This question leads on from its predecessor here: decoding an http header value
The Question:
In my test assertion failure, I am printing out the following contents of error_message:
Error! Expecting <alternative><media_type_no_parameters><media_type_with_parameters> in header value: "text/html garbage ; charset = \"ISO-8859-5\"" at position: 0
Which is unhelpful...
What is the correct way to get a nice syntax error that says:
Error! token_pair has invalid syntax here:
text/html garbage ; charset = "ISO-8859-5"
^ must be eoi or separator of type ;
Background:
HTTP Content-Type in a request has the following form:
type/subtype *( ; param[=param_value]) <eoi>
Where type and subtype many not be quoted or be separated by spaces, param is not quoted, and param_value is both optional and optionally quoted.
Other than between type/subtype spaces or horizontal tabs may be used as white space. There may also be space before type/subtype.
For now I am ignoring the possibility of HTTP line breaks or comments as I understand that they are deprecated.
Summary:
There shall be one type, one subtype and zero or more parameters. type and subtype are HTTP tokens, which is to say that they may not contain delimiters ("/\[]<>,; and so on) or spaces.
Thus, the following header is legal:
text/html ; charset = "ISO-8859-5"
And the following header is illegal:
text/html garbage ; charset = "ISO-8859-5"
^^^^^^^ illegal - must be either ; or <eoi>
The code I am using to parse this (seemingly simple, but actually quite devious) protocol component is below.
Code
My code, adapted from sehe's fantasic answer here
(warning, prerequisites are google test and boost)
//#define BOOST_SPIRIT_DEBUG
#include <boost/config/warning_disable.hpp>
#include <gtest/gtest.h>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/fusion/include/adapted.hpp>
#include <utility>
#include <vector>
#include <string>
#include <iostream>
using token_pair = std::pair<std::string, std::string>;
struct parameter {
std::string name;
std::string value;
bool has_value;
};
struct media_type {
token_pair type_subtype;
std::vector<parameter> params;
};
BOOST_FUSION_ADAPT_STRUCT(parameter, name, value, has_value)
BOOST_FUSION_ADAPT_STRUCT(media_type, type_subtype, params)
namespace qi = boost::spirit::qi;
namespace phoenix = boost::phoenix;
using namespace std::literals;
template<class Iterator>
struct components
{
components()
{
using qi::ascii::char_;
spaces = char_(" \t");
token = +~char_( "()<>#,;:\\\"/[]?={} \t");
token_pair_rule = token >> '/' >> token;
quoted_string = '"' >> *('\\' >> char_ | ~char_('"')) >> '"';
value = quoted_string | token;
name_only = token >> qi::attr("") >> qi::attr(false);
nvp = token >> '=' >> value >> qi::attr(true);
any_parameter = ';' >> (nvp | name_only);
some_parameters = +any_parameter;
parameters = *any_parameter;
qi::on_error<qi::fail>(
token,
this->report_error(qi::_1, qi::_2, qi::_3, qi::_4)
);
BOOST_SPIRIT_DEBUG_NODES((token)
(quoted_string)
(value)
(name_only)
(nvp)
(any_parameter)
(parameters)
)
}
protected:
using Skipper = qi::space_type;
Skipper spaces;
qi::rule<Iterator, std::string()> quoted_string, token, value;
qi::rule<Iterator, parameter(), Skipper> nvp, name_only, any_parameter;
qi::rule<Iterator, std::vector<parameter>(), Skipper> parameters, some_parameters;
qi::rule<Iterator, token_pair()> token_pair_rule;
public:
std::string error_message;
protected:
struct ReportError {
// the result type must be explicit for Phoenix
template<typename, typename, typename, typename>
struct result { typedef void type; };
ReportError(std::string& error_message)
: error_message(error_message) {}
// contract the string to the surrounding new-line characters
template<typename Iter>
void operator()(Iter first, Iter last,
Iter error, const qi::info& what) const
{
using namespace std::string_literals;
std::ostringstream ss;
ss << "Error! Expecting "
<< what
<< " in header value: " << std::quoted(std::string(first, last))
<< " at position: " << error - first;
error_message = ss.str();
}
std::string& error_message;
};
const phoenix::function<ReportError> report_error = ReportError(error_message);
};
template<class Iterator>
struct token_grammar
: components<Iterator>
, qi::grammar<Iterator, media_type()>
{
token_grammar() : token_grammar::base_type(media_type_rule)
{
media_type_with_parameters = token_pair_rule >> qi::skip(spaces)[some_parameters];
media_type_no_parameters = token_pair_rule >> qi::attr(std::vector<parameter>()) >> qi::skip(spaces)[qi::eoi];
media_type_rule = qi::eps > (qi::hold[media_type_no_parameters]
| qi::hold[media_type_with_parameters]);
BOOST_SPIRIT_DEBUG_NODES((media_type_with_parameters)
(media_type_no_parameters)
(media_type_rule))
qi::on_error<qi::fail>(
media_type_rule,
this->report_error(qi::_1, qi::_2, qi::_3, qi::_4)
);
}
private:
using Skipper = typename token_grammar::components::Skipper;
using token_grammar::components::spaces;
using token_grammar::components::token;
using token_grammar::components::token_pair_rule;
using token_grammar::components::value;
using token_grammar::components::any_parameter;
using token_grammar::components::parameters;
using token_grammar::components::some_parameters;
public:
qi::rule<Iterator, media_type()> media_type_no_parameters, media_type_with_parameters, media_type_rule;
};
TEST(spirit_test, test1)
{
token_grammar<std::string::const_iterator> grammar{};
auto test = R"__test(application/json )__test"s;
auto ct = media_type {};
bool r = parse(test.cbegin(), test.cend(), grammar, ct);
EXPECT_EQ("application", ct.type_subtype.first);
EXPECT_EQ("json", ct.type_subtype.second);
EXPECT_EQ(0, ct.params.size());
ct = {};
test = R"__test(text/html ; charset = "ISO-8859-5")__test"s;
parse(test.cbegin(), test.cend(), grammar, ct);
EXPECT_EQ("text", ct.type_subtype.first);
EXPECT_EQ("html", ct.type_subtype.second);
ASSERT_EQ(1, ct.params.size());
EXPECT_TRUE(ct.params[0].has_value);
EXPECT_EQ("charset", ct.params[0].name);
EXPECT_EQ("ISO-8859-5", ct.params[0].value);
auto mt = media_type {};
parse(test.cbegin(), test.cend(), grammar.media_type_rule, mt);
EXPECT_EQ("text", mt.type_subtype.first);
EXPECT_EQ("html", mt.type_subtype.second);
EXPECT_EQ(1, mt.params.size());
//
// Introduce a failure case
//
mt = media_type {};
test = R"__test(text/html garbage ; charset = "ISO-8859-5")__test"s;
r = parse(test.cbegin(), test.cend(), grammar.media_type_rule, mt);
EXPECT_FALSE(r);
EXPECT_EQ("", grammar.error_message);
}
Related
I want to write a simple C++ parser which extracts the block hierarchy. I am using this rule:
std::string rest_content;
std::vector<boost::tuple<std::string, std::string>> scopes;
qi::rule<It, qi::ascii::space_type> block = *(
r.comment
| r.scope[push_back(boost::phoenix::ref(scopes), _1)]
| qi::char_[boost::phoenix::ref(rest_content) += _1] // rest
);
qi::phrase_parse(first, last,
block,
ascii::space);
which is supposed to break down code into three parts: comment, scope (code surrounded by "{}") and "rest".
The problem is that all the space characters are removed from the "rest". I need those spaces for later parsing (such as extracting identifiers).
I have tried using qi::skip, qi::lexeme and qi::raw to keep spaces:
// one of many failed attempts
qi::rule<It, qi::ascii::space_type> block = qi::lexeme[*(
qi::skip[r.comment]
| qi::skip[r.scope[push_back(boost::phoenix::ref(scopes), _1)]]
| qi::char_[push_back(boost::phoenix::ref(rest_content), _1)]
)];
but it never works.
So how to keep space characters? Any help is welcome. Thanks.
If you're parsing C++ code this way you may be biting off more than you can chew.
I'll answer, but the answer should show you how limited this approach is going to be. Just imagine parsing through
namespace q::x {
namespace y {
struct A {
template <typename = ns1::c<int>, typename...> struct C;
};
template <typename T, typename... Ts>
struct A::C final : ns2::ns3::base<A::C<T, Ts...>, Ts...> {
int simple = [](...) {
enum class X : unsigned { answer = 42, };
struct {
auto operator()(...) -> decltype(auto) {
return static_cast<int>(X::answer);
}
} iife;
return iife();
}("/* }}} */"); // {{{
};
}
}
and getting it right. And yes. that's valid code.
In fact it's so tricky, that it's easy to make "grown compilers" (GCC) trip: https://wandbox.org/permlink/FzcaSl6tbn18jq4f (Clang has no issue: https://wandbox.org/permlink/wu0mFwQiTOogKB5L).
That said, let me refer to my old explanation of how rule declarations and skippers work together: Boost spirit skipper issues
And show an approximation of what I'd do.
The comments
Actually, the comments should be part of your skipper, so let's make it so:
using SkipRule = qi::rule<It>;
SkipRule comment_only
= "//" >> *~qi::char_("\r\n") >> qi::eol
| "/*" >> *(qi::char_ - "*/") >> "*/"
;
Now for general skipping, we want to include whitespace:
SkipRule comment_or_ws
= qi::space | comment_only;
Now we want to parse types and identifiers:
qi::rule<It, std::string()> type
= ( qi::string("struct")
| qi::string("class")
| qi::string("union")
| qi::string("enum") >> -(*comment_or_ws >> qi::string("class"))
| qi::string("namespace")
)
>> !qi::graph // must be followed by whitespace
;
qi::rule<It, std::string()> identifier =
qi::char_("a-zA-Z_") >> *qi::char_("a-zA-Z_0-9")
;
I've /guessed/ that struct X { }; would be an example of a "scope" for you, and the tuple would contain ("struct", "X").
As a bonus I used attribute adaption of std::pair and show how to insert into a multimap for good measure later on
qi::rule<It, std::pair<std::string, std::string>()> scope
= qi::skip(comment_or_ws.alias()) [
type >> identifier
>> *~qi::char_(";{") // ignore some stuff like base classes
>> qi::omit["{" >> *~qi::char_("}") >> "}" | ';']
];
Note a big short-coming here is that the first non-commented '}' will "end" the scope. That's not how the language works (see the leading example)
Now we can conclude with an improved "block" rule:
qi::rule<It, SkipRule> block
= *(
scope [px::insert(px::ref(scopes), _1)]
| qi::skip(comment_only.alias()) [
qi::as_string[qi::raw[+(qi::char_ - scope)]] [px::ref(rest_content) += _1]
] // rest
);
Note that
- we override the comment_or_ws skipper with comment_only so we don't drop all whitespace from "rest content"
- inversely, we override the skipper to include whitespace inside the scope rule because otherwise the negative scope invocation (char_ - scope) would do the wrong thing because it wouldn't skip whitespace
Full Demo
Live On Coliru
//#define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted/std_pair.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
namespace qi = boost::spirit::qi;
namespace px = boost::phoenix;
int main() {
using It = std::string::const_iterator;
using namespace qi::labels;
std::string rest_content;
std::multimap<std::string, std::string> scopes;
using SkipRule = qi::rule<It>;
SkipRule comment_only
= "//" >> *~qi::char_("\r\n") >> qi::eol
| "/*" >> *(qi::char_ - "*/") >> "*/"
;
SkipRule comment_or_ws
= qi::space | comment_only;
qi::rule<It, std::string()> type
= ( qi::string("struct")
| qi::string("class")
| qi::string("union")
| qi::string("enum") >> -(*comment_or_ws >> qi::string("class"))
| qi::string("namespace")
)
>> !qi::graph // must be followed by whitespace
;
qi::rule<It, std::string()> identifier =
qi::char_("a-zA-Z_") >> *qi::char_("a-zA-Z_0-9")
;
qi::rule<It, std::pair<std::string, std::string>()> scope
= qi::skip(comment_or_ws.alias()) [
type >> identifier
>> *~qi::char_(";{") // ignore some stuff like base classes
>> qi::omit["{" >> *~qi::char_("}") >> "}" | ';']
];
qi::rule<It, SkipRule> block
= *(
scope [px::insert(px::ref(scopes), _1)]
| qi::skip(comment_only.alias()) [
qi::as_string[qi::raw[+(qi::char_ - scope)]] [px::ref(rest_content) += _1]
] // rest
);
//BOOST_SPIRIT_DEBUG_NODES((block)(scope)(identifier)(type))
std::string const code = R"(
// some random sample "code"
struct base {
std::vector<int> ints;
};
/* class skipped_comment : base { };
*/
namespace q { namespace nested { } } // nested is not supported
class forward_declared;
template <typename T> // actually basically ignored
class
Derived
: base {
std::string more_data_members;
};
enum class MyEnum : int32_t {
foo = 0,
bar, /* whoop } */
qux = foo + bar
};
int main() {
return 0;
}
)";
qi::phrase_parse(begin(code), end(code), block, comment_or_ws);
for (auto& [k,v] : scopes) {
std::cout << k << ": " << v << "\n";
}
std::cout << "------------------ BEGIN REST_CONTENT -----------------\n";
std::cout << rest_content << "\n";
std::cout << "------------------ END REST_CONENT --------------------\n";
}
Which parses the following sample input:
// some random sample "code"
struct base {
std::vector<int> ints;
};
/* class skipped_comment : base { };
*/
namespace q { namespace nested { } } // nested is not supported
class forward_declared;
template <typename T> // actually basically ignored
class
Derived
: base {
std::string more_data_members;
};
enum class MyEnum : int32_t {
foo = 0,
bar, /* whoop } */
qux = foo + bar
};
int main() {
return 0;
}
Printing
class: forward_declared
class: Derived
enumclass: MyEnum
namespace: q
struct: base
------------------ BEGIN REST_CONTENT -----------------
;}template <typename T>;;
int main() {
return 0;
}
------------------ END REST_CONENT --------------------
Conclusion
This result seems a decent pointer to
explain how to tackle the specific hurdle
demonstrate how this approach to parsing is breaking down at the slightest obstacle (namespace a { namespace b { } } for example)
Caveat Emptor
Once again, I find myself reaching for boost spirit. Once again I find myself defeated by it.
A HTTP header value takes the general form:
text/html; q=1.0, text/*; q=0.8, image/gif; q=0.6, image/jpeg; q=0.6, image/*; q=0.5, */*; q=0.1
i.e. value *OWS [; *OWS name *OWS [= *OWS possibly_quoted_value] *OWS [...]] *OWS [ , <another value> ...]
so in my mind, this header decodes to:
value[0]:
text/html
params:
name : q
value : 1.0
value[1]:
text/*
params:
name : q
value : 0.8
...
and so on.
I am certain that to anyone who knows how, the boost::spirit::qi syntax for this is trivial.
I humbly ask for your assistance.
for example, here's the outline of the code which decodes the Content-Type header, which is limited to one value of the form type/subtype, with any number of parameters of the form <sp> ; <sp> token=token|quoted_string
template<class Iter>
void parse(ContentType& ct, Iter first, Iter last)
{
ct.mutable_type()->append(to_lower(consume_token(first, last)));
consume_lit(first, last, '/');
ct.mutable_subtype()->append(to_lower(consume_token(first, last)));
while (first != last) {
skipwhite(first, last);
if (consume_char_if(first, last, ';'))
{
auto p = ct.add_parameters();
skipwhite(first, last);
p->set_name(to_lower(consume_token(first, last)));
skipwhite(first, last);
if (consume_char_if(first, last, '='))
{
skipwhite(first, last);
p->set_value(consume_token_or_quoted(first, last));
}
else {
// no value on this parameter
}
}
else if (consume_char_if(first, last, ','))
{
// normally we should get the next value-token here but in the case of Content-Type
// we must barf
throw std::runtime_error("invalid use of ; in Content-Type");
}
}
}
ContentType& populate(ContentType& ct, const std::string& header_value)
{
parse(ct, header_value.begin(), header_value.end());
return ct;
}
OK, after an heroic 24 hours of struggle (well, not really - more like reading the manual over and over again...), I've found a way that works.
I am by no means competent with boost::spirit. If someone out there can improve on this answer, please do post it.
This spirit state machine takes the value of a header (with one, optionally parameterised, value) and turns it into a content_type structure.
My amateur reading of the HTTP standard indicates that some headers have the form (spaces here indicate any amount of white space, values may be quoted or not:
Header-Name: tokena/tokenb [; param1 = "value" [; param2 = value]...]
whereas others have the more general form:
Header-Name: token [; param1 = "value"[; param2 = value]...] [ , token ...]
This code covers the first case - i.e. the HTTP Content-Type header value. I will need to extend it to cater for the Accept header (which can advertise multiple values with parameters) - that will come later.
So here's the code. Please by all means show me how to improve it!!
#define BOOST_SPIRIT_DEBUG
#include <gtest/gtest.h>
#include <boost/spirit/include/qi.hpp>
#include <boost/config/warning_disable.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/qi_char.hpp>
#include <boost/spirit/include/phoenix_core.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>
#include <boost/spirit/include/phoenix_fusion.hpp>
#include <boost/spirit/include/phoenix_stl.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/fusion/include/std_pair.hpp>
#include <utility>
#include <vector>
#include <string>
#include <boost/variant.hpp>
namespace qi = boost::spirit::qi;
namespace ascii = boost::spirit::ascii;
using unary_parameter = std::string;
struct binary_parameter
{
std::string name;
std::string value;
};
BOOST_FUSION_ADAPT_STRUCT(binary_parameter,
(std::string, name)
(std::string, value))
using parameter = boost::variant<unary_parameter, binary_parameter>;
struct type_subtype
{
std::string type;
std::string subtype;
};
BOOST_FUSION_ADAPT_STRUCT(type_subtype,
(std::string, type)
(std::string, subtype))
using content_type_pair = std::pair<std::string, std::string>;
struct content_type
{
type_subtype type;
std::vector<parameter> params;
};
BOOST_FUSION_ADAPT_STRUCT(content_type,
(type_subtype, type)
(std::vector<parameter>, params))
template<class Iterator>
struct token_grammar : qi::grammar<Iterator, content_type()>
{
token_grammar() : token_grammar::base_type(content_type_rule)
{
using ascii::char_;
using qi::omit;
using qi::eoi;
CR = char_('\r');
LF = char_('\n');
CRLF = CR >> LF;
SP = char_(' ');
HT = char_('\t');
LWS = -CRLF >> +(SP | HT);
UPALPHA = char_('A', 'Z');
LOALPHA = char_('a', 'z');
ALPHA = UPALPHA | LOALPHA;
DIGIT = char_('0', '9');
CTL = char_(0, 31) | char_(127);
QUOT = char_('"');
TEXT = (char_ - CTL) | HT;
separator = char_('(') | ')' | '<' | '>' | '#'
| ',' | ';' | ':' | '\\' | '"'
| '/' | '[' | ']' | '?' | '='
| '{' | '}' | SP | HT;
end_sequence = separator | space;
token = +(char_ - separator);
qdtext = char_ - char_('"') - '\\';
quoted_pair = omit[char_('\\')] >> char_;
quoted_string = omit[char_('"')] >> *(qdtext | quoted_pair) >> omit[char_('"')];
value = quoted_string | token ;
type_subtype_rule = token >> '/' >> token;
name_only = token;
nvp = token >> omit[*SP] >> omit['='] >> omit[*SP] >> value;
any_parameter = omit[*SP] >> omit[char_(';')] >> omit[*SP] >> (nvp | name_only);
content_type_rule = type_subtype_rule >> *any_parameter;
BOOST_SPIRIT_DEBUG_NODES((qdtext)(quoted_pair)(quoted_string)(value)(token)(separator));
}
qi::rule<Iterator, void()> CR, LF, CRLF, SP, HT, LWS, CTL, QUOT;
qi::rule<Iterator, char()> UPALPHA, LOALPHA, ALPHA, DIGIT, TEXT, qdtext, quoted_pair;
qi::rule<Iterator, void()> separator, space, end_sequence;
qi::rule<Iterator, std::string()> quoted_string, token, value;
qi::rule<Iterator, type_subtype()> type_subtype_rule;
qi::rule<Iterator, unary_parameter()> name_only;
qi::rule<Iterator, binary_parameter()> nvp;
qi::rule<Iterator, parameter()> any_parameter;
qi::rule<Iterator, content_type()> content_type_rule;
};
TEST(spirit_test, test1)
{
token_grammar<std::string::const_iterator> grammar{};
std::string test = R"__test(application/json )__test";
content_type ct;
bool r = qi::parse(test.cbegin(), test.cend(), grammar, ct);
EXPECT_EQ("application", ct.type.type);
EXPECT_EQ("json", ct.type.subtype);
EXPECT_EQ(0, ct.params.size());
ct = {};
test = R"__test(text/html ; charset = "ISO-8859-5")__test";
qi::parse(test.cbegin(), test.cend(), grammar, ct);
EXPECT_EQ("text", ct.type.type);
EXPECT_EQ("html", ct.type.subtype);
ASSERT_EQ(1, ct.params.size());
ASSERT_EQ(typeid(binary_parameter), ct.params[0].type());
auto& x = boost::get<binary_parameter>(ct.params[0]);
EXPECT_EQ("charset", x.name);
EXPECT_EQ("ISO-8859-5", x.value);
}
I've taken the code as posted by OP and given it a review.
there's no need to specify void(). In fact it's preferable to use qi::unused_type in such cases, which is what rules will default to if no attribute type is declared.
there no need for char_ if you don't wish to expose the attribute. Use lit instead.
there is no need to wrap every char parser in a rule. That hurts performance. It's best to leave the proto expression tree un-evaluated as long so Qi can optimize parser expressions more, and the compiler can inline more.
Also, Qi doesn't have move semantics on attributes, so avoiding redundant rules eliminates redundant copies of sub-attributes that get concatenated in the containing rules.
Sample alternative spelling (caution, see Assigning parsers to auto variables)
auto CR = qi::lit('\r');
auto LF = qi::lit('\n');
auto CRLF = qi::lit("\r\n");
auto HT = qi::lit('\t');
auto SP = qi::lit(' ');
auto LWS = qi::copy(-CRLF >> +(SP | HT)); // deepcopy
UPALPHA = char_('A', 'Z');
LOALPHA = char_('a', 'z');
ALPHA = UPALPHA | LOALPHA;
DIGIT = char_('0', '9');
//CTL = char_(0, 31) | char_(127);
TEXT = char_("\t\x20-\x7e\x80-\xff");
Since you didn't have to use char_, you also don't have kill the attribute using qi::omit[].
When you are in a Qi domain expression template, raw string/char literals are implicitly wrapped in a qi::lit so, you can simply things like
quoted_pair = omit[char_('\\')] >> char_;
quoted_string = omit[char_('"')] >> *(qdtext | quoted_pair) >> omit[char_('"')];
to just
quoted_pair = '\\' >> char_;
quoted_string = '"' >> *(qdtext | quoted_pair) >> '"';
instead of spelling out skipping spaces with omit[*SP] all the time, just declare the rule with a skipper. Now, you can simplify
nvp = token >> omit[*SP] >> omit['='] >> omit[*SP] >> value;
any_parameter = omit[*SP] >> omit[char_(';')] >> omit[*SP] >> (nvp | name_only);
content_type_rule = type_subtype_rule >> *any_parameter;
to just
nvp = token >> '=' >> value;
any_parameter = ';' >> (nvp | name_only);
content_type_rule = type_subtype_rule >> qi::skip(spaces)[*any_parameter];
Note that any subrule invocations of rules that are declared without a skipper are implicitly lexeme: Boost spirit skipper issues
there were many redundant/unused headers
recent compilers + boost versions make BOOST_FUSION_ADAPT_STRUCT much simpler by using decltype
The results of simplifying are much less noisy:
//#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
#include <boost/fusion/include/adapted.hpp>
struct parameter {
boost::optional<std::string> name;
std::string value;
};
struct type_subtype {
std::string type;
std::string subtype;
};
struct content_type {
type_subtype type;
std::vector<parameter> params;
};
BOOST_FUSION_ADAPT_STRUCT(type_subtype, type, subtype)
BOOST_FUSION_ADAPT_STRUCT(content_type, type, params)
template<class Iterator>
struct token_grammar : qi::grammar<Iterator, content_type()>
{
token_grammar() : token_grammar::base_type(content_type_rule)
{
using qi::ascii::char_;
spaces = char_(' ');
token = +~char_( "()<>#,;:\\\"/[]?={} \t");
quoted_string = '"' >> *('\\' >> char_ | ~char_('"')) >> '"';
value = quoted_string | token;
type_subtype_rule = token >> '/' >> token;
name_only = token;
nvp = token >> '=' >> value;
any_parameter = ';' >> (nvp | name_only);
content_type_rule = type_subtype_rule >> qi::skip(spaces) [*any_parameter];
BOOST_SPIRIT_DEBUG_NODES((nvp)(any_parameter)(content_type_rule)(quoted_string)(token)(value)(type_subtype_rule))
}
private:
using Skipper = qi::space_type;
Skipper spaces;
qi::rule<Iterator, binary_parameter(), Skipper> nvp;
qi::rule<Iterator, parameter(), Skipper> any_parameter;
qi::rule<Iterator, content_type()> content_type_rule;
// lexemes
qi::rule<Iterator, std::string()> quoted_string, token, value;
qi::rule<Iterator, type_subtype()> type_subtype_rule;
qi::rule<Iterator, unary_parameter()> name_only;
};
See it Live On Coliru (with the same test cases)
BONUS
I'd prefer a simpler AST in a case like this. By injecting some attribute values using qi::attr you can avoid using boost::variant and/or even avoid boost::optional:
struct parameter {
bool have_name;
std::string name;
std::string value;
};
struct type_subtype {
std::string type;
std::string subtype;
};
struct content_type {
type_subtype type;
std::vector<parameter> params;
};
BOOST_FUSION_ADAPT_STRUCT(parameter, have_name, name, value)
BOOST_FUSION_ADAPT_STRUCT(type_subtype, type, subtype)
BOOST_FUSION_ADAPT_STRUCT(content_type, type, params)
namespace qi = boost::spirit::qi;
template<class Iterator>
struct token_grammar : qi::grammar<Iterator, content_type()>
{
token_grammar() : token_grammar::base_type(content_type_rule)
{
using qi::ascii::char_;
spaces = char_(' ');
token = +~char_( "()<>#,;:\\\"/[]?={} \t");
quoted_string = '"' >> *('\\' >> char_ | ~char_('"')) >> '"';
value = quoted_string | token;
type_subtype_rule = token >> '/' >> token;
name_only = qi::attr(false) >> qi::attr("") >> token;
nvp = qi::attr(true) >> token >> '=' >> value;
any_parameter = ';' >> (nvp | name_only);
content_type_rule = type_subtype_rule >> qi::skip(spaces) [*any_parameter];
BOOST_SPIRIT_DEBUG_NODES((nvp)(any_parameter)(content_type_rule)(quoted_string)(token)(value)(type_subtype_rule))
}
private:
using Skipper = qi::space_type;
Skipper spaces;
qi::rule<Iterator, parameter(), Skipper> nvp, name_only, any_parameter;
qi::rule<Iterator, content_type()> content_type_rule;
// lexemes
qi::rule<Iterator, std::string()> quoted_string, token, value;
qi::rule<Iterator, type_subtype()> type_subtype_rule;
};
Consider the following example extracted from a more complex code:
#include <boost/fusion/adapted.hpp>
#include <boost/fusion/include/std_pair.hpp>
#include <boost/phoenix.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/support_istream_iterator.hpp>
#include <map>
#include <string>
namespace qi = boost::spirit::qi;
namespace phx = boost::phoenix;
// The class implements a XML tag storing the name and a variable number of attributes:
struct Tag
{
// The typedef defines the type used for a XML name:
typedef std::string name_type;
// The typedef defines the type used for a XML value:
typedef std::string value_type;
// The typedef defines the type of a XML attribute:
typedef std::pair<
name_type,
value_type
> attribute_type;
// The type defines a list of attributes.
// Note: We use a std::map to simplify the attribute search.
typedef std::map<
name_type,
value_type
> list_type;
// Clear all information stored within the instance:
void clear( )
{
m_name.clear( ); m_attribute.clear( );
}
std::size_t m_indent; // The tag shall be / is indented by m_indent number of tabs.
name_type m_name; // Name of the tag.
list_type m_attribute; // List of tag attributes.
};
// Define the mapping between Tools::Serialization::Archive::Type::Xml::Format::Tag and boost::fusion:
BOOST_FUSION_ADAPT_STRUCT( Tag,
( std::size_t , m_indent )
( Tag::name_type, m_name )
( Tag::list_type, m_attribute ) )
// This class implements the decoder skipper grammar:
template < typename _Iterator >
struct skipper
: qi::grammar< _Iterator >
{
skipper( ) : skipper::base_type( m_skipper )
{
// The rule defines the default skipper grammar:
m_skipper = ( qi::space ) // Skip all "spaces".
|
( qi::cntrl ); // Skip all "cntrl".
}
// The following variables define the rules used within this grammar:
qi::rule< _Iterator > m_skipper;
};
// This class implements the grammar used to parse a XML "begin tag".
// The expected format is as follows: <name a="xyz" b="xyz" ... N="xyz">
template < typename _Iterator, typename _Skipper >
struct tag_begin : qi::grammar< _Iterator, Tag( ), _Skipper >
{
tag_begin( ) : tag_begin::base_type( m_tag )
{
// The rule for a XML name shall stop when a ' ' or '>' is detected:
m_string = qi::lexeme[ *( qi::char_( "a-zA-Z0-9_.:" ) ) ];
// The rule for a XML attribute shall parse the following format: 'name="value"':
m_attribute = m_string
>> "=\""
>> m_string
>> '"';
// The rule for an XML attribute list is a sequence of attributes separated by ' ':
m_list = *( m_attribute - '>' );
// Finally the resulting XML tag has the following format: <name a="xyz" b="xyz" ... N="xyz">
m_tag = '<'
>> -qi::int_
>> m_string
>> m_list
>> '>';
// Enable debug support for the used rules. To activate the debug output define macro BOOST_SPIRIT_DEBUG:
BOOST_SPIRIT_DEBUG_NODES( ( m_string )( m_attribute )( m_list ) )
}
// The following variables define the rules used within this grammar:
qi::rule< _Iterator, Tag::name_type( ) , _Skipper > m_string;
qi::rule< _Iterator, Tag::attribute_type( ), _Skipper > m_attribute;
qi::rule< _Iterator, Tag::list_type( ) , _Skipper > m_list;
qi::rule< _Iterator, Tag( ) , _Skipper > m_tag;
};
bool beginTag( std::istream& stream, Tag& tag )
{
// Ensure that no whitespace characters are skipped:
stream.unsetf( std::ios::skipws );
// Create begin and end iterator for given stream:
boost::spirit::istream_iterator begin( stream );
boost::spirit::istream_iterator end;
// Define the grammar skipper type:
typedef skipper<
boost::spirit::istream_iterator
> skipper_type;
// Create an instance of the used skipper:
skipper_type sk;
// Create an instance of the used grammar:
tag_begin<
boost::spirit::istream_iterator,
skipper_type
> gr;
// Try to parse the data stored within the stream according the grammar and store the result in the tag variable:
bool r = boost::spirit::qi::phrase_parse( begin,
end,
gr,
sk,
tag );
char nextSym = 0;
stream >> nextSym;
for( auto i = tag.m_attribute.begin( ); i != tag.m_attribute.end( ); ++i )
{
std::cout << i->first << " : " << i->second << std::endl;
}
std::cout << "Next symbol: " << nextSym << std::endl;
return r;
}
int main( )
{
std::stringstream s;
s << "<object cName=\"bool\" cVersion=\"1\" vName=\"bool\"> <value>0</value></object>";
Tag t;
beginTag( s, t );
return 0;
}
I use the grammar to extract the xml tag content. In principle this works as expected and the results are as follows:
cName : bool
cVersion : 1
vName : bool
Next symbol: v
The problem is that the parser consumes to much data. My expectation is that the parser stops when first tag is closed '>'. But it seems that the parser consumes also the following spaces and the '<' symbol. So the next symbol read from the stream is equal to 'v'. I would like to avoid this because following parser calls expect the '<' symbol. Any ideas ?
There's no reliable way to achieve this.
The problem is you're not re-using the istream_iterators across parse calls. The whole purpose for boost::spirit::istream_iterator is provide a multi_pass capable iterator on top of an InputIterator¹.
Because Spirit allows arbitrary grammars with arbitrary backtracking, you cannot prevent consuming more than the input that was actually successfully parsed.
The obvious solution here is to integrate all the subsequent steps into the same grammar and/or to reuse the iterators (so the iterator's stored backtrack buffer still contains the characters you need).
Demonstration / Proof of Concept
Here is a version that parses open tags in a loop
while (boost::spirit::qi::phrase_parse(begin, end, gr, sk, tag)) {
std::cout << "============\nParsed open tag '" << tag.m_name << "'\n";
for (auto const& p: tag.m_attribute)
std::cout << p.first << ": " << p.second << "\n";
count += 1;
tag.clear();
};
std::cout << "Next symbol: ";
std::copy(begin, end, std::ostream_iterator<char>(std::cout));
And it prints:
============
Parsed open tag 'object'
cName: bool
cVersion: 1
vName: bool
============
Parsed open tag 'value'
Next symbol: 0</value>
</object>
Live On Coliru
//#define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted.hpp>
#include <boost/spirit/include/qi.hpp>
#include <map>
namespace qi = boost::spirit::qi;
// The class implements a XML tag storing the name and a variable number of
// attributes:
struct Tag {
typedef std::string name_type;
typedef std::string value_type;
typedef std::pair<name_type, value_type> attribute_type;
typedef std::map<name_type, value_type> list_type;
// Clear all information stored within the instance:
void clear() {
m_name.clear();
m_attribute.clear();
}
std::size_t m_indent; // The tag shall be / is indented by m_indent number of tabs.
name_type m_name; // Name of the tag.
list_type m_attribute; // List of tag attributes.
};
BOOST_FUSION_ADAPT_STRUCT(Tag, m_indent, m_name, m_attribute)
// This class implements the grammar used to parse a "XML" begin tag.
// The expected format is as follows: <name a="xyz" b="xyz" ... N="xyz">
template <typename Iterator, typename Skipper> struct tag_begin : qi::grammar<Iterator, Tag(), Skipper> {
tag_begin() : tag_begin::base_type(m_tag) {
m_string = *qi::char_("a-zA-Z0-9_.:");
m_attribute = m_string >> '=' >> qi::lexeme['"' >> m_string >> '"'];
m_attributes = *m_attribute;
m_tag = '<' >> -qi::int_ >> m_string >> m_attributes >> '>';
BOOST_SPIRIT_DEBUG_NODES((m_string)(m_attribute)(m_attributes))
}
private:
// The following variables define the rules used within this grammar:
qi::rule<Iterator, Tag::attribute_type(), Skipper> m_attribute;
qi::rule<Iterator, Tag::list_type(), Skipper> m_attributes;
qi::rule<Iterator, Tag(), Skipper> m_tag;
// lexemes
qi::rule<Iterator, Tag::name_type()> m_string;
};
bool beginTag(std::istream &stream, Tag &tag) {
// Ensure that no whitespace characters are skipped:
stream.unsetf(std::ios::skipws);
typedef boost::spirit::istream_iterator It;
typedef qi::rule<It> skipper_type;
skipper_type sk = qi::space | qi::cntrl;
tag_begin<boost::spirit::istream_iterator, skipper_type> gr;
It begin(stream), end;
int count = 0;
while (boost::spirit::qi::phrase_parse(begin, end, gr, sk, tag)) {
std::cout << "============\nParsed open tag '" << tag.m_name << "'\n";
for (auto const& p: tag.m_attribute)
std::cout << p.first << ": " << p.second << "\n";
count += 1;
tag.clear();
};
std::cout << "Next symbol: ";
std::copy(begin, end, std::ostream_iterator<char>(std::cout));
return count > 0;
}
int main() {
std::stringstream s;
s << R"(
<object cName="bool" cVersion="1" vName="bool">
<value>0</value>
</object>
)";
Tag t;
beginTag(s, t);
}
¹ (which is strictly forward-only and cannot be repeatedly dereferenced)
I'm trying to parse a CSV file (with header line) using boost spirit.
The csv is not in a constant format. Sometimes there is some extra column or the order of the column is mixed. I'm interested in few columns, whose header name is well known.
For instance my CSV may look like:
Name,Surname,Age
John,Doe,32
Or:
Age,Name
32,John
I want to parse only the content of Name and Age (N.B. Age is integer type). At the moment i come out with a very ugly solution where Spirit parses the first line and creates a vector that contains an enum in the positions i'm interested into. And then i have to do the parsing of the terminal symbols by hand...
enum LineItems {
NAME, AGE, UNUSED
};
struct CsvLine {
string name;
int age;
};
using Column = std::string;
using CsvFile = std::vector<CsvLine>;
template<typename It>
struct CsvGrammar: qi::grammar<It, CsvFile(), qi::locals<std::vector<LineItems>>, qi::blank_type> {
CsvGrammar() :
CsvGrammar::base_type(start) {
using namespace qi;
static const char colsep = ',';
start = qi::omit[header[qi::_a = qi::_1]] >> eol >> line(_a) % eol;
header = (lit("Name")[phx::push_back(phx::ref(qi::_val), LineItems::NAME)]
| lit("Age")[phx::push_back(phx::ref(qi::_val), LineItems::AGE)]
| column[phx::push_back(phx::ref(qi::_val), LineItems::UNUSED)]) % colsep;
line = (column % colsep)[phx::bind(&CsvGrammar<It>::convertFunc, this, qi::_1, qi::_r1,
qi::_val)];
column = quoted | *~char_(",\n");
quoted = '"' >> *("\"\"" | ~char_("\"\n")) >> '"';
}
void convertFunc(std::vector<string>& columns, std::vector<LineItems>& positions, CsvLine &csvLine) {
//terminal symbol parsing here, and assign to csvLine struct.
...
}
private:
qi::rule<It, CsvFile(), qi::locals<std::vector<LineItems>>, qi::blank_type> start;
qi::rule<It, std::vector<LineItems>(), qi::blank_type> header;
qi::rule<It, CsvLine(std::vector<LineItems>), qi::blank_type> line;
qi::rule<It, Column(), qi::blank_type> column;
qi::rule<It, std::string()> quoted;
qi::rule<It, qi::blank_type> empty;
};
Here is the full source.
What if the header parser could prepare a vector<rule<...>*> and the "line parser" just use this vector to parse itself? a sort of advanced nabialek trick (i've been trying but i couldn't make it).
Or is there any better way to parse this kind of CSV with Spirit?
(any help is appreciated, thank you in advance)
I'd go with the concept that you have,
I think it's plenty elegant (the qi locals even allow reentrant use of this).
To reduce the cruft in the rules (Boost Spirit: "Semantic actions are evil"?) you could move the "conversion function" off into attribute transformation customization points.
Oops. As commented that was too simple. However, you can still reduce the cruftiness quite a bit. With two simple tweaks, the grammar reads:
item.add("Name", NAME)("Age", AGE);
start = omit[ header[_a=_1] ] >> eol >> line(_a) % eol;
header = (item | omit[column] >> attr(UNUSED)) % colsep;
line = (column % colsep) [convert];
column = quoted | *~char_(",\n");
quoted = '"' >> *("\"\"" | ~char_("\"\n")) >> '"';
The tweaks:
using qi::symbols to map from header to LineItem
using a raw semantinc action ([convert]) which directly access the context (see boost spirit semantic action parameters):
struct final {
using Ctx = typename decltype(line)::context_type;
void operator()(Columns const& columns, Ctx &ctx, bool &pass) const {
auto& csvLine = boost::fusion::at_c<0>(ctx.attributes);
auto& positions = boost::fusion::at_c<1>(ctx.attributes);
int i =0;
for (LineItems position : positions) {
switch (position) {
case NAME: csvLine.name = columns[i]; break;
case AGE: csvLine.age = atoi(columns[i].c_str()); break;
default: break;
}
i++;
}
pass = true; // returning false fails the `line` rule
}
} convert;
Arguably the upshot is akin to doing auto convert = phx::bind(&CsvGrammar<It>::convertFunc, this, qi::_1, qi::_r1, qi::_val) but using auto with Proto/Phoenix/Spirit expressions is notoriously error prone (UB due to dangling refs to temporaries from the expression template), so I'd certainly prefer the way shown above.
Live On Coliru
//#define BOOST_SPIRIT_DEBUG
#define BOOST_SPIRIT_USE_PHOENIX_V3
#include <iostream>
#include <boost/fusion/include/at_c.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <string>
#include <vector>
namespace qi = boost::spirit::qi;
namespace phx = boost::phoenix;
using std::string;
enum LineItems { NAME, AGE, UNUSED };
struct CsvLine {
string name;
int age;
};
using Column = std::string;
using Columns = std::vector<Column>;
using CsvFile = std::vector<CsvLine>;
template<typename It>
struct CsvGrammar: qi::grammar<It, CsvFile(), qi::locals<std::vector<LineItems>>, qi::blank_type> {
CsvGrammar() : CsvGrammar::base_type(start) {
using namespace qi;
static const char colsep = ',';
item.add("Name", NAME)("Age", AGE);
start = qi::omit[ header[_a=_1] ] >> eol >> line(_a) % eol;
header = (item | omit[column] >> attr(UNUSED)) % colsep;
line = (column % colsep) [convert];
column = quoted | *~char_(",\n");
quoted = '"' >> *("\"\"" | ~char_("\"\n")) >> '"';
BOOST_SPIRIT_DEBUG_NODES((header)(column)(quoted));
}
private:
qi::rule<It, std::vector<LineItems>(), qi::blank_type> header;
qi::rule<It, CsvFile(), qi::locals<std::vector<LineItems>>, qi::blank_type> start;
qi::rule<It, CsvLine(std::vector<LineItems> const&), qi::blank_type> line;
qi::rule<It, Column(), qi::blank_type> column;
qi::rule<It, std::string()> quoted;
qi::rule<It, qi::blank_type> empty;
qi::symbols<char, LineItems> item;
struct final {
using Ctx = typename decltype(line)::context_type;
void operator()(Columns const& columns, Ctx &ctx, bool &pass) const {
auto& csvLine = boost::fusion::at_c<0>(ctx.attributes);
auto& positions = boost::fusion::at_c<1>(ctx.attributes);
int i =0;
for (LineItems position : positions) {
switch (position) {
case NAME: csvLine.name = columns[i]; break;
case AGE: csvLine.age = atoi(columns[i].c_str()); break;
default: break;
}
i++;
}
pass = true; // returning false fails the `line` rule
}
} convert;
};
int main() {
const std::string s = "Surname,Name,Age,\nJohn,Doe,32\nMark,Smith,43";
auto f(begin(s)), l(end(s));
CsvGrammar<std::string::const_iterator> p;
CsvFile parsed;
bool ok = qi::phrase_parse(f, l, p, qi::blank, parsed);
if (ok) {
for (CsvLine line : parsed) {
std::cout << '[' << line.name << ']' << '[' << line.age << ']';
std::cout << std::endl;
}
} else {
std::cout << "Parse failed\n";
}
if (f != l)
std::cout << "Remaining unparsed: '" << std::string(f, l) << "'\n";
}
Prints
[Doe][32]
[Smith][43]
The following program is an artificial example (reduced from a larger grammar on which I'm working) to exhibit a strange behaviour.
The output of the program run as is is "hello" and is incorrect.
If I remove the (useless in this example) semantic action from the quoted_string rule the output is the expected "foo=hello".
#define BOOST_RESULT_OF_USE_DECLTYPE
#define BOOST_SPIRIT_USE_PHOENIX_V3
#include <vector>
#include <string>
#include <iostream>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include "utils.hpp"
namespace t {
using std::vector;
using std::string;
namespace qi = boost::spirit::qi;
namespace phx = boost::phoenix;
template <typename Iterator, typename Skipper=qi::space_type>
struct G1 : qi::grammar<Iterator, string(), Skipper> {
template <typename T>
using rule = qi::rule<Iterator, T, Skipper>;
qi::rule<Iterator, string(), qi::locals<char>> quoted_string;
rule<string()> start;
G1() : G1::base_type(start, "G1") {
{
using qi::_1;
using qi::_a;
using attr_signature = vector<char>;
auto handler = [](attr_signature const& elements) -> string {
string output;
for(auto& e : elements) {
output += e;
}
return output;
};
quoted_string = (qi::omit[qi::char_("'\"")[_a = _1]]
>> +(qi::char_ - qi::char_(_a))
>> qi::lit(_a))[qi::_val = phx::bind(handler, _1)];
}
start = qi::string("foo") >> -(qi::string("=") >> quoted_string);
}
};
string parse(string const input) {
G1<string::const_iterator> g;
string result;
phrase_parse(begin(input), end(input), g, qi::standard::space, result);
return result;
}
};
int main() {
using namespace std;
auto r = t::parse("foo='hello'");
cout << r << endl;
}
I can definitely find a workaround, but I'd figure out what am I missing
Like #cv_and_he explained, you're overwriting the attribute with the result of handler(_1). Since attributes are passed by reference, you lose the original value.
Automatic attribute propagation rules know how to concatenate "string" container values, so why don't you just use the default implementation?
quoted_string %= qi::omit[qi::char_("'\"")[_a = _1]]
>> +(qi::char_ - qi::char_(_a))
>> qi::lit(_a);
(Note the %=; this enables automatic propagation even in the presence of semantic actions).
Alternatively, you can push-back from inside the SA:
>> +(qi::char_ - qi::char_(_a)) [ phx::push_back(qi::_val, _1) ]
And, if you really need some processing done in handler, make it take the string by reference:
auto handler = [](attr_signature const& elements, std::string& attr) {
for(auto& e : elements) {
attr += e;
}
};
quoted_string = (qi::omit[qi::char_("'\"")[_a = _1]]
>> +(qi::char_ - qi::char_(_a))
>> qi::lit(_a)) [ phx::bind(handler, _1, qi::_val) ];
All these approaches work.
For really heavy duty things, I have in the past used a custom string type with boost::spirit::traits customization points to do the transformations:
http://www.boost.org/doc/libs/1_55_0/libs/spirit/doc/html/spirit/advanced/customize.html