getCodepage.groovy

// 文字コード判定
// ソースコードのコードページを再帰的に判定し続ける

import com.ibm.icu.text.CharsetDetector
@Grab(group='com.ibm.icu', module='icu4j', version='56.1')
def detector = new CharsetDetector()

// UTF-8, UTF-16 UTF-32, Windows-31j
// ISO-8859-2, windows-1252, windows-1250, ISO-8859-2, ISO-8859-1, Big5, UTF-16LE

new File(".").eachFileRecurse { file -> 
    if(file.isFile() && 
      (file.name.endsWith("TXT")||
       file.name.endsWith("RPGLE")||
       file.name.endsWith("CLP")||
       file.name.endsWith("PF")||
       file.name.endsWith("LF")||
       file.name.endsWith("DSPF")||
       file.name.endsWith("PRTF")||
       file.name.endsWith("RPGLE")||
       file.name.endsWith("cpy")||
       file.name.endsWith("txt")||
       file.name.endsWith("java")||
       file.name.endsWith("text")||
       file.name.endsWith("cbl")||
       file.name.endsWith("jcl")) ) { 
        curName  = file.getPath().replaceAll(/.\\(.*)/) {m0,m1 -> m1}
        bytes1 = new File(curName).getBytes()
        fileCodepage = detector.setText(bytes1).detect().getName()
        if (fileCodepage =~ (/ISO-8859-1|ISO-8859-2|windows-1250|windows-1252|Big5|UTF-16LE/)) {
			if(!(file.text =~ /^[^ -~｡-ﾟ]/)) {print "NoKanji "}
		} 
        print fileCodepage +"\t"
        println file.getAbsolutePath().minus(".\\") 
    }
}

Detects codepage of source code recursively.