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

您可以使用fopen,fscanf函数打开和读取.csv文件,但重要的是解析数据。使用分隔符解析数据的最简单方法。对于.csv,分隔符为','。

假设你的data1.csv文件如下所示:

A,45,76,01
B,77,67,02
C,63,76,03
D,65,44,04

您可以标记数据并存储在字符数组中,然后使用atoi()等函数进行适当的转换

FILE *fp;
char str1[10], str2[10], str3[10], str4[10];

fp = fopen("G:\\data1.csv", "r");
if(NULL == fp)
{
    printf("\nError in opening file.");
    return 0;
}
while(EOF != fscanf(fp, " %[^,], %[^,], %[^,], %s, %s, %s, %s ", str1, str2, str3, str4))
{
    printf("\n%s %s %s %s", str1, str2, str3, str4);
}
fclose(fp);

[^,], ^ -它颠倒了逻辑,意思是匹配任何不包含逗号的字符串,然后最后,表示匹配终止前一个字符串的逗号。

其他回答

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!

如果您正在使用Visual Studio / MFC,下面的解决方案可能会使您的工作更轻松。它支持Unicode和MBCS,有注释,除了CString之外没有其他依赖项,对我来说工作得很好。它不支持在带引号的字符串中嵌入换行符,但我不在乎,只要它在这种情况下不崩溃,它不会崩溃。

总体策略是,将带引号的字符串和空字符串作为特殊情况处理,其余使用Tokenize。对于带引号的字符串,策略是找到真正的结束引号,跟踪是否遇到了连续的引号对。如果是,则使用Replace将成对转换为单个。毫无疑问,有更有效的方法,但在我的案例中,性能还不够重要,不足以证明进一步优化的合理性。

class CParseCSV {
public:
// Construction
    CParseCSV(const CString& sLine);

// Attributes
    bool    GetString(CString& sDest);

protected:
    CString m_sLine;    // line to extract tokens from
    int     m_nLen;     // line length in characters
    int     m_iPos;     // index of current position
};

CParseCSV::CParseCSV(const CString& sLine) : m_sLine(sLine)
{
    m_nLen = m_sLine.GetLength();
    m_iPos = 0;
}

bool CParseCSV::GetString(CString& sDest)
{
    if (m_iPos < 0 || m_iPos > m_nLen)  // if position out of range
        return false;
    if (m_iPos == m_nLen) { // if at end of string
        sDest.Empty();  // return empty token
        m_iPos = -1;    // really done now
        return true;
    }
    if (m_sLine[m_iPos] == '\"') {  // if current char is double quote
        m_iPos++;   // advance to next char
        int iTokenStart = m_iPos;
        bool    bHasEmbeddedQuotes = false;
        while (m_iPos < m_nLen) {   // while more chars to parse
            if (m_sLine[m_iPos] == '\"') {  // if current char is double quote
                // if next char exists and is also double quote
                if (m_iPos < m_nLen - 1 && m_sLine[m_iPos + 1] == '\"') {
                    // found pair of consecutive double quotes
                    bHasEmbeddedQuotes = true;  // request conversion
                    m_iPos++;   // skip first quote in pair
                } else  // next char doesn't exist or is normal
                    break;  // found closing quote; exit loop
            }
            m_iPos++;   // advance to next char
        }
        sDest = m_sLine.Mid(iTokenStart, m_iPos - iTokenStart);
        if (bHasEmbeddedQuotes) // if string contains embedded quote pairs
            sDest.Replace(_T("\"\""), _T("\""));    // convert pairs to singles
        m_iPos += 2;    // skip closing quote and trailing delimiter if any
    } else if (m_sLine[m_iPos] == ',') {    // else if char is comma
        sDest.Empty();  // return empty token
        m_iPos++;   // advance to next char
    } else {    // else get next comma-delimited token
        sDest = m_sLine.Tokenize(_T(","), m_iPos);
    }
    return true;
}

// calling code should look something like this:

    CStdioFile  fIn(pszPath, CFile::modeRead);
    CString sLine, sToken;
    while (fIn.ReadString(sLine)) { // for each line of input file
        if (!sLine.IsEmpty()) { // ignore blank lines
            CParseCSV   csv(sLine);
            while (csv.GetString(sToken)) {
                // do something with sToken here
            }
        }
    }

c++ String工具箱库(StrTk)有一个令牌网格类,它允许你从文本文件、字符串或字符缓冲区加载数据,并以行-列的方式解析/处理它们。

您可以指定行分隔符和列分隔符,或者只使用默认值。

void foo()
{
   std::string data = "1,2,3,4,5\n"
                      "0,2,4,6,8\n"
                      "1,3,5,7,9\n";

   strtk::token_grid grid(data,data.size(),",");

   for(std::size_t i = 0; i < grid.row_count(); ++i)
   {
      strtk::token_grid::row_type r = grid.row(i);
      for(std::size_t j = 0; j < r.size(); ++j)
      {
         std::cout << r.get<int>(j) << "\t";
      }
      std::cout << std::endl;
   }
   std::cout << std::endl;
}

更多的例子可以在这里找到

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;
}

您可以使用fopen,fscanf函数打开和读取.csv文件,但重要的是解析数据。使用分隔符解析数据的最简单方法。对于.csv,分隔符为','。

假设你的data1.csv文件如下所示:

A,45,76,01
B,77,67,02
C,63,76,03
D,65,44,04

您可以标记数据并存储在字符数组中,然后使用atoi()等函数进行适当的转换

FILE *fp;
char str1[10], str2[10], str3[10], str4[10];

fp = fopen("G:\\data1.csv", "r");
if(NULL == fp)
{
    printf("\nError in opening file.");
    return 0;
}
while(EOF != fscanf(fp, " %[^,], %[^,], %[^,], %s, %s, %s, %s ", str1, str2, str3, str4))
{
    printf("\n%s %s %s %s", str1, str2, str3, str4);
}
fclose(fp);

[^,], ^ -它颠倒了逻辑,意思是匹配任何不包含逗号的字符串,然后最后,表示匹配终止前一个字符串的逗号。