文件解析之CSV

你的名字 2022-04-10 02:53 582阅读 0赞

最近使用CSV文件做过一个项目，实现了一个CSV文件解析类如下：

**upub.h**

#pragma once
    
    using namespace std;
    
    #include <iostream>
    #include <fstream>  
    #include <sstream>  
    
    #include <deque>
    #include <vector>
    #include <stack>
    
    #include <string>  
    
    #include <stdio.h>
    #include <string.h>
    #include <stdlib.h>
    #include <time.h>
    
    #define FLOAT_MAX (3.4e+38)
    #define FLOAT_MIN (3.4e-38)
    #define DOUBLE_MAX (1.7e+308)
    #define DOUBLE_MIN (1.7e-308)
    
    typedef enum ussvtype { 
    	USS_VTYPE_NULL = 0,
    	USS_VTYPE_BOOL,
    	USS_VTYPE_INT32,
    	USS_VTYPE_UINT32,
    	USS_VTYPE_DOUBLE
    }ussvtype;
    
    typedef struct ussvar {
        ussvtype vt;
        
        union {
            bool bol;
            signed int i32;
            unsigned int u32;
            double dou;
        }val;
    } ussvar;

**ucsv.h：**

#include "upub.h"
    
    #pragma once
    // using namespace std;
    
    #include <iostream>
    #include <fstream>  
    #include <sstream>  
    
    #include <deque>
    #include <vector>
    #include <stack>
    
    #include <string>  
    
    #include <stdio.h>
    #include <string.h>
    #include <stdlib.h>
    #include <time.h>
    
    #define FLOAT_MAX (3.4e+38)
    #define FLOAT_MIN (3.4e-38)
    #define DOUBLE_MAX (1.7e+308)
    #define DOUBLE_MIN (1.7e-308)
    
    
    typedef vector<string> ROWVEC;  
    
    enum  
    {  
        FILE_STATE_NULL,  
        FILE_STATE_READ,  
        FILE_STATE_WRITE,  
    };  
    
    class ufilecsv  
    {  
    public:  
        ufilecsv();
        ~ufilecsv();
        bool    open(bool bIsRead, const char* strPath, const char* strFilename);  
        bool    close();
        bool    setio();
        bool    sethead(const char* head);
    
        // 读接口  
        template<class T>  
        bool read(const char* strFieldName, T& data)  
        {  
            if (m_nFileState != FILE_STATE_READ)  
            {  
                return false;  
            }  
      
            int n   = findfield(strFieldName);  
            if (n == -1 || n >= m_CSVCurRow.size())  
            {  
                return false;  
            }  
    
            /*can't support string which contains space, so add readstring()*/
            stringstream ss;  
            ss << m_CSVCurRow[n];  
            ss >> data;  
      
            return true;  
        }  
      
        // 写接口  
        template<class T>  
        bool write(const char* strFieldName, T data)  
        {  
            if (m_nFileState != FILE_STATE_WRITE)  
            {  
                return false;  
            }  
      
            int n   = findfield(strFieldName);  
            if (n == -1)  
            {  
                return false;  
            }  
            
            /*can't support string which contains space, so add writestring()*/
            stringstream ss;  
            ss << data;  
            m_CSVCurRow[n]  = ss.str();  
      
            return true;  
        }  
    
        bool readstring(const char* strFieldName, char* data, int size)  
        {  
            if (m_nFileState != FILE_STATE_READ)  
            {  
                return false;  
            }  
      
            int n   = findfield(strFieldName);  
            if (n == -1 || n >= m_CSVCurRow.size())  
            {  
                return false;  
            }  
      
            strncpy(data, m_CSVCurRow[n].data(), size-1);
      
            return true;  
        }  
    
        bool writestring(const char* strFieldName, char* data, int size)  
        {  
            if (m_nFileState != FILE_STATE_WRITE)  
            {  
                return false;  
            }  
      
            int n   = findfield(strFieldName);  
            if (n == -1)  
            {  
                return false;  
            }  
    
            m_CSVCurRow[n]  = data;  
      
            return true;  
        }  
    
    private:  
        void    readhead();  
        void    parserow(const char* strRow, int nSize, ROWVEC& result);  
        int     findfield(const char* strRow);  
    private:  
        int         m_nFileState;  
        fstream     m_CSVFile;  
        ROWVEC      m_CSVHead;  
        ROWVEC      m_CSVCurRow;  
    
        char        m_headline[4096];
    };

**ucsv.cpp：**

#include "stdafx.h"
    #include "ucsv.h"
    
    //string转wstring
    std::wstring Utf82Unicode(const std::string& utf8string)  
    {  
    	int widesize = ::MultiByteToWideChar(CP_UTF8, 0, utf8string.c_str(), -1, NULL, 0);  
    	if (widesize == ERROR_NO_UNICODE_TRANSLATION)  
    	{  
    		throw std::exception("Invalid UTF-8 sequence.");  
    	}  
    	if (widesize == 0)  
    	{  
    		throw std::exception("Error in conversion.");  
    	}  
    	std::vector<wchar_t> resultstring(widesize);  
    	int convresult = ::MultiByteToWideChar(CP_UTF8, 0, utf8string.c_str(), -1, &resultstring[0], widesize);  
    	if (convresult != widesize)  
    	{  
    		throw std::exception("La falla!");  
    	}  
    	return std::wstring(&resultstring[0]);  
    }  
    
    int replace(string& src_str, const string& old_str, const string& new_str)  
    {  
        int count   = 0;  
        int old_str_len = int(old_str.length());  
        int new_str_len = int(new_str.length());  
        int pos = 0;  
        while((pos=int(src_str.find(old_str,pos)))!=string::npos)  
        {  
            src_str.replace(pos,old_str_len,new_str);  
            pos+=new_str_len;  
            ++count;  
        }  
        return count;  
    }   
    
    ufilecsv::ufilecsv()
    {
        memset(m_headline, 0, sizeof(m_headline));
    }
    
    ufilecsv::~ufilecsv()
    {
        
    }
    
    void ufilecsv::readhead()  
    {  
        char strHeadLine[4096];
        
        m_CSVFile.getline(strHeadLine, sizeof(strHeadLine));
        
        if ((m_headline[0] != 0) && (strcmp(m_headline, strHeadLine) != 0))
        {
            parserow(m_headline, sizeof(m_headline), m_CSVHead);  
        }
        else
        {
            parserow(strHeadLine, sizeof(strHeadLine), m_CSVHead);  
        }
    }  
      
    void ufilecsv::parserow(const char* strRow, int nSize, ROWVEC& result)  
    {  
        result.clear();  
      
        bool    bIsInWord   = false;  
        bool    bIsHaveSpace = false;  
        string  strCurWorld;  
      
        for (int i=0; i<nSize; i++)  
        {  
            char ch = strRow[i];  
            if (ch == '\0')  
            {  
                if (i >= 1 && strRow[i-1] == ',')  
                {  
                    strCurWorld = ' ';  
                }  
      
                break;  
            }  
      
            bool bIsAdd = true;  
    		if (ch<=0)
    		{
    			bIsAdd=false;
    		}
      
            switch (ch)  
            {  
            case ',':  
                {  
                    if (!bIsInWord)  
                    {  
                        // 一项结束  
      
                        result.push_back(strCurWorld);  
      
                        bIsInWord   = false;  
                        bIsHaveSpace    = false;  
                        strCurWorld = "";  
      
                        bIsAdd  = false;  
                    }  
                }  
                break;  
            case '"':  
                {  
                    if (!bIsInWord)  
                    {  
                        bIsInWord   = true;  
                        bIsHaveSpace    = true;  
      
                        bIsAdd  = false;  
                    }  
                    else  
                    {  
                        if ('"' == strRow[i+1])  
                        {  
                            i++;  
                        }  
                        else if (bIsHaveSpace)  
                        {  
                            bIsInWord   = false;  
      
                            bIsAdd  = false;  
                        }  
                        else  
                        {  
                        }  
      
                    }  
                }  
                break;  
    		case '?':
    			bIsAdd=false;
    			break;
            default:  
                //bIsInWord = true;  
                break;  
            };  
      
            if (bIsAdd)  
            {  
                strCurWorld += ch;  
            }  
      
        }  
      
        if (strCurWorld != "")  
        {  
            result.push_back(strCurWorld);  
        }  
      
    }  
      
    int ufilecsv::findfield(const char* strRow)  
    {  
        if (m_nFileState == FILE_STATE_NULL)  
        {  
            return -1;  
        }  
    	ROWVEC::iterator pStart = m_CSVHead.begin();
    	ROWVEC::iterator pEnd = m_CSVHead.end();
    	while(pStart != pEnd)
    	{
    		wstring arr = Utf82Unicode(*pStart);
    		CString csTemp;
    		csTemp=strRow;
    		CString csTemp1(arr.c_str());
    
            if (!csTemp1.CompareNoCase(csTemp))  
            {  
                return int(pStart - m_CSVHead.begin());  
            }  
    		pStart++;
        }  
      
        return -1;  
    }  
      
      
    bool ufilecsv::open(bool bIsRead, const char* strPath, const char* strFilename)  
    {  
        m_nFileState    = FILE_STATE_NULL;  
        string strFullFileName(strPath);  
        strFullFileName += strFilename;  
    
        if (!bIsRead)
        {
            m_CSVFile.open(strFullFileName.c_str(), ios_base::out|ios_base::app); 
            if (m_CSVFile.is_open())
            {
                m_CSVFile.close();
           }
        }
        
    
        m_CSVFile.open(strFullFileName.c_str(), ios_base::in); 
        
        if (!m_CSVFile.is_open())  
        {  
            return false;  
        }  
      
        readhead();  
      
        if (bIsRead)  
        {  
            m_nFileState    = FILE_STATE_READ;  
        }  
    	else  
        {  
            m_nFileState    = FILE_STATE_WRITE;  
            m_CSVFile.close();  
            m_CSVFile.open(strFullFileName.c_str(), ios_base::out|ios_base::app);  
            if (!m_CSVFile.is_open())  
            {  
                return false;  
            }  
      
            m_CSVCurRow = m_CSVHead;  
            setio();  
        }  
      
        return true;  
    }  
    
    bool ufilecsv::close()  
    {  
        m_nFileState    = FILE_STATE_NULL;  
      
        if (!m_CSVFile.is_open())  
        {  
            return true;  
        }  
        
        m_CSVFile.close();
      
        return true;  
    }
      
    // 读接口  
    bool ufilecsv::setio()  
    {  
        if (m_nFileState == FILE_STATE_READ)  
        {  
            char strHeadLine[4096];
            
            if (m_CSVFile.eof())  
            {  
                return false;  
            }  
            
            m_CSVFile.getline(strHeadLine, sizeof(strHeadLine));  
    
            parserow(strHeadLine, sizeof(strHeadLine), m_CSVCurRow);  
        }
        else if (m_nFileState == FILE_STATE_WRITE)
        {
            for (ROWVEC::iterator it    = m_CSVCurRow.begin();  
            it != m_CSVCurRow.end(); it++)  
            {  
                string str = *it;  
                *it = "";  
                replace(str, "\"", "\"\"");  
          
                m_CSVFile << '"' << str << '"';  
                if (it + 1 != m_CSVCurRow.end())  
                {  
                    m_CSVFile << ',';  
                }  
            }  
          
            m_CSVFile << endl;  
        }
        else
        {
            return false;
        }
        
        return true;  
    }
    
    bool ufilecsv::sethead(const char* head)  
    {  
        strcpy(m_headline, head);
        return true;  
    }

**读取文件示例：**

void Clanguage::ReadF()
    {
    	ROWVEC head;
    	CString str;
    	CString Htxt[4]={_T("type"),_T("VID"),_T("language"),_T("strvalue")};
    	ufilecsv file;
    	char* id="1";
    	CString filePath = _T("G:\\vs2010\\项目\\Language\\");
    	CString fileName = _T("language.txt");
    	char* cArrTemp=new char[128];
    	for (int i=0;i<4;i++)
    	{
    		head.push_back(WcharToChar(Htxt[i].GetBuffer()));
    	}
    	
    	if (file.open(true, WcharToChar(filePath.GetBuffer()), WcharToChar(fileName.GetBuffer())))
    	{
    		int i=0;
    		while(file.setio())
    		{
    			CString one;
    			langdata ldata;
    			file.read(head[0].c_str(),cArrTemp);
    			ldata.type=atoi(cArrTemp);
    			file.read(head[1].c_str(),cArrTemp);
    			strcpy(ldata.VID, cArrTemp);
    			file.read(head[2].c_str(),cArrTemp);
    			strcpy(ldata.language, cArrTemp);
    			file.read(head[3].c_str(),cArrTemp);
    			strcpy(ldata.strvalue, cArrTemp);
    			m_langdatalist.push_back(ldata);
    		}
    		file.close();
    	}
    	else
    	{
    		AfxMessageBox(_T("文件打开失败！"));
    		return;
    	}
    }