1}. Fallback is LLVM style.", File,
        Style.takeError());
    Style = format::getLLVMStyle();
  }
  return *Style;
}

llvm::Expected<tooling::Replacements>
cleanupAndFormat(StringRef Code, const tooling::Replacements &Replaces,
                 const format::FormatStyle &Style) {
  auto CleanReplaces = cleanupAroundReplacements(Code, Replaces, Style);
  if (!CleanReplaces)
    return CleanReplaces;
  return formatReplacements(Code, std::move(*CleanReplaces), Style);
}

static void
lex(llvm::StringRef Code, const LangOptions &LangOpts,
    llvm::function_ref<void(const clang::Token &, const SourceManager &SM)>
        Action) {
  // FIXME: InMemoryFileAdapter crashes unless the buffer is null terminated!
  std::string NullTerminatedCode = Code.str();
  SourceManagerForFile FileSM("dummy.cpp", NullTerminatedCode);
  auto &SM = FileSM.get();
  auto FID = SM.getMainFileID();
  // Create a raw lexer (with no associated preprocessor object).
  Lexer Lex(FID, SM.getBuffer(FID), SM, LangOpts);
  Token Tok;

  while (!Lex.LexFromRawLexer(Tok))
    Action(Tok, SM);
  // LexFromRawLexer returns true after it lexes last token, so we still have
  // one more token to report.
  Action(Tok, SM);
}

llvm::StringMap<unsigned> collectIdentifiers(llvm::StringRef Content,
                                             const format::FormatStyle &Style) {
  llvm::StringMap<unsigned> Identifiers;
  auto LangOpt = format::getFormattingLangOpts(Style);
  lex(Content, LangOpt, [&](const clang::Token &Tok, const SourceManager &) {
    if (Tok.getKind() == tok::raw_identifier)
      ++Identifiers[Tok.getRawIdentifier()];
  });
  return Identifiers;
}

std::vector<Range> collectIdentifierRanges(llvm::StringRef Identifier,
                                           llvm::StringRef Content,
                                           const LangOptions &LangOpts) {
  std::vector<Range> Ranges;
  lex(Content, LangOpts, [&](const clang::Token &Tok, const SourceManager &SM) {
    if (Tok.getKind() != tok::raw_identifier)
      return;
    if (Tok.getRawIdentifier() != Identifier)
      return;
    auto Range = getTokenRange(SM, LangOpts, Tok.getLocation());
    if (!Range)
      return;
    Ranges.push_back(*Range);
  });
  return Ranges;
}

namespace {
struct NamespaceEvent {
  enum {
    BeginNamespace, // namespace <ns> {.     Payload is resolved <ns>.
    EndNamespace,   // } // namespace <ns>.  Payload is resolved *outer*
                    // namespace.
    UsingDirective  // using namespace <ns>. Payload is unresolved <ns>.
  } Trigger;
  std::string Payload;
  Position Pos;
};
// Scans C++ source code for constructs that change the visible namespaces.
void parseNamespaceEvents(llvm::StringRef Code,
                          const format::FormatStyle &Style,
                          llvm::function_ref<void(NamespaceEvent)> Callback) {

  // Stack of enclosing namespaces, e.g. {"clang", "clangd"}
  std::vector<std::string> Enclosing; // Contains e.g. "clang", "clangd"
  // Stack counts open braces. true if the brace opened a namespace.
  std::vector<bool> BraceStack;

  enum {
    Default,
    Namespace,          // just saw 'namespace'
    NamespaceName,      // just saw 'namespace' NSName
    Using,              // just saw 'using'
    UsingNamespace,     // just saw 'using namespace'
    UsingNamespaceName, // just saw 'using namespace' NSName
  } State = Default;
  std::string NSName;

  NamespaceEvent Event;
  lex(Code, format::getFormattingLangOpts(Style),
      [&](const clang::Token &Tok,const SourceManager &SM) {
    Event.Pos = sourceLocToPosition(SM, Tok.getLocation());
    switch (Tok.getKind()) {
    case tok::raw_identifier:
      // In raw mode, this could be a keyword or a name.
      switch (State) {
      case UsingNamespace:
      case UsingNamespaceName:
        NSName.append(Tok.getRawIdentifier());
        State = UsingNamespaceName;
        break;
      case Namespace:
      case NamespaceName:
        NSName.append(Tok.getRawIdentifier());
        State = NamespaceName;
        break;
      case Using:
        State =
            (Tok.getRawIdentifier() == "namespace") ? UsingNamespace : Default;
        break;
      case Default:
        NSName.clear();
        if (Tok.getRawIdentifier() == "namespace")
          State = Namespace;
        else if (Tok.getRawIdentifier() == "using")
          State = Using;
        break;
      }
      break;
    case tok::coloncolon:
      // This can come at the beginning or in the middle of a namespace name.
      switch (State) {
      case UsingNamespace:
      case UsingNamespaceName:
        NSName.append("::");
        State = UsingNamespaceName;
        break;
      case NamespaceName:
        NSName.append("::");
        State = NamespaceName;
        break;
      case Namespace: // Not legal here.
      case Using:
      case Default:
        State = Default;
        break;
      }
      break;
    case tok::l_brace:
      // Record which { started a namespace, so we know when } ends one.
      if (State == NamespaceName) {
        // Parsed: namespace <name> {
        BraceStack.push_back(true);
        Enclosing.push_back(NSName);
        Event.Trigger = NamespaceEvent::BeginNamespace;
        Event.Payload = llvm::join(Enclosing, "::");
        Callback(Event);
      } else {
        // This case includes anonymous namespaces (State = Namespace).
        // For our purposes, they're not namespaces and we ignore them.
        BraceStack.push_back(false);
      }
      State = Default;
      break;
    case tok::r_brace:
      // If braces are unmatched, we're going to be confused, but don't crash.
      if (!BraceStack.empty()) {
        if (BraceStack.back()) {
          // Parsed: } // namespace
          Enclosing.pop_back();
          Event.Trigger = NamespaceEvent::EndNamespace;
          Event.Payload = llvm::join(Enclosing, "::");
          Callback(Event);
        }
        BraceStack.pop_back();
      }
      break;
    case tok::semi:
      if (State == UsingNamespaceName) {
        // Parsed: using namespace <name> ;
        Event.Trigger = NamespaceEvent::UsingDirective;
        Event.Payload = std::move(NSName);
        Callback(Event);
      }
      State = Default;
      break;
    default:
      State = Default;
      break;
    }
  });
}

// Returns the prefix namespaces of NS: {"" ... NS}.
llvm::SmallVector<llvm::StringRef, 8> ancestorNamespaces(llvm::StringRef NS) {
  llvm::SmallVector<llvm::StringRef, 8> Results;
  Results.push_back(NS.take_front(0));
  NS.split(Results, "::", /*MaxSplit=*/-1, /*KeepEmpty=*/false);
  for (llvm::StringRef &R : Results)
    R = NS.take_front(R.end() - NS.begin());
  return Results;
}

} // namespace

std::vector<std::string> visibleNamespaces(llvm::StringRef Code,
                                           const format::FormatStyle &Style) {
  std::string Current;
  // Map from namespace to (resolved) namespaces introduced via using directive.
  llvm::StringMap<llvm::StringSet<>> UsingDirectives;

  parseNamespaceEvents(Code, Style, [&](NamespaceEvent Event) {
    llvm::StringRef NS = Event.Payload;
    switch (Event.Trigger) {
    case NamespaceEvent::BeginNamespace:
    case NamespaceEvent::EndNamespace:
      Current = std::move(Event.Payload);
      break;
    case NamespaceEvent::UsingDirective:
      if (NS.consume_front("::"))
        UsingDirectives[Current].insert(NS);
      else {
        for (llvm::StringRef Enclosing : ancestorNamespaces(Current)) {
          if (Enclosing.empty())
            UsingDirectives[Current].insert(NS);
          else
            UsingDirectives[Current].insert((Enclosing + "::" + NS).str());
        }
      }
      break;
    }
  });

  std::vector<std::string> Found;
  for (llvm::StringRef Enclosing : ancestorNamespaces(Current)) {
    Found.push_back(Enclosing);
    auto It = UsingDirectives.find(Enclosing);
    if (It != UsingDirectives.end())
      for (const auto &Used : It->second)
        Found.push_back(Used.getKey());
  }

  llvm::sort(Found, [&](const std::string &LHS, const std::string &RHS) {
    if (Current == RHS)
      return false;
    if (Current == LHS)
      return true;
    return LHS < RHS;
  });
  Found.erase(std::unique(Found.begin(), Found.end()), Found.end());
  return Found;
}

llvm::StringSet<> collectWords(llvm::StringRef Content) {
  // We assume short words are not significant.
  // We may want to consider other stopwords, e.g. language keywords.
  // (A very naive implementation showed no benefit, but lexing might do better)
  static constexpr int MinWordLength = 4;

  std::vector<CharRole> Roles(Content.size());
  calculateRoles(Content, Roles);

  llvm::StringSet<> Result;
  llvm::SmallString<256> Word;
  auto Flush = [&] {
    if (Word.size() >= MinWordLength) {
      for (char &C : Word)
        C = llvm::toLower(C);
      Result.insert(Word);
    }
    Word.clear();
  };
  for (unsigned I = 0; I < Content.size(); ++I) {
    switch (Roles[I]) {
    case Head:
      Flush();
      LLVM_FALLTHROUGH;
    case Tail:
      Word.push_back(Content[I]);
      break;
    case Unknown:
    case Separator:
      Flush();
      break;
    }
  }
  Flush();

  return Result;
}

llvm::Optional<DefinedMacro> locateMacroAt(SourceLocation Loc,
                                           Preprocessor &PP) {
  const auto &SM = PP.getSourceManager();
  const auto &LangOpts = PP.getLangOpts();
  Token Result;
  if (Lexer::getRawToken(SM.getSpellingLoc(Loc), Result, SM, LangOpts, false))
    return None;
  if (Result.is(tok::raw_identifier))
    PP.LookUpIdentifierInfo(Result);
  IdentifierInfo *IdentifierInfo = Result.getIdentifierInfo();
  if (!IdentifierInfo || !IdentifierInfo->hadMacroDefinition())
    return None;

  std::pair<FileID, unsigned int> DecLoc = SM.getDecomposedExpansionLoc(Loc);
  // Get the definition just before the searched location so that a macro
  // referenced in a '#undef MACRO' can still be found.
  SourceLocation BeforeSearchedLocation =
      SM.getMacroArgExpandedLocation(SM.getLocForStartOfFile(DecLoc.first)
                                         .getLocWithOffset(DecLoc.second - 1));
  MacroDefinition MacroDef =
      PP.getMacroDefinitionAtLoc(IdentifierInfo, BeforeSearchedLocation);
  if (auto *MI = MacroDef.getMacroInfo())
    return DefinedMacro{IdentifierInfo->getName(), MI};
  return None;
}

llvm::Expected<std::string> Edit::apply() const {
  return tooling::applyAllReplacements(InitialCode, Replacements);
}

std::vector<TextEdit> Edit::asTextEdits() const {
  return replacementsToEdits(InitialCode, Replacements);
}

bool Edit::canApplyTo(llvm::StringRef Code) const {
  // Create line iterators, since line numbers are important while applying our
  // edit we cannot skip blank lines.
  auto LHS = llvm::MemoryBuffer::getMemBuffer(Code);
  llvm::line_iterator LHSIt(*LHS, /*SkipBlanks=*/false);

  auto RHS = llvm::MemoryBuffer::getMemBuffer(InitialCode);
  llvm::line_iterator RHSIt(*RHS, /*SkipBlanks=*/false);

  // Compare the InitialCode we prepared the edit for with the Code we received
  // line by line to make sure there are no differences.
  // FIXME: This check is too conservative now, it should be enough to only
  // check lines around the replacements contained inside the Edit.
  while (!LHSIt.is_at_eof() && !RHSIt.is_at_eof()) {
    if (*LHSIt != *RHSIt)
      return false;
    ++LHSIt;
    ++RHSIt;
  }

  // After we reach EOF for any of the files we make sure the other one doesn't
  // contain any additional content except empty lines, they should not
  // interfere with the edit we produced.
  while (!LHSIt.is_at_eof()) {
    if (!LHSIt->empty())
      return false;
    ++LHSIt;
  }
  while (!RHSIt.is_at_eof()) {
    if (!RHSIt->empty())
      return false;
    ++RHSIt;
  }
  return true;
}

llvm::Error reformatEdit(Edit &E, const format::FormatStyle &Style) {
  if (auto NewEdits = cleanupAndFormat(E.InitialCode, E.Replacements, Style))
    E.Replacements = std::move(*NewEdits);
  else
    return NewEdits.takeError();
  return llvm::Error::success();
}

EligibleRegion getEligiblePoints(llvm::StringRef Code,
                                 llvm::StringRef FullyQualifiedName,
                                 const format::FormatStyle &Style) {
  EligibleRegion ER;
  // Start with global namespace.
  std::vector<std::string> Enclosing = {""};
  // FIXME: In addition to namespaces try to generate events for function
  // definitions as well. One might use a closing parantheses(")" followed by an
  // opening brace "{" to trigger the start.
  parseNamespaceEvents(Code, Style, [&](NamespaceEvent Event) {
    // Using Directives only introduces declarations to current scope, they do
    // not change the current namespace, so skip them.
    if (Event.Trigger == NamespaceEvent::UsingDirective)
      return;
    // Do not qualify the global namespace.
    if (!Event.Payload.empty())
      Event.Payload.append("::");

    std::string CurrentNamespace;
    if (Event.Trigger == NamespaceEvent::BeginNamespace) {
      Enclosing.emplace_back(std::move(Event.Payload));
      CurrentNamespace = Enclosing.back();
      // parseNameSpaceEvents reports the beginning position of a token; we want
      // to insert after '{', so increment by one.
      ++Event.Pos.character;
    } else {
      // Event.Payload points to outer namespace when exiting a scope, so use
      // the namespace we've last entered instead.
      CurrentNamespace = std::move(Enclosing.back());
      Enclosing.pop_back();
      assert(Enclosing.back() == Event.Payload);
    }

    // Ignore namespaces that are not a prefix of the target.
    if (!FullyQualifiedName.startswith(CurrentNamespace))
      return;

    // Prefer the namespace that shares the longest prefix with target.
    if (CurrentNamespace.size() > ER.EnclosingNamespace.size()) {
      ER.EligiblePoints.clear();
      ER.EnclosingNamespace = CurrentNamespace;
    }
    if (CurrentNamespace.size() == ER.EnclosingNamespace.size())
      ER.EligiblePoints.emplace_back(std::move(Event.Pos));
  });
  // If there were no shared namespaces just return EOF.
  if (ER.EligiblePoints.empty()) {
    assert(ER.EnclosingNamespace.empty());
    ER.EligiblePoints.emplace_back(offsetToPosition(Code, Code.size()));
  }
  return ER;
}

bool isHeaderFile(llvm::StringRef FileName,
                  llvm::Optional<LangOptions> LangOpts) {
  // Respect the langOpts, for non-file-extension cases, e.g. standard library
  // files.
  if (LangOpts && LangOpts->IsHeaderFile)
    return true;
  namespace types = clang::driver::types;
  auto Lang = types::lookupTypeForExtension(
      llvm::sys::path::extension(FileName).substr(1));
  return Lang != types::TY_INVALID && types::onlyPrecompileType(Lang);
}

} // namespace clangd
} // namespace clang