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

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

其他回答

您还可以看看Qt库的功能。

它有正则表达式支持,QString类有很好的方法,例如split()返回QStringList,通过使用提供的分隔符分割原始字符串获得的字符串列表。应该足以为csv文件..

要获得具有给定标题名的列,我使用以下方法:c++继承Qt问题qstring

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);
}

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();
}

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));
      }
   }
}

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;
}