read tar.gz file

TarGZIPArchiveFileReader.groovy

import org.apache.commons.compress.archivers.tar.TarArchiveEntry
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream
import org.apache.commons.io.FileUtils

import java.nio.file.Files
import java.util.zip.GZIPInputStream


url = new URL("http://xxx.tar.gz")
tempFile = Files.createTempFile(null, null)

tempFile.toFile().deleteOnExit()

FileUtils.copyURLToFile(url, tempFile.toFile())

byte[] buffer = new byte[1024];

try {
    GZIPInputStream zis = new GZIPInputStream(new FileInputStream(tempFile.toFile()));
    TarArchiveInputStream taris = new TarArchiveInputStream(zis)
    TarArchiveEntry entry;
    ByteArrayOutputStream bao = new ByteArrayOutputStream();

    while ((entry = taris.getNextTarEntry()) != null) {
        //忽略目录，与crc校验文件
        if (entry.isDirectory() || entry.getName().endsWith(".crc")) {
            continue;
        }
        //忽略空文件
        if (entry.getSize() == 0) {
            continue;
        }

        int len;
        while ((len = taris.read(buffer)) >0) {
            bao.write(buffer, 0, len);
        }
    }


    long lineNumber = new LineNumberReader(new InputStreamReader(new ByteArrayInputStream(bao.toByteArray()))).lines().count();
    println lineNumber
} catch (Exception e) {
    throw new RuntimeException("gzip read fail", e);
}