I have a INI file like
[Section1]
Value1 = /home/%USER%/Desktop
Value2 = /home/%USER%/%SOME_ENV%/Test
and want to parse it using Boost. I tried using Boost property_tree like
boost::property_tree::ptree pt;
boost::property_tree::ini_parser::read_ini("config.ini", pt);
std::cout << pt.get<std::string>("Section1.Value1") << std::endl;
std::cout << pt.get<std::string>("Section1.Value2") << std::endl;
But it didn't expand the environment variable. Output looks like
/home/%USER%/Desktop
/home/%USER%/%SOME_ENV%/Test
I was expecting something like
/home/Maverick/Desktop
/home/Maverick/Doc/Test
I am not sure if it is even possible with boost property_tree.
I would appreciate any hint to parse this kind of file using boost.
And here's another take on it, using the old crafts:
not requiring Spirit, or indeed Boost
not hardwiring the interface to std::string (instead allowing any combination of input iterators and output iterator)
handling %% "properly" as a single % 1
The essence:
#include <string>
#include <algorithm>
static std::string safe_getenv(std::string const& macro) {
auto var = getenv(macro.c_str());
return var? var : macro;
}
template <typename It, typename Out>
Out expand_env(It f, It l, Out o)
{
bool in_var = false;
std::string accum;
while (f!=l)
{
switch(auto ch = *f++)
{
case '%':
if (in_var || (*f!='%'))
{
in_var = !in_var;
if (in_var)
accum.clear();
else
{
accum = safe_getenv(accum);
o = std::copy(begin(accum), end(accum), o);
}
break;
} else
++f; // %% -> %
default:
if (in_var)
accum += ch;
else
*o++ = ch;
}
}
return o;
}
#include <iterator>
std::string expand_env(std::string const& input)
{
std::string result;
expand_env(begin(input), end(input), std::back_inserter(result));
return result;
}
#include <iostream>
#include <sstream>
#include <list>
int main()
{
// same use case as first answer, show `%%` escape
std::cout << "'" << expand_env("Greeti%%ng is %HOME% world!") << "'\n";
// can be done streaming, to any container
std::istringstream iss("Greeti%%ng is %HOME% world!");
std::list<char> some_target;
std::istreambuf_iterator<char> f(iss), l;
expand_env(f, l, std::back_inserter(some_target));
std::cout << "Streaming results: '" << std::string(begin(some_target), end(some_target)) << "'\n";
// some more edge cases uses to validate the algorithm (note `%%` doesn't
// act as escape if the first ends a 'pending' variable)
std::cout << "'" << expand_env("") << "'\n";
std::cout << "'" << expand_env("%HOME%") << "'\n";
std::cout << "'" << expand_env(" %HOME%") << "'\n";
std::cout << "'" << expand_env("%HOME% ") << "'\n";
std::cout << "'" << expand_env("%HOME%%HOME%") << "'\n";
std::cout << "'" << expand_env(" %HOME%%HOME% ") << "'\n";
std::cout << "'" << expand_env(" %HOME% %HOME% ") << "'\n";
}
Which, on my box, prints:
'Greeti%ng is /home/sehe world!'
Streaming results: 'Greeti%ng is /home/sehe world!'
''
'/home/sehe'
' /home/sehe'
'/home/sehe '
'/home/sehe/home/sehe'
' /home/sehe/home/sehe '
' /home/sehe /home/sehe '
1 Of course, "properly" is subjective. At the very least, I think this
would be useful (how else would you configure a value legitimitely containing %?)
is how cmd.exe does it on Windows
I'm pretty sure that this could be done trivally (see my newer answer) using a handwritten parser, but I'm personally a fan of Spirit:
grammar %= (*~char_("%")) % as_string ["%" >> +~char_("%") >> "%"]
[ _val += phx::bind(safe_getenv, _1) ];
Meaning:
take all non-% chars, if any
then take any word from inside %s and pass it through safe_getenv before appending
Now, safe_getenv is a trivial wrapper:
static std::string safe_getenv(std::string const& macro) {
auto var = getenv(macro.c_str());
return var? var : macro;
}
Here's a complete minimal implementation:
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
static std::string safe_getenv(std::string const& macro) {
auto var = getenv(macro.c_str());
return var? var : macro;
}
std::string expand_env(std::string const& input)
{
using namespace boost::spirit::qi;
using boost::phoenix::bind;
static const rule<std::string::const_iterator, std::string()> compiled =
*(~char_("%")) [ _val+=_1 ]
% as_string ["%" >> +~char_("%") >> "%"] [ _val += bind(safe_getenv, _1) ];
std::string::const_iterator f(input.begin()), l(input.end());
std::string result;
parse(f, l, compiled, result);
return result;
}
int main()
{
std::cout << expand_env("Greeting is %HOME% world!\n");
}
This prints
Greeting is /home/sehe world!
on my box
Notes
this is not optimized (well, not beyond compiling the rule once)
replace_regex_copy would do as nicely and more efficient (?)
see this answer for a slightly more involved 'expansion' engine: Compiling a simple parser with Boost.Spirit
using output iterator instead of std::string for accumulation
allowing nested variables
allowing escapes
Related
I am still trying to wrap my head around Boost::Spirit.
I want to parse two words into a variable. When I can do that, into a struct.
The single word compiles, the Variable doesn't. Why?
#include <boost/spirit/include/qi.hpp>
#include <boost/tuple/tuple.hpp>
#include <string>
#include <iostream>
using namespace boost::spirit;
/*
class Syntax : public qi::parser{
};
*/
int main()
{
//get user input
std::string input;
std::getline(std::cin, input);
auto it = input.begin();
bool result;
//define grammar for a single word
auto word_grammar = +qi::alnum - qi::space;
std::string singleWord;
result = qi::parse(
it, input.end(),
word_grammar,
singleWord
);
if(!result){
std::cout << "Failed to parse a word" << '\n';
return -1;
}
std::cout << "\"" << singleWord << "\"" << '\n';
//Now parse two words into a variable
std::cout << "Variable:\n";
typedef boost::tuple<std::string, std::string> Variable;
Variable variable;
auto variable_grammar = word_grammar >> word_grammar;
result = qi::parse(
it, input.end(),
variable_grammar,
variable
);
if(!result){
std::cout << "Failed to parse a variable" << '\n';
return -1;
}
std::cout << "\"" << variable.get<0>() << "\" \"" << variable.get<1>() << "\"" << '\n';
//now parse a list of variables
std::cout << "List of Variables:\n";
std::list<Variable> variables;
result = qi::parse(
it, input.end(),
variable_grammar % +qi::space,
variable
);
if(!result){
std::cout << "Failed to parse a list of variables" << '\n';
return -1;
}
for(auto var : variables)
std::cout << "DataType: " << var.get<0>() << ", VariableName: " << var.get<1>() << '\n';
}
In the end I want to parse something like this:
int a
float b
string name
Templates are nice, but when problems occur the error messages are just not human readable (thus no point in posting them here).
I am using the gcc
Sorry to take so long. I've been building a new web server in a hurry and had much to learn.
Here is what it looks like in X3. I think it is easier to deal with than qi. And then, I've used it a lot more. But then qi is much more mature, richer. That said, x3 is meant to be adaptable, hackable. So you can make it do just about anything you want.
So, live on coliru
#include <string>
#include <iostream>
#include <vector>
#include <boost/spirit/home/x3.hpp>
#include <boost/tuple/tuple.hpp>
//as pointed out, for the error 'The parser expects tuple-like attribute type'
#include <boost/fusion/adapted/boost_tuple.hpp>
//our declarations
using Variable = boost::tuple<std::string, std::string>;
using Vector = std::vector<Variable>;
namespace parsers {
using namespace boost::spirit::x3;
auto const word = lexeme[+char_("a-zA-Z")];
//note, using 'space' as the stock skipper
auto const tuple = word >> word;
}
std::ostream& operator << (std::ostream& os, /*const*/ Variable& obj) {
return os << obj.get<0>() << ' ' << obj.get<1>();
}
std::ostream& operator << (std::ostream& os, /*const*/ Vector& obj) {
for (auto& item : obj)
os << item << " : ";
return os;
}
template<typename P, typename A>
bool test_parse(std::string in, P parser, A& attr) {
auto begin(in.begin());
bool r = phrase_parse(begin, in.end(), parser, boost::spirit::x3::space, attr);
std::cout << "result:\n " << attr << std::endl;
return r;
}
int main()
{
//not recomended but this is testing stuff
using namespace boost::spirit::x3;
using namespace parsers;
std::string input("first second third forth");
//parse one word
std::string singleWord;
test_parse(input, word, singleWord);
//parse two words into a variable
Variable variable;
test_parse(input, tuple, variable);
//parse two sets of two words
Vector vector;
test_parse(input, *tuple, vector);
}
You may like this form of testing. You can concentrate on testing parsers without a lot of extra code. It makes it easier down the road to keep your basic parsers in their own namespace. Oh yea, x3 compiles much faster than qi!
The single word compiles, the Variable doesn't. Why?
There are missing two #includes:
#include <boost/fusion/adapted/boost_tuple.hpp>
#include <boost/spirit/include/qi_list.hpp>
I'm trying to create a GPIB parser using Spirit.Qi. Sometimes the response can
be either an error or a normal response. This seemed like a good use case for
the alternative parser which yields a boost::variant; however, if one of the
variant types contains a string the code fails to compile. Here is a simplified
version that reproduces the error.
struct C1 {
std::string h{""};
int i{0};
};
BOOST_FUSION_ADAPT_STRUCT(C1, (std::string, h)(int, i))
struct C2 {
std::string h{""};
std::string c{};
};
BOOST_FUSION_ADAPT_STRUCT(C2, (std::string, h)(std::string, c))
using VariantType = boost::variant<C1, C2>;
int main() {
std::string s2{"C2:Zoo3"};
VariantType v1;
if(qi::parse(s1.begin(), s1.end(),
(qi::string("C1") >> ":" >> qi::int_) |
(qi::string("C2") >> ":" >> *qi::char_),
v1)) {
if(boost::get<C1>(&v1)) {
auto a1 = boost::get<C1>(v1);
std::cout << "Parsing Succeeded, a1 = " << a1.h << ":"
<< a1.i << std::endl;
}
else {
auto a2 = boost::get<C2>(v1);
std::cout << "Parsing Succeeded, a2 = " << a2.h << ":"
<< a2.c << std::endl;
}
}
else {
std::cout << "Parsing Failed" << std::endl;
}
return 0;
}
I've experimented with various parsers other than *qi::char_ (eg. qi::string) to no avail. If I change C2::c to a char it works ok for 1 char. The best workaround I have found so far is to change C2::c to a std::vector<char>, this works fine but isn't ideal. I also tried telling Qi that std::string is a container like here. But qi knows what a std::string is so I'm pretty sure it ignores my customization. I think this is all because std::string isn't a POD and wasn't supported in unions until the rules were relaxed, but it works with boost::variant when it isn't in a struct, and std::vector works. Any ideas/workarounds would be appreciated.
*Note: I didn't post the compiler errors as they are long and mangled and I figured this was a known issue of std::string and variants. If they would be helpful let me know and I'll post them.
There's nothing wrong with the code, as far as I can tell.
I've tested on c++1{1,4,y} and boost 1.{57,58}.0, using gcc {4.9,5.x} and clang++ 3.5.
I suspect you may have an awkward Boost verion. Try using qi::as_string[*qi::char_] there. ¹
Live On Coliru
#include <iostream>
#include <boost/fusion/adapted/struct.hpp>
#include <boost/spirit/include/qi.hpp>
struct C1 {
std::string h{""};
int i{0};
friend std::ostream& operator<<(std::ostream& os, C1 const& c1) {
return os << "C1 {h:'" << c1.h << "', i:'" << c1.i << "'}";
}
};
struct C2 {
std::string h{""};
std::string c{};
friend std::ostream& operator<<(std::ostream& os, C2 const& c2) {
return os << "C2 {h:'" << c2.h << "', c:'" << c2.c << "'}";
}
};
BOOST_FUSION_ADAPT_STRUCT(C1, (std::string, h)(int, i))
BOOST_FUSION_ADAPT_STRUCT(C2, (std::string, h)(std::string, c))
using VariantType = boost::variant<C1, C2>;
namespace qi = boost::spirit::qi;
int main() {
VariantType value;
for(std::string s1 : {
"C2:Zoo3",
"C1:1234"
})
{
if(qi::parse(s1.begin(), s1.end(),
(qi::string("C1") >> ":" >> qi::int_) |
(qi::string("C2") >> ":" >> *qi::char_),
value))
std::cout << "Parsing Succeeded: " << value << "\n";
else
std::cout << "Parsing Failed" << std::endl;
}
}
Prints
Parsing Succeeded: C2 {h:'C2', c:'Zoo3'}
Parsing Succeeded: C1 {h:'C1', i:'1234'}
¹ I don't recommend qi::attr_cast<> as I remember this having had an awkward bug in awkwardly old boost versions.
I am trying to create a C++ code that using boost libraries reads an input file like the following,
1 12 13 0 0 1 0 INLE
.
.
.
In this case, I must do an action if the condition specified on the last column of the right is INLE.
I have the following code,
#include <iostream>
#include <fstream>
#include <string>
#include <boost/algorithm/string/predicate.hpp>
int main(int argc, const char * argv[])
{
std::string line;
const std::string B_condition = "INLE";
std::ifstream myfile ("ramp.bnd");
if (myfile.is_open())
{
while ( getline (myfile,line) )
{
if (boost::algorithm::ends_with(line,B_condition)==true)
{
std::cout << "Its True! \n"; // just for testing
//add complete code
}
}
myfile.close();
}
else std::cout << "Unable to open file";
return 0;
}
while compiling there are no issues, but when I run, it doesnt shows anything.
By the other side, if I modify my boolean condition to false, it will print "Its true!" the number of lines that my input file has.
What am I doing wrong?
Thanks!!
I can only assume that:
your file contains whitespace at the end (use trim)
your file has windows line ends (CRLF) but you're reading it as UNIX text files, meaning that the lines will include a trailing `\r' (CR) (often shown as ^M in various text editors/pagers).
So, either
fix the line endings
trim whitespace from the lines before comparing
or both
Best: use a 'proper' parser to do the work.
Update adding a quick & dirty approach using Boost Spirit: see it Live On Coliru
int main()
{
std::ifstream myfile("ramp.bnd");
myfile.unsetf(std::ios::skipws);
boost::spirit::istream_iterator f(myfile), l;
using namespace qi;
bool ok = phrase_parse(f, l,
(repeat(7) [ int_ ] >> as_string[lexeme[+(char_ - eol)]])
[ phx::bind(process_line, _1, _2) ]
% eol, // supports CRLF and LF
blank);
if (!ok)
std::cerr << "Parse errors\n";
if (f!=l)
std::cerr << "Remaing input: '" << std::string(f,l) << "'\n";
}
As you can see, it validates the whole line, assuming (for now) that the columns are 7 integer values and a string (e.g. "INLE"). Now, the actual work is much simpler and can be implemented in a separate function:
void process_line(std::vector<int> const& values, std::string const& kind)
{
if (kind == "INLE")
{
std::cout << "Column 1: " << values[0] << "\n";
}
}
The actual processing function doesn't have to meddle with trimming, line ends, even parsing the details columns :)
Full Code for reference
#include <iostream>
#include <fstream>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
namespace qi = boost::spirit::qi;
namespace phx = boost::phoenix;
static const std::string B_condition = "INLE";
void process_line(std::vector<int> const& values, std::string const& kind)
{
if (kind == "INLE")
{
std::cout << "Column 1: " << values[0] << "\n";
}
}
int main()
{
std::ifstream myfile("ramp.bnd");
myfile.unsetf(std::ios::skipws);
boost::spirit::istream_iterator f(myfile), l;
using namespace qi;
bool ok = phrase_parse(f, l,
(repeat(7) [ int_ ] >> as_string[lexeme[+(char_ - eol)]])
[ phx::bind(process_line, _1, _2) ]
% eol, // supports CRLF and LF
blank);
if (!ok)
std::cerr << "Parse errors\n";
if (f!=l)
std::cerr << "Remaing input: '" << std::string(f,l) << "'\n";
}
You don't need a library like boost at all. A solution with pur standard C++ is possible in some lines of code too:
const std::string B_condition = "INLE";
std::ifstream myfile ("ramp.bnd");
for( char c; myfile >> c; )
{
if( std::isdigit(c, myfile.getloc() ) ) // needs #include <locale>
{
int i;
if( myfile.putback(c) >> i )
std::cout << "read " << i << std::endl; // do something with 'i'
}
else
{
std::string token;
if( myfile.putback(c) >> token )
{
if( token == B_condition )
std::cout << B_condition << " found\n";
else
; // no number, no B_condition -> what ever You want to do
}
}
}
Using boost spirit, I'd like to extract a string that is followed by some data in parentheses. The relevant string is separated by a space from the opening parenthesis. Unfortunately, the string itself may contain spaces. I'm looking for a concise solution that returns the string without a trailing space.
The following code illustrates the problem:
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>
#include <string>
#include <iostream>
namespace qi = boost::spirit::qi;
using std::string;
using std::cout;
using std::endl;
void
test_input(const string &input)
{
string::const_iterator b = input.begin();
string::const_iterator e = input.end();
string parsed;
bool const r = qi::parse(b, e,
*(qi::char_ - qi::char_("(")) >> qi::lit("(Spirit)"),
parsed
);
if(r) {
cout << "PASSED:" << endl;
} else {
cout << "FAILED:" << endl;
}
cout << " Parsed: \"" << parsed << "\"" << endl;
cout << " Rest: \"" << string(b, e) << "\"" << endl;
}
int main()
{
test_input("Fine (Spirit)");
test_input("Hello, World (Spirit)");
return 0;
}
Its output is:
PASSED:
Parsed: "Fine "
Rest: ""
PASSED:
Parsed: "Hello, World "
Rest: ""
With this simple grammar, the extracted string is always followed by a space (that I 'd like to eliminate).
The solution should work within Spirit since this is only part of a larger grammar. (Thus, it would probably be clumsy to trim the extracted strings after parsing.)
Thank you in advance.
Like the comment said, in the case of a single space, you can just hard code it. If you need to be more flexible or tolerant:
I'd use a skipper with raw to "cheat" the skipper for your purposes:
bool const r = qi::phrase_parse(b, e,
qi::raw [ *(qi::char_ - qi::char_("(")) ] >> qi::lit("(Spirit)"),
qi::space,
parsed
);
This works, and prints
PASSED:
Parsed: "Fine"
Rest: ""
PASSED:
Parsed: "Hello, World"
Rest: ""
See it Live on Coliru
Full program for reference:
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>
#include <string>
#include <iostream>
namespace qi = boost::spirit::qi;
using std::string;
using std::cout;
using std::endl;
void
test_input(const string &input)
{
string::const_iterator b = input.begin();
string::const_iterator e = input.end();
string parsed;
bool const r = qi::phrase_parse(b, e,
qi::raw [ *(qi::char_ - qi::char_("(")) ] >> qi::lit("(Spirit)"),
qi::space,
parsed
);
if(r) {
cout << "PASSED:" << endl;
} else {
cout << "FAILED:" << endl;
}
cout << " Parsed: \"" << parsed << "\"" << endl;
cout << " Rest: \"" << string(b, e) << "\"" << endl;
}
int main()
{
test_input("Fine (Spirit)");
test_input("Hello, World (Spirit)");
return 0;
}
I need to parse and generate some texts from and to c++ objects.
The syntax is:
command #param #param #param
There is set of commands some of them have no params etc.
Params are mainly numbers.
The question is: Should I use Boost Spirit for this task? Or just simply tokenize each line evaluate function to call from string compare with command, read additional parameters and create cpp object from it?
If you suggest using Spirit or any other solution it would be nice if you could provide some examples similiar to my problem. I've read and tried all examples from Boost Spirit doc.
I implemented more or less precisely this in a previous answer to the question " Using boost::bind with boost::function: retrieve binded variable type ".
The complete working sample program (which expects a very similar grammar) using Boost Spirit is here: https://gist.github.com/1314900. You'd just want to remove the /execute literals for your grammar, so edit Line 41 from
if (!phrase_parse(f,l, "/execute" > (
to
if (!phrase_parse(f,l, (
The example script
WriteLine "bogus"
Write "here comes the answer: "
Write 42
Write 31415e-4
Write "that is the inverse of" 24 "and answers nothing"
Shutdown "Bye" 9
Shutdown "Test default value for retval"
Now results in the following output after execution:
WriteLine('bogus');
Write(string: 'here comes the answer: ');
Write(double: 42);
Write(double: 3.1415);
Write(string: 'that is the inverse of');
Write(double: 24);
Write(string: 'and answers nothing');
Shutdown(reason: 'Bye', retval: 9)
Shutdown(reason: 'Test default value for retval', retval: 0)
Full Code
For archival purposes:
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <fstream>
namespace qi = boost::spirit::qi;
namespace phx = boost::phoenix;
///////////////////////////////////
// 'domain classes' (scriptables)
struct Echo
{
void WriteLine(const std::string& s) { std::cout << "WriteLine('" << s << "');" << std::endl; }
void WriteStr (const std::string& s) { std::cout << "Write(string: '" << s << "');" << std::endl; }
void WriteInt (int i) { std::cout << "Write(int: " << i << ");" << std::endl; }
void WriteDbl (double d) { std::cout << "Write(double: " << d << ");" << std::endl; }
void NewLine () { std::cout << "NewLine();" << std::endl; }
} echoService;
struct Admin
{
void Shutdown(const std::string& reason, int retval)
{
std::cout << "Shutdown(reason: '" << reason << "', retval: " << retval << ")" << std::endl;
// exit(retval);
}
} adminService;
void execute(const std::string& command)
{
typedef std::string::const_iterator It;
It f(command.begin()), l(command.end());
using namespace qi;
using phx::bind;
using phx::ref;
rule<It, std::string(), space_type> stringlit = lexeme[ '"' >> *~char_('"') >> '"' ];
try
{
if (!phrase_parse(f,l, /*"/execute" >*/ (
(lit("WriteLine")
> stringlit [ bind(&Echo::WriteLine, ref(echoService), _1) ])
| (lit("Write") >> +(
double_ [ bind(&Echo::WriteDbl, ref(echoService), _1) ] // the order matters
| int_ [ bind(&Echo::WriteInt, ref(echoService), _1) ]
| stringlit [ bind(&Echo::WriteStr, ref(echoService), _1) ]
))
| (lit("NewLine") [ bind(&Echo::NewLine, ref(echoService)) ])
| (lit("Shutdown") > (stringlit > (int_ | attr(0)))
[ bind(&Admin::Shutdown, ref(adminService), _1, _2) ])
), space))
{
if (f!=l) // allow whitespace only lines
std::cerr << "** (error interpreting command: " << command << ")" << std::endl;
}
}
catch (const expectation_failure<It>& e)
{
std::cerr << "** (unexpected input '" << std::string(e.first, std::min(e.first+10, e.last)) << "') " << std::endl;
}
if (f!=l)
std::cerr << "** (warning: skipping unhandled input '" << std::string(f,l) << "')" << std::endl;
}
int main()
{
std::ifstream ifs("input.txt");
std::string command;
while (std::getline(ifs/*std::cin*/, command))
execute(command);
}
For simple formatted, easily tested input, tokenizing should be enough.
When tokenizing, you can read a line from the input and put that in a stringstream (iss). From iss, you read the first word and pass that to a command factory which creates the right command for you. Then you can pass iss to the readInParameters function of the new command, so each command can parse it own parameters and check whether all parameters are valid.
Not tested code-sample:
std::string line;
std::getline(inputStream, line);
std::istringstream iss(line);
std::string strCmd;
iss >> strCmd;
try
{
std::unique_ptr<Cmd> newCmd = myCmdFactory(strCmd);
newCmd->readParameters(iss);
newCmd->execute();
//...
}
catch (std::exception& e)
{
std::cout << "Issue with received command: " << e.what() << "\n";
}