forked from apache/spark
/
ddl.scala
197 lines (164 loc) · 6.81 KB
/
ddl.scala
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.sql.sources
import scala.language.implicitConversions
import scala.util.parsing.combinator.syntactical.StandardTokenParsers
import scala.util.parsing.combinator.PackratParsers
import org.apache.spark.Logging
import org.apache.spark.sql.catalyst.types._
import org.apache.spark.sql.catalyst.plans.logical._
import org.apache.spark.sql.catalyst.SqlLexical
/**
* A parser for foreign DDL commands.
*/
private[sql] class DDLParser extends StandardTokenParsers with PackratParsers with Logging {
def apply(input: String): Option[LogicalPlan] = {
phrase(ddl)(new lexical.Scanner(input)) match {
case Success(r, x) => Some(r)
case x =>
logDebug(s"Not recognized as DDL: $x")
None
}
}
def parseType(input: String): DataType = {
phrase(dataType)(new lexical.Scanner(input)) match {
case Success(r, x) => r
case x =>
sys.error(s"Unsupported dataType: $x")
}
}
protected case class Keyword(str: String)
protected implicit def asParser(k: Keyword): Parser[String] =
lexical.allCaseVersions(k.str).map(x => x : Parser[String]).reduce(_ | _)
protected val CREATE = Keyword("CREATE")
protected val TEMPORARY = Keyword("TEMPORARY")
protected val TABLE = Keyword("TABLE")
protected val USING = Keyword("USING")
protected val OPTIONS = Keyword("OPTIONS")
// Data types.
protected val STRING = Keyword("STRING")
protected val FLOAT = Keyword("FLOAT")
protected val INT = Keyword("INT")
protected val TINYINT = Keyword("TINYINT")
protected val SMALLINT = Keyword("SMALLINT")
protected val DOUBLE = Keyword("DOUBLE")
protected val BIGINT = Keyword("BIGINT")
protected val BINARY = Keyword("BINARY")
protected val BOOLEAN = Keyword("BOOLEAN")
protected val DECIMAL = Keyword("DECIMAL")
protected val DATE = Keyword("DATE")
protected val TIMESTAMP = Keyword("TIMESTAMP")
protected val VARCHAR = Keyword("VARCHAR")
protected val ARRAY = Keyword("ARRAY")
protected val MAP = Keyword("MAP")
protected val STRUCT = Keyword("STRUCT")
// Use reflection to find the reserved words defined in this class.
protected val reservedWords =
this.getClass
.getMethods
.filter(_.getReturnType == classOf[Keyword])
.map(_.invoke(this).asInstanceOf[Keyword].str)
override val lexical = new SqlLexical(reservedWords)
protected lazy val ddl: Parser[LogicalPlan] = createTable
/**
* `CREATE TEMPORARY TABLE avroTable
* USING org.apache.spark.sql.avro
* OPTIONS (path "../hive/src/test/resources/data/files/episodes.avro")`
* or
* `CREATE TEMPORARY TABLE avroTable(intField int, stringField string...)
* USING org.apache.spark.sql.avro
* OPTIONS (path "../hive/src/test/resources/data/files/episodes.avro")`
*/
protected lazy val createTable: Parser[LogicalPlan] =
(
CREATE ~ TEMPORARY ~ TABLE ~> ident
~ (tableCols).? ~ (USING ~> className) ~ (OPTIONS ~> options) ^^ {
case tableName ~ columns ~ provider ~ opts =>
val tblColumns = if(columns.isEmpty) Seq.empty else columns.get
CreateTableUsing(tableName, tblColumns, provider, opts)
}
)
protected lazy val tableCols: Parser[Seq[StructField]] = "(" ~> repsep(column, ",") <~ ")"
protected lazy val options: Parser[Map[String, String]] =
"(" ~> repsep(pair, ",") <~ ")" ^^ { case s: Seq[(String, String)] => s.toMap }
protected lazy val className: Parser[String] = repsep(ident, ".") ^^ { case s => s.mkString(".")}
protected lazy val pair: Parser[(String, String)] = ident ~ stringLit ^^ { case k ~ v => (k,v) }
protected lazy val column: Parser[StructField] =
ident ~ dataType ^^ { case columnName ~ typ =>
StructField(cleanIdentifier(columnName), typ)
}
protected lazy val primitiveType: Parser[DataType] =
STRING ^^^ StringType |
BINARY ^^^ BinaryType |
BOOLEAN ^^^ BooleanType |
TINYINT ^^^ ByteType |
SMALLINT ^^^ ShortType |
INT ^^^ IntegerType |
BIGINT ^^^ LongType |
FLOAT ^^^ FloatType |
DOUBLE ^^^ DoubleType |
fixedDecimalType | // decimal with precision/scale
DECIMAL ^^^ DecimalType.Unlimited | // decimal with no precision/scale
DATE ^^^ DateType |
TIMESTAMP ^^^ TimestampType |
VARCHAR ~ "(" ~ numericLit ~ ")" ^^^ StringType
protected lazy val fixedDecimalType: Parser[DataType] =
(DECIMAL ~ "(" ~> numericLit) ~ ("," ~> numericLit <~ ")") ^^ {
case precision ~ scale => DecimalType(precision.toInt, scale.toInt)
}
protected lazy val arrayType: Parser[DataType] =
ARRAY ~> "<" ~> dataType <~ ">" ^^ {
case tpe => ArrayType(tpe)
}
protected lazy val mapType: Parser[DataType] =
MAP ~> "<" ~> dataType ~ "," ~ dataType <~ ">" ^^ {
case t1 ~ _ ~ t2 => MapType(t1, t2)
}
protected lazy val structField: Parser[StructField] =
ident ~ ":" ~ dataType ^^ {
case fieldName ~ _ ~ tpe => StructField(cleanIdentifier(fieldName), tpe, nullable = true)
}
protected lazy val structType: Parser[DataType] =
(STRUCT ~> "<" ~> repsep(structField, ",") <~ ">" ^^ {
case fields => new StructType(fields)
}) |
(STRUCT ~> "<>" ^^ {
case fields => new StructType(Nil)
})
private[sql] lazy val dataType: Parser[DataType] =
arrayType |
mapType |
structType |
primitiveType
protected val escapedIdentifier = "`([^`]+)`".r
/** Strips backticks from ident if present */
protected def cleanIdentifier(ident: String): String = ident match {
case escapedIdentifier(i) => i
case plainIdent => plainIdent
}
}
/**
* Builds a map in which keys are case insensitive
*/
protected class CaseInsensitiveMap(map: Map[String, String]) extends Map[String, String] {
val baseMap = map.map(kv => kv.copy(_1 = kv._1.toLowerCase))
override def get(k: String): Option[String] = baseMap.get(k.toLowerCase)
override def + [B1 >: String](kv: (String, B1)): Map[String, B1] =
baseMap + kv.copy(_1 = kv._1.toLowerCase)
override def iterator: Iterator[(String, String)] = baseMap.iterator
override def -(key: String): Map[String, String] = baseMap - key.toLowerCase()
}