我想有效地解析大型类CSV文件,这些文件的列顺序是我在运行时得到的。使用Spirit Qi,我将使用lazy
辅助解析器解析每个字段,该解析器将在运行时选择要应用于每列的特定于列的解析器。但是X3似乎没有lazy
(尽管它是listed in documentation)。在阅读SO的建议之后,我决定编写一个自定义解析器。
它结果非常好,但现在我注意到我并不需要将pos
变量暴露在自定义解析器本身之外的任何地方。我已经尝试将它放入自定义解析器本身并开始收到编译器错误,指出column_value_parser
对象是只读的。我可以以某种方式将pos
放入解析器结构吗?
获得编译时错误的简化代码,注释掉了我的工作版本部分:
#include <iostream>
#include <variant>
#include <boost/spirit/home/x3.hpp>
#include <boost/spirit/home/support.hpp>
namespace helpers {
// https://bitbashing.io/std-visit.html
template<class... Ts> struct overloaded : Ts... { using Ts::operator()...; };
template<class... Ts> overloaded(Ts...) -> overloaded<Ts...>;
}
auto const unquoted_text_field = *(boost::spirit::x3::char_ - ',' - boost::spirit::x3::eol);
struct text { };
struct integer { };
struct real { };
struct skip { };
typedef std::variant<text, integer, real, skip> column_variant;
struct column_value_parser : boost::spirit::x3::parser<column_value_parser> {
typedef boost::spirit::unused_type attribute_type;
std::vector<column_variant>& columns;
// size_t& pos;
size_t pos;
// column_value_parser(std::vector<column_variant>& columns, size_t& pos)
column_value_parser(std::vector<column_variant>& columns)
: columns(columns)
// , pos(pos)
, pos(0)
{ }
template<typename It, typename Ctx, typename Other, typename Attr>
bool parse(It& f, It l, Ctx& ctx, Other const& other, Attr& attr) const {
auto const saved_f = f;
bool successful = false;
visit(
helpers::overloaded {
[&](skip const&) {
successful = boost::spirit::x3::parse(f, l, boost::spirit::x3::omit[unquoted_text_field]);
},
[&](text& c) {
std::string value;
successful = boost::spirit::x3::parse(f, l, unquoted_text_field, value);
if(successful) {
std::cout << "Text: " << value << '\n';
}
},
[&](integer& c) {
int value;
successful = boost::spirit::x3::parse(f, l, boost::spirit::x3::int_, value);
if(successful) {
std::cout << "Integer: " << value << '\n';
}
},
[&](real& c) {
double value;
successful = boost::spirit::x3::parse(f, l, boost::spirit::x3::double_, value);
if(successful) {
std::cout << "Real: " << value << '\n';
}
}
},
columns[pos]);
if(successful) {
pos = (pos + 1) % columns.size();
return true;
} else {
f = saved_f;
return false;
}
}
};
int main(int argc, char *argv[])
{
std::string input = "Hello,1,13.7,XXX\nWorld,2,1e3,YYY";
// Comes from external source.
std::vector<column_variant> columns = {text{}, integer{}, real{}, skip{}};
size_t pos = 0;
boost::spirit::x3::parse(
input.begin(), input.end(),
// (column_value_parser(columns, pos) % ',') % boost::spirit::x3::eol);
(column_value_parser(columns) % ',') % boost::spirit::x3::eol);
}
XY:我的目标是在具有少量RAM的机器上在合理的时间内解析~500 GB的伪CSV文件,转换为(大致)[行号,列名,值]的列表,然后存入。格式实际上比CSV更复杂:数据库转储格式化为......人性化的方式,列值实际上是几个小的子语言(例如日期或呃,类似于整个apache日志行填充到单个字段中的东西),而且我经常只提取每列的一个特定部分。不同的文件可能具有不同的列和不同的顺序,我只能通过解析包含原始查询的另一组文件来学习。值得庆幸的是,Spirit让它变得轻而易举......
答案 0 :(得分:3)
三个答案:
pos
成为mutable
成员x3::with<>
pos
可变<强> Live On Wandbox 强>
#include <iostream>
#include <variant>
#include <boost/spirit/home/x3.hpp>
#include <boost/spirit/home/support.hpp>
namespace helpers {
// https://bitbashing.io/std-visit.html
template<class... Ts> struct overloaded : Ts... { using Ts::operator()...; };
template<class... Ts> overloaded(Ts...) -> overloaded<Ts...>;
}
auto const unquoted_text_field = *(boost::spirit::x3::char_ - ',' - boost::spirit::x3::eol);
struct text { };
struct integer { };
struct real { };
struct skip { };
typedef std::variant<text, integer, real, skip> column_variant;
struct column_value_parser : boost::spirit::x3::parser<column_value_parser> {
typedef boost::spirit::unused_type attribute_type;
std::vector<column_variant>& columns;
size_t mutable pos = 0;
struct pos_tag;
column_value_parser(std::vector<column_variant>& columns)
: columns(columns)
{ }
template<typename It, typename Ctx, typename Other, typename Attr>
bool parse(It& f, It l, Ctx& /*ctx*/, Other const& /*other*/, Attr& /*attr*/) const {
auto const saved_f = f;
bool successful = false;
visit(
helpers::overloaded {
[&](skip const&) {
successful = boost::spirit::x3::parse(f, l, boost::spirit::x3::omit[unquoted_text_field]);
},
[&](text&) {
std::string value;
successful = boost::spirit::x3::parse(f, l, unquoted_text_field, value);
if(successful) {
std::cout << "Text: " << value << '\n';
}
},
[&](integer&) {
int value;
successful = boost::spirit::x3::parse(f, l, boost::spirit::x3::int_, value);
if(successful) {
std::cout << "Integer: " << value << '\n';
}
},
[&](real&) {
double value;
successful = boost::spirit::x3::parse(f, l, boost::spirit::x3::double_, value);
if(successful) {
std::cout << "Real: " << value << '\n';
}
}
},
columns[pos]);
if(successful) {
pos = (pos + 1) % columns.size();
return true;
} else {
f = saved_f;
return false;
}
}
};
int main() {
std::string input = "Hello,1,13.7,XXX\nWorld,2,1e3,YYY";
std::vector<column_variant> columns = {text{}, integer{}, real{}, skip{}};
boost::spirit::x3::parse(
input.begin(), input.end(),
(column_value_parser(columns) % ',') % boost::spirit::x3::eol);
}
x3::with<>
这是类似的,但有更好的(重新)入侵和封装:
<强> Live On Wandbox 强>
#include <iostream>
#include <variant>
#include <boost/spirit/home/x3.hpp>
#include <boost/spirit/home/support.hpp>
namespace helpers {
// https://bitbashing.io/std-visit.html
template<class... Ts> struct overloaded : Ts... { using Ts::operator()...; };
template<class... Ts> overloaded(Ts...) -> overloaded<Ts...>;
}
auto const unquoted_text_field = *(boost::spirit::x3::char_ - ',' - boost::spirit::x3::eol);
struct text { };
struct integer { };
struct real { };
struct skip { };
typedef std::variant<text, integer, real, skip> column_variant;
struct column_value_parser : boost::spirit::x3::parser<column_value_parser> {
typedef boost::spirit::unused_type attribute_type;
std::vector<column_variant>& columns;
column_value_parser(std::vector<column_variant>& columns)
: columns(columns)
{ }
template<typename It, typename Ctx, typename Other, typename Attr>
bool parse(It& f, It l, Ctx const& ctx, Other const& /*other*/, Attr& /*attr*/) const {
auto const saved_f = f;
bool successful = false;
size_t& pos = boost::spirit::x3::get<pos_tag>(ctx).value;
visit(
helpers::overloaded {
[&](skip const&) {
successful = boost::spirit::x3::parse(f, l, boost::spirit::x3::omit[unquoted_text_field]);
},
[&](text&) {
std::string value;
successful = boost::spirit::x3::parse(f, l, unquoted_text_field, value);
if(successful) {
std::cout << "Text: " << value << '\n';
}
},
[&](integer&) {
int value;
successful = boost::spirit::x3::parse(f, l, boost::spirit::x3::int_, value);
if(successful) {
std::cout << "Integer: " << value << '\n';
}
},
[&](real&) {
double value;
successful = boost::spirit::x3::parse(f, l, boost::spirit::x3::double_, value);
if(successful) {
std::cout << "Real: " << value << '\n';
}
}
},
columns[pos]);
if(successful) {
pos = (pos + 1) % columns.size();
return true;
} else {
f = saved_f;
return false;
}
}
template <typename T>
struct Mutable { T mutable value; };
struct pos_tag;
auto invoke() const {
return boost::spirit::x3::with<pos_tag>(Mutable<size_t>{}) [ *this ];
}
};
int main() {
std::string input = "Hello,1,13.7,XXX\nWorld,2,1e3,YYY";
std::vector<column_variant> columns = {text{}, integer{}, real{}, skip{}};
column_value_parser p(columns);
boost::spirit::x3::parse(
input.begin(), input.end(),
(p.invoke() % ',') % boost::spirit::x3::eol);
}
因为它在X3中更容易,我最喜欢的是按需生成解析器。
没有要求,这是我最简单的建议:
<强> Live On Wandbox 强>
#include <boost/spirit/home/x3.hpp>
namespace x3 = boost::spirit::x3;
namespace CSV {
struct text { };
struct integer { };
struct real { };
struct skip { };
auto const unquoted_text_field = *~x3::char_(",\n");
static inline auto as_parser(skip) { return x3::omit[unquoted_text_field]; }
static inline auto as_parser(text) { return unquoted_text_field; }
static inline auto as_parser(integer) { return x3::int_; }
static inline auto as_parser(real) { return x3::double_; }
template <typename... Spec>
static inline auto line_parser(Spec... spec) {
auto delim = ',' | &(x3::eoi | x3::eol);
return ((as_parser(spec) >> delim) >> ... >> x3::eps);
}
template <typename... Spec> static inline auto csv_parser(Spec... spec) {
return line_parser(spec...) % x3::eol;
}
}
#include <iostream>
#include <iomanip>
using namespace CSV;
int main() {
std::string const input = "Hello,1,13.7,XXX\nWorld,2,1e3,YYY";
auto f = begin(input), l = end(input);
auto p = csv_parser(text{}, integer{}, real{}, skip{});
if (parse(f, l, p)) {
std::cout << "Parsed\n";
} else {
std::cout << "Failed\n";
}
if (f!=l) {
std::cout << "Remaining: " << std::quoted(std::string(f,l)) << "\n";
}
}
启用了调试信息的版本:
<强> Live On Wandbox 强>
<line>
<try>Hello,1,13.7,XXX\nWor</try>
<CSV::text>
<try>Hello,1,13.7,XXX\nWor</try>
<success>,1,13.7,XXX\nWorld,2,</success>
</CSV::text>
<CSV::integer>
<try>1,13.7,XXX\nWorld,2,1</try>
<success>,13.7,XXX\nWorld,2,1e</success>
</CSV::integer>
<CSV::real>
<try>13.7,XXX\nWorld,2,1e3</try>
<success>,XXX\nWorld,2,1e3,YYY</success>
</CSV::real>
<CSV::skip>
<try>XXX\nWorld,2,1e3,YYY</try>
<success>\nWorld,2,1e3,YYY</success>
</CSV::skip>
<success>\nWorld,2,1e3,YYY</success>
</line>
<line>
<try>World,2,1e3,YYY</try>
<CSV::text>
<try>World,2,1e3,YYY</try>
<success>,2,1e3,YYY</success>
</CSV::text>
<CSV::integer>
<try>2,1e3,YYY</try>
<success>,1e3,YYY</success>
</CSV::integer>
<CSV::real>
<try>1e3,YYY</try>
<success>,YYY</success>
</CSV::real>
<CSV::skip>
<try>YYY</try>
<success></success>
</CSV::skip>
<success></success>
</line>
Parsed
对于任何mutable
,请注意副作用。例如。如果您有a | b
且a
包含column_value_parser
,则pos
会在a
1>}时回滚增加b
的副作用。失败,而Skip(1)
匹配。
简而言之,这会使您的解析功能不纯。