embulk-output-mailchimp 0.2.3 → 0.3.2

data/gradlew

@@ -0,0 +1,160 @@
+#!/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
+
+# 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 "$SAVED" >/dev/null
+
+CLASSPATH=$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 "$CLASSPATH"`
+    JAVACMD=`cygpath --unix "$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
+
+# 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/output/mailchimp.rb

@@ -1,172 +1,3 @@
-require 'mailchimp'
-require 'perfect_retry'
-
-require 'securerandom'
-
-module Embulk
-  module Output
-
-    class Mailchimp < OutputPlugin
-      Plugin.register_output("mailchimp", self)
-
-      class Client
-        def initialize(apikey)
-          @client = ::Mailchimp::API.new(apikey)
-        rescue ::Mailchimp::InvalidApiKeyError => e
-          raise Embulk::ConfigError.new(e.message)
-        end
-
-        def batch_subscribe_list(list_id, subscribers, double_optin, update_existing, replace_interests)
-          @client.lists.batch_subscribe(list_id, subscribers, double_optin, update_existing, replace_interests)
-        rescue ::Mailchimp::UserUnderMaintenanceError, ::Mailchimp::TooManyConnectionsError => e
-          Embulk.logger.warn e.message
-          raise e
-        end
-      end
-
-      MAX_EMAIL_COUNT = 1_000
-
-      def self.transaction(config, schema, count, &control)
-        task = {
-          apikey:                 config.param("apikey",                 :string),
-          list_id:                config.param("list_id",                :string),
-          double_optin:           config.param("double_optin",           :bool,    default: false),
-          update_existing:        config.param("update_existing",        :bool,    default: false),
-          replace_interests:      config.param("replace_interests",      :bool,    default: true),
-          email_column:           config.param("email_column",           :string,  default: "email"),
-          fname_column:           config.param("fname_column",           :string,  default: "fname"),
-          lname_column:           config.param("lname_column",           :string,  default: "lname"),
-          grouping_columns:       config.param("grouping_columns",       :array,   default: nil),
-          retry_limit:            config.param("retry_limit",            :integer, default: 5),
-          retry_initial_wait_sec: config.param("retry_initial_wait_sec", :integer, default: 1),
-          stop_on_invalid_record: config.param("stop_on_invalid_record", :bool,    default: true),
-        }
-
-        Client.new(task[:apikey]) # NOTE for validate apikey
-        raise Embulk::ConfigError.new("schema has no '#{task[:email_column]}' column") if schema.none? {|s| s.name == task[:email_column] }
-
-        task_reports = yield(task)
-        next_config_diff = {}
-        return next_config_diff
-      end
-
-      def init
-        @client            = Client.new(task[:apikey])
-        @list_id           = task[:list_id]
-        @double_optin      = task[:double_optin]
-        @update_existing   = task[:update_existing]
-        @replace_interests = task[:replace_interests]
-        @email_column      = task[:email_column]
-        @fname_column      = task[:fname_column]
-        @lname_column      = task[:lname_column]
-        @grouping_columns  = task[:grouping_columns]
-        @subscribers       = []
-
-        @retry_manager = PerfectRetry.new do |config|
-          config.limit = task[:retry_limit]
-          config.sleep = lambda{|n| task[:retry_initial_wait_sec] * (2 ** (n - 1)) }
-          config.logger = Embulk.logger
-          config.log_level = nil
-          config.dont_rescues = [Embulk::ConfigError, Embulk::DataError]
-        end
-        @stop_on_invalid_record = task[:stop_on_invalid_record]
-      end
-
-      def close
-      end
-
-      def add(page)
-        # output code:
-        page.each do |record|
-          row = Hash[schema.names.zip(record)]
-          if row[@email_column]
-            add_subscriber row
-
-            flush_subscribers! unless @subscribers.size < MAX_EMAIL_COUNT
-          else
-            raise Embulk::DataError.new("#{@email_column} is empty") if @stop_on_invalid_record
-          end
-        end
-      end
-
-      def finish
-        flush_subscribers!
-      end
-
-      def abort
-      end
-
-      def commit
-        task_report = {}
-        return task_report
-      end
-
-      private
-
-      # NOTE we expect row has #{email_column} column.
-      #      expected full data is following columns.
-      #  | #{email_column} | #{fname_column} | #{lname_column} | #{grouping_columns[0]} | #{grouping_columns[1]…|
-      #  |-----------------|-----------------|-----------------|------------------------|-----------------------|
-      #  | hi@example.com  | first_name      | last_name       | music,book             | middle                |
-      def add_subscriber(row)
-        return unless row[@email_column]
-
-        merge_columns = {fname: @fname_column, lname: @lname_column}
-
-        # NOTE merge_vars can add extra infomation.
-        #      https://apidocs.mailchimp.com/api/2.0/lists/merge-vars.php
-        #      embulk-output-mailchimp can add following infomation
-        #        - lname
-        #        - fname
-        #        - interest group
-        merge_vars = merge_columns.each_with_object({}) do |(key, col_name), m|
-          m[key] = row[col_name] if row[col_name]
-        end
-
-        if @grouping_columns && !@grouping_columns.empty?
-          merge_vars[:groupings] = []
-
-          @grouping_columns.each do |group|
-            groups = row[group].to_s.split(",")
-            next if groups.empty?
-
-            merge_vars[:groupings] << {
-              'name'   => group,
-              'groups' => groups,
-            }
-          end
-        end
-
-        @subscribers << {
-          EMAIL: {
-            email: row[@email_column]
-          },
-          merge_vars: merge_vars,
-        }
-      end
-
-      def flush_subscribers!
-        return if @subscribers.empty?
-
-        send_subscribers!
-        @subscribers = []
-      end
-
-      def send_subscribers!
-        @retry_manager.with_retry do
-          request_id = SecureRandom.uuid
-          Embulk.logger.info "[#{request_id}] Request : #{@subscribers.size} items"
-          res = @client.batch_subscribe_list(
-            @list_id,
-            @subscribers,
-            @double_optin,
-            @update_existing,
-            @replace_interests
-          )
-          Embulk.logger.info "[#{request_id}] Result : #{res.to_s}"
-        end
-      end
-    end
-
-  end
-end
+Embulk::JavaPlugin.register_output(
+  "mailchimp", "org.embulk.output.mailchimp.MailChimpOutputPlugin",
+  File.expand_path('../../../../classpath', __FILE__))