Enhanced OpenXmlImporter with new functionality for retrieving comments and notes

README-V2.md

@@ -342,17 +342,47 @@ var excelImporter = MiniExcel.Importers.GetOpenXmlImporter();
 var sheetNames = excelImporter.GetSheetNames(path);
 ```
 
-#### 6. Get the columns' names from an Excel sheet
+#### 6. Get the columns' names from an Excel worksheet
 
 ```csharp
 var excelImporter = MiniExcel.Importers.GetOpenXmlImporter();
 var columns = excelImporter.GetColumnNames(path); 
 
 // columns = [ColumnName1, ColumnName2, ...] when there is a header row
 // columns = ["A","B",...] otherwise
+
+```
+#### 7. Retrieve Comments from an Excel worksheet
+
+You can extract threaded comments and their replies from a worksheet using the `RetrieveComments` method:
+
+```csharp
+var excelImporter = MiniExcel.Importers.GetOpenXmlImporter(); 
+var comments = excelImporter.RetrieveComments(path, sheetName: "Sheet1").Comments;
+
+foreach (var comment in comments) 
+{
+    Console.WriteLine($"Cell: {comment.CellAddress}");
+    Console.WriteLine($"{comment.CreatedAt:yy-MM-dd HH:mm}, {comment.Author.DisplayName}: {comment.Text}");
+
+    foreach (var reply in comment.Replies)
+    {
+        Console.WriteLine($"{reply.CreatedAt:yy-MM-dd HH:mm}, {reply.Author.DisplayName}: {reply.Text}");    
+    }
+}
+```
+
+You can similarly retrieve notes as well:
+```csharp
+var notes = excelImporter.RetrieveComments(path, sheetName: "Sheet1").Notes;
+foreach (var note in notes) 
+{
+    Console.WriteLine($"Cell: {note.CellAddress}");
+    Console.WriteLine($"{note.Author.DisplayName}: {note.Text}");
+}
 ```
 
-#### 7. Casting dynamic rows to IDictionary
+#### 8. Casting dynamic rows to IDictionary
 
 Under the hood the dynamic objects returned in a query are implemented using `ExpandoObject`,
 making it possible to cast them to `IDictionary<string,object>`:
@@ -370,7 +400,7 @@ foreach(IDictionary<string,object> row in excelImporter.Query(path))
 }
 ```
 
-#### 8. Query Excel sheet as a DataTable
+#### 9. Query Excel worksheet as a DataTable
 
 This is not recommended, as `DataTable` will forcibly load all data into memory, effectively losing the advantages MiniExcel offers.
 
@@ -379,15 +409,15 @@ var excelImporter = MiniExcel.Importers.GetOpenXmlImporter();
 var table = excelImporter.QueryAsDataTable(path);
 ```
 
-#### 9. Specify what cell to start reading data from
+#### 10. Specify what cell to start reading data from
 
 ```csharp
 var excelImporter = MiniExcel.Importers.GetOpenXmlImporter();
 excelImporter.Query(path, startCell: "B3")
 ```
 ![image](https://user-images.githubusercontent.com/12729184/117260316-8593c400-ae81-11eb-9877-c087b7ac2b01.png)
 
-#### 10. Fill Merged Cells
+#### 11. Fill Merged Cells
 
 If the Excel sheet being queried contains merged cells it is possble to enable the option to fill every row with the merged value.
 
@@ -410,7 +440,7 @@ Filling of cells with variable width and height is also supported
 >Note: The performance will take a hit when enabling the feature.
 >This happens because in the OpenXml standard the `mergeCells` are indicated at the bottom of the file, which leads to the need of reading the whole sheet twice.
 
-#### 11. Big files and disk-based cache
+#### 12. Big files and disk-based cache
 
 If the SharedStrings file size exceeds 5 MB, MiniExcel will default to use a local disk cache.
 E.g: on the file [10x100000.xlsx](https://github.com/MiniExcel/MiniExcel/files/8403819/NotDuplicateSharedStrings_10x100000.xlsx) (one million rows of data), when disabling the disk cache the maximum memory usage is 195 MB, but with disk cache enabled only 65 MB of memory are used. 

src/Directory.Packages.props

@@ -1,6 +1,6 @@
 <Project>
   <ItemGroup>
-    <PackageReference Include="Zomp.SyncMethodGenerator" Version="1.6.13" PrivateAssets="all" IncludeAssets="runtime; build; native; contentfiles; analyzers; buildtransitive" />
+    <PackageReference Include="Zomp.SyncMethodGenerator" Version="[1.6.13]" PrivateAssets="all" IncludeAssets="runtime; build; native; contentfiles; analyzers; buildtransitive" />
   </ItemGroup>
   <ItemGroup Condition="'$(TargetFramework)' == 'netstandard2.0'">
     <PackageReference Include="Microsoft.Bcl.Memory" Version="10.0.5" />

src/MiniExcel.Core/WriteAdapters/DataReaderWriteAdapter.cs

@@ -18,7 +18,7 @@
         {
             var columnName = _reader.GetName(i);
             if (!_configuration.DynamicColumnFirst || 
-                _configuration.DynamicColumns.Any(d => string.Equals(d.Key, columnName, StringComparison.OrdinalIgnoreCase)))
+                _configuration.DynamicColumns?.Any(d => string.Equals(d.Key, columnName, StringComparison.OrdinalIgnoreCase)) is true)
             {
                 var map = ColumnMappingsProvider.GetColumnMappingFromDynamicConfiguration(columnName, _configuration);
                 mappings.Add(map);
@@ -47,7 +47,7 @@
             if (map is not { ExcelIgnoreColumn: true })
             {
                 var columnIndex = _configuration.DynamicColumnFirst 
                     ? _reader.GetOrdinal(map.Key.ToString())
                     : i;
 
                 result.Add(new CellWriteInfo(_reader.GetValue(columnIndex), column, map));

src/MiniExcel.OpenXml/Api/OpenXmlExporter.cs

@@ -18,7 +18,12 @@ public async Task<int> InsertSheetAsync(string path, object value, string? sheet
             return rowsWritten.FirstOrDefault();
         }
 
+#if NET8_0_OR_GREATER
+        var stream = new FileStream(path, FileMode.Open, FileAccess.ReadWrite, FileShare.Read, 4096, FileOptions.SequentialScan);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = new FileStream(path, FileMode.Open, FileAccess.ReadWrite, FileShare.Read, 4096, FileOptions.SequentialScan);
+#endif
         return await InsertSheetAsync(stream, value, sheetName, printHeader, overwriteSheet, configuration, progress, cancellationToken).ConfigureAwait(false);
     }
 
@@ -46,8 +51,13 @@ public async Task<int[]> ExportAsync(string path, object value, bool printHeader
             throw new NotSupportedException("MiniExcel's Export does not support the .xlsm format");
 
         var filePath = path.EndsWith(".xlsx",  StringComparison.InvariantCultureIgnoreCase) ? path : $"{path}.xlsx" ;
-
+
+#if NET8_0_OR_GREATER
+        var stream = overwriteFile ? File.Create(filePath) : new FileStream(filePath, FileMode.CreateNew);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = overwriteFile ? File.Create(filePath) : new FileStream(filePath, FileMode.CreateNew);
+#endif
         return await ExportAsync(stream, value, printHeader, sheetName, configuration, progress, cancellationToken).ConfigureAwait(false);
     }
 

src/MiniExcel.OpenXml/Api/OpenXmlImporter.cs

@@ -1,4 +1,3 @@
-using System.Dynamic;
 using MiniExcelLib.OpenXml;
 using OpenXmlReader = MiniExcelLib.OpenXml.OpenXmlReader;
 
@@ -16,11 +15,14 @@ public async IAsyncEnumerable<T> QueryAsync<T>(string path, string? sheetName =
         string startCell = "A1", bool treatHeaderAsData = false, OpenXmlConfiguration? configuration = null,
         [EnumeratorCancellation] CancellationToken cancellationToken = default) where T : class, new()
     {
+#if NET8_0_OR_GREATER
+        var stream = FileHelper.OpenSharedRead(path);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = FileHelper.OpenSharedRead(path);
-
+#endif
         var query = QueryAsync<T>(stream, sheetName, startCell, treatHeaderAsData, configuration, cancellationToken);
 
-        //Foreach yield return twice reason : https://stackoverflow.com/questions/66791982/ienumerable-extract-code-lazy-loading-show-stream-was-not-readable
         await foreach (var item in query.ConfigureAwait(false))
             yield return item; 
     }
@@ -40,7 +42,13 @@ public async IAsyncEnumerable<dynamic> QueryAsync(string path, bool useHeaderRow
         string? sheetName = null, string startCell = "A1", OpenXmlConfiguration? configuration = null,
         [EnumeratorCancellation] CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = FileHelper.OpenSharedRead(path);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = FileHelper.OpenSharedRead(path);
+#endif
+
         await foreach (var item in QueryAsync(stream, useHeaderRow, sheetName, startCell, configuration, cancellationToken).ConfigureAwait(false))
             yield return item;
     }
@@ -72,7 +80,12 @@ public async IAsyncEnumerable<dynamic> QueryRangeAsync(string path, bool useHead
         string? sheetName = null, string startCell = "A1", string endCell = "", OpenXmlConfiguration? configuration = null,
         [EnumeratorCancellation] CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = FileHelper.OpenSharedRead(path);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = FileHelper.OpenSharedRead(path);
+#endif
         await foreach (var item in QueryRangeAsync(stream, useHeaderRow, sheetName, startCell, endCell, configuration, cancellationToken).ConfigureAwait(false))
             yield return item;
     }
@@ -93,7 +106,12 @@ public async IAsyncEnumerable<dynamic> QueryRangeAsync(string path, bool useHead
         int? endColumnIndex = null, OpenXmlConfiguration? configuration = null,
         [EnumeratorCancellation] CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = FileHelper.OpenSharedRead(path);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = FileHelper.OpenSharedRead(path);
+#endif
         await foreach (var item in QueryRangeAsync(stream, useHeaderRow, sheetName, startRowIndex, startColumnIndex, endRowIndex, endColumnIndex, configuration, cancellationToken).ConfigureAwait(false))
             yield return item;
     }
@@ -121,7 +139,12 @@ public async Task<DataTable> QueryAsDataTableAsync(string path, bool useHeaderRo
         string? sheetName = null, string startCell = "A1", OpenXmlConfiguration? configuration = null,
         CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = FileHelper.OpenSharedRead(path);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = FileHelper.OpenSharedRead(path);
+#endif
         return await QueryAsDataTableAsync(stream, useHeaderRow, sheetName, startCell, configuration, cancellationToken).ConfigureAwait(false);
     }
 
@@ -133,7 +156,6 @@ public async Task<DataTable> QueryAsDataTableAsync(Stream stream, bool useHeader
         string? sheetName = null, string startCell = "A1", OpenXmlConfiguration? configuration = null,
         CancellationToken cancellationToken = default)
     {
-        /*Issue #279*/
         sheetName ??= (await GetSheetNamesAsync(stream, configuration, cancellationToken).ConfigureAwait(false)).First();
 
         var dt = new DataTable(sheetName);
@@ -187,7 +209,12 @@ public async Task<DataTable> QueryAsDataTableAsync(Stream stream, bool useHeader
     [CreateSyncVersion]
     public async Task<List<string>> GetSheetNamesAsync(string path, OpenXmlConfiguration? config = null, CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = FileHelper.OpenSharedRead(path);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = FileHelper.OpenSharedRead(path);
+#endif
         return await GetSheetNamesAsync(stream, config, cancellationToken).ConfigureAwait(false);
     }
 
@@ -207,7 +234,12 @@ public async Task<List<string>> GetSheetNamesAsync(Stream stream, OpenXmlConfigu
     [CreateSyncVersion]
     public async Task<List<SheetInfo>> GetSheetInformationsAsync(string path, OpenXmlConfiguration? config = null, CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = FileHelper.OpenSharedRead(path);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = FileHelper.OpenSharedRead(path);
+#endif
         return await GetSheetInformationsAsync(stream, config, cancellationToken).ConfigureAwait(false);
     }
 
@@ -226,7 +258,12 @@ public async Task<List<SheetInfo>> GetSheetInformationsAsync(Stream stream, Open
     [CreateSyncVersion]
     public async Task<IList<ExcelRange>> GetSheetDimensionsAsync(string path, CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = FileHelper.OpenSharedRead(path);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = FileHelper.OpenSharedRead(path);
+#endif
         return await GetSheetDimensionsAsync(stream, cancellationToken).ConfigureAwait(false);
     }
 
@@ -242,7 +279,12 @@ public async Task<ICollection<string>> GetColumnNamesAsync(string path, bool use
         string? sheetName = null, string startCell = "A1", OpenXmlConfiguration? configuration = null,
         CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = FileHelper.OpenSharedRead(path);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = FileHelper.OpenSharedRead(path);
+#endif
         return await GetColumnNamesAsync(stream, useHeaderRow, sheetName, startCell, configuration, cancellationToken).ConfigureAwait(false);
     }
 
@@ -260,6 +302,25 @@ public async Task<ICollection<string>> GetColumnNamesAsync(Stream stream, bool u
         return [];
     }
 
+    [CreateSyncVersion]
+    public async Task<CommentResultSet> RetrieveCommentsAsync(string path, string? sheetName, CancellationToken cancellationToken = default)
+    {
+#if NET8_0_OR_GREATER
+        var stream = FileHelper.OpenSharedRead(path);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
+        using var stream = FileHelper.OpenSharedRead(path);
+#endif
+        return await RetrieveCommentsAsync(stream, sheetName, cancellationToken).ConfigureAwait(false);
+    }
+
+    [CreateSyncVersion]
+    public async Task<CommentResultSet> RetrieveCommentsAsync(Stream stream, string? sheetName, CancellationToken cancellationToken = default)
+    {
+        using var reader = await OpenXmlReader.CreateAsync(stream, null, cancellationToken).ConfigureAwait(false);
+        return await reader.ReadCommentsAsync(sheetName, cancellationToken).ConfigureAwait(false);
+    }
+
     #endregion
 
     #region DataReader

src/MiniExcel.OpenXml/Api/OpenXmlTemplater.cs

@@ -13,7 +13,12 @@ internal OpenXmlTemplater() { }
     [CreateSyncVersion]
     public async Task AddPictureAsync(string path, CancellationToken cancellationToken = default, params MiniExcelPicture[] images)
     {
+#if NET8_0_OR_GREATER
+        var stream = File.Open(path, FileMode.OpenOrCreate);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = File.Open(path, FileMode.OpenOrCreate);
+#endif
         await MiniExcelPictureImplement.AddPictureAsync(stream, cancellationToken, images).ConfigureAwait(false);
     }
 
@@ -27,15 +32,26 @@ public async Task AddPictureAsync(Stream excelStream, CancellationToken cancella
     public async Task FillTemplateAsync(string path, string templatePath, object value, bool overwriteFile = false,
         OpenXmlConfiguration? configuration = null, CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = overwriteFile ? File.Create(path) : File.Open(path, FileMode.CreateNew);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = overwriteFile ? File.Create(path) : File.Open(path, FileMode.CreateNew);
+#endif
         await FillTemplateAsync(stream, templatePath, value, configuration, cancellationToken).ConfigureAwait(false);
     }
 
     [CreateSyncVersion]
     public async Task FillTemplateAsync(string path, Stream templateStream, object value, bool  overwriteFile = false,
         OpenXmlConfiguration? configuration = null, CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = overwriteFile ? File.Create(path) : File.Open(path, FileMode.CreateNew);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = overwriteFile ? File.Create(path) : File.Open(path, FileMode.CreateNew);
+#endif
+
         var template = GetOpenXmlTemplate(stream, configuration);
         await template.SaveAsByTemplateAsync(templateStream, value, cancellationToken).ConfigureAwait(false);
     }
@@ -60,7 +76,12 @@ public async Task FillTemplateAsync(Stream stream, Stream templateStream, object
     public async Task FillTemplateAsync(string path, byte[] templateBytes, object value, bool overwriteFile = false,
         OpenXmlConfiguration? configuration = null, CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = overwriteFile ? File.Create(path) :  File.Open(path, FileMode.CreateNew);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = overwriteFile ? File.Create(path) :  File.Open(path, FileMode.CreateNew);
+#endif
         await FillTemplateAsync(stream, templateBytes, value, configuration, cancellationToken).ConfigureAwait(false);
     }
 
@@ -78,7 +99,12 @@ public async Task FillTemplateAsync(Stream stream, byte[] templateBytes, object
     public async Task MergeSameCellsAsync(string mergedFilePath, string path,
         OpenXmlConfiguration? configuration = null, CancellationToken cancellationToken = default)
     {
+#if NET8_0_OR_GREATER
+        var stream = File.Create(mergedFilePath);
+        await using var disposableStream = stream.ConfigureAwait(false); 
+#else
         using var stream = File.Create(mergedFilePath);
+#endif
         await MergeSameCellsAsync(stream, path, configuration, cancellationToken).ConfigureAwait(false);
     }
 

src/MiniExcel.OpenXml/Constants/Schemas.cs

@@ -2,9 +2,16 @@
 
 internal static class Schemas
 {
-    public const string SpreadsheetmlXmlns = "http://schemas.openxmlformats.org/spreadsheetml/2006/main";
-    public const string SpreadsheetmlXmlStrictns = "http://purl.oclc.org/ooxml/spreadsheetml/main";
-    public const string SpreadsheetmlXmlRelationshipns = "http://schemas.openxmlformats.org/officeDocument/2006/relationships";
-    public const string SpreadsheetmlXmlStrictRelationshipns = "http://purl.oclc.org/ooxml/officeDocument/relationships";
+    public const string SpreadsheetmlXmlNs = "http://schemas.openxmlformats.org/spreadsheetml/2006/main";
+    public const string SpreadsheetmlXmlStrictNs = "http://purl.oclc.org/ooxml/spreadsheetml/main";
+
+    public const string OpenXmlPackageRelationships = "http://schemas.openxmlformats.org/package/2006/relationships";
+    public const string SpreadsheetmlXmlRelationships = "http://schemas.openxmlformats.org/officeDocument/2006/relationships";
+    public const string SpreadsheetmlXmlStrictRelationships = "http://purl.oclc.org/ooxml/officeDocument/relationships";
+    public const string SpreadsheetmlXmlComments = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/comments";
+    public const string SpreadsheetmlXmlThreadedComment = "http://schemas.microsoft.com/office/2017/10/relationships/threadedComment";
+
     public const string SpreadsheetmlXmlX14Ac = "http://schemas.microsoft.com/office/spreadsheetml/2009/9/ac";
-}
+    public const string SpreadsheetmlXmlX18Tc = "http://schemas.microsoft.com/office/spreadsheetml/2018/threadedcomments";
+    public const string SpreadsheetmlXmlX14R = "http://schemas.microsoft.com/office/spreadsheetml/2014/revision";
+}