任务
将数据从excel
导入DataTable
问题
不会跳过不包含任何数据的单元格,并且该行中包含数据的下一个单元格将用作空列的值。 E.g
A1 为空 A2 的值为Tom
,然后导入数据A1
时获取值 A2 和 A2 仍为空
为了清楚说明我在下面提供一些屏幕截图
这是Excel数据
代码
public class ImportExcelOpenXml
{
public static DataTable Fill_dataTable(string fileName)
{
DataTable dt = new DataTable();
using (SpreadsheetDocument spreadSheetDocument = SpreadsheetDocument.Open(fileName, false))
{
WorkbookPart workbookPart = spreadSheetDocument.WorkbookPart;
IEnumerable<Sheet> sheets = spreadSheetDocument.WorkbookPart.Workbook.GetFirstChild<Sheets>().Elements<Sheet>();
string relationshipId = sheets.First().Id.Value;
WorksheetPart worksheetPart = (WorksheetPart)spreadSheetDocument.WorkbookPart.GetPartById(relationshipId);
Worksheet workSheet = worksheetPart.Worksheet;
SheetData sheetData = workSheet.GetFirstChild<SheetData>();
IEnumerable<Row> rows = sheetData.Descendants<Row>();
foreach (Cell cell in rows.ElementAt(0))
{
dt.Columns.Add(GetCellValue(spreadSheetDocument, cell));
}
foreach (Row row in rows) //this will also include your header row...
{
DataRow tempRow = dt.NewRow();
for (int i = 0; i < row.Descendants<Cell>().Count(); i++)
{
tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants<Cell>().ElementAt(i));
}
dt.Rows.Add(tempRow);
}
}
dt.Rows.RemoveAt(0); //...so i'm taking it out here.
return dt;
}
public static string GetCellValue(SpreadsheetDocument document, Cell cell)
{
SharedStringTablePart stringTablePart = document.WorkbookPart.SharedStringTablePart;
string value = cell.CellValue.InnerXml;
if (cell.DataType != null && cell.DataType.Value == CellValues.SharedString)
{
return stringTablePart.SharedStringTable.ChildElements[Int32.Parse(value)].InnerText;
}
else
{
return value;
}
}
}
我的想法
我认为
存在一些问题 public IEnumerable<T> Descendants<T>() where T : OpenXmlElement;
如果我想使用Descendants
IEnumerable<Row> rows = sheetData.Descendants<<Row>();
int colCnt = rows.ElementAt(0).Count();
OR
如果我使用Descendants
IEnumerable<Row> rows = sheetData.Descendants<<Row>();
int rowCnt = rows.Count();`
在这两种情况下Descendants
都会跳过空单元格
是否有Descendants
的其他选择。
非常感谢您的建议
PS:我还想过使用 A1,A2 之类的列名来获取单元格值,但为了做到这一点,我必须得到不是列和行的确切数量可以使用Descendants
函数。
答案 0 :(得分:11)
如果连续所有单元格中都有数据,那么一切都运行良好。你连续一个空单元格的那一刻就会出现问题。
为什么会在第一时间发生?
这是因为在下面的代码中:
row.Descendants<Cell>().Count()
Count()
是非空填充的单元格(不是所有列)的数量。因此,当您将row.Descendants<Cell>().ElementAt(i)
作为参数传递给GetCellValue
方法时:
GetCellValue(spreadSheetDocument, row.Descendants<Cell>().ElementAt(i));
然后它会找到下一个非空填充的单元格的内容(不一定是该列索引中的内容,i
),例如如果第一列是空的并且我们调用ElementAt(1)
,它将返回第二列中的值,而整个逻辑会搞乱。
解决方案 - 我们需要处理空单元格的出现:基本上我们需要找出单元格的原始列索引,以防前面有空单元格。因此,您需要替换以下的for循环代码:
for (int i = 0; i < row.Descendants<Cell>().Count(); i++)
{
tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants<Cell>().ElementAt(i));
}
带
for (int i = 0; i < row.Descendants<Cell>().Count(); i++)
{
Cell cell = row.Descendants<Cell>().ElementAt(i);
int actualCellIndex = CellReferenceToIndex(cell);
tempRow[actualCellIndex] = GetCellValue(spreadSheetDocument, cell);
}
并在您的代码中添加以下方法,该代码在上面修改过的代码段中用于获取任何单元格的原始/正确列索引:
private static int CellReferenceToIndex(Cell cell)
{
int index = 0;
string reference = cell.CellReference.ToString().ToUpper();
foreach (char ch in reference)
{
if (Char.IsLetter(ch))
{
int value = (int)ch - (int)'A';
index = (index == 0) ? value : ((index + 1) * 26) + value;
}
else
return index;
}
return index;
}
答案 1 :(得分:5)
public void Read2007Xlsx()
{
try
{
DataTable dt = new DataTable();
using (SpreadsheetDocument spreadSheetDocument = SpreadsheetDocument.Open(@"D:\File.xlsx", false))
{
WorkbookPart workbookPart = spreadSheetDocument.WorkbookPart;
IEnumerable<Sheet> sheets = spreadSheetDocument.WorkbookPart.Workbook.GetFirstChild<Sheets>().Elements<Sheet>();
string relationshipId = sheets.First().Id.Value;
WorksheetPart worksheetPart = (WorksheetPart)spreadSheetDocument.WorkbookPart.GetPartById(relationshipId);
Worksheet workSheet = worksheetPart.Worksheet;
SheetData sheetData = workSheet.GetFirstChild<SheetData>();
IEnumerable<Row> rows = sheetData.Descendants<Row>();
foreach (Cell cell in rows.ElementAt(0))
{
dt.Columns.Add(GetCellValue(spreadSheetDocument, cell));
}
foreach (Row row in rows) //this will also include your header row...
{
DataRow tempRow = dt.NewRow();
int columnIndex = 0;
foreach (Cell cell in row.Descendants<Cell>())
{
// Gets the column index of the cell with data
int cellColumnIndex = (int)GetColumnIndexFromName(GetColumnName(cell.CellReference));
cellColumnIndex--; //zero based index
if (columnIndex < cellColumnIndex)
{
do
{
tempRow[columnIndex] = ""; //Insert blank data here;
columnIndex++;
}
while (columnIndex < cellColumnIndex);
}
tempRow[columnIndex] = GetCellValue(spreadSheetDocument, cell);
columnIndex++;
}
dt.Rows.Add(tempRow);
}
}
dt.Rows.RemoveAt(0); //...so i'm taking it out here.
}
catch (Exception ex)
{
}
}
/// <summary>
/// Given a cell name, parses the specified cell to get the column name.
/// </summary>
/// <param name="cellReference">Address of the cell (ie. B2)</param>
/// <returns>Column Name (ie. B)</returns>
public static string GetColumnName(string cellReference)
{
// Create a regular expression to match the column name portion of the cell name.
Regex regex = new Regex("[A-Za-z]+");
Match match = regex.Match(cellReference);
return match.Value;
}
/// <summary>
/// Given just the column name (no row index), it will return the zero based column index.
/// Note: This method will only handle columns with a length of up to two (ie. A to Z and AA to ZZ).
/// A length of three can be implemented when needed.
/// </summary>
/// <param name="columnName">Column Name (ie. A or AB)</param>
/// <returns>Zero based index if the conversion was successful; otherwise null</returns>
public static int? GetColumnIndexFromName(string columnName)
{
//return columnIndex;
string name = columnName;
int number = 0;
int pow = 1;
for (int i = name.Length - 1; i >= 0; i--)
{
number += (name[i] - 'A' + 1) * pow;
pow *= 26;
}
return number;
}
public static string GetCellValue(SpreadsheetDocument document, Cell cell)
{
SharedStringTablePart stringTablePart = document.WorkbookPart.SharedStringTablePart;
if (cell.CellValue ==null)
{
return "";
}
string value = cell.CellValue.InnerXml;
if (cell.DataType != null && cell.DataType.Value == CellValues.SharedString)
{
return stringTablePart.SharedStringTable.ChildElements[Int32.Parse(value)].InnerText;
}
else
{
return value;
}
}
答案 2 :(得分:0)
试试这段代码,我做了一些修改,对我有用。
public static DataTable Fill_dataTable(string filePath)
{
DataTable dt = new DataTable();
using (SpreadsheetDocument doc = SpreadsheetDocument.Open(filePath, false))
{
Sheet sheet = doc.WorkbookPart.Workbook.Sheets.GetFirstChild<Sheet>();
Worksheet worksheet = doc.WorkbookPart.GetPartById(sheet.Id.Value) as WorksheetPart.Worksheet;
IEnumerable<Row> rows = worksheet.GetFirstChild<SheetData>().Descendants<Row>();
DataTable dt = new DataTable();
List<string> columnRef = new List<string>();
foreach (Row row in rows)
{
if (row.RowIndex != null)
{
if (row.RowIndex.Value == 1)
{
foreach (Cell cell in row.Descendants<Cell>())
{
dt.Columns.Add(GetValue(doc, cell));
columnRef.Add(cell.CellReference.ToString().Substring(0, cell.CellReference.ToString().Length - 1));
}
}
else
{
dt.Rows.Add();
int i = 0;
foreach (Cell cell in row.Descendants<Cell>())
{
while (columnRef(i) + dt.Rows.Count + 1 != cell.CellReference)
{
dt.Rows(dt.Rows.Count - 1)(i) = "";
i += 1;
}
dt.Rows(dt.Rows.Count - 1)(i) = GetValue(doc, cell);
i += 1;
}
}
}
}
}
return dt;
}