#requires -version 2.0

<#
 -----------------------------------------------------------------------------
 Script: Get-ContentWords.ps1
 Version: 0.1
 Author: Jeffery Hicks
    http://jdhitsolutions.com/blog
    http://twitter.com/JeffHicks
    http://www.ScriptingGeek.com
 Date: 1/24/2012
 Keywords:
 Comments:

  Get a list of sorted unique "words" from a text file
  or script. Good way to catch typos.
 "Those who forget to script are doomed to repeat their work."

  ****************************************************************
  * DO NOT USE IN A PRODUCTION ENVIRONMENT UNTIL YOU HAVE TESTED *
  * THOROUGHLY IN A LAB ENVIRONMENT. USE AT YOUR OWN RISK.  IF   *
  * YOU DO NOT UNDERSTAND WHAT THIS SCRIPT DOES OR HOW IT WORKS, *
  * DO NOT USE IT OUTSIDE OF A SECURE, TEST SETTING.             *
  ****************************************************************
 -----------------------------------------------------------------------------
 #>
 

Function Get-ContentWords {

[cmdletbinding()]

Param (
[Parameter(Position=0,Mandatory=$True,
HelpMessage="Enter the filename for your text file",
ValueFromPipeline=$True)]
[string]$Path
)

Begin {
    Set-StrictMode -Version 2.0
    
    Write-Verbose "Starting $($myinvocation.mycommand)"
    
    #define a regular expression pattern to detect "words"
    [regex]$word="\b\S+\b"
}

Process {

    if ($path.gettype().Name -eq "FileInfo") {
      #$Path is a file object
      Write-Verbose "Getting content from $($Path.Fullname)"
      $content=Get-Content -Path $path.Fullname
    }
    else {
        #$Path is a string
        Write-Verbose "Getting content from $path"
        $content=get-content -Path $Path
    }

    #add a little information
    $stats=$content | Measure-Object -Word
    Write-Verbose "Found approximately $($stats.words) words"

    #write sorted unique values
    $word.Matches($content) | select Value -unique | sort Value
 }
 
End {
    Write-Verbose "Ending $($myinvocation.mycommand)"
    }
    
} #close function