I'm a beginner in Boost::spirit and I want to define grammar that parses TTCN language.
(http://www.trex.informatik.uni-goettingen.de/trac/wiki/ttcn-3_4.5.1)
I'm trying to define some rules for 'primitve' parsers like Alpha, AlphaNum to be faitful 1 to 1 to original grammar but obviously I do something wrong because grammar defined this way does not work.
But when I use primite parsers in place of TTCN's it started to work.
Can someone tell why 'manually' defined rules does not work as expected ?
How to fix it, because I would like to stick close to original grammar.
Is it a begginer's code bug or something different ?
#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/classic_symbols.hpp>
#include <boost/spirit/include/classic_tree_to_xml.hpp>
#include <boost/spirit/include/classic_position_iterator.hpp>
#include <boost/spirit/include/classic_core.hpp>
#include <boost/spirit/include/classic_parse_tree.hpp>
#include <boost/spirit/include/classic_ast.hpp>
#include <iostream>
#include <string>
#include <boost/spirit/home/classic/debug.hpp>
using namespace boost::spirit::classic;
using namespace std;
using namespace BOOST_SPIRIT_CLASSIC_NS;
typedef node_iter_data_factory<int> factory_t;
typedef position_iterator<std::string::iterator> pos_iterator_t;
typedef tree_match<pos_iterator_t, factory_t> parse_tree_match_t;
typedef parse_tree_match_t::const_tree_iterator iter_t;
struct ParseGrammar: public grammar<ParseGrammar>
{
template<typename ScannerT>
struct definition
{
definition(ParseGrammar const &)
{
KeywordImport = str_p("import");
KeywordAll = str_p("all");
SemiColon = ch_p(';');
Underscore = ch_p('_');
NonZeroNum = range_p('1','9');
Num = ch_p('0') | NonZeroNum;
UpperAlpha = range_p('A', 'Z');
LowerAlpha = range_p('a', 'z');
Alpha = UpperAlpha | LowerAlpha;
AlphaNum = Alpha | Num;
//this does not!
Identifier = lexeme_d[Alpha >> *(AlphaNum | Underscore)];
// Uncomment below line to make rule work
// Identifier = lexeme_d[alpha_p >> *(alnum_p | Underscore)];
Module = KeywordImport >> Identifier >> KeywordAll >> SemiColon;
BOOST_SPIRIT_DEBUG_NODE(Module);
BOOST_SPIRIT_DEBUG_NODE(KeywordImport);
BOOST_SPIRIT_DEBUG_NODE(KeywordAll);
BOOST_SPIRIT_DEBUG_NODE(Identifier);
BOOST_SPIRIT_DEBUG_NODE(SemiColon);
}
rule<ScannerT> KeywordImport,KeywordAll,Module,Identifier,SemiColon;
rule<ScannerT> Alpha,UpperAlpha,LowerAlpha,Underscore,Num,AlphaNum;
rule<ScannerT> NonZeroNum;
rule<ScannerT> const&
start() const { return Module; }
};
};
int main()
{
ParseGrammar resolver; // Our parser
BOOST_SPIRIT_DEBUG_NODE(resolver);
string content = "import foobar all;";
pos_iterator_t pos_begin(content.begin(), content.end());
pos_iterator_t pos_end;
tree_parse_info<pos_iterator_t, factory_t> info;
info = ast_parse<factory_t>(pos_begin, pos_end, resolver, space_p);
std::cout << "\ninfo.length : " << info.length << std::endl;
std::cout << "info.full : " << info.full << std::endl;
if(info.full)
{
std::cout << "OK: Parsing succeeded\n\n";
}
else
{
int line = info.stop.get_position().line;
int column = info.stop.get_position().column;
std::cout << "-------------------------\n";
std::cout << "ERROR: Parsing failed\n";
std::cout << "stopped at: " << line << ":" << column << "\n";
std::cout << "-------------------------\n";
}
return 0;
}
I don't do Spirit Classic (which has been deprecated for some years now).
I can only assume you've mixed something up with skippers. Here's the thing translated into Spirit V2:
#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/support_line_pos_iterator.hpp>
namespace qi = boost::spirit::qi;
typedef boost::spirit::line_pos_iterator<std::string::const_iterator> pos_iterator_t;
template <typename Iterator = pos_iterator_t, typename Skipper = qi::space_type>
struct ParseGrammar: public qi::grammar<Iterator, Skipper>
{
ParseGrammar() : ParseGrammar::base_type(Module)
{
using namespace qi;
KeywordImport = lit("import");
KeywordAll = lit("all");
SemiColon = lit(';');
#if 1
// this rule obviously works
Identifier = lexeme [alpha >> *(alnum | '_')];
#else
// this does too, but less efficiently
Underscore = lit('_');
NonZeroNum = char_('1','9');
Num = char_('0') | NonZeroNum;
UpperAlpha = char_('A', 'Z');
LowerAlpha = char_('a', 'z');
Alpha = UpperAlpha | LowerAlpha;
AlphaNum = Alpha | Num;
Identifier = lexeme [Alpha >> *(AlphaNum | Underscore)];
#endif
Module = KeywordImport >> Identifier >> KeywordAll >> SemiColon;
BOOST_SPIRIT_DEBUG_NODES((Module)(KeywordImport)(KeywordAll)(Identifier)(SemiColon))
}
qi::rule<Iterator, Skipper> Module;
qi::rule<Iterator> KeywordImport,KeywordAll,Identifier,SemiColon;
qi::rule<Iterator> Alpha,UpperAlpha,LowerAlpha,Underscore,Num,AlphaNum;
qi::rule<Iterator> NonZeroNum;
};
int main()
{
std::string const content = "import \r\n\r\nfoobar\r\n\r\n all; bogus";
pos_iterator_t first(content.begin()), iter=first, last(content.end());
ParseGrammar<pos_iterator_t> resolver; // Our parser
bool ok = phrase_parse(iter, last, resolver, qi::space);
std::cout << std::boolalpha;
std::cout << "\nok : " << ok << std::endl;
std::cout << "full : " << (iter == last) << std::endl;
if(ok && iter==last)
{
std::cout << "OK: Parsing fully succeeded\n\n";
}
else
{
int line = get_line(iter);
int column = get_column(first, iter);
std::cout << "-------------------------\n";
std::cout << "ERROR: Parsing failed or not complete\n";
std::cout << "stopped at: " << line << ":" << column << "\n";
std::cout << "remaining: '" << std::string(iter, last) << "'\n";
std::cout << "-------------------------\n";
}
return 0;
}
I've added a little "bogus" at the end of input, so the output becomes a nicer demonstration:
<Module>
<try>import \r\n\r\nfoobar\r\n\r</try>
<KeywordImport>
<try>import \r\n\r\nfoobar\r\n\r</try>
<success> \r\n\r\nfoobar\r\n\r\n all;</success>
<attributes>[]</attributes>
</KeywordImport>
<Identifier>
<try>foobar\r\n\r\n all; bogu</try>
<success>\r\n\r\n all; bogus</success>
<attributes>[]</attributes>
</Identifier>
<KeywordAll>
<try>all; bogus</try>
<success>; bogus</success>
<attributes>[]</attributes>
</KeywordAll>
<SemiColon>
<try>; bogus</try>
<success> bogus</success>
<attributes>[]</attributes>
</SemiColon>
<success> bogus</success>
<attributes>[]</attributes>
</Module>
ok : true
full : false
-------------------------
ERROR: Parsing failed or not complete
stopped at: 3:8
remaining: 'bogus'
-------------------------
That all said, this is what I'd probably reduce it to:
template <typename Iterator, typename Skipper = qi::space_type>
struct ParseGrammar: public qi::grammar<Iterator, Skipper>
{
ParseGrammar() : ParseGrammar::base_type(Module)
{
using namespace qi;
Identifier = alpha >> *(alnum | '_');
Module = "import" >> Identifier >> "all" >> ';';
BOOST_SPIRIT_DEBUG_NODES((Module)(Identifier))
}
qi::rule<Iterator, Skipper> Module;
qi::rule<Iterator> Identifier;
};
As you can see, the Identifier rule is implicitely a lexeme because it doesn't declared to use a skipper.
See it Live on Coliru
Related
I'm trying to implement a very specific grammar, which requires me at a certain point to parse a list of comma separated integers. The qi rule looks like the following:
qi::rule<Iterator, ascii::space_type> ident;
qi::rule<Iterator, ascii::space_type> nlist;
...
ident = char_ >> nlist;
nlist = ("(" >> int_ % "," >> ")");
...
I need to pass the values up to the ident rule (The expression ident has to create a syntax tree node, where the parsed values from nlist are required for the constructor). I thought about creating and filling a std::vector and use the semantic action like _val = vector<int>.... What is now unclear to me is how do I create a vector of arbitrary length from this rule, since I do not make any assumptions on how long the input will be or using a predefined vector like the examples.
Is this even possible or does is there a better way to do it?
This is the bread and butter of Spirit Qi.
Just use any compatible attribute type and profit:
using nlist_t = std::vector<int>;
using ident_t = std::pair<char, nlist_t>;
qi::rule<Iterator, ident_t(), qi::ascii::space_type> ident;
qi::rule<Iterator, nlist_t(), qi::ascii::space_type> nlist;
Note: For std::pair attribute compatibility, include the relevant fusion header:
Live On Coliru
#include <boost/fusion/adapted/std_pair.hpp>
#include <boost/spirit/include/qi.hpp>
namespace qi = boost::spirit::qi;
int main()
{
using nlist_t = std::vector<int>;
using ident_t = std::pair<char, nlist_t>;
using Iterator = std::string::const_iterator;
qi::rule<Iterator, ident_t(), qi::ascii::space_type> ident;
qi::rule<Iterator, nlist_t(), qi::ascii::space_type> nlist;
ident = qi::char_ >> nlist;
nlist = '(' >> qi::int_ % ',' >> ')';
for (std::string const input : { "a (1,2,3)", "+(881,-2,42) \n", "?(0)" }) {
ident_t data;
if (qi::phrase_parse(input.begin(), input.end(), ident, qi::ascii::space, data)) {
std::cout << "Parsed: " << data.first << "(";
for (auto i : data.second) std::cout << i << ",";
std::cout << ")\n";
} else
std::cout << "Parse failed: '" << input << "'\n";
}
}
Prints
Parsed: a(1,2,3,)
Parsed: +(881,-2,42,)
Parsed: ?(0,)
BONUS
Version with imagined Ast type using phoenix::construct:
Also Live On Coliru
#include <boost/fusion/adapted/std_pair.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/phoenix.hpp>
namespace qi = boost::spirit::qi;
namespace px = boost::phoenix;
namespace OoShinyAst {
using MyName = char;
using MyArgument = int;
using MyArgumentList = std::vector<MyArgument>;
struct MyIdent {
MyName name;
MyArgumentList args;
MyIdent() = default;
MyIdent(MyName name, MyArgumentList args)
: name(std::move(name)), args(std::move(args)) { }
};
}
int main()
{
using Iterator = std::string::const_iterator;
qi::rule<Iterator, OoShinyAst::MyIdent(), qi::ascii::space_type> ident;
qi::rule<Iterator, OoShinyAst::MyArgumentList(), qi::ascii::space_type> nlist;
nlist = '(' >> qi::int_ % ',' >> ')';
ident = (qi::char_ >> nlist) [ qi::_val = px::construct<OoShinyAst::MyIdent>(qi::_1, qi::_2) ];
for (std::string const input : { "a (1,2,3)", "+(881,-2,42) \n", "?(0)" }) {
OoShinyAst::MyIdent data;
if (qi::phrase_parse(input.begin(), input.end(), ident, qi::ascii::space, data)) {
std::cout << "Parsed: " << data.name << "(";
for (auto i : data.args) std::cout << i << ",";
std::cout << ")\n";
} else
std::cout << "Parse failed: '" << input << "'\n";
}
}
I am currently implementing a parser which succeeds on the "strongest" match for spirit::qi. There are meaningful applications for such a thing. E.g matching references to either simple refs (eg "willy") or namespace qualified refs (eg. "willy::anton"). That's not my actual real world case but it is almost self-explanatory, I guess. At least it helped me to track down the issue.
I found a solution for that. It works perfectly, when the skipper parser is not involved (i.e. there is nothing to skip). It does not work as expected if there are areas which need skipping.
I believe, I tracked down the problem. It seems like under certain conditions spaces are actually not skipped allthough they should be.
Below is find a self-contained very working example. It loops over some rules and some input to provide enough information. If you run it with BOOST_SPIRIT_DEBUG enabled, you get in particular the output:
<qualifier>
<try> :: anton</try>
<fail/>
</qualifier>
I think, this one should not have failed. Am I right guessing so? Does anyone know a way to get around that? Or is it just my poor understanding of qi semantics? Thank you very much for your time. :)
My environment: MSVC 2015 latest, target win32 console
#define BOOST_SPIRIT_DEBUG
#include <io.h>
#include<map>
#include <boost/spirit/include/qi.hpp>
typedef std::string::const_iterator iterator_type;
namespace qi = boost::spirit::qi;
using map_type = std::map<std::string, qi::rule<iterator_type, std::string()>&>;
namespace maxence { namespace parser {
template <typename Iterator>
struct ident : qi::grammar<Iterator, std::string()>
{
ident();
qi::rule<Iterator, std::string()>
id, id_raw;
qi::rule<Iterator, std::string()>
not_used,
qualifier,
qualified_id, simple_id,
id_reference, id_reference_final;
map_type rules = {
{ "E1", id },
{ "E2", id_raw}
};
};
template <typename Iterator>
// we actually don't need the start rule (see below)
ident<Iterator>::ident() : ident::base_type(not_used)
{
id_reference = (!simple_id >> qualified_id) | (!qualified_id >> simple_id);
id_reference_final = id_reference;
///////////////////////////////////////////////////
// standard simple id (not followed by
// delimiter "::")
simple_id = (qi::alpha | '_') >> *(qi::alnum | '_') >> !qi::lit("::");
///////////////////////////////////////////////////
// this is qualifier <- "::" simple_id
// I repeat the simple_id pattern here to make sure
// this demo has no "early match" issues
qualifier = qi::string("::") > (qi::alpha | '_') >> *(qi::alnum | '_');
///////////////////////////////////////////////////
// this is: qualified_id <- simple_id qualifier*
qualified_id = (qi::alpha | '_') >> *(qi::alnum | '_') >> +(qualifier) >> !qi::lit("::");
id = id_reference_final;
id_raw = qi::raw[id_reference_final];
BOOST_SPIRIT_DEBUG_NODES(
(id)
(id_raw)
(qualifier)
(qualified_id)
(simple_id)
(id_reference)
(id_reference_final)
)
}
}}
int main()
{
maxence::parser::ident<iterator_type> ident;
using ss_map_type = std::map<std::string, std::string>;
ss_map_type parser_input =
{
{ "Simple id (behaves ok)", "willy" },
{ "Qualified id (behaves ok)", "willy::anton" },
{ "Skipper involved (unexpected)", "willy :: anton" }
};
for (ss_map_type::const_iterator input = parser_input.begin(); input != parser_input.end(); input++) {
for (map_type::const_iterator example = ident.rules.begin(); example != ident.rules.end(); example++) {
std::string to_parse = input->second;
std::string result;
std::string parser_name = (example->second).name();
std::cout << "--------------------------------------------" << std::endl;
std::cout << "Description: " << input->first << std::endl;
std::cout << "Parser [" << parser_name << "] parsing [" << to_parse << "]" << std::endl;
auto b(to_parse.begin()), e(to_parse.end());
// --- test for parser success
bool success = qi::phrase_parse(b, e, (example)->second, qi::space, result);
if (success) std::cout << "Parser succeeded. Result: " << result << std::endl;
else std::cout << " Parser failed. " << std::endl;
//--- test for EOI
if (b == e) {
std::cout << "EOI reached.";
if (success) std::cout << " The sun is shining brightly. :)";
} else {
std::cout << "Failure: EOI not reached. Remaining: [";
while (b != e) std::cout << *b++; std::cout << "]";
}
std::cout << std::endl << "--------------------------------------------" << std::endl;
}
}
return 0;
}
Here is an example of the syntax -- two groups of items:
I_name m_name parameter1=value parameter2=value
I_name m_name parameter1=value \
parameter2=value
My question is how to define the skip-type.
It is not just space_type but space_type minus newline.
But newline followed by backslash is a skip-type.
E.g.
I define name like that:
qi::rule<Iterator, std::string(), ascii::space_type> m_sName;
m_sName %= qi::lexeme[ascii::alpha >> *ascii::alnum];
This is obviously not correct, as the space_type must include newline-backslash.
The following grammar works for me.
*("\\\n" | ~qi::char_('\n')) % '\n'
It will ignore any newline after the backslash. And the following is a simple test.
#include <vector>
#include <string>
#include <boost/config/warning_disable.hpp>
#include <boost/spirit/include/qi.hpp>
#define BOOST_TEST_MODULE example
#include <boost/test/unit_test.hpp>
typedef std::vector<std::string> Lines;
inline auto ParseLines(std::string const& str) {
Lines lines;
namespace qi = boost::spirit::qi;
if (qi::parse(
str.begin(), str.end(),
*("\\\n" | ~qi::char_('\n')) % '\n',
lines)) {
return lines;
}
else {
throw std::invalid_argument("Parse error at ParseLines");
}
}
BOOST_AUTO_TEST_CASE(TestParseLines) {
std::string const str =
"I_name m_name parameter1=value parameter2=value\n"
"I_name m_name parameter1 = value \\\n"
"parameter2 = value";
Lines const expected{
"I_name m_name parameter1=value parameter2=value",
"I_name m_name parameter1 = value parameter2 = value"
};
BOOST_TEST(ParseLines(str) == expected);
}
You should use "-std=c++14 -lboost_unit_test_framework" for compilation. Anyway, it is easy to convert the code for c++03.
qi::blank is exactly that. It's qi::space without newlines.
You can do this too: ("\\\n" | qi::blank)
To be able to declare a rule with such a skipper, define a skipper grammar:
template <typename It>
struct my_skipper : qi::grammar<It> {
my_skipper() : my_skipper::base_type(start) {}
qi::rule<It> start = ("\\\n" | qi::blank);
};
Full Demo
Live On Coliru
#include <boost/spirit/include/qi.hpp>
#include <boost/fusion/include/adapted.hpp>
#include <map>
namespace qi = boost::spirit::qi;
namespace ast {
struct record {
std::string iname, mname;
std::map<std::string, std::string> params;
};
using records = std::vector<record>;
}
BOOST_FUSION_ADAPT_STRUCT(ast::record, iname, mname, params)
template <typename It>
struct my_parser : qi::grammar<It, ast::records()> {
using Skipper = qi::rule<It>;
my_parser() : my_parser::base_type(start) {
skipper = ("\\\n" | qi::blank);
name = +qi::graph;
key = +(qi::graph - '=');
param = key >> '=' >> name;
record = name >> name >> *param;
records = *(record >> +qi::eol);
start = qi::skip(qi::copy(skipper)) [ records ];
}
private:
Skipper skipper;
qi::rule<It, ast::records(), Skipper> records;
qi::rule<It, ast::record(), Skipper> record;
qi::rule<It, ast::records()> start;
qi::rule<It, std::pair<std::string, std::string>()> param;
qi::rule<It, std::string()> name, key;
};
int main() {
#if 1
using It = boost::spirit::istream_iterator;
It f(std::cin >> std::noskipws), l;
#else
using It = std::string::const_iterator;
std::string const input = "something here a=1\n";
It f = input.begin(), l = input.end();
#endif
ast::records data;
bool ok = qi::parse(f, l, my_parser<It>(), data);
if (ok) {
std::cout << "Parsed:\n";
for (auto& r : data) {
std::cout << "\t" << r.iname << " " << r.mname;
for (auto& p : r.params)
std::cout << " [" << p.first << ": " << p.second << "]";
std::cout << "\n";
}
} else {
std::cout << "Parse failed\n";
}
if (f!=l)
std::cout << "Remaining input: '" << std::string(f,l) << "'\n";
}
Prints (for the input in your question):
Parsed:
I_name m_name [parameter1: value] [parameter2: value]
I_name m_name [parameter1: value] [parameter2: value]
Writing Qi grammar with Phoenix bind I got a compilation error like
boost/spirit/home/support/context.hpp(180): error C2338: index_is_out_of_bounds
here
>> ruleHandId_[phx::bind(&parseContext::handId_, qi::_r1) = qi::_1];
I just havent too much expirience with phoenix binding but perv bind in the line
ruleStart_ = ruleEncoding_[phx::bind(&parseContext::encoding_, qi::_r1) = qi::_1]
works good without compilation errors
It's all under MSVC from VS2013 with boost 1.56 x86
Whats I do wrong under code with the compilation error?
Source Code
#include <boost/spirit/include/qi.hpp>
#include <boost/phoenix/phoenix.hpp>
#include <boost/shared_ptr.hpp>
#include <sstream>
namespace sp = boost::spirit;
namespace qi = boost::spirit::qi;
namespace phx = boost::phoenix;
struct parseContext {
std::string encoding_;
uint64_t handId_;
};
typedef boost::shared_ptr<parseContext> parseContextShPtr;
template <typename Iterator>
struct parseGrammar : qi::grammar<Iterator, void(parseContext&)> {
parseGrammar() : parseGrammar::base_type(ruleStart_)
{
ruleStart_ = ruleEncoding_[phx::bind(&parseContext::encoding_, qi::_r1) = qi::_1]
>> ruleHandHeader_;
ruleEncoding_ = qi::lit("ABC");
ruleHandHeader_ = qi::lit("DEF") >> qi::space
>> qi::lit("XYZ #")
>> ruleHandId_[phx::bind(&parseContext::handId_, qi::_r1) = qi::_1];
ruleHandId_ = qi::long_long;
}
// Rules
qi::rule<Iterator, void(parseContext&)> ruleStart_;
qi::rule<Iterator, std::string()> ruleEncoding_;
qi::rule<Iterator> ruleHandHeader_;
qi::rule<Iterator, uint64_t> ruleHandId_;
};
void test()
{
std::string s("ABCDEF XYZ #555: PQI #777");
std::stringstream sb;
sb.unsetf(std::ios::skipws);
sb << s;
const parseGrammar<sp::istream_iterator> p;
sp::istream_iterator b(sb);
sp::istream_iterator e;
parseContextShPtr ctx(new parseContext);
bool r = qi::parse(b, e, p(phx::ref(*ctx.get())));
if (r) {
std::cout << "Success" << std::endl;
}
else {
std::cout << "Failure" << std::endl;
}
std::cout << std::string(b, e).substr(0, 32) << std::endl;
}
Some of the placeholders cannot be bound.
This could be because ruleEncoding_ doesn't expose an attribute (for _1) (unlikely) or ruleStart_ doesn't have the inherited attribute (_r1).
That's all I can tell you right now.
Edit It was the latter. ruleHandHeader doesn't declare any attributes, let alone an inherited attribute to bind to _r1
Update To the comment.
Here are some suggestions. Much in the vein of my oft-repeated advice to avoid semantic actions (Boost Spirit: "Semantic actions are evil"?), I'd adapt the structure as a fusion sequence:
And use much simplified grammar rules:
ruleStart_ = ruleEncoding_ >> ruleHandHeader_;
ruleEncoding_ = "ABC";
ruleHandId_ = qi::long_long;
ruleHandHeader_ = "DEF XYZ #" >> ruleHandId_;
Now, adding in BOOST_SPIRIT_DEBUG macros and fixing uint64_t to uint64_t() in the rule definition:
Live On Coliru
#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
#include <boost/fusion/adapted/struct.hpp>
#include <boost/shared_ptr.hpp>
#include <sstream>
namespace qi = boost::spirit::qi;
struct parseContext {
std::string encoding_;
uint64_t handId_;
};
BOOST_FUSION_ADAPT_STRUCT(parseContext, (std::string, encoding_)(uint64_t,handId_))
typedef boost::shared_ptr<parseContext> parseContextShPtr;
template <typename Iterator>
struct parseGrammar : qi::grammar<Iterator, parseContext()> {
parseGrammar() : parseGrammar::base_type(ruleStart_)
{
ruleStart_ = ruleEncoding_ >> ruleHandHeader_;
ruleEncoding_ = "ABC";
ruleHandId_ = qi::long_long;
ruleHandHeader_ = "DEF XYZ #" >> ruleHandId_;
BOOST_SPIRIT_DEBUG_NODES((ruleStart_)(ruleEncoding_)(ruleHandId_)(ruleHandHeader_))
}
// Rules
qi::rule<Iterator, parseContext()> ruleStart_;
qi::rule<Iterator, std::string()> ruleEncoding_;
qi::rule<Iterator, uint64_t()> ruleHandId_, ruleHandHeader_;
};
void test()
{
std::stringstream sb("ABCDEF XYZ #555: PQI #777");
sb.unsetf(std::ios::skipws);
typedef boost::spirit::istream_iterator It;
const parseGrammar<It> p;
It b(sb), e;
parseContextShPtr ctx(new parseContext);
bool r = qi::parse(b, e, p, *ctx);
if (r) {
std::cout << "Success: " << ctx->encoding_ << ", " << ctx->handId_ << std::endl;
}
else {
std::cout << "Failure" << std::endl;
}
if (b!=e)
std::cout << "Remaining: '" << std::string(b, e).substr(0, 32) << "'...\n";
}
int main()
{
test();
}
Prints
Success: ABC, 555
Remaining: ': PQI #777'...
Lets say I have code like this (line numbers for reference):
1:
2:function FuncName_1 {
3: var Var_1 = 3;
4: var Var_2 = 4;
5: ...
I want to write a grammar that parses such text, puts all indentifiers (function and variable names) infos into a tree (utree?).
Each node should preserve: line_num, column_num and symbol value. example:
root: FuncName_1 (line:2,col:10)
children[0]: Var_1 (line:3, col:8)
children[1]: Var_1 (line:4, col:9)
I want to put it into the tree because I plan to traverse through that tree and for each node I must know the 'context': (all parent nodes of current nodes).
E.g, while processing node with Var_1, I must know that this is a name for local variable for function FuncName_1 (that is currently being processed as node, but one level earlier)
I cannot figure out few things
Can this be done in Spirit with semantic actions and utree's ? Or should I use variant<> trees ?
How to pass to the node those three informations (column,line,symbol_name) at the same time ? I know I must use pos_iterator as iterator type for grammar but how to access those information in sematic action ?
I'm a newbie in Boost so I read the Spirit documentaiton over and over, I try to google my problems but I somehow cannot put all the pieces together ot find the solution. Seems like there was no one me with such use case like mine before (or I'm just not able to find it)
Looks like the only solutions with position iterator are the ones with parsing error handling, but this is not the case I'm interested in.
The code that only parses the code I was taking about is below but I dont know how to move forward with it.
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/support_line_pos_iterator.hpp>
namespace qi = boost::spirit::qi;
typedef boost::spirit::line_pos_iterator<std::string::const_iterator> pos_iterator_t;
template<typename Iterator=pos_iterator_t, typename Skipper=qi::space_type>
struct ParseGrammar: public qi::grammar<Iterator, Skipper>
{
ParseGrammar():ParseGrammar::base_type(SourceCode)
{
using namespace qi;
KeywordFunction = lit("function");
KeywordVar = lit("var");
SemiColon = lit(';');
Identifier = lexeme [alpha >> *(alnum | '_')];
VarAssignemnt = KeywordVar >> Identifier >> char_('=') >> int_ >> SemiColon;
SourceCode = KeywordFunction >> Identifier >> '{' >> *VarAssignemnt >> '}';
}
qi::rule<Iterator, Skipper> SourceCode;
qi::rule<Iterator > KeywordFunction;
qi::rule<Iterator, Skipper> VarAssignemnt;
qi::rule<Iterator> KeywordVar;
qi::rule<Iterator> SemiColon;
qi::rule<Iterator > Identifier;
};
int main()
{
std::string const content = "function FuncName_1 {\n var Var_1 = 3;\n var Var_2 = 4; }";
pos_iterator_t first(content.begin()), iter = first, last(content.end());
ParseGrammar<pos_iterator_t> resolver; // Our parser
bool ok = phrase_parse(iter,
last,
resolver,
qi::space);
std::cout << std::boolalpha;
std::cout << "\nok : " << ok << std::endl;
std::cout << "full : " << (iter == last) << std::endl;
if(ok && iter == last)
{
std::cout << "OK: Parsing fully succeeded\n\n";
}
else
{
int line = get_line(iter);
int column = get_column(first, iter);
std::cout << "-------------------------\n";
std::cout << "ERROR: Parsing failed or not complete\n";
std::cout << "stopped at: " << line << ":" << column << "\n";
std::cout << "remaining: '" << std::string(iter, last) << "'\n";
std::cout << "-------------------------\n";
}
return 0;
}
This has been a fun exercise, where I finally put together a working demo of on_success[1] to annotate AST nodes.
Let's assume we want an AST like:
namespace ast
{
struct LocationInfo {
unsigned line, column, length;
};
struct Identifier : LocationInfo {
std::string name;
};
struct VarAssignment : LocationInfo {
Identifier id;
int value;
};
struct SourceCode : LocationInfo {
Identifier function;
std::vector<VarAssignment> assignments;
};
}
I know, 'location information' is probably overkill for the SourceCode node, but you know... Anyways, to make it easy to assign attributes to these nodes without requiring semantic actions or lots of specifically crafted constructors:
#include <boost/fusion/adapted/struct.hpp>
BOOST_FUSION_ADAPT_STRUCT(ast::Identifier, (std::string, name))
BOOST_FUSION_ADAPT_STRUCT(ast::VarAssignment, (ast::Identifier, id)(int, value))
BOOST_FUSION_ADAPT_STRUCT(ast::SourceCode, (ast::Identifier, function)(std::vector<ast::VarAssignment>, assignments))
There. Now we can declare the rules to expose these attributes:
qi::rule<Iterator, ast::SourceCode(), Skipper> SourceCode;
qi::rule<Iterator, ast::VarAssignment(), Skipper> VarAssignment;
qi::rule<Iterator, ast::Identifier()> Identifier;
// no skipper, no attributes:
qi::rule<Iterator> KeywordFunction, KeywordVar, SemiColon;
We don't (essentially) modify the grammar, at all: attribute propagation is "just automatic"[2] :
KeywordFunction = lit("function");
KeywordVar = lit("var");
SemiColon = lit(';');
Identifier = as_string [ alpha >> *(alnum | char_("_")) ];
VarAssignment = KeywordVar >> Identifier >> '=' >> int_ >> SemiColon;
SourceCode = KeywordFunction >> Identifier >> '{' >> *VarAssignment >> '}';
The magic
How do we get the source location information attached to our nodes?
auto set_location_info = annotate(_val, _1, _3);
on_success(Identifier, set_location_info);
on_success(VarAssignment, set_location_info);
on_success(SourceCode, set_location_info);
Now, annotate is just a lazy version of a calleable that is defined as:
template<typename It>
struct annotation_f {
typedef void result_type;
annotation_f(It first) : first(first) {}
It const first;
template<typename Val, typename First, typename Last>
void operator()(Val& v, First f, Last l) const {
do_annotate(v, f, l, first);
}
private:
void static do_annotate(ast::LocationInfo& li, It f, It l, It first) {
using std::distance;
li.line = get_line(f);
li.column = get_column(first, f);
li.length = distance(f, l);
}
static void do_annotate(...) { }
};
Due to way in which get_column works, the functor is stateful (as it remembers the start iterator)[3]. As you can see do_annotate just accepts anything that derives from LocationInfo.
Now, the proof of the pudding:
std::string const content = "function FuncName_1 {\n var Var_1 = 3;\n var Var_2 = 4; }";
pos_iterator_t first(content.begin()), iter = first, last(content.end());
ParseGrammar<pos_iterator_t> resolver(first); // Our parser
ast::SourceCode program;
bool ok = phrase_parse(iter,
last,
resolver,
qi::space,
program);
std::cout << std::boolalpha;
std::cout << "ok : " << ok << std::endl;
std::cout << "full: " << (iter == last) << std::endl;
if(ok && iter == last)
{
std::cout << "OK: Parsing fully succeeded\n\n";
std::cout << "Function name: " << program.function.name << " (see L" << program.printLoc() << ")\n";
for (auto const& va : program.assignments)
std::cout << "variable " << va.id.name << " assigned value " << va.value << " at L" << va.printLoc() << "\n";
}
else
{
int line = get_line(iter);
int column = get_column(first, iter);
std::cout << "-------------------------\n";
std::cout << "ERROR: Parsing failed or not complete\n";
std::cout << "stopped at: " << line << ":" << column << "\n";
std::cout << "remaining: '" << std::string(iter, last) << "'\n";
std::cout << "-------------------------\n";
}
This prints:
ok : true
full: true
OK: Parsing fully succeeded
Function name: FuncName_1 (see L1:1:56)
variable Var_1 assigned value 3 at L2:3:14
variable Var_2 assigned value 4 at L3:3:15
Full Demo Program
See it Live On Coliru
Also showing:
error handling, e.g.:
Error: expecting "=" in line 3:
var Var_2 - 4; }
^---- here
ok : false
full: false
-------------------------
ERROR: Parsing failed or not complete
stopped at: 1:1
remaining: 'function FuncName_1 {
var Var_1 = 3;
var Var_2 - 4; }'
-------------------------
BOOST_SPIRIT_DEBUG macros
A bit of a hacky way to conveniently stream the LocationInfo part of any AST node, sorry :)
//#define BOOST_SPIRIT_DEBUG
#define BOOST_SPIRIT_USE_PHOENIX_V3
#include <boost/fusion/adapted/struct.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/spirit/include/support_line_pos_iterator.hpp>
#include <iomanip>
namespace qi = boost::spirit::qi;
namespace phx= boost::phoenix;
typedef boost::spirit::line_pos_iterator<std::string::const_iterator> pos_iterator_t;
namespace ast
{
namespace manip { struct LocationInfoPrinter; }
struct LocationInfo {
unsigned line, column, length;
manip::LocationInfoPrinter printLoc() const;
};
struct Identifier : LocationInfo {
std::string name;
};
struct VarAssignment : LocationInfo {
Identifier id;
int value;
};
struct SourceCode : LocationInfo {
Identifier function;
std::vector<VarAssignment> assignments;
};
///////////////////////////////////////////////////////////////////////////
// Completely unnecessary tweak to get a "poor man's" io manipulator going
// so we can do `std::cout << x.printLoc()` on types of `x` deriving from
// LocationInfo
namespace manip {
struct LocationInfoPrinter {
LocationInfoPrinter(LocationInfo const& ref) : ref(ref) {}
LocationInfo const& ref;
friend std::ostream& operator<<(std::ostream& os, LocationInfoPrinter const& lip) {
return os << lip.ref.line << ':' << lip.ref.column << ':' << lip.ref.length;
}
};
}
manip::LocationInfoPrinter LocationInfo::printLoc() const { return { *this }; }
// feel free to disregard this hack
///////////////////////////////////////////////////////////////////////////
}
BOOST_FUSION_ADAPT_STRUCT(ast::Identifier, (std::string, name))
BOOST_FUSION_ADAPT_STRUCT(ast::VarAssignment, (ast::Identifier, id)(int, value))
BOOST_FUSION_ADAPT_STRUCT(ast::SourceCode, (ast::Identifier, function)(std::vector<ast::VarAssignment>, assignments))
struct error_handler_f {
typedef qi::error_handler_result result_type;
template<typename T1, typename T2, typename T3, typename T4>
qi::error_handler_result operator()(T1 b, T2 e, T3 where, T4 const& what) const {
std::cerr << "Error: expecting " << what << " in line " << get_line(where) << ": \n"
<< std::string(b,e) << "\n"
<< std::setw(std::distance(b, where)) << '^' << "---- here\n";
return qi::fail;
}
};
template<typename It>
struct annotation_f {
typedef void result_type;
annotation_f(It first) : first(first) {}
It const first;
template<typename Val, typename First, typename Last>
void operator()(Val& v, First f, Last l) const {
do_annotate(v, f, l, first);
}
private:
void static do_annotate(ast::LocationInfo& li, It f, It l, It first) {
using std::distance;
li.line = get_line(f);
li.column = get_column(first, f);
li.length = distance(f, l);
}
static void do_annotate(...) {}
};
template<typename Iterator=pos_iterator_t, typename Skipper=qi::space_type>
struct ParseGrammar: public qi::grammar<Iterator, ast::SourceCode(), Skipper>
{
ParseGrammar(Iterator first) :
ParseGrammar::base_type(SourceCode),
annotate(first)
{
using namespace qi;
KeywordFunction = lit("function");
KeywordVar = lit("var");
SemiColon = lit(';');
Identifier = as_string [ alpha >> *(alnum | char_("_")) ];
VarAssignment = KeywordVar > Identifier > '=' > int_ > SemiColon; // note: expectation points
SourceCode = KeywordFunction >> Identifier >> '{' >> *VarAssignment >> '}';
on_error<fail>(VarAssignment, handler(_1, _2, _3, _4));
on_error<fail>(SourceCode, handler(_1, _2, _3, _4));
auto set_location_info = annotate(_val, _1, _3);
on_success(Identifier, set_location_info);
on_success(VarAssignment, set_location_info);
on_success(SourceCode, set_location_info);
BOOST_SPIRIT_DEBUG_NODES((KeywordFunction)(KeywordVar)(SemiColon)(Identifier)(VarAssignment)(SourceCode))
}
phx::function<error_handler_f> handler;
phx::function<annotation_f<Iterator>> annotate;
qi::rule<Iterator, ast::SourceCode(), Skipper> SourceCode;
qi::rule<Iterator, ast::VarAssignment(), Skipper> VarAssignment;
qi::rule<Iterator, ast::Identifier()> Identifier;
// no skipper, no attributes:
qi::rule<Iterator> KeywordFunction, KeywordVar, SemiColon;
};
int main()
{
std::string const content = "function FuncName_1 {\n var Var_1 = 3;\n var Var_2 - 4; }";
pos_iterator_t first(content.begin()), iter = first, last(content.end());
ParseGrammar<pos_iterator_t> resolver(first); // Our parser
ast::SourceCode program;
bool ok = phrase_parse(iter,
last,
resolver,
qi::space,
program);
std::cout << std::boolalpha;
std::cout << "ok : " << ok << std::endl;
std::cout << "full: " << (iter == last) << std::endl;
if(ok && iter == last)
{
std::cout << "OK: Parsing fully succeeded\n\n";
std::cout << "Function name: " << program.function.name << " (see L" << program.printLoc() << ")\n";
for (auto const& va : program.assignments)
std::cout << "variable " << va.id.name << " assigned value " << va.value << " at L" << va.printLoc() << "\n";
}
else
{
int line = get_line(iter);
int column = get_column(first, iter);
std::cout << "-------------------------\n";
std::cout << "ERROR: Parsing failed or not complete\n";
std::cout << "stopped at: " << line << ":" << column << "\n";
std::cout << "remaining: '" << std::string(iter, last) << "'\n";
std::cout << "-------------------------\n";
}
return 0;
}
[1] sadly un(der)documented, except for the conjure sample(s)
[2] well, I used as_string to get proper assignment to Identifier without too much work
[3] There could be smarter ways about this in terms of performance, but for now, let's keep it simple