对不起,我的C/C++不是那么好,但是对我来说,下面的现有代码看起来像垃圾.它也有一个错误 - 当str ="07/02/2010"由'\ 0'终止时失败 - .我认为不是修复错误,而是可以重写.在Python中它只是'kas\nhjkfh kjsdjkasf'.split().我知道这是C-ish代码,但分割字符串不是那么复杂!坚持使用相同的签名,而不使用额外的库,我怎样才能改进它 - 让它简短又甜蜜？我可以说这个代码闻起来,例如因为else句子一直到最后.
线路失败:
_tcsncpy_s(
s.GetBuffer((int) (nIndex-nLast)),
nIndex-nLast,
psz+nLast,
(size_t) (nIndex-nLast)
);
当字符串"07/02/2010"以'\ 0'结尾时,它将尝试将11个字符写入只有10个字符长的缓冲区.
全功能:
#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(",");此成员变量仅用于此功能.我想我现在看到了标记化的意义 - 它试图解析一个日期和时间......等等,还有更多!这是下面调用此函数的代码.请帮我改进一下.我的一些同事声称C#使它们不比C++更有效率.我曾经觉得自己像个白痴,因为我无法对我说同样的话.
// 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;
}
小智 14
该字符串工具包库(Strtk)具有以下问题的解决方案:
#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;
}
更多例子可以在这里找到
在C++中,最简单的方法是使用stsringstream:
std::istringstream buffer("kas\nhjkfh kjsdjkasf");
std::vector<std::string> strings;
std::copy(std::istream_iterator<std::string>(buffer),
std::istream_iterator<std::string>(),
std::back_inserter(strings));
我没有试图坚持完全相同的签名,主要是因为大多数都是非标准的,所以它一般不适用于C++.
另一种可能性是使用Boost::tokenizer,但显然确实涉及另一个库,所以我不会试图更详细地介绍它.
我不确定这是否符合"奇异语法".我可能要在那方面做一点工作......
编辑:我已经知道了 - 而是初始化向量:
std::istringstream buffer("kas\nhjkfh kjsdjkasf");
std::vector<std::string> strings(
(std::istream_iterator<std::string>(buffer)),
std::istream_iterator<std::string>());
"bizarro"部分是没有围绕第一个参数的额外括号,这将调用"最令人烦恼的解析",因此它将声明一个函数而不是定义一个向量.:-)
编辑2:就问题的编辑而言,似乎几乎不可能直接回答 - 它取决于太多类型(例如,CGXStyle,CLVDateTime)既不是标准也不是解释.举个例子,我根本不能完全遵循它.另外,这看起来像是一个相当差的设计,让用户输入或多或少含糊不清的东西,然后试图理清这些混乱.最好使用一个只允许明确输入的控件,你可以直接读取一些包含日期和时间的字段.
Edit3:执行拆分的代码也将逗号视为分隔符,可以这样做:
#include <iostream>
#include <locale>
#include <algorithm>
#include <vector>
#include <sstream>
class my_ctype : public std::ctype<char> {
public:
mask const *get_table() {
// this copies the "classic" table used by <ctype.h>:
static std::vector<std::ctype<char>::mask>
table(classic_table(), classic_table()+table_size);
// Anything we want to separate tokens, we mark its spot in the table as 'space'.
table[','] = (mask)space;
// and return a pointer to the table:
return &table[0];
}
my_ctype(size_t refs=0) : std::ctype<char>(get_table(), false, refs) { }
};
int main() {
// put our data in a strea:
std::istringstream buffer("first kas\nhjkfh kjsdjk,asf\tlast");
// Create a ctype object and tell the stream to use it for parsing tokens:
my_ctype parser;
buffer.imbue(std::locale(std::locale(), &parser));
// separate the stream into tokens:
std::vector<std::string> strings(
(std::istream_iterator<std::string>(buffer)),
std::istream_iterator<std::string>());
// copy the tokes to cout so we can see what we got:
std::copy(strings.begin(), strings.end(),
std::ostream_iterator<std::string>(std::cout, "\n"));
return 0;
}