I have a file which contains some "entity" data in Valve's format. It's basically a key-value deal, and it looks like this:
{
"world_maxs" "3432 4096 822"
"world_mins" "-2408 -4096 -571"
"skyname" "sky_alpinestorm_01"
"maxpropscreenwidth" "-1"
"detailvbsp" "detail_sawmill.vbsp"
"detailmaterial" "detail/detailsprites_sawmill"
"classname" "worldspawn"
"mapversion" "1371"
"hammerid" "1"
}
{
"origin" "553 -441 322"
"targetname" "tonemap_global"
"classname" "env_tonemap_controller"
"hammerid" "90580"
}
Each pair of {} counts as one entity, and the rows inside count as KeyValues. As you can see, it's fairly straightforward.
I want to process this data into a vector<map<string, string> > in C++. To do this, I've tried using regular expressions that come with Boost. Here is what I have so far:
static const boost::regex entityRegex("\\{(\\s*\"([A-Za-z0-9_]+)\"\\s*\"([^\"]+)\")+\\s*\\}");
boost::smatch what;
while (regex_search(entitiesString, what, entityRegex)) {
cout << what[0] << endl;
cout << what[1] << endl;
cout << what[2] << endl;
cout << what[3] << endl;
break; // TODO
}
Easier-to-read regex:
\{(\s*"([A-Za-z0-9_]+)"\s*"([^"]+)")+\s*\}
I'm not sure the regex is well-formed for my problem yet, but it seems to print the last key-value pair (hammerid, 1) at least.
My question is, how would I go about extracting the "nth" matched subexpression within an expression? Or is there not really a practical way to do this? Would it perhaps be better to write two nested while-loops, one which searches for the {} patterns, and then one which searches for the actual key-value pairs?
Thanks!
Using a parser generator you can code a proper parser.
For example, using Boost Spirit you can define the rules of the grammar inline as C++ expressions:
start = *entity;
entity = '{' >> *entry >> '}';
entry = text >> text;
text = '"' >> *~char_('"') >> '"';
Here's a full demo:
Live On Coliru
#include <boost/spirit/include/qi.hpp>
#include <boost/fusion/adapted/std_pair.hpp>
#include <map>
using Entity = std::map<std::string, std::string>;
using ValveData = std::vector<Entity>;
namespace qi = boost::spirit::qi;
template <typename It, typename Skipper = qi::space_type>
struct Grammar : qi::grammar<It, ValveData(), Skipper>
{
Grammar() : Grammar::base_type(start) {
using namespace qi;
start = *entity;
entity = '{' >> *entry >> '}';
entry = text >> text;
text = '"' >> *~char_('"') >> '"';
BOOST_SPIRIT_DEBUG_NODES((start)(entity)(entry)(text))
}
private:
qi::rule<It, ValveData(), Skipper> start;
qi::rule<It, Entity(), Skipper> entity;
qi::rule<It, std::pair<std::string, std::string>(), Skipper> entry;
qi::rule<It, std::string()> text;
};
int main()
{
using It = boost::spirit::istream_iterator;
Grammar<It> parser;
It f(std::cin >> std::noskipws), l;
ValveData data;
bool ok = qi::phrase_parse(f, l, parser, qi::space, data);
if (ok) {
std::cout << "Parsing success:\n";
int count = 0;
for(auto& entity : data)
{
++count;
for (auto& entry : entity)
std::cout << "Entity " << count << ": [" << entry.first << "] -> [" << entry.second << "]\n";
}
} else {
std::cout << "Parsing failed\n";
}
if (f!=l)
std::cout << "Remaining unparsed input: '" << std::string(f,l) << "'\n";
}
Which prints (for the input shown):
Parsing success:
Entity 1: [classname] -> [worldspawn]
Entity 1: [detailmaterial] -> [detail/detailsprites_sawmill]
Entity 1: [detailvbsp] -> [detail_sawmill.vbsp]
Entity 1: [hammerid] -> [1]
Entity 1: [mapversion] -> [1371]
Entity 1: [maxpropscreenwidth] -> [-1]
Entity 1: [skyname] -> [sky_alpinestorm_01]
Entity 1: [world_maxs] -> [3432 4096 822]
Entity 1: [world_mins] -> [-2408 -4096 -571]
Entity 2: [classname] -> [env_tonemap_controller]
Entity 2: [hammerid] -> [90580]
Entity 2: [origin] -> [553 -441 322]
Entity 2: [targetname] -> [tonemap_global]
I think doing it all with one regex expression is hard because of the variable number of entries inside each entity {}. Personally I would consider using simply std::readline to do your parsing.
#include <map>
#include <vector>
#include <string>
#include <sstream>
#include <iostream>
std::istringstream iss(R"~(
{
"world_maxs" "3432 4096 822"
"world_mins" "-2408 -4096 -571"
"skyname" "sky_alpinestorm_01"
"maxpropscreenwidth" "-1"
"detailvbsp" "detail_sawmill.vbsp"
"detailmaterial" "detail/detailsprites_sawmill"
"classname" "worldspawn"
"mapversion" "1371"
"hammerid" "1"
}
{
"origin" "553 -441 322"
"targetname" "tonemap_global"
"classname" "env_tonemap_controller"
"hammerid" "90580"
}
)~");
int main()
{
std::string skip;
std::string entity;
std::vector<std::map<std::string, std::string> > vm;
// skip to open brace, read entity until close brace
while(std::getline(iss, skip, '{') && std::getline(iss, entity, '}'))
{
// turn entity into input stream
std::istringstream iss(entity);
// temporary map
std::map<std::string, std::string> m;
std::string key, val;
// skip to open quote, read key to close quote
while(std::getline(iss, skip, '"') && std::getline(iss, key, '"'))
{
// skip to open quote read val to close quote
if(std::getline(iss, skip, '"') && std::getline(iss, val, '"'))
m[key] = val;
}
// move map (no longer needed)
vm.push_back(std::move(m));
}
for(auto& m: vm)
{
for(auto& p: m)
std::cout << p.first << ": " << p.second << '\n';
std::cout << '\n';
}
}
Output:
classname: worldspawn
detailmaterial: detail/detailsprites_sawmill
detailvbsp: detail_sawmill.vbsp
hammerid: 1
mapversion: 1371
maxpropscreenwidth: -1
skyname: sky_alpinestorm_01
world_maxs: 3432 4096 822
world_mins: -2408 -4096 -571
classname: env_tonemap_controller
hammerid: 90580
origin: 553 -441 322
targetname: tonemap_global
I would have written it like this:
^\{(\s*"([A-Za-z0-9_]+)"\s*"([^"]+)")+\s*\}$
Or splited the regex into two strings. First match the curly braces, then loop through the content of curly braces line for line.
Match curly braces: ^(\{[^\}]+)$
Match the lines: ^(\s*"([A-Za-z0-9_]+)"\s*"([^"]+)"\s*)$
Related
I'm trying to create a (pretty simple) parser using boost::spirit::qi to extract messages from a stream. Each message starts from a short marker and ends with \r\n. The message body is ASCII text (letters and numbers) separated by a comma. For example:
!START,01,2.3,ABC\r\n
!START,456.2,890\r\n
I'm using unit tests to check the parser and everything works well when I pass only correct messages one by one. But when I try to emulate some invalid input, like:
!START,01,2.3,ABC\r\n
trash-message
!START,456.2,890\r\n
The parser doesn't see the following messages after an unexpected text.
I'm new in boost::spirit and I'd like to know how a parser based on boost::spirit::qi::grammar is supposed to work.
My question is:
Should the parser slide in the input stream and try to find a beginning of a message?
Or the caller should check the parsing result and in case of failure move an iterator and then recall the parser again?
Many thanks for considering my request.
My question is: Should the parser slide in the input stream and try to find a beginning of a message?
Only when you tell it to. It's called qi::parse, not qi::search. But obviously you can make a grammar ignore things.
Live On Coliru
//#define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted.hpp>
#include <boost/spirit/include/qi.hpp>
#include <iomanip>
#include <iostream>
namespace qi = boost::spirit::qi;
struct Command {
enum Type { START, QUIT, TRASH } type = TRASH;
std::vector<std::string> args;
};
using Commands = std::vector<Command>;
BOOST_FUSION_ADAPT_STRUCT(Command, type, args)
template <typename It> struct CmdParser : qi::grammar<It, Commands()> {
CmdParser() : CmdParser::base_type(commands_) {
type_.add("!start", Command::START);
type_.add("!quit", Command::QUIT);
trash_ = *~qi::char_("\r\n"); // just ignore the entire line
arg_ = *~qi::char_(",\r\n");
command_ = qi::no_case[type_] >> *(',' >> arg_);
commands_ = *((command_ | trash_) >> +qi::eol);
BOOST_SPIRIT_DEBUG_NODES((trash_)(arg_)(command_)(commands_))
}
private:
qi::symbols<char, Command::Type> type_;
qi::rule<It, Commands()> commands_;
qi::rule<It, Command()> command_;
qi::rule<It, std::string()> arg_;
qi::rule<It> trash_;
};
int main() {
std::string_view input = "!START,01,2.3,ABC\r\n"
"trash-message\r\n"
"!START,456.2,890\r\n";
using It = std::string_view::const_iterator;
static CmdParser<It> const parser;
Commands parsed;
auto f = input.begin(), l = input.end();
if (parse(f, l, parser, parsed)) {
std::cout << "Parsed:\n";
for(Command const& cmd : parsed) {
std::cout << cmd.type;
for (auto& arg: cmd.args)
std::cout << ", " << quoted(arg);
std::cout << "\n";
}
} else {
std::cout << "Parse failed\n";
}
if (f != l)
std::cout << "Remaining unparsed: " << quoted(std::string(f, l)) << "\n";
}
Printing
Parsed:
0, "01", "2.3", "ABC"
2
0, "456.2", "890"
I'm attempting to parse a string of whitespace-delimited, optionally-tagged keywords. For example
descr:expense type:receivable customer 27.3
where the expression before the colon is the tag, and it is optional (i.e. a default tag is assumed).
I can't quite get the parser to do what I want. I've made some minor adaptations from a canonical example whose purpose it is to parse key/value pairs (much like an HTTP query string).
typedef std::pair<boost::optional<std::string>, std::string> pair_type;
typedef std::vector<pair_type> pairs_type;
template <typename Iterator>
struct field_value_sequence_default_field
: qi::grammar<Iterator, pairs_type()>
{
field_value_sequence_default_field()
: field_value_sequence_default_field::base_type(query)
{
query = pair >> *(qi::lit(' ') >> pair);
pair = -(field >> ':') >> value;
field = +qi::char_("a-zA-Z0-9");
value = +qi::char_("a-zA-Z0-9+-\\.");
}
qi::rule<Iterator, pairs_type()> query;
qi::rule<Iterator, pair_type()> pair;
qi::rule<Iterator, std::string()> field, value;
};
However, when I parse it, when the tag is left out, the optional<string> isn't empty/false. Rather, it's got a copy of the value. The second part of the pair has the value as well.
If the untagged keyword can't be a tag (syntax rules, e.g. has a decimal point), then things work like I'd expect.
What am I doing wrong? Is this a conceptual mistake with the PEG?
Rather, it's got a copy of the value. The second part of the pair has the value as well.
This is the common pitfall with container attributes and backtracking: use qi::hold, e.g. Understanding Boost.spirit's string parser
pair = -qi::hold[field >> ':'] >> value;
Complete sample Live On Coliru
#include <boost/spirit/include/qi.hpp>
#include <boost/fusion/adapted/std_pair.hpp>
#include <boost/optional/optional_io.hpp>
#include <iostream>
namespace qi = boost::spirit::qi;
typedef std::pair<boost::optional<std::string>, std::string> pair_type;
typedef std::vector<pair_type> pairs_type;
template <typename Iterator>
struct Grammar : qi::grammar<Iterator, pairs_type()>
{
Grammar() : Grammar::base_type(query) {
query = pair % ' ';
pair = -qi::hold[field >> ':'] >> value;
field = +qi::char_("a-zA-Z0-9");
value = +qi::char_("a-zA-Z0-9+-\\.");
}
private:
qi::rule<Iterator, pairs_type()> query;
qi::rule<Iterator, pair_type()> pair;
qi::rule<Iterator, std::string()> field, value;
};
int main()
{
using It = std::string::const_iterator;
for (std::string const input : {
"descr:expense type:receivable customer 27.3",
"expense type:receivable customer 27.3",
"descr:expense receivable customer 27.3",
"expense receivable customer 27.3",
}) {
It f = input.begin(), l = input.end();
std::cout << "==== '" << input << "' =============\n";
pairs_type data;
if (qi::parse(f, l, Grammar<It>(), data)) {
std::cout << "Parsed: \n";
for (auto& p : data) {
std::cout << p.first << "\t->'" << p.second << "'\n";
}
} else {
std::cout << "Parse failed\n";
}
if (f != l)
std::cout << "Remaining unparsed: '" << std::string(f,l) << "'\n";
}
}
Printing
==== 'descr:expense type:receivable customer 27.3' =============
Parsed:
descr ->'expense'
type ->'receivable'
-- ->'customer'
-- ->'27.3'
==== 'expense type:receivable customer 27.3' =============
Parsed:
-- ->'expense'
type ->'receivable'
-- ->'customer'
-- ->'27.3'
==== 'descr:expense receivable customer 27.3' =============
Parsed:
descr ->'expense'
-- ->'receivable'
-- ->'customer'
-- ->'27.3'
==== 'expense receivable customer 27.3' =============
Parsed:
-- ->'expense'
-- ->'receivable'
-- ->'customer'
-- ->'27.3'
After some delay I'm now again trying to parse some ASCII text file
surrounded by some binary characters.
Parsing text file with binary envelope using boost Spririt
However I'm now struggling if a skip parser is the right approach?
The grammar of the file (it's a JEDEC file) is quite simple:
Each data field in the file starts with a single letter and ends with an asterisk. The data field can contain spaces and carriage return.
After the asterisk spaces and carriage return might follow too before the
next field identifier.
This is what I used to start building a parser for such a file:
phrase_parse(first, last,
// First char in File
char_('\x02') >>
// Data field
*((print[cout << _1] | graph[cout << _1]) - char_('*')) >>
// End of data followed by 4 digit hexnumber. How to limit?
char_('\x03') >> *xdigit,
// Skip asterisks
char_('*') );
Unfortunately I don't get any output from this one. Does someone have an idea what might be wrong?
Sample file:
<STX>
JEDEC file generated by John Doe*
DM SIGNETICS(PHILIPS)*
DD GAL16R8*
QP20*
QV0*
G0*F0*
L00000 1110101111100110111101101110111100111111*
CDEAD*
<ETX>BEEF
and this is what I want to achive:
Start: JEDEC file generated by John Doe
D: M SIGNETICS(PHILIPS)
D: D GAL16R8
Q: P20
Q: V0
G: 0
F: 0
L: 00000 1110101111100110111101101110111100111111
C: DEAD
End: BEEF
I would suggest you want to use a skipper at the toplevel rule only. And use it to skip the insignificant whitespace.
You don't use a skipper for the asterisks because you do not want to ignore them. If they're ignored, your rules cannot act upon them.
Furthermore the inner rules should not use the space skipper for the simple reason that whitespace and linefeeds are valid field data in JEDEC.
So, the upshot of all this would be:
value = *(ascii::char_("\x20-\x7e\r\n") - '*') >> '*';
field = ascii::graph >> value;
start = STX >> value >> *field >> ETX >> xmit_checksum;
Where the rules would be declared with the respective skippers:
qi::uint_parser<uint16_t, 16, 4, 4> xmit_checksum;
qi::rule<It, ascii::space_type> start;
qi::rule<It> field, value; // no skippers - they are lexemes
Take-away: Split your grammar up in rules. Be happier for it.
Processing the results
Your sample needlessly mixes responsibilities for parsing and "printing".
I'd suggest not using semantic actions here (Boost Spirit: "Semantic actions are evil"?).
Instead, declare appropriate attribute types:
struct JEDEC {
std::string caption;
struct field {
char id;
std::string value;
};
std::vector<field> fields;
uint16_t checksum;
};
And declare them in your rules:
qi::rule<It, ast::JEDEC(), ascii::space_type> start;
qi::rule<It, ast::JEDEC::field()> field;
qi::rule<It, std::string()> value;
qi::uint_parser<uint16_t, 16, 4, 4> xmit_checksum;
Now, nothing needs to be changed in your grammar, and you can print the desired output with:
inline static std::ostream& operator<<(std::ostream& os, JEDEC const& jedec) {
os << "Start: " << jedec.caption << "\n";
for(auto& f : jedec.fields)
os << f.id << ": " << f.value << "\n";
auto saved = os.rdstate();
os << "End: " << std::hex << std::setw(4) << std::setfill('0') << jedec.checksum;
os.setstate(saved);
return os;
}
LIVE DEMO
Here's a demo program that ties it together using the sample input from your question:
Live On Coliru
//#define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted/struct.hpp>
#include <boost/spirit/include/qi.hpp>
#include <iomanip>
namespace qi = boost::spirit::qi;
namespace ascii = qi::ascii;
namespace ast {
struct JEDEC {
std::string caption;
struct field {
char id;
std::string value;
};
std::vector<field> fields;
uint16_t checksum;
};
inline static std::ostream& operator<<(std::ostream& os, JEDEC const& jedec) {
os << "Start: " << jedec.caption << "\n";
for(auto& f : jedec.fields)
os << f.id << ": " << f.value << "\n";
auto saved = os.rdstate();
os << "End: " << std::hex << std::setw(4) << std::setfill('0') << std::uppercase << jedec.checksum;
os.setstate(saved);
return os;
}
}
BOOST_FUSION_ADAPT_STRUCT(ast::JEDEC::field,
(char, id)(std::string, value))
BOOST_FUSION_ADAPT_STRUCT(ast::JEDEC,
(std::string, caption)
(std::vector<ast::JEDEC::field>, fields)
(uint16_t, checksum))
template <typename It>
struct JedecGrammar : qi::grammar<It, ast::JEDEC(), ascii::space_type>
{
JedecGrammar() : JedecGrammar::base_type(start) {
const char STX = '\x02';
const char ETX = '\x03';
value = *(ascii::char_("\x20-\x7e\r\n") - '*') >> '*';
field = ascii::graph >> value;
start = STX >> value >> *field >> ETX >> xmit_checksum;
BOOST_SPIRIT_DEBUG_NODES((start)(field)(value))
}
private:
qi::rule<It, ast::JEDEC(), ascii::space_type> start;
qi::rule<It, ast::JEDEC::field()> field;
qi::rule<It, std::string()> value;
qi::uint_parser<uint16_t, 16, 4, 4> xmit_checksum;
};
int main() {
typedef boost::spirit::istream_iterator It;
It first(std::cin>>std::noskipws), last;
JedecGrammar<It> g;
ast::JEDEC jedec;
bool ok = phrase_parse(first, last, g, ascii::space, jedec);
if (ok)
{
std::cout << "Parse success\n";
std::cout << jedec;
}
else
std::cout << "Parse failed\n";
if (first != last)
std::cout << "Remaining input unparsed: '" << std::string(first, last) << "'\n";
}
Output:
Start: JEDEC file generated by John Doe
D: M SIGNETICS(PHILIPS)
D: D GAL16R8
Q: P20
Q: V0
G: 0
F: 0
L: 00000 1110101111100110111101101110111100111111
C: DEAD
End: BEEF
Take-away: See your dentist twice a year.
From a previous post I found a way to parse with boost::spirit a struct of this type:
"parameter" : {
"name" : "MyName" ,
"type" : "MyType" ,
"unit" : "MyUnit" ,
"cardinality" : "MyCardinality",
"value" : "MyValue"
}
It's a simple JSON with key-value pairs. Now I want to parse this struct regardless to variable orders. I.e. I want to parse into the same object also this struct:
"parameter" : {
"type" : "MyType" ,
"value" : "MyValue" ,
"unit" : "MyUnit" ,
"cardinality" : "MyCardinality",
"name" : "MyName"
}
I know that I can use the ^ operator in order to parse data in any order but I dont't know how to handles commas at ends of lines but last. How can I parse both structures?
This is the #sehe code from previous post. Grammar is defined here.
#define BOOST_SPIRIT_DEBUG
#include <boost/fusion/include/io.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
// This is pasted and copied from another header file
namespace StateMachine {
namespace Private {
struct LuaParameterData {
std::wstring name;
std::wstring type;
std::wstring unit;
std::wstring cardinality;
std::wstring value;
};
} // namespace Private
} // namespace StateMachine
BOOST_FUSION_ADAPT_STRUCT(
StateMachine::Private::LuaParameterData,
(std::wstring, name)
(std::wstring, type)
(std::wstring, unit)
(std::wstring, cardinality)
(std::wstring, value)
)
namespace qi = boost::spirit::qi;
// From here original file continues
namespace StateMachine {
namespace Private {
template<typename Iterator>
struct LuaParameterDataParser : qi::grammar<Iterator, LuaParameterData(), qi::ascii::space_type>
{
LuaParameterDataParser() : LuaParameterDataParser::base_type(start)
{
quotedString = qi::lexeme['"' >> +(qi::ascii::char_ - '"') >> '"'];
start =
qi::lit("\"parameter\"")
>> ':'
>> '{'
>> qi::lit("\"name\"" ) >> ':' >> quotedString >> ','
>> qi::lit("\"type\"" ) >> ':' >> quotedString >> ','
>> qi::lit("\"unit\"" ) >> ':' >> quotedString >> ','
>> qi::lit("\"cardinality\"") >> ':' >> quotedString >> ','
>> qi::lit("\"value\"" ) >> ':' >> quotedString
>> '}'
;
BOOST_SPIRIT_DEBUG_NODES((start)(quotedString));
}
qi::rule<Iterator, std::string(), qi::ascii::space_type> quotedString;
qi::rule<Iterator, LuaParameterData(), qi::ascii::space_type> start;
};
} // namespace Private
} // namespace StateMachine
int main() {
using It = std::string::const_iterator;
std::string const input = R"(
"parameter" : {
"name" : "name" ,
"type" : "type" ,
"unit" : "unit" ,
"cardinality" : "cardinality",
"value" : "value"
}
)";
It f = input.begin(),
l = input.end();
StateMachine::Private::LuaParameterDataParser<It> p;
StateMachine::Private::LuaParameterData data;
bool ok = qi::phrase_parse(f, l, p, qi::ascii::space, data);
if (ok) {
std::wcout << L"Parsed: \n";
std::wcout << L"\tname: " << data.name << L'\n';
std::wcout << L"\ttype: " << data.type << L'\n';
std::wcout << L"\tunit: " << data.unit << L'\n';
std::wcout << L"\tcardinality: " << data.cardinality << L'\n';
std::wcout << L"\tvalue: " << data.value << L'\n';
} else {
std::wcout << L"Parse failure\n";
}
if (f!=l)
std::wcout << L"Remaining unparsed: '" << std::wstring(f,l) << L"'\n";
}
I'm going to refer to a set of recent answers where I've been over things quite extensively:
Parsing heterogeneous data using Boost::Spirit
ad-hoc JSON-like parsing Reading JSON file with C++ and BOOST
application of a more general JSON grammar: Reading JSON file with C++ and BOOST
Tangentially related:
Boost Spirit : something like permutation, but not exactly
http://boost-spirit.com/home/2011/04/16/the-keyword-parser/: the keyword parser
I want to a list of name-value pairs. Each list is terminated by a '.' and EOL. Each name-value pair is separated by a ':'. Each pair is separated by a ';' in the list. E.g.
NAME1: VALUE1; NAME2: VALUE2; NAME3: VALUE3.<EOL>
The problem I have is that the values contain '.' and the last value always consumes the '.' at the EOL. Can I use some sort of lookahead to ensure the last '.' before the EOL is treated differently?
I have created a sample, that presumably looks like what you have. The tweak is in the following line:
value = lexeme [ *(char_ - ';' - ("." >> (eol|eoi))) ];
Note how - ("." >> (eol|eoi))) means: exclude any . that is immediately followed by end-of-line or end-of-input.
Test case (also live on http://liveworkspace.org/code/949b1d711772828606ddc507acf4fb4b):
const std::string input =
"name1: value 1; other name : value #2.\n"
"name.sub1: value.with.periods; other.sub2: \"more fun!\"....\n";
bool ok = doParse(input, qi::blank);
Output:
parse success
data: name1 : value 1 ; other name : value #2 .
data: name.sub1 : value.with.periods ; other.sub2 : "more fun!"... .
Full code:
#include <boost/fusion/adapted.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/karma.hpp>
#include <map>
#include <vector>
namespace qi = boost::spirit::qi;
namespace karma = boost::spirit::karma;
namespace phx = boost::phoenix;
typedef std::map<std::string, std::string> map_t;
typedef std::vector<map_t> maps_t;
template <typename It, typename Skipper = qi::space_type>
struct parser : qi::grammar<It, maps_t(), Skipper>
{
parser() : parser::base_type(start)
{
using namespace qi;
name = lexeme [ +~char_(':') ];
value = lexeme [ *(char_ - ';' - ('.' >> (eol|eoi))) ];
line = ((name >> ':' >> value) % ';') >> '.';
start = line % eol;
}
private:
qi::rule<It, std::string(), Skipper> name, value;
qi::rule<It, map_t(), Skipper> line;
qi::rule<It, maps_t(), Skipper> start;
};
template <typename C, typename Skipper>
bool doParse(const C& input, const Skipper& skipper)
{
auto f(std::begin(input)), l(std::end(input));
parser<decltype(f), Skipper> p;
maps_t data;
try
{
bool ok = qi::phrase_parse(f,l,p,skipper,data);
if (ok)
{
std::cout << "parse success\n";
for (auto& line : data)
std::cout << "data: " << karma::format_delimited((karma::string << ':' << karma::string) % ';' << '.', ' ', line) << '\n';
}
else std::cerr << "parse failed: '" << std::string(f,l) << "'\n";
//if (f!=l) std::cerr << "trailing unparsed: '" << std::string(f,l) << "'\n";
return ok;
} catch(const qi::expectation_failure<decltype(f)>& e)
{
std::string frag(e.first, e.last);
std::cerr << e.what() << "'" << frag << "'\n";
}
return false;
}
int main()
{
const std::string input =
"name1: value 1; other name : value #2.\n"
"name.sub1: value.with.periods; other.sub2: \"more fun!\"....\n";
bool ok = doParse(input, qi::blank);
return ok? 0 : 255;
}