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
该解决方案检测这4种情况
完整的课程在
https://github.com/pedro-vicente/csv-parser
1,field 2,field 3,
1,field 2,"field 3 quoted, with separator",
1,field 2,"field 3
with newline",
1,field 2,"field 3
with newline and separator,",
它一个字符一个字符地读取文件,每次读取一行到一个向量(字符串),因此适合于非常大的文件。
使用
迭代直到返回空行(文件结束)。行是一个向量,其中每个条目都是一个CSV列。
read_csv_t csv;
csv.open("../test.csv");
std::vector<std::string> row;
while (true)
{
row = csv.read_row();
if (row.size() == 0)
{
break;
}
}
类声明
class read_csv_t
{
public:
read_csv_t();
int open(const std::string &file_name);
std::vector<std::string> read_row();
private:
std::ifstream m_ifs;
};
实现
std::vector<std::string> read_csv_t::read_row()
{
bool quote_mode = false;
std::vector<std::string> row;
std::string column;
char c;
while (m_ifs.get(c))
{
switch (c)
{
/////////////////////////////////////////////////////////////////////////////////////////////////////
//separator ',' detected.
//in quote mode add character to column
//push column if not in quote mode
/////////////////////////////////////////////////////////////////////////////////////////////////////
case ',':
if (quote_mode == true)
{
column += c;
}
else
{
row.push_back(column);
column.clear();
}
break;
/////////////////////////////////////////////////////////////////////////////////////////////////////
//quote '"' detected.
//toggle quote mode
/////////////////////////////////////////////////////////////////////////////////////////////////////
case '"':
quote_mode = !quote_mode;
break;
/////////////////////////////////////////////////////////////////////////////////////////////////////
//line end detected
//in quote mode add character to column
//return row if not in quote mode
/////////////////////////////////////////////////////////////////////////////////////////////////////
case '\n':
case '\r':
if (quote_mode == true)
{
column += c;
}
else
{
return row;
}
break;
/////////////////////////////////////////////////////////////////////////////////////////////////////
//default, add character to column
/////////////////////////////////////////////////////////////////////////////////////////////////////
default:
column += c;
break;
}
}
//return empty vector if end of file detected
m_ifs.close();
std::vector<std::string> v;
return v;
}
其他回答
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();
}
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)。
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
}
}
}
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;
}
@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;
}