2017-05-17 01:10:25 +02:00
|
|
|
//===- llvm/ADT/StringExtras.h - Useful string functions --------*- C++ -*-===//
|
2005-04-21 22:19:05 +02:00
|
|
|
//
|
2003-10-20 21:46:57 +02:00
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
2007-12-29 20:59:42 +01:00
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
2005-04-21 22:19:05 +02:00
|
|
|
//
|
2003-10-20 21:46:57 +02:00
|
|
|
//===----------------------------------------------------------------------===//
|
2001-06-06 22:29:01 +02:00
|
|
|
//
|
|
|
|
// This file contains some functions that are useful when dealing with strings.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2004-09-02 00:55:40 +02:00
|
|
|
#ifndef LLVM_ADT_STRINGEXTRAS_H
|
|
|
|
#define LLVM_ADT_STRINGEXTRAS_H
|
2001-06-06 22:29:01 +02:00
|
|
|
|
2017-06-14 22:11:46 +02:00
|
|
|
#include "llvm/ADT/ArrayRef.h"
|
2017-06-23 14:55:02 +02:00
|
|
|
#include "llvm/ADT/SmallString.h"
|
2009-10-17 20:21:06 +02:00
|
|
|
#include "llvm/ADT/StringRef.h"
|
2017-05-17 01:10:25 +02:00
|
|
|
#include <cassert>
|
|
|
|
#include <cstddef>
|
|
|
|
#include <cstdint>
|
2017-06-23 14:55:02 +02:00
|
|
|
#include <cstdlib>
|
2017-05-17 01:10:25 +02:00
|
|
|
#include <cstring>
|
2017-06-06 13:49:48 +02:00
|
|
|
#include <iterator>
|
2017-05-17 01:10:25 +02:00
|
|
|
#include <string>
|
|
|
|
#include <utility>
|
2001-10-29 14:24:31 +01:00
|
|
|
|
2003-11-11 23:41:34 +01:00
|
|
|
namespace llvm {
|
2017-05-17 01:10:25 +02:00
|
|
|
|
2010-01-11 19:03:24 +01:00
|
|
|
template<typename T> class SmallVectorImpl;
|
2017-05-17 01:10:25 +02:00
|
|
|
class raw_ostream;
|
2003-11-11 23:41:34 +01:00
|
|
|
|
2010-11-27 14:19:46 +01:00
|
|
|
/// hexdigit - Return the hexadecimal character for the
|
2012-09-13 14:34:29 +02:00
|
|
|
/// given number \p X (which should be less than 16).
|
2010-11-27 14:19:46 +01:00
|
|
|
static inline char hexdigit(unsigned X, bool LowerCase = false) {
|
|
|
|
const char HexChar = LowerCase ? 'a' : 'A';
|
|
|
|
return X < 10 ? '0' + X : HexChar + X - 10;
|
2008-10-15 01:26:20 +02:00
|
|
|
}
|
|
|
|
|
2014-01-27 05:07:36 +01:00
|
|
|
/// Construct a string ref from a boolean.
|
|
|
|
static inline StringRef toStringRef(bool B) {
|
|
|
|
return StringRef(B ? "true" : "false");
|
|
|
|
}
|
|
|
|
|
2017-06-14 22:11:46 +02:00
|
|
|
/// Construct a string ref from an array ref of unsigned chars.
|
|
|
|
static inline StringRef toStringRef(ArrayRef<uint8_t> Input) {
|
|
|
|
return StringRef(reinterpret_cast<const char *>(Input.begin()), Input.size());
|
|
|
|
}
|
|
|
|
|
2013-01-18 22:45:30 +01:00
|
|
|
/// Interpret the given character \p C as a hexadecimal digit and return its
|
|
|
|
/// value.
|
|
|
|
///
|
|
|
|
/// If \p C is not a valid hex digit, -1U is returned.
|
|
|
|
static inline unsigned hexDigitValue(char C) {
|
|
|
|
if (C >= '0' && C <= '9') return C-'0';
|
|
|
|
if (C >= 'a' && C <= 'f') return C-'a'+10U;
|
|
|
|
if (C >= 'A' && C <= 'F') return C-'A'+10U;
|
|
|
|
return -1U;
|
|
|
|
}
|
|
|
|
|
2016-01-31 21:00:22 +01:00
|
|
|
static inline std::string utohexstr(uint64_t X, bool LowerCase = false) {
|
|
|
|
char Buffer[17];
|
|
|
|
char *BufPtr = std::end(Buffer);
|
|
|
|
|
|
|
|
if (X == 0) *--BufPtr = '0';
|
2002-04-07 10:36:19 +02:00
|
|
|
|
|
|
|
while (X) {
|
2005-01-28 08:22:20 +01:00
|
|
|
unsigned char Mod = static_cast<unsigned char>(X) & 15;
|
2014-07-14 23:56:54 +02:00
|
|
|
*--BufPtr = hexdigit(Mod, LowerCase);
|
2002-04-07 10:36:19 +02:00
|
|
|
X >>= 4;
|
|
|
|
}
|
2009-01-09 20:25:42 +01:00
|
|
|
|
2016-01-31 21:00:22 +01:00
|
|
|
return std::string(BufPtr, std::end(Buffer));
|
2002-04-07 10:36:19 +02:00
|
|
|
}
|
|
|
|
|
2016-04-21 07:54:23 +02:00
|
|
|
/// Convert buffer \p Input to its hexadecimal representation.
|
|
|
|
/// The returned string is double the size of \p Input.
|
2017-06-14 22:11:46 +02:00
|
|
|
inline std::string toHex(StringRef Input) {
|
2016-04-21 07:54:23 +02:00
|
|
|
static const char *const LUT = "0123456789ABCDEF";
|
|
|
|
size_t Length = Input.size();
|
|
|
|
|
|
|
|
std::string Output;
|
|
|
|
Output.reserve(2 * Length);
|
|
|
|
for (size_t i = 0; i < Length; ++i) {
|
|
|
|
const unsigned char c = Input[i];
|
|
|
|
Output.push_back(LUT[c >> 4]);
|
|
|
|
Output.push_back(LUT[c & 15]);
|
|
|
|
}
|
|
|
|
return Output;
|
|
|
|
}
|
|
|
|
|
2017-06-14 22:11:46 +02:00
|
|
|
inline std::string toHex(ArrayRef<uint8_t> Input) {
|
|
|
|
return toHex(toStringRef(Input));
|
|
|
|
}
|
|
|
|
|
2017-04-25 22:21:35 +02:00
|
|
|
static inline uint8_t hexFromNibbles(char MSB, char LSB) {
|
|
|
|
unsigned U1 = hexDigitValue(MSB);
|
|
|
|
unsigned U2 = hexDigitValue(LSB);
|
|
|
|
assert(U1 != -1U && U2 != -1U);
|
|
|
|
|
|
|
|
return static_cast<uint8_t>((U1 << 4) | U2);
|
|
|
|
}
|
|
|
|
|
|
|
|
/// Convert hexadecimal string \p Input to its binary representation.
|
|
|
|
/// The return string is half the size of \p Input.
|
|
|
|
static inline std::string fromHex(StringRef Input) {
|
|
|
|
if (Input.empty())
|
|
|
|
return std::string();
|
|
|
|
|
|
|
|
std::string Output;
|
|
|
|
Output.reserve((Input.size() + 1) / 2);
|
|
|
|
if (Input.size() % 2 == 1) {
|
|
|
|
Output.push_back(hexFromNibbles('0', Input.front()));
|
|
|
|
Input = Input.drop_front();
|
|
|
|
}
|
|
|
|
|
|
|
|
assert(Input.size() % 2 == 0);
|
|
|
|
while (!Input.empty()) {
|
|
|
|
uint8_t Hex = hexFromNibbles(Input[0], Input[1]);
|
|
|
|
Output.push_back(Hex);
|
|
|
|
Input = Input.drop_front(2);
|
|
|
|
}
|
|
|
|
return Output;
|
|
|
|
}
|
|
|
|
|
2017-05-14 19:11:05 +02:00
|
|
|
/// \brief Convert the string \p S to an integer of the specified type using
|
|
|
|
/// the radix \p Base. If \p Base is 0, auto-detects the radix.
|
|
|
|
/// Returns true if the number was successfully converted, false otherwise.
|
|
|
|
template <typename N> bool to_integer(StringRef S, N &Num, unsigned Base = 0) {
|
|
|
|
return !S.getAsInteger(Base, Num);
|
|
|
|
}
|
|
|
|
|
2017-06-23 14:55:02 +02:00
|
|
|
namespace detail {
|
|
|
|
template <typename N>
|
|
|
|
inline bool to_float(const Twine &T, N &Num, N (*StrTo)(const char *, char **)) {
|
|
|
|
SmallString<32> Storage;
|
|
|
|
StringRef S = T.toNullTerminatedStringRef(Storage);
|
|
|
|
char *End;
|
|
|
|
N Temp = StrTo(S.data(), &End);
|
|
|
|
if (*End != '\0')
|
|
|
|
return false;
|
|
|
|
Num = Temp;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
inline bool to_float(const Twine &T, float &Num) {
|
|
|
|
return detail::to_float(T, Num, std::strtof);
|
|
|
|
}
|
|
|
|
|
|
|
|
inline bool to_float(const Twine &T, double &Num) {
|
|
|
|
return detail::to_float(T, Num, std::strtod);
|
|
|
|
}
|
|
|
|
|
|
|
|
inline bool to_float(const Twine &T, long double &Num) {
|
|
|
|
return detail::to_float(T, Num, std::strtold);
|
|
|
|
}
|
|
|
|
|
2006-05-31 23:25:50 +02:00
|
|
|
static inline std::string utostr(uint64_t X, bool isNeg = false) {
|
2010-04-11 21:00:03 +02:00
|
|
|
char Buffer[21];
|
2016-01-31 02:12:35 +01:00
|
|
|
char *BufPtr = std::end(Buffer);
|
2009-01-09 20:25:42 +01:00
|
|
|
|
2001-06-06 22:29:01 +02:00
|
|
|
if (X == 0) *--BufPtr = '0'; // Handle special case...
|
2009-01-09 20:25:42 +01:00
|
|
|
|
2001-06-06 22:29:01 +02:00
|
|
|
while (X) {
|
2004-06-04 21:10:30 +02:00
|
|
|
*--BufPtr = '0' + char(X % 10);
|
2001-06-06 22:29:01 +02:00
|
|
|
X /= 10;
|
|
|
|
}
|
2009-01-09 20:25:42 +01:00
|
|
|
|
2001-06-06 22:29:01 +02:00
|
|
|
if (isNeg) *--BufPtr = '-'; // Add negative sign...
|
2016-01-31 02:12:35 +01:00
|
|
|
return std::string(BufPtr, std::end(Buffer));
|
2001-06-06 22:29:01 +02:00
|
|
|
}
|
|
|
|
|
2006-05-24 21:21:13 +02:00
|
|
|
static inline std::string itostr(int64_t X) {
|
2005-04-21 22:19:05 +02:00
|
|
|
if (X < 0)
|
2004-08-19 00:56:12 +02:00
|
|
|
return utostr(static_cast<uint64_t>(-X), true);
|
|
|
|
else
|
|
|
|
return utostr(static_cast<uint64_t>(X));
|
|
|
|
}
|
2005-04-21 22:19:05 +02:00
|
|
|
|
2010-01-11 20:45:18 +01:00
|
|
|
/// 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 StrInStrNoCase(StringRef s1, StringRef s2);
|
|
|
|
|
2003-12-29 06:06:38 +01:00
|
|
|
/// 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.
|
2010-01-11 19:03:24 +01:00
|
|
|
/// The function returns a pair containing the extracted token and the
|
|
|
|
/// remaining tail string.
|
|
|
|
std::pair<StringRef, StringRef> getToken(StringRef Source,
|
|
|
|
StringRef Delimiters = " \t\n\v\f\r");
|
2003-12-29 06:06:38 +01:00
|
|
|
|
2006-11-28 23:32:35 +01:00
|
|
|
/// SplitString - Split up the specified string according to the specified
|
|
|
|
/// delimiters, appending the result fragments to the output list.
|
2010-01-11 19:03:24 +01:00
|
|
|
void SplitString(StringRef Source,
|
|
|
|
SmallVectorImpl<StringRef> &OutFragments,
|
|
|
|
StringRef Delimiters = " \t\n\v\f\r");
|
2006-11-28 23:32:35 +01:00
|
|
|
|
2011-04-15 07:18:47 +02:00
|
|
|
/// HashString - Hash function for strings.
|
2009-10-17 20:21:06 +02:00
|
|
|
///
|
2017-04-27 01:15:10 +02:00
|
|
|
/// This is the Bernstein hash function.
|
|
|
|
//
|
|
|
|
// FIXME: Investigate whether a modified bernstein hash function performs
|
|
|
|
// better: http://eternallyconfuzzled.com/tuts/algorithms/jsw_tut_hashing.aspx
|
|
|
|
// X*33+c -> X*33^c
|
|
|
|
static inline unsigned HashString(StringRef Str, unsigned Result = 0) {
|
|
|
|
for (StringRef::size_type i = 0, e = Str.size(); i != e; ++i)
|
|
|
|
Result = Result * 33 + (unsigned char)Str[i];
|
|
|
|
return Result;
|
2009-10-17 20:21:06 +02:00
|
|
|
}
|
|
|
|
|
2012-09-22 03:24:21 +02:00
|
|
|
/// Returns the English suffix for an ordinal integer (-st, -nd, -rd, -th).
|
|
|
|
static inline StringRef getOrdinalSuffix(unsigned Val) {
|
|
|
|
// It is critically important that we do this perfectly for
|
|
|
|
// user-written sequences with over 100 elements.
|
|
|
|
switch (Val % 100) {
|
|
|
|
case 11:
|
|
|
|
case 12:
|
|
|
|
case 13:
|
|
|
|
return "th";
|
|
|
|
default:
|
|
|
|
switch (Val % 10) {
|
|
|
|
case 1: return "st";
|
|
|
|
case 2: return "nd";
|
|
|
|
case 3: return "rd";
|
|
|
|
default: return "th";
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
[IR] Properly handle escape characters in Attribute::getAsString()
If an attribute name has special characters such as '\01', it is not
properly printed in LLVM assembly language format. Since the format
expects the special characters are printed as it is, it has to contain
escape characters to make it printable.
Before:
attributes #0 = { ... "counting-function"="^A__gnu_mcount_nc" ...
After:
attributes #0 = { ... "counting-function"="\01__gnu_mcount_nc" ...
Reviewers: hfinkel, rengolin, rjmccall, compnerd
Subscribers: nemanjai, mcrosier, hans, shenhan, majnemer, llvm-commits
Differential Revision: https://reviews.llvm.org/D23792
llvm-svn: 280357
2016-09-01 13:44:06 +02:00
|
|
|
/// PrintEscapedString - Print each character of the specified string, escaping
|
|
|
|
/// it if it is not printable or if it is an escape char.
|
|
|
|
void PrintEscapedString(StringRef Name, raw_ostream &Out);
|
|
|
|
|
2016-09-27 18:37:30 +02:00
|
|
|
namespace detail {
|
|
|
|
|
2013-09-03 22:43:54 +02:00
|
|
|
template <typename IteratorT>
|
|
|
|
inline std::string join_impl(IteratorT Begin, IteratorT End,
|
|
|
|
StringRef Separator, std::input_iterator_tag) {
|
|
|
|
std::string S;
|
|
|
|
if (Begin == End)
|
|
|
|
return S;
|
|
|
|
|
|
|
|
S += (*Begin);
|
|
|
|
while (++Begin != End) {
|
|
|
|
S += Separator;
|
|
|
|
S += (*Begin);
|
|
|
|
}
|
|
|
|
return S;
|
|
|
|
}
|
|
|
|
|
|
|
|
template <typename IteratorT>
|
|
|
|
inline std::string join_impl(IteratorT Begin, IteratorT End,
|
|
|
|
StringRef Separator, std::forward_iterator_tag) {
|
|
|
|
std::string S;
|
|
|
|
if (Begin == End)
|
|
|
|
return S;
|
|
|
|
|
|
|
|
size_t Len = (std::distance(Begin, End) - 1) * Separator.size();
|
|
|
|
for (IteratorT I = Begin; I != End; ++I)
|
|
|
|
Len += (*Begin).size();
|
|
|
|
S.reserve(Len);
|
|
|
|
S += (*Begin);
|
|
|
|
while (++Begin != End) {
|
|
|
|
S += Separator;
|
|
|
|
S += (*Begin);
|
|
|
|
}
|
|
|
|
return S;
|
|
|
|
}
|
|
|
|
|
2016-09-27 18:37:30 +02:00
|
|
|
template <typename Sep>
|
|
|
|
inline void join_items_impl(std::string &Result, Sep Separator) {}
|
|
|
|
|
|
|
|
template <typename Sep, typename Arg>
|
|
|
|
inline void join_items_impl(std::string &Result, Sep Separator,
|
|
|
|
const Arg &Item) {
|
|
|
|
Result += Item;
|
|
|
|
}
|
|
|
|
|
|
|
|
template <typename Sep, typename Arg1, typename... Args>
|
|
|
|
inline void join_items_impl(std::string &Result, Sep Separator, const Arg1 &A1,
|
|
|
|
Args &&... Items) {
|
|
|
|
Result += A1;
|
|
|
|
Result += Separator;
|
|
|
|
join_items_impl(Result, Separator, std::forward<Args>(Items)...);
|
|
|
|
}
|
|
|
|
|
|
|
|
inline size_t join_one_item_size(char C) { return 1; }
|
|
|
|
inline size_t join_one_item_size(const char *S) { return S ? ::strlen(S) : 0; }
|
|
|
|
|
|
|
|
template <typename T> inline size_t join_one_item_size(const T &Str) {
|
|
|
|
return Str.size();
|
|
|
|
}
|
|
|
|
|
|
|
|
inline size_t join_items_size() { return 0; }
|
|
|
|
|
|
|
|
template <typename A1> inline size_t join_items_size(const A1 &A) {
|
|
|
|
return join_one_item_size(A);
|
|
|
|
}
|
|
|
|
template <typename A1, typename... Args>
|
|
|
|
inline size_t join_items_size(const A1 &A, Args &&... Items) {
|
|
|
|
return join_one_item_size(A) + join_items_size(std::forward<Args>(Items)...);
|
|
|
|
}
|
2017-05-17 01:10:25 +02:00
|
|
|
|
|
|
|
} // end namespace detail
|
2016-09-27 18:37:30 +02:00
|
|
|
|
2013-09-03 22:43:54 +02:00
|
|
|
/// Joins the strings in the range [Begin, End), adding Separator between
|
|
|
|
/// the elements.
|
|
|
|
template <typename IteratorT>
|
|
|
|
inline std::string join(IteratorT Begin, IteratorT End, StringRef Separator) {
|
2017-05-17 01:10:25 +02:00
|
|
|
using tag = typename std::iterator_traits<IteratorT>::iterator_category;
|
2017-03-30 13:06:25 +02:00
|
|
|
return detail::join_impl(Begin, End, Separator, tag());
|
2016-09-27 18:37:30 +02:00
|
|
|
}
|
|
|
|
|
2017-03-21 20:35:05 +01:00
|
|
|
/// Joins the strings in the range [R.begin(), R.end()), adding Separator
|
|
|
|
/// between the elements.
|
|
|
|
template <typename Range>
|
|
|
|
inline std::string join(Range &&R, StringRef Separator) {
|
|
|
|
return join(R.begin(), R.end(), Separator);
|
|
|
|
}
|
|
|
|
|
2016-09-27 18:37:30 +02:00
|
|
|
/// Joins the strings in the parameter pack \p Items, adding \p Separator
|
|
|
|
/// between the elements. All arguments must be implicitly convertible to
|
|
|
|
/// std::string, or there should be an overload of std::string::operator+=()
|
|
|
|
/// that accepts the argument explicitly.
|
|
|
|
template <typename Sep, typename... Args>
|
|
|
|
inline std::string join_items(Sep Separator, Args &&... Items) {
|
|
|
|
std::string Result;
|
|
|
|
if (sizeof...(Items) == 0)
|
|
|
|
return Result;
|
|
|
|
|
2017-03-30 13:06:25 +02:00
|
|
|
size_t NS = detail::join_one_item_size(Separator);
|
|
|
|
size_t NI = detail::join_items_size(std::forward<Args>(Items)...);
|
2016-09-27 18:37:30 +02:00
|
|
|
Result.reserve(NI + (sizeof...(Items) - 1) * NS + 1);
|
2017-03-30 13:06:25 +02:00
|
|
|
detail::join_items_impl(Result, Separator, std::forward<Args>(Items)...);
|
2016-09-27 18:37:30 +02:00
|
|
|
return Result;
|
2013-09-03 22:43:54 +02:00
|
|
|
}
|
|
|
|
|
2017-05-17 01:10:25 +02:00
|
|
|
} // end namespace llvm
|
2003-11-11 23:41:34 +01:00
|
|
|
|
2017-05-17 01:10:25 +02:00
|
|
|
#endif // LLVM_ADT_STRINGEXTRAS_H
|