CharsetDetector task for Gradle, utilizes juniversalchardet

charSetDetector.gradle

import org.mozilla.universalchardet.UniversalDetector

buildscript {
    repositories {
        mavenCentral()
    }
    dependencies {
        classpath files('juniversalchardet-1.0.3.jar') // not available in public repository :(
    }
}

task findEncoding(type: CharsetDetector) {
    inputFile = file('someFile')
}

class CharsetDetector extends DefaultTask
{
    @InputFile
    File inputFile

    /**
     * Straight port of code sample on http://code.google.com/p/juniversalchardet/
     * @return
     */
    @TaskAction
    def detect()
    {
        byte[] buf = new byte[4096]
        FileInputStream fis = new FileInputStream(inputFile)

        // (1)
        UniversalDetector detector = new UniversalDetector(null)

        // (2)
        int nread
        while ((nread = fis.read(buf)) > 0 && !detector.isDone())
        {
            detector.handleData(buf, 0, nread)
        }
        // (3)
        detector.dataEnd()

        // (4)
        String encoding = detector.getDetectedCharset()
        if (encoding)
        {
            println("Detected encoding = " + encoding)
        }
        else
        {
            println("No encoding detected.")
        }

        // (5)
        detector.reset()
    }
}