如何使这个递归规则工作
How do I get this recursive rule to work?
我想解析（在第一个例子中，只识别，保留符号）LaTeX数学。现在，我在超级和下标以及大括号的组合方面遇到了问题（例如，a^{bc}及其组合，我的基本a^b工作得很好）。一个最小的例子（尽可能短，同时保持可读性）：
#include <iostream>
using std::cout;
#include <string>
using std::string;
#include <boost/spirit/home/x3.hpp>
namespace x3 = boost::spirit::x3;
using x3::space;
using x3::char_;
using x3::lit;
using x3::repeat;
x3::rule<struct scripts, string> scripts = "super- and subscripts";
x3::rule<struct braced_thing, string> braced_thing = "thing optionaly surrounded by curly braces";
x3::rule<struct superscript, string> superscript = "superscript";
x3::rule<struct subscript, string> subscript = "subscript";
// main rule: any number of items with or without braces
auto const scripts_def = *braced_thing;
// second level main rule: optional braces, and any number of characters or sub/superscripts
auto const braced_thing_def = -lit('{') >> *(subscript | superscript | repeat(1)[(char_ - "_^{}")]) >> -lit('}');
// superscript: things of the form a^b where a and b can be surrounded by curly braces
auto const superscript_def = braced_thing >> '^' >> braced_thing;
// subscript: things of the form a_b where a and b can be surrounded by curly braces
auto const subscript_def = braced_thing >> '_' >> braced_thing;
BOOST_SPIRIT_DEFINE(scripts)
BOOST_SPIRIT_DEFINE(braced_thing)
BOOST_SPIRIT_DEFINE(superscript)
BOOST_SPIRIT_DEFINE(subscript)
int main()
{
const string input = "a^{b_x y}_z {v_x}^{{x^z}_y}";
string output; // will only contain the characters as the grammar is defined above
auto first = input.begin();
auto last = input.end();
const bool result = x3::phrase_parse(first, last,
scripts,
space,
output);
if(first != last)
std::cout << "partial match only:n" << output << 'n';
else if(!result)
std::cout << "parse failed!n";
else
std::cout << "parsing succeeded:n" << output << 'n';
}
它也可在Coliru上使用。
问题是，这个segfault（我相信有明显的原因），我没有其他方法，好吧，用…表达式语法来表达这个。
我还没有考虑@cv_and_he的建议，而是亲自调试语法。我想出了这个：
auto token = lexeme [ +~char_("_^{} trn") ];
auto simple = '{' >> sequence >> '}' | token;
auto expr = lexeme [ simple % char_("_^") ];
auto sequence_def = expr % +space;
给我带来的基本上是对实际语法的逐步反思/想象。
我花了两次时间思考获得
"a b"解析的正确方法（起初我"破解"了char_(" _^")中的另一个下标运算符，但我得到的印象是，它不会像你预期的那样导致AST。线索是你在空间中使用了队长）
目前，还没有AST，但我们只是使用.."收获"匹配的原始字符串。。x3::raw[...]。
活大肠杆菌
//#define BOOST_SPIRIT_X3_DEBUG
#include <iostream>
#include <string>
#include <boost/spirit/home/x3.hpp>
namespace x3 = boost::spirit::x3;
namespace grammar {
using namespace x3;
rule<struct _s> sequence { "sequence" };
auto simple = rule<struct _s> {"simple"} = '{' >> sequence >> '}' | lexeme [ +~char_("_^{} trn") ];
auto expr = rule<struct _e> {"expr"} = lexeme [ simple % char_("_^") ];
auto sequence_def = expr % +space;
BOOST_SPIRIT_DEFINE(sequence)
}
int main() {
for (const std::string input : {
"a",
"a^b", "a_b", "a b",
"{a}^{b}", "{a}_{b}", "{a} {b}",
"a^{b_x y}",
"a^{b_x y}_z {v_x}^{{x^z}_y}"
})
{
std::string output; // will only contain the characters as the grammar is defined above
auto first = input.begin(), last = input.end();
bool result = x3::parse(first, last, x3::raw[grammar::sequence], output);
if (result)
std::cout << "Parse success: '" << output << "'n";
else
std::cout << "parse failed!n";
if (last!=first)
std::cout << "remaining unparsed: '" << std::string(first, last) << "'n";
}
}
输出：
Parse success: 'a'
Parse success: 'a^b'
Parse success: 'a_b'
Parse success: 'a b'
Parse success: '{a}^{b}'
Parse success: '{a}_{b}'
Parse success: '{a} {b}'
Parse success: 'a^{b_x y}'
Parse success: 'a^{b_x y}_z {v_x}^{{x^z}_y}'
启用调试信息的输出：
<sequence>
<try>a</try>
<expr>
<try>a</try>
<simple>
<try>a</try>
<success></success>
</simple>
<success></success>
</expr>
<success></success>
</sequence>
Parse success: 'a'
<sequence>
<try>a^b</try>
<expr>
<try>a^b</try>
<simple>
<try>a^b</try>
<success>^b</success>
</simple>
<simple>
<try>b</try>
<success></success>
</simple>
<success></success>
</expr>
<success></success>
</sequence>
Parse success: 'a^b'
<sequence>
<try>a_b</try>
<expr>
<try>a_b</try>
<simple>
<try>a_b</try>
<success>_b</success>
</simple>
<simple>
<try>b</try>
<success></success>
</simple>
<success></success>
</expr>
<success></success>
</sequence>
Parse success: 'a_b'
<sequence>
<try>a b</try>
<expr>
<try>a b</try>
<simple>
<try>a b</try>
<success> b</success>
</simple>
<success> b</success>
</expr>
<expr>
<try>b</try>
<simple>
<try>b</try>
<success></success>
</simple>
<success></success>
</expr>
<success></success>
</sequence>
Parse success: 'a b'
<sequence>
<try>{a}^{b}</try>
<expr>
<try>{a}^{b}</try>
<simple>
<try>{a}^{b}</try>
<sequence>
<try>a}^{b}</try>
<expr>
<try>a}^{b}</try>
<simple>
<try>a}^{b}</try>
<success>}^{b}</success>
</simple>
<success>}^{b}</success>
</expr>
<success>}^{b}</success>
</sequence>
<success>^{b}</success>
</simple>
<simple>
<try>{b}</try>
<sequence>
<try>b}</try>
<expr>
<try>b}</try>
<simple>
<try>b}</try>
<success>}</success>
</simple>
<success>}</success>
</expr>
<success>}</success>
</sequence>
<success></success>
</simple>
<success></success>
</expr>
<success></success>
</sequence>
Parse success: '{a}^{b}'
<sequence>
<try>{a}_{b}</try>
<expr>
<try>{a}_{b}</try>
<simple>
<try>{a}_{b}</try>
<sequence>
<try>a}_{b}</try>
<expr>
<try>a}_{b}</try>
<simple>
<try>a}_{b}</try>
<success>}_{b}</success>
</simple>
<success>}_{b}</success>
</expr>
<success>}_{b}</success>
</sequence>
<success>_{b}</success>
</simple>
<simple>
<try>{b}</try>
<sequence>
<try>b}</try>
<expr>
<try>b}</try>
<simple>
<try>b}</try>
<success>}</success>
</simple>
<success>}</success>
</expr>
<success>}</success>
</sequence>
<success></success>
</simple>
<success></success>
</expr>
<success></success>
</sequence>
Parse success: '{a}_{b}'
<sequence>
<try>{a} {b}</try>
<expr>
<try>{a} {b}</try>
<simple>
<try>{a} {b}</try>
<sequence>
<try>a} {b}</try>
<expr>
<try>a} {b}</try>
<simple>
<try>a} {b}</try>
<success>} {b}</success>
</simple>
<success>} {b}</success>
</expr>
<success>} {b}</success>
</sequence>
<success> {b}</success>
</simple>
<success> {b}</success>
</expr>
<expr>
<try>{b}</try>
<simple>
<try>{b}</try>
<sequence>
<try>b}</try>
<expr>
<try>b}</try>
<simple>
<try>b}</try>
<success>}</success>
</simple>
<success>}</success>
</expr>
<success>}</success>
</sequence>
<success></success>
</simple>
<success></success>
</expr>
<success></success>
</sequence>
Parse success: '{a} {b}'
<sequence>
<try>a^{b_x y}</try>
<expr>
<try>a^{b_x y}</try>
<simple>
<try>a^{b_x y}</try>
<success>^{b_x y}</success>
</simple>
<simple>
<try>{b_x y}</try>
<sequence>
<try>b_x y}</try>
<expr>
<try>b_x y}</try>
<simple>
<try>b_x y}</try>
<success>_x y}</success>
</simple>
<simple>
<try>x y}</try>
<success> y}</success>
</simple>
<success> y}</success>
</expr>
<expr>
<try>y}</try>
<simple>
<try>y}</try>
<success>}</success>
</simple>
<success>}</success>
</expr>
<success>}</success>
</sequence>
<success></success>
</simple>
<success></success>
</expr>
<success></success>
</sequence>
Parse success: 'a^{b_x y}'
<sequence>
<try>a^{b_x y}_z {v_x}^{{</try>
<expr>
<try>a^{b_x y}_z {v_x}^{{</try>
<simple>
<try>a^{b_x y}_z {v_x}^{{</try>
<success>^{b_x y}_z {v_x}^{{x</success>
</simple>
<simple>
<try>{b_x y}_z {v_x}^{{x^</try>
<sequence>
<try>b_x y}_z {v_x}^{{x^z</try>
<expr>
<try>b_x y}_z {v_x}^{{x^z</try>
<simple>
<try>b_x y}_z {v_x}^{{x^z</try>
<success>_x y}_z {v_x}^{{x^z}</success>
</simple>
<simple>
<try>x y}_z {v_x}^{{x^z}_</try>
<success> y}_z {v_x}^{{x^z}_y</success>
</simple>
<success> y}_z {v_x}^{{x^z}_y</success>
</expr>
<expr>
<try>y}_z {v_x}^{{x^z}_y}</try>
<simple>
<try>y}_z {v_x}^{{x^z}_y}</try>
<success>}_z {v_x}^{{x^z}_y}</success>
</simple>
<success>}_z {v_x}^{{x^z}_y}</success>
</expr>
<success>}_z {v_x}^{{x^z}_y}</success>
</sequence>
<success>_z {v_x}^{{x^z}_y}</success>
</simple>
<simple>
<try>z {v_x}^{{x^z}_y}</try>
<success> {v_x}^{{x^z}_y}</success>
</simple>
<success> {v_x}^{{x^z}_y}</success>
</expr>
<expr>
<try>{v_x}^{{x^z}_y}</try>
<simple>
<try>{v_x}^{{x^z}_y}</try>
<sequence>
<try>v_x}^{{x^z}_y}</try>
<expr>
<try>v_x}^{{x^z}_y}</try>
<simple>
<try>v_x}^{{x^z}_y}</try>
<success>_x}^{{x^z}_y}</success>
</simple>
<simple>
<try>x}^{{x^z}_y}</try>
<success>}^{{x^z}_y}</success>
</simple>
<success>}^{{x^z}_y}</success>
</expr>
<success>}^{{x^z}_y}</success>
</sequence>
<success>^{{x^z}_y}</success>
</simple>
<simple>
<try>{{x^z}_y}</try>
<sequence>
<try>{x^z}_y}</try>
<expr>
<try>{x^z}_y}</try>
<simple>
<try>{x^z}_y}</try>
<sequence>
<try>x^z}_y}</try>
<expr>
<try>x^z}_y}</try>
<simple>
<try>x^z}_y}</try>
<success>^z}_y}</success>
</simple>
<simple>
<try>z}_y}</try>
<success>}_y}</success>
</simple>
<success>}_y}</success>
</expr>
<success>}_y}</success>
</sequence>
<success>_y}</success>
</simple>
<simple>
<try>y}</try>
<success>}</success>
</simple>
<success>}</success>
</expr>
<success>}</success>
</sequence>
<success></success>
</simple>
<success></success>
</expr>
<success></success>
</sequence>
Parse success: 'a^{b_x y}_z {v_x}^{{x^z}_y}'
相关文章：
- QSqlquery prepare(）和bindvalue(）不工作
- 此代码是否违反一个定义规则
- 导入库可以跨dll版本工作吗
- 生成文件不对文件使用隐式规则
- 以螺旋方式打印矩阵的程序.(工作不好）
- 对象指针在c++中是如何工作的
- 为什么在Windows上的VS 2019和Clang 9中"size_t"在没有标题的情况下工作
- VSOMEIP-2个设备之间的通信(TCP/UDP）不工作
- 为字符串中每 N 个字符插入空格的函数没有按照我认为的方式工作？
- C++为线程工作动态地分割例程
- 为什么我的 std::ref 无法按预期工作?
- 变量可能尚未初始化[MIRA 2012规则9.1，强制性]
- 布尔比较运算符是如何在C++中工作的
- 静态结构和一个定义规则
- SampleConsensusPrerejective(ext.RANSAC）是如何真正工作的
- 不确定要在我的main中放入什么才能使我的代码正常工作
- 已签名/未签名的别名规则是否按预期工作
- 如何使这个递归规则工作
- 为什么RegSetValueEx工作，即使我打破了关于会计NUL终止长度的规则
- 当二进制运算符两边的签名不同时，提升规则如何工作
