Merge pull request #1695 from scriptingstudio/master

[Get-HtmlTable] XPath optimization

.github/workflows/ci.yml

@@ -3,9 +3,12 @@ on:
     branches:
       - master
       - Set-up-GHA-CI/CD
+    paths-ignore:
+      - 'Examples/**'
       
   pull_request:
   
+
 jobs:
   validate:
     runs-on: ${{ matrix.os }}

Examples/Charts/ChartDataSeparatePage.ps1

@@ -0,0 +1,35 @@
+$data = ConvertFrom-Csv @"
+Region,State,Units,Price
+West,Texas,927,923.71
+North,Tennessee,466,770.67
+East,Florida,520,458.68
+East,Maine,828,661.24
+West,Virginia,465,053.58
+North,Missouri,436,235.67
+South,Kansas,214,992.47
+North,North Dakota,789,640.72
+South,Delaware,712,508.55
+"@
+
+$xlfile = "$PSScriptRoot\spike.xlsx"
+Remove-Item $xlfile -ErrorAction SilentlyContinue
+
+$xlpkg = $data | Export-Excel $xlfile -WorksheetName Data -AutoNameRange -PassThru
+
+$null = Add-Worksheet -ExcelPackage $xlpkg -WorksheetName Summary -Activate
+
+$params = @{
+    Worksheet = $xlpkg.Summary
+    Title     = "Sales by Region"
+    ChartType = 'ColumnClustered'
+    
+    # XRange    = "Data!A2:A10"
+    # YRange    = "Data!C2:C10"
+
+    XRange    = 'Data!Region'
+    YRange    = 'Data!Units'
+}
+
+Add-ExcelChart  @params
+
+Close-ExcelPackage $xlpkg -Show

ImportExcel.psd1

@@ -6,7 +6,7 @@
     RootModule         = 'ImportExcel.psm1'
 
     # Version number of this module.
-    ModuleVersion      = '7.8.4'
+    ModuleVersion      = '7.8.10'
 
     # ID used to uniquely identify this module
     GUID               = '60dd4136-feff-401a-ba27-a84458c57ede'
@@ -54,6 +54,7 @@ Check out the How To Videos https://www.youtube.com/watch?v=U3Ne_yX4tYo&list=PL5
         'Export-Excel',
         'Export-ExcelSheet',        
         'Get-ExcelColumnName',
+        'Get-ExcelFileSchema',
         'Get-ExcelFileSummary', 
         'Get-ExcelSheetDimensionAddress',       
         'Get-ExcelSheetInfo',
@@ -149,7 +150,7 @@ Check out the How To Videos https://www.youtube.com/watch?v=U3Ne_yX4tYo&list=PL5
             Tags         = @("Excel", "EPPlus", "Export", "Import")
 
             # The web address of an icon which can be used in galleries to represent this module
-            #IconUri = "http://pesterbdd.com/images/Pester.png"
+            #IconUri = 
 
             # The web address of this module's project or support homepage.
             ProjectUri   = "https://github.com/dfinke/ImportExcel"

Private/ArgumentCompletion.ps1

@@ -67,9 +67,8 @@ function WorksheetArgumentCompleter {
     param($commandName, $parameterName, $wordToComplete, $commandAst, $fakeBoundParameter)
     $xlPath = $fakeBoundParameter['Path']
     if (Test-Path -Path $xlPath) {
-        $xlpkg = Open-ExcelPackage -ReadOnly -Path $xlPath
+        $xlSheet = Get-ExcelSheetInfo -Path $xlPath
-        $WorksheetNames = $xlPkg.Workbook.Worksheets.Name
+        $WorksheetNames = $xlSheet.Name
-        Close-ExcelPackage -nosave -ExcelPackage $xlpkg
         $WorksheetNames.where( { $_ -like "*$wordToComplete*" }) | foreach-object {
             New-Object -TypeName System.Management.Automation.CompletionResult -ArgumentList "'$_'",
             $_ , ([System.Management.Automation.CompletionResultType]::ParameterValue) , $_

Public/ConvertFrom-ExcelData.ps1

@@ -8,7 +8,8 @@ function ConvertFrom-ExcelData {
         [ScriptBlock]$ScriptBlock,
         [Alias("Sheet")]
         $WorksheetName = 1,
-        [int]$HeaderRow = 1,
+		[Alias('HeaderRow', 'TopRow')]
+        [int]$StartRow = 1,
         [string[]]$Header,
         [switch]$NoHeader,
         [switch]$DataOnly

Public/ConvertTo-ExcelXlsx.ps1

@@ -45,11 +45,18 @@ function ConvertTo-ExcelXlsx {
             throw "Could not create Excel.Application ComObject. Please verify that Excel is installed."
         }
 
-        $Excel.Visible = $false
+        try {  
-        $null = $Excel.Workbooks.Open($xlsFile.FullName)
+            $Excel.Visible = $false
-        $Excel.ActiveWorkbook.SaveAs($xlsxPath, $xlFixedFormat)
+            $null = $Excel.Workbooks.Open($xlsFile.FullName, $null, $true)
-        $Excel.ActiveWorkbook.Close()
+            $Excel.ActiveWorkbook.SaveAs($xlsxPath, $xlFixedFormat)
-        $Excel.Quit()
+        }
+        finally {
+            if ($null -ne $Excel.ActiveWorkbook) {
+                $Excel.ActiveWorkbook.Close()
+            }
+            
+            $Excel.Quit()
+        }
     }
 }
 

Public/Get-ExcelFileSchema.ps1

@@ -0,0 +1,47 @@
+function Get-ExcelFileSchema {
+    <#
+        .SYNOPSIS
+            Gets the schema of an Excel file.
+
+        .DESCRIPTION
+            The Get-ExcelFileSchema function gets the schema of an Excel file by returning the property names of the first row of each worksheet in the file.
+
+        .PARAMETER Path
+            Specifies the path to the Excel file.
+
+        .PARAMETER Compress
+            Indicates whether to compress the json output.
+
+        .OUTPUTS
+            Json
+
+        .EXAMPLE
+            Get-ExcelFileSchema -Path .\example.xlsx
+    #>
+
+    [CmdletBinding()]
+    param(
+        [Parameter(ValueFromPipelineByPropertyName, Mandatory)]
+        [Alias('FullName')]    
+        $Path,
+        [Switch]$Compress
+    )
+
+    Begin {
+        $result = @()
+    }
+
+    Process {        
+        $excelFiles = Get-ExcelFileSummary $Path
+        
+        foreach ($excelFile in $excelFiles) {
+            $data = Import-Excel $Path -WorksheetName $excelFile.WorksheetName | Select-Object -First 1
+            $names = $data[0].PSObject.Properties.name
+            $result += $excelFile | Add-Member -MemberType NoteProperty -Name "PropertyNames" -Value $names -PassThru
+        }
+    }
+
+    End {
+        $result | ConvertTo-Json -Compress:$Compress
+    }
+}

Public/Get-HtmlTable.ps1

@@ -50,7 +50,9 @@ function Get-HtmlTable {
     else {
         $h    = ConvertFrom-Html -Content $r.Content
         if ($TableIndex -is [valuetype]) { $TableIndex += 1}
-        $rows =    $h.SelectNodes("//table[$TableIndex]//tr")
+        $rows = try {
+               $h.SelectSingleNode("//table[$TableIndex]").SelectNodes(".//tr")
+        } catch {}
         if (-not $rows) {Write-Warning "Could not find rows for `"//table[$TableIndex]`" in $Url ."}
         if ( -not  $propertyNames) {
             if (   $tableHeaders  = $rows[$FirstDataRow].SelectNodes("th")) {

Public/Import-Excel.ps1

@@ -37,8 +37,7 @@
         [ValidateNotNullOrEmpty()]
         [String]$Password,
         [Int[]]$ImportColumns,
-        [Switch]$Raw,
+        [Switch]$Raw
-        [Switch]$UseSpectre
     )
     end {
         $sw = [System.Diagnostics.Stopwatch]::StartNew()
@@ -253,9 +252,6 @@
                         $entry.Value
                     }
                 }
-                elseif ($UseSpectre) {
-                    $xlBook | Format-SpectreTable
-                }
                 elseif ($Worksheet.Count -eq 1) {
                     $xlBook["$targetSheetname"]
                 }

README.md

@@ -19,10 +19,13 @@ Consider donating. Thank you!
 <br>
 <br>
 
-[![Build Status](https://dougfinke.visualstudio.com/ImportExcel/_apis/build/status/dfinke.ImportExcel?branchName=master)](https://dougfinke.visualstudio.com/ImportExcel/_build)
+[![Follow on Twitter](https://img.shields.io/twitter/follow/dfinke.svg?style=social&label=Follow%20%40dfinke)](https://twitter.com/dfinke)
+[![Subscribe on YouTube](https://img.shields.io/youtube/channel/subscribers/UCP47ZkO5EDkoI2sr-3P4ShQ
+)](https://youtube.com/@dougfinke/)
+<br/>
+<br/>
 [![](https://img.shields.io/powershellgallery/v/ImportExcel.svg)](https://www.powershellgallery.com/packages/ImportExcel)
 [![](https://img.shields.io/powershellgallery/dt/ImportExcel.svg)](https://www.powershellgallery.com/packages/ImportExcel)
-[![](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/dfinke/ImportExcel/tree/70ab9e46c776e96fb287682d5b9b4b51a0ec3bac/LICENSE.txt)
 <a href="https://www.paypal.com/paypalme/DougCharlesFinke"><img src="https://img.shields.io/badge/Donate-PayPal-green.svg" alt="Donate"></a>
 
 # Overview

__tests__/Get-ExcelFileSchema.tests.ps1

@@ -0,0 +1,54 @@
+if (-not (Get-command Import-Excel -ErrorAction SilentlyContinue)) {
+    Import-Module $PSScriptRoot\..\ImportExcel.psd1
+}
+
+Describe "Test getting the schema of an Excel file" -Tag GetExcelFileSchema {
+
+    BeforeAll {
+        $script:excelFile = "TestDrive:\test.xlsx"
+        $data = ConvertFrom-Csv @"
+Region,State,Units,Price
+West,Texas,927,923.71
+North,Tennessee,466,770.67
+East,Florida,520,458.68
+East,Maine,828,661.24
+West,Virginia,465,053.58
+North,Missouri,436,235.67
+South,Kansas,214,992.47
+North,North Dakota,789,640.72
+South,Delaware,712,508.55
+"@
+        $data | Export-Excel $excelFile 
+    }
+
+    It "Test Get-ExcelFileSchema function exists" {        
+        $function = Get-Command Get-ExcelFileSchema -ErrorAction SilentlyContinue
+        $function | Should -Not -Be $null
+    }
+
+    It "Test Get-ExcelFileSchema returns json" {
+        $actual = Get-ExcelFileSchema -Path $excelFile
+        $actual | Should -Not -Be $null
+        $actual | Should -BeOfType [string]        
+    }
+
+    It "Test Get-ExcelFileSchema correct json" {
+        $actual = Get-ExcelFileSchema -Path $excelFile
+        $actual = $actual | ConvertFrom-Json 
+
+        $actual.ExcelFile | Should -BeExactly "test.xlsx"
+        $actual.WorksheetName | Should -BeExactly "Sheet1"
+        $actual.Visible | Should -Be $true
+        $actual.Rows | Should -Be 10
+        $actual.Columns | Should -Be 4
+        $actual.Address | Should -BeExactly "A1:D10"
+        
+        $actual.Path | Should -BeExactly ("TestDrive:" + [System.IO.Path]::DirectorySeparatorChar)
+        
+        $actual.PropertyNames.Count | Should -Be 4
+        $actual.PropertyNames[0] | Should -BeExactly "Region"
+        $actual.PropertyNames[1] | Should -BeExactly "State"
+        $actual.PropertyNames[2] | Should -BeExactly "Units"
+        $actual.PropertyNames[3] | Should -BeExactly "Price"
+    }
+}

changelog.md

@@ -1,3 +1,60 @@
+# 7.8.10
+
+- Thank you https://github.com/evenmartinsen for the PR to fix the AV
+
+# 7.8.9
+
+- Thanks to (Edward Miller)[https://github.com/edwardmiller-mesirow] for improving `ConvertTo-ExcelXlsx`and making it more robust
+
+# 7.8.8
+
+- Fix the release
+
+# 7.8.7
+
+- Thanks to [Phil Bossman](https://github.com/pbossman) for the PR and fixing this.
+    
+    Now, back again, you can type `Import-Excel .\yearlySales.xlsx`, press <ctrl+space> and get a list of the worksheets in the Excel file
+
+    ![alt text](images/AutoCompleteSheetNames.png)    
+
+# Infrastructure change
+
+- Thank you to [RipFence](https://github.com/RipFence) who asked how to place a chart on a different sheet from the data and then did a PR adding the example.
+- added `ignore` so files checked into examples do not trigger a CI run
+
+# 7.8.6
+
+- Thank you [John Boyne](https://github.com/kyllath)
+    - Add missing parameter aliases to align with caller/callee
+
+# 7.8.5
+
+- Added `Get-ExcelFileSchema` to get the schema of an Excel file.
+- This was added to support interacting with `ChatGPT`. Passing the schema to the `ChatGPT` via `PowerShellAI` let's you ask questions about the data including generating code based on the schema.
+
+```powershell
+Get-ExcelFileSchema .\salesData.xlsx
+```
+
+```json
+{
+  "ExcelFile": "salesData.xlsx",
+  "WorksheetName": "Sheet1",
+  "Visible": true,
+  "Rows": 10,
+  "Columns": 4,
+  "Address": "A1:D10",
+  "Path": ".",
+  "PropertyNames": [
+    "Region",
+    "State",
+    "Units",
+    "Price"
+  ]
+}
+```
+
 # 7.8.x
 
 Thanks to [Thomas Hofkens](https://github.com/thkn-hofa)