txt2utf8.ps1

#Requires -version 3.0

##############################################################################
# Filename : txt2utf8.ps1
# Version  : v1.0
# Gist URL : https://gist.github.com/oiotoxt/5586ccbce94ba7018ba4

##############################################################################
#
# Convert text files recursively to UTF-8
#
# \ option : input directory
# \ option : with or without BOM
# \ option : CR+LF ==> LF
# \ option : filter
#
# Assumption
#   Input-file-without-BOM is encoded in system-codepage(e.g. CP1252, CP949)
#
# Hint
#   For Remote Signed : Run <Set-ExecutionPolicy RemoteSigned>
#   For Unrestricted  : Run <Set-ExecutionPolicy Unrestricted>

##############################################################################
# config

# input directory (relative or absolute. write drive-name in capital letter)
$_srcDir = "TextFolder"
#$_srcDir = "C:\TextFolder"

# with or without BOM
$_withBom = $TRUE

# CR+LF ==> LF
$_forceLf = $TRUE

# filter
[String[]] $_include = @("*.*")
#[String[]] $_include = @("*.h", "*.cpp")

# filter
[String[]] $_exclude = @("")
#[String[]] $_exclude = @("*.log")

##############################################################################
# output directory

$_dstDir = $_srcDir

if ($_withBom) {
    $_dstDir = $_dstDir + ".UTF8+BOM"
} else {
    $_dstDir = $_dstDir + ".UTF8+NOBOM"
}

if ($_forceLf) {
    $_dstDir = $_dstDir + "&LF"
}

##############################################################################
# converter ( any ==> UTF8 )

Function ConvertToUtf8(
    [String] $srcDir, [String] $dstDir,
    [String[]] $include, [String[]] $exclude,
    [bool] $withBom, [bool] $forceLF) {

    $cnt = 0
    $encoding = New-Object System.Text.UTF8Encoding($withBom)

    foreach($item in Get-ChildItem $srcDir -Include $include -Exclude $exclude -Recurse) {
        if ($item.PSIsContainer) {
            continue
        }

        if (!$item.Fullname.Contains($srcDir)) {
            Write-Host "Error. Please compare the following two lines."
            Write-Host ">> `$item.Fullname :" $item.Fullname
            Write-Host ">> `$srcDir        :" $srcDir
            return
        }

        $dst = $item.Fullname.Replace($srcDir, $dstDir)

        if (!(Test-Path $(Split-Path $dst -Parent))) {
            New-Item $(Split-Path $dst -Parent) -type Directory
        }

        Get-Content $item |
        Out-File -Filepath $dst -Encoding utf8

        if ($forceLF) {
            $fileContents = [IO.File]::ReadAllText($dst) -Replace "`r`n", "`n"
        } else {
            $fileContents = [IO.File]::ReadAllText($dst)
        }

        [System.IO.File]::WriteAllText($dst, $fileContents, $encoding)

        Write-Host "------------------------------------------------------------------------------"
        Write-Host "`$src   :" $item
        Write-Host "`$dst   :" $dst
        Write-Host "LENGTH :" $item.Length "==>" (Get-Item $dst).Length

        $cnt++
    }

    Write-Host "`n* * * * * * * *" $cnt "file(s) converted * * * * * * * *"
}

##############################################################################
# run

ConvertToUtf8 $_srcDir $_dstDir $_include $_exclude $_withBom $_forceLf

Text 파일들을 UTF8로 일괄 변경해주는 Windows PowerShell 스크립트 입니다.

옵션

• 소스 폴더 지정
• BOM(Byte Order Mark) 붙일지 말지 선택
• 줄바꿈 문자 선택 (CRLF, LF)
• 파일 필터 (*.cpp 만 선택 등)

주의!

• 지정한 소스 폴더 내부에 BOM이 없는 파일이 있다면 현재 시스템의 코드 페이지(한글=CP949)로 인코딩된 파일이라고 가정합니다. (즉 UTF8 파일이 아니라고 가정합니다)

---

시나리오

1. 관리자 권한으로 PowerShell 실행
2. 다음 커맨드 실행

Set-ExecutionPolicy Unrestricted

3. 다음 라인 수정

$_srcDir = "TextFolder"

4. 다음 커맨드 실행

./txt2utf8.ps1