161 src/test/spark/ParallelArraySplitSuite.scala
@@ -0,0 +1,161 @@
package spark
import org.scalatest.FunSuite
import org.scalatest.prop.Checkers
import org.scalacheck.Arbitrary._
import org.scalacheck.Gen
import org.scalacheck.Prop._
class ParallelArraySplitSuite extends FunSuite with Checkers {
test("one element per slice") {
val data = Array(1, 2, 3)
val slices = ParallelArray.slice(data, 3)
assert(slices.size === 3)
assert(slices(0).mkString(",") === "1")
assert(slices(1).mkString(",") === "2")
assert(slices(2).mkString(",") === "3")
}
test("one slice") {
val data = Array(1, 2, 3)
val slices = ParallelArray.slice(data, 1)
assert(slices.size === 1)
assert(slices(0).mkString(",") === "1,2,3")
}
test("equal slices") {
val data = Array(1, 2, 3, 4, 5, 6, 7, 8, 9)
val slices = ParallelArray.slice(data, 3)
assert(slices.size === 3)
assert(slices(0).mkString(",") === "1,2,3")
assert(slices(1).mkString(",") === "4,5,6")
assert(slices(2).mkString(",") === "7,8,9")
}
test("non-equal slices") {
val data = Array(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
val slices = ParallelArray.slice(data, 3)
assert(slices.size === 3)
assert(slices(0).mkString(",") === "1,2,3")
assert(slices(1).mkString(",") === "4,5,6")
assert(slices(2).mkString(",") === "7,8,9,10")
}
test("splitting exclusive range") {
val data = 0 until 100
val slices = ParallelArray.slice(data, 3)
assert(slices.size === 3)
assert(slices(0).mkString(",") === (0 to 32).mkString(","))
assert(slices(1).mkString(",") === (33 to 65).mkString(","))
assert(slices(2).mkString(",") === (66 to 99).mkString(","))
}
test("splitting inclusive range") {
val data = 0 to 100
val slices = ParallelArray.slice(data, 3)
assert(slices.size === 3)
assert(slices(0).mkString(",") === (0 to 32).mkString(","))
assert(slices(1).mkString(",") === (33 to 66).mkString(","))
assert(slices(2).mkString(",") === (67 to 100).mkString(","))
}
test("empty data") {
val data = new Array[Int](0)
val slices = ParallelArray.slice(data, 5)
assert(slices.size === 5)
for (slice <- slices) assert(slice.size === 0)
}
test("zero slices") {
val data = Array(1, 2, 3)
intercept[IllegalArgumentException] { ParallelArray.slice(data, 0) }
}
test("negative number of slices") {
val data = Array(1, 2, 3)
intercept[IllegalArgumentException] { ParallelArray.slice(data, -5) }
}
test("exclusive ranges sliced into ranges") {
val data = 1 until 100
val slices = ParallelArray.slice(data, 3)
assert(slices.size === 3)
assert(slices.map(_.size).reduceLeft(_+_) === 99)
assert(slices.forall(_.isInstanceOf[SerializableRange]))
}
test("inclusive ranges sliced into ranges") {
val data = 1 to 100
val slices = ParallelArray.slice(data, 3)
assert(slices.size === 3)
assert(slices.map(_.size).reduceLeft(_+_) === 100)
assert(slices.forall(_.isInstanceOf[SerializableRange]))
}
test("large ranges don't overflow") {
val N = 100 * 1000 * 1000
val data = 0 until N
val slices = ParallelArray.slice(data, 40)
assert(slices.size === 40)
for (i <- 0 until 40) {
assert(slices(i).isInstanceOf[SerializableRange])
val range = slices(i).asInstanceOf[SerializableRange]
assert(range.start === i * (N / 40), "slice " + i + " start")
assert(range.end === (i+1) * (N / 40), "slice " + i + " end")
assert(range.step === 1, "slice " + i + " step")
}
}
test("random array tests") {
val gen = for {
d <- arbitrary[List[Int]]
n <- Gen.choose(1, 100)
} yield (d, n)
val prop = forAll(gen) {
(tuple: (List[Int], Int)) =>
val d = tuple._1
val n = tuple._2
val slices = ParallelArray.slice(d, n)
("n slices" |: slices.size == n) &&
("concat to d" |: Array.concat(slices: _*).mkString(",") == d.mkString(",")) &&
("equal sizes" |: slices.map(_.size).forall(x => x==d.size/n || x==d.size/n+1))
}
check(prop)
}
test("random exclusive range tests") {
val gen = for {
a <- Gen.choose(-100, 100)
b <- Gen.choose(-100, 100)
step <- Gen.choose(-5, 5) suchThat (_ != 0)
n <- Gen.choose(1, 100)
} yield (a until b by step, n)
val prop = forAll(gen) {
case (d: Range, n: Int) =>
val slices = ParallelArray.slice(d, n)
("n slices" |: slices.size == n) &&
("all ranges" |: slices.forall(_.isInstanceOf[SerializableRange])) &&
("concat to d" |: Array.concat(slices: _*).mkString(",") == d.mkString(",")) &&
("equal sizes" |: slices.map(_.size).forall(x => x==d.size/n || x==d.size/n+1))
}
check(prop)
}
test("random inclusive range tests") {
val gen = for {
a <- Gen.choose(-100, 100)
b <- Gen.choose(-100, 100)
step <- Gen.choose(-5, 5) suchThat (_ != 0)
n <- Gen.choose(1, 100)
} yield (a to b by step, n)
val prop = forAll(gen) {
case (d: Range, n: Int) =>
val slices = ParallelArray.slice(d, n)
("n slices" |: slices.size == n) &&
("all ranges" |: slices.forall(_.isInstanceOf[SerializableRange])) &&
("concat to d" |: Array.concat(slices: _*).mkString(",") == d.mkString(",")) &&
("equal sizes" |: slices.map(_.size).forall(x => x==d.size/n || x==d.size/n+1))
}
check(prop)
}
}
124 src/test/spark/repl/ReplSuite.scala
@@ -0,0 +1,124 @@
package spark.repl
import java.io._
import org.scalatest.FunSuite
class ReplSuite extends FunSuite {
def runInterpreter(master: String, input: String): String = {
val in = new BufferedReader(new StringReader(input + "\n"))
val out = new StringWriter()
val interp = new SparkInterpreterLoop(in, new PrintWriter(out), master)
spark.repl.Main.interp = interp
interp.main(new Array[String](0))
spark.repl.Main.interp = null
return out.toString
}
def assertContains(message: String, output: String) {
assert(output contains message,
"Interpreter output did not contain '" + message + "':\n" + output)
}
def assertDoesNotContain(message: String, output: String) {
assert(!(output contains message),
"Interpreter output contained '" + message + "':\n" + output)
}
test ("simple foreach with accumulator") {
val output = runInterpreter("local", """
val accum = sc.accumulator(0)
sc.parallelize(1 to 10).foreach(x => accum += x)
accum.value
""")
assertDoesNotContain("error:", output)
assertDoesNotContain("Exception", output)
assertContains("res1: Int = 55", output)
}
test ("external vars") {
val output = runInterpreter("local", """
var v = 7
sc.parallelize(1 to 10).map(x => v).toArray.reduceLeft(_+_)
v = 10
sc.parallelize(1 to 10).map(x => v).toArray.reduceLeft(_+_)
""")
assertDoesNotContain("error:", output)
assertDoesNotContain("Exception", output)
assertContains("res0: Int = 70", output)
assertContains("res2: Int = 100", output)
}
test ("external classes") {
val output = runInterpreter("local", """
class C {
def foo = 5
}
sc.parallelize(1 to 10).map(x => (new C).foo).toArray.reduceLeft(_+_)
""")
assertDoesNotContain("error:", output)
assertDoesNotContain("Exception", output)
assertContains("res0: Int = 50", output)
}
test ("external functions") {
val output = runInterpreter("local", """
def double(x: Int) = x + x
sc.parallelize(1 to 10).map(x => double(x)).toArray.reduceLeft(_+_)
""")
assertDoesNotContain("error:", output)
assertDoesNotContain("Exception", output)
assertContains("res0: Int = 110", output)
}
test ("external functions that access vars") {
val output = runInterpreter("local", """
var v = 7
def getV() = v
sc.parallelize(1 to 10).map(x => getV()).toArray.reduceLeft(_+_)
v = 10
sc.parallelize(1 to 10).map(x => getV()).toArray.reduceLeft(_+_)
""")
assertDoesNotContain("error:", output)
assertDoesNotContain("Exception", output)
assertContains("res0: Int = 70", output)
assertContains("res2: Int = 100", output)
}
test ("cached vars") {
// Test that the value that a cached var had when it was created is used,
// even if that cached var is then modified in the driver program
val output = runInterpreter("local", """
var array = new Array[Int](5)
val cachedArray = sc.cache(array)
sc.parallelize(0 to 4).map(x => cachedArray.value(x)).toArray
array(0) = 5
sc.parallelize(0 to 4).map(x => cachedArray.value(x)).toArray
""")
assertDoesNotContain("error:", output)
assertDoesNotContain("Exception", output)
assertContains("res0: Array[Int] = Array(0, 0, 0, 0, 0)", output)
assertContains("res2: Array[Int] = Array(5, 0, 0, 0, 0)", output)
}
test ("running on Nexus") {
val output = runInterpreter("localquiet", """
var v = 7
def getV() = v
sc.parallelize(1 to 10).map(x => getV()).toArray.reduceLeft(_+_)
v = 10
sc.parallelize(1 to 10).map(x => getV()).toArray.reduceLeft(_+_)
var array = new Array[Int](5)
val cachedArray = sc.cache(array)
sc.parallelize(0 to 4).map(x => cachedArray.value(x)).toArray
array(0) = 5
sc.parallelize(0 to 4).map(x => cachedArray.value(x)).toArray
""")
assertDoesNotContain("error:", output)
assertDoesNotContain("Exception", output)
assertContains("res0: Int = 70", output)
assertContains("res2: Int = 100", output)
assertContains("res3: Array[Int] = Array(0, 0, 0, 0, 0)", output)
assertContains("res5: Array[Int] = Array(0, 0, 0, 0, 0)", output)
}
}
BIN third_party/ScalaCheck-1.5.jar
Binary file not shown.
BIN third_party/asm-3.2/.DS_Store
Binary file not shown.
3 third_party/asm-3.2/lib/all/README.txt
@@ -0,0 +1,3 @@
It is highly recommended to use only the necessary ASM jars for your
application instead of using the asm-all jar, unless you really need
all ASM packages.
BIN third_party/asm-3.2/lib/all/asm-all-3.2.jar
Binary file not shown.
15 third_party/asm-3.2/lib/all/asm-all-3.2.pom
@@ -0,0 +1,15 @@
<project>
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>asm</groupId>
<artifactId>asm-parent</artifactId>
<version>3.2</version>
</parent>
<name>ASM All</name>
<groupId>asm</groupId>
<artifactId>asm-all</artifactId>
<packaging>jar</packaging>
</project>
BIN third_party/asm-3.2/lib/all/asm-debug-all-3.2.jar
Binary file not shown.
15 third_party/asm-3.2/lib/all/asm-debug-all-3.2.pom
@@ -0,0 +1,15 @@
<project>
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>asm</groupId>
<artifactId>asm-parent</artifactId>
<version>3.2</version>
</parent>
<name>ASM All</name>
<groupId>asm</groupId>
<artifactId>asm-all</artifactId>
<packaging>jar</packaging>
</project>
BIN third_party/asm-3.2/lib/asm-3.2.jar
Binary file not shown.
14 third_party/asm-3.2/lib/asm-3.2.pom
@@ -0,0 +1,14 @@
<project>
<modelVersion>4.0.0</modelVersion>
<parent>
<artifactId>asm-parent</artifactId>
<groupId>asm</groupId>
<version>3.2</version>
</parent>
<name>ASM Core</name>
<artifactId>asm</artifactId>
<packaging>jar</packaging>
</project>
BIN third_party/asm-3.2/lib/asm-analysis-3.2.jar
Binary file not shown.
21 third_party/asm-3.2/lib/asm-analysis-3.2.pom
@@ -0,0 +1,21 @@
<project>
<modelVersion>4.0.0</modelVersion>
<parent>
<artifactId>asm-parent</artifactId>
<groupId>asm</groupId>
<version>3.2</version>
</parent>
<name>ASM Analysis</name>
<artifactId>asm-analysis</artifactId>
<packaging>jar</packaging>
<dependencies>
<dependency>
<artifactId>asm-tree</artifactId>
<groupId>asm</groupId>
</dependency>
</dependencies>
</project>
BIN third_party/asm-3.2/lib/asm-commons-3.2.jar
Binary file not shown.
21 third_party/asm-3.2/lib/asm-commons-3.2.pom
@@ -0,0 +1,21 @@
<project>
<modelVersion>4.0.0</modelVersion>
<parent>
<artifactId>asm-parent</artifactId>
<groupId>asm</groupId>
<version>3.2</version>
</parent>
<name>ASM Commons</name>
<artifactId>asm-commons</artifactId>
<packaging>jar</packaging>
<dependencies>
<dependency>
<artifactId>asm-tree</artifactId>
<groupId>asm</groupId>
</dependency>
</dependencies>
</project>
136 third_party/asm-3.2/lib/asm-parent-3.2.pom
@@ -0,0 +1,136 @@
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0
http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<artifactId>asm-parent</artifactId>
<groupId>asm</groupId>
<version>3.2</version>
<packaging>pom</packaging>
<name>ASM</name>
<description>A very small and fast Java bytecode manipulation framework</description>
<url>http://asm.objectweb.org/</url>
<organization>
<name>ObjectWeb</name>
<url>http://www.objectweb.org/</url>
</organization>
<inceptionYear>2000</inceptionYear>
<licenses>
<license>
<name>BSD</name>
<url>http://asm.objectweb.org/license.html</url>
</license>
</licenses>
<developers>
<developer>
<name>Eric Bruneton</name>
<id>ebruneton</id>
<email>Eric.Bruneton@rd.francetelecom.com</email>
<roles>
<role>Creator</role>
<role>Java Developer</role>
</roles>
</developer>
<developer>
<name>Eugene Kuleshov</name>
<id>eu</id>
<email>eu@javatx.org</email>
<roles>
<role>Java Developer</role>
</roles>
</developer>
</developers>
<scm>
<connection>scm:cvs:pserver:anonymous:@cvs.forge.objectweb.org:/cvsroot/asm:asm</connection>
<developerConnection>scm:cvs:ext:${maven.username}@cvs.forge.objectweb.org:/cvsroot/asm:asm</developerConnection>
<url>http://cvs.forge.objectweb.org/cgi-bin/viewcvs.cgi/asm/asm/</url>
</scm>
<issueManagement>
<url>http://forge.objectweb.org/tracker/?group_id=23</url>
</issueManagement>
<dependencyManagement>
<dependencies>
<dependency>
<artifactId>asm</artifactId>
<groupId>${project.groupId}</groupId>
<version>${project.version}</version>
</dependency>
<dependency>
<artifactId>asm-tree</artifactId>
<groupId>${project.groupId}</groupId>
<version>${project.version}</version>
</dependency>
<dependency>
<artifactId>asm-analysis</artifactId>
<groupId>${project.groupId}</groupId>
<version>${project.version}</version>
</dependency>
<dependency>
<artifactId>asm-commons</artifactId>
<groupId>${project.groupId}</groupId>
<version>${project.version}</version>
</dependency>
<dependency>
<artifactId>asm-util</artifactId>
<groupId>${project.groupId}</groupId>
<version>${project.version}</version>
</dependency>
<dependency>
<artifactId>asm-xml</artifactId>
<groupId>${project.groupId}</groupId>
<version>${project.version}</version>
</dependency>
</dependencies>
</dependencyManagement>
<mailingLists>
<mailingList>
<name>ASM Users List</name>
<subscribe>sympa@ow2.org?subject=subscribe%20asm</subscribe>
<unsubscribe>sympa@ow2.org?subject=unsubscribe%20asm</unsubscribe>
<post>asm@ow2.org</post>
<archive>http://www.ow2.org/wws/arc/asm</archive>
</mailingList>
<mailingList>
<name>ASM Team List</name>
<subscribe>sympa@ow2.org?subject=subscribe%20asm-team</subscribe>
<unsubscribe>sympa@ow2.org?subject=unsubscribe%20asm-team</unsubscribe>
<post>asm-team@ow2.org</post>
<archive>http://www.ow2.org/wws/arc/asm-team</archive>
</mailingList>
</mailingLists>
<distributionManagement>
<downloadUrl>http://mojo.codehaus.org/my-project</downloadUrl>
<repository>
<id>objectweb</id>
<uniqueVersion>false</uniqueVersion>
<name>ObjectWeb Maven 2.0 Repository</name>
<url>dav:https://maven.forge.objectweb.org:8002/maven2/</url>
<layout>default</layout>
</repository>
<snapshotRepository>
<id>objectweb.snapshots</id>
<uniqueVersion>false</uniqueVersion>
<name>ObjectWeb Maven 2.0 Snapshot Repository</name>
<url>dav:https://maven.forge.objectweb.org:8002/maven2-snapshot/</url>
<layout>default</layout>
</snapshotRepository>
</distributionManagement>
</project>
BIN third_party/asm-3.2/lib/asm-tree-3.2.jar
Binary file not shown.
21 third_party/asm-3.2/lib/asm-tree-3.2.pom
@@ -0,0 +1,21 @@
<project>
<modelVersion>4.0.0</modelVersion>
<parent>
<artifactId>asm-parent</artifactId>
<groupId>asm</groupId>
<version>3.2</version>
</parent>
<name>ASM Tree</name>
<artifactId>asm-tree</artifactId>
<packaging>jar</packaging>
<dependencies>
<dependency>
<artifactId>asm</artifactId>
<groupId>asm</groupId>
</dependency>
</dependencies>
</project>
BIN third_party/asm-3.2/lib/asm-util-3.2.jar
Binary file not shown.
21 third_party/asm-3.2/lib/asm-util-3.2.pom
@@ -0,0 +1,21 @@
<project>
<modelVersion>4.0.0</modelVersion>
<parent>
<artifactId>asm-parent</artifactId>
<groupId>asm</groupId>
<version>3.2</version>
</parent>
<name>ASM Util</name>
<artifactId>asm-util</artifactId>
<packaging>jar</packaging>
<dependencies>
<dependency>
<artifactId>asm-tree</artifactId>
<groupId>asm</groupId>
</dependency>
</dependencies>
</project>
BIN third_party/asm-3.2/lib/asm-xml-3.2.jar
Binary file not shown.
21 third_party/asm-3.2/lib/asm-xml-3.2.pom
@@ -0,0 +1,21 @@
<project>
<modelVersion>4.0.0</modelVersion>
<parent>
<artifactId>asm-parent</artifactId>
<groupId>asm</groupId>
<version>3.2</version>
</parent>
<name>ASM XML</name>
<artifactId>asm-xml</artifactId>
<packaging>jar</packaging>
<dependencies>
<dependency>
<artifactId>asm-util</artifactId>
<groupId>asm</groupId>
</dependency>
</dependencies>
</project>
BIN third_party/colt.jar
Binary file not shown.
202 third_party/google-collect-1.0-rc5/COPYING
@@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed 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.
BIN third_party/google-collect-1.0-rc5/google-collect-1.0-rc5.jar
Binary file not shown.
BIN third_party/hadoop-0.20.0/.DS_Store
Binary file not shown.
8,288 third_party/hadoop-0.20.0/CHANGES.txt

Large diffs are not rendered by default.

Oops, something went wrong.
244 third_party/hadoop-0.20.0/LICENSE.txt
@@ -0,0 +1,244 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed 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.
APACHE HADOOP SUBCOMPONENTS:
The Apache Hadoop project contains subcomponents with separate copyright
notices and license terms. Your use of the source code for the these
subcomponents is subject to the terms and conditions of the following
licenses.
For the org.apache.hadoop.util.bloom.* classes:
/**
*
* Copyright (c) 2005, European Commission project OneLab under contract
* 034819 (http://www.one-lab.org)
* All rights reserved.
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
* - Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* - Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the distribution.
* - Neither the name of the University Catholique de Louvain - UCL
* nor the names of its contributors may be used to endorse or
* promote products derived from this software without specific prior
* written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
2 third_party/hadoop-0.20.0/NOTICE.txt
@@ -0,0 +1,2 @@
This product includes software developed by The Apache Software
Foundation (http://www.apache.org/).
31 third_party/hadoop-0.20.0/README.txt
@@ -0,0 +1,31 @@
For the latest information about Hadoop, please visit our website at:
http://hadoop.apache.org/core/
and our wiki, at:
http://wiki.apache.org/hadoop/
This distribution includes cryptographic software. The country in
which you currently reside may have restrictions on the import,
possession, use, and/or re-export to another country, of
encryption software. BEFORE using any encryption software, please
check your country's laws, regulations and policies concerning the
import, possession, or use, and re-export of encryption software, to
see if this is permitted. See <http://www.wassenaar.org/> for more
information.
The U.S. Government Department of Commerce, Bureau of Industry and
Security (BIS), has classified this software as Export Commodity
Control Number (ECCN) 5D002.C.1, which includes information security
software using or performing cryptographic functions with asymmetric
algorithms. The form and manner of this Apache Software Foundation
distribution makes it eligible for export under the License Exception
ENC Technology Software Unrestricted (TSU) exception (see the BIS
Export Administration Regulations, Section 740.13) for both object
code and source code.
The following provides more details on the included cryptographic
software:
Hadoop Core uses the SSL libraries from the Jetty project written
by mortbay.org.
289 third_party/hadoop-0.20.0/bin/hadoop
@@ -0,0 +1,289 @@
#!/usr/bin/env bash
# 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.
# The Hadoop command script
#
# Environment Variables
#
# JAVA_HOME The java implementation to use. Overrides JAVA_HOME.
#
# HADOOP_CLASSPATH Extra Java CLASSPATH entries.
#
# HADOOP_HEAPSIZE The maximum amount of heap to use, in MB.
# Default is 1000.
#
# HADOOP_OPTS Extra Java runtime options.
#
# HADOOP_NAMENODE_OPTS These options are added to HADOOP_OPTS
# HADOOP_CLIENT_OPTS when the respective command is run.
# HADOOP_{COMMAND}_OPTS etc HADOOP_JT_OPTS applies to JobTracker
# for e.g. HADOOP_CLIENT_OPTS applies to
# more than one command (fs, dfs, fsck,
# dfsadmin etc)
#
# HADOOP_CONF_DIR Alternate conf dir. Default is ${HADOOP_HOME}/conf.
#
# HADOOP_ROOT_LOGGER The root appender. Default is INFO,console
#
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
cygwin=false
case "`uname`" in
CYGWIN*) cygwin=true;;
esac
# if no args specified, show usage
if [ $# = 0 ]; then
echo "Usage: hadoop [--config confdir] COMMAND"
echo "where COMMAND is one of:"
echo " namenode -format format the DFS filesystem"
echo " secondarynamenode run the DFS secondary namenode"
echo " namenode run the DFS namenode"
echo " datanode run a DFS datanode"
echo " dfsadmin run a DFS admin client"
echo " mradmin run a Map-Reduce admin client"
echo " fsck run a DFS filesystem checking utility"
echo " fs run a generic filesystem user client"
echo " balancer run a cluster balancing utility"
echo " jobtracker run the MapReduce job Tracker node"
echo " pipes run a Pipes job"
echo " tasktracker run a MapReduce task Tracker node"
echo " job manipulate MapReduce jobs"
echo " queue get information regarding JobQueues"
echo " version print the version"
echo " jar <jar> run a jar file"
echo " distcp <srcurl> <desturl> copy file or directories recursively"
echo " archive -archiveName NAME <src>* <dest> create a hadoop archive"
echo " daemonlog get/set the log level for each daemon"
echo " or"
echo " CLASSNAME run the class named CLASSNAME"
echo "Most commands print help when invoked w/o parameters."
exit 1
fi
# get arguments
COMMAND=$1
shift
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
. "${HADOOP_CONF_DIR}/hadoop-env.sh"
fi
# some Java parameters
if [ "$JAVA_HOME" != "" ]; then
#echo "run java in $JAVA_HOME"
JAVA_HOME=$JAVA_HOME
fi
if [ "$JAVA_HOME" = "" ]; then
echo "Error: JAVA_HOME is not set."
exit 1
fi
JAVA=$JAVA_HOME/bin/java
JAVA_HEAP_MAX=-Xmx1000m
# check envvars which might override default args
if [ "$HADOOP_HEAPSIZE" != "" ]; then
#echo "run with heapsize $HADOOP_HEAPSIZE"
JAVA_HEAP_MAX="-Xmx""$HADOOP_HEAPSIZE""m"
#echo $JAVA_HEAP_MAX
fi
# CLASSPATH initially contains $HADOOP_CONF_DIR
CLASSPATH="${HADOOP_CONF_DIR}"
CLASSPATH=${CLASSPATH}:$JAVA_HOME/lib/tools.jar
# for developers, add Hadoop classes to CLASSPATH
if [ -d "$HADOOP_HOME/build/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/classes
fi
if [ -d "$HADOOP_HOME/build/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build
fi
if [ -d "$HADOOP_HOME/build/test/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/test/classes
fi
if [ -d "$HADOOP_HOME/build/tools" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/tools
fi
# so that filenames w/ spaces are handled correctly in loops below
IFS=
# for releases, add core hadoop jar & webapps to CLASSPATH
if [ -d "$HADOOP_HOME/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME
fi
for f in $HADOOP_HOME/hadoop-*-core.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
# add libs to CLASSPATH
for f in $HADOOP_HOME/lib/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
if [ -d "$HADOOP_HOME/build/ivy/lib/Hadoop/common" ]; then
for f in $HADOOP_HOME/build/ivy/lib/Hadoop/common/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
fi
for f in $HADOOP_HOME/lib/jsp-2.1/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
for f in $HADOOP_HOME/hadoop-*-tools.jar; do
TOOL_PATH=${TOOL_PATH}:$f;
done
for f in $HADOOP_HOME/build/hadoop-*-tools.jar; do
TOOL_PATH=${TOOL_PATH}:$f;
done
# add user-specified CLASSPATH last
if [ "$HADOOP_CLASSPATH" != "" ]; then
CLASSPATH=${CLASSPATH}:${HADOOP_CLASSPATH}
fi
# default log directory & file
if [ "$HADOOP_LOG_DIR" = "" ]; then
HADOOP_LOG_DIR="$HADOOP_HOME/logs"
fi
if [ "$HADOOP_LOGFILE" = "" ]; then
HADOOP_LOGFILE='hadoop.log'
fi
# default policy file for service-level authorization
if [ "$HADOOP_POLICYFILE" = "" ]; then
HADOOP_POLICYFILE="hadoop-policy.xml"
fi
# restore ordinary behaviour
unset IFS
# figure out which class to run
if [ "$COMMAND" = "namenode" ] ; then
CLASS='org.apache.hadoop.hdfs.server.namenode.NameNode'
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_NAMENODE_OPTS"
elif [ "$COMMAND" = "secondarynamenode" ] ; then
CLASS='org.apache.hadoop.hdfs.server.namenode.SecondaryNameNode'
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_SECONDARYNAMENODE_OPTS"
elif [ "$COMMAND" = "datanode" ] ; then
CLASS='org.apache.hadoop.hdfs.server.datanode.DataNode'
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_DATANODE_OPTS"
elif [ "$COMMAND" = "fs" ] ; then
CLASS=org.apache.hadoop.fs.FsShell
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "dfs" ] ; then
CLASS=org.apache.hadoop.fs.FsShell
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "dfsadmin" ] ; then
CLASS=org.apache.hadoop.hdfs.tools.DFSAdmin
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "mradmin" ] ; then
CLASS=org.apache.hadoop.mapred.tools.MRAdmin
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "fsck" ] ; then
CLASS=org.apache.hadoop.hdfs.tools.DFSck
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "balancer" ] ; then
CLASS=org.apache.hadoop.hdfs.server.balancer.Balancer
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_BALANCER_OPTS"
elif [ "$COMMAND" = "jobtracker" ] ; then
CLASS=org.apache.hadoop.mapred.JobTracker
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_JOBTRACKER_OPTS"
elif [ "$COMMAND" = "tasktracker" ] ; then
CLASS=org.apache.hadoop.mapred.TaskTracker
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_TASKTRACKER_OPTS"
elif [ "$COMMAND" = "job" ] ; then
CLASS=org.apache.hadoop.mapred.JobClient
elif [ "$COMMAND" = "queue" ] ; then
CLASS=org.apache.hadoop.mapred.JobQueueClient
elif [ "$COMMAND" = "pipes" ] ; then
CLASS=org.apache.hadoop.mapred.pipes.Submitter
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "version" ] ; then
CLASS=org.apache.hadoop.util.VersionInfo
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "jar" ] ; then
CLASS=org.apache.hadoop.util.RunJar
elif [ "$COMMAND" = "distcp" ] ; then
CLASS=org.apache.hadoop.tools.DistCp
CLASSPATH=${CLASSPATH}:${TOOL_PATH}
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "daemonlog" ] ; then
CLASS=org.apache.hadoop.log.LogLevel
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "archive" ] ; then
CLASS=org.apache.hadoop.tools.HadoopArchives
CLASSPATH=${CLASSPATH}:${TOOL_PATH}
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
elif [ "$COMMAND" = "sampler" ] ; then
CLASS=org.apache.hadoop.mapred.lib.InputSampler
HADOOP_OPTS="$HADOOP_OPTS $HADOOP_CLIENT_OPTS"
else
CLASS=$COMMAND
fi
# cygwin path translation
if $cygwin; then
CLASSPATH=`cygpath -p -w "$CLASSPATH"`
HADOOP_HOME=`cygpath -w "$HADOOP_HOME"`
HADOOP_LOG_DIR=`cygpath -w "$HADOOP_LOG_DIR"`
TOOL_PATH=`cygpath -p -w "$TOOL_PATH"`
fi
# setup 'java.library.path' for native-hadoop code if necessary
JAVA_LIBRARY_PATH=''
if [ -d "${HADOOP_HOME}/build/native" -o -d "${HADOOP_HOME}/lib/native" ]; then
JAVA_PLATFORM=`CLASSPATH=${CLASSPATH} ${JAVA} -Xmx32m org.apache.hadoop.util.PlatformName | sed -e "s/ /_/g"`
if [ -d "$HADOOP_HOME/build/native" ]; then
JAVA_LIBRARY_PATH=${HADOOP_HOME}/build/native/${JAVA_PLATFORM}/lib
fi
if [ -d "${HADOOP_HOME}/lib/native" ]; then
if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then
JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}:${HADOOP_HOME}/lib/native/${JAVA_PLATFORM}
else
JAVA_LIBRARY_PATH=${HADOOP_HOME}/lib/native/${JAVA_PLATFORM}
fi
fi
fi
# cygwin path translation
if $cygwin; then
JAVA_LIBRARY_PATH=`cygpath -p "$JAVA_LIBRARY_PATH"`
fi
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.dir=$HADOOP_LOG_DIR"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.file=$HADOOP_LOGFILE"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.home.dir=$HADOOP_HOME"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.id.str=$HADOOP_IDENT_STRING"
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.root.logger=${HADOOP_ROOT_LOGGER:-INFO,console}"
if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then
HADOOP_OPTS="$HADOOP_OPTS -Djava.library.path=$JAVA_LIBRARY_PATH"
fi
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.policy.file=$HADOOP_POLICYFILE"
# run it
exec "$JAVA" $JAVA_HEAP_MAX $HADOOP_OPTS -classpath "$CLASSPATH" $CLASS "$@"
68 third_party/hadoop-0.20.0/bin/hadoop-config.sh
@@ -0,0 +1,68 @@
# 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.
# included in all the hadoop scripts with source command
# should not be executable directly
# also should not be passed any arguments, since we need original $*
# resolve links - $0 may be a softlink
this="$0"
while [ -h "$this" ]; do
ls=`ls -ld "$this"`
link=`expr "$ls" : '.*-> \(.*\)$'`
if expr "$link" : '.*/.*' > /dev/null; then
this="$link"
else
this=`dirname "$this"`/"$link"
fi
done
# convert relative path to absolute path
bin=`dirname "$this"`
script=`basename "$this"`
bin=`cd "$bin"; pwd`
this="$bin/$script"
# the root of the Hadoop installation
export HADOOP_HOME=`dirname "$this"`/..
#check to see if the conf dir is given as an optional argument
if [ $# -gt 1 ]
then
if [ "--config" = "$1" ]
then
shift
confdir=$1
shift
HADOOP_CONF_DIR=$confdir
fi
fi
# Allow alternate conf dir location.
HADOOP_CONF_DIR="${HADOOP_CONF_DIR:-$HADOOP_HOME/conf}"
#check to see it is specified whether to use the slaves or the
# masters file
if [ $# -gt 1 ]
then
if [ "--hosts" = "$1" ]
then
shift
slavesfile=$1
shift
export HADOOP_SLAVES="${HADOOP_CONF_DIR}/$slavesfile"
fi
fi
143 third_party/hadoop-0.20.0/bin/hadoop-daemon.sh
@@ -0,0 +1,143 @@
#!/usr/bin/env bash
# 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.
# Runs a Hadoop command as a daemon.
#
# Environment Variables
#
# HADOOP_CONF_DIR Alternate conf dir. Default is ${HADOOP_HOME}/conf.
# HADOOP_LOG_DIR Where log files are stored. PWD by default.
# HADOOP_MASTER host:path where hadoop code should be rsync'd from
# HADOOP_PID_DIR The pid files are stored. /tmp by default.
# HADOOP_IDENT_STRING A string representing this instance of hadoop. $USER by default
# HADOOP_NICENESS The scheduling priority for daemons. Defaults to 0.
##
usage="Usage: hadoop-daemon.sh [--config <conf-dir>] [--hosts hostlistfile] (start|stop) <hadoop-command> <args...>"
# if no args specified, show usage
if [ $# -le 1 ]; then
echo $usage
exit 1
fi
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# get arguments
startStop=$1
shift
command=$1
shift
hadoop_rotate_log ()
{
log=$1;
num=5;
if [ -n "$2" ]; then
num=$2
fi
if [ -f "$log" ]; then # rotate logs
while [ $num -gt 1 ]; do
prev=`expr $num - 1`
[ -f "$log.$prev" ] && mv "$log.$prev" "$log.$num"
num=$prev
done
mv "$log" "$log.$num";
fi
}
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
. "${HADOOP_CONF_DIR}/hadoop-env.sh"
fi
# get log directory
if [ "$HADOOP_LOG_DIR" = "" ]; then
export HADOOP_LOG_DIR="$HADOOP_HOME/logs"
fi
mkdir -p "$HADOOP_LOG_DIR"
if [ "$HADOOP_PID_DIR" = "" ]; then
HADOOP_PID_DIR=/tmp
fi
if [ "$HADOOP_IDENT_STRING" = "" ]; then
export HADOOP_IDENT_STRING="$USER"
fi
# some variables
export HADOOP_LOGFILE=hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.log
export HADOOP_ROOT_LOGGER="INFO,DRFA"
log=$HADOOP_LOG_DIR/hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.out
pid=$HADOOP_PID_DIR/hadoop-$HADOOP_IDENT_STRING-$command.pid
# Set default scheduling priority
if [ "$HADOOP_NICENESS" = "" ]; then
export HADOOP_NICENESS=0
fi
case $startStop in
(start)
mkdir -p "$HADOOP_PID_DIR"
if [ -f $pid ]; then
if kill -0 `cat $pid` > /dev/null 2>&1; then
echo $command running as process `cat $pid`. Stop it first.
exit 1
fi
fi
if [ "$HADOOP_MASTER" != "" ]; then
echo rsync from $HADOOP_MASTER
rsync -a -e ssh --delete --exclude=.svn --exclude='logs/*' --exclude='contrib/hod/logs/*' $HADOOP_MASTER/ "$HADOOP_HOME"
fi
hadoop_rotate_log $log
echo starting $command, logging to $log
cd "$HADOOP_HOME"
nohup nice -n $HADOOP_NICENESS "$HADOOP_HOME"/bin/hadoop --config $HADOOP_CONF_DIR $command "$@" > "$log" 2>&1 < /dev/null &
echo $! > $pid
sleep 1; head "$log"
;;
(stop)
if [ -f $pid ]; then
if kill -0 `cat $pid` > /dev/null 2>&1; then
echo stopping $command
kill `cat $pid`
else
echo no $command to stop
fi
else
echo no $command to stop
fi
;;
(*)
echo $usage
exit 1
;;
esac
34 third_party/hadoop-0.20.0/bin/hadoop-daemons.sh
@@ -0,0 +1,34 @@
#!/usr/bin/env bash
# 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.
# Run a Hadoop command on all slave hosts.
usage="Usage: hadoop-daemons.sh [--config confdir] [--hosts hostlistfile] [start|stop] command args..."
# if no args specified, show usage
if [ $# -le 1 ]; then
echo $usage
exit 1
fi
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. $bin/hadoop-config.sh
exec "$bin/slaves.sh" --config $HADOOP_CONF_DIR cd "$HADOOP_HOME" \; "$bin/hadoop-daemon.sh" --config $HADOOP_CONF_DIR "$@"
99 third_party/hadoop-0.20.0/bin/rcc
@@ -0,0 +1,99 @@
#!/usr/bin/env bash
# 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.
# The Hadoop record compiler
#
# Environment Variables
#
# JAVA_HOME The java implementation to use. Overrides JAVA_HOME.
#
# HADOOP_OPTS Extra Java runtime options.
#
# HADOOP_CONF_DIR Alternate conf dir. Default is ${HADOOP_HOME}/conf.
#
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
. "${HADOOP_CONF_DIR}/hadoop-env.sh"
fi
# some Java parameters
if [ "$JAVA_HOME" != "" ]; then
#echo "run java in $JAVA_HOME"
JAVA_HOME=$JAVA_HOME
fi
if [ "$JAVA_HOME" = "" ]; then
echo "Error: JAVA_HOME is not set."
exit 1
fi
JAVA=$JAVA_HOME/bin/java
JAVA_HEAP_MAX=-Xmx1000m
# CLASSPATH initially contains $HADOOP_CONF_DIR
CLASSPATH="${HADOOP_CONF_DIR}"
CLASSPATH=${CLASSPATH}:$JAVA_HOME/lib/tools.jar
# for developers, add Hadoop classes to CLASSPATH
if [ -d "$HADOOP_HOME/build/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/classes
fi
if [ -d "$HADOOP_HOME/build/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build
fi
if [ -d "$HADOOP_HOME/build/test/classes" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME/build/test/classes
fi
# so that filenames w/ spaces are handled correctly in loops below
IFS=
# for releases, add core hadoop jar & webapps to CLASSPATH
if [ -d "$HADOOP_HOME/webapps" ]; then
CLASSPATH=${CLASSPATH}:$HADOOP_HOME
fi
for f in $HADOOP_HOME/hadoop-*-core.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
# add libs to CLASSPATH
for f in $HADOOP_HOME/lib/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
for f in $HADOOP_HOME/lib/jetty-ext/*.jar; do
CLASSPATH=${CLASSPATH}:$f;
done
# restore ordinary behaviour
unset IFS
CLASS='org.apache.hadoop.record.compiler.generated.Rcc'
# cygwin path translation
if expr `uname` : 'CYGWIN*' > /dev/null; then
CLASSPATH=`cygpath -p -w "$CLASSPATH"`
fi
# run it
exec "$JAVA" $HADOOP_OPTS -classpath "$CLASSPATH" $CLASS "$@"
68 third_party/hadoop-0.20.0/bin/slaves.sh
@@ -0,0 +1,68 @@
#!/usr/bin/env bash
# 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.
# Run a shell command on all slave hosts.
#
# Environment Variables
#
# HADOOP_SLAVES File naming remote hosts.
# Default is ${HADOOP_CONF_DIR}/slaves.
# HADOOP_CONF_DIR Alternate conf dir. Default is ${HADOOP_HOME}/conf.
# HADOOP_SLAVE_SLEEP Seconds to sleep between spawning remote commands.
# HADOOP_SSH_OPTS Options passed to ssh when running remote commands.
##
usage="Usage: slaves.sh [--config confdir] command..."
# if no args specified, show usage
if [ $# -le 0 ]; then
echo $usage
exit 1
fi
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# If the slaves file is specified in the command line,
# then it takes precedence over the definition in
# hadoop-env.sh. Save it here.
HOSTLIST=$HADOOP_SLAVES
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
. "${HADOOP_CONF_DIR}/hadoop-env.sh"
fi
if [ "$HOSTLIST" = "" ]; then
if [ "$HADOOP_SLAVES" = "" ]; then
export HOSTLIST="${HADOOP_CONF_DIR}/slaves"
else
export HOSTLIST="${HADOOP_SLAVES}"
fi
fi
for slave in `cat "$HOSTLIST"|sed "s/#.*$//;/^$/d"`; do
ssh $HADOOP_SSH_OPTS $slave $"${@// /\\ }" \
2>&1 | sed "s/^/$slave: /" &
if [ "$HADOOP_SLAVE_SLEEP" != "" ]; then
sleep $HADOOP_SLAVE_SLEEP
fi
done
wait
30 third_party/hadoop-0.20.0/bin/start-all.sh
@@ -0,0 +1,30 @@
#!/usr/bin/env bash
# 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.
# Start all hadoop daemons. Run this on master node.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# start dfs daemons
"$bin"/start-dfs.sh --config $HADOOP_CONF_DIR
# start mapred daemons
"$bin"/start-mapred.sh --config $HADOOP_CONF_DIR
25 third_party/hadoop-0.20.0/bin/start-balancer.sh
@@ -0,0 +1,25 @@
#!/usr/bin/env bash
# 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.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# Start balancer daemon.
"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR start balancer $@
52 third_party/hadoop-0.20.0/bin/start-dfs.sh
@@ -0,0 +1,52 @@
#!/usr/bin/env bash
# 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.
# Start hadoop dfs daemons.
# Optinally upgrade or rollback dfs state.
# Run this on master node.
usage="Usage: start-dfs.sh [-upgrade|-rollback]"
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# get arguments
if [ $# -ge 1 ]; then
nameStartOpt=$1
shift
case $nameStartOpt in
(-upgrade)
;;
(-rollback)
dataStartOpt=$nameStartOpt
;;
(*)
echo $usage
exit 1
;;
esac
fi
# start dfs daemons
# start namenode after datanodes, to minimize time namenode is up w/o data
# note: datanodes will log connection errors until namenode starts
"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR start namenode $nameStartOpt
"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR start datanode $dataStartOpt
"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR --hosts masters start secondarynamenode
29 third_party/hadoop-0.20.0/bin/start-mapred.sh
@@ -0,0 +1,29 @@
#!/usr/bin/env bash
# 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.
# Start hadoop map reduce daemons. Run this on master node.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# start mapred daemons
# start jobtracker first to minimize connection errors at startup
"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR start jobtracker
"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR start tasktracker
27 third_party/hadoop-0.20.0/bin/stop-all.sh
@@ -0,0 +1,27 @@
#!/usr/bin/env bash
# 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.
# Stop all hadoop daemons. Run this on master node.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
"$bin"/stop-mapred.sh --config $HADOOP_CONF_DIR
"$bin"/stop-dfs.sh --config $HADOOP_CONF_DIR
26 third_party/hadoop-0.20.0/bin/stop-balancer.sh
@@ -0,0 +1,26 @@
#!/usr/bin/env bash
# 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.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
# Stop balancer daemon.
# Run this on the machine where the balancer is running
"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR stop balancer
29 third_party/hadoop-0.20.0/bin/stop-dfs.sh
@@ -0,0 +1,29 @@
#!/usr/bin/env bash
# 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.
# Stop hadoop DFS daemons. Run this on master node.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR stop namenode
"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR stop datanode
"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR --hosts masters stop secondarynamenode
28 third_party/hadoop-0.20.0/bin/stop-mapred.sh
@@ -0,0 +1,28 @@
#!/usr/bin/env bash
# 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.
# Stop hadoop map reduce daemons. Run this on master node.
bin=`dirname "$0"`
bin=`cd "$bin"; pwd`
. "$bin"/hadoop-config.sh
"$bin"/hadoop-daemon.sh --config $HADOOP_CONF_DIR stop jobtracker
"$bin"/hadoop-daemons.sh --config $HADOOP_CONF_DIR stop tasktracker
1,796 third_party/hadoop-0.20.0/build.xml

Large diffs are not rendered by default.

Oops, something went wrong.
258 third_party/hadoop-0.20.0/c++/Linux-amd64-64/include/hadoop/Pipes.hh
@@ -0,0 +1,258 @@
/**
* 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.
*/
#ifndef HADOOP_PIPES_HH
#define HADOOP_PIPES_HH
#ifdef SWIG
%module (directors="1") HadoopPipes
%include "std_string.i"
%feature("director") Mapper;
%feature("director") Reducer;
%feature("director") Partitioner;
%feature("director") RecordReader;
%feature("director") RecordWriter;
%feature("director") Factory;
#else
#include <string>
#endif
namespace HadoopPipes {
/**
* This interface defines the interface between application code and the
* foreign code interface to Hadoop Map/Reduce.
*/
/**
* A JobConf defines the properties for a job.
*/
class JobConf {
public:
virtual bool hasKey(const std::string& key) const = 0;
virtual const std::string& get(const std::string& key) const = 0;
virtual int getInt(const std::string& key) const = 0;
virtual float getFloat(const std::string& key) const = 0;
virtual bool getBoolean(const std::string&key) const = 0;
virtual ~JobConf() {}
};
/**
* Task context provides the information about the task and job.
*/
class TaskContext {
public:
/**
* Counter to keep track of a property and its value.
*/
class Counter {
private:
int id;
public:
Counter(int counterId) : id(counterId) {}
Counter(const Counter& counter) : id(counter.id) {}
int getId() const { return id; }
};
/**
* Get the JobConf for the current task.
*/
virtual const JobConf* getJobConf() = 0;
/**
* Get the current key.
* @return the current key
*/
virtual const std::string& getInputKey() = 0;
/**
* Get the current value.
* @return the current value
*/
virtual const std::string& getInputValue() = 0;
/**
* Generate an output record
*/
virtual void emit(const std::string& key, const std::string& value) = 0;
/**
* Mark your task as having made progress without changing the status
* message.
*/
virtual void progress() = 0;
/**
* Set the status message and call progress.
*/
virtual void setStatus(const std::string& status) = 0;
/**
* Register a counter with the given group and name.
*/
virtual Counter*
getCounter(const std::string& group, const std::string& name) = 0;
/**
* Increment the value of the counter with the given amount.
*/
virtual void incrementCounter(const Counter* counter, uint64_t amount) = 0;
virtual ~TaskContext() {}
};
class MapContext: public TaskContext {
public:
/**
* Access the InputSplit of the mapper.
*/
virtual const std::string& getInputSplit() = 0;
/**
* Get the name of the key class of the input to this task.
*/
virtual const std::string& getInputKeyClass() = 0;
/**
* Get the name of the value class of the input to this task.
*/
virtual const std::string& getInputValueClass() = 0;
};
class ReduceContext: public TaskContext {
public:
/**
* Advance to the next value.
*/
virtual bool nextValue() = 0;
};
class Closable {
public:
virtual void close() {}
virtual ~Closable() {}
};
/**
* The application's mapper class to do map.
*/
class Mapper: public Closable {
public:
virtual void map(MapContext& context) = 0;
};
/**
* The application's reducer class to do reduce.
*/
class Reducer: public Closable {
public:
virtual void reduce(ReduceContext& context) = 0;
};
/**
* User code to decide where each key should be sent.
*/
class Partitioner {
public:
virtual int partition(const std::string& key, int numOfReduces) = 0;
virtual ~Partitioner() {}
};
/**
* For applications that want to read the input directly for the map function
* they can define RecordReaders in C++.
*/
class RecordReader: public Closable {
public:
virtual bool next(std::string& key, std::string& value) = 0;
/**
* The progress of the record reader through the split as a value between
* 0.0 and 1.0.
*/
virtual float getProgress() = 0;
};
/**
* An object to write key/value pairs as they are emited from the reduce.
*/
class RecordWriter: public Closable {
public:
virtual void emit(const std::string& key,
const std::string& value) = 0;
};
/**
* A factory to create the necessary application objects.
*/
class Factory {
public:
virtual Mapper* createMapper(MapContext& context) const = 0;
virtual Reducer* createReducer(ReduceContext& context) const = 0;
/**
* Create a combiner, if this application has one.
* @return the new combiner or NULL, if one is not needed
*/
virtual Reducer* createCombiner(MapContext& context) const {
return NULL;
}
/**
* Create an application partitioner object.
* @return the new partitioner or NULL, if the default partitioner should be
* used.
*/
virtual Partitioner* createPartitioner(MapContext& context) const {
return NULL;
}
/**
* Create an application record reader.
* @return the new RecordReader or NULL, if the Java RecordReader should be
* used.
*/
virtual RecordReader* createRecordReader(MapContext& context) const {
return NULL;
}
/**
* Create an application record writer.
* @return the new RecordWriter or NULL, if the Java RecordWriter should be
* used.
*/
virtual RecordWriter* createRecordWriter(ReduceContext& context) const {
return NULL;
}
virtual ~Factory() {}
};
/**
* Run the assigned task in the framework.
* The user's main function should set the various functions using the
* set* functions above and then call this.
* @return true, if the task succeeded.
*/
bool runTask(const Factory& factory);
}
#endif
169 third_party/hadoop-0.20.0/c++/Linux-amd64-64/include/hadoop/SerialUtils.hh
@@ -0,0 +1,169 @@
/**
* 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.
*/
#ifndef HADOOP_SERIAL_UTILS_HH
#define HADOOP_SERIAL_UTILS_HH
#include <string>
namespace HadoopUtils {
/**
* A simple exception class that records a message for the user.
*/
class Error {
private:
std::string error;
public:
/**
* Create an error object with the given message.
*/
Error(const std::string& msg);
/**
* Construct an error object with the given message that was created on
* the given file, line, and functino.
*/
Error(const std::string& msg,
const std::string& file, int line, const std::string& function);
/**
* Get the error message.
*/
const std::string& getMessage() const;
};
/**
* Check to make sure that the condition is true, and throw an exception
* if it is not. The exception will contain the message and a description
* of the source location.
*/
#define HADOOP_ASSERT(CONDITION, MESSAGE) \
{ \
if (!(CONDITION)) { \
throw HadoopUtils::Error((MESSAGE), __FILE__, __LINE__, \
__PRETTY_FUNCTION__); \
} \
}
/**
* An interface for an input stream.
*/
class InStream {
public:
/**
* Reads len bytes from the stream into the buffer.
* @param buf the buffer to read into
* @param buflen the length of the buffer
* @throws Error if there are problems reading
*/
virtual void read(void *buf, size_t len) = 0;
virtual ~InStream() {}
};
/**
* An interface for an output stream.
*/
class OutStream {
public:
/**
* Write the given buffer to the stream.
* @param buf the data to write
* @param len the number of bytes to write
* @throws Error if there are problems writing
*/
virtual void write(const void *buf, size_t len) = 0;
/**
* Flush the data to the underlying store.
*/
virtual void flush() = 0;
virtual ~OutStream() {}
};
/**
* A class to read a file as a stream.
*/
class FileInStream : public InStream {
public:
FileInStream();
bool open(const std::string& name);
bool open(FILE* file);
void read(void *buf, size_t buflen);
bool skip(size_t nbytes);
bool close();
virtual ~FileInStream();
private:
/**
* The file to write to.
*/
FILE *mFile;
/**
* Does is this class responsible for closing the FILE*?
*/
bool isOwned;
};
/**
* A class to write a stream to a file.
*/
class FileOutStream: public OutStream {
public:
/**
* Create a stream that isn't bound to anything.
*/
FileOutStream();
/**
* Create the given file, potentially overwriting an existing file.
*/
bool open(const std::string& name, bool overwrite);
bool open(FILE* file);
void write(const void* buf, size_t len);
bool advance(size_t nbytes);
void flush();
bool close();
virtual ~FileOutStream();
private:
FILE *mFile;
bool isOwned;
};
/**
* A stream that reads from a string.
*/
class StringInStream: public InStream {
public:
StringInStream(const std::string& str);
virtual void read(void *buf, size_t buflen);
private:
const std::string& buffer;
std::string::const_iterator itr;
};
void serializeInt(int32_t t, OutStream& stream);
int32_t deserializeInt(InStream& stream);
void serializeLong(int64_t t, OutStream& stream);
int64_t deserializeLong(InStream& stream);
void serializeFloat(float t, OutStream& stream);
float deserializeFloat(InStream& stream);
void serializeString(const std::string& t, OutStream& stream);
void deserializeString(std::string& t, InStream& stream);
}
#endif
81 third_party/hadoop-0.20.0/c++/Linux-amd64-64/include/hadoop/StringUtils.hh
@@ -0,0 +1,81 @@
/**
* 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.
*/
#ifndef HADOOP_STRING_UTILS_HH
#define HADOOP_STRING_UTILS_HH
#include <stdint.h>
#include <string>
#include <vector>
namespace HadoopUtils {
/**
* Convert an integer to a string.
*/
std::string toString(int32_t x);
/**
* Convert a string to an integer.
* @throws Error if the string is not a valid integer
*/
int32_t toInt(const std::string& val);
/**
* Convert the string to a float.
* @throws Error if the string is not a valid float
*/
float toFloat(const std::string& val);
/**
* Convert the string to a boolean.
* @throws Error if the string is not a valid boolean value
*/
bool toBool(const std::string& val);
/**
* Get the current time in the number of milliseconds since 1970.
*/
uint64_t getCurrentMillis();
/**
* Split a string into "words". Multiple deliminators are treated as a single
* word break, so no zero-length words are returned.
* @param str the string to split
* @param separator a list of characters that divide words
*/
std::vector<std::string> splitString(const std::string& str,
const char* separator);
/**
* Quote a string to avoid "\", non-printable characters, and the
* deliminators.
* @param str the string to quote
* @param deliminators the set of characters to always quote
*/
std::string quoteString(const std::string& str,
const char* deliminators);
/**
* Unquote the given string to return the original string.
* @param str the string to unquote
*/
std::string unquoteString(const std::string& str);
}
#endif
96 third_party/hadoop-0.20.0/c++/Linux-amd64-64/include/hadoop/TemplateFactory.hh
@@ -0,0 +1,96 @@
/**
* 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.
*/
#ifndef HADOOP_PIPES_TEMPLATE_FACTORY_HH
#define HADOOP_PIPES_TEMPLATE_FACTORY_HH
namespace HadoopPipes {
template <class mapper, class reducer>
class TemplateFactory2: public Factory {
public:
Mapper* createMapper(MapContext& context) const {
return new mapper(context);
}
Reducer* createReducer(ReduceContext& context) const {
return new reducer(context);
}
};
template <class mapper, class reducer, class partitioner>
class TemplateFactory3: public TemplateFactory2<mapper,reducer> {
public:
Partitioner* createPartitioner(MapContext& context) const {
return new partitioner(context);
}
};
template <class mapper, class reducer>
class TemplateFactory3<mapper, reducer, void>
: public TemplateFactory2<mapper,reducer> {
};
template <class mapper, class reducer, class partitioner, class combiner>
class TemplateFactory4
: public TemplateFactory3<mapper,reducer,partitioner>{
public:
Reducer* createCombiner(MapContext& context) const {
return new combiner(context);
}
};
template <class mapper, class reducer, class partitioner>
class TemplateFactory4<mapper,reducer,partitioner,void>
: public TemplateFactory3<mapper,reducer,partitioner>{
};
template <class mapper, class reducer, class partitioner,
class combiner, class recordReader>
class TemplateFactory5
: public TemplateFactory4<mapper,reducer,partitioner,combiner>{
public:
RecordReader* createRecordReader(MapContext& context) const {
return new recordReader(context);
}
};
template <class mapper, class reducer, class partitioner,class combiner>
class TemplateFactory5<mapper,reducer,partitioner,combiner,void>
: public TemplateFactory4<mapper,reducer,partitioner,combiner>{
};
template <class mapper, class reducer, class partitioner=void,
class combiner=void, class recordReader=void,
class recordWriter=void>
class TemplateFactory
: public TemplateFactory5<mapper,reducer,partitioner,combiner,recordReader>{
public:
RecordWriter* createRecordWriter(ReduceContext& context) const {
return new recordWriter(context);
}
};
template <class mapper, class reducer, class partitioner,
class combiner, class recordReader>
class TemplateFactory<mapper, reducer, partitioner, combiner, recordReader,
void>
: public TemplateFactory5<mapper,reducer,partitioner,combiner,recordReader>{
};
}
#endif
BIN third_party/hadoop-0.20.0/c++/Linux-amd64-64/lib/libhadooppipes.a
Binary file not shown.
BIN third_party/hadoop-0.20.0/c++/Linux-amd64-64/lib/libhadooputils.a
Binary file not shown.
258 third_party/hadoop-0.20.0/c++/Linux-i386-32/include/hadoop/Pipes.hh
@@ -0,0 +1,258 @@
/**
* 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.
*/
#ifndef HADOOP_PIPES_HH
#define HADOOP_PIPES_HH
#ifdef SWIG
%module (directors="1") HadoopPipes
%include "std_string.i"
%feature("director") Mapper;
%feature("director") Reducer;
%feature("director") Partitioner;
%feature("director") RecordReader;
%feature("director") RecordWriter;
%feature("director") Factory;
#else
#include <string>
#endif
namespace HadoopPipes {
/**
* This interface defines the interface between application code and the
* foreign code interface to Hadoop Map/Reduce.
*/
/**
* A JobConf defines the properties for a job.
*/
class JobConf {
public:
virtual bool hasKey(const std::string& key) const = 0;
virtual const std::string& get(const std::string& key) const = 0;
virtual int getInt(const std::string& key) const = 0;
virtual float getFloat(const std::string& key) const = 0;
virtual bool getBoolean(const std::string&key) const = 0;
virtual ~JobConf() {}
};
/**
* Task context provides the information about the task and job.
*/
class TaskContext {
public:
/**
* Counter to keep track of a property and its value.
*/
class Counter {
private:
int id;
public:
Counter(int counterId) : id(counterId) {}
Counter(const Counter& counter) : id(counter.id) {}
int getId() const { return id; }
};
/**
* Get the JobConf for the current task.
*/
virtual const JobConf* getJobConf() = 0;
/**
* Get the current key.
* @return the current key
*/
virtual const std::string& getInputKey() = 0;
/**
* Get the current value.
* @return the current value
*/
virtual const std::string& getInputValue() = 0;
/**
* Generate an output record
*/
virtual void emit(const std::string& key, const std::string& value) = 0;
/**
* Mark your task as having made progress without changing the status
* message.
*/
virtual void progress() = 0;
/**
* Set the status message and call progress.
*/
virtual void setStatus(const std::string& status) = 0;
/**
* Register a counter with the given group and name.
*/
virtual Counter*
getCounter(const std::string& group, const std::string& name) = 0;
/**
* Increment the value of the counter with the given amount.
*/
virtual void incrementCounter(const Counter* counter, uint64_t amount) = 0;
virtual ~TaskContext() {}
};
class MapContext: public TaskContext {
public:
/**
* Access the InputSplit of the mapper.
*/
virtual const std::string& getInputSplit() = 0;
/**
* Get the name of the key class of the input to this task.
*/
virtual const std::string& getInputKeyClass() = 0;
/**
* Get the name of the value class of the input to this task.
*/
virtual const std::string& getInputValueClass() = 0;
};
class ReduceContext: public TaskContext {
public:
/**
* Advance to the next value.
*/
virtual bool nextValue() = 0;
};
class Closable {
public:
virtual void close() {}
virtual ~Closable() {}
};
/**
* The application's mapper class to do map.
*/
class Mapper: public Closable {
public:
virtual void map(MapContext& context) = 0;
};
/**
* The application's reducer class to do reduce.
*/
class Reducer: public Closable {
public:
virtual void reduce(ReduceContext& context) = 0;
};
/**
* User code to decide where each key should be sent.
*/
class Partitioner {
public:
virtual int partition(const std::string& key, int numOfReduces) = 0;
virtual ~Partitioner() {}
};
/**
* For applications that want to read the input directly for the map function
* they can define RecordReaders in C++.
*/
class RecordReader: public Closable {
public:
virtual bool next(std::string& key, std::string& value) = 0;
/**
* The progress of the record reader through the split as a value between
* 0.0 and 1.0.
*/
virtual float getProgress() = 0;
};
/**
* An object to write key/value pairs as they are emited from the reduce.
*/
class RecordWriter: public Closable {
public:
virtual void emit(const std::string& key,
const std::string& value) = 0;
};
/**
* A factory to create the necessary application objects.
*/
class Factory {
public:
virtual Mapper* createMapper(MapContext& context) const = 0;
virtual Reducer* createReducer(ReduceContext& context) const = 0;
/**
* Create a combiner, if this application has one.
* @return the new combiner or NULL, if one is not needed
*/
virtual Reducer* createCombiner(MapContext& context) const {
return NULL;
}
/**
* Create an application partitioner object.
* @return the new partitioner or NULL, if the default partitioner should be
* used.
*/
virtual Partitioner* createPartitioner(MapContext& context) const {
return NULL;
}
/**
* Create an application record reader.
* @return the new RecordReader or NULL, if the Java RecordReader should be
* used.
*/
virtual RecordReader* createRecordReader(MapContext& context) const {
return NULL;
}
/**
* Create an application record writer.
* @return the new RecordWriter or NULL, if the Java RecordWriter should be
* used.
*/
virtual RecordWriter* createRecordWriter(ReduceContext& context) const {
return NULL;
}
virtual ~Factory() {}
};
/**
* Run the assigned task in the framework.
* The user's main function should set the various functions using the
* set* functions above and then call this.
* @return true, if the task succeeded.
*/
bool runTask(const Factory& factory);
}
#endif
Oops, something went wrong.