Merge pull request #497 from tdas/docs-update

Updated Spark Streaming Programming Guide

Here is the updated version of the Spark Streaming Programming Guide. This is still a work in progress, but the major changes are in place. So feedback is most welcome.

In general, I have tried to make the guide to easier to understand even if the reader does not know much about Spark. The updated website is hosted here -

http://www.eecs.berkeley.edu/~tdas/spark_docs/streaming-programming-guide.html

The major changes are:
- Overview illustrates the usecases of Spark Streaming - various input sources and various output sources
- An example right after overview to quickly give an idea of what Spark Streaming program looks like
- Made Java API and examples a first class citizen like Scala by using tabs to show both Scala and Java examples (similar to AMPCamp tutorial's code tabs)
- Highlighted the DStream operations updateStateByKey and transform because of their powerful nature
- Updated driver node failure recovery text to highlight automatic recovery in Spark standalone mode
- Added information about linking and using the external input sources like Kafka and Flume
- In general, reorganized the sections to better show the Basic section and the more advanced sections like Tuning and Recovery.

Todos:
- Links to the docs of external Kafka, Flume, etc
- Illustrate window operation with figure as well as example.

Author: Tathagata Das <tathagata.das1565@gmail.com>

== Merge branch commits ==

commit 18ff10556570b39d672beeb0a32075215cfcc944
Author: Tathagata Das <tathagata.das1565@gmail.com>
Date:   Tue Jan 28 21:49:30 2014 -0800

    Fixed a lot of broken links.

commit 34a5a6008dac2e107624c7ff0db0824ee5bae45f
Author: Tathagata Das <tathagata.das1565@gmail.com>
Date:   Tue Jan 28 18:02:28 2014 -0800

    Updated github url to use SPARK_GITHUB_URL variable.

commit f338a60ae8069e0a382d2cb170227e5757cc0b7a
Author: Tathagata Das <tathagata.das1565@gmail.com>
Date:   Mon Jan 27 22:42:42 2014 -0800

    More updates based on Patrick and Harvey's comments.

commit 89a81ff25726bf6d26163e0dd938290a79582c0f
Author: Tathagata Das <tathagata.das1565@gmail.com>
Date:   Mon Jan 27 13:08:34 2014 -0800

    Updated docs based on Patricks PR comments.

commit d5b6196b532b5746e019b959a79ea0cc013a8fc3
Author: Tathagata Das <tathagata.das1565@gmail.com>
Date:   Sun Jan 26 20:15:58 2014 -0800

    Added spark.streaming.unpersist config and info on StreamingListener interface.

commit e3dcb46ab83d7071f611d9b5008ba6bc16c9f951
Author: Tathagata Das <tathagata.das1565@gmail.com>
Date:   Sun Jan 26 18:41:12 2014 -0800

    Fixed docs on StreamingContext.getOrCreate.

commit 6c29524639463f11eec721e4d17a9d7159f2944b
Author: Tathagata Das <tathagata.das1565@gmail.com>
Date:   Thu Jan 23 18:49:39 2014 -0800

    Added example and figure for window operations, and links to Kafka and Flume API docs.

commit f06b964a51bb3b21cde2ff8bdea7d9785f6ce3a9
Author: Tathagata Das <tathagata.das1565@gmail.com>
Date:   Wed Jan 22 22:49:12 2014 -0800

    Fixed missing endhighlight tag in the MLlib guide.

commit 036a7d46187ea3f2a0fb8349ef78f10d6c0b43a9
Merge: eab351d a1cd185
Author: Tathagata Das <tathagata.das1565@gmail.com>
Date:   Wed Jan 22 22:17:42 2014 -0800

    Merge remote-tracking branch 'apache/master' into docs-update

commit eab351d05c0baef1d4b549e1581310087158d78d
Author: Tathagata Das <tathagata.das1565@gmail.com>
Date:   Wed Jan 22 22:17:15 2014 -0800

    Update Spark Streaming Programming Guide.

1 files changed, 106 insertions, 0 deletions

diff --git a/docs/js/main.js b/docs/js/main.js
index 8b13789179..102699789a 100755
--- a/docs/js/main.js
+++ b/docs/js/main.js
@@ -1 +1,107 @@
 
+// From docs.scala-lang.org
+function styleCode() {
+  if (typeof disableStyleCode != "undefined") {
+    return;
+  }
+  $(".codetabs pre code").parent().each(function() {
+    if (!$(this).hasClass("prettyprint")) {
+      var lang = $(this).parent().data("lang");
+      if (lang == "python") {
+        lang = "py"
+      }
+      if (lang == "bash") {
+        lang = "bsh"
+      }
+      $(this).addClass("prettyprint lang-"+lang+" linenums");
+    }
+  });
+  console.log("runningPrettyPrint()")
+  prettyPrint();
+}
+
+
+function codeTabs() {
+  var counter = 0;
+  var langImages = {
+    "scala": "img/scala-sm.png",
+    "python": "img/python-sm.png",
+    "java": "img/java-sm.png"
+  };
+  $("div.codetabs").each(function() {
+    $(this).addClass("tab-content");
+
+    // Insert the tab bar
+    var tabBar = $('<ul class="nav nav-tabs" data-tabs="tabs"></ul>');
+    $(this).before(tabBar);
+
+    // Add each code sample to the tab bar:
+    var codeSamples = $(this).children("div");
+    codeSamples.each(function() {
+      $(this).addClass("tab-pane");
+      var lang = $(this).data("lang");
+      var image = $(this).data("image");
+      var notabs = $(this).data("notabs");
+      var capitalizedLang = lang.substr(0, 1).toUpperCase() + lang.substr(1);
+      var id = "tab_" + lang + "_" + counter;
+      $(this).attr("id", id);
+      if (image != null && langImages[lang]) {
+        var buttonLabel = "<img src='" +langImages[lang] + "' alt='" + capitalizedLang + "' />";
+      } else if (notabs == null) {
+        var buttonLabel = "<b>" + capitalizedLang + "</b>";
+      } else {
+        var buttonLabel = ""
+      }
+      tabBar.append(
+        '<li><a class="tab_' + lang + '" href="#' + id + '">' + buttonLabel + '</a></li>'
+      );
+    });
+
+    codeSamples.first().addClass("active");
+    tabBar.children("li").first().addClass("active");
+    counter++;
+  });
+  $("ul.nav-tabs a").click(function (e) {
+    // Toggling a tab should switch all tabs corresponding to the same language
+    // while retaining the scroll position
+    e.preventDefault();
+    var scrollOffset = $(this).offset().top - $(document).scrollTop();
+    $("." + $(this).attr('class')).tab('show');
+    $(document).scrollTop($(this).offset().top - scrollOffset);
+  });
+}
+
+function makeCollapsable(elt, accordionClass, accordionBodyId, title) {
+  $(elt).addClass("accordion-inner");
+  $(elt).wrap('<div class="accordion ' + accordionClass + '"></div>')
+  $(elt).wrap('<div class="accordion-group"></div>')
+  $(elt).wrap('<div id="' + accordionBodyId + '" class="accordion-body collapse"></div>')
+  $(elt).parent().before(
+    '<div class="accordion-heading">' +
+      '<a class="accordion-toggle" data-toggle="collapse" href="#' + accordionBodyId + '">' +
+             title +
+      '</a>' +
+    '</div>'
+  );
+}
+
+function viewSolution() {
+  var counter = 0
+  $("div.solution").each(function() {
+    var id = "solution_" + counter
+    makeCollapsable(this, "", id,
+      '<i class="icon-ok-sign" style="text-decoration: none; color: #0088cc">' +
+      '</i>' + "View Solution");
+    counter++;
+  });
+}
+
+
+$(document).ready(function() {
+  codeTabs();
+  viewSolution();
+  $('#chapter-toc').toc({exclude: '', context: '.container'});
+  $('#chapter-toc').prepend('<p class="chapter-toc-header">In This Chapter</p>');
+  makeCollapsable($('#global-toc'), "", "global-toc", "Show Table of Contents");
+  //styleCode();
+});