我正在发布几个使用 Spark SQL 的解决方案更专注于准确的模式匹配给定文本中的搜索字符串。
1:使用CrossJoin
import spark.implicits._
val df1 = Seq(
(1, "2017-2-13", "ABX-3354 gsfette"),
(2, "2017-3-18", "TYET-3423 asdsad"),
(3, "2017-2-09", "TYET-3423 rewriu"),
(4, "2017-2-13", "ABX-335442324"), //changed from "ABX-3354 42324"
(5, "2017-4-01", "aerrTYET-3423") //changed from "TYET-3423 aerr"
).toDF("id", "dt", "txt")
val df2 = Seq(
("mfr1", "ABX-3354"),
("mfr2", "TYET-3423")
).toDF("col1", "key")
//match function for filter
def matcher(row: Row): Boolean = row.getAs[String]("txt")
.contains(row.getAs[String]("key"))
val join = df1.crossJoin(df2)
import org.apache.spark.sql.functions.count
val result = join.filter(matcher _)
.groupBy("key")
.agg(count("txt").as("count"))
2:使用广播变量
import spark.implicits._
val df1 = Seq(
(1, "2017-2-13", "ABX-3354 gsfette"),
(2, "2017-3-18", "TYET-3423 asdsad"),
(3, "2017-2-09", "TYET-3423 rewriu"),
(4, "2017-2-13", "ABX-3354 42324"),
(5, "2017-4-01", "aerrTYET-3423"),
(6, "2017-4-01", "aerrYET-3423")
).toDF("id", "dt", "pattern")
//small dataset to broadcast
val df2 = Seq(
("mfr1", "ABX-3354"),
("mfr2", "TYET-3423")
).map(_._2) // considering only 2 values in pair
//Lookup to use in UDF
val lookup = spark.sparkContext.broadcast(df2)
//Udf
import org.apache.spark.sql.functions._
val matcher = udf((txt: String) => {
val matches: Seq[String] = lookup.value.filter(txt.contains(_))
if (matches.size > 0) matches.head else null
})
val result = df1.withColumn("match", matcher($"pattern"))
.filter($"match".isNotNull) // not interested in non matching records
.groupBy("match")
.agg(count("pattern").as("count"))
两种解决方案都会产生相同的输出
result.show()
+---------+-----+
| key|count|
+---------+-----+
|TYET-3423| 3|
| ABX-3354| 2|
+---------+-----+