//===- 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); // Strange exponential notation! StrTmp[static_cast<unsigned>(F1NumEnd-F1P)] = 'e'; 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); // Strange exponential notation! StrTmp[static_cast<unsigned>(F2NumEnd-F2P)] = 'e'; 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; }