├── .gitignore
├── LICENSE
├── README.md
├── build.sbt
├── pom.xml
├── spark-dbf.sh
└── src
├── main
├── java
│ └── com
│ │ └── esri
│ │ └── spark
│ │ └── dbf
│ │ └── DBFUtils.java
└── scala
│ └── com
│ └── esri
│ └── spark
│ └── dbf
│ ├── DBFRelation.scala
│ ├── DefaultSource.scala
│ └── package.scala
└── test
├── java
└── com
│ └── esri
│ └── JavaTestSuite.java
├── resources
├── log4j.properties
├── logback.xml
└── test.dbf
└── scala
└── com
└── esri
└── spark
└── dbf
└── DBFSuite.scala
/.gitignore:
--------------------------------------------------------------------------------
1 | *.class
2 | *.log
3 | *.iml
4 |
5 | .idea
6 | .DS_Store
7 |
8 | # sbt specific
9 | .cache/
10 | .history/
11 | .lib/
12 | dist/*
13 | target/
14 | lib_managed/
15 | src_managed/
16 | project/boot/
17 | project/plugins/project/
18 |
19 | # Scala-IDE specific
20 | .scala_dependencies
21 | .worksheet
22 |
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "{}"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright {yyyy} {name of copyright owner}
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
202 |
203 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # Spark SQL DBF Library
2 |
3 | A library for querying [DBF](http://www.digitalpreservation.gov/formats/fdd/fdd000325.shtml) data with [Spark SQL](http://spark.apache.org/docs/latest/sql-programming-guide.html).
4 |
5 | *This is work in progress* and is based on the [spark-avro](https://github.com/databricks/spark-avro) project.
6 | The "Ye Olde" DBF file format encapsulates data and schema just like the modern Avro format. So it was natural and
7 | quick to mutate the avro project and adapt it to our trusty and ubiquitous dbf format.
8 |
9 | ## Requirements
10 | This library requires Spark 1.2+ and depends on my [Shapefile](https://github.com/mraad/Shapefile) github project.
11 |
12 | ## Building
13 | Typically, [SBT](http://www.scala-sbt.org/) is used to build Scala based projects, but, I'm using [Maven](http://maven.apache.org/) to build this one.
14 | The pom.xml has plugins to compile scala and java sources.
15 |
16 | Make sure to first clone and install the [Shapefile](https://github.com/mraad/Shapefile) project, then
17 |
18 | ```
19 | $ mvn clean install
20 | ```
21 |
22 | ## Linking
23 | You can link against this library in your program at the following coordinates:
24 |
25 | ```
26 | groupId: com.esri
27 | artifactId: spark-dbf
28 | version: 0.1
29 | ```
30 |
31 | The spark-dbf jar file can also be added to a Spark using the `--jars` command line option.
32 | For example, to include it when starting the spark shell:
33 |
34 | ```
35 | $ bin/spark-shell --jars spark-dbf-0.1.jar
36 | ```
37 |
38 | ## Examples
39 |
40 | The following are based on the first 1 million records of the [NYC taxi trips](http://chriswhong.com/).
41 | you can download the sample dbf from [here](https://dl.dropboxusercontent.com/u/2193160/trips1M.dbf)
42 |
43 |
44 | ```
45 | $ wget https://dl.dropboxusercontent.com/u/2193160/trips1M.dbf
46 | ```
47 |
48 | ### Scala API
49 |
50 | ```scala
51 | import org.apache.spark.sql.SQLContext
52 | val sqlContext = new SQLContext(sc)
53 | import sqlContext._
54 | import com.esri.spark.dbf._
55 | val trips = sqlContext.dbfFile("trips1M.dbf")
56 | trips.schema.fields.foreach(println)
57 | trips.registerTempTable("trips")
58 | sql("select count(*) from trips").collect
59 | sql("select tripdist from trips order by tripdist desc limit 10").collect
60 |
61 | ```
62 |
63 | ### Python and SQL API
64 | DBF data can be queried in pure SQL or from python by registering the data as a temporary table.
65 |
66 |
67 | ```sql
68 | CREATE TEMPORARY TABLE trips
69 | USING com.esri.spark.dbf
70 | OPTIONS (path "trips1M.dbf")
71 | ```
72 |
73 | ### Java API
74 | DBF files can be read using static functions in DBFUtils.
75 |
76 |
77 | ```java
78 | import com.esri.spark.dbf.DBFUtils;
79 |
80 | JavaSchemaRDD trips = DBFUtils.dbfFile(sqlContext, "trips1M.dbf");
81 | ```
82 |
83 | ## Sample spark shell session with simple geometry UDF
84 |
85 | This sample uses our [Geometry API](https://github.com/Esri/geometry-api-java) to define a UDF that calculates the
86 | distance in meters between two lat/lon pairs.
87 |
88 | ```shell
89 | $ ./spark-dbf.sh
90 | ```
91 |
92 | ```scala
93 | import com.esri.core.geometry.{GeometryEngine, Point}
94 | import org.apache.spark.sql.SQLContext
95 | val sqlContext = new SQLContext(sc)
96 | import sqlContext._
97 | import com.esri.spark.dbf._
98 | sqlContext.dbfFile("trips1M.dbf").registerTempTable("trips")
99 | sqlContext.registerFunction("ST_DISTANCE", (x1: Float, y1: Float, x2: Float, y2: Float) => GeometryEngine.geodesicDistanceOnWGS84(new Point(x1, y1), new Point(x2, y2)))
100 | sql("select tripdist*1609.34,ST_DISTANCE(plon,plat,dlon,dlat) from trips limit 20").foreach(println)
101 | ```
102 |
--------------------------------------------------------------------------------
/build.sbt:
--------------------------------------------------------------------------------
1 | name := "spark-dbf"
2 |
3 | version := "0.1"
4 |
5 | organization := "com.esri"
6 |
7 | scalaVersion := "2.10.4"
8 |
9 | resolvers += "Local Maven Repository" at "file:///"+Path.userHome+"/.m2/repository"
10 |
11 | libraryDependencies += "com.esri" % "Shapefile" % "1.3.1"
12 |
13 | libraryDependencies += "org.apache.spark" %% "spark-sql" % "1.2.0" % "provided"
14 |
15 | libraryDependencies += "org.apache.avro" % "avro" % "1.7.7" exclude("org.mortbay.jetty", "servlet-api")
16 |
17 | libraryDependencies += "org.apache.avro" % "avro-mapred" % "1.7.7" exclude("org.mortbay.jetty", "servlet-api")
18 |
19 | publishMavenStyle := true
20 |
21 | pomExtra := (
22 | https://github.com/mraad/spark-dbf
23 |
24 |
25 | Apache License, Verision 2.0
26 | http://www.apache.org/licenses/LICENSE-2.0.html
27 | repo
28 |
29 |
30 |
31 | git@github.com:mraad/spark-dbf.git
32 | scm:git:git@github.com:mraad/spark-dbf.git
33 |
34 |
35 |
36 | mraad
37 | Mansour Raad
38 | https://github.com/mraad
39 | mraad@esri.com
40 |
41 | )
42 |
43 | libraryDependencies += "org.scalatest" %% "scalatest" % "2.2.1" % "test"
44 |
45 | libraryDependencies += "junit" % "junit" % "4.12" % "test"
46 |
--------------------------------------------------------------------------------
/pom.xml:
--------------------------------------------------------------------------------
1 |
3 | 4.0.0
4 |
5 | com.esri
6 | spark-dbf
7 | 0.1
8 | jar
9 |
10 |
11 | UTF-8
12 | 1.7
13 | provided
14 |
15 |
16 |
17 |
18 | Apache License, Verision 2.0
19 | http://www.apache.org/licenses/LICENSE-2.0.html
20 | repo
21 |
22 |
23 |
24 |
25 | git@github.com:mraad/spark-dbf.git
26 | scm:git:git@github.com:mraad/spark-dbf.git
27 |
28 |
29 |
30 |
31 | mraad
32 | Mansour Raad
33 | mraad@esri.com
34 |
35 |
36 |
37 |
38 |
39 | cloudera-releases
40 | https://repository.cloudera.com/artifactory/cloudera-repos
41 |
42 | true
43 |
44 |
45 | false
46 |
47 |
48 |
49 | maven2-repository.dev.java.net
50 | http://download.java.net/maven/2
51 |
52 |
53 | scala-tools.org
54 | Scala-tools Maven2 Repository
55 | http://scala-tools.org/repo-releases
56 |
57 |
58 |
59 |
60 |
61 | scala-tools.org
62 | Scala-tools Maven2 Repository
63 | http://scala-tools.org/repo-releases
64 |
65 |
66 |
67 |
68 |
69 | org.apache.spark
70 | spark-core_2.10
71 | ${spark.version}
72 | ${spark.scope}
73 |
74 |
75 | org.slf4j
76 | slf4j-log4j12
77 |
78 |
79 |
80 |
81 | org.apache.spark
82 | spark-sql_2.10
83 | ${spark.version}
84 | ${spark.scope}
85 |
86 |
87 | org.slf4j
88 | slf4j-log4j12
89 |
90 |
91 |
92 |
93 | ch.qos.logback
94 | logback-classic
95 | 1.1.2
96 | ${spark.scope}
97 |
98 |
99 | com.esri
100 | Shapefile
101 | 1.3.1
102 |
103 |
104 | junit
105 | junit
106 | 4.12
107 | test
108 |
109 |
110 | org.scalatest
111 | scalatest_2.10
112 | 3.0.0-SNAP4
113 | test
114 |
115 |
116 |
117 |
118 |
119 |
120 |
121 | net.alchim31.maven
122 | scala-maven-plugin
123 | 3.2.0
124 |
125 |
126 |
127 |
128 |
129 | net.alchim31.maven
130 | scala-maven-plugin
131 | 3.2.0
132 |
133 |
134 | scala-compile-first
135 | process-resources
136 |
137 | compile
138 |
139 |
140 |
141 | scala-test-compile-first
142 | process-test-resources
143 |
144 | testCompile
145 |
146 |
147 |
148 |
149 | ${scala.version}
150 | incremental
151 | true
152 |
153 |
154 |
155 | org.apache.maven.plugins
156 | maven-compiler-plugin
157 | 3.2
158 |
159 | ${java.version}
160 | ${java.version}
161 |
162 |
163 |
164 | org.apache.maven.plugins
165 | maven-dependency-plugin
166 | 2.9
167 |
168 |
169 | copy-dependencies
170 | prepare-package
171 |
172 | copy-dependencies
173 |
174 |
175 | ${project.build.directory}/libs
176 | false
177 | false
178 | true
179 | runtime
180 | test
181 |
182 |
183 |
184 |
185 |
186 | org.apache.maven.plugins
187 | maven-jar-plugin
188 | 2.4
189 |
190 |
191 |
192 | com.esri.DBFApp
193 | true
194 | libs/
195 |
196 |
197 |
198 |
199 |
200 |
201 |
202 |
203 |
204 | DBFApp
205 |
206 | false
207 |
208 |
209 | compile
210 |
211 |
212 |
213 | spark130
214 |
215 | false
216 |
217 |
218 | 1.3.0-SNAPSHOT
219 |
220 |
221 |
222 | spark120
223 |
224 | true
225 |
226 |
227 | 1.2.0
228 |
229 |
230 |
231 | spark110-cdh5
232 |
233 | false
234 |
235 |
236 | 1.1.0-cdh5.2.1
237 |
238 |
239 |
240 | scala-2.10
241 |
242 | true
243 |
244 | scala-2.10
245 |
246 |
247 |
248 | 2.10.4
249 |
250 |
251 |
252 | cdh5
253 |
254 | true
255 |
256 |
257 | 2.3.0-cdh5.1.2
258 |
259 |
260 |
261 | hdp21
262 |
263 | false
264 |
265 |
266 | 2.4.0
267 |
268 |
269 |
270 |
271 |
--------------------------------------------------------------------------------
/spark-dbf.sh:
--------------------------------------------------------------------------------
1 | #!/bin/sh
2 | dest=target
3 | libs=${dest}/libs
4 | spark-shell --jars ${dest}/spark-dbf-0.1.jar,${libs}/Shapefile-1.3.1.jar,${libs}/commons-io-2.4.jar,${libs}/esri-geometry-api-1.2.jar,${libs}/jackson-core-asl-1.9.11.jar,${libs}/json-20090211.jar
5 |
--------------------------------------------------------------------------------
/src/main/java/com/esri/spark/dbf/DBFUtils.java:
--------------------------------------------------------------------------------
1 | package com.esri.spark.dbf;
2 |
3 | import org.apache.spark.sql.api.java.JavaSQLContext;
4 | import org.apache.spark.sql.api.java.JavaSchemaRDD;
5 |
6 | /**
7 | * A collection of static functions for working with dbf in Spark SQL
8 | */
9 | public class DBFUtils
10 | {
11 | /**
12 | * Returns a Schema RDD for the given dbf path.
13 | */
14 | public static JavaSchemaRDD dbfFile(final JavaSQLContext sqlContext, final String path)
15 | {
16 | final DBFRelation relation = new DBFRelation(path, sqlContext.sqlContext());
17 | return sqlContext.baseRelationToSchemaRDD(relation);
18 | }
19 |
20 | }
21 |
--------------------------------------------------------------------------------
/src/main/scala/com/esri/spark/dbf/DBFRelation.scala:
--------------------------------------------------------------------------------
1 | package com.esri.spark.dbf
2 |
3 | import com.esri.dbf.{DBFField, DBFHeader}
4 | import com.esri.mapred.DBFInputFormat
5 | import org.apache.hadoop.fs.{FileSystem, Path}
6 | import org.apache.hadoop.io._
7 | import org.apache.spark.sql._
8 | import org.apache.spark.sql.sources.PrunedScan
9 |
10 | import scala.collection.JavaConverters._
11 |
12 | /**
13 | * Extends `PrunedScan` to map the RDD to specified columns.
14 | * @param location the location of the dbf file
15 | * @param sqlContext the SQL context
16 | *
17 | * TODO - extend PrunedFilterScan to apply 'smart' filter !
18 | */
19 | case class DBFRelation(location: String)(@transient val sqlContext: SQLContext) extends PrunedScan {
20 |
21 | /**
22 | * http://polyglot-window.blogspot.com/2009/03/arm-blocks-in-scala-revisited.html
23 | * http://stackoverflow.com/questions/2207425/what-automatic-resource-management-alternatives-exists-for-scala
24 | */
25 | private[dbf] def using[A <: {def close() : Unit}, B](r: A)(f: A => B): B = try {
26 | f(r)
27 | }
28 | finally {
29 | r.close()
30 | }
31 |
32 | private[dbf] def toStructField(field: DBFField): StructField = {
33 | StructField(field.fieldName, toDataType(field))
34 | }
35 |
36 | private[dbf] def toDataType(field: DBFField): DataType = {
37 | field.dataType match {
38 | case 'C' => StringType
39 | case 'D' => LongType
40 | case 'F' => FloatType
41 | case 'L' => BooleanType
42 | case 'N' => toNumeType(field)
43 | case other => sys.error(s"Unsupported type $other")
44 | }
45 | }
46 |
47 | private[dbf] def toNumeType(field: DBFField): DataType = {
48 | if (field.decimalCount > 0) DoubleType
49 | else if (field.fieldLength < 5) ShortType
50 | else if (field.fieldLength < 8) IntegerType else LongType
51 | }
52 |
53 | /**
54 | * Determine the RDD Schema based on the DBF header info.
55 | * @return StructType instance
56 | */
57 | override def schema = {
58 | val path = new Path(location)
59 | val fs = FileSystem.get(path.toUri, sqlContext.sparkContext.hadoopConfiguration)
60 | using(fs.open(path)) { dataInputStream => {
61 | StructType(DBFHeader.read(dataInputStream).fields.asScala.map(toStructField(_)))
62 | }
63 | }
64 | }
65 |
66 | /**
67 | * This is depending on Hadoop's implementation of InputFormat in the Shapefile project
68 | *
69 | * TODO - Optimize in Shapefile lib to return List(values) rather than Map(field name -> value)
70 | */
71 | private[dbf] val baseRDD = sqlContext.sparkContext.hadoopFile(
72 | location,
73 | classOf[DBFInputFormat],
74 | classOf[LongWritable],
75 | classOf[MapWritable],
76 | sqlContext.sparkContext.defaultMinPartitions
77 | ) // TODO - should this be cached ?
78 |
79 | private[dbf] def toValue(record: (LongWritable, MapWritable), name: String): Any = {
80 | record._2.get(new Text(name)) match {
81 | case d: DoubleWritable => d.get
82 | case f: FloatWritable => f.get
83 | case l: LongWritable => l.get
84 | case i: IntWritable => i.get
85 | case t: Text => t.toString
86 | case other => other // TODO throw exception or Option ?
87 | }
88 | }
89 |
90 | override def buildScan(requiredColumns: Array[String]) = baseRDD.map(record => {
91 | Row.fromSeq(requiredColumns.map { col => toValue(record, col)})
92 | })
93 |
94 | }
--------------------------------------------------------------------------------
/src/main/scala/com/esri/spark/dbf/DefaultSource.scala:
--------------------------------------------------------------------------------
1 | package com.esri.spark.dbf
2 |
3 | import org.apache.spark.sql.SQLContext
4 | import org.apache.spark.sql.sources.{BaseRelation, RelationProvider}
5 |
6 | /**
7 | * Provides access to dbf data from pure SQL statements (i.e. for users of the JDBC server).
8 | */
9 | class DefaultSource extends RelationProvider {
10 | /**
11 | * Creates a new relation for data store in dbf given a `path` as a parameter.
12 | */
13 | override def createRelation(
14 | sqlContext: SQLContext,
15 | parameters: Map[String, String]): BaseRelation = {
16 | DBFRelation(parameters("path"))(sqlContext)
17 | }
18 | }
19 |
--------------------------------------------------------------------------------
/src/main/scala/com/esri/spark/dbf/package.scala:
--------------------------------------------------------------------------------
1 | package com.esri.spark
2 |
3 | import org.apache.spark.sql.SQLContext
4 |
5 | package object dbf {
6 |
7 | /**
8 | * Adds a method, `dbfFile`, to SQLContext that allows reading data stored in DBF.
9 | */
10 | implicit class DBFSQLContext(sqlContext: SQLContext) {
11 | def dbfFile(filePath: String) =
12 | sqlContext.baseRelationToSchemaRDD(DBFRelation(filePath)(sqlContext))
13 | }
14 |
15 | }
16 |
--------------------------------------------------------------------------------
/src/test/java/com/esri/JavaTestSuite.java:
--------------------------------------------------------------------------------
1 | package com.esri;
2 |
3 | import com.esri.core.geometry.Point;
4 | import org.apache.spark.api.java.JavaSparkContext;
5 | import org.apache.spark.sql.api.java.DataType;
6 | import org.apache.spark.sql.api.java.JavaSQLContext;
7 | import org.apache.spark.sql.api.java.Row;
8 | import org.apache.spark.sql.api.java.UDF2;
9 | import org.junit.After;
10 | import org.junit.Before;
11 | import org.junit.Ignore;
12 | import org.junit.Test;
13 |
14 | import java.io.Serializable;
15 |
16 | /**
17 | */
18 | public class JavaTestSuite implements Serializable
19 | {
20 |
21 | private transient JavaSparkContext sc;
22 | private transient JavaSQLContext sqlContext;
23 |
24 | @Before
25 | public void setUp()
26 | {
27 | sc = new JavaSparkContext("local", "JavaAPISuite");
28 | sqlContext = new JavaSQLContext(sc);
29 | }
30 |
31 | @After
32 | public void tearDown()
33 | {
34 | sc.stop();
35 | sc = null;
36 | }
37 |
38 | @SuppressWarnings("unchecked")
39 | @Test
40 | @Ignore
41 | public void pointTest()
42 | {
43 | sqlContext.registerFunction("ST_POINT", new UDF2()
44 | {
45 | @Override
46 | public Point call(final Double x, final Double y) throws Exception
47 | {
48 | return new Point(x, y);
49 | }
50 | }, DataType.BinaryType);
51 |
52 | Row result = (Row) sqlContext.sql("SELECT ST_POINT(1.0, 2.0)")
53 | .first();
54 | // System.out.println("result.toString() = " + result.toString());
55 | // assert (result.get(0).);
56 | }
57 |
58 | }
59 |
--------------------------------------------------------------------------------
/src/test/resources/log4j.properties:
--------------------------------------------------------------------------------
1 | # Set everything to be logged to the console
2 | log4j.rootCategory=INFO, console
3 | log4j.appender.console=org.apache.log4j.ConsoleAppender
4 | log4j.appender.console.target=System.out
5 | log4j.appender.console.layout=org.apache.log4j.PatternLayout
6 | log4j.appender.console.layout.ConversionPattern=%d{HH:mm:ss} %p %c{1}: %m%n
7 |
8 | # Settings to quiet third party logs that are too verbose
9 | log4j.logger.org.eclipse.jetty=WARN
10 | log4j.logger.org.eclipse.jetty.util.component.AbstractLifeCycle=ERROR
11 | log4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO
12 | log4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO
13 |
--------------------------------------------------------------------------------
/src/test/resources/logback.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
6 |
7 |
10 | %d{HH:mm:ss.SSS} %-5level - %msg%n
11 |
12 |
13 |
14 |
15 |
16 |
17 |
--------------------------------------------------------------------------------
/src/test/resources/test.dbf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/mraad/spark-dbf/b1083de1d6cb2ae90892af2d7a979425ea846a50/src/test/resources/test.dbf
--------------------------------------------------------------------------------
/src/test/scala/com/esri/spark/dbf/DBFSuite.scala:
--------------------------------------------------------------------------------
1 | package com.esri.spark.dbf
2 |
3 | import com.esri.core.geometry.Point
4 | import org.apache.spark.sql.test._
5 | import org.scalatest.FunSuite
6 |
7 | /* Implicits */
8 |
9 | import org.apache.spark.sql.test.TestSQLContext._
10 |
11 | /**
12 | */
13 | class DBFSuite extends FunSuite {
14 |
15 | val dbfFile = "src/test/resources/test.dbf"
16 |
17 | test("dsl test") {
18 | val results = TestSQLContext
19 | .dbfFile(dbfFile)
20 | .select('AText)
21 | .collect()
22 |
23 | assert(results.size === 2)
24 | }
25 |
26 | test("sql test") {
27 | sql( s"""
28 | |CREATE TEMPORARY TABLE dbfTable
29 | |USING com.esri.spark.dbf
30 | |OPTIONS (path "$dbfFile")
31 | """.stripMargin.replaceAll("\n", " "))
32 |
33 | assert(sql("SELECT * FROM dbfTable").collect().size === 2)
34 | }
35 |
36 | }
37 |
--------------------------------------------------------------------------------