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

不好意思,但是为了隐藏几行代码,这似乎是非常复杂的语法。

为什么不这样呢:

/**

  Read line from a CSV file

  @param[in] fp file pointer to open file
  @param[in] vls reference to vector of strings to hold next line

  */
void readCSV( FILE *fp, std::vector<std::string>& vls )
{
    vls.clear();
    if( ! fp )
        return;
    char buf[10000];
    if( ! fgets( buf,999,fp) )
        return;
    std::string s = buf;
    int p,q;
    q = -1;
    // loop over columns
    while( 1 ) {
        p = q;
        q = s.find_first_of(",\n",p+1);
        if( q == -1 ) 
            break;
        vls.push_back( s.substr(p+1,q-p-1) );
    }
}

int _tmain(int argc, _TCHAR* argv[])
{
    std::vector<std::string> vls;
    FILE * fp = fopen( argv[1], "r" );
    if( ! fp )
        return 1;
    readCSV( fp, vls );
    readCSV( fp, vls );
    readCSV( fp, vls );
    std::cout << "row 3, col 4 is " << vls[3].c_str() << "\n";

    return 0;
}

其他回答

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);
    }

当对CSV文件使用Boost Tokenizer escaped_list_separator时,应该注意以下几点:

它需要一个转义字符(默认的反斜杠- \) 它需要一个分割符/分隔符-字符(默认逗号-,) 它需要一个引号字符(默认的引号- ")

wiki指定的CSV格式规定数据字段可以包含引号分隔符(支持):

1997年,福特E350,“超级豪华卡车”

由wiki指定的CSV格式规定单引号应该用双引号处理(escaped_list_separator将剥离所有引号字符):

1997年,福特E350,“超级”“豪华”“卡车”

CSV格式没有指定应该删除任何反斜杠字符(escaped_list_separator将删除所有转义字符)。

修复boost escaped_list_separator的默认行为的一个可能的变通方法:

首先将所有反斜杠字符(\)替换为两个反斜杠字符(\\),这样它们就不会被剥离。 其次,将所有双引号("")替换为一个反斜杠字符和一个引号(\")

这种变通方法有一个副作用,即由双引号表示的空数据字段将被转换为单引号标记。在遍历令牌时,必须检查令牌是否是单引号,并将其视为空字符串。

不漂亮,但它工作,只要在引号中没有换行。

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;
}

如果你不想在你的项目中包含boost(如果你只打算使用它来进行CSV解析,它就相当大了……)

我在这里有幸使用CSV解析:

http://www.zedwood.com/article/112/cpp-csv-parser

它处理带引号的字段-但不处理内联\n字符(这可能对大多数用途都很好)。

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;
}