Spark SQL语法解析

1 从文本到执行计划

主要由两步组成：

词法分析：将文本解析解析为标识。
语法分析：将标识解析为抽象语法树。

# org.apache.spark.sql.catalyst.parser.AbstractSqlParser#parse
  protected def parse[T](command: String)(toResult: SqlBaseParser => T): T = {
    logDebug(s"Parsing command: $command")

    val lexer = new SqlBaseLexer(new UpperCaseCharStream(CharStreams.fromString(command)))
    lexer.removeErrorListeners()
    lexer.addErrorListener(ParseErrorListener)

    val tokenStream = new CommonTokenStream(lexer)
    val parser = new SqlBaseParser(tokenStream)
    parser.addParseListener(PostProcessor)
    parser.removeErrorListeners()
    parser.addErrorListener(ParseErrorListener)
    parser.legacy_setops_precedence_enabled = conf.setOpsPrecedenceEnforced
    parser.legacy_exponent_literal_as_decimal_enabled = conf.exponentLiteralAsDecimalEnabled
    parser.SQL_standard_keyword_behavior = conf.ansiEnabled

    try {
      try {
        // first, try parsing with potentially faster SLL mode
        parser.getInterpreter.setPredictionMode(PredictionMode.SLL)
        toResult(parser)
      }
      catch {
        case e: ParseCancellationException =>
          // if we fail, parse with LL mode
          tokenStream.seek(0) // rewind input stream
          parser.reset()

          // Try Again.
          parser.getInterpreter.setPredictionMode(PredictionMode.LL)
          toResult(parser)
      }
    }
    catch {
      case e: ParseException if e.command.isDefined =>
        throw e
      case e: ParseException =>
        throw e.withCommand(command)
      case e: AnalysisException =>
        val position = Origin(e.line, e.startPosition)
        throw new ParseException(Option(command), e.message, position, position)
    }
  }

# 执行效果
behavior of "parser"

  it should "convert SELECT into a LogicalPlan" in {
    val parsedPlan = sparkSession.sessionState.sqlParser.parsePlan("SELECT * FROM numbers WHERE nr > 1")

    parsedPlan.toString() should include ("'Project [*]")
    parsedPlan.toString() should include ("+- 'Filter ('nr > 1)")
    parsedPlan.toString() should include ("   +- 'UnresolvedRelation `numbers`")
  }

  it should "convert filter into an Expression" in {
    val parsedExpression = sparkSession.sessionState.sqlParser.parseExpression("nr > 1")

    parsedExpression shouldBe a [GreaterThan]
    parsedExpression.asInstanceOf[GreaterThan].left shouldBe a [UnresolvedAttribute]
    parsedExpression.asInstanceOf[GreaterThan].right shouldBe a [Literal]
  }

  it should "convert data type into Spark StructType" in {
    val parsedType = sparkSession.sessionState.sqlParser.parseDataType("struct")

    parsedType.toString shouldEqual "StructType(StructField(nr,IntegerType,true), StructField(letter,StringType,true))"
  }


  it should "convert data type into a schema" in {
    val parsedSchema = sparkSession.sessionState.sqlParser.parseTableSchema("nr INTEGER, letter STRING")

    parsedSchema.toString shouldEqual "StructType(StructField(nr,IntegerType,true), StructField(letter,StringType,true))"
  }

1 从文本到执行计划

参考资料