embulk 0.6.5 → 0.6.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8621bf795aec3de19d66acb38d35a988f1a1a8c7
-  data.tar.gz: 765914d9e5386fd53451ec4a7e03a527a2b811b4
+  metadata.gz: 06d9d42d47c71ddd9c290abc3fd90eae09756157
+  data.tar.gz: 4a1104ff4fb9657b5a2305120d8ffe0f2992c9ff
 SHA512:
-  metadata.gz: 8f693d267fbdc5a24d22e2a1c9a09a668746c4216cb5de63091e608652998bf37deae8080877d91c35abe03c05565a9d19f5eff218ebad5cca21e0de30c988e2
-  data.tar.gz: 67279b67ab2dc0667a1b0122b32bb45f29de95d7818d364a36f37ad8845469969a9cdfec823bc83722084522c7459bcfef6a528ac6708864c2935bd99b1e3508
+  metadata.gz: 9df10a5c5d6a0c77b38352f96d5f1cedbd658c0ac5a41e1720a3c8baa9f65685c742a34d0e6569d6bbb3d2c2e43423b48e3cc8d167dd4f8982568ea92f29d4eb
+  data.tar.gz: 75887fa0b97bc9750cca1d4abdeb500d0f8e83fd0ede84f467e671c83754acf0e3abb1a82a18c106d9e1250587f5b286a1c598fadeb7249d0c4320df0279f47c

data/README.md

@@ -2,7 +2,7 @@
 
 Embulk is a plugin-based parallel bulk data loader that helps **data transfer** between various **storages**, **databases**, **NoSQL** and **cloud services**.
 
-You can release plugins to share your efforts of data cleaning, error handling, transaction control, and retrying. Packaging effrots into plugins **brings OSS-style development to the data scripts** which **was tend to be one-time adhoc scripts**.
+You can release plugins to share your efforts of data cleaning, error handling, transaction control, and retrying. Packaging efforts into plugins **brings OSS-style development to the data scripts** which **was tend to be one-time adhoc scripts**.
 
 [Embulk, an open-source plugin-based parallel bulk data loader](http://www.slideshare.net/frsyuki/embuk-making-data-integration-works-relaxed) at Slideshare
 

data/build.gradle

@@ -11,7 +11,7 @@ def release_projects = [project(":embulk-core"), project(":embulk-standards")]
 
 allprojects {
     group = 'org.embulk'
-    version = '0.6.5'
+    version = '0.6.6'
 
     ext {
         jrubyVersion = '1.7.19'

data/embulk-core/src/main/java/org/embulk/exec/GuessExecutor.java

@@ -150,6 +150,9 @@ public class GuessExecutor
                 input.transaction(guessInputConfig, new InputPlugin.Control() {
                     public List<CommitReport> run(TaskSource inputTaskSource, Schema schema, int taskCount)
                     {
+                        if (taskCount == 0) {
+                            throw new NoSampleException("No input files to guess");
+                        }
                         // TODO repeat runwith taskIndex++ if NoSampleException happens
                         input.run(inputTaskSource, null, 0, new PageOutput() {
                             @Override

data/embulk-core/src/main/java/org/embulk/exec/SamplingParserPlugin.java

@@ -57,6 +57,10 @@ public class SamplingParserPlugin
             runner.transaction(samplingInputConfig, new InputPlugin.Control() {
                 public List<CommitReport> run(TaskSource taskSource, Schema schema, int taskCount)
                 {
+                    if (taskCount == 0) {
+                        throw new NoSampleException("No input files to read sample data");
+                    }
+                    // TODO repeat runwith taskIndex++ if NoSampleException happens
                     runner.run(taskSource, schema, 0, new PageOutput() {
                         @Override
                         public void add(Page page)

data/embulk-core/src/main/java/org/embulk/spi/util/InputStreamFileInput.java

@@ -103,7 +103,14 @@ public class InputStreamFileInput
     public void close()
     {
         try {
-            provider.close();
+            try {
+                if (current != null) {
+                    current.close();
+                    current = null;
+                }
+            } finally {
+                provider.close();
+            }
         } catch (IOException ex) {
             throw new RuntimeException(ex);
         }

data/embulk-docs/src/built-in.rst

@@ -48,7 +48,7 @@ A configuration file consists of following sections:
 
 * **out:** Output plugin options. An output plugin is either record-based (`Oracle <https://github.com/embulk/embulk-output-jdbc>`_, `Elasticsearch <https://github.com/muga/embulk-output-elasticsearch>`_, etc) or file-based (`Google Cloud Storage <https://github.com/hakobera/embulk-output-gcs>`_, `Command <https://github.com/embulk/embulk-output-command>`_, etc)
 
-  * **formatter:** If the output is file-based, fromatter plugin formats a file format (such as built-in csv, `JSON <https://github.com/takei-yuya/embulk-formatter-jsonl>`_)
+  * **formatter:** If the output is file-based, formatter plugin formats a file format (such as built-in csv, `JSON <https://github.com/takei-yuya/embulk-formatter-jsonl>`_)
 
   * **encoder:** If the output is file-based, encoder plugin encodes compression or encryption (such as built-in gzip)
 

data/embulk-docs/src/customization.rst

@@ -75,7 +75,7 @@ Step 3: Confirm it works
 
 The next step is to actually use the plugin.
 
-Let's supporse you have a configuration file named ``your-config.yml``. You can use the plugin using embulk with ``-L`` argument:
+Let's suppose you have a configuration file named ``your-config.yml``. You can use the plugin using embulk with ``-L`` argument:
 
 ::
 

data/embulk-docs/src/recipe/scheduled-csv-load-to-elasticsearch-kibana4.rst

@@ -11,7 +11,7 @@ This article shows how to:
 * Visualize the data with Kibana interactively.
 * Schedule the data loading every hour using cron.
 
-This guide assumes you are using Ubuntu 12.0 Precise or Mac OS X.
+This guide assumes you are using Ubuntu 12.04 Precise or Mac OS X.
 
 Setup Elasticsearch and Kibana 4
 ------------------

data/embulk-docs/src/release.rst

@@ -4,6 +4,7 @@ Release Notes
 .. toctree::
     :maxdepth: 1
 
+    release/release-0.6.6
     release/release-0.6.5
     release/release-0.6.4
     release/release-0.6.3

data/embulk-docs/src/release/release-0.6.6.rst

@@ -0,0 +1,17 @@
+Release 0.6.6
+==================================
+
+General Changes
+------------------
+
+* Fixed a problem that timestamp format guess code can't guess format if the string includes day of 30 and 31.
+* ``guess`` and ``preview`` throw NoSampleException with appropriate error message if there are no input tasks.
+
+Plugin API
+------------------
+
+* ``spi.util.InputStreamFileInput#close`` closes currently opened InputStream.
+
+Release Date
+------------------
+2015-05-04

data/lib/embulk/data/new/java/build.gradle.erb

@@ -36,7 +36,7 @@ task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
 
 task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
     jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
-    script "${project.name}-${project.version}.gem"
+    script "pkg/${project.name}-${project.version}.gem"
 }
 
 task "package"(dependsOn: ["gemspec", "classpath"]) << {

data/lib/embulk/guess/time_format_guess.rb

@@ -4,8 +4,8 @@ module Embulk::Guess
       YEAR = /[1-4][0-9]{3}/
       MONTH         = /10|11|12|[0 ]?[0-9]/
       MONTH_NODELIM = /10|11|12|[0][0-9]/
-      DAY         = /[1-2][0-9]|[0 ]?[1-9]|30|31/
-      DAY_NODELIM = /[1-2][0-9]|[0][1-9]|30|31/
+      DAY         = /31|30|[1-2][0-9]|[0 ]?[1-9]/
+      DAY_NODELIM = /31|30|[1-2][0-9]|[0][1-9]/
       HOUR         = /20|21|22|23|24|1[0-9]|[0 ]?[0-9]/
       HOUR_NODELIM = /20|21|22|23|24|1[0-9]|[0][0-9]/
       MINUTE         = SECOND         = /60|[1-5][0-9]|[0 ]?[0-9]/

data/lib/embulk/version.rb

@@ -1,3 +1,3 @@
 module Embulk
-  VERSION = '0.6.5'
+  VERSION = '0.6.6'
 end

data/test/guess/test_time_format_guess.rb

@@ -47,6 +47,10 @@ class TimeFormatGuessTest < ::Test::Unit::TestCase
     assert_guess "%d/%m/%Y", "21/01/2014"
   end
 
+  def test_format_borders
+    assert_guess "%Y-%m-%d %H:%M:%S.%N",    "2014-12-31 23:59:59.999999999"
+  end
+
   def test_format_iso8601
     assert_guess "%Y-%m-%d", "1981-04-05"
     assert_guess "%Y-%m-%dT%H", "2007-04-06T13"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: embulk
 version: !ruby/object:Gem::Version
-  version: 0.6.5
+  version: 0.6.6
 platform: ruby
 authors:
 - Sadayuki Furuhashi
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2015-04-22 00:00:00.000000000 Z
+date: 2015-05-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -295,6 +295,7 @@ files:
 - embulk-docs/src/release/release-0.6.3.rst
 - embulk-docs/src/release/release-0.6.4.rst
 - embulk-docs/src/release/release-0.6.5.rst
+- embulk-docs/src/release/release-0.6.6.rst
 - embulk-standards/build.gradle
 - embulk-standards/src/main/java/org/embulk/standards/CsvFormatterPlugin.java
 - embulk-standards/src/main/java/org/embulk/standards/CsvParserPlugin.java
@@ -400,8 +401,8 @@ files:
 - classpath/bval-jsr303-0.5.jar
 - classpath/commons-beanutils-core-1.8.3.jar
 - classpath/commons-lang3-3.1.jar
-- classpath/embulk-core-0.6.5.jar
-- classpath/embulk-standards-0.6.5.jar
+- classpath/embulk-core-0.6.6.jar
+- classpath/embulk-standards-0.6.6.jar
 - classpath/guava-18.0.jar
 - classpath/guice-3.0.jar
 - classpath/guice-multibindings-3.0.jar