我需要在c++中加载和使用CSV文件数据。在这一点上，它实际上只是一个以逗号分隔的解析器(即不用担心转义新行和逗号)。主要需要的是逐行解析器，它将在每次调用方法时为下一行返回一个向量。
我发现这篇文章看起来很有前途: http://www.boost.org/doc/libs/1_35_0/libs/spirit/example/fundamental/list_parser.cpp
我从未使用过Boost's Spirit，但我愿意尝试一下。但前提是我忽略了一个更直接的解决方案。
当前回答
我有一个更快的解决方案，最初是针对这个问题的:
如何拉动不同弦的特定部分?
但它显然是关闭的。但我不会把它扔掉:
#include <iostream>
#include <string>
#include <regex>
std::string text = "\"4,\"\"3\"\",\"\"Mon May 11 03:17:40 UTC 2009\"\",\"\"kindle2\"\",\"\"tpryan\"\",\"\"TEXT HERE\"\"\";;;;";
int main()
{
std::regex r("(\".*\")(\".*\")(\".*\")(\".*\")(\".*\")(\".*\")(\".*\")(\".*\")(\".*\")(\".*\")");
std::smatch m;
std::regex_search(text, m, r);
std::cout<<"FOUND: "<<m[9]<<std::endl;
return 0;
}
只需根据索引从smatch集合中挑选出您想要的匹配项。 正则表达式是福气。
其他回答
如果可以的话，这是我简单快速的贡献。 没有提高。
接受分隔符和分隔符中的分隔符，只要成对或远离分隔符即可。
#include <iostream>
#include <vector>
#include <fstream>
std::vector<std::string> SplitCSV(const std::string &data, char separator, char delimiter)
{
std::vector<std::string> Values;
std::string Val = "";
bool VDel = false; // Is within delimiter?
size_t CDel = 0; // Delimiters counter within delimiters.
const char *C = data.c_str();
size_t P = 0;
do
{
if ((Val.length() == 0) && (C[P] == delimiter))
{
VDel = !VDel;
CDel = 0;
P++;
continue;
}
if (VDel)
{
if (C[P] == delimiter)
{
if (((CDel % 2) == 0) && ( (C[P+1] == separator) || (C[P+1] == 0) || (C[P+1] == '\n') || (C[P+1] == '\r') ))
{
VDel = false;
CDel = 0;
P++;
continue;
}
else
CDel++;
}
}
else
{
if (C[P] == separator)
{
Values.push_back(Val);
Val = "";
P++;
continue;
}
if ((C[P] == 0) || (C[P] == '\n') || (C[P] == '\r'))
break;
}
Val += C[P];
P++;
} while(P < data.length());
Values.push_back(Val);
return Values;
}
bool ReadCsv(const std::string &fname, std::vector<std::vector<std::string>> &data,
char separator = ',', char delimiter = '\"')
{
bool Ret = false;
std::ifstream FCsv(fname);
if (FCsv)
{
FCsv.seekg(0, FCsv.end);
size_t Siz = FCsv.tellg();
if (Siz > 0)
{
FCsv.seekg(0);
data.clear();
std::string Line;
while (getline(FCsv, Line, '\n'))
data.push_back(SplitCSV(Line, separator, delimiter));
Ret = true;
}
FCsv.close();
}
return Ret;
}
int main(int argc, char *argv[])
{
std::vector<std::vector<std::string>> Data;
ReadCsv("fsample.csv", Data);
return 0;
}
我的版本只使用标准c++ 11库。它很好地处理Excel CSV引用:
spam eggs,"foo,bar","""fizz buzz"""
1.23,4.567,-8.00E+09
代码是作为有限状态机编写的，每次只消耗一个字符。我认为这更容易解释。
#include <istream>
#include <string>
#include <vector>
enum class CSVState {
UnquotedField,
QuotedField,
QuotedQuote
};
std::vector<std::string> readCSVRow(const std::string &row) {
CSVState state = CSVState::UnquotedField;
std::vector<std::string> fields {""};
size_t i = 0; // index of the current field
for (char c : row) {
switch (state) {
case CSVState::UnquotedField:
switch (c) {
case ',': // end of field
fields.push_back(""); i++;
break;
case '"': state = CSVState::QuotedField;
break;
default: fields[i].push_back(c);
break; }
break;
case CSVState::QuotedField:
switch (c) {
case '"': state = CSVState::QuotedQuote;
break;
default: fields[i].push_back(c);
break; }
break;
case CSVState::QuotedQuote:
switch (c) {
case ',': // , after closing quote
fields.push_back(""); i++;
state = CSVState::UnquotedField;
break;
case '"': // "" -> "
fields[i].push_back('"');
state = CSVState::QuotedField;
break;
default: // end of quote
state = CSVState::UnquotedField;
break; }
break;
}
}
return fields;
}
/// Read CSV file, Excel dialect. Accept "quoted fields ""with quotes"""
std::vector<std::vector<std::string>> readCSV(std::istream &in) {
std::vector<std::vector<std::string>> table;
std::string row;
while (!in.eof()) {
std::getline(in, row);
if (in.bad() || in.fail()) {
break;
}
auto fields = readCSVRow(row);
table.push_back(fields);
}
return table;
}
使用Boost Tokenizer的解决方案:
std::vector<std::string> vec;
using namespace boost;
tokenizer<escaped_list_separator<char> > tk(
line, escaped_list_separator<char>('\\', ',', '\"'));
for (tokenizer<escaped_list_separator<char> >::iterator i(tk.begin());
i!=tk.end();++i)
{
vec.push_back(*i);
}
另一种快速简单的方法是使用Boost。I / O:融合
#include <iostream>
#include <sstream>
#include <boost/fusion/adapted/boost_tuple.hpp>
#include <boost/fusion/sequence/io.hpp>
namespace fusion = boost::fusion;
struct CsvString
{
std::string value;
// Stop reading a string once a CSV delimeter is encountered.
friend std::istream& operator>>(std::istream& s, CsvString& v) {
v.value.clear();
for(;;) {
auto c = s.peek();
if(std::istream::traits_type::eof() == c || ',' == c || '\n' == c)
break;
v.value.push_back(c);
s.get();
}
return s;
}
friend std::ostream& operator<<(std::ostream& s, CsvString const& v) {
return s << v.value;
}
};
int main() {
std::stringstream input("abc,123,true,3.14\n"
"def,456,false,2.718\n");
typedef boost::tuple<CsvString, int, bool, double> CsvRow;
using fusion::operator<<;
std::cout << std::boolalpha;
using fusion::operator>>;
input >> std::boolalpha;
input >> fusion::tuple_open("") >> fusion::tuple_close("\n") >> fusion::tuple_delimiter(',');
for(CsvRow row; input >> row;)
std::cout << row << '\n';
}
输出:
(abc 123 true 3.14)
(def 456 false 2.718)
你可以在escaped_list_separator中使用Boost Tokenizer。
Escaped_list_separator解析csv的超集。Boost::记号赋予器
这只使用Boost标记器头文件，不需要链接到Boost库。
下面是一个例子，(详情请参阅c++中使用Boost Tokenizer解析CSV文件或Boost:: Tokenizer):
#include <iostream> // cout, endl
#include <fstream> // fstream
#include <vector>
#include <string>
#include <algorithm> // copy
#include <iterator> // ostream_operator
#include <boost/tokenizer.hpp>
int main()
{
using namespace std;
using namespace boost;
string data("data.csv");
ifstream in(data.c_str());
if (!in.is_open()) return 1;
typedef tokenizer< escaped_list_separator<char> > Tokenizer;
vector< string > vec;
string line;
while (getline(in,line))
{
Tokenizer tok(line);
vec.assign(tok.begin(),tok.end());
// vector now contains strings from one row, output to cout here
copy(vec.begin(), vec.end(), ostream_iterator<string>(cout, "|"));
cout << "\n----------------------" << endl;
}
}
