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
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;
}
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;
}
我写了一个很好的解析CSV文件的方法,我认为我应该把它作为一个答案:
#include <algorithm>
#include <fstream>
#include <iostream>
#include <stdlib.h>
#include <stdio.h>
struct CSVDict
{
std::vector< std::string > inputImages;
std::vector< double > inputLabels;
};
/**
\brief Splits the string
\param str String to split
\param delim Delimiter on the basis of which splitting is to be done
\return results Output in the form of vector of strings
*/
std::vector<std::string> stringSplit( const std::string &str, const std::string &delim )
{
std::vector<std::string> results;
for (size_t i = 0; i < str.length(); i++)
{
std::string tempString = "";
while ((str[i] != *delim.c_str()) && (i < str.length()))
{
tempString += str[i];
i++;
}
results.push_back(tempString);
}
return results;
}
/**
\brief Parse the supplied CSV File and obtain Row and Column information.
Assumptions:
1. Header information is in first row
2. Delimiters are only used to differentiate cell members
\param csvFileName The full path of the file to parse
\param inputColumns The string of input columns which contain the data to be used for further processing
\param inputLabels The string of input labels based on which further processing is to be done
\param delim The delimiters used in inputColumns and inputLabels
\return Vector of Vector of strings: Collection of rows and columns
*/
std::vector< CSVDict > parseCSVFile( const std::string &csvFileName, const std::string &inputColumns, const std::string &inputLabels, const std::string &delim )
{
std::vector< CSVDict > return_CSVDict;
std::vector< std::string > inputColumnsVec = stringSplit(inputColumns, delim), inputLabelsVec = stringSplit(inputLabels, delim);
std::vector< std::vector< std::string > > returnVector;
std::ifstream inFile(csvFileName.c_str());
int row = 0;
std::vector< size_t > inputColumnIndeces, inputLabelIndeces;
for (std::string line; std::getline(inFile, line, '\n');)
{
CSVDict tempDict;
std::vector< std::string > rowVec;
line.erase(std::remove(line.begin(), line.end(), '"'), line.end());
rowVec = stringSplit(line, delim);
// for the first row, record the indeces of the inputColumns and inputLabels
if (row == 0)
{
for (size_t i = 0; i < rowVec.size(); i++)
{
for (size_t j = 0; j < inputColumnsVec.size(); j++)
{
if (rowVec[i] == inputColumnsVec[j])
{
inputColumnIndeces.push_back(i);
}
}
for (size_t j = 0; j < inputLabelsVec.size(); j++)
{
if (rowVec[i] == inputLabelsVec[j])
{
inputLabelIndeces.push_back(i);
}
}
}
}
else
{
for (size_t i = 0; i < inputColumnIndeces.size(); i++)
{
tempDict.inputImages.push_back(rowVec[inputColumnIndeces[i]]);
}
for (size_t i = 0; i < inputLabelIndeces.size(); i++)
{
double test = std::atof(rowVec[inputLabelIndeces[i]].c_str());
tempDict.inputLabels.push_back(std::atof(rowVec[inputLabelIndeces[i]].c_str()));
}
return_CSVDict.push_back(tempDict);
}
row++;
}
return return_CSVDict;
}
这是一个旧线程,但它仍然在搜索结果的顶部,所以我添加我的解决方案使用std::stringstream和一个简单的字符串替换方法由Yves Baumes我在这里找到。
下面的例子将逐行读取文件,忽略以//开头的注释行,并将其他行解析为字符串、int和double的组合。Stringstream进行解析,但希望字段由空格分隔,因此我使用stringreplace首先将逗号转换为空格。它可以处理制表符,但不处理带引号的字符串。
坏的或丢失的输入被简单地忽略,这可能是好事,也可能不是好事,这取决于您的情况。
#include <string>
#include <sstream>
#include <fstream>
void StringReplace(std::string& str, const std::string& oldStr, const std::string& newStr)
// code by Yves Baumes
// http://stackoverflow.com/questions/1494399/how-do-i-search-find-and-replace-in-a-standard-string
{
size_t pos = 0;
while((pos = str.find(oldStr, pos)) != std::string::npos)
{
str.replace(pos, oldStr.length(), newStr);
pos += newStr.length();
}
}
void LoadCSV(std::string &filename) {
std::ifstream stream(filename);
std::string in_line;
std::string Field;
std::string Chan;
int ChanType;
double Scale;
int Import;
while (std::getline(stream, in_line)) {
StringReplace(in_line, ",", " ");
std::stringstream line(in_line);
line >> Field >> Chan >> ChanType >> Scale >> Import;
if (Field.substr(0,2)!="//") {
// do your stuff
// this is CBuilder code for demonstration, sorry
ShowMessage((String)Field.c_str() + "\n" + Chan.c_str() + "\n" + IntToStr(ChanType) + "\n" +FloatToStr(Scale) + "\n" +IntToStr(Import));
}
}
}
@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;
}
由于所有CSV问题似乎都被重定向到这里,我想我应该在这里发布我的答案。这个回答并没有直接回答提问者的问题。我希望能够读取已知的CSV格式的流,而且每个字段的类型都已经知道。当然,可以使用下面的方法将每个字段处理为字符串类型。
作为我希望能够使用CSV输入流的一个例子,考虑以下输入(取自维基百科的CSV页面):
const char input[] =
"Year,Make,Model,Description,Price\n"
"1997,Ford,E350,\"ac, abs, moon\",3000.00\n"
"1999,Chevy,\"Venture \"\"Extended Edition\"\"\",\"\",4900.00\n"
"1999,Chevy,\"Venture \"\"Extended Edition, Very Large\"\"\",\"\",5000.00\n"
"1996,Jeep,Grand Cherokee,\"MUST SELL!\n\
air, moon roof, loaded\",4799.00\n"
;
然后,我希望能够像这样读取数据:
std::istringstream ss(input);
std::string title[5];
int year;
std::string make, model, desc;
float price;
csv_istream(ss)
>> title[0] >> title[1] >> title[2] >> title[3] >> title[4];
while (csv_istream(ss)
>> year >> make >> model >> desc >> price) {
//...do something with the record...
}
这就是我最后得到的解。
struct csv_istream {
std::istream &is_;
csv_istream (std::istream &is) : is_(is) {}
void scan_ws () const {
while (is_.good()) {
int c = is_.peek();
if (c != ' ' && c != '\t') break;
is_.get();
}
}
void scan (std::string *s = 0) const {
std::string ws;
int c = is_.get();
if (is_.good()) {
do {
if (c == ',' || c == '\n') break;
if (s) {
ws += c;
if (c != ' ' && c != '\t') {
*s += ws;
ws.clear();
}
}
c = is_.get();
} while (is_.good());
if (is_.eof()) is_.clear();
}
}
template <typename T, bool> struct set_value {
void operator () (std::string in, T &v) const {
std::istringstream(in) >> v;
}
};
template <typename T> struct set_value<T, true> {
template <bool SIGNED> void convert (std::string in, T &v) const {
if (SIGNED) v = ::strtoll(in.c_str(), 0, 0);
else v = ::strtoull(in.c_str(), 0, 0);
}
void operator () (std::string in, T &v) const {
convert<is_signed_int<T>::val>(in, v);
}
};
template <typename T> const csv_istream & operator >> (T &v) const {
std::string tmp;
scan(&tmp);
set_value<T, is_int<T>::val>()(tmp, v);
return *this;
}
const csv_istream & operator >> (std::string &v) const {
v.clear();
scan_ws();
if (is_.peek() != '"') scan(&v);
else {
std::string tmp;
is_.get();
std::getline(is_, tmp, '"');
while (is_.peek() == '"') {
v += tmp;
v += is_.get();
std::getline(is_, tmp, '"');
}
v += tmp;
scan();
}
return *this;
}
template <typename T>
const csv_istream & operator >> (T &(*manip)(T &)) const {
is_ >> manip;
return *this;
}
operator bool () const { return !is_.fail(); }
};
使用以下helper,可以通过c++ 11中的新积分特征模板进行简化:
template <typename T> struct is_signed_int { enum { val = false }; };
template <> struct is_signed_int<short> { enum { val = true}; };
template <> struct is_signed_int<int> { enum { val = true}; };
template <> struct is_signed_int<long> { enum { val = true}; };
template <> struct is_signed_int<long long> { enum { val = true}; };
template <typename T> struct is_unsigned_int { enum { val = false }; };
template <> struct is_unsigned_int<unsigned short> { enum { val = true}; };
template <> struct is_unsigned_int<unsigned int> { enum { val = true}; };
template <> struct is_unsigned_int<unsigned long> { enum { val = true}; };
template <> struct is_unsigned_int<unsigned long long> { enum { val = true}; };
template <typename T> struct is_int {
enum { val = (is_signed_int<T>::val || is_unsigned_int<T>::val) };
};
在网上试试!