我想比较两个输入 csv 文件以查看是否添加或删除了行。解决这个问题的最佳方法是什么?我没有使用列名称,因为所有文件的列名称不一致。
private void compare_btn_Click(object sender, EventArgs e)
{
string firstFile = firstExcel_txt.Text;
var results = ReadExcel(openFileDialog1);
string secondFile = secondExcel_txt.Text;
var results2 = ReadExcel(openFileDialog2);
}
阅读:
public object ReadExcel(OpenFileDialog openFileDialog)
{
var _excelFile = new ExcelQueryFactory(openFileDialog.FileName);
var _info = from c in _excelFile.WorksheetNoHeader() select c;
string header1, header2, header3;
foreach (var item in _info)
{
header1 = item.ElementAt(0);
header2 = item.ElementAt(1);
header3 = item.ElementAt(2);
}
return _info;
}
任何有关我如何做到这一点的帮助都会很棒。
我建议你计算Excel文件每一行的哈希值,然后你可以继续比较每一行的哈希值,看看它是否与另一个文件上的任何哈希值匹配(请参阅源代码中的注释)
我还提供了一些类来存储 Excel 文件的内容
using System.Security.Cryptography;
private void compare_btn_Click(object sender, EventArgs e)
{
string firstFile = firstExcel_txt.Text;
ExcelInfo file1 = ReadExcel(openFileDialog1);
string secondFile = secondExcel_txt.Text;
ExcelInfo file2 = ReadExcel(openFileDialog2);
CompareExcels(file1,file2) ;
}
public void CompareExcels(ExcelInfo fileA, ExcelInfo fileB)
{
foreach(ExcelRow rowA in fileA.excelRows)
{
//If the current hash of a row of fileA does not exists in fileB then it was removed
if(! fileB.ContainsHash(rowA.hash))
{
Console.WriteLine("Row removed" + rowA.ToString());
}
}
foreach(ExcelRow rowB in fileB.excelRows)
{
//If the current hash of a row of fileB does not exists in fileA then it was added
if(! fileA.ContainsHash(rowB.hash))
{
Console.WriteLine("Row added" + rowB.ToString());
}
}
}
public Class ExcelRow
{
public List<String> lstCells ;
public byte[] hash
public ExcelRow()
{
lstCells = new List<String>() ;
}
public override string ToString()
{
string resp ;
resp = string.Empty ;
foreach(string cellText in lstCells)
{
if(resp != string.Empty)
{
resp = resp + "," + cellText ;
}
else
{
resp = cellText ;
}
}
return resp ;
}
public void CalculateHash()
{
byte[] rowBytes ;
byte[] cellBytes ;
int pos ;
int numRowBytes ;
//Determine how much bytes are required to store a single excel row
numRowBytes = 0 ;
foreach(string cellText in lstCells)
{
numRowBytes += NumBytes(cellText) ;
}
//Allocate space to calculate the HASH of a single row
rowBytes= new byte[numRowBytes]
pos = 0 ;
//Concatenate the cellText of each cell, converted to bytes,into a single byte array
foreach(string cellText in lstCells)
{
cellBytes = GetBytes(cellText) ;
System.Buffer.BlockCopy(cellBytes, 0, rowBytes, pos, cellBytes.Length);
pos = cellBytes.Length ;
}
hash = new MD5CryptoServiceProvider().ComputeHash(rowBytes);
}
static int NumBytes(string str)
{
return str.Length * sizeof(char);
}
static byte[] GetBytes(string str)
{
byte[] bytes = new byte[NumBytes(str)];
System.Buffer.BlockCopy(str.ToCharArray(), 0, bytes, 0, bytes.Length);
return bytes;
}
}
public Class ExcelInfo
{
public List<ExcelRow> excelRows ;
public ExcelInfo()
{
excelRows = new List<ExcelRow>();
}
public bool ContainsHash(byte[] hashToLook)
{
bool found ;
found = false ;
foreach(ExcelRow eRow in excelRows)
{
found = EqualHash(eRow.hash, hashToLook) ;
if(found)
{
break ;
}
}
return found ;
}
public static EqualHash(byte[] hashA, byte[] hashB)
{
bool bEqual ;
int i ;
bEqual = false;
if (hashA.Length == hashB.Length)
{
i = 0;
while ((i < hashA.Length) && (hashA[i] == hashB[i]))
{
i++ ;
}
if (i == hashA.Length)
{
bEqual = true;
}
}
return bEqual ;
}
}
public ExcelInfo ReadExcel(OpenFileDialog openFileDialog)
{
var _excelFile = new ExcelQueryFactory(openFileDialog.FileName);
var _info = from c in _excelFile.WorksheetNoHeader() select c;
ExcelRow excelRow ;
ExcelInfo resp ;
resp = new ExcelInfo() ;
foreach (var item in _info)
{
excelRow = new ExcelRow() ;
//Add all the cells (with a for each)
excelRow.lstCells.Add(item.ElementAt(0));
excelRow.lstCells.Add(item.ElementAt(1));
....
//Add the last cell of the row
excelRow.lstCells.Add(item.ElementAt(N));
//Calculate the hash of the row
excelRow.CalculateHash() ;
//Add the row to the ExcelInfo object
resp.excelRows.Add(excelRow) ;
}
return resp ;
}
最准确的方法是将它们都转换为字节数组,检查两者转换为数组时是否存在差异,使用以下链接获取简单的示例,了解如何将Excel表格转换为字节数组 :
现在您已将两个 Excel 工作表转换为 byte[],您应该通过检查字节数组是否相等来检查它们是否存在差异。
可以通过多种方式进行检查,如下所示,使用
linq
:
using System.Linq; //SequenceEqual
byte[] FirstExcelFileBytes = null;
byte[] SecondExcelFileBytes = null;
FirstExcelFileBytes = GetFirstExcelFile();
SecondExcelFileBytes = GetSecondExcelFile();
if (FirstExcelFileBytes.SequenceEqual<byte>(SecondExcelFileBytes) == true)
{
MessageBox.Show("Arrays are equal");
}
else
{
MessageBox.Show("Arrays don't match");
}
有足够多的其他方法来查找比较字节数组,您应该做一些研究,了解哪种方法最适合您。
使用以下链接,检查诸如
Row added
、row removed
等内容。
我最近正在处理相同的问题陈述,我必须比较两个 Excel 文件并打印两个文件之间的任何差异。
我采用的方法是将两个 Excel 文件导出到 DataTable,然后逐个单元格进行比较。
使用 Syncfusion.XlsIO 的 C# 代码片段:
public static DataTable SaveExcelToDataTable(string filePath)
{
//Create an instance of ExcelEngine
ExcelEngine excelEngine = new ExcelEngine();
//Initialize application
IApplication application = excelEngine.Excel;
application.DefaultVersion = ExcelVersion.Xlsx;
//Open existing workbook with data entered
FileStream inputStream = new FileStream(filePath, FileMode.Open, FileAccess.Read);
IWorkbook workbook = application.Workbooks.Open(inputStream);
//Access first worksheet from the workbook instance
IWorksheet worksheet = workbook.Worksheets[0];
//Export Excel to DataTable
DataTable dataTable = worksheet.ExportDataTable(worksheet.UsedRange, ExcelExportDataTableOptions.ColumnNames);
return dataTable;
}
public static bool CompareDataTables(DataTable dt1, DataTable dt2)
{
if (dt1.Rows.Count != dt2.Rows.Count || dt1.Columns.Count != dt2.Columns.Count)
return false;
for (int i = 0; i < dt1.Rows.Count; i++)
{
for (int c = 0; c < dt1.Columns.Count; c++)
{
if (!Equals(dt1.Rows[i][c], dt2.Rows[i][c]))
return false;
}
}
return true;
}