mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 18:54:02 +01:00
8fc32bf8f9
The standard library functions ::isprint/std::isprint have platform-
and locale-dependent behavior which makes LLVM's output less
predictable. In particular, regression tests my fail depending on the
implementation of these functions.
Implement llvm::isPrint in StringExtras.h with a standard behavior and
replace all uses of ::isprint/std::isprint by a call it llvm::isPrint.
The function is inlined and does not look up language settings so it
should perform better than the standard library's version.
Such a replacement has already been done for isdigit, isalpha, isxdigit
in r314883. gtest does the same in gtest-printers.cc using the following
justification:
// Returns true if c is a printable ASCII character. We test the
// value of c directly instead of calling isprint(), which is buggy on
// Windows Mobile.
inline bool IsPrintableAscii(wchar_t c) {
return 0x20 <= c && c <= 0x7E;
}
Similar issues have also been encountered by Julia:
https://github.com/JuliaLang/julia/issues/7416
I noticed the problem myself when on Windows isprint('\t') started to
evaluate to true (see https://stackoverflow.com/questions/51435249) and
thus caused several unit tests to fail. The result of isprint doesn't
seem to be well-defined even for ASCII characters. Therefore I suggest
to replace isprint by a platform-independent version.
Differential Revision: https://reviews.llvm.org/D49680
llvm-svn: 338034
92 lines
3.1 KiB
C++
92 lines
3.1 KiB
C++
//===-- StringExtras.cpp - Implement the StringExtras header --------------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file implements the StringExtras.h header
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "llvm/ADT/StringExtras.h"
|
|
#include "llvm/ADT/SmallVector.h"
|
|
#include "llvm/Support/raw_ostream.h"
|
|
using namespace llvm;
|
|
|
|
/// StrInStrNoCase - Portable version of strcasestr. Locates the first
|
|
/// occurrence of string 's1' in string 's2', ignoring case. Returns
|
|
/// the offset of s2 in s1 or npos if s2 cannot be found.
|
|
StringRef::size_type llvm::StrInStrNoCase(StringRef s1, StringRef s2) {
|
|
size_t N = s2.size(), M = s1.size();
|
|
if (N > M)
|
|
return StringRef::npos;
|
|
for (size_t i = 0, e = M - N + 1; i != e; ++i)
|
|
if (s1.substr(i, N).equals_lower(s2))
|
|
return i;
|
|
return StringRef::npos;
|
|
}
|
|
|
|
/// getToken - This function extracts one token from source, ignoring any
|
|
/// leading characters that appear in the Delimiters string, and ending the
|
|
/// token at any of the characters that appear in the Delimiters string. If
|
|
/// there are no tokens in the source string, an empty string is returned.
|
|
/// The function returns a pair containing the extracted token and the
|
|
/// remaining tail string.
|
|
std::pair<StringRef, StringRef> llvm::getToken(StringRef Source,
|
|
StringRef Delimiters) {
|
|
// Figure out where the token starts.
|
|
StringRef::size_type Start = Source.find_first_not_of(Delimiters);
|
|
|
|
// Find the next occurrence of the delimiter.
|
|
StringRef::size_type End = Source.find_first_of(Delimiters, Start);
|
|
|
|
return std::make_pair(Source.slice(Start, End), Source.substr(End));
|
|
}
|
|
|
|
/// SplitString - Split up the specified string according to the specified
|
|
/// delimiters, appending the result fragments to the output list.
|
|
void llvm::SplitString(StringRef Source,
|
|
SmallVectorImpl<StringRef> &OutFragments,
|
|
StringRef Delimiters) {
|
|
std::pair<StringRef, StringRef> S = getToken(Source, Delimiters);
|
|
while (!S.first.empty()) {
|
|
OutFragments.push_back(S.first);
|
|
S = getToken(S.second, Delimiters);
|
|
}
|
|
}
|
|
|
|
void llvm::printEscapedString(StringRef Name, raw_ostream &Out) {
|
|
for (unsigned i = 0, e = Name.size(); i != e; ++i) {
|
|
unsigned char C = Name[i];
|
|
if (isPrint(C) && C != '\\' && C != '"')
|
|
Out << C;
|
|
else
|
|
Out << '\\' << hexdigit(C >> 4) << hexdigit(C & 0x0F);
|
|
}
|
|
}
|
|
|
|
void llvm::printHTMLEscaped(StringRef String, raw_ostream &Out) {
|
|
for (char C : String) {
|
|
if (C == '&')
|
|
Out << "&";
|
|
else if (C == '<')
|
|
Out << "<";
|
|
else if (C == '>')
|
|
Out << ">";
|
|
else if (C == '\"')
|
|
Out << """;
|
|
else if (C == '\'')
|
|
Out << "'";
|
|
else
|
|
Out << C;
|
|
}
|
|
}
|
|
|
|
void llvm::printLowerCase(StringRef String, raw_ostream &Out) {
|
|
for (const char C : String)
|
|
Out << toLower(C);
|
|
}
|