我正在尝试使用 boost spirit 为以下BNF规则编写解析器
(提升v1.64)
规则是:
<numeric-literal>::= integer
<type-name> ::= "in" | "out" | "in_out"
<array-type-spec> ::= <type-spec> "[" [<numeric-literal>] "]"
<tuple-type-spec> ::= "(" <type-spec> ("," <type-spec>)+ ")"
<type-spec> ::= <type-name> | <array-type-spec> | <tuple-type-spec>
以下是我的尝试,使用boost::make_recursive_variant
它似乎在字符串in
上工作正常
但它在in[2]
上失败了
我的错在哪里?
什么是优雅的解决方案?
namespace Ast {
enum class TypeName { IN, OUT, INOUT};
using NumericLiteral = int;
using TypeSpec = boost::make_recursive_variant
<
TypeName,
std::pair<boost::recursive_variant_, NumericLiteral>,
std::vector < boost::recursive_variant_ >
>::type;
}
//grammar:
namespace myGrammar {
namespace qi = boost::spirit::qi;
template <typename Iterator = char const*,typename Signature = Ast::TypeSpec()>
struct myRules : qi::grammar < Iterator, Signature> {
myRules() : myRules::base_type(start) {
fillSymbols();
rNumericLiteral = qi::int_;
rTypeName = sTypeName;
rTypeSpec = rTypeName | (rTypeSpec >> '[' >> rNumericLiteral >> ']') | ('(' >> qi::repeat(2, qi::inf)[(rTypeSpec % ',')] >> ')');
start = qi::skip(qi::space)[rTypeSpec];
}
private:
using Skipper = qi::space_type;
qi::rule<Iterator, Ast::TypeSpec()> start;
qi::rule<Iterator, Ast::NumericLiteral(), Skipper> rNumericLiteral;
qi::rule<Iterator, Ast::TypeName(), Skipper> rTypeName;
qi::rule<Iterator, Ast::TypeSpec(), Skipper> rTypeSpec;
//symbols
qi::symbols<char, Ast::TypeName>sTypeName;
void fillSymbols()
{
using namespace Ast;
sTypeName.add
("in", TypeName::IN)
("out", TypeName::OUT)
("in_out", TypeName::INOUT)
}
};
}
答案 0 :(得分:2)
将语法1:1转换为PEG语法存在问题,因为左递归会导致无限递归。
您仍然可以轻松地重新排列规则,因此不会发生左递归,但是您在合成所需的AST时会遇到更多麻烦。
这是一个中途站,有一半不错的测试结果:
<强> Live On Coliru 强>
//#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
#include <boost/fusion/adapted/std_pair.hpp>
/*
<numeric-literal> ::= integer
<type-name> ::= "in" | "out" | "in_out"
<array-type-spec> ::= <type-spec> "[" [<numeric-literal>] "]"
<tuple-type-spec> ::= "(" <type-spec> ("," <type-spec>)+ ")"
<type-spec> ::= <type-name> | <array-type-spec> | <tuple-type-spec>
*/
namespace Ast {
enum class TypeName { IN, OUT, INOUT };
static inline std::ostream& operator<<(std::ostream& os, TypeName tn) {
switch(tn) {
case TypeName::IN: return os << "IN";
case TypeName::OUT: return os << "OUT";
case TypeName::INOUT: return os << "INOUT";
}
return os << "?";
}
using NumericLiteral = int;
using TypeSpec = boost::make_recursive_variant<
TypeName,
std::pair<boost::recursive_variant_, NumericLiteral>,
std::vector<boost::recursive_variant_>
>::type;
using ArraySpec = std::pair<TypeSpec, NumericLiteral>;
using TupleSpec = std::vector<TypeSpec>;
}
// grammar:
namespace myGrammar {
namespace qi = boost::spirit::qi;
template <typename Iterator = char const *, typename Signature = Ast::TypeSpec()>
struct myRules : qi::grammar<Iterator, Signature> {
myRules() : myRules::base_type(start) {
rNumericLiteral = qi::int_;
rTypeName = sTypeName >> !qi::alpha;
rTupleSpec = '(' >> rTypeSpec >> +(',' >> rTypeSpec) >> ')';
rScalarSpec = rTypeName | rTupleSpec;
rArraySpec = rScalarSpec >> '[' >> rNumericLiteral >> ']';
rTypeSpec = rArraySpec | rScalarSpec;
start = qi::skip(qi::space)[rTypeSpec >> qi::eoi];
BOOST_SPIRIT_DEBUG_NODES((start)(rTypeSpec)(rTypeName)(rArraySpec)(rScalarSpec)(rTypeSpec)(rNumericLiteral))
}
private:
using Skipper = qi::space_type;
qi::rule<Iterator, Ast::TypeSpec()> start;
qi::rule<Iterator, Ast::NumericLiteral(), Skipper> rNumericLiteral;
qi::rule<Iterator, Ast::ArraySpec(), Skipper> rArraySpec;
qi::rule<Iterator, Ast::TypeSpec(), Skipper> rTypeSpec, rScalarSpec;
qi::rule<Iterator, Ast::TupleSpec(), Skipper> rTupleSpec;
// implicit lexeme
qi::rule<Iterator, Ast::TypeName()> rTypeName;
// symbols
struct TypeName_r : qi::symbols<char, Ast::TypeName> {
TypeName_r() {
using Ast::TypeName;
add ("in", TypeName::IN)
("out", TypeName::OUT)
("in_out", TypeName::INOUT);
}
} sTypeName;
};
}
static inline std::ostream& operator<<(std::ostream& os, Ast::TypeSpec tn) {
struct {
std::ostream& _os;
void operator()(Ast::TypeSpec const& ts) const {
apply_visitor(*this, ts);
}
void operator()(Ast::TypeName tn) const { std::cout << tn; }
void operator()(Ast::TupleSpec const& tss) const {
std::cout << "(";
for (auto const& ts: tss) {
(*this)(ts);
std::cout << ", ";
}
std::cout << ")";
}
void operator()(Ast::ArraySpec const& as) const {
(*this)(as.first);
std::cout << '[' << as.second << ']';
}
} const dumper{os};
dumper(tn);
return os;
}
int main() {
using It = std::string::const_iterator;
myGrammar::myRules<It> const parser;
std::string const test_ok[] = {
"in",
"out",
"in_out",
"(in, out)",
"(out, in)",
"(in, in, in, out, in_out)",
"in[13]",
"in[0]",
"in[-2]",
"in[1][2][3]",
"in[3][3][3]",
"(in[3][3][3], out, in_out[0])",
"(in[3][3][3], out, in_out[0])",
"(in, out)[13]",
"(in, out)[13][0]",
};
std::string const test_fail[] = {
"",
"i n",
"inout",
"()",
"(in)",
"(out)",
"(in_out)",
"IN",
};
auto expect = [&](std::string const& sample, bool expected) {
It f = sample.begin(), l = sample.end();
Ast::TypeSpec spec;
bool ok = parse(f, l, parser, spec);
std::cout << "Test passed:" << std::boolalpha << (expected == ok) << "\n";
if (expected || (expected != ok)) {
if (ok) {
std::cout << "Parsed: " << spec << "\n";
} else {
std::cout << "Parse failed\n";
}
}
if (f!=l) {
std::cout << "Remaining unparsed: '" << std::string(f,l) << "'\n";
}
};
for (std::string const sample : test_ok) expect(sample, true);
for (std::string const sample : test_fail) expect(sample, false);
}
打印
Test passed:true
Parsed: IN
Test passed:true
Parsed: OUT
Test passed:true
Parsed: INOUT
Test passed:true
Parsed: (IN, OUT, )
Test passed:true
Parsed: (OUT, IN, )
Test passed:true
Parsed: (IN, IN, IN, OUT, INOUT, )
Test passed:true
Parsed: IN[13]
Test passed:true
Parsed: IN[0]
Test passed:true
Parsed: IN[-2]
Test passed:false
Parse failed
Remaining unparsed: 'in[1][2][3]'
Test passed:false
Parse failed
Remaining unparsed: 'in[3][3][3]'
Test passed:false
Parse failed
Remaining unparsed: '(in[3][3][3], out, in_out[0])'
Test passed:false
Parse failed
Remaining unparsed: '(in[3][3][3], out, in_out[0])'
Test passed:true
Parsed: (IN, OUT, )[13]
Test passed:false
Parse failed
Remaining unparsed: '(in, out)[13][0]'
Test passed:true
Test passed:true
Remaining unparsed: 'i n'
Test passed:true
Remaining unparsed: 'inout'
Test passed:true
Remaining unparsed: '()'
Test passed:true
Remaining unparsed: '(in)'
Test passed:true
Remaining unparsed: '(out)'
Test passed:true
Remaining unparsed: '(in_out)'
Test passed:true
Remaining unparsed: 'IN'
正如您所看到的,除了像in[1][2]
这样的链式数组维度之外,大多数事情都得到了正确的解析。麻烦的是我们通过在规则中引入“优先级”来解决歧义:
rScalarSpec = rTypeName | rTupleSpec;
rArraySpec = rScalarSpec >> '[' >> rNumericLiteral >> ']';
rTypeSpec = rArraySpec | rScalarSpec;
这意味着我们始终首先尝试预期数组维度,如果我们找不到,则只回退到标量类型规范。这是因为任何array-spec总是首先匹配为scalarspec,因此无法解析数组维度部分。
要修复多维案例,您可以尝试断言[
不遵循数组规范:
rArraySpec = rScalarSpec >> '[' >> rNumericLiteral >> ']' >> !qi::lit('[')
| rArraySpec >> '[' >> rNumericLiteral >> ']';
但是 - BOOM - 我们再次回到左递归(如果我们进入第二个分支,例如in[1][
)。
我想到了两个想法。
我想说删除AST中标量/数组规范之间的区别是非常有益的。如果标量被视为零秩数组,那只意味着我们总是可以将可选维度解析为相同的结果AST类型。
另一个想法或多或少继续沿着上面所示的道路前进,并且如果推测的标量规格后跟一个'['字符,则需要一直向下回溯。在(very long spec)[1][1][1][1][1][1][1][1][1][1]
等情况下,这会导致最糟糕的最坏情况。
让我实现喝咖啡休息后概述的第一个想法:)
此处TypeSpec始终带有(可能为空)维度集合:
namespace Ast {
enum class TypeName { IN, OUT, INOUT };
static inline std::ostream& operator<<(std::ostream& os, TypeName tn) {
switch(tn) {
case TypeName::IN: return os << "IN";
case TypeName::OUT: return os << "OUT";
case TypeName::INOUT: return os << "INOUT";
}
return os << "?";
}
struct TypeSpec;
using ScalarSpec = boost::make_recursive_variant<
TypeName,
std::vector<TypeSpec>
>::type;
struct TypeSpec {
ScalarSpec spec;
std::vector<unsigned> dim;
};
using TupleSpec = std::vector<TypeSpec>;
}
请注意,我们还通过使尺寸无符号来改进。语法将检查完整性不是0
。由于这个原因,一些“积极”的测试案例已经转移到“预期到失败”的案例中。
现在语法很简单:
rRank %= qi::uint_ [qi::_pass = (qi::_1 > 0)];
rTypeName = sTypeName;
rTupleSpec = '(' >> rTypeSpec >> +(',' >> rTypeSpec) >> ')';
rScalarSpec = rTypeName | rTupleSpec;
rTypeSpec = rScalarSpec >> *('[' >> rRank >> ']');
注意使用Phoenix声明数组维度不能为0的语义操作
这是现场演示,显示所有测试通过:
<强> Live On Coliru 强>
//#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/fusion/adapted.hpp>
/*
<numeric-literal> ::= integer
<type-name> ::= "in" | "out" | "in_out"
<array-type-spec> ::= <type-spec> "[" [<numeric-literal>] "]"
<tuple-type-spec> ::= "(" <type-spec> ("," <type-spec>)+ ")"
<type-spec> ::= <type-name> | <array-type-spec> | <tuple-type-spec>
*/
namespace Ast {
enum class TypeName { IN, OUT, INOUT };
static inline std::ostream& operator<<(std::ostream& os, TypeName tn) {
switch(tn) {
case TypeName::IN: return os << "IN";
case TypeName::OUT: return os << "OUT";
case TypeName::INOUT: return os << "INOUT";
}
return os << "?";
}
struct TypeSpec;
using ScalarSpec = boost::make_recursive_variant<
TypeName,
std::vector<TypeSpec>
>::type;
struct TypeSpec {
ScalarSpec spec;
std::vector<unsigned> dim;
};
using TupleSpec = std::vector<TypeSpec>;
}
BOOST_FUSION_ADAPT_STRUCT(Ast::TypeSpec, spec, dim)
// grammar:
namespace myGrammar {
namespace qi = boost::spirit::qi;
template <typename Iterator = char const *, typename Signature = Ast::TypeSpec()>
struct myRules : qi::grammar<Iterator, Signature> {
myRules() : myRules::base_type(start) {
rRank %= qi::uint_ [qi::_pass = (qi::_1 > 0)];
rTypeName = sTypeName;
rTupleSpec = '(' >> rTypeSpec >> +(',' >> rTypeSpec) >> ')';
rScalarSpec = rTypeName | rTupleSpec;
rTypeSpec = rScalarSpec >> *('[' >> rRank >> ']');
start = qi::skip(qi::space)[rTypeSpec >> qi::eoi];
BOOST_SPIRIT_DEBUG_NODES((start)(rTypeSpec)(rTypeName)(rScalarSpec)(rTypeSpec)(rRank))
}
private:
using Skipper = qi::space_type;
qi::rule<Iterator, Ast::TypeSpec()> start;
qi::rule<Iterator, Ast::ScalarSpec(), Skipper> rScalarSpec;
qi::rule<Iterator, Ast::TypeSpec(), Skipper> rTypeSpec;
qi::rule<Iterator, Ast::TupleSpec(), Skipper> rTupleSpec;
// implicit lexeme
qi::rule<Iterator, Ast::TypeName()> rTypeName;
qi::rule<Iterator, unsigned()> rRank;
// symbols
struct TypeName_r : qi::symbols<char, Ast::TypeName> {
TypeName_r() {
using Ast::TypeName;
add ("in", TypeName::IN)
("out", TypeName::OUT)
("in_out", TypeName::INOUT);
}
} sTypeName;
};
}
static inline std::ostream& operator<<(std::ostream& os, Ast::TypeSpec tn) {
struct {
std::ostream& _os;
void operator()(Ast::ScalarSpec const& ts) const {
apply_visitor(*this, ts);
}
void operator()(Ast::TypeName tn) const { std::cout << tn; }
void operator()(Ast::TupleSpec const& tss) const {
std::cout << "(";
for (auto const& ts: tss) {
(*this)(ts);
std::cout << ", ";
}
std::cout << ")";
}
void operator()(Ast::TypeSpec const& as) const {
(*this)(as.spec);
for (auto rank : as.dim)
std::cout << '[' << rank << ']';
}
} const dumper{os};
dumper(tn);
return os;
}
int main() {
using It = std::string::const_iterator;
myGrammar::myRules<It> const parser;
std::string const test_ok[] = {
"in",
"out",
"in_out",
"(in, out)",
"(out, in)",
"(in, in, in, out, in_out)",
"in[13]",
"in[1][2][3]",
"in[3][3][3]",
"(in[3][3][3], out, in_out[1])",
"(in[3][3][3], out, in_out[1])",
"(in, out)[13]",
"(in, out)[13][14]",
};
std::string const test_fail[] = {
"",
"i n",
"inout",
"()",
"(in)",
"(out)",
"(in_out)",
"IN",
"in[0]",
"in[-2]",
"(in[3][3][3], out, in_out[0])",
"(in[3][3][3], out, in_out[0])",
};
auto expect = [&](std::string const& sample, bool expected) {
It f = sample.begin(), l = sample.end();
Ast::TypeSpec spec;
bool ok = parse(f, l, parser, spec);
std::cout << "Test passed:" << std::boolalpha << (expected == ok) << "\n";
if (expected || (expected != ok)) {
if (ok) {
std::cout << "Parsed: " << spec << "\n";
} else {
std::cout << "Parse failed\n";
}
}
if (f!=l) {
std::cout << "Remaining unparsed: '" << std::string(f,l) << "'\n";
}
};
for (std::string const sample : test_ok) expect(sample, true);
for (std::string const sample : test_fail) expect(sample, false);
}
打印
Test passed:true
Parsed: IN
Test passed:true
Parsed: OUT
Test passed:true
Parsed: INOUT
Test passed:true
Parsed: (IN, OUT, )
Test passed:true
Parsed: (OUT, IN, )
Test passed:true
Parsed: (IN, IN, IN, OUT, INOUT, )
Test passed:true
Parsed: IN[13]
Test passed:true
Parsed: IN[1][2][3]
Test passed:true
Parsed: IN[3][3][3]
Test passed:true
Parsed: (IN[3][3][3], OUT, INOUT[1], )
Test passed:true
Parsed: (IN[3][3][3], OUT, INOUT[1], )
Test passed:true
Parsed: (IN, OUT, )[13]
Test passed:true
Parsed: (IN, OUT, )[13][14]
Test passed:true
Test passed:true
Remaining unparsed: 'i n'
Test passed:true
Remaining unparsed: 'inout'
Test passed:true
Remaining unparsed: '()'
Test passed:true
Remaining unparsed: '(in)'
Test passed:true
Remaining unparsed: '(out)'
Test passed:true
Remaining unparsed: '(in_out)'
Test passed:true
Remaining unparsed: 'IN'
Test passed:true
Remaining unparsed: 'in[0]'
Test passed:true
Remaining unparsed: 'in[-2]'
Test passed:true
Remaining unparsed: '(in[3][3][3], out, in_out[0])'
Test passed:true
Remaining unparsed: '(in[3][3][3], out, in_out[0])'