compile time/runtime variable name/enum value name information - c++

Is it possible to obtain variable name or enum value name at compile time/runtime? In particular, namespace::/class::/struct::/union::-qualified (with adjustable depth, like have UNIX patch unility -p/--strip= option). In gcc 4.8.1 I can write:
#include <iostream>
#include <ostream>
#include <cstdlib>
enum class mnemocode
{
fwait,
finit,
fninit,
fstsw,
fnstsw,
// ...
sahf,
ret,
prologue,
epilogue,
sp_inc,
sp_dec,
call
};
inline /* till C++14 cannot be constexpr */
auto mnemocode_name(mnemocode _mnemocode)
{
switch (_mnemocode) {
case mnemocode::fwait : return "fwait";
case mnemocode::finit : return "finit";
case mnemocode::fninit : return "fninit";
case mnemocode::fstsw : return "fstsw";
case mnemocode::fnstsw : return "fnstsw";
// ...
case mnemocode::sahf : return "sahf";
case mnemocode::ret : return "ret";
case mnemocode::prologue : return "prologue";
case mnemocode::epilogue : return "epilogue";
case mnemocode::sp_inc : return "sp_inc";
case mnemocode::sp_dec : return "sp_dec";
case mnemocode::call : return "call";
default : return "[unknown instruction]";
}
}
inline
std::ostream & operator << (std::ostream & out, mnemocode _mnemocode)
{
return out << mnemocode_name(_mnemocode);
}
int main()
{
std::cout << mnemocode::fwait << std::endl; // fwait
return EXIT_SUCCESS;
}
But I want to be able to do the following:
template< typename M, typename = typename std::enable_if< std::is_same< mnemocode, typename std::remove_reference< typename std::remove_cv< M >::type >::type >::value >
inline constexpr
auto mnemocode_name(M && _mnemocode)
{
constexpr auto const depth = std::numeric_limits< std::size_t >::max(); // remove all qualifiers before last operator ::
return abi::__get_value_info(_mnemocode).name(depth); // compile time if M is constexpr
}
by means of some imaginary constexpr abi::__get_value_info(symbol) class.
GCC allows me to write:
#include <iostream>
#include <string>
#include <type_traits>
#include <cxxabi.h>
#include <cstdlib>
template< typename T >
/* cannot be constexpr :( */
const char * this_type()
{
return __PRETTY_FUNCTION__;
}
template< typename T >
std::string theirs_type()
{
int status = 0;
auto realname_(abi::__cxa_demangle(typeid(T).name(), nullptr, nullptr, &status));
switch (status) {
case -1: return "Could not allocate memory";
case -2: return "Invalid name under the C++ ABI mangling rules";
case -3: return "Invalid argument to demangle";
}
std::string os(realname_);
std::free(realname_);
if (std::is_volatile< T >::value) {
os = "volatile " + os;
}
if (std::is_const< T >::value) {
os += " const";
}
if (std::is_rvalue_reference< T >::value) {
os += " &&";
} else if (std::is_lvalue_reference< T >::value) {
os += " &";
}
return os;
}
int main()
{
std::cout << this_type< decltype(static_cast< double const >(double())) >() << std::endl; // const char* this_type() [with T = double]
std::cout << theirs_type< double const && >() << std::endl; // double &&
return EXIT_SUCCESS;
}
But this is only about the type names and too far from compile time deduction.
I guess that's all I come up here, would require almost embedded into my executable debugger and the availability of the section with the debug information. But I still do not think, that it's impossible at all.

There may be other solutions but the way I normally do this is to play with #defines
1) define your enums in a file (say enumdef.h)
ENUMDEF(fwait)
ENUMDEF(finit)
...
ENUMDEF(call)
2) Declare a header for the enums
#ifndef EnumDefEnum_h
#define EnumDefEnum_h
enum mnemcode
{
#define ENUMDEF(x) x,
#include "enumdef.h"
#undef ENUMDEF
mnemcodeMax
};
#endif
3) To print them
#include "enumdefenum.h"
static const char* mnem_str[] =
{
#define ENUMDEF(x) #x,
#include "enumdef.h"
#undef ENUMDEF
""
};
const char* mnem_name(mnemcode index)
{
return mnem_str[index];
}
4) You could even use them in switch statements if you keep to a naming convention
switch (index)
{
// Put in a pragma to tell you which one it is because the compiler will
// tell you the line number in enumdef.h: not the one in this file
#pragma message("switch statement in some routine")
#define ENUMDEF(x) \
case x: Do##x(whatever); break;
#include "enumdef.h"
#undef ENUMDEF
}

Related

Getting field names with boost::pfr

Hi I'm using boost::pfr for basic reflection, it works fine, but the problem is it is only print or deal with the field values, like with boost::pfr::io it prints each member of the struct, but how can I print it as name value pairs, same issue with for_each_field, the functor only accepts values, but not names. How can I get the field names?
struct S {
int n;
std::string name;
};
S o{1, "foo"};
std::cout << boost::pfr::io(o);
// Outputs: {1, "foo"}, how can I get n = 1, name = "foo"?
If you think adapting a struct is not too intrusive (it doesn't change your existing definitions, and you don't even need to have it in a public header):
BOOST_FUSION_ADAPT_STRUCT(S, n, name)
Then you can concoct a general operator<< for sequences:
namespace BF = boost::fusion;
template <typename T,
typename Enable = std::enable_if_t<
// BF::traits::is_sequence<T>::type::value>
std::is_same_v<BF::struct_tag, typename BF::traits::tag_of<T>::type>>>
std::ostream& operator<<(std::ostream& os, T const& v)
{
bool first = true;
auto visitor = [&]<size_t I>() {
os << (std::exchange(first, false) ? "" : ", ")
<< BF::extension::struct_member_name<T, I>::call()
<< " = " << BF::at_c<I>(v);
};
// visit members
[&]<size_t... II>(std::index_sequence<II...>)
{
return ((visitor.template operator()<II>(), ...);
}
(std::make_index_sequence<BF::result_of::size<T>::type::value>{});
return os;
}
(Prior to c++20 this would require some explicit template types instead of the lambdas, perhaps making it more readable. I guess I'm lazy...)
Here's a live demo: Live On Compiler Explorer
n = 1, name = foo
Bonus: Correctly quoting string-like types
Live On Compiler Explorer
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/fusion/include/for_each.hpp>
#include <boost/fusion/include/at_c.hpp>
#include <iostream>
#include <iomanip>
namespace MyLib {
struct S {
int n;
std::string name;
};
namespace BF = boost::fusion;
static auto inline pretty(std::string_view sv) { return std::quoted(sv); }
template <typename T,
typename Enable = std::enable_if_t<
not std::is_constructible_v<std::string_view, T const&>>>
static inline T const& pretty(T const& v)
{
return v;
}
template <typename T,
typename Enable = std::enable_if_t<
// BF::traits::is_sequence<T>::type::value>
std::is_same_v<BF::struct_tag, typename BF::traits::tag_of<T>::type>>>
std::ostream& operator<<(std::ostream& os, T const& v)
{
bool first = true;
auto visitor = [&]<size_t I>() {
os << (std::exchange(first, false) ? "" : ", ")
<< BF::extension::struct_member_name<T, I>::call()
<< " = " << pretty(BF::at_c<I>(v));
};
// visit members
[&]<size_t... II>(std::index_sequence<II...>)
{
return (visitor.template operator()<II>(), ...);
}
(std::make_index_sequence<BF::result_of::size<T>::type::value>{});
return os;
}
} // namespace MyLib
BOOST_FUSION_ADAPT_STRUCT(MyLib::S, n, name)
int main()
{
MyLib::S o{1, "foo"};
std::cout << o << "\n";
}
Outputs:
n = 1, name = "foo"
The library cannot offer any such functionality because it is currently impossible to obtain the name of a member of a class as value of an object.
If you want to output field names, you need to declare string objects mapped with the members and implement a operator<< which uses these strings manually.
To do this a more sophisticated reflection library would probably offer macros to use in the definition of the members. Macros can expand their argument(s) into a declaration using the provided name as identifier while also producing code using the name as string literal (via the # macro replacement operator).
It's stupid but hey, with a stringifying macro per field it could be enough for you.
C++14, no additional library
#include <boost/pfr.hpp>
struct S
{
int n;
std::string name;
static char const* const s_memNames[2];
};
char const* const S::s_memNames[2] = {"n", "name"};
// utility
template< size_t I, typename TR >
char const* MemberName()
{
using T = std::remove_reference_t<TR>;
if (I < std::size(T::s_memNames))
return T::s_memNames[I];
return nullptr;
}
// test:
#include <iostream>
using std::cout;
template< size_t I, typename T >
void StreamAt(T&& inst)
{
char const* n = MemberName<I,T>();
auto& v = boost::pfr::get<I>(inst);
cout << "(" << n << " = " << v << ")";
}
int main()
{
S s{2, "boo"};
boost::pfr::for_each_field(s, [&](const auto&, auto I)
{
StreamAt<decltype(I)::value>(s);
cout << "\n";
});
}
output:
(n = 2)
(name = boo)
(previous version of the suggestion, this one has more fluff so less interesting)
#include <boost/pfr.hpp>
// library additions:
static char const* g_names[100];
template< size_t V >
struct Id : std::integral_constant<size_t, V > {};
template< size_t I, typename T >
using TypeAt = boost::pfr::tuple_element_t<I, T>;
template<std::size_t Pos, class Struct>
constexpr int Ni() // name index
{
return std::tuple_element_t<Pos, typename std::remove_reference_t<Struct>::NamesAt >::value;
}
struct StaticCaller
{
template< typename Functor >
StaticCaller(Functor f) { f();}
};
///
/// YOUR CODE HERE
struct S
{
using NamesAt = std::tuple<Id<__COUNTER__>, Id<__COUNTER__>>; // add this
int n;
std::string name;
static void Init() // add this
{
g_names[Ni<0,S>()] = "n";
g_names[Ni<1,S>()] = "name";
}
};
StaticCaller g_sc__LINE__(S::Init); // add this
// utilities
template< size_t I, typename T >
auto GetValueName(T&& inst)
{
return std::make_pair(boost::pfr::get<I>(inst), g_names[Ni<I,T>()]);
}
// test:
#include <iostream>
using std::cout;
template< size_t I, typename T >
void StreamAt(T&& inst)
{
auto const& [v,n] = GetValueName<I>(inst);
cout << "(" << v << ", " << n << ")";
}
int main()
{
S s{2, "boo"};
boost::pfr::for_each_field(s, [&](const auto&, auto I)
{
StreamAt<decltype(I)::value>(s);
cout << "\n";
});
}
output
(2, n)
(boo, name)

How can I code something like a switch for std::variant?

I have some var = std::variant<std::monostate, a, b, c> when a, b, c is some types.
How, at runtime, do I check what type var contains?
In the official documentation I found information that if var contains a type and I write std::get<b>(var) I get an exception. So I thought about this solution:
try {
std::variant<a>(var);
// Do something
} catch(const std::bad_variant_access&) {
try {
std::variant<b>(var);
// Do something else
} catch(const std::bad_variant_access&) {
try {
std::variant<c>(var);
// Another else
} catch (const std::bad_variant_access&) {
// std::monostate
}
}
}
But it's so complicated and ugly! Is there a simpler way to check what type std::variant contains?
std::visit is the way to go:
There is even overloaded to allow inlined visitor:
// helper type for the visitor #4
template<class... Ts> struct overloaded : Ts... { using Ts::operator()...; };
// explicit deduction guide (not needed as of C++20)
template<class... Ts> overloaded(Ts...) -> overloaded<Ts...>;
and so:
std::visit(overloaded{
[](std::monostate&){/*..*/},
[](a&){/*..*/},
[](b&){/*..*/},
[](c&){/*..*/}
}, var);
To use chained if-branches instead, you might used std::get_if
if (auto* v = std::get_if<a>(var)) {
// ...
} else if (auto* v = std::get_if<b>(var)) {
// ...
} else if (auto* v = std::get_if<c>(var)) {
// ...
} else { // std::monostate
// ...
}
The most simple way is to switch based on the current std::variant::index(). This approach requires your types (std::monostate, A, B, C) to always stay in the same order.
// I omitted C to keep the example simpler, the principle is the same
using my_variant = std::variant<std::monostate, A, B>;
void foo(my_variant &v) {
switch (v.index()) {
case 0: break; // do nothing because the type is std::monostate
case 1: {
doSomethingWith(std::get<A>(v));
break;
}
case 2: {
doSomethingElseWith(std::get<B>(v));
break;
}
}
}
If your callable works with any type, you can also use std::visit:
void bar(my_variant &v) {
std::visit([](auto &&arg) -> void {
// Here, arg is std::monostate, A or B
// This lambda needs to compile with all three options.
// The lambda returns void because we don't modify the variant, so
// we could also use const& arg.
}, v);
}
If you don't want std::visit to accept std::monostate, then just check if the index is 0. Once again, this relies on std::monostate being the first type of the variant, so it is good practice to always make it the first.
You can also detect the type using if-constexpr inside the callable. With this approach, the arguments don't have to be in the same order anymore:
void bar(my_variant &v) {
std::visit([](auto &&arg) -> my_variant {
using T = std::decay_t<decltype(arg)>;
if constexpr (std::is_same_v<std::monostate, T>) {
return arg; // arg is std::monostate here
}
else if constexpr (std::is_same_v<A, T>) {
return arg + arg; // arg is A here
}
else if constexpr (std::is_same_v<B, T>) {
return arg * arg; // arg is B here
}
}, v);
}
Note that the first lambda returns void because it just processes the current value of the variant. If you want to modify the variant, your lambda needs to return my_variant again.
You could use an overloaded visitor inside std::visit to handle A or B separately. See std::visit for more examples.
You can use standard std::visit
Usage example:
#include <variant>
#include <iostream>
#include <type_traits>
struct a {};
struct b {};
struct c {};
int main()
{
std::variant<a, b, c> var = a{};
std::visit([](auto&& arg) {
using T = std::decay_t<decltype(arg)>;
if constexpr (std::is_same_v<T, a>)
std::cout << "is an a" << '\n';
else if constexpr (std::is_same_v<T, b>)
std::cout << "is a b" << '\n';
else if constexpr (std::is_same_v<T, c>)
std::cout << "is a c" << '\n';
else
std::cout << "is not in variant type list" << '\n';
}, var);
}
Well, with some macro magic, you can do something like:
#include <variant>
#include <type_traits>
#include <iostream>
#define __X_CONCAT_1(x,y) x ## y
#define __X_CONCAT(x,y) __X_CONCAT_1(x,y)
template <typename T>
struct __helper { };
// extract the type from a declaration
// we use function-type magic to get that: typename __helper<void ( (declaration) )>::type
// declaration is "int &x" for example, this class template extracts "int"
template <typename T>
struct __helper<void (T)> {
using type = std::remove_reference_t<T>;
};
#define variant_if(variant, declaration) \
if (bool __X_CONCAT(variant_if_bool_, __LINE__) = true; auto * __X_CONCAT(variant_if_ptr_, __LINE__) = std::get_if<typename __helper<void ( (declaration) )>::type>(&(variant))) \
for (declaration = * __X_CONCAT(variant_if_ptr_, __LINE__); __X_CONCAT(variant_if_bool_, __LINE__); __X_CONCAT(variant_if_bool_, __LINE__) = false)
#define variant_switch(variant) if (auto &__variant_switch_v = (variant); true)
#define variant_case(x) variant_if(__variant_switch_v, x)
int main() {
std::variant<int, long> v = 12;
std::variant<int, long> w = 32l;
std::cout << "variant_if test" << std::endl;
variant_if(v, int &x) {
std::cout << "int = " << x << std::endl;
}
else variant_if(v, long &x) {
std::cout << "long = " << x << std::endl;
}
std::cout << "variant_switch test" << std::endl;
variant_switch(v) {
variant_case(int &x) {
std::cout << "int = " << x << std::endl;
variant_switch (w) {
variant_case(int &x) {
std::cout << "int = " << x << std::endl;
}
variant_case(long &x) {
std::cout << "long = " << x << std::endl;
}
}
};
variant_case(long &x) {
std::cout << "long = " << x << std::endl;
variant_switch (w) {
variant_case(int &x) {
std::cout << "int = " << x << std::endl;
}
variant_case(long &x) {
std::cout << "long = " << x << std::endl;
}
}
};
}
return 0;
}
I tested this approach with GCC and Clang, no guarantees for MSVC.

C++ Return data from a Variant according to the given typename

I have following function template to return specific type of data from a VARIANT, according to the given typename.
template <typename T>
T VariantGetValue(VARIANT Variant) {
std::string S(typeid(T).name());
if (S == "wchar_t* __ptr64") { return Variant.bstrVal; }
if (S == "unsigned int") { return Variant.uintVal; }
}
So, as I needed to return an unsigned int type from a VARIANT, I tried using above function like:
return VariantGetValue<unsigned int>(CV);
But, unfortunately compiler seems to ignore if (S == "....) case here and gives me error:
C2440 - 'return': cannot convert from 'BSTR' to 'unsigned int'
But, if I remove the line if (S == "wchar_t* __ptr64") { return Variant.bstrVal; }, compiler only gives me following warning:
C4715 - 'VariantGetValue': not all control paths return a value
Can I suppress this error and continue? Is it safe or are there any alternate ways to do this without compiler errors?
You cannot have multiple return types based on a branch the code is going to take at runtime. Your best bet here is to work with explicit specializations.
template < typename T >
T VariantGetValue(VARIANT) = delete;
template <>
unsigned int VariantGetValue<unsigned int>(VARIANT Variant)
{
VARIANT var;
InitVariantFromUInt32(unsigned int{}, &var);
if (Variant.vt != var.vt)
throw std::runtime_error("bad get");
return Variant.uintVal;
}
template <>
BSTR VariantGetValue<BSTR>(VARIANT Variant)
{
if (/* check that Variant stores wchar_t* __ptr64 */)
throw std::runtime_error("bad get");
return Variant.bstrVal;
}
This, by the way, is what std::get does for std::variant.
#include <iostream>
#include <variant>
using Variant = std::variant<int,std::string>;
int main()
{
Variant v(13);
std::cout << std::get<int>(v) << '\n'; // 13
//std::cout << std::get<std::string>(v) << '\n'; // std::bad_variant_access
}
I have implemented a full example to perhaps clarify some questions raised in the comments.
#include <iostream>
#include <stdlib.h>
#include <string.h>
// Implement a mock VARIANT, don't take this code too seriously
typedef unsigned int VARTYPE;
typedef char* BSTR;
enum { VT_UI4, VT_BSTR };
struct VARIANT
{
VARIANT() : bstrVal(nullptr) {}
VARTYPE vt;
union {
unsigned int uintVal;
BSTR bstrVal;
};
};
void InitVariantFromUInt32(unsigned int u, VARIANT * v)
{
v->vt = VT_UI4;
v->uintVal = u;
}
void InitVariantFromString(char const * s, VARIANT * v)
{
v->vt = VT_BSTR;
delete[] v->bstrVal;
v->bstrVal = new char[strlen(s)];
strcpy(v->bstrVal, s);
}
// VARIANT get value functions
template < typename T >
T VariantGetValue(VARIANT) = delete;
template <>
unsigned int VariantGetValue<unsigned int>(VARIANT Variant)
{
if (Variant.vt != VT_UI4)
throw std::runtime_error("bad get");
return Variant.uintVal;
}
template <>
BSTR VariantGetValue<BSTR>(VARIANT Variant)
{
if (Variant.vt != VT_BSTR)
throw std::runtime_error("bad get");
return Variant.bstrVal;
}
int main()
{
VARIANT v;
InitVariantFromUInt32(14, &v);
std::cout << VariantGetValue<unsigned int>(v) << '\n';
try {
std::cout << VariantGetValue<BSTR>(v) << '\n';
} catch (std::exception const& e) {
std::cout << "Get failed!" << '\n';
}
VARIANT w;
InitVariantFromString("Hello World!", &w);
std::cout << VariantGetValue<BSTR>(w) << '\n';
//std::cout << VariantGetValue<bool>(w) << '\n'; // error: call to deleted function 'VariantGetValue'
}

Is it possible to ASSERT_DOES_NOT_COMPILE with GTest?

Assume a template class where we assert at compile time that the integer template argument must be greater zero:
template<int N>
class A
{
public:
A() {
static_assert(N > 0, "N needs to be greater 0.");
}
};
Is it possible to create a googletest unit test that compiles, but reports the error at runtime? For example:
TEST(TestA, ConstructionNotAllowedWithZero)
{
ASSERT_DOES_NOT_COMPILE(
{
A< 0 > a;
}
);
}
There is a way, but sadly it's probably not the way you want.
My first thought was to try to get SFINAE to discount an overload by expanding an invalid lambda in an unevaluated context. Unhappily (in your case), this is specifically disallowed...
#define CODE { \
utter garbage \
}
struct test
{
template<class T>
static std::false_type try_compile(...) { return{}; }
template<class T>
static auto try_compile(int)
-> decltype([]() CODE, void(), std::true_type());
{ return {}; }
};
struct tag {};
using does_compile = decltype(test::try_compile<tag>(0));
output:
./maybe_compile.cpp:88:17: error: lambda expression in an unevaluated operand
-> decltype([]() CODE, void(), std::true_type());
So it was back to the drawing board and a good old system call to call out to the compiler...
#include <iostream>
#include <string>
#include <cstdlib>
#include <fstream>
#include <sstream>
struct temp_file {
temp_file()
: filename(std::tmpnam(nullptr))
{}
~temp_file() {
std::remove(filename.c_str());
}
std::string filename;
};
bool compiles(const std::string code, std::ostream& reasons)
{
using namespace std::string_literals;
temp_file capture_file;
temp_file cpp_file;
std::ofstream of(cpp_file.filename);
std::copy(std::begin(code), std::end(code), std::ostream_iterator<char>(of));
of.flush();
of.close();
const auto cmd_line = "c++ -x c++ -o /dev/null "s + cpp_file.filename + " 2> " + capture_file.filename;
auto val = system(cmd_line.c_str());
std::ifstream ifs(capture_file.filename);
reasons << ifs.rdbuf();
ifs.close();
return val == 0;
}
auto main() -> int
{
std::stringstream reasons1;
const auto code1 =
R"code(
#include <iostream>
int main() {
return 0;
}
)code";
std::cout << "compiles: " << compiles(code1, reasons1) << std::endl;
std::stringstream reasons2;
const auto code2 =
R"code(
#include <iostream>
int main() {
FOO!!!!XC#£$%^&*()VBNMYGHH
return 0;
}
)code";
std::cout << "compiles: " << compiles(code2, reasons2) << std::endl;
std::cout << "\nAnd here's why...\n";
std::cout << reasons2.str() << std::endl;
return 0;
}
which in my case gives the following example output:
compiles: 1
compiles: 0
And here's why...
/var/tmp/tmp.3.2dADZ7:4:9: error: use of undeclared identifier 'FOO'
FOO!!!!XC#£$%^&*()VBNMYGHH
^
/var/tmp/tmp.3.2dADZ7:4:19: error: non-ASCII characters are not allowed outside of literals and identifiers
FOO!!!!XC#£$%^&*()VBNMYGHH
^
2 errors generated.
of course you can add all the necessary macros around the call to compiles() in order to GTESTify it. You will of course have to set command line options on the c-compiler invocation to set the correct paths and defines.

Using Boost.Spirit.Lex and stream iterators

I want use Boost.Spirit.Lex to lex a binary file; for this purpose I wrote the following program (here is an extract):
#include <boost/spirit/include/lex_lexertl.hpp>
#include <boost/spirit/include/support_multi_pass.hpp>
#include <boost/bind.hpp>
#include <boost/ref.hpp>
#include <fstream>
#include <iterator>
#include <string>
namespace spirit = boost::spirit;
namespace lex = spirit::lex;
#define X 1
#define Y 2
#define Z 3
template<typename L>
class word_count_tokens : public lex::lexer<L>
{
public:
word_count_tokens () {
this->self.add
("[^ \t\n]+", X)
("\n", Y)
(".", Z);
}
};
class counter
{
public:
typedef bool result_type;
template<typename T>
bool operator () (const T &t, size_t &c, size_t &w, size_t &l) const {
switch (t.id ()) {
case X:
++w; c += t.value ().size ();
break;
case Y:
++l; ++c;
break;
case Z:
++c;
break;
}
return true;
}
};
int main (int argc, char **argv)
{
std::ifstream ifs (argv[1], std::ios::in | std::ios::binary);
auto first = spirit::make_default_multi_pass (std::istream_iterator<char> (ifs));
auto last = spirit::make_default_multi_pass (std::istream_iterator<char> ());
size_t w, c, l;
word_count_tokens<lex::lexertl::lexer<>> word_count_functor;
w = c = l = 0;
bool r = lex::tokenize (first, last, word_count_functor, boost::bind (counter (), _1, boost::ref (c), boost::ref (w), boost::ref (l)));
ifs.close ();
if (r) {
std::cout << l << ", " << w << ", " << c << std::endl;
}
return 0;
}
The build returns the following error:
lexer.hpp:390:46: error: non-const lvalue reference to type 'const char *' cannot bind to a value of unrelated type
Now, the error is due to definition of concrete lexer, lex::lexer<>; in fact its first parameter is defaulted to const char *. I obtain the same error also if I use spirit::istream_iterator or spirit::make_default_multi_pass (.....).
But if I specify the correct template parameters of lex::lexer<> I obtain a plethora of errors!
Solutions?
Update
I have putted all source file; it's the word_counter site's example.
Okay, since the question was changed, here's a new answer, addressing some points with the complete code sample.
Firstly, you need to use a custom token type. I.e.
word_count_tokens<lex::lexertl::lexer<lex::lexertl::token<boost::spirit::istream_iterator>>> word_count_functor;
// instead of:
// word_count_tokens<lex::lexertl::lexer<>> word_count_functor;
Obviously, it's customary to typedef lex::lexertl::token<boost::spirit::istream_iterator>
You need to use min_token_id instead of token IDs 1,2,3. Also, make it an enum for ease of maintenance:
enum token_ids {
X = lex::min_token_id + 1,
Y,
Z,
};
You can no longer just use .size() on the default token value() since the iterator range is not RandomAccessRange anymore. Instead, employ boost::distance() which is specialized for iterator_range:
++w; c += boost::distance(t.value()); // t.value ().size ();
Combining these fixes: Live On Coliru
#include <boost/spirit/include/lex_lexertl.hpp>
#include <boost/spirit/include/support_istream_iterator.hpp>
#include <boost/bind.hpp>
#include <fstream>
namespace spirit = boost::spirit;
namespace lex = spirit::lex;
enum token_ids {
X = lex::min_token_id + 1,
Y,
Z,
};
template<typename L>
class word_count_tokens : public lex::lexer<L>
{
public:
word_count_tokens () {
this->self.add
("[^ \t\n]+", X)
("\n" , Y)
("." , Z);
}
};
struct counter
{
typedef bool result_type;
template<typename T>
bool operator () (const T &t, size_t &c, size_t &w, size_t &l) const {
switch (t.id ()) {
case X:
++w; c += boost::distance(t.value()); // t.value ().size ();
break;
case Y:
++l; ++c;
break;
case Z:
++c;
break;
}
return true;
}
};
int main (int argc, char **argv)
{
std::ifstream ifs (argv[1], std::ios::in | std::ios::binary);
ifs >> std::noskipws;
boost::spirit::istream_iterator first(ifs), last;
word_count_tokens<lex::lexertl::lexer<lex::lexertl::token<boost::spirit::istream_iterator>>> word_count_functor;
size_t w = 0, c = 0, l = 0;
bool r = lex::tokenize (first, last, word_count_functor,
boost::bind (counter (), _1, boost::ref (c), boost::ref (w), boost::ref (l)));
ifs.close ();
if (r) {
std::cout << l << ", " << w << ", " << c << std::endl;
}
}
When run on itself, prints
65, 183, 1665
I think the real problem is not shown. You don't show first or last and I have a feeling you might have temporaries there.
Here's a sample I came up with to verify, perhaps you can see what it is you're doing ---wrong--- differently :)
Live on Coliru (memory mapped an byte-vector, via const char*)
And this alternative (using spirit::istream_iterator)
#include <boost/spirit/include/lex_lexertl.hpp>
#include <boost/spirit/include/qi.hpp>
#include <fstream>
#ifdef MEMORY_MAPPED
# include <boost/iostreams/device/mapped_file.hpp>
#endif
namespace /*anon*/
{
namespace qi =boost::spirit::qi;
namespace lex=boost::spirit::lex;
template <typename Lexer>
struct mylexer_t : lex::lexer<Lexer>
{
mylexer_t()
{
fileheader = "hello";
this->self = fileheader
| space [ lex::_pass = lex::pass_flags::pass_ignore ];
}
lex::token_def<lex::omit>
fileheader, space;
};
template <typename Iterator> struct my_grammar_t
: public qi::grammar<Iterator>
{
template <typename TokenDef>
my_grammar_t(TokenDef const& tok)
: my_grammar_t::base_type(header)
{
header = tok.fileheader;
BOOST_SPIRIT_DEBUG_NODE(header);
}
private:
qi::rule<Iterator> header;
};
}
namespace /* */ {
std::string safechar(char ch) {
switch (ch) {
case '\t': return "\\t"; break;
case '\0': return "\\0"; break;
case '\r': return "\\r"; break;
case '\n': return "\\n"; break;
}
return std::string(1, ch);
}
template <typename It>
std::string showtoken(const boost::iterator_range<It>& range)
{
std::ostringstream oss;
oss << '[';
std::transform(range.begin(), range.end(), std::ostream_iterator<std::string>(oss), safechar);
oss << ']';
return oss.str();
}
}
bool parsefile(const std::string& spec)
{
#ifdef MEMORY_MAPPED
typedef char const* It;
boost::iostreams::mapped_file mmap(spec.c_str(), boost::iostreams::mapped_file::readonly);
char const *first = mmap.const_data();
char const *last = first + mmap.size();
#else
typedef char const* It;
std::ifstream in(spec.c_str());
in.unsetf(std::ios::skipws);
std::string v(std::istreambuf_iterator<char>(in.rdbuf()), std::istreambuf_iterator<char>());
It first = &v[0];
It last = first+v.size();
#endif
typedef lex::lexertl::token<It /*, boost::mpl::vector<char, unsigned int, std::string> */> token_type;
typedef lex::lexertl::actor_lexer<token_type> lexer_type;
typedef mylexer_t<lexer_type>::iterator_type iterator_type;
try
{
static mylexer_t<lexer_type> mylexer;
static my_grammar_t<iterator_type> parser(mylexer);
auto iter = mylexer.begin(first, last);
auto end = mylexer.end();
bool r = qi::parse(iter, end, parser);
r = r && (iter == end);
if (!r)
std::cerr << spec << ": parsing failed at: \"" << std::string(first, last) << "\"\n";
return r;
}
catch (const qi::expectation_failure<iterator_type>& e)
{
std::cerr << "FIXME: expected " << e.what_ << ", got '";
for (auto it=e.first; it!=e.last; it++)
std::cerr << showtoken(it->value());
std::cerr << "'" << std::endl;
return false;
}
}
int main()
{
if (parsefile("input.bin"))
return 0;
return 1;
}
For the variant:
typedef boost::spirit::istream_iterator It;
std::ifstream in(spec.c_str());
in.unsetf(std::ios::skipws);
It first(in), last;