2003-12-29 05:07:02 +00:00
|
|
|
//===-- StringExtras.cpp - Implement the StringExtras header --------------===//
|
2005-04-21 22:55:34 +00:00
|
|
|
//
|
2003-12-29 05:07:02 +00:00
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
2007-12-29 20:36:04 +00:00
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
2005-04-21 22:55:34 +00:00
|
|
|
//
|
2003-12-29 05:07:02 +00:00
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file implements the StringExtras.h header
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2004-09-01 22:55:40 +00:00
|
|
|
#include "llvm/ADT/StringExtras.h"
|
2008-02-20 11:08:44 +00:00
|
|
|
#include <cstring>
|
2003-12-29 05:07:02 +00:00
|
|
|
using namespace llvm;
|
|
|
|
|
|
|
|
/// 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 Source source string is updated in place to remove the returned string
|
|
|
|
/// and any delimiter prefix from it.
|
|
|
|
std::string llvm::getToken(std::string &Source, const char *Delimiters) {
|
|
|
|
unsigned NumDelimiters = std::strlen(Delimiters);
|
|
|
|
|
|
|
|
// Figure out where the token starts.
|
|
|
|
std::string::size_type Start =
|
|
|
|
Source.find_first_not_of(Delimiters, 0, NumDelimiters);
|
|
|
|
if (Start == std::string::npos) Start = Source.size();
|
|
|
|
|
|
|
|
// Find the next occurance of the delimiter.
|
|
|
|
std::string::size_type End =
|
|
|
|
Source.find_first_of(Delimiters, Start, NumDelimiters);
|
|
|
|
if (End == std::string::npos) End = Source.size();
|
|
|
|
|
|
|
|
// Create the return token.
|
|
|
|
std::string Result = std::string(Source.begin()+Start, Source.begin()+End);
|
2005-04-21 22:55:34 +00:00
|
|
|
|
2003-12-29 05:07:02 +00:00
|
|
|
// Erase the token that we read in.
|
|
|
|
Source.erase(Source.begin(), Source.begin()+End);
|
2005-04-21 22:55:34 +00:00
|
|
|
|
2003-12-29 05:07:02 +00:00
|
|
|
return Result;
|
|
|
|
}
|
2006-07-14 22:54:39 +00:00
|
|
|
|
2006-11-28 22:32:35 +00:00
|
|
|
/// SplitString - Split up the specified string according to the specified
|
|
|
|
/// delimiters, appending the result fragments to the output list.
|
|
|
|
void llvm::SplitString(const std::string &Source,
|
|
|
|
std::vector<std::string> &OutFragments,
|
|
|
|
const char *Delimiters) {
|
|
|
|
std::string S = Source;
|
|
|
|
|
|
|
|
std::string S2 = getToken(S, Delimiters);
|
|
|
|
while (!S2.empty()) {
|
|
|
|
OutFragments.push_back(S2);
|
|
|
|
S2 = getToken(S, Delimiters);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2006-07-14 22:54:39 +00:00
|
|
|
|
|
|
|
/// UnescapeString - Modify the argument string, turning two character sequences
|
2007-08-05 19:33:11 +00:00
|
|
|
/// @verbatim
|
|
|
|
/// like '\\' 'n' into '\n'. This handles: \e \a \b \f \n \r \t \v \' \ and
|
2006-07-14 22:54:39 +00:00
|
|
|
/// \num (where num is a 1-3 byte octal value).
|
2007-08-05 19:33:11 +00:00
|
|
|
/// @endverbatim
|
2006-07-14 22:54:39 +00:00
|
|
|
void llvm::UnescapeString(std::string &Str) {
|
|
|
|
for (unsigned i = 0; i != Str.size(); ++i) {
|
|
|
|
if (Str[i] == '\\' && i != Str.size()-1) {
|
|
|
|
switch (Str[i+1]) {
|
|
|
|
default: continue; // Don't execute the code after the switch.
|
|
|
|
case 'a': Str[i] = '\a'; break;
|
|
|
|
case 'b': Str[i] = '\b'; break;
|
|
|
|
case 'e': Str[i] = 27; break;
|
|
|
|
case 'f': Str[i] = '\f'; break;
|
|
|
|
case 'n': Str[i] = '\n'; break;
|
|
|
|
case 'r': Str[i] = '\r'; break;
|
|
|
|
case 't': Str[i] = '\t'; break;
|
|
|
|
case 'v': Str[i] = '\v'; break;
|
|
|
|
case '\'': Str[i] = '\''; break;
|
|
|
|
case '\\': Str[i] = '\\'; break;
|
|
|
|
}
|
|
|
|
// Nuke the second character.
|
|
|
|
Str.erase(Str.begin()+i+1);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/// EscapeString - Modify the argument string, turning '\\' and anything that
|
|
|
|
/// doesn't satisfy std::isprint into an escape sequence.
|
|
|
|
void llvm::EscapeString(std::string &Str) {
|
|
|
|
for (unsigned i = 0; i != Str.size(); ++i) {
|
|
|
|
if (Str[i] == '\\') {
|
|
|
|
++i;
|
|
|
|
Str.insert(Str.begin()+i, '\\');
|
|
|
|
} else if (Str[i] == '\t') {
|
|
|
|
Str[i++] = '\\';
|
|
|
|
Str.insert(Str.begin()+i, 't');
|
|
|
|
} else if (Str[i] == '\n') {
|
|
|
|
Str[i++] = '\\';
|
|
|
|
Str.insert(Str.begin()+i, 'n');
|
|
|
|
} else if (!std::isprint(Str[i])) {
|
|
|
|
// Always expand to a 3-digit octal escape.
|
|
|
|
unsigned Char = Str[i];
|
|
|
|
Str[i++] = '\\';
|
|
|
|
Str.insert(Str.begin()+i++, '0'+((Char/64) & 7));
|
|
|
|
Str.insert(Str.begin()+i++, '0'+((Char/8) & 7));
|
|
|
|
Str.insert(Str.begin()+i , '0'+( Char & 7));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|