Custom stream manipulator for streaming integers in any base - c++

I can make an std::ostream object output integer numbers in hex, for example
std::cout << std::hex << 0xabc; //prints `abc`, not the base-10 representation
Is there any manipulator that is universal for all bases? Something like
std::cout << std::base(4) << 20; //I want this to output 110
If there is one, then I have no further question.
If there isn't one, then can I write one? Won't it require me to access private implementation details of std::ostream?
Note that I know I can write a function that takes a number and converts it to a string which is the representation of that number in any base. Or I can use one that already exists. I am asking about custom stream manipulators - are they possible?

You can do something like the following. I have commented the code to explain what each part is doing, but essentially its this:
Create a "manipulator" struct which stores some data in the stream using xalloc and iword.
Create a custom num_put facet which looks for your manipulator and applies the manipulation.
Here is the code...
Edit: Note that im not sure I handled the std::ios_base::internal flag correctly here - as I dont actually know what its for.
Edit 2: I found out what std::ios_base::internal is for, and updated the code to handle it.
Edit 3: Added a call to std::locacle::global to show how to make all the standard stream classes support the new stream manipulator by default, rather than having to imbue them.
#include <algorithm>
#include <cassert>
#include <climits>
#include <iomanip>
#include <iostream>
#include <locale>
namespace StreamManip {
// Define a base manipulator type, its what the built in stream manipulators
// do when they take parameters, only they return an opaque type.
struct BaseManip
{
int mBase;
BaseManip(int base) : mBase(base)
{
assert(base >= 2);
assert(base <= 36);
}
static int getIWord()
{
// call xalloc once to get an index at which we can store data for this
// manipulator.
static int iw = std::ios_base::xalloc();
return iw;
}
void apply(std::ostream& os) const
{
// store the base value in the manipulator.
os.iword(getIWord()) = mBase;
}
};
// We need this so we can apply our custom stream manipulator to the stream.
std::ostream& operator<<(std::ostream& os, const BaseManip& bm)
{
bm.apply(os);
return os;
}
// convience function, so we can do std::cout << base(16) << 100;
BaseManip base(int b)
{
return BaseManip(b);
}
// A custom number output facet. These are used by the std::locale code in
// streams. The num_put facet handles the output of numberic values as characters
// in the stream. Here we create one that knows about our custom manipulator.
struct BaseNumPut : std::num_put<char>
{
// These absVal functions are needed as std::abs doesnt support
// unsigned types, but the templated doPutHelper works on signed and
// unsigned types.
unsigned long int absVal(unsigned long int a) const
{
return a;
}
unsigned long long int absVal(unsigned long long int a) const
{
return a;
}
template <class NumType>
NumType absVal(NumType a) const
{
return std::abs(a);
}
template <class NumType>
iter_type doPutHelper(iter_type out, std::ios_base& str, char_type fill, NumType val) const
{
// Read the value stored in our xalloc location.
const int base = str.iword(BaseManip::getIWord());
// we only want this manipulator to affect the next numeric value, so
// reset its value.
str.iword(BaseManip::getIWord()) = 0;
// normal number output, use the built in putter.
if (base == 0 || base == 10)
{
return std::num_put<char>::do_put(out, str, fill, val);
}
// We want to conver the base, so do it and output.
// Base conversion code lifted from Nawaz's answer
int digits[CHAR_BIT * sizeof(NumType)];
int i = 0;
NumType tempVal = absVal(val);
while (tempVal != 0)
{
digits[i++] = tempVal % base;
tempVal /= base;
}
// Get the format flags.
const std::ios_base::fmtflags flags = str.flags();
// Add the padding if needs by (i.e. they have used std::setw).
// Only applies if we are right aligned, or none specified.
if (flags & std::ios_base::right ||
!(flags & std::ios_base::internal || flags & std::ios_base::left))
{
std::fill_n(out, str.width() - i, fill);
}
if (val < 0)
{
*out++ = '-';
}
// Handle the internal adjustment flag.
if (flags & std::ios_base::internal)
{
std::fill_n(out, str.width() - i, fill);
}
char digitCharLc[] = "0123456789abcdefghijklmnopqrstuvwxyz";
char digitCharUc[] = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
const char *digitChar = (str.flags() & std::ios_base::uppercase)
? digitCharUc
: digitCharLc;
while (i)
{
// out is an iterator that accepts characters
*out++ = digitChar[digits[--i]];
}
// Add the padding if needs by (i.e. they have used std::setw).
// Only applies if we are left aligned.
if (str.flags() & std::ios_base::left)
{
std::fill_n(out, str.width() - i, fill);
}
// clear the width
str.width(0);
return out;
}
// Overrides for the virtual do_put member functions.
iter_type do_put(iter_type out, std::ios_base& str, char_type fill, long val) const
{
return doPutHelper(out, str, fill, val);
}
iter_type do_put(iter_type out, std::ios_base& str, char_type fill, unsigned long val) const
{
return doPutHelper(out, str, fill, val);
}
};
} // namespace StreamManip
int main()
{
// Create a local the uses our custom num_put
std::locale myLocale(std::locale(), new StreamManip::BaseNumPut());
// Set our locacle to the global one used by default in all streams created
// from here on in. Any streams created in this app will now support the
// StreamManip::base modifier.
std::locale::global(myLocale);
// imbue std::cout, so it uses are custom local.
std::cout.imbue(myLocale);
std::cerr.imbue(myLocale);
// Output some stuff.
std::cout << std::setw(50) << StreamManip::base(2) << std::internal << -255 << std::endl;
std::cout << StreamManip::base(4) << 255 << std::endl;
std::cout << StreamManip::base(8) << 255 << std::endl;
std::cout << StreamManip::base(10) << 255 << std::endl;
std::cout << std::uppercase << StreamManip::base(16) << 255 << std::endl;
return 0;
}

Custom manipulators are indeed possible. See for example this question. I'm not familiar with any specific one for universal bases.

You really have two separate problems. The one I think you're asking about is entirely solvable. The other, unfortunately, is rather less so.
Allocating and using some space in the stream to hold some stream state is a problem that was foreseen. Streams have a couple of members (xalloc, iword, pword) that let you allocate a spot in an array in the stream, and read/write data there. As such, the stream manipulator itself is entirely possible. You'd basically use xalloc to allocate a spot in the stream's array to hold the current base, to be used by the insertion operator when it converts a number.
The problem for which I don't see a solution is rather simpler: the standard library already provides an operator<< to insert an int into a stream, and it obviously does not know about your hypothetical data to hold the base for a conversion. You can't overload that, because it would need exactly the same signature as the existing one, so your overload would be ambiguous.
The overloads for int, short, etc., however, are overloaded member functions. I guess if you wanted to badly enough, you could get by with using a template to overload operator<<. If I recall correctly, that would be preferred over even an exact match with a non-template function as the library provides. You'd still be breaking the rules, but if you put such a template in namespace std, there's at least some chance that it would work.

I attempted to write a code, and its working with some limitations. Its not stream manipulator as such, as that is simply not possible, as pointed out by others (especially #Jerry).
Here is my code:
struct base
{
mutable std::ostream *_out;
int _value;
base(int value=10) : _value(value) {}
template<typename T>
const base& operator << (const T & data) const
{
*_out << data;
return *this;
}
const base& operator << (const int & data) const
{
switch(_value)
{
case 2:
case 4:
case 8: return print(data);
case 16: *_out << std::hex << data; break;
default: *_out << data;
}
return *this;
}
const base & print(int data) const
{
int digits[CHAR_BIT * sizeof(int)], i = 0;
while(data)
{
digits[i++] = data % _value;
data /= _value;
}
while(i) *_out << digits[--i] ;
return *this;
}
friend const base& operator <<(std::ostream& out, const base& b)
{
b._out = &out;
return b;
}
};
And this is the test code:
int main() {
std::cout << base(2) << 255 <<", " << 54 << ", " << 20<< "\n";
std::cout << base(4) << 255 <<", " << 54 << ", " << 20<< "\n";
std::cout << base(8) << 255 <<", " << 54 << ", " << 20<< "\n";
std::cout << base(16) << 255 <<", " << 54 << ", " << 20<< "\n";
}
Output:
11111111, 110110, 10100
3333, 312, 110
377, 66, 24
ff, 36, 14
Online demo : http://www.ideone.com/BWhW5
Limitations:
The base cannot be changed twice. So this would be an error:
std::cout << base(4) << 879 << base(8) << 9878 ; //error
Other manipulator cannot be used after base is used:
std::cout << base(4) << 879 << std::hex << 9878 ; //error
std::cout << std::hex << 879 << base(8) << 9878 ; //ok
std::endl cannot be used after base is used:
std::cout << base(4) << 879 << std::endl ; //error
//that is why I used "\n" in the test code.

I don't think that syntax is possible for arbitrary streams (using a manipulator, #gigantt linked an answer that shows some alternative non-manipulator solutions). The standard manipulators merely set options that are implemented inside the stream.
OTOH, you could certainly make this syntax work:
std::cout << base(4, 20);
Where base is an object that provides a stream insertion operator (no need to return a temporary string).

Related

C++: Printing with conditional format depending on the base of an int value

In c++, Is there any format specifier to print an unsigned in different base, depending on its value? A format specifier expressing something like this:
using namespace std;
if(x > 0xF000)
cout << hex << "0x" << x;
else
cout << dec << x ;
Because I will have to do this a lot of times in my current project, I would like to know if c++ provides such a format specifier.
There is no such functionality built-in to C++. You can use a simple wrapper to accomplish this, though:
struct large_hex {
unsigned int x;
};
ostream& operator <<(ostream& os, const large_hex& lh) {
if (lh.x > 0xF000) {
return os << "0x" << hex << lh.x << dec;
} else {
return os << lh.x;
}
}
Use as cout << large_hex{x}.
If you want to make the threshold configurable you could make it a second field of large_hex or a template parameter (exercise for the reader).

Unexpected results from ios_base::xalloc() and ostream::iword() (iomanip)

My goal is to have an iomanip inserter with parameter that can be used to determine if a message will be printed to the stream (or not.) The idea is that a static mask will include bits set for the categories of messages that should be streamed (and bits cleared for messages to be discarded.) The inserter will be used to specify what category (or categories) a message belongs to and if the mask anded with the presented categories is not zero, the message would be streamed out. I have this working but with file scope mask and categories. It seems to me that (at least the category) could be stored with the stream using xalloc() to provide an index and iword() to store/retrieve values at that index but that seems not to be working for me. I have read various Internet references for these functions and my expectation is that sequential calls to xalloc() should return increasing values. In the code below the value returned is always 4. My second puzzlement is where the storage for the iword() backing store is held. Is this static for ostream? Part of every ostream object?
Code follows
#include <iostream>
#include <sstream>
// from http://stackoverflow.com/questions/2212776/overload-handling-of-stdendl
//
// g++ -o blah blah.cpp
//
// Adding an iomanip with argument as in
// http://stackoverflow.com/questions/20792101/how-to-store-formatting-settings-with-an-iostream
//
using namespace std;
// don't really want file scope variables... Can these be stored in stream?
static int pri=0; // value for a message
static int mask=1; // mask for enabled output (if pri&mask => output)
static int priIDX() { // find index for storing priority choice
static int rc = ios_base::xalloc();
return rc;
}
class setPri // Store priority in stream (but how to retrieve when needed?)
{
size_t _n;
public:
explicit setPri(size_t n): _n(n) {}
size_t getn() const {return _n;}
friend ostream& operator<<(ostream& os, const setPri& obj)
{
size_t n = obj.getn();
int ix = priIDX();
pri = os.iword(ix) = n; // save in stream (?) and to file scope variable
os << "setPri(" << n << ") ix:" << ix << " "; // indicate update
return os;
}
};
class MyStream: public ostream
{
// Write a stream buffer that discards if mask & pri not zero
class MyStreamBuf: public stringbuf
{
ostream& output;
public:
MyStreamBuf(ostream& str)
:output(str)
{}
// When we sync the stream with the output.
// 1) report priority mask (temporary)
// 2) Write output if same bit set in mask and priority
// 3) flush the actual output stream we are using.
virtual int sync ( )
{
int ix = priIDX();
int myPri(output.iword(ix));
output << "ix:" << ix << " myPri:" << myPri << '\n';
if( mask & pri) // can't use (myPri&mask)
output << ' ' << str();
str("");
output.flush();
return 0;
}
};
// My Stream just uses a version of my special buffer
MyStreamBuf buffer;
public:
MyStream(ostream& str)
:buffer(str)
{
rdbuf(&buffer);
}
};
int main()
{
MyStream myStream(cout);
myStream << setPri(1) << " this should output" << endl;
myStream << setPri(2) << " this should not output" << endl;
myStream << setPri(3) << " this should also output" << endl;
}
Note that in sync() the code tries to fetch the value from the stream but the returned value is always 0 as if it was not set to begin with.
In my searches to get to this point I have seen comments that it is not a good idea to subclass an ostream. Feel free to suggest a better alternative! (That I can understand. ;) )
Thanks!
static int priIDX() { // find index for storing priority choice
static int rc = ios_base::xalloc();
return rc;
}
This will always return the same value, as your value is static. And therefore only initialized on the first call.
The storage for the iword data is dynamic and allocated separately by each stream object whenever something is stored there.

How to print a bunch of integers with the same formatting?

I would like to print a bunch of integers on 2 fields with '0' as fill character. I can do it but it leads to code duplication. How should I change the code so that the code duplication can be factored out?
#include <ctime>
#include <sstream>
#include <iomanip>
#include <iostream>
using namespace std;
string timestamp() {
time_t now = time(0);
tm t = *localtime(&now);
ostringstream ss;
t.tm_mday = 9; // cheat a little to test it
t.tm_hour = 8;
ss << (t.tm_year+1900)
<< setw(2) << setfill('0') << (t.tm_mon+1) // Code duplication
<< setw(2) << setfill('0') << t.tm_mday
<< setw(2) << setfill('0') << t.tm_hour
<< setw(2) << setfill('0') << t.tm_min
<< setw(2) << setfill('0') << t.tm_sec;
return ss.str();
}
int main() {
cout << timestamp() << endl;
return 0;
}
I have tried
std::ostream& operator<<(std::ostream& s, int i) {
return s << std::setw(2) << std::setfill('0') << i;
}
but it did not work, the operator<< calls are ambigous.
EDIT I got 4 awesome answers and I picked the one that is perhaps the simplest and the most generic one (that is, doesn't assume that we are dealing with timestamps). For the actual problem, I will probably use std::put_time or strftime though.
In C++20 you'll be able to do this with std::format in a less verbose way:
ss << std::format("{}{:02}{:02}{:02}{:02}{:02}",
t.tm_year + 1900, t.tm_mon + 1, t.tm_mday,
t.tm_hour, t.tm_min, t.tm_sec);
and it's even easier with the {fmt} library that supports tm formatting directly:
auto s = fmt::format("{:%Y%m%d%H%M%S}", t);
You need a proxy for your string stream like this:
struct stream{
std::ostringstream ss;
stream& operator<<(int i){
ss << std::setw(2) << std::setfill('0') << i;
return *this; // See Note below
}
};
Then your formatting code will just be this:
stream ss;
ss << (t.tm_year+1900)
<< (t.tm_mon+1)
<< t.tm_mday
<< t.tm_hour
<< t.tm_min
<< t.tm_sec;
return ss.ss.str();
ps. Note the general format of my stream::operator<<() which does its work first, then returns something.
The "obvious" solution is to use a manipulator to install a custom std::num_put<char> facet which just formats ints as desired.
The above statement may be a bit cryptic although it entirely describes the solution. Below is the code to actually implement the logic. The first ingredient is a special std::num_put<char> facet which is just a class derived from std::num_put<char> and overriding one of its virtual functions. The used facet is a filtering facet which looks at a flag stored with the stream (using iword()) to determine whether it should change the behavior or not. Here is the code:
class num_put
: public std::num_put<char>
{
std::locale loc_;
static int index() {
static int rc(std::ios_base::xalloc());
return rc;
}
friend std::ostream& twodigits(std::ostream&);
friend std::ostream& notwodigits(std::ostream&);
public:
num_put(std::locale loc): loc_(loc) {}
iter_type do_put(iter_type to, std::ios_base& fmt,
char fill, long value) const {
if (fmt.iword(index())) {
fmt.width(2);
return std::use_facet<std::num_put<char> >(this->loc_)
.put(to, fmt, '0', value);
}
else {
return std::use_facet<std::num_put<char> >(this->loc_)
.put(to, fmt, fill, value);
}
}
};
The main part is the do_put() member function which decides how the value needs to be formatted: If the flag in fmt.iword(index()) is non-zero, it sets the width to 2 and calls the formatting function with a fill character of 0. The width is going to be reset anyway and the fill character doesn't get stored with the stream, i.e., there is no need for any clean-up.
Normally, the code would probably live in a separate translation unit and it wouldn't be declared in a header. The only functions really declared in a header would be twodigits() and notwodigits() which are made friends in this case to provide access to the index() member function. The index() member function just allocates an index usable with std::ios_base::iword() when called the time and it then just returns this index. The manipulators twodigits() and notwodigits() primarily set this index. If the num_put facet isn't installed for the stream twodigits() also installs the facet:
std::ostream& twodigits(std::ostream& out)
{
if (!dynamic_cast<num_put const*>(
&std::use_facet<std::num_put<char> >(out.getloc()))) {
out.imbue(std::locale(out.getloc(), new num_put(out.getloc())));
}
out.iword(num_put::index()) = true;
return out;
}
std::ostream& notwodigits(std::ostream& out)
{
out.iword(num_put::index()) = false;
return out;
}
The twodigits() manipulator allocates the num_put facet using new num_put(out.getloc()). It doesn't require any clean-up because installing a facet in a std::locale object does the necessary clean-up. The original std::locale of the stream is accessed using out.getloc(). It is changed by the facet. In theory the notwodigits could restore the original std::locale instead of using a flag. However, imbue() can be a relatively expensive operation and using a flag should be a lot cheaper. Of course, if there are lots of similar formatting flags, things may become different...
To demonstrate the use of the manipulators there is a simple test program below. It sets up the formatting flag twodigits twice to verify that facet is only created once (it would be a bit silly to create a chain of std::locales to pass through the formatting:
int main()
{
std::cout << "some-int='" << 1 << "' "
<< twodigits << '\n'
<< "two-digits1='" << 1 << "' "
<< "two-digits2='" << 2 << "' "
<< "two-digits3='" << 3 << "' "
<< notwodigits << '\n'
<< "some-int='" << 1 << "' "
<< twodigits << '\n'
<< "two-digits4='" << 4 << "' "
<< '\n';
}
Besides formatting integers with std::setw / std::setfill or ios_base::width / basic_ios::fill, if you want to format a date/time object you may want to consider using std::put_time / std::gettime
For convenient output formatting you may use boost::format() with sprintf-like formatting options:
#include <boost/format.hpp>
#include <iostream>
int main() {
int i1 = 1, i2 = 10, i3 = 100;
std::cout << boost::format("%03i %03i %03i\n") % i1 % i2 % i3;
// output is: 001 010 100
}
Little code duplication, additional implementation effort is marginal.
If all you want to do is output formatting of your timestamp, you should obviously use strftime(). That's what it's made for:
#include <ctime>
#include <iostream>
std::string timestamp() {
char buf[20];
const char fmt[] = "%Y%m%d%H%M%S";
time_t now = time(0);
strftime(buf, sizeof(buf), fmt, localtime(&now));
return buf;
}
int main() {
std::cout << timestamp() << std::endl;
}
operator<<(std::ostream& s, int i) is "ambiguous" because such a function already exists.
All you need to do is give that function a signature that doesn't conflict.

Retrieving flags in c++ streams

How can i make use of flags in c++ streams? I know of ios_base::flags(), but when i cout them or compare them, they dont change values even with a new flag. a simple program:
#include <iostream>
using namespace std;
int main(){
cout << cout.flags() << endl;//4098
cout << std::hex << cout.flags() << endl;// 0x1002
return 0;
}
doesnt change the outputted default value (at least for me) of 4098.
my ultimate goal is to compare the stream to flags to see which are set, NOT TO SET NEW ONES. can anyone show me an example of how to do this?
With this code:
cout << std::hex << cout.flags() << endl;
The compiler is allowed to evaluate it in this order:
ios_base::fmtflags f = cout.flags(); // store value before applying std::hex
cout << hex;
cout << f;
cout << endl;
So you're not guaranteed to "see" flag changes this way. However, it is not Undefined Behavior.
The flags are a "bitmask type", which is defined to have certain properties – the actual type used is implementation-defined, but integers, enums, and std::bitsets are possibilities. You can use the normal bit-manipulation operators: ^, &, |, and ~:
bool is_hex(std::ios_base &s) {
return (s.flags() & s.basefield) == s.hex;
}
// is_oct is identical, except with s.oct
// Nothing set in basefield means "determine base from input" for istreams,
// and ostreams use base 10. This makes is_dec harder to write.
bool is_anybase(std::istream &s) {
return (s.flags() & s.basefield) == 0;
}
bool is_dec(std::istream &s) {
std::ios_base::fmtflags base = s.flags() & s.basefield;
return base == dec;
}
bool is_dec(std::ostream &s) {
std::ios_base::fmtflags base = s.flags() & s.basefield;
return (base == dec) || (base == 0);
}
// Purposeful overload ambiguity on std::iostream.
// In 0x, we could write:
bool is_dec(std::iostream &s) = delete;
For an example, this is how std::hex works:
std::ios_base& hex(std::ios_base &s) {
s.setf(s.hex, s.basefield);
return s;
}
Where setf does:
ios_base::fmtflags fmtflags = s.hex; // first parameter
ios_base::fmtflags mask = s.basefield; // second parameter
s.flags((s.flags() & ~mask) | (fmtflags & mask));

how do I print an unsigned char as hex in c++ using ostream?

I want to work with unsigned 8-bit variables in C++. Either unsigned char or uint8_t do the trick as far as the arithmetic is concerned (which is expected, since AFAIK uint8_t is just an alias for unsigned char, or so the debugger presents it.
The problem is that if I print out the variables using ostream in C++ it treats it as char. If I have:
unsigned char a = 0;
unsigned char b = 0xff;
cout << "a is " << hex << a <<"; b is " << hex << b << endl;
then the output is:
a is ^#; b is 377
instead of
a is 0; b is ff
I tried using uint8_t, but as I mentioned before, that's typedef'ed to unsigned char, so it does the same. How can I print my variables correctly?
Edit: I do this in many places throughout my code. Is there any way I can do this without casting to int each time I want to print?
Use:
cout << "a is " << hex << (int) a <<"; b is " << hex << (int) b << endl;
And if you want padding with leading zeros then:
#include <iomanip>
...
cout << "a is " << setw(2) << setfill('0') << hex << (int) a ;
As we are using C-style casts, why not go the whole hog with terminal C++ badness and use a macro!
#define HEX( x )
setw(2) << setfill('0') << hex << (int)( x )
you can then say
cout << "a is " << HEX( a );
Edit: Having said that, MartinStettner's solution is much nicer!
I would suggest using the following technique:
struct HexCharStruct
{
unsigned char c;
HexCharStruct(unsigned char _c) : c(_c) { }
};
inline std::ostream& operator<<(std::ostream& o, const HexCharStruct& hs)
{
return (o << std::hex << (int)hs.c);
}
inline HexCharStruct hex(unsigned char _c)
{
return HexCharStruct(_c);
}
int main()
{
char a = 131;
std::cout << hex(a) << std::endl;
}
It's short to write, has the same efficiency as the original solution and it lets you choose to use the "original" character output. And it's type-safe (not using "evil" macros :-))
You can read more about this at http://cpp.indi.frih.net/blog/2014/09/tippet-printing-numeric-values-for-chars-and-uint8_t/ and http://cpp.indi.frih.net/blog/2014/08/code-critique-stack-overflow-posters-cant-print-the-numeric-value-of-a-char/. I am only posting this because it has become clear that the author of the above articles does not intend to.
The simplest and most correct technique to do print a char as hex is
unsigned char a = 0;
unsigned char b = 0xff;
auto flags = cout.flags(); //I only include resetting the ioflags because so
//many answers on this page call functions where
//flags are changed and leave no way to
//return them to the state they were in before
//the function call
cout << "a is " << hex << +a <<"; b is " << +b << endl;
cout.flags(flags);
The readers digest version of how this works is that the unary + operator forces a no op type conversion to an int with the correct signedness. So, an unsigned char converts to unsigned int, a signed char converts to int, and a char converts to either unsigned int or int depending on whether char is signed or unsigned on your platform (it comes as a shock to many that char is special and not specified as either signed or unsigned).
The only negative of this technique is that it may not be obvious what is happening to a someone that is unfamiliar with it. However, I think that it is better to use the technique that is correct and teach others about it rather than doing something that is incorrect but more immediately clear.
Well, this works for me:
std::cout << std::hex << (0xFF & a) << std::endl;
If you just cast (int) as suggested it might add 1s to the left of a if its most significant bit is 1. So making this binary AND operation guarantees the output will have the left bits filled by 0s and also converts it to unsigned int forcing cout to print it as hex.
I hope this helps.
In C++20 you'll be able to use std::format to do this:
std::cout << std::format("a is {:x}; b is {:x}\n", a, b);
Output:
a is 0; b is ff
In the meantime you can use the {fmt} library, std::format is based on. {fmt} also provides the print function that makes this even easier and more efficient (godbolt):
fmt::print("a is {:x}; b is {:x}\n", a, b);
Disclaimer: I'm the author of {fmt} and C++20 std::format.
Hm, it seems I re-invented the wheel yesterday... But hey, at least it's a generic wheel this time :) chars are printed with two hex digits, shorts with 4 hex digits and so on.
template<typename T>
struct hex_t
{
T x;
};
template<typename T>
hex_t<T> hex(T x)
{
hex_t<T> h = {x};
return h;
}
template<typename T>
std::ostream& operator<<(std::ostream& os, hex_t<T> h)
{
char buffer[2 * sizeof(T)];
for (auto i = sizeof buffer; i--; )
{
buffer[i] = "0123456789ABCDEF"[h.x & 15];
h.x >>= 4;
}
os.write(buffer, sizeof buffer);
return os;
}
I think TrungTN and anon's answer is okay, but MartinStettner's way of implementing the hex() function is not really simple, and too dark, considering hex << (int)mychar is already a workaround.
here is my solution to make "<<" operator easier:
#include <sstream>
#include <iomanip>
string uchar2hex(unsigned char inchar)
{
ostringstream oss (ostringstream::out);
oss << setw(2) << setfill('0') << hex << (int)(inchar);
return oss.str();
}
int main()
{
unsigned char a = 131;
std::cout << uchar2hex(a) << std::endl;
}
It's just not worthy implementing a stream operator :-)
I think we are missing an explanation of how these type conversions work.
char is platform dependent signed or unsigned. In x86 char is equivalent to signed char.
When an integral type (char, short, int, long) is converted to a larger capacity type, the conversion is made by adding zeros to the left in case of unsigned types and by sign extension for signed ones. Sign extension consists in replicating the most significant (leftmost) bit of the original number to the left till we reach the bit size of the target type.
Hence if I am in a signed char by default system and I do this:
char a = 0xF0; // Equivalent to the binary: 11110000
std::cout << std::hex << static_cast<int>(a);
We would obtain F...F0 since the leading 1 bit has been extended.
If we want to make sure that we only print F0 in any system we would have to make an additional intermediate type cast to an unsigned char so that zeros are added instead and, since they are not significant for a integer with only 8-bits, not printed:
char a = 0xF0; // Equivalent to the binary: 11110000
std::cout << std::hex << static_cast<int>(static_cast<unsigned char>(a));
This produces F0
I'd do it like MartinStettner but add an extra parameter for number of digits:
inline HexStruct hex(long n, int w=2)
{
return HexStruct(n, w);
}
// Rest of implementation is left as an exercise for the reader
So you have two digits by default but can set four, eight, or whatever if you want to.
eg.
int main()
{
short a = 3142;
std:cout << hex(a,4) << std::endl;
}
It may seem like overkill but as Bjarne said: "libraries should be easy to use, not easy to write".
I would suggest:
std::cout << setbase(16) << 32;
Taken from:
http://www.cprogramming.com/tutorial/iomanip.html
You can try the following code:
unsigned char a = 0;
unsigned char b = 0xff;
cout << hex << "a is " << int(a) << "; b is " << int(b) << endl;
cout << hex
<< "a is " << setfill('0') << setw(2) << int(a)
<< "; b is " << setfill('0') << setw(2) << int(b)
<< endl;
cout << hex << uppercase
<< "a is " << setfill('0') << setw(2) << int(a)
<< "; b is " << setfill('0') << setw(2) << int(b)
<< endl;
Output:
a is 0; b is ff
a is 00; b is ff
a is 00; b is FF
I use the following on win32/linux(32/64 bit):
#include <iostream>
#include <iomanip>
template <typename T>
std::string HexToString(T uval)
{
std::stringstream ss;
ss << "0x" << std::setw(sizeof(uval) * 2) << std::setfill('0') << std::hex << +uval;
return ss.str();
}
I realize this is an old question, but its also a top Google result in searching for a solution to a very similar problem I have, which is the desire to implement arbitrary integer to hex string conversions within a template class. My end goal was actually a Gtk::Entry subclass template that would allow editing various integer widths in hex, but that's beside the point.
This combines the unary operator+ trick with std::make_unsigned from <type_traits> to prevent the problem of sign-extending negative int8_t or signed char values that occurs in this answer
Anyway, I believe this is more succinct than any other generic solution. It should work for any signed or unsigned integer types, and throws a compile-time error if you attempt to instantiate the function with any non-integer types.
template <
typename T,
typename = typename std::enable_if<std::is_integral<T>::value, T>::type
>
std::string toHexString(const T v)
{
std::ostringstream oss;
oss << std::hex << +((typename std::make_unsigned<T>::type)v);
return oss.str();
}
Some example usage:
int main(int argc, char**argv)
{
int16_t val;
// Prints 'ff' instead of "ffffffff". Unlike the other answer using the '+'
// operator to extend sizeof(char) int types to int/unsigned int
std::cout << toHexString(int8_t(-1)) << std::endl;
// Works with any integer type
std::cout << toHexString(int16_t(0xCAFE)) << std::endl;
// You can use setw and setfill with strings too -OR-
// the toHexString could easily have parameters added to do that.
std::cout << std::setw(8) << std::setfill('0') <<
toHexString(int(100)) << std::endl;
return 0;
}
Update: Alternatively, if you don't like the idea of the ostringstream being used, you can combine the templating and unary operator trick with the accepted answer's struct-based solution for the following. Note that here, I modified the template by removing the check for integer types. The make_unsigned usage might be enough for compile time type safety guarantees.
template <typename T>
struct HexValue
{
T value;
HexValue(T _v) : value(_v) { }
};
template <typename T>
inline std::ostream& operator<<(std::ostream& o, const HexValue<T>& hs)
{
return o << std::hex << +((typename std::make_unsigned<T>::type) hs.value);
}
template <typename T>
const HexValue<T> toHex(const T val)
{
return HexValue<T>(val);
}
// Usage:
std::cout << toHex(int8_t(-1)) << std::endl;
If you're using prefill and signed chars, be careful not to append unwanted 'F's
char out_character = 0xBE;
cout << setfill('0') << setw(2) << hex << unsigned short(out_character);
prints: ffbe
using int instead of short results in ffffffbe
To prevent the unwanted f's you can easily mask them out.
char out_character = 0xBE;
cout << setfill('0') << setw(2) << hex << unsigned short(out_character) & 0xFF;
I'd like to post my re-re-inventing version based on #FredOverflow's. I made the following modifications.
fix:
Rhs of operator<< should be of const reference type. In #FredOverflow's code, h.x >>= 4 changes output h, which is surprisingly not compatible with standard library, and type T is requared to be copy-constructable.
Assume only CHAR_BITS is a multiple of 4. #FredOverflow's code assumes char is 8-bits, which is not always true, in some implementations on DSPs, particularly, it is not uncommon that char is 16-bits, 24-bits, 32-bits, etc.
improve:
Support all other standard library manipulators available for integral types, e.g. std::uppercase. Because format output is used in _print_byte, standard library manipulators are still available.
Add hex_sep to print separate bytes (note that in C/C++ a 'byte' is by definition a storage unit with the size of char). Add a template parameter Sep and instantiate _Hex<T, false> and _Hex<T, true> in hex and hex_sep respectively.
Avoid binary code bloat. Function _print_byte is extracted out of operator<<, with a function parameter size, to avoid instantiation for different Size.
More on binary code bloat:
As mentioned in improvement 3, no matter how extensively hex and hex_sep is used, only two copies of (nearly) duplicated function will exits in binary code: _print_byte<true> and _print_byte<false>. And you might realized that this duplication can also be eliminated using exactly the same approach: add a function parameter sep. Yes, but if doing so, a runtime if(sep) is needed. I want a common library utility which may be used extensively in the program, thus I compromised on the duplication rather than runtime overhead. I achieved this by using compile-time if: C++11 std::conditional, the overhead of function call can hopefully be optimized away by inline.
hex_print.h:
namespace Hex
{
typedef unsigned char Byte;
template <typename T, bool Sep> struct _Hex
{
_Hex(const T& t) : val(t)
{}
const T& val;
};
template <typename T, bool Sep>
std::ostream& operator<<(std::ostream& os, const _Hex<T, Sep>& h);
}
template <typename T> Hex::_Hex<T, false> hex(const T& x)
{ return Hex::_Hex<T, false>(x); }
template <typename T> Hex::_Hex<T, true> hex_sep(const T& x)
{ return Hex::_Hex<T, true>(x); }
#include "misc.tcc"
hex_print.tcc:
namespace Hex
{
struct Put_space {
static inline void run(std::ostream& os) { os << ' '; }
};
struct No_op {
static inline void run(std::ostream& os) {}
};
#if (CHAR_BIT & 3) // can use C++11 static_assert, but no real advantage here
#error "hex print utility need CHAR_BIT to be a multiple of 4"
#endif
static const size_t width = CHAR_BIT >> 2;
template <bool Sep>
std::ostream& _print_byte(std::ostream& os, const void* ptr, const size_t size)
{
using namespace std;
auto pbyte = reinterpret_cast<const Byte*>(ptr);
os << hex << setfill('0');
for (int i = size; --i >= 0; )
{
os << setw(width) << static_cast<short>(pbyte[i]);
conditional<Sep, Put_space, No_op>::type::run(os);
}
return os << setfill(' ') << dec;
}
template <typename T, bool Sep>
inline std::ostream& operator<<(std::ostream& os, const _Hex<T, Sep>& h)
{
return _print_byte<Sep>(os, &h.val, sizeof(T));
}
}
test:
struct { int x; } output = {0xdeadbeef};
cout << hex_sep(output) << std::uppercase << hex(output) << endl;
output:
de ad be ef DEADBEEF
This will also work:
std::ostream& operator<< (std::ostream& o, unsigned char c)
{
return o<<(int)c;
}
int main()
{
unsigned char a = 06;
unsigned char b = 0xff;
std::cout << "a is " << std::hex << a <<"; b is " << std::hex << b << std::endl;
return 0;
}
I have used in this way.
char strInput[] = "yourchardata";
char chHex[2] = "";
int nLength = strlen(strInput);
char* chResut = new char[(nLength*2) + 1];
memset(chResut, 0, (nLength*2) + 1);
for (int i = 0; i < nLength; i++)
{
sprintf(chHex, "%02X", strInput[i]& 0x00FF);
memcpy(&(chResut[i*2]), chHex, 2);
}
printf("\n%s",chResut);
delete chResut;
chResut = NULL;