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

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!

其他回答

您需要做的第一件事是确保文件存在。来完成 这你只需要尝试打开文件流的路径。在你 打开文件流使用stream.fail()查看它是否如预期的那样工作, 与否。

bool fileExists(string fileName)
{

ifstream test;

test.open(fileName.c_str());

if (test.fail())
{
    test.close();
    return false;
}
else
{
    test.close();
    return true;
}
}

您还必须验证所提供的文件是正确的文件类型。 要做到这一点,您需要查看提供的文件路径直到 您可以找到文件扩展名。一旦你有了文件扩展名,请确保 它是一个。csv文件。

bool verifyExtension(string filename)
{
int period = 0;

for (unsigned int i = 0; i < filename.length(); i++)
{
    if (filename[i] == '.')
        period = i;
}

string extension;

for (unsigned int i = period; i < filename.length(); i++)
    extension += filename[i];

if (extension == ".csv")
    return true;
else
    return false;
}

此函数将返回稍后在错误消息中使用的文件扩展名。

string getExtension(string filename)
{
int period = 0;

for (unsigned int i = 0; i < filename.length(); i++)
{
    if (filename[i] == '.')
        period = i;
}

string extension;

if (period != 0)
{
    for (unsigned int i = period; i < filename.length(); i++)
        extension += filename[i];
}
else
    extension = "NO FILE";

return extension;
}

这个函数实际上会调用上面创建的错误检查,然后解析文件。

void parseFile(string fileName)
{
    if (fileExists(fileName) && verifyExtension(fileName))
    {
        ifstream fs;
        fs.open(fileName.c_str());
        string fileCommand;

        while (fs.good())
        {
            string temp;

            getline(fs, fileCommand, '\n');

            for (unsigned int i = 0; i < fileCommand.length(); i++)
            {
                if (fileCommand[i] != ',')
                    temp += fileCommand[i];
                else
                    temp += " ";
            }

            if (temp != "\0")
            {
                // Place your code here to run the file.
            }
        }
        fs.close();
    }
    else if (!fileExists(fileName))
    {
        cout << "Error: The provided file does not exist: " << fileName << endl;

        if (!verifyExtension(fileName))
        {
            if (getExtension(fileName) != "NO FILE")
                cout << "\tCheck the file extension." << endl;
            else
                cout << "\tThere is no file in the provided path." << endl;
        }
    }
    else if (!verifyExtension(fileName)) 
    {
        if (getExtension(fileName) != "NO FILE")
            cout << "Incorrect file extension provided: " << getExtension(fileName) << endl;
        else
            cout << "There is no file in the following path: " << fileName << endl;
    }
}

下面是Unicode CSV解析器的另一个实现(使用wchar_t)。我写了一部分,乔纳森·莱弗勒写了剩下的部分。

注意:此解析器旨在尽可能地复制Excel的行为,特别是在导入损坏或格式错误的CSV文件时。

这是最初的问题-用多行字段和转义双引号解析CSV文件

这是作为SSCCE(简短,自包含,正确示例)的代码。

#include <stdbool.h>
#include <wchar.h>
#include <wctype.h>

extern const wchar_t *nextCsvField(const wchar_t *p, wchar_t sep, bool *newline);

// Returns a pointer to the start of the next field,
// or zero if this is the last field in the CSV
// p is the start position of the field
// sep is the separator used, i.e. comma or semicolon
// newline says whether the field ends with a newline or with a comma
const wchar_t *nextCsvField(const wchar_t *p, wchar_t sep, bool *newline)
{
    // Parse quoted sequences
    if ('"' == p[0]) {
        p++;
        while (1) {
            // Find next double-quote
            p = wcschr(p, L'"');
            // If we don't find it or it's the last symbol
            // then this is the last field
            if (!p || !p[1])
                return 0;
            // Check for "", it is an escaped double-quote
            if (p[1] != '"')
                break;
            // Skip the escaped double-quote
            p += 2;
        }
    }

    // Find next newline or comma.
    wchar_t newline_or_sep[4] = L"\n\r ";
    newline_or_sep[2] = sep;
    p = wcspbrk(p, newline_or_sep);

    // If no newline or separator, this is the last field.
    if (!p)
        return 0;

    // Check if we had newline.
    *newline = (p[0] == '\r' || p[0] == '\n');

    // Handle "\r\n", otherwise just increment
    if (p[0] == '\r' && p[1] == '\n')
        p += 2;
    else
        p++;

    return p;
}

static wchar_t *csvFieldData(const wchar_t *fld_s, const wchar_t *fld_e, wchar_t *buffer, size_t buflen)
{
    wchar_t *dst = buffer;
    wchar_t *end = buffer + buflen - 1;
    const wchar_t *src = fld_s;

    if (*src == L'"')
    {
        const wchar_t *p = src + 1;
        while (p < fld_e && dst < end)
        {
            if (p[0] == L'"' && p+1 < fld_s && p[1] == L'"')
            {
                *dst++ = p[0];
                p += 2;
            }
            else if (p[0] == L'"')
            {
                p++;
                break;
            }
            else
                *dst++ = *p++;
        }
        src = p;
    }
    while (src < fld_e && dst < end)
        *dst++ = *src++;
    if (dst >= end)
        return 0;
    *dst = L'\0';
    return(buffer);
}

static void dissect(const wchar_t *line)
{
    const wchar_t *start = line;
    const wchar_t *next;
    bool     eol;
    wprintf(L"Input %3zd: [%.*ls]\n", wcslen(line), wcslen(line)-1, line);
    while ((next = nextCsvField(start, L',', &eol)) != 0)
    {
        wchar_t buffer[1024];
        wprintf(L"Raw Field: [%.*ls] (eol = %d)\n", (next - start - eol), start, eol);
        if (csvFieldData(start, next-1, buffer, sizeof(buffer)/sizeof(buffer[0])) != 0)
            wprintf(L"Field %3zd: [%ls]\n", wcslen(buffer), buffer);
        start = next;
    }
}

static const wchar_t multiline[] =
   L"First field of first row,\"This field is multiline\n"
    "\n"
    "but that's OK because it's enclosed in double quotes, and this\n"
    "is an escaped \"\" double quote\" but this one \"\" is not\n"
    "   \"This is second field of second row, but it is not multiline\n"
    "   because it doesn't start \n"
    "   with an immediate double quote\"\n"
    ;

int main(void)
{
    wchar_t line[1024];

    while (fgetws(line, sizeof(line)/sizeof(line[0]), stdin))
        dissect(line);
    dissect(multiline);

    return 0;
}

可以使用std::regex。

根据文件大小和可用内存,可以逐行读取,也可以完全在std::string中读取。

读取文件可以使用:

std::ifstream t("file.txt");
std::string sin((std::istreambuf_iterator<char>(t)),
                 std::istreambuf_iterator<char>());

然后你可以和这个相匹配,它实际上是根据你的需要定制的。

std::regex word_regex(",\\s]+");
auto what = 
    std::sregex_iterator(sin.begin(), sin.end(), word_regex);
auto wend = std::sregex_iterator();

std::vector<std::string> v;
for (;what!=wend ; wend) {
    std::smatch match = *what;
    v.push_back(match.str());
}

你可能想看看我的自由/开源软件项目CSVfix(更新链接),这是一个用c++编写的CSV流编辑器。CSV解析器不是什么好东西,但它完成了工作,整个包可以在不编写任何代码的情况下满足您的需要。

CSV解析器请参见alib/src/a_csv.cpp,使用示例请参见csvlib/src/csved_ioman.cpp (IOManager::ReadCSV)。

不管怎样,下面是我的实现。它处理wstring输入,但是可以很容易地调整为string。它不处理字段中的换行符(因为我的应用程序也不这样做,但添加它的支持并不太难),它不符合RFC中的“\r\n”行尾(假设您使用std::getline),但它确实正确地处理空格修剪和双引号(希望如此)。

using namespace std;

// trim whitespaces around field or double-quotes, remove double-quotes and replace escaped double-quotes (double double-quotes)
wstring trimquote(const wstring& str, const wstring& whitespace, const wchar_t quotChar)
{
    wstring ws;
    wstring::size_type strBegin = str.find_first_not_of(whitespace);
    if (strBegin == wstring::npos)
        return L"";

    wstring::size_type strEnd = str.find_last_not_of(whitespace);
    wstring::size_type strRange = strEnd - strBegin + 1;

    if((str[strBegin] == quotChar) && (str[strEnd] == quotChar))
    {
        ws = str.substr(strBegin+1, strRange-2);
        strBegin = 0;
        while((strEnd = ws.find(quotChar, strBegin)) != wstring::npos)
        {
            ws.erase(strEnd, 1);
            strBegin = strEnd+1;
        }

    }
    else
        ws = str.substr(strBegin, strRange);
    return ws;
}

pair<unsigned, unsigned> nextCSVQuotePair(const wstring& line, const wchar_t quotChar, unsigned ofs = 0)
{
    pair<unsigned, unsigned> r;
    r.first = line.find(quotChar, ofs);
    r.second = wstring::npos;
    if(r.first != wstring::npos)
    {
        r.second = r.first;
        while(((r.second = line.find(quotChar, r.second+1)) != wstring::npos)
            && (line[r.second+1] == quotChar)) // WARNING: assumes null-terminated string such that line[r.second+1] always exist
            r.second++;

    }
    return r;
}

unsigned parseLine(vector<wstring>& fields, const wstring& line)
{
    unsigned ofs, ofs0, np;
    const wchar_t delim = L',';
    const wstring whitespace = L" \t\xa0\x3000\x2000\x2001\x2002\x2003\x2004\x2005\x2006\x2007\x2008\x2009\x200a\x202f\x205f";
    const wchar_t quotChar = L'\"';
    pair<unsigned, unsigned> quot;

    fields.clear();

    ofs = ofs0 = 0;
    quot = nextCSVQuotePair(line, quotChar);
    while((np = line.find(delim, ofs)) != wstring::npos)
    {
        if((np > quot.first) && (np < quot.second))
        { // skip delimiter inside quoted field
            ofs = quot.second+1;
            quot = nextCSVQuotePair(line, quotChar, ofs);
            continue;
        }
        fields.push_back( trimquote(line.substr(ofs0, np-ofs0), whitespace, quotChar) );
        ofs = ofs0 = np+1;
    }
    fields.push_back( trimquote(line.substr(ofs0), whitespace, quotChar) );

    return fields.size();
}