在Powershell中合并两个CSV文件，但某些输出条目因缺少数据而加倍
我目前正在为一个工作项目设置文件上传。上传的文件应包含所有项目以及必要的数据和所有变化（如大小或长度）。问题是，我无法将变化数据导出到与常规项目数据相同的文件中，因此我认为，由于我已经使用powershell脚本处理处理和上载，因此我可以在使用powershell上载结果之前合并这两个文件 以下是两个CSV文件的标题：在Powershell中合并两个CSV文件，但某些输出条目因缺少数据而加倍,powershell,csv,merge,pscustomobject,Powershell,Csv,Merge,Pscustomobject,我目前正在为一个工作项目设置文件上传。上传的文件应包含所有项目以及必要的数据和所有变化（如大小或长度）。问题是，我无法将变化数据导出到与常规项目数据相同的文件中，因此我认为，由于我已经使用powershell脚本处理处理和上载，因此我可以在使用powershell上载结果之前合并这两个文件 以下是两个CSV文件的标题： feed_file Artikelnummer,EAN,Hersteller,Produktname,EKPreis,UVP,Produktbeschreibung,Produk
feed_file
Artikelnummer,EAN,Hersteller,Produktname,EKPreis,UVP,Produktbeschreibung,ProduktURL,BildURL,Bestand
variant_file
"VaterArtikelnummer";"Artikelnummer";"UVP";"Bestand";"Variationsname1";"Variationsname2";"Variationsname3";"Variationswertname1";"Variationswertname2";"Variationswertname3";"EKPreis"
$feedFile = import-csv <File>
$Variant = import-csv <File>
函数连接对象{
[CmdletBinding（）]
Param
(
[参数（必需=$true，
ValueFromPipeLine=$true）]
[object[]]$Left，
#用$Left加入的列表
[参数（必需=$true）]
[object[]]$Right，
[参数（必需=$true）]
[字符串]$LeftJoinProperty，
[参数（必需=$true）]
[字符串]$RightJoinProperty，
[object[]$LeftProperties='*'，
#我们希望输出中包含$Right的属性。
#与LeftProperties类似，每个属性可以是普通名称、通配符或哈希表。请参阅LeftProperties注释。
[object[]$RightProperties='*'，
[验证集（'AllInLeft'、'onlyfinboth'、'AllInBoth'、'AllInRight'）]
[参数（必需=$false）]
[string]$Type='AllInLeft'，
[字符串]$前缀，
[字符串]$后缀
)
开始
{
函数AddItemProperty（$item、$properties、$hash）
{
如果（$null-相等$item）
{
返回
}
foreach（$properties中的$properties）
{
$propertyHash=$property-as[hashtable]
如果（$null-ne$propertyHash）
{
$hashName=$propertyHash[“名称”]-作为[字符串]
$expression=$propertyHash[“expression”]-作为[scriptblock]
$expressionValue=$expression.Invoke（$item）[0]
$hash[$hashName]=$expressionValue
}
其他的
{
foreach（$item.psobject.Properties中的itemProperty）
{
if（$itemProperty.Name-类似$property）
{
$hash[$itemProperty.Name]=$itemProperty.Value
}
}
}
}
}
函数TranslateProperties
{
[cmdletbinding（）]
param(
[对象[]]$Properties，
[psobject]$RealObject，
[字符串]$Side）
foreach（$Prop in$Properties）
{
$propertyHash=$Prop-as[hashtable]
如果（$null-ne$propertyHash）
{
$hashName=$propertyHash[“名称”]-作为[字符串]
$expression=$propertyHash[“expression”]-作为[scriptblock]
$ScriptString=$expression.tostring（）
if（$ScriptString-notmatch'param\（'））
{
编写详细的“属性'$HashName'`：将参数（`$\'）添加到脚本块'$ScriptString''
$Expression=[ScriptBlock]：：Create（“参数（`$\`n$ScriptString”）
}
$Output=@{Name=$HashName；Expression=$Expression}
Write Verbose“找到名为$（$Output.name）的$Side属性哈希，表达式：`n$（$Output.expression | out string）”
$Output
}
其他的
{
foreach（$RealObject.psobject.Properties中的ThisProp）
{
if（$ThisProp.Name-类似$Prop）
{
详细写入“找到$Side属性“$（$ThisProp.Name）””
$ThisProp.Name
}
}
}
}
}
函数WriteJoinObjectOutput（$leftItem、$rightItem、$leftProperties、$rightProperties）
{
$properties=@{}
AddItemProperties$leftItem$leftProperties$properties
AddItemProperties$rightItem$rightProperties$properties
"12345678_9",,,,"388,7","894,00",,,,"1","12345678","Größe","","","58","",""
"12345678_9","3210987654321","Hersteller","Produktname","388.70","894","Beschreibung","ProduktURL","BildURL","0","12345678","Größe","","","58","",""
$feedFile = import-csv <File>
$Variant = import-csv <File>
$feedFile | Join-Object -Right $variant_file -LeftJoinProperty ArtikelNummer -RightJoinProperty ArtikelNummer -Type OnlyIfInBoth
function Join-Object {
<#
.SYNOPSIS
Join data from two sets of objects based on a common value
.DESCRIPTION
Join data from two sets of objects based on a common value
For more details, see the accompanying blog post:
http://ramblingcookiemonster.github.io/Join-Object/
For even more details, see the original code and discussions that this borrows from:
Dave Wyatt's Join-Object - http://powershell.org/wp/forums/topic/merging-very-large-collections
Lucio Silveira's Join-Object - http://blogs.msdn.com/b/powershell/archive/2012/07/13/join-object.aspx
.PARAMETER Left
'Left' collection of objects to join. You can use the pipeline for Left.
The objects in this collection should be consistent.
We look at the properties on the first object for a baseline.
.PARAMETER Right
'Right' collection of objects to join.
The objects in this collection should be consistent.
We look at the properties on the first object for a baseline.
.PARAMETER LeftJoinProperty
Property on Left collection objects that we match up with RightJoinProperty on the Right collection
.PARAMETER RightJoinProperty
Property on Right collection objects that we match up with LeftJoinProperty on the Left collection
.PARAMETER LeftProperties
One or more properties to keep from Left. Default is to keep all Left properties (*).
Each property can:
- Be a plain property name like "Name"
- Contain wildcards like "*"
- Be a hashtable like @{Name="Product Name";Expression={$_.Name}}.
Name is the output property name
Expression is the property value ($_ as the current object)
Alternatively, use the Suffix or Prefix parameter to avoid collisions
Each property using this hashtable syntax will be excluded from suffixes and prefixes
.PARAMETER RightProperties
One or more properties to keep from Right. Default is to keep all Right properties (*).
Each property can:
- Be a plain property name like "Name"
- Contain wildcards like "*"
- Be a hashtable like @{Name="Product Name";Expression={$_.Name}}.
Name is the output property name
Expression is the property value ($_ as the current object)
Alternatively, use the Suffix or Prefix parameter to avoid collisions
Each property using this hashtable syntax will be excluded from suffixes and prefixes
.PARAMETER Prefix
If specified, prepend Right object property names with this prefix to avoid collisions
Example:
Property Name = 'Name'
Suffix = 'j_'
Resulting Joined Property Name = 'j_Name'
.PARAMETER Suffix
If specified, append Right object property names with this suffix to avoid collisions
Example:
Property Name = 'Name'
Suffix = '_j'
Resulting Joined Property Name = 'Name_j'
.PARAMETER Type
Type of join. Default is AllInLeft.
AllInLeft will have all elements from Left at least once in the output, and might appear more than once
if the where clause is true for more than one element in right, Left elements with matches in Right are
preceded by elements with no matches.
SQL equivalent: outer left join (or simply left join)
AllInRight is similar to AllInLeft.
OnlyIfInBoth will cause all elements from Left to be placed in the output, only if there is at least one
match in Right.
SQL equivalent: inner join (or simply join)
AllInBoth will have all entries in right and left in the output. Specifically, it will have all entries
in right with at least one match in left, followed by all entries in Right with no matches in left,
followed by all entries in Left with no matches in Right.
SQL equivalent: full join
.EXAMPLE
#
#Define some input data.
$l = 1..5 | Foreach-Object {
[pscustomobject]@{
Name = "jsmith$_"
Birthday = (Get-Date).adddays(-1)
}
}
$r = 4..7 | Foreach-Object{
[pscustomobject]@{
Department = "Department $_"
Name = "Department $_"
Manager = "jsmith$_"
}
}
#We have a name and Birthday for each manager, how do we find their department, using an inner join?
Join-Object -Left $l -Right $r -LeftJoinProperty Name -RightJoinProperty Manager -Type OnlyIfInBoth -RightProperties Department
# Name Birthday Department
# ---- -------- ----------
# jsmith4 4/14/2015 3:27:22 PM Department 4
# jsmith5 4/14/2015 3:27:22 PM Department 5
.EXAMPLE
#
#Define some input data.
$l = 1..5 | Foreach-Object {
[pscustomobject]@{
Name = "jsmith$_"
Birthday = (Get-Date).adddays(-1)
}
}
$r = 4..7 | Foreach-Object{
[pscustomobject]@{
Department = "Department $_"
Name = "Department $_"
Manager = "jsmith$_"
}
}
#We have a name and Birthday for each manager, how do we find all related department data, even if there are conflicting properties?
$l | Join-Object -Right $r -LeftJoinProperty Name -RightJoinProperty Manager -Type AllInLeft -Prefix j_
# Name Birthday j_Department j_Name j_Manager
# ---- -------- ------------ ------ ---------
# jsmith1 4/14/2015 3:27:22 PM
# jsmith2 4/14/2015 3:27:22 PM
# jsmith3 4/14/2015 3:27:22 PM
# jsmith4 4/14/2015 3:27:22 PM Department 4 Department 4 jsmith4
# jsmith5 4/14/2015 3:27:22 PM Department 5 Department 5 jsmith5
.EXAMPLE
#
#Hey! You know how to script right? Can you merge these two CSVs, where Path1's IP is equal to Path2's IP_ADDRESS?
#Get CSV data
$s1 = Import-CSV $Path1
$s2 = Import-CSV $Path2
#Merge the data, using a full outer join to avoid omitting anything, and export it
Join-Object -Left $s1 -Right $s2 -LeftJoinProperty IP_ADDRESS -RightJoinProperty IP -Prefix 'j_' -Type AllInBoth |
Export-CSV $MergePath -NoTypeInformation
.EXAMPLE
#
# "Hey Warren, we need to match up SSNs to Active Directory users, and check if they are enabled or not.
# I'll e-mail you an unencrypted CSV with all the SSNs from gmail, what could go wrong?"
# Import some SSNs.
$SSNs = Import-CSV -Path D:\SSNs.csv
#Get AD users, and match up by a common value, samaccountname in this case:
Get-ADUser -Filter "samaccountname -like 'wframe*'" |
Join-Object -LeftJoinProperty samaccountname -Right $SSNs `
-RightJoinProperty samaccountname -RightProperties ssn `
-LeftProperties samaccountname, enabled, objectclass
.NOTES
This borrows from:
Dave Wyatt's Join-Object - http://powershell.org/wp/forums/topic/merging-very-large-collections/
Lucio Silveira's Join-Object - http://blogs.msdn.com/b/powershell/archive/2012/07/13/join-object.aspx
Changes:
Always display full set of properties
Display properties in order (left first, right second)
If specified, add suffix or prefix to right object property names to avoid collisions
Use a hashtable rather than ordereddictionary (avoid case sensitivity)
.LINK
http://ramblingcookiemonster.github.io/Join-Object/
.FUNCTIONALITY
PowerShell Language
#>
[CmdletBinding()]
Param
(
[Parameter(Mandatory=$true,
ValueFromPipeLine = $true)]
[object[]] $Left,
# List to join with $Left
[Parameter(Mandatory=$true)]
[object[]] $Right,
[Parameter(Mandatory = $true)]
[string] $LeftJoinProperty,
[Parameter(Mandatory = $true)]
[string] $RightJoinProperty,
[object[]]$LeftProperties = '*',
# Properties from $Right we want in the output.
# Like LeftProperties, each can be a plain name, wildcard or hashtable. See the LeftProperties comments.
[object[]]$RightProperties = '*',
[validateset( 'AllInLeft', 'OnlyIfInBoth', 'AllInBoth', 'AllInRight')]
[Parameter(Mandatory=$false)]
[string]$Type = 'AllInLeft',
[string]$Prefix,
[string]$Suffix
)
Begin
{
function AddItemProperties($item, $properties, $hash)
{
if ($null -eq $item)
{
return
}
foreach($property in $properties)
{
$propertyHash = $property -as [hashtable]
if($null -ne $propertyHash)
{
$hashName = $propertyHash["name"] -as [string]
$expression = $propertyHash["expression"] -as [scriptblock]
$expressionValue = $expression.Invoke($item)[0]
$hash[$hashName] = $expressionValue
}
else
{
foreach($itemProperty in $item.psobject.Properties)
{
if ($itemProperty.Name -like $property)
{
$hash[$itemProperty.Name] = $itemProperty.Value
}
}
}
}
}
function TranslateProperties
{
[cmdletbinding()]
param(
[object[]]$Properties,
[psobject]$RealObject,
[string]$Side)
foreach($Prop in $Properties)
{
$propertyHash = $Prop -as [hashtable]
if($null -ne $propertyHash)
{
$hashName = $propertyHash["name"] -as [string]
$expression = $propertyHash["expression"] -as [scriptblock]
$ScriptString = $expression.tostring()
if($ScriptString -notmatch 'param\(')
{
Write-Verbose "Property '$HashName'`: Adding param(`$_) to scriptblock '$ScriptString'"
$Expression = [ScriptBlock]::Create("param(`$_)`n $ScriptString")
}
$Output = @{Name =$HashName; Expression = $Expression }
Write-Verbose "Found $Side property hash with name $($Output.Name), expression:`n$($Output.Expression | out-string)"
$Output
}
else
{
foreach($ThisProp in $RealObject.psobject.Properties)
{
if ($ThisProp.Name -like $Prop)
{
Write-Verbose "Found $Side property '$($ThisProp.Name)'"
$ThisProp.Name
}
}
}
}
}
function WriteJoinObjectOutput($leftItem, $rightItem, $leftProperties, $rightProperties)
{
$properties = @{}
AddItemProperties $leftItem $leftProperties $properties
AddItemProperties $rightItem $rightProperties $properties
New-Object psobject -Property $properties
}
#Translate variations on calculated properties. Doing this once shouldn't affect perf too much.
foreach($Prop in @($LeftProperties + $RightProperties))
{
if($Prop -as [hashtable])
{
foreach($variation in ('n','label','l'))
{
if(-not $Prop.ContainsKey('Name') )
{
if($Prop.ContainsKey($variation) )
{
$Prop.Add('Name',$Prop[$Variation])
}
}
}
if(-not $Prop.ContainsKey('Name') -or $Prop['Name'] -like $null )
{
Throw "Property is missing a name`n. This should be in calculated property format, with a Name and an Expression:`n@{Name='Something';Expression={`$_.Something}}`nAffected property:`n$($Prop | out-string)"
}
if(-not $Prop.ContainsKey('Expression') )
{
if($Prop.ContainsKey('E') )
{
$Prop.Add('Expression',$Prop['E'])
}
}
if(-not $Prop.ContainsKey('Expression') -or $Prop['Expression'] -like $null )
{
Throw "Property is missing an expression`n. This should be in calculated property format, with a Name and an Expression:`n@{Name='Something';Expression={`$_.Something}}`nAffected property:`n$($Prop | out-string)"
}
}
}
$leftHash = @{}
$rightHash = @{}
# Hashtable keys can't be null; we'll use any old object reference as a placeholder if needed.
$nullKey = New-Object psobject
$bound = $PSBoundParameters.keys -contains "InputObject"
if(-not $bound)
{
[System.Collections.ArrayList]$LeftData = @()
}
}
Process
{
#We pull all the data for comparison later, no streaming
if($bound)
{
$LeftData = $Left
}
Else
{
foreach($Object in $Left)
{
[void]$LeftData.add($Object)
}
}
}
End
{
foreach ($item in $Right)
{
$key = $item.$RightJoinProperty
if ($null -eq $key)
{
$key = $nullKey
}
$bucket = $rightHash[$key]
if ($null -eq $bucket)
{
$bucket = New-Object System.Collections.ArrayList
$rightHash.Add($key, $bucket)
}
$null = $bucket.Add($item)
}
foreach ($item in $LeftData)
{
$key = $item.$LeftJoinProperty
if ($null -eq $key)
{
$key = $nullKey
}
$bucket = $leftHash[$key]
if ($null -eq $bucket)
{
$bucket = New-Object System.Collections.ArrayList
$leftHash.Add($key, $bucket)
}
$null = $bucket.Add($item)
}
$LeftProperties = TranslateProperties -Properties $LeftProperties -Side 'Left' -RealObject $LeftData[0]
$RightProperties = TranslateProperties -Properties $RightProperties -Side 'Right' -RealObject $Right[0]
#I prefer ordered output. Left properties first.
[string[]]$AllProps = $LeftProperties
#Handle prefixes, suffixes, and building AllProps with Name only
$RightProperties = foreach($RightProp in $RightProperties)
{
if(-not ($RightProp -as [Hashtable]))
{
Write-Verbose "Transforming property $RightProp to $Prefix$RightProp$Suffix"
@{
Name="$Prefix$RightProp$Suffix"
Expression=[scriptblock]::create("param(`$_) `$_.'$RightProp'")
}
$AllProps += "$Prefix$RightProp$Suffix"
}
else
{
Write-Verbose "Skipping transformation of calculated property with name $($RightProp.Name), expression:`n$($RightProp.Expression | out-string)"
$AllProps += [string]$RightProp["Name"]
$RightProp
}
}
$AllProps = $AllProps | Select -Unique
Write-Verbose "Combined set of properties: $($AllProps -join ', ')"
foreach ( $entry in $leftHash.GetEnumerator() )
{
$key = $entry.Key
$leftBucket = $entry.Value
$rightBucket = $rightHash[$key]
if ($null -eq $rightBucket)
{
if ($Type -eq 'AllInLeft' -or $Type -eq 'AllInBoth')
{
foreach ($leftItem in $leftBucket)
{
WriteJoinObjectOutput $leftItem $null $LeftProperties $RightProperties | Select $AllProps
}
}
}
else
{
foreach ($leftItem in $leftBucket)
{
foreach ($rightItem in $rightBucket)
{
WriteJoinObjectOutput $leftItem $rightItem $LeftProperties $RightProperties | Select $AllProps
}
}
}
}
if ($Type -eq 'AllInRight' -or $Type -eq 'AllInBoth')
{
foreach ($entry in $rightHash.GetEnumerator())
{
$key = $entry.Key
$rightBucket = $entry.Value
$leftBucket = $leftHash[$key]
if ($null -eq $leftBucket)
{
foreach ($rightItem in $rightBucket)
{
WriteJoinObjectOutput $null $rightItem $LeftProperties $RightProperties | Select $AllProps
}
}
}
}
}
}