llvm-project/llvm/lib/Support/FileUtilities.cpp

//===- Support/FileUtilities.cpp - File System Utilities ------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements a family of utility functions which are useful for doing
// various things with files.
//
//===----------------------------------------------------------------------===//

#include "llvm/Support/FileUtilities.h"
#include "llvm/System/Path.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/ADT/OwningPtr.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/StringExtras.h"
#include <cstdlib>
#include <cstring>
#include <cctype>
using namespace llvm;

static bool isSignedChar(char C) {
  return (C == '+' || C == '-');
}

static bool isExponentChar(char C) {
  switch (C) {
  case 'D':  // Strange exponential notation.
  case 'd':  // Strange exponential notation.
  case 'e':
  case 'E': return true;
  default: return false;
  }
}

static bool isNumberChar(char C) {
  switch (C) {
  case '0': case '1': case '2': case '3': case '4':
  case '5': case '6': case '7': case '8': case '9':
  case '.': return true;
  default: return isSignedChar(C) || isExponentChar(C);
  }
}

static const char *BackupNumber(const char *Pos, const char *FirstChar) {
  // If we didn't stop in the middle of a number, don't backup.
  if (!isNumberChar(*Pos)) return Pos;

  // Otherwise, return to the start of the number.
  while (Pos > FirstChar && isNumberChar(Pos[-1])) {
    --Pos;
    if (Pos > FirstChar && isSignedChar(Pos[0]) && !isExponentChar(Pos[-1]))
      break;
  }
  return Pos;
}

/// EndOfNumber - Return the first character that is not part of the specified
/// number.  This assumes that the buffer is null terminated, so it won't fall
/// off the end.
static const char *EndOfNumber(const char *Pos) {
  while (isNumberChar(*Pos))
    ++Pos;
  return Pos;
}

/// CompareNumbers - compare two numbers, returning true if they are different.
static bool CompareNumbers(const char *&F1P, const char *&F2P,
                           const char *F1End, const char *F2End,
                           double AbsTolerance, double RelTolerance,
                           std::string *ErrorMsg) {
  const char *F1NumEnd, *F2NumEnd;
  double V1 = 0.0, V2 = 0.0;

  // If one of the positions is at a space and the other isn't, chomp up 'til
  // the end of the space.
  while (isspace(*F1P) && F1P != F1End)
    ++F1P;
  while (isspace(*F2P) && F2P != F2End)
    ++F2P;

  // If we stop on numbers, compare their difference.
  if (!isNumberChar(*F1P) || !isNumberChar(*F2P)) {
    // The diff failed.
    F1NumEnd = F1P;
    F2NumEnd = F2P;
  } else {
    // Note that some ugliness is built into this to permit support for numbers
    // that use "D" or "d" as their exponential marker, e.g. "1.234D45".  This
    // occurs in 200.sixtrack in spec2k.
    V1 = strtod(F1P, const_cast<char**>(&F1NumEnd));
    V2 = strtod(F2P, const_cast<char**>(&F2NumEnd));

    if (*F1NumEnd == 'D' || *F1NumEnd == 'd') {
      // Copy string into tmp buffer to replace the 'D' with an 'e'.
      SmallString<200> StrTmp(F1P, EndOfNumber(F1NumEnd)+1);
      StrTmp[F1NumEnd-F1P] = 'e';  // Strange exponential notation!
      
      V1 = strtod(&StrTmp[0], const_cast<char**>(&F1NumEnd));
      F1NumEnd = F1P + (F1NumEnd-&StrTmp[0]);
    }
    
    if (*F2NumEnd == 'D' || *F2NumEnd == 'd') {
      // Copy string into tmp buffer to replace the 'D' with an 'e'.
      SmallString<200> StrTmp(F2P, EndOfNumber(F2NumEnd)+1);
      StrTmp[F2NumEnd-F2P] = 'e';  // Strange exponential notation!
      
      V2 = strtod(&StrTmp[0], const_cast<char**>(&F2NumEnd));
      F2NumEnd = F2P + (F2NumEnd-&StrTmp[0]);
    }
  }

  if (F1NumEnd == F1P || F2NumEnd == F2P) {
    if (ErrorMsg) {
      *ErrorMsg = "FP Comparison failed, not a numeric difference between '";
      *ErrorMsg += F1P[0];
      *ErrorMsg += "' and '";
      *ErrorMsg += F2P[0];
      *ErrorMsg += "'";
    }
    return true;
  }

  // Check to see if these are inside the absolute tolerance
  if (AbsTolerance < std::abs(V1-V2)) {
    // Nope, check the relative tolerance...
    double Diff;
    if (V2)
      Diff = std::abs(V1/V2 - 1.0);
    else if (V1)
      Diff = std::abs(V2/V1 - 1.0);
    else
      Diff = 0;  // Both zero.
    if (Diff > RelTolerance) {
      if (ErrorMsg) {
        *ErrorMsg = "Compared: " + ftostr(V1) + " and " + ftostr(V2) + "\n";
        *ErrorMsg += "abs. diff = " + ftostr(std::abs(V1-V2)) + 
                     " rel.diff = " + ftostr(Diff) + "\n";
        *ErrorMsg += "Out of tolerance: rel/abs: " + ftostr(RelTolerance) +
                     "/" + ftostr(AbsTolerance);
      }
      return true;
    }
  }

  // Otherwise, advance our read pointers to the end of the numbers.
  F1P = F1NumEnd;  F2P = F2NumEnd;
  return false;
}

/// DiffFilesWithTolerance - Compare the two files specified, returning 0 if the
/// files match, 1 if they are different, and 2 if there is a file error.  This
/// function differs from DiffFiles in that you can specify an absolete and
/// relative FP error that is allowed to exist.  If you specify a string to fill
/// in for the error option, it will set the string to an error message if an
/// error occurs, allowing the caller to distinguish between a failed diff and a
/// file system error.
///
int llvm::DiffFilesWithTolerance(const sys::PathWithStatus &FileA,
                                 const sys::PathWithStatus &FileB,
                                 double AbsTol, double RelTol,
                                 std::string *Error) {
  const sys::FileStatus *FileAStat = FileA.getFileStatus(false, Error);
  if (!FileAStat)
    return 2;
  const sys::FileStatus *FileBStat = FileB.getFileStatus(false, Error);
  if (!FileBStat)
    return 2;

  // Check for zero length files because some systems croak when you try to
  // mmap an empty file.
  size_t A_size = FileAStat->getSize();
  size_t B_size = FileBStat->getSize();

  // If they are both zero sized then they're the same
  if (A_size == 0 && B_size == 0)
    return 0;

  // If only one of them is zero sized then they can't be the same
  if ((A_size == 0 || B_size == 0)) {
    if (Error)
      *Error = "Files differ: one is zero-sized, the other isn't";
    return 1;
  }

  // Now its safe to mmap the files into memory becasue both files
  // have a non-zero size.
  OwningPtr<MemoryBuffer> F1(MemoryBuffer::getFile(FileA.c_str(), Error));
  OwningPtr<MemoryBuffer> F2(MemoryBuffer::getFile(FileB.c_str(), Error));
  if (F1 == 0 || F2 == 0)
    return 2;
  
  // Okay, now that we opened the files, scan them for the first difference.
  const char *File1Start = F1->getBufferStart();
  const char *File2Start = F2->getBufferStart();
  const char *File1End = F1->getBufferEnd();
  const char *File2End = F2->getBufferEnd();
  const char *F1P = File1Start;
  const char *F2P = File2Start;

  if (A_size == B_size) {
    // Are the buffers identical?  Common case: Handle this efficiently.
    if (std::memcmp(File1Start, File2Start, A_size) == 0)
      return 0;

    if (AbsTol == 0 && RelTol == 0) {
      if (Error)
        *Error = "Files differ without tolerance allowance";
      return 1;   // Files different!
    }
  }

  bool CompareFailed = false;
  while (1) {
    // Scan for the end of file or next difference.
    while (F1P < File1End && F2P < File2End && *F1P == *F2P)
      ++F1P, ++F2P;

    if (F1P >= File1End || F2P >= File2End) break;

    // Okay, we must have found a difference.  Backup to the start of the
    // current number each stream is at so that we can compare from the
    // beginning.
    F1P = BackupNumber(F1P, File1Start);
    F2P = BackupNumber(F2P, File2Start);

    // Now that we are at the start of the numbers, compare them, exiting if
    // they don't match.
    if (CompareNumbers(F1P, F2P, File1End, File2End, AbsTol, RelTol, Error)) {
      CompareFailed = true;
      break;
    }
  }

  // Okay, we reached the end of file.  If both files are at the end, we
  // succeeded.
  bool F1AtEnd = F1P >= File1End;
  bool F2AtEnd = F2P >= File2End;
  if (!CompareFailed && (!F1AtEnd || !F2AtEnd)) {
    // Else, we might have run off the end due to a number: backup and retry.
    if (F1AtEnd && isNumberChar(F1P[-1])) --F1P;
    if (F2AtEnd && isNumberChar(F2P[-1])) --F2P;
    F1P = BackupNumber(F1P, File1Start);
    F2P = BackupNumber(F2P, File2Start);

    // Now that we are at the start of the numbers, compare them, exiting if
    // they don't match.
    if (CompareNumbers(F1P, F2P, File1End, File2End, AbsTol, RelTol, Error))
      CompareFailed = true;

    // If we found the end, we succeeded.
    if (F1P < File1End || F2P < File2End)
      CompareFailed = true;
  }

  return CompareFailed;
}