c++ - 在 C/C++ 中使用空格作为分隔符将字符串拆分为字符串数组的更好方法

Question

抱歉，我的 C/C++ 不太好，但以下现有代码即使对我来说也像是垃圾。它还有一个错误 - 当 str = "07/02/2010"以 '\0' 终止时失败 - 。我认为与其修复错误，不如重写它。在 Python 中，它只是 'kas\nhjkfh kjsdjkasf'.split()。我知道这是 C-ish 代码，但拆分字符串不会那么复杂!坚持相同的签名，并且不使用额外的库，我该如何改进它 - 让它简短而甜蜜？我可以看出这段代码有异味，例如因为结尾处的 else 子句。

失败的线路:

_tcsncpy_s(
    s.GetBuffer((int) (nIndex-nLast)),
    nIndex-nLast,
    psz+nLast,
    (size_t) (nIndex-nLast)
);

如果字符串“07/02/2010”以 '\0' 结尾，它将尝试将 11 个字符写入一个只有 10 个字符长的缓冲区。

功能齐全:

#define 

// This will return the text string as a string array
// This function is called from SetControlText to parse the
// text string into an array of CStrings that the control
// Gadgets will attempt to interpret

BOOL CLVGridDateTimeCtrl::ParseTextWithCurrentFormat(const CString& str, const CGXStyle* pOldStyle, CStringArray& strArray )
{
    // Unused:
    pOldStyle;

    // we assume that the significant segments are seperated by space

    // Please change m_strDelim to add other delimiters

    CString s;

    LPCTSTR psz = (LPCTSTR) str;

    BOOL bLastCharSpace = FALSE;
    DWORD size = str.GetLength()+1;

    // (newline will start a new row, tab delimiter will
    // move to the next column).
    // parse buffer (DBCS aware)
    for (DWORD nIndex = 0, nLast = 0; nIndex < size; nIndex += _tclen(psz+nIndex))
    {
        // check for a delimiter
        if (psz[nIndex] == _T('\0') || _tcschr(_T("\r\n"), psz[nIndex]) || _tcschr(_T(" "), psz[nIndex])
            ||!_tcscspn(&psz[nIndex], (LPCTSTR)m_strDelim))
        {
            s.ReleaseBuffer();
            s.Empty();
            // abort parsing the string if next char
            // is an end-of-string
            if (psz[nIndex] == _T('\0'))
            {
                if (psz[nIndex] == _T('\r') && psz[nIndex+1] == _T('\n'))
                    nIndex++;

                _tcsncpy_s(s.GetBuffer((int) (nIndex-nLast)),
                    nIndex-nLast,
                            psz+nLast,
                            (size_t) (nIndex-nLast));
                CString temStr = s;
                strArray.Add(temStr);
                temStr.Empty();
                break;
            }

            else if (_tcscspn(&psz[nIndex], (LPCTSTR)m_strDelim) == 0 && !bLastCharSpace)
            {
                if (psz[nIndex] == _T('\r') && psz[nIndex+1] == _T('\n'))
                    nIndex++;

                _tcsncpy_s(s.GetBuffer((int) (nIndex-nLast)),
                    nIndex-nLast,
                            psz+nLast,
                            (size_t) (nIndex-nLast));
                CString temStr = s;
                strArray.Add(temStr);
                temStr.Empty();
                bLastCharSpace = TRUE;
                // abort parsing the string if next char
                // is an end-of-string
                if (psz[nIndex+1] == _T('\0'))
                    break;

            }
            // Now, that the value has been copied to the cell,
            // let's check if we should jump to a new row.
            else if (_tcschr(_T(" "), psz[nIndex]) && !bLastCharSpace)
            {
                if (psz[nIndex] == _T('\r') && psz[nIndex+1] == _T('\n'))
                    nIndex++;

                _tcsncpy_s(s.GetBuffer((int) (nIndex-nLast)),
                    nIndex-nLast,
                            psz+nLast,
                            (size_t) (nIndex-nLast));
                CString temStr = s;
                strArray.Add(temStr);
                temStr.Empty();
                bLastCharSpace = TRUE;
                // abort parsing the string if next char
                // is an end-of-string
                if (psz[nIndex+1] == _T('\0'))
                    break;
            }

            nLast = nIndex + _tclen(psz+nIndex);


        }
        else
        {   
            // nLast = nIndex + _tclen(psz+nIndex);
            bLastCharSpace = FALSE;
        }
    }
    if (strArray.GetSize())
        return TRUE;
    else
        return FALSE;
}

编辑:m_strDelim = _T(","); 并且这个成员变量只在这个函数中使用。我想我现在看到了标记化的意义——它试图解析日期和时间……等等，还有更多!下面是调用此函数的代码。请帮助我改善这一点。我的一些同事声称 C# 并不比 C++ 更高效。我曾经觉得自己像个白痴，因为不能对我说同样的话。

// SetControlText will attempt to convert the text to a valid date first with
// the help of COleDateTime and then with the help of the Date control and the
// current format

BOOL CLVGridDateTimeCtrl::ConvertControlTextToValue(CString& str, ROWCOL nRow, ROWCOL nCol, const CGXStyle* pOldStyle)
{
    CGXStyle* pStyle = NULL;
    BOOL bSuccess = FALSE;

    if (pOldStyle == NULL)
    {
        pStyle = Grid()->CreateStyle();
        Grid()->ComposeStyleRowCol(nRow, nCol, pStyle);
        pOldStyle = pStyle;
    }

    // allow only valid input
    {
        // First do this
        CLVDateTime dt;

        if (str.IsEmpty())
        {
            ;
            // if (Grid()->IsCurrentCell(nRow, nCol))
            //  Reset();
            bSuccess = TRUE;
        }
        else if (dt.ParseDateTime(str,CLVGlobals::IsUSDateFormat()) && (DATE) dt != 0)
        {
            SetDateTime(dt);
            if (m_bDateValueAsNumber)
                str.Format(_T("%g"), (DATE) dt);
            else
                str = dt.Format();
            bSuccess = TRUE;
        }
        else
        {
            // parse the string using the current format
            CStringArray strArray;
            if (!ParseTextWithCurrentFormat(str, pOldStyle, strArray))
                return FALSE;

            UpdateNullStatus(m_TextCtrlWnd);

            SetFormat(m_TextCtrlWnd, *pOldStyle);

            int nArrIndex = 0;
            for(int i=0; i<m_TextCtrlWnd.m_gadgets.GetSize(); i++)
            {
                int val = m_TextCtrlWnd.m_gadgets[i]->GetValue();   
                // s.Empty();
                if(m_TextCtrlWnd.m_gadgets[i]->IsKindOf(RUNTIME_CLASS(SECDTNumericGadget)))
                {
                    // TRACE(_T("The value %s\n"), strArray[nArrIndex]);
                    ((CLVDTNumericGadget*)m_TextCtrlWnd.m_gadgets[i])->m_nNewValue = _ttoi(strArray[nArrIndex]);    
                    nArrIndex++;
                    if (nArrIndex>strArray.GetUpperBound())
                            break;
                }
                else if(m_TextCtrlWnd.m_gadgets[i]->IsKindOf(RUNTIME_CLASS(SECDTListGadget)) && val!=-1)
                {
                    int nIndex = ((CLVDTListGadget*)m_TextCtrlWnd.m_gadgets[i])->FindMatch(strArray[nArrIndex], ((CLVDTListGadget*)m_TextCtrlWnd.m_gadgets[i])->GetValue()+1);
                    if (nIndex!=-1)
                    {
                        // TRACE(_T("The value %s\n"), strArray[nArrIndex]);
                        ((CLVDTListGadget*)m_TextCtrlWnd.m_gadgets[i])->SetValue(nIndex);
                        nArrIndex++;
                        if (nArrIndex>strArray.GetUpperBound())
                            break;
                    }

                }

                CLVDBValue dbDate = m_TextCtrlWnd.GetDateTime();
                if (dbDate.IsNull())
                    str = _T("");
                else
                {
                    CLVDateTime dt = (CLVDateTime)dbDate;
                    if (m_bDateValueAsNumber)
                        str.Format(_T("%g"), (DATE) dt);
                    else
                        str = dt.Format();
                }
            }
            bSuccess = TRUE;
        }
    }

    if (pStyle)
        Grid()->RecycleStyle(pStyle);

    return bSuccess;
}

Answer 1

String Toolkit Library (Strtk)对您的问题有以下解决方案:

#include <string>
#include <deque>
#include "strtk.hpp"
int main()
{ 
   std::string data("kas\nhjkfh kjsdjkasf");
   std::deque<std::string> str_list;
   strtk::parse(data, ", \r\n", str_list);
   return 0;
}

更多示例请见 Here