Permalink
Browse files

Initial Import

  • Loading branch information...
0 parents commit 790a1aa146313fa58ce50f9ca3db801fcf467d0a @johnynek johnynek committed with caniszczyk Jan 10, 2012
Showing with 6,293 additions and 0 deletions.
  1. +9 −0 .gitignore
  2. +177 −0 LICENSE
  3. +13 −0 NOTICE
  4. +67 −0 README.md
  5. +8 −0 project/build.properties
  6. +25 −0 project/build/Project.scala
  7. +13 −0 project/plugins/Plugins.scala
  8. +206 −0 scripts/scald.rb
  9. +56 −0 scripts/scalding_gen.rb
  10. +99 −0 src/main/scala/com/twitter/scalding/Args.scala
  11. +348 −0 src/main/scala/com/twitter/scalding/DateRange.scala
  12. +128 −0 src/main/scala/com/twitter/scalding/FieldConversions.scala
  13. +1,112 −0 src/main/scala/com/twitter/scalding/GeneratedConversions.scala
  14. +448 −0 src/main/scala/com/twitter/scalding/GroupBuilder.scala
  15. +95 −0 src/main/scala/com/twitter/scalding/Job.scala
  16. +313 −0 src/main/scala/com/twitter/scalding/KryoHadoopSerialization.scala
  17. +56 −0 src/main/scala/com/twitter/scalding/MemoryTap.scala
  18. +76 −0 src/main/scala/com/twitter/scalding/Mode.scala
  19. +285 −0 src/main/scala/com/twitter/scalding/Operations.scala
  20. +312 −0 src/main/scala/com/twitter/scalding/RichPipe.scala
  21. +298 −0 src/main/scala/com/twitter/scalding/Source.scala
  22. +96 −0 src/main/scala/com/twitter/scalding/Tool.scala
  23. +89 −0 src/main/scala/com/twitter/scalding/TupleBase.scala
  24. +105 −0 src/main/scala/com/twitter/scalding/TupleConversions.scala
  25. +50 −0 src/main/scala/com/twitter/scalding/examples/MergeTest.scala
  26. +179 −0 src/main/scala/com/twitter/scalding/examples/PageRank.scala
  27. +10 −0 src/main/scala/com/twitter/scalding/examples/WordCountJob.scala
  28. +56 −0 src/test/scala/com/twitter/scalding/ArgTest.scala
  29. +382 −0 src/test/scala/com/twitter/scalding/CoreTest.scala
  30. +159 −0 src/test/scala/com/twitter/scalding/DateTest.scala
  31. +128 −0 src/test/scala/com/twitter/scalding/FieldImpsTest.scala
  32. +65 −0 src/test/scala/com/twitter/scalding/JobTest.scala
  33. +129 −0 src/test/scala/com/twitter/scalding/KryoTests.scala
  34. +38 −0 src/test/scala/com/twitter/scalding/PageRankTest.scala
  35. +20 −0 src/test/scala/com/twitter/scalding/WordCountTest.scala
  36. +223 −0 tutorial/CodeSnippets.md
  37. +75 −0 tutorial/Tutorial0.scala
  38. +53 −0 tutorial/Tutorial1.scala
  39. +64 −0 tutorial/Tutorial2.scala
  40. +70 −0 tutorial/Tutorial3.scala
  41. +69 −0 tutorial/Tutorial4.scala
  42. +87 −0 tutorial/Tutorial5.scala
  43. +2 −0 tutorial/data/hello.txt
@@ -0,0 +1,9 @@
+*.swp
+BUILD
+target/
+lib_managed/
+project/boot/
+project/build/target/
+project/plugins/target/
+project/plugins/lib_managed/
+project/plugins/src_managed/
177 LICENSE
@@ -0,0 +1,177 @@
+
+ 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
13 NOTICE
@@ -0,0 +1,13 @@
+scalding is a Scala API for Cascading.
+Copyright 2012 Twitter, Inc.
+
+Third Party Dependencies:
+
+Cascading 2.0
+Apache Public License 2.0
+http://www.cascading.org
+
+Hadoop 0.20.2
+Apache Public License 2.0
+http://hadoop.apache.org
+
@@ -0,0 +1,67 @@
+# Scalding
+Scalding is a library that has two components:
+
+* a scala DSL to make map-reduce computations look very similar to scala's collection API
+* a wrapper to Cascading to make simpler to define the usual use cases of jobs, tests and describing new data on HDFS.
+
+To run scala scalding jobs, a script, scald.rb is provided in scripts/. Run this script
+with no arguments to see usage tips. You will need to customize the default variables
+at the head of that script for your environment.
+
+You should follow the scalding project on twitter: <http://twitter.com/scalding>
+
+## Word Count
+Hadoop is a distributed system for counting words. Here is how it's done in scalding. You can find this in examples:
+
+ package com.twitter.scalding.examples
+
+ import com.twitter.scalding._
+
+ class WordCountJob(args : Args) extends Job(args) {
+ TextLine( args("input") ).read.
+ flatMap('line -> 'word) { line : String => line.split("\\s+") }.
+ groupBy('word) { _.size }.
+ write( Tsv( args("output") ) )
+ }
+
+##Tutorial
+See tutorial/ for examples of how to use the DSL. See tutorial/CodeSnippets.md for some
+example scalding snippets.
+
+## Building
+0. Install sbt 0.7.4
+1. sbt update (takes 2 minutes or more)
+2. sbt test
+3. sbt package-dist
+
+use "sbt assembly" if you need to make a fat jar with all dependencies (recommended to work with
+scald.rb in scripts).
+
+## Mailing list
+
+Currently we are using the cascading-user mailing list for discussions.
+<http://groups.google.com/group/cascading-user>
+
+Follow the scalding project on twitter for updates: <http://twitter.com/scalding>
+
+## Bugs
+In the remote possibility that there exist bugs in this code, please report them to:
+<https://github.com/twitter/scalding/issues>
+
+## Authors:
+* Avi Bryant <http://twitter.com/avibryant>
+* Oscar Boykin <http://twitter.com/posco>
+* Argyris Zymnis <http://twitter.com/argyris>
+
+Thanks for assistance and contributions:
+
+* Chris Wensel <http://twitter.com/cwensel>
+* Ning Liang <http://twitter.com/ningliang>
+* Dmitriy Ryaboy <http://twitter.com/squarecog>
+* Dong Wang <http://twitter.com/dongwang218>
+* Edwin Chen <http://twitter.com/edchedch>
+
+## License
+Copyright 2012 Twitter, Inc.
+
+Licensed under the Apache License, Version 2.0: http://www.apache.org/licenses/LICENSE-2.0
@@ -0,0 +1,8 @@
+#Project properties
+#Tue Dec 13 13:52:46 PST 2011
+project.organization=com.twitter
+project.name=scalding
+sbt.version=0.7.4
+project.version=0.2.0
+build.scala.versions=2.8.1
+project.initialize=false
@@ -0,0 +1,25 @@
+import sbt._
+import com.twitter.sbt._
+import reaktor.scct.ScctProject
+
+class Project(info: ProjectInfo) extends StandardProject(info)
+ with PackageDist
+ with IdeaProject
+ with assembly.AssemblyBuilder
+ with ScctProject {
+
+ override def distZipName = "%s.zip".format(name)
+
+ //Setup the cascading maven repo:
+ val conjars = "Concurrent Maven Repo" at "http://conjars.org/repo"
+ val c2core = "cascading" % "cascading-core" % "2.0.0-wip-165"
+ val c2local = "cascading" % "cascading-local" % "2.0.0-wip-165"
+ val c2hadoop = "cascading" % "cascading-hadoop" % "2.0.0-wip-165"
+
+ val hadoop = "org.apache.hadoop" % "hadoop-core" % "0.20.2"
+ val commons = "commons-lang" % "commons-lang" % "2.4"
+ val kryo = "de.javakaffee" % "kryo-serializers" % "0.9"
+
+ // Testing
+ val specs = "org.scala-tools.testing" % "specs_2.8.0" % "1.6.5" % "test"
+}
@@ -0,0 +1,13 @@
+import sbt._
+
+class Plugins(info: ProjectInfo) extends PluginDefinition(info) {
+ val twitterRepo = "com.twitter" at "http://maven.twttr.com"
+ val defaultProject = "com.twitter" % "standard-project" % "0.9.25"
+ val sbtIdeaRepo = "sbt-idea-repo" at "http://mpeltonen.github.com/maven/"
+ val sbtIdea = "com.github.mpeltonen" % "sbt-idea-plugin" % "0.3.0"
+ val scctRepo = "scct-repo" at "http://mtkopone.github.com/scct/maven-repo/"
+ lazy val scctPlugin = "reaktor" % "sbt-scct-for-2.8" % "0.1-SNAPSHOT"
+
+ val codaRepo = "Coda Hale's Repository" at "http://repo.codahale.com/"
+ val assemblySBT = "com.codahale" % "assembly-sbt" % "0.1"
+}
Oops, something went wrong.

0 comments on commit 790a1aa

Please sign in to comment.