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
}
}
}
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
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;
}
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();
}
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!
