simhash实现

import com.clearspring.analytics.hash.MurmurHash

/**
  * Created by fhqplzj on 17-3-1 at 下午6:07.
  */
object Sim {
  def simHash(features: Array[String], weights: Array[Int]): Long = {
    val hist = Array.ofDim[Int](64)
    features.zip(weights).foreach {
      case (feature, weight) => {
        val hash = MurmurHash.hash64(feature)
        for (i <- 0 until 64) {
          if ((hash & (1 << i)) == 0) {
            hist(i) += -weight
          } else {
            hist(i) += weight
          }
        }
      }
    }
    var result: Long = 0
    for (i <- 0 until 64) {
      if (hist(i) >= 0) {
        result |= (1 << i)
      }
    }
    result
  }

  def main(args: Array[String]): Unit = {
    val features = "zhao jun haha".split(" ")
    val weights = Array.fill(features.length)(1)
    println(simHash(features, weights))
  }
}