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
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
|
/*
* 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.catalog
import org.apache.spark.annotation.Experimental
import org.apache.spark.sql.{AnalysisException, DataFrame, Dataset}
import org.apache.spark.sql.types.StructType
/**
* Catalog interface for Spark. To access this, use `SparkSession.catalog`.
*
* @since 2.0.0
*/
abstract class Catalog {
/**
* Returns the current default database in this session.
*
* @since 2.0.0
*/
def currentDatabase: String
/**
* Sets the current default database in this session.
*
* @since 2.0.0
*/
def setCurrentDatabase(dbName: String): Unit
/**
* Returns a list of databases available across all sessions.
*
* @since 2.0.0
*/
def listDatabases(): Dataset[Database]
/**
* Returns a list of tables in the current database.
* This includes all temporary tables.
*
* @since 2.0.0
*/
def listTables(): Dataset[Table]
/**
* Returns a list of tables in the specified database.
* This includes all temporary tables.
*
* @since 2.0.0
*/
@throws[AnalysisException]("database does not exist")
def listTables(dbName: String): Dataset[Table]
/**
* Returns a list of functions registered in the current database.
* This includes all temporary functions
*
* @since 2.0.0
*/
def listFunctions(): Dataset[Function]
/**
* Returns a list of functions registered in the specified database.
* This includes all temporary functions
*
* @since 2.0.0
*/
@throws[AnalysisException]("database does not exist")
def listFunctions(dbName: String): Dataset[Function]
/**
* Returns a list of columns for the given table in the current database or
* the given temporary table.
*
* @since 2.0.0
*/
@throws[AnalysisException]("table does not exist")
def listColumns(tableName: String): Dataset[Column]
/**
* Returns a list of columns for the given table in the specified database.
*
* @since 2.0.0
*/
@throws[AnalysisException]("database or table does not exist")
def listColumns(dbName: String, tableName: String): Dataset[Column]
/**
* Find the database with the specified name. This throws an AnalysisException when the database
* cannot be found.
*
* @since 2.1.0
*/
@throws[AnalysisException]("database does not exist")
def findDatabase(dbName: String): Database
/**
* Find the table with the specified name. This table can be a temporary table or a table in the
* current database. This throws an AnalysisException when the table cannot be found.
*
* @since 2.1.0
*/
@throws[AnalysisException]("table does not exist")
def findTable(tableName: String): Table
/**
* Find the table with the specified name in the specified database. This throws an
* AnalysisException when the table cannot be found.
*
* @since 2.1.0
*/
@throws[AnalysisException]("database or table does not exist")
def findTable(dbName: String, tableName: String): Table
/**
* Find the function with the specified name. This function can be a temporary function or a
* function in the current database. This throws an AnalysisException when the function cannot
* be found.
*
* @since 2.1.0
*/
@throws[AnalysisException]("function does not exist")
def findFunction(functionName: String): Function
/**
* Find the function with the specified name. This throws an AnalysisException when the function
* cannot be found.
*
* @since 2.1.0
*/
@throws[AnalysisException]("database or function does not exist")
def findFunction(dbName: String, functionName: String): Function
/**
* Check if the database with the specified name exists.
*
* @since 2.1.0
*/
def databaseExists(dbName: String): Boolean
/**
* Check if the table with the specified name exists. This can either be a temporary table or a
* table in the current database.
*
* @since 2.1.0
*/
def tableExists(tableName: String): Boolean
/**
* Check if the table with the specified name exists in the specified database.
*
* @since 2.1.0
*/
def tableExists(dbName: String, tableName: String): Boolean
/**
* Check if the function with the specified name exists. This can either be a temporary function
* or a function in the current database.
*
* @since 2.1.0
*/
def functionExists(functionName: String): Boolean
/**
* Check if the function with the specified name exists in the specified database.
*
* @since 2.1.0
*/
def functionExists(dbName: String, functionName: String): Boolean
/**
* :: Experimental ::
* Creates an external table from the given path and returns the corresponding DataFrame.
* It will use the default data source configured by spark.sql.sources.default.
*
* @since 2.0.0
*/
@Experimental
def createExternalTable(tableName: String, path: String): DataFrame
/**
* :: Experimental ::
* Creates an external table from the given path based on a data source
* and returns the corresponding DataFrame.
*
* @since 2.0.0
*/
@Experimental
def createExternalTable(tableName: String, path: String, source: String): DataFrame
/**
* :: Experimental ::
* Creates an external table from the given path based on a data source and a set of options.
* Then, returns the corresponding DataFrame.
*
* @since 2.0.0
*/
@Experimental
def createExternalTable(
tableName: String,
source: String,
options: java.util.Map[String, String]): DataFrame
/**
* :: Experimental ::
* (Scala-specific)
* Creates an external table from the given path based on a data source and a set of options.
* Then, returns the corresponding DataFrame.
*
* @since 2.0.0
*/
@Experimental
def createExternalTable(
tableName: String,
source: String,
options: Map[String, String]): DataFrame
/**
* :: Experimental ::
* Create an external table from the given path based on a data source, a schema and
* a set of options. Then, returns the corresponding DataFrame.
*
* @since 2.0.0
*/
@Experimental
def createExternalTable(
tableName: String,
source: String,
schema: StructType,
options: java.util.Map[String, String]): DataFrame
/**
* :: Experimental ::
* (Scala-specific)
* Create an external table from the given path based on a data source, a schema and
* a set of options. Then, returns the corresponding DataFrame.
*
* @since 2.0.0
*/
@Experimental
def createExternalTable(
tableName: String,
source: String,
schema: StructType,
options: Map[String, String]): DataFrame
/**
* Drops the temporary view with the given view name in the catalog.
* If the view has been cached before, then it will also be uncached.
*
* @param viewName the name of the view to be dropped.
* @since 2.0.0
*/
def dropTempView(viewName: String): Unit
/**
* Returns true if the table is currently cached in-memory.
*
* @since 2.0.0
*/
def isCached(tableName: String): Boolean
/**
* Caches the specified table in-memory.
*
* @since 2.0.0
*/
def cacheTable(tableName: String): Unit
/**
* Removes the specified table from the in-memory cache.
*
* @since 2.0.0
*/
def uncacheTable(tableName: String): Unit
/**
* Removes all cached tables from the in-memory cache.
*
* @since 2.0.0
*/
def clearCache(): Unit
/**
* Invalidate and refresh all the cached metadata of the given table. For performance reasons,
* Spark SQL or the external data source library it uses might cache certain metadata about a
* table, such as the location of blocks. When those change outside of Spark SQL, users should
* call this function to invalidate the cache.
*
* If this table is cached as an InMemoryRelation, drop the original cached version and make the
* new version cached lazily.
*
* @since 2.0.0
*/
def refreshTable(tableName: String): Unit
/**
* Invalidate and refresh all the cached data (and the associated metadata) for any dataframe that
* contains the given data source path.
*
* @since 2.0.0
*/
def refreshByPath(path: String): Unit
}
|
