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。
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
当你使用boost::spirit这样漂亮的东西时,你应该感到自豪
这里我的一个解析器的尝试(几乎)符合这个链接的CSV规范(我不需要在字段中换行)。逗号周围的空格也被省略了)。
在你克服了编译这段代码需要等待10秒的令人震惊的经历之后:),你就可以坐下来享受了。
// csvparser.cpp
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>
#include <iostream>
#include <string>
namespace qi = boost::spirit::qi;
namespace bascii = boost::spirit::ascii;
template <typename Iterator>
struct csv_parser : qi::grammar<Iterator, std::vector<std::string>(),
bascii::space_type>
{
qi::rule<Iterator, char() > COMMA;
qi::rule<Iterator, char() > DDQUOTE;
qi::rule<Iterator, std::string(), bascii::space_type > non_escaped;
qi::rule<Iterator, std::string(), bascii::space_type > escaped;
qi::rule<Iterator, std::string(), bascii::space_type > field;
qi::rule<Iterator, std::vector<std::string>(), bascii::space_type > start;
csv_parser() : csv_parser::base_type(start)
{
using namespace qi;
using qi::lit;
using qi::lexeme;
using bascii::char_;
start = field % ',';
field = escaped | non_escaped;
escaped = lexeme['"' >> *( char_ -(char_('"') | ',') | COMMA | DDQUOTE) >> '"'];
non_escaped = lexeme[ *( char_ -(char_('"') | ',') ) ];
DDQUOTE = lit("\"\"") [_val = '"'];
COMMA = lit(",") [_val = ','];
}
};
int main()
{
std::cout << "Enter CSV lines [empty] to quit\n";
using bascii::space;
typedef std::string::const_iterator iterator_type;
typedef csv_parser<iterator_type> csv_parser;
csv_parser grammar;
std::string str;
int fid;
while (getline(std::cin, str))
{
fid = 0;
if (str.empty())
break;
std::vector<std::string> csv;
std::string::const_iterator it_beg = str.begin();
std::string::const_iterator it_end = str.end();
bool r = phrase_parse(it_beg, it_end, grammar, space, csv);
if (r && it_beg == it_end)
{
std::cout << "Parsing succeeded\n";
for (auto& field: csv)
{
std::cout << "field " << ++fid << ": " << field << std::endl;
}
}
else
{
std::cout << "Parsing failed\n";
}
}
return 0;
}
编译:
make csvparser
测试(例子摘自维基百科):
./csvparser
Enter CSV lines [empty] to quit
1999,Chevy,"Venture ""Extended Edition, Very Large""",,5000.00
Parsing succeeded
field 1: 1999
field 2: Chevy
field 3: Venture "Extended Edition, Very Large"
field 4:
field 5: 5000.00
1999,Chevy,"Venture ""Extended Edition, Very Large""",,5000.00"
Parsing failed
其他回答
如果您所需要的只是加载一个双精度数据文件(没有整数,没有文本),那么这里有一个随时可用的函数。
#include <sstream>
#include <fstream>
#include <iterator>
#include <string>
#include <vector>
#include <algorithm>
using namespace std;
/**
* Parse a CSV data file and fill the 2d STL vector "data".
* Limits: only "pure datas" of doubles, not encapsulated by " and without \n inside.
* Further no formatting in the data (e.g. scientific notation)
* It however handles both dots and commas as decimal separators and removes thousand separator.
*
* returnCodes[0]: file access 0-> ok 1-> not able to read; 2-> decimal separator equal to comma separator
* returnCodes[1]: number of records
* returnCodes[2]: number of fields. -1 If rows have different field size
*
*/
vector<int>
readCsvData (vector <vector <double>>& data, const string& filename, const string& delimiter, const string& decseparator){
int vv[3] = { 0,0,0 };
vector<int> returnCodes(&vv[0], &vv[0]+3);
string rowstring, stringtoken;
double doubletoken;
int rowcount=0;
int fieldcount=0;
data.clear();
ifstream iFile(filename, ios_base::in);
if (!iFile.is_open()){
returnCodes[0] = 1;
return returnCodes;
}
while (getline(iFile, rowstring)) {
if (rowstring=="") continue; // empty line
rowcount ++; //let's start with 1
if(delimiter == decseparator){
returnCodes[0] = 2;
return returnCodes;
}
if(decseparator != "."){
// remove dots (used as thousand separators)
string::iterator end_pos = remove(rowstring.begin(), rowstring.end(), '.');
rowstring.erase(end_pos, rowstring.end());
// replace decimal separator with dots.
replace(rowstring.begin(), rowstring.end(),decseparator.c_str()[0], '.');
} else {
// remove commas (used as thousand separators)
string::iterator end_pos = remove(rowstring.begin(), rowstring.end(), ',');
rowstring.erase(end_pos, rowstring.end());
}
// tokenize..
vector<double> tokens;
// Skip delimiters at beginning.
string::size_type lastPos = rowstring.find_first_not_of(delimiter, 0);
// Find first "non-delimiter".
string::size_type pos = rowstring.find_first_of(delimiter, lastPos);
while (string::npos != pos || string::npos != lastPos){
// Found a token, convert it to double add it to the vector.
stringtoken = rowstring.substr(lastPos, pos - lastPos);
if (stringtoken == "") {
tokens.push_back(0.0);
} else {
istringstream totalSString(stringtoken);
totalSString >> doubletoken;
tokens.push_back(doubletoken);
}
// Skip delimiters. Note the "not_of"
lastPos = rowstring.find_first_not_of(delimiter, pos);
// Find next "non-delimiter"
pos = rowstring.find_first_of(delimiter, lastPos);
}
if(rowcount == 1){
fieldcount = tokens.size();
returnCodes[2] = tokens.size();
} else {
if ( tokens.size() != fieldcount){
returnCodes[2] = -1;
}
}
data.push_back(tokens);
}
iFile.close();
returnCodes[1] = rowcount;
return returnCodes;
}
由于我现在不习惯boost,我将建议一个更简单的解决方案。假设您的.csv文件有100行,每行有10个数字,用“,”分隔。你可以用下面的代码以数组的形式加载这个数据:
#include <iostream>
#include <fstream>
#include <sstream>
#include <string>
using namespace std;
int main()
{
int A[100][10];
ifstream ifs;
ifs.open("name_of_file.csv");
string s1;
char c;
for(int k=0; k<100; k++)
{
getline(ifs,s1);
stringstream stream(s1);
int j=0;
while(1)
{
stream >>A[k][j];
stream >> c;
j++;
if(!stream) {break;}
}
}
}
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;
}
如果你确实关心正确解析CSV,这将做它…相对较慢,因为它一次只处理一个字符。
void ParseCSV(const string& csvSource, vector<vector<string> >& lines)
{
bool inQuote(false);
bool newLine(false);
string field;
lines.clear();
vector<string> line;
string::const_iterator aChar = csvSource.begin();
while (aChar != csvSource.end())
{
switch (*aChar)
{
case '"':
newLine = false;
inQuote = !inQuote;
break;
case ',':
newLine = false;
if (inQuote == true)
{
field += *aChar;
}
else
{
line.push_back(field);
field.clear();
}
break;
case '\n':
case '\r':
if (inQuote == true)
{
field += *aChar;
}
else
{
if (newLine == false)
{
line.push_back(field);
lines.push_back(line);
field.clear();
line.clear();
newLine = true;
}
}
break;
default:
newLine = false;
field.push_back(*aChar);
break;
}
aChar++;
}
if (field.size())
line.push_back(field);
if (line.size())
lines.push_back(line);
}
@sastanin的解决方案的一个小版本,以便它可以处理引号中的换行。
std::vector<std::vector<std::string>> readCSV(std::istream &in) {
std::vector<std::vector<std::string>> table;
while (!in.eof()) {
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;
case '\n': // newline
table.push_back(fields);
state = CSVState::UnquotedField;
fields = vector<string>{""};
i = 0;
default: // end of quote
state = CSVState::UnquotedField;
break; }
break;
}
}
}
return table;
}