embulk-output-s3_parquet 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: fac4eca9b96e218930333123d01d82ec5acae146
+  data.tar.gz: dc1de337cd4ada9fa86d53239be85b5a154115c1
+SHA512:
+  metadata.gz: 8451431ba506a80159ad768017268b826e73f6010fcb923804f6b3a8f8cb27e7669e90c4d8f25a6d348d55ce558fd8ea488942451a973c7d8387bd70a825fb77
+  data.tar.gz: 835f5d30265595270925e57587bea633a1e6156cfa8f7b660af3eac1539fcf9b40f1e7dfb986ae4a290c67b7eee2638275846cfa86edd217168ff5b2c0672313

data/.gitignore

@@ -0,0 +1,12 @@
+*~
+/pkg/
+/tmp/
+*.gemspec
+.gradle/
+/classpath/
+build/
+.idea
+/.settings/
+/.metadata/
+.classpath
+.project

data/.scalafmt.conf

@@ -0,0 +1,9 @@
+# https://scalameta.org/scalafmt/#Configuration
+
+style = IntelliJ
+maxColumn = 160
+align = none
+newlines.penalizeSingleSelectMultiArgList = false
+newlines.alwaysBeforeElseAfterCurlyIf = true
+newlines.alwaysBeforeTopLevelStatements = true
+

data/CHANGELOG.md

@@ -0,0 +1,9 @@
+0.0.2 (2019-01-21)
+==================
+
+* [Fix] Close local buffer files before uploading even if lots of pages exist.
+
+0.0.1 (2019-01-18)
+==================
+
+* First Release

data/LICENSE.txt

@@ -0,0 +1,21 @@
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,122 @@
+# S3 Parquet output plugin for Embulk
+
+[Embulk](https://github.com/embulk/embulk/) output plugin to dump records as [Apache Parquet](https://parquet.apache.org/) files on S3.
+
+## Overview
+
+* **Plugin type**: output
+* **Load all or nothing**: no
+* **Resume supported**: no
+* **Cleanup supported**: yes
+
+## Configuration
+
+- **bucket**: s3 bucket name (string, required)
+- **path_prefix**: prefix of target keys (string, optional)
+- **sequence_format**: format of the sequence number of the output files (string, default: `"%03d.%02d."`)
+  - **sequence_format** formats task index and sequence number in a task. 
+- **file_ext**: path suffix of the output files (string, default: `"parquet"`)
+- **compression_codec**: compression codec for parquet file (`"uncompressed"`,`"snappy"`,`"gzip"`,`"lzo"`,`"brotli"`,`"lz4"` or `"zstd"`, default: `"uncompressed"`)
+- **default_timestamp_format**: default timestamp format (string, default: `"%Y-%m-%d %H:%M:%S.%6N %z"`)
+- **default_timezone**: default timezone (string, default: `"UTC"`)
+- **column_options**: a map whose keys are name of columns, and values are configuration with following parameters (optional)
+  - **timezone**: timezone if type of this column is timestamp. If not set, **default_timezone** is used. (string, optional)
+  - **format**: timestamp format if type of this column is timestamp. If not set, **default_timestamp_format**: is used. (string, optional)
+- **canned_acl**: grants one of [canned ACLs](https://docs.aws.amazon.com/AmazonS3/latest/dev/acl-overview.html#CannedACL) for created objects (string, default: `private`)
+- **block_size**: The block size is the size of a row group being buffered in memory. This limits the memory usage when writing. Larger values will improve the I/O when reading but consume more memory when writing. (int, default: `134217728` (128MB))
+- **page_size**: The page size is for compression. When reading, each page can be decompressed independently. A block is composed of pages. The page is the smallest unit that must be read fully to access a single record. If this value is too small, the compression will deteriorate. (int, default: `1048576` (1MB))
+- **max_padding_size**: The max size (bytes) to write as padding and the min size of a row group (int, default: `8388608` (8MB))
+- **enable_dictionary_encoding**: The boolean value is to enable/disable dictionary encoding. (boolean, default: `true`)
+- **auth_method**: name of mechanism to authenticate requests (`"basic"`, `"env"`, `"instance"`, `"profile"`, `"properties"`, `"anonymous"`, or `"session"`, default: `"default"`)
+  - `"basic"`: uses **access_key_id** and **secret_access_key** to authenticate.
+  - `"env"`: uses `AWS_ACCESS_KEY_ID` (or `AWS_ACCESS_KEY`) and `AWS_SECRET_KEY` (or `AWS_SECRET_ACCESS_KEY`) environment variables.
+  - `"instance"`: uses EC2 instance profile or attached ECS task role.
+  - `"profile"`: uses credentials written in a file. Format of the file is as following, where `[...]` is a name of profile.
+    ```
+    [default]
+    aws_access_key_id=YOUR_ACCESS_KEY_ID
+    aws_secret_access_key=YOUR_SECRET_ACCESS_KEY
+
+    [profile2]
+    ...
+    ```
+  - `"properties"`: uses aws.accessKeyId and aws.secretKey Java system properties.
+  - `"anonymous"`: uses anonymous access. This auth method can access only public files.
+  - `"session"`: uses temporary-generated **access_key_id**, **secret_access_key** and **session_token**.
+  - `"assume_role"`: uses temporary-generated credentials by assuming **role_arn** role.
+  - `"default"`: uses AWS SDK's default strategy to look up available credentials from runtime environment. This method behaves like the combination of the following methods.
+    1. `"env"`
+    1. `"properties"`
+    1. `"profile"`
+    1. `"instance"`
+- **profile_file**: path to a profiles file. this is optionally used when **auth_method** is `"profile"`. (string, default: given by `AWS_CREDENTIAL_PROFILES_FILE` environment variable, or ~/.aws/credentials).
+- **profile_name**: name of a profile. this is optionally used when **auth_method** is `"profile"`. (string, default: `"default"`)
+- **access_key_id**: aws access key id. this is required when **auth_method** is `"basic"` or `"session"`. (string, optional)
+- **secret_access_key**: aws secret access key. this is required when **auth_method** is `"basic"` or `"session"`. (string, optional)
+- **session_token**: aws session token. this is required when **auth_method** is `"session"`. (string, optional)
+- **role_arn**: arn of the role to assume. this is required for **auth_method** is `"assume_role"`. (string, optional)
+- **role_session_name**: an identifier for the assumed role session. this is required when **auth_method** is `"assume_role"`. (string, optional)  
+- **role_external_id**: a unique identifier that is used by third parties when assuming roles in their customers' accounts. this is optionally used for **auth_method**: `"assume_role"`. (string, optional)
+- **role_session_duration_seconds**: duration, in seconds, of the role session. this is optionally used for **auth_method**: `"assume_role"`. (int, optional) 
+- **scope_down_policy**: an iam policy in json format. this is optionally used for **auth_method**: `"assume_role"`. (string, optional)
+- **endpoint**: The AWS Service endpoint (string, optional)
+- **region**: The AWS region (string, optional)
+- **http_proxy**: Indicate whether using when accessing AWS via http proxy. (optional)
+  - **host** proxy host (string, required)
+  - **port** proxy port (int, optional)
+  - **protocol** proxy protocol (string, default: `"https"`)
+  - **user** proxy user (string, optional)
+  - **password** proxy password (string, optional)
+- **buffer_dir**: buffer directory for parquet files to be uploaded on S3 (string, default: Create a Temporary Directory)
+
+
+## Example
+
+```yaml
+out:
+  type: s3_parquet
+  bucket: my-bucket
+  path_prefix: path/to/my-obj.
+  file_ext: snappy.parquet
+  compression_codec: snappy
+  default_timezone: Asia/Tokyo
+  canned_acl: bucket-owner-full-control
+```
+
+## Note
+
+* The current implementation does not support [LogicalTypes](https://github.com/apache/parquet-format/blob/2b38663/LogicalTypes.md). I will implement them later as **column_options**. So, currently **timestamp** type and **json** type are stored as UTF-8 String. Please be careful.  
+
+## Development
+
+### Run example:
+
+```shell
+$ ./gradlew classpath
+$ embulk run example/config.yml -Ilib
+```
+
+### Run test:
+
+```shell
+$ ./gradlew test
+```
+
+### Build
+
+```
+$ ./gradlew gem  # -t to watch change of files and rebuild continuously
+```
+
+### Release gem:
+Fix [build.gradle](./build.gradle), then
+
+
+```shell
+$ ./gradlew gemPush
+
+```
+
+## ChangeLog
+
+[CHANGELOG.md](./CHANGELOG.md)

data/build.gradle

@@ -0,0 +1,101 @@
+plugins {
+    id "scala"
+    id "com.jfrog.bintray" version "1.1"
+    id "com.github.jruby-gradle.base" version "1.5.0"
+    id "com.diffplug.gradle.spotless" version "3.13.0"
+    id "com.adarshr.test-logger" version "1.6.0"  // For Pretty test logging
+}
+import com.github.jrubygradle.JRubyExec
+repositories {
+    mavenCentral()
+    jcenter()
+}
+configurations {
+    provided
+}
+
+version = "0.0.2"
+
+sourceCompatibility = 1.8
+targetCompatibility = 1.8
+
+dependencies {
+    compile  "org.embulk:embulk-core:0.9.12"
+    provided "org.embulk:embulk-core:0.9.12"
+
+    compile 'org.scala-lang:scala-library:2.12.8'
+    ['s3', 'sts'].each { v ->
+        compile "com.amazonaws:aws-java-sdk-${v}:1.11.479"
+    }
+    ['column', 'common', 'encoding', 'format', 'hadoop', 'jackson'].each { v ->
+        compile "org.apache.parquet:parquet-${v}:1.10.0"
+    }
+    compile 'org.apache.hadoop:hadoop-common:2.9.2'
+    compile 'org.xerial.snappy:snappy-java:1.1.7.2'
+
+    testCompile 'org.scalatest:scalatest_2.12:3.0.5'
+    testCompile 'org.embulk:embulk-test:0.9.12'
+    testCompile 'org.embulk:embulk-standards:0.9.12'
+    testCompile 'cloud.localstack:localstack-utils:0.1.15'
+    testCompile 'org.apache.parquet:parquet-tools:1.8.0'
+    testCompile 'org.apache.hadoop:hadoop-client:2.9.2'
+}
+
+testlogger {
+    theme "mocha"
+}
+
+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 "-S"
+    script "gem"
+    scriptArgs "build", "${project.name}.gemspec"
+    doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
+}
+
+task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
+    jrubyArgs "-S"
+    script "gem"
+    scriptArgs "push", "pkg/${project.name}-${project.version}.gem"
+}
+
+task "package"(dependsOn: ["gemspec", "classpath"]) {
+    doLast {
+        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       = "${project.version}"
+  spec.authors       = ["Civitaspo"]
+  spec.summary       = %[S3 Parquet output plugin for Embulk]
+  spec.description   = %[Dumps records to S3 Parquet.]
+  spec.email         = ["civitaspo@gmail.com"]
+  spec.licenses      = ["MIT"]
+  spec.homepage      = "https://github.com/civitaspo/embulk-output-s3_parquet"
+
+  spec.files         = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
+  spec.test_files    = spec.files.grep(%r"^(test|spec)/")
+  spec.require_paths = ["lib"]
+
+  #spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
+  spec.add_development_dependency 'bundler', ['~> 1.0']
+  spec.add_development_dependency 'rake', ['~> 12.0']
+end
+/$)
+    }
+}
+clean { delete "${project.name}.gemspec" }

data/example/config.yml

@@ -0,0 +1,25 @@
+
+in:
+  type: file
+  path_prefix: ./example/data.tsv
+  parser:
+    type: csv
+    delimiter: "\t"
+    skip_header_lines: 0
+    null_string: ""
+    columns:
+      - { name: id, type: long }
+      - { name: description, type: string }
+      - { name: name, type: string }
+      - { name: t, type: timestamp, format: "%Y-%m-%d %H:%M:%S %z"}
+      - { name: payload, type: json}
+    stop_on_invalid_record: true
+
+out:
+  type: s3_parquet
+  bucket: my-bucket
+  path_prefix: path/to/my-obj.
+  file_ext: snappy.parquet
+  compression_codec: snappy
+  default_timezone: Asia/Tokyo
+  canned_acl: bucket-owner-full-control

data/example/data.tsv

@@ -0,0 +1,5 @@
+0	c20ef94602	c212c89f91	2017-10-24 03:54:35 +0900	{"a":0,"b":"99"}
+1	330a9fc33a	e25b33b616	2017-10-22 19:53:31 +0900	{"a":1,"b":"a9"}
+2	707b3b7588	90823c6a1f	2017-10-23 23:42:43 +0900	{"a":2,"b":"96"}
+3	8d8288e66f		2017-10-22 06:12:13 +0900	{"a":3,"b":"86"}
+4	c54d8b6481	e56a40571c	2017-10-23 04:59:16 +0900	{"a":4,"b":"d2"}

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,5 @@
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-4.1-bin.zip

data/gradlew

@@ -0,0 +1,172 @@
+#!/usr/bin/env sh
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# 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\"`/" >/dev/null
+APP_HOME="`pwd -P`"
+cd "$SAVED" >/dev/null
+
+APP_NAME="Gradle"
+APP_BASE_NAME=`basename "$0"`
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn () {
+    echo "$*"
+}
+
+die () {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+nonstop=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+  NONSTOP* )
+    nonstop=true
+    ;;
+esac
+
+CLASSPATH=$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 "$darwin" = "false" -a "$nonstop" = "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 "$CLASSPATH"`
+    JAVACMD=`cygpath --unix "$JAVACMD"`
+
+    # 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
+
+# Escape application args
+save () {
+    for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
+    echo " "
+}
+APP_ARGS=$(save "$@")
+
+# Collect all arguments for the java command, following the shell quoting and substitution rules
+eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
+
+# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
+if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
+  cd "$(dirname "$0")"
+fi
+
+exec "$JAVACMD" "$@"