summaryrefslogtreecommitdiff
path: root/lib/Support/FileUtilities.cpp
blob: 68953d347fe06567ff198e4514507924ba715c73 (plain)
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
//===- 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/ADT/SmallString.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/raw_ostream.h"
#include <cctype>
#include <cstdlib>
#include <cstring>
#include <system_error>
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.
  bool HasPeriod = false;
  while (Pos > FirstChar && isNumberChar(Pos[-1])) {
    // Backup over at most one period.
    if (Pos[-1] == '.') {
      if (HasPeriod)
        break;
      HasPeriod = true;
    }

    --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(static_cast<unsigned char>(*F1P)) && F1P != F1End)
    ++F1P;
  while (isspace(static_cast<unsigned char>(*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) {
        raw_string_ostream(*ErrorMsg)
          << "Compared: " << V1 << " and " << V2 << '\n'
          << "abs. diff = " << std::abs(V1-V2) << " rel.diff = " << Diff << '\n'
          << "Out of tolerance: rel/abs: " << RelTolerance << '/'
          << 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(StringRef NameA,
                                 StringRef NameB,
                                 double AbsTol, double RelTol,
                                 std::string *Error) {
  // Now its safe to mmap the files into memory because both files
  // have a non-zero size.
  std::unique_ptr<MemoryBuffer> F1;
  if (error_code ec = MemoryBuffer::getFile(NameA, F1)) {
    if (Error)
      *Error = ec.message();
    return 2;
  }
  std::unique_ptr<MemoryBuffer> F2;
  if (error_code ec = MemoryBuffer::getFile(NameB, F2)) {
    if (Error)
      *Error = ec.message();
    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;
  uint64_t A_size = F1->getBufferSize();
  uint64_t B_size = F2->getBufferSize();

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

  // Otherwise, we are done a tolerances are set.
  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;
}