我有这个csv行
std::string s = R"(1997,Ford,E350,"ac, abs, moon","some "rusty" parts",3000.00)";
我可以使用boost::tokenizer
解析它:
typedef boost::tokenizer< boost::escaped_list_separator<char> , std::string::const_iterator, std::string> Tokenizer;
boost::escaped_list_separator<char> seps('\\', ',', '\"');
Tokenizer tok(s, seps);
for (auto i : tok)
{
std::cout << i << std::endl;
}
它是正确的,除了令牌“生锈”应该有双引号被剥离。
这是我尝试使用boost :: spirit
boost::spirit::classic::rule<> list_csv_item = !(boost::spirit::classic::confix_p('\"', *boost::spirit::classic::c_escape_ch_p, '\"') | boost::spirit::classic::longest_d[boost::spirit::classic::real_p | boost::spirit::classic::int_p]);
std::vector<std::string> vec_item;
std::vector<std::string> vec_list;
boost::spirit::classic::rule<> list_csv = boost::spirit::classic::list_p(list_csv_item[boost::spirit::classic::push_back_a(vec_item)],',')[boost::spirit::classic::push_back_a(vec_list)];
boost::spirit::classic::parse_info<> result = parse(s.c_str(), list_csv);
if (result.hit)
{
for (auto i : vec_item)
{
cout << i << endl;
}
}
问题:
不起作用,仅打印第一个令牌
为什么要提升::精神::经典?找不到使用Spirit V2的例子
设置很残酷..但我可以忍受这个
**我真的想使用boost::spirit
,因为它往往很快
预期产出:
1997
Ford
E350
ac, abs, moon
some "rusty" parts
3000.00
答案 0 :(得分:9)
有关解析(可选)引用分隔字段的背景信息,包括不同的引号字符(
'
,"
),请参阅此处:对于非常非常非常完整的示例,完整支持部分引用的值和
splitInto(input, output, ' ');
采用'任意'输出容器和分隔符表达式的方法,请参见此处:
解决您的确切问题,假设 引用或未加引号的字段( 字段值中没有部分引号<)>,使用Spirit V2:
让我们采用可能有效的最简单的“抽象数据类型”:
using Column = std::string;
using Columns = std::vector<Column>;
using CsvLine = Columns;
using CsvFile = std::vector<CsvLine>;
重复的双引号转义一个双引号语义(正如我在评论中指出的那样),你应该可以使用类似的东西:
static const char colsep = ',';
start = -line % eol;
line = column % colsep;
column = quoted | *~char_(colsep);
quoted = '"' >> *("\"\"" | ~char_('"')) >> '"';
以下完整的测试程序打印
[1997][Ford][E350][ac, abs, moon][rusty][3001.00]
(注意BOOST_SPIRIT_DEBUG定义以便于调试)。见 Live on Coliru
//#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
namespace qi = boost::spirit::qi;
using Column = std::string;
using Columns = std::vector<Column>;
using CsvLine = Columns;
using CsvFile = std::vector<CsvLine>;
template <typename It>
struct CsvGrammar : qi::grammar<It, CsvFile(), qi::blank_type>
{
CsvGrammar() : CsvGrammar::base_type(start)
{
using namespace qi;
static const char colsep = ',';
start = -line % eol;
line = column % colsep;
column = quoted | *~char_(colsep);
quoted = '"' >> *("\"\"" | ~char_('"')) >> '"';
BOOST_SPIRIT_DEBUG_NODES((start)(line)(column)(quoted));
}
private:
qi::rule<It, CsvFile(), qi::blank_type> start;
qi::rule<It, CsvLine(), qi::blank_type> line;
qi::rule<It, Column(), qi::blank_type> column;
qi::rule<It, std::string()> quoted;
};
int main()
{
const std::string s = R"(1997,Ford,E350,"ac, abs, moon","""rusty""",3001.00)";
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(auto& line : parsed) {
for(auto& col : line)
std::cout << '[' << col << ']';
std::cout << std::endl;
}
} else
{
std::cout << "Parse failed\n";
}
if (f!=l)
std::cout << "Remaining unparsed: '" << std::string(f,l) << "'\n";
}
答案 1 :(得分:5)
Sehe的帖子看起来比我的更干净,但是我把它放在一起有点,所以这里反正:
#include <boost/tokenizer.hpp>
#include <boost/spirit/include/qi.hpp>
namespace qi = boost::spirit::qi;
int main() {
const std::string s = R"(1997,Ford,E350,"ac, abs, moon",""rusty"",3000.00)";
// Tokenizer
typedef boost::tokenizer< boost::escaped_list_separator<char> , std::string::const_iterator, std::string> Tokenizer;
boost::escaped_list_separator<char> seps('\\', ',', '\"');
Tokenizer tok(s, seps);
for (auto i : tok)
std::cout << i << "\n";
std::cout << "\n";
// Boost Spirit Qi
qi::rule<std::string::const_iterator, std::string()> quoted_string = '"' >> *(qi::char_ - '"') >> '"';
qi::rule<std::string::const_iterator, std::string()> valid_characters = qi::char_ - '"' - ',';
qi::rule<std::string::const_iterator, std::string()> item = *(quoted_string | valid_characters );
qi::rule<std::string::const_iterator, std::vector<std::string>()> csv_parser = item % ',';
std::string::const_iterator s_begin = s.begin();
std::string::const_iterator s_end = s.end();
std::vector<std::string> result;
bool r = boost::spirit::qi::parse(s_begin, s_end, csv_parser, result);
assert(r == true);
assert(s_begin == s_end);
for (auto i : result)
std::cout << i << std::endl;
std::cout << "\n";
}
这输出:
1997
Ford
E350
ac, abs, moon
rusty
3000.00
1997
Ford
E350
ac, abs, moon
rusty
3000.00
值得注意的事情:这不会实现完整的CSV解析器。您还需要查看转义字符或实现所需的任何其他内容。
:如果你正在查看文档,那么你知道,在Qi中,'a'
相当于boost::spirit::qi::lit('a')
而"abc"
是等价的到boost::spirit::qi::lit("abc")
。
关于双引号:因此,正如Sehe在上面的评论中指出的那样,输入文本中""
周围的规则意味着什么并不直接。如果您希望""
不在引用字符串中的所有实例都转换为"
,那么以下内容就可以了。
qi::rule<std::string::const_iterator, std::string()> double_quote_char = "\"\"" >> qi::attr('"');
qi::rule<std::string::const_iterator, std::string()> item = *(double_quote_char | quoted_string | valid_characters );