embulk-input-azure_blob_storage 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 5cba152c50dbcb32fdafe2a64b65f2c0a9e82558
+  data.tar.gz: 634d95bfb9102801640a57fd06ee4466d779439c
+SHA512:
+  metadata.gz: 735c5cfe513d77d0d2f0b69b9d86f898742d2b1907968410ebecb56b9e58eda7e69fa4a03b747049006ba5e527c16fb482473e4b64731c6ae5c496760fa120a9
+  data.tar.gz: b8488a1dba1362a38f2b18b833d74312c1c760878b090bfea2824a836912a3775000743689f38fcc41efc45fc799dabbc408e94d3c0819ba7293433ef6aa741e

data/.gitignore

@@ -0,0 +1,14 @@
+target/
+build/
+pkg/
+*.iml
+*~
+._*
+.idea
+tmp/
+vendor/
+/classpath/
+/.bundle
+.yardoc
+/embulk-*.jar
+/.gradle

data/README.md

@@ -0,0 +1,62 @@
+# Azure blob Storage file input plugin for Embulk
+
+[Embulk](http://www.embulk.org/) file input plugin read files stored on [Microsoft Azure](https://azure.microsoft.com/) [blob Storage](https://azure.microsoft.com/en-us/documentation/articles/storage-introduction/#blob-storage)
+
+## Overview
+
+* **Plugin type**: file input
+* **Resume supported**: no
+* **Cleanup supported**: yes
+
+## Configuration
+
+First, create Azure [Storage Account](https://azure.microsoft.com/en-us/documentation/articles/storage-create-storage-account/).
+
+- **account_name**: storage account name (string, required)
+- **account_key**: primary access key (string, required)
+- **container**: container name data stored (string, required)
+- **path_prefix**: prefix of target keys (string, required) (string, required)
+
+## Example
+
+```yaml
+in:
+  type: azure_blob_storage
+  account_name: myaccount
+  account_key: myaccount_key
+  container: my-container
+  path_prefix: logs/csv-
+```
+
+Example for "sample_01.csv.gz" , generated by [embulk example](https://github.com/embulk/embulk#trying-examples)
+
+```yaml
+in:
+  type: azure_blob_storage
+  account_name: myaccount
+  account_key: myaccount_key
+  container: my-container
+  path_prefix: logs/csv-
+  decoders:
+  - {type: gzip}
+  parser:
+    charset: UTF-8
+    newline: CRLF
+    type: csv
+    delimiter: ','
+    quote: '"'
+    header_line: true
+    columns:
+    - {name: id, type: long}
+    - {name: account, type: long}
+    - {name: time, type: timestamp, format: '%Y-%m-%d %H:%M:%S'}
+    - {name: purchase, type: timestamp, format: '%Y%m%d'}
+    - {name: comment, type: string}
+out: {type: stdout}
+```
+
+## Build
+
+```
+$ ./gradlew gem  # -t to watch change of files and rebuild continuously
+```

data/build.gradle

@@ -0,0 +1,74 @@
+plugins {
+    id "com.jfrog.bintray" version "1.1"
+    id "com.github.jruby-gradle.base" version "0.1.5"
+    id "java"
+}
+import com.github.jrubygradle.JRubyExec
+repositories {
+    mavenCentral()
+    jcenter()
+}
+configurations {
+    provided
+}
+
+version = "0.1.0"
+
+dependencies {
+    compile  "org.embulk:embulk-core:0.7.5"
+    provided "org.embulk:embulk-core:0.7.5"
+
+    compile "com.microsoft.azure:azure-storage:4.0.0"
+
+    testCompile "junit:junit:4.+"
+}
+
+task classpath(type: Copy, dependsOn: ["jar"]) {
+    doFirst { file("classpath").deleteDir() }
+    from (configurations.runtime - configurations.provided + files(jar.archivePath))
+    into "classpath"
+}
+clean { delete "classpath" }
+
+task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
+    jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
+    script "${project.name}.gemspec"
+    doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
+}
+
+task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
+    jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
+    script "pkg/${project.name}-${project.version}.gem"
+}
+
+task "package"(dependsOn: ["gemspec", "classpath"]) << {
+    println "> Build succeeded."
+    println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
+}
+
+task gemspec {
+    ext.gemspecFile = file("${project.name}.gemspec")
+    inputs.file "build.gradle"
+    outputs.file gemspecFile
+    doLast { gemspecFile.write($/
+Gem::Specification.new do |spec|
+  spec.name          = "${project.name}"
+  spec.version       = "${project.version}"
+  spec.authors       = ["Satoshi Akama"]
+  spec.summary       = %[Microsoft Azure blob Storage file input plugin for Embulk]
+  spec.description   = %[Reads files stored on Microsoft Azure blob Storage.]
+  spec.email         = ["satoshiakama@gmail.com"]
+  spec.licenses      = ["Apache-2.0"]
+  spec.homepage      = "https://github.com/sakama/embulk-input-azure_blob_storage"
+
+  spec.files         = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
+  spec.test_files    = spec.files.grep(%r"^(test|spec)/")
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency 'bundler', ['~> 1.0']
+  spec.add_development_dependency 'rake', ['>= 10.0']
+end
+/$)
+    }
+}
+clean { delete "${project.name}.gemspec" }

data/embulk-input-azure_blob_storage.gemspec

@@ -0,0 +1,18 @@
+
+Gem::Specification.new do |spec|
+  spec.name          = "embulk-input-azure_blob_storage"
+  spec.version       = "0.1.0"
+  spec.authors       = ["Satoshi Akama"]
+  spec.summary       = %[Microsoft Azure blob Storage file input plugin for Embulk]
+  spec.description   = %[Reads files stored on Microsoft Azure blob Storage.]
+  spec.email         = ["satoshiakama@gmail.com"]
+  spec.licenses      = ["Apache-2.0"]
+  spec.homepage      = "https://github.com/sakama/embulk-input-azure_blob_storage"
+
+  spec.files         = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
+  spec.test_files    = spec.files.grep(%r"^(test|spec)/")
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency 'bundler', ['~> 1.0']
+  spec.add_development_dependency 'rake', ['>= 10.0']
+end

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Tue Aug 11 00:26:20 PDT 2015
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-2.6-bin.zip

data/gradlew

@@ -0,0 +1,164 @@
+#!/usr/bin/env bash
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+APP_NAME="Gradle"
+APP_BASE_NAME=`basename "$0"`
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn ( ) {
+    echo "$*"
+}
+
+die ( ) {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+esac
+
+# For Cygwin, ensure paths are in UNIX format before anything is touched.
+if $cygwin ; then
+    [ -n "$JAVA_HOME" ] && JAVA_HOME=`cygpath --unix "$JAVA_HOME"`
+fi
+
+# Attempt to set APP_HOME
+# Resolve links: $0 may be a link
+PRG="$0"
+# Need this for relative symlinks.
+while [ -h "$PRG" ] ; do
+    ls=`ls -ld "$PRG"`
+    link=`expr "$ls" : '.*-> \(.*\)$'`
+    if expr "$link" : '/.*' > /dev/null; then
+        PRG="$link"
+    else
+        PRG=`dirname "$PRG"`"/$link"
+    fi
+done
+SAVED="`pwd`"
+cd "`dirname \"$PRG\"`/" >&-
+APP_HOME="`pwd -P`"
+cd "$SAVED" >&-
+
+CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
+
+# Determine the Java command to use to start the JVM.
+if [ -n "$JAVA_HOME" ] ; then
+    if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
+        # IBM's JDK on AIX uses strange locations for the executables
+        JAVACMD="$JAVA_HOME/jre/sh/java"
+    else
+        JAVACMD="$JAVA_HOME/bin/java"
+    fi
+    if [ ! -x "$JAVACMD" ] ; then
+        die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+    fi
+else
+    JAVACMD="java"
+    which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+fi
+
+# Increase the maximum file descriptors if we can.
+if [ "$cygwin" = "false" -a "$darwin" = "false" ] ; then
+    MAX_FD_LIMIT=`ulimit -H -n`
+    if [ $? -eq 0 ] ; then
+        if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
+            MAX_FD="$MAX_FD_LIMIT"
+        fi
+        ulimit -n $MAX_FD
+        if [ $? -ne 0 ] ; then
+            warn "Could not set maximum file descriptor limit: $MAX_FD"
+        fi
+    else
+        warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
+    fi
+fi
+
+# For Darwin, add options to specify how the application appears in the dock
+if $darwin; then
+    GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
+fi
+
+# For Cygwin, switch paths to Windows format before running java
+if $cygwin ; then
+    APP_HOME=`cygpath --path --mixed "$APP_HOME"`
+    CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
+
+    # We build the pattern for arguments to be converted via cygpath
+    ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
+    SEP=""
+    for dir in $ROOTDIRSRAW ; do
+        ROOTDIRS="$ROOTDIRS$SEP$dir"
+        SEP="|"
+    done
+    OURCYGPATTERN="(^($ROOTDIRS))"
+    # Add a user-defined pattern to the cygpath arguments
+    if [ "$GRADLE_CYGPATTERN" != "" ] ; then
+        OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
+    fi
+    # Now convert the arguments - kludge to limit ourselves to /bin/sh
+    i=0
+    for arg in "$@" ; do
+        CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
+        CHECK2=`echo "$arg"|egrep -c "^-"`                                 ### Determine if an option
+
+        if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then                    ### Added a condition
+            eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
+        else
+            eval `echo args$i`="\"$arg\""
+        fi
+        i=$((i+1))
+    done
+    case $i in
+        (0) set -- ;;
+        (1) set -- "$args0" ;;
+        (2) set -- "$args0" "$args1" ;;
+        (3) set -- "$args0" "$args1" "$args2" ;;
+        (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
+        (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
+        (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
+        (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
+        (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
+        (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
+    esac
+fi
+
+# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
+function splitJvmOpts() {
+    JVM_OPTS=("$@")
+}
+eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
+JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
+
+exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"

data/gradlew.bat

@@ -0,0 +1,90 @@
+@if "%DEBUG%" == "" @echo off
+@rem ##########################################################################
+@rem
+@rem  Gradle startup script for Windows
+@rem
+@rem ##########################################################################
+
+@rem Set local scope for the variables with windows NT shell
+if "%OS%"=="Windows_NT" setlocal
+
+@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+set DEFAULT_JVM_OPTS=
+
+set DIRNAME=%~dp0
+if "%DIRNAME%" == "" set DIRNAME=.
+set APP_BASE_NAME=%~n0
+set APP_HOME=%DIRNAME%
+
+@rem Find java.exe
+if defined JAVA_HOME goto findJavaFromJavaHome
+
+set JAVA_EXE=java.exe
+%JAVA_EXE% -version >NUL 2>&1
+if "%ERRORLEVEL%" == "0" goto init
+
+echo.
+echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:findJavaFromJavaHome
+set JAVA_HOME=%JAVA_HOME:"=%
+set JAVA_EXE=%JAVA_HOME%/bin/java.exe
+
+if exist "%JAVA_EXE%" goto init
+
+echo.
+echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:init
+@rem Get command-line arguments, handling Windowz variants
+
+if not "%OS%" == "Windows_NT" goto win9xME_args
+if "%@eval[2+2]" == "4" goto 4NT_args
+
+:win9xME_args
+@rem Slurp the command line arguments.
+set CMD_LINE_ARGS=
+set _SKIP=2
+
+:win9xME_args_slurp
+if "x%~1" == "x" goto execute
+
+set CMD_LINE_ARGS=%*
+goto execute
+
+:4NT_args
+@rem Get arguments from the 4NT Shell from JP Software
+set CMD_LINE_ARGS=%$
+
+:execute
+@rem Setup the command line
+
+set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
+
+@rem Execute Gradle
+"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
+
+:end
+@rem End local scope for the variables with windows NT shell
+if "%ERRORLEVEL%"=="0" goto mainEnd
+
+:fail
+rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
+rem the _cmd.exe /c_ return code!
+if  not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
+exit /b 1
+
+:mainEnd
+if "%OS%"=="Windows_NT" endlocal
+
+:omega

data/lib/embulk/input/azure_blob_storage.rb

@@ -0,0 +1,3 @@
+Embulk::JavaPlugin.register_input(
+  "azure_blob_storage", "org.embulk.input.azure_blob_storage.AzureBlobStorageFileInputPlugin",
+  File.expand_path('../../../../classpath', __FILE__))

data/src/main/java/org/embulk/input/azure_blob_storage/AzureBlobStorageFileInputPlugin.java

@@ -0,0 +1,220 @@
+package org.embulk.input.azure_blob_storage;
+
+import java.util.List;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.io.InputStream;
+import java.io.IOException;
+import java.security.InvalidKeyException;
+import java.net.URISyntaxException;
+import com.google.common.base.Optional;
+import com.google.common.collect.ImmutableList;
+import com.google.common.base.Throwables;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigException;
+import org.embulk.config.ConfigInject;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.Task;
+import org.embulk.config.TaskSource;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.ConfigDiff;
+import org.embulk.config.TaskReport;
+import org.embulk.spi.Exec;
+import org.embulk.spi.FileInputPlugin;
+import org.embulk.spi.BufferAllocator;
+import org.embulk.spi.TransactionalFileInput;
+import org.embulk.spi.util.InputStreamFileInput;
+import com.microsoft.azure.storage.*;
+import com.microsoft.azure.storage.blob.*;
+import org.slf4j.Logger;
+
+public class AzureBlobStorageFileInputPlugin
+        implements FileInputPlugin
+{
+    public interface PluginTask
+            extends Task
+    {
+        @Config("account_name")
+        String getAccountName();
+
+        @Config("account_key")
+        String getAccountKey();
+
+        @Config("container")
+        String getContainer();
+
+        @Config("path_prefix")
+        String getPathPrefix();
+
+        @Config("last_path")
+        @ConfigDefault("null")
+        Optional<String> getLastPath();
+
+        @Config("max_results")
+        @ConfigDefault("5000")
+        int getMaxResults();
+
+        List<String> getFiles();
+
+        void setFiles(List<String> files);
+
+        @ConfigInject
+        BufferAllocator getBufferAllocator();
+    }
+
+    private static final Logger log = Exec.getLogger(AzureBlobStorageFileInputPlugin.class);
+
+    @Override
+    public ConfigDiff transaction(ConfigSource config, FileInputPlugin.Control control)
+    {
+        final PluginTask task = config.loadConfig(PluginTask.class);
+
+        CloudBlobClient blobClient = newAzureClient(task.getAccountName(), task.getAccountKey());
+        task.setFiles(listFiles(blobClient, task));
+
+        return resume(task.dump(), task.getFiles().size(), control);
+    }
+
+    @Override
+    public ConfigDiff resume(TaskSource taskSource, int taskCount, FileInputPlugin.Control control)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+
+        control.run(taskSource, taskCount);
+
+        ConfigDiff configDiff = Exec.newConfigDiff();
+
+        List<String> files = new ArrayList<> (task.getFiles());
+        if (files.isEmpty()) {
+            if (task.getLastPath().isPresent()) {
+                configDiff.set("last_path", task.getLastPath().get());
+            }
+        } else {
+            Collections.sort(files);
+            configDiff.set("last_path", files.get(files.size() - 1));
+        }
+        return configDiff;
+    }
+
+    @Override
+    public void cleanup(TaskSource taskSource, int taskCount, List<TaskReport> successTaskReports)
+    {
+    }
+
+    private static CloudBlobClient newAzureClient(String accountName, String accountKey)
+    {
+        String connectionString = "DefaultEndpointsProtocol=http;" +
+                "AccountName=" + accountName + ";" +
+                "AccountKey=" + accountKey;
+
+        CloudStorageAccount account;
+        try {
+            account = CloudStorageAccount.parse(connectionString);
+        } catch (InvalidKeyException | URISyntaxException ex) {
+            throw new ConfigException(ex);
+        }
+        return account.createCloudBlobClient();
+    }
+
+    private List<String> listFiles(CloudBlobClient client, PluginTask task)
+    {
+        if (task.getPathPrefix().equals("/")) {
+            log.info("Listing files with prefix \"/\". This doesn't mean all files in a bucket. If you intend to read all files, use \"path_prefix: ''\" (empty string) instead.");
+        }
+
+        return listFilesWithPrefix(client, task.getContainer(), task.getPathPrefix(), task.getLastPath(), task.getMaxResults());
+    }
+
+    private static List<String> listFilesWithPrefix(CloudBlobClient client, String containerName,
+                                             String prefix, Optional<String> lastPath, int maxResults)
+    {
+        ImmutableList.Builder<String> builder = ImmutableList.builder();
+        // It seems I can't cast lastKey<String> to token<ResultContinuation> by Azure SDK for Java
+        String lastKey = lastPath.orNull();
+        ResultContinuation token = null;
+
+        try {
+            CloudBlobContainer container = client.getContainerReference(containerName);
+            ResultSegment<ListBlobItem> blobs;
+            do {
+                blobs = container.listBlobsSegmented(prefix, true, null, maxResults, token, null, null);
+                log.debug(String.format("result count(include directory):%s continuationToken:%s", blobs.getLength() ,blobs.getContinuationToken()));
+                for (ListBlobItem blobItem : blobs.getResults()) {
+                    if (blobItem instanceof CloudBlob) {
+                        CloudBlob blob = (CloudBlob) blobItem;
+                        if (blob.exists() && !blob.getUri().toString().endsWith("/")) {
+                            builder.add(blob.getName());
+                            log.debug(String.format("name:%s, class:%s, uri:%s", blob.getName(), blob.getClass(), blob.getUri()));
+                        }
+                    }
+                }
+                token = blobs.getContinuationToken();
+            } while (blobs.getContinuationToken() != null);
+        } catch (URISyntaxException | StorageException ex) {
+            throw Throwables.propagate(ex);
+        }
+        return builder.build();
+    }
+
+    @Override
+    public TransactionalFileInput open(TaskSource taskSource, int taskIndex)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+        return new AzureFileInput(task, taskIndex);
+    }
+
+    class AzureFileInput
+            extends InputStreamFileInput
+            implements TransactionalFileInput
+    {
+        public AzureFileInput (PluginTask task, int taskIndex)
+        {
+            super(task.getBufferAllocator(), new SingleFileProvider(task, taskIndex));
+        }
+        public void abort() {}
+
+        public TaskReport commit() {
+            return Exec.newTaskReport();
+        }
+
+        @Override
+        public void close() {}
+    }
+
+    class SingleFileProvider
+            implements InputStreamFileInput.Provider
+    {
+        private CloudBlobClient client;
+        private final String containerName;
+        private final String key;
+        private boolean opened = false;
+
+        public SingleFileProvider(PluginTask task, int taskIndex)
+        {
+            this.client = newAzureClient(task.getAccountName(), task.getAccountKey());
+            this.containerName = task.getContainer();
+            this.key = task.getFiles().get(taskIndex);
+        }
+
+        @Override
+        public InputStream openNext() throws IOException
+        {
+            if (opened) {
+                return null;
+            }
+            opened = true;
+            InputStream inputStream = null;
+            try {
+                CloudBlobContainer container = client.getContainerReference(containerName);
+                CloudBlob blob = container.getBlockBlobReference(key);
+                inputStream = blob.openInputStream();
+            } catch (StorageException | URISyntaxException ex) {
+                Throwables.propagate(ex);
+            }
+            return inputStream;
+        }
+
+        @Override
+        public void close() {}
+    }
+}

data/src/test/java/org/embulk/input/azure_blob_storage/TestAzureBlobStorageFileInputPlugin.java

@@ -0,0 +1,5 @@
+package org.embulk.input.azure_blob_storage;
+
+public class TestAzureBlobStorageFileInputPlugin
+{
+}

metadata

@@ -0,0 +1,87 @@
+--- !ruby/object:Gem::Specification
+name: embulk-input-azure_blob_storage
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Satoshi Akama
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2015-10-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  name: bundler
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  name: rake
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '10.0'
+description: Reads files stored on Microsoft Azure blob Storage.
+email:
+- satoshiakama@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- README.md
+- build.gradle
+- embulk-input-azure_blob_storage.gemspec
+- gradle/wrapper/gradle-wrapper.jar
+- gradle/wrapper/gradle-wrapper.properties
+- gradlew
+- gradlew.bat
+- lib/embulk/input/azure_blob_storage.rb
+- src/main/java/org/embulk/input/azure_blob_storage/AzureBlobStorageFileInputPlugin.java
+- src/test/java/org/embulk/input/azure_blob_storage/TestAzureBlobStorageFileInputPlugin.java
+- classpath/azure-storage-4.0.0.jar
+- classpath/commons-lang3-3.4.jar
+- classpath/embulk-input-azure_blob_storage-0.1.0.jar
+- classpath/jackson-core-2.6.0.jar
+homepage: https://github.com/sakama/embulk-input-azure_blob_storage
+licenses:
+- Apache-2.0
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project:
+rubygems_version: 2.1.9
+signing_key:
+specification_version: 4
+summary: Microsoft Azure blob Storage file input plugin for Embulk
+test_files: []