embulk-input-ftp 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 0333d873277223fc5c1d369fa1417e2481df6ac0
+  data.tar.gz: c3b61c7abde8c581303b993613e788378d133372
+SHA512:
+  metadata.gz: 790052dc1eafaaa5aa093fa6ba0d12fe7ccc64b21de203fcbdc8495807b420549176e19524096a4b02765e26470cc7a1d04358c47e3878f59a6288fedb4941c6
+  data.tar.gz: 5e1755a9388bbeefb9c6a4e6f2c9e96833568a7ab6861fde7985b1c88f6995bd439a65e059f2c73175c102e845a61e35391f20e7f239abe40051aa646ecf405e

data/.gitignore

@@ -0,0 +1,8 @@
+*~
+/pkg/
+/tmp/
+*.gemspec
+.gradle/
+/classpath/
+build/
+.idea

data/ChangeLog

@@ -0,0 +1,5 @@
+
+Release 0.1.0 - 2015-04-29
+
+* First release
+

data/README.md

@@ -0,0 +1,35 @@
+# FTP file input plugin for Embulk
+
+## Overview
+
+* **Plugin type**: file input
+* **Resume supported**: yes
+* **Cleanup supported**: yes
+
+## Configuration
+
+- **host**: FTP server address (string, required)
+- **port**: FTP server port number (integer, default: 21)
+- **user**: user name to login (string, optional)
+- **password**: password to login (string, default: `""`)
+- **path_prefix** prefix of target keys (string, required)
+- **passive_mode**: use passive mode (boolean, default: true)
+- **ascii_mode**: use ASCII mode instead of binary mode (boolean, default: false)
+
+## Example
+
+```yaml
+in:
+  type: ftp
+  host: ftp.example.net
+  port: 21
+  user: anonymous
+  password: "mypassword"
+  path_prefix: /ftp/file/path/prefix
+```
+
+## Build
+
+```
+$ ./gradlew gem
+```

data/build.gradle

@@ -0,0 +1,73 @@
+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:0.6.5"
+    provided "org.embulk:embulk-core:0.6.5"
+    compile files("libs/ftp4j-1.7.2.jar")
+    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       = "${project.version}"
+  spec.authors       = ["Sadayuki Furuhashi"]
+  spec.summary       = %[Ftp file input plugin for Embulk]
+  spec.description   = %[Reads files stored on Ftp.]
+  spec.email         = ["frsyuki@gmail.com"]
+  spec.licenses      = ["Apache 2.0"]
+  spec.homepage      = "https://github.com/embulk/embulk-input-ftp"
+
+  spec.files         = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
+  spec.test_files    = spec.files.grep(%r"^(test|spec)/")
+  spec.require_paths = ["lib"]
+
+  #spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
+  spec.add_development_dependency 'bundler', ['~> 1.0']
+  spec.add_development_dependency 'rake', ['>= 10.0']
+end
+/$)
+    }
+}
+clean { delete "${project.name}.gemspec" }

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Wed Feb 04 13:46:12 PST 2015
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-2.2.1-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/ftp.rb

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

data/src/main/java/org/embulk/input/FtpFileInputPlugin.java

@@ -0,0 +1,583 @@
+package org.embulk.input;
+
+import java.util.List;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.concurrent.Executors;
+import java.util.concurrent.ExecutorService;
+import java.io.IOException;
+import java.io.InterruptedIOException;
+import java.io.InputStream;
+import java.nio.channels.Channels;
+import org.slf4j.Logger;
+import com.google.common.util.concurrent.ThreadFactoryBuilder;
+import com.google.common.collect.ImmutableList;
+import com.google.common.base.Optional;
+import com.google.common.base.Throwables;
+import com.google.common.base.Function;
+import it.sauronsoftware.ftp4j.FTPClient;
+import it.sauronsoftware.ftp4j.FTPFile;
+import it.sauronsoftware.ftp4j.FTPConnector;
+import it.sauronsoftware.ftp4j.FTPCommunicationListener;
+import it.sauronsoftware.ftp4j.FTPDataTransferListener;
+import it.sauronsoftware.ftp4j.FTPException;
+import it.sauronsoftware.ftp4j.FTPIllegalReplyException;
+import it.sauronsoftware.ftp4j.FTPDataTransferException;
+import it.sauronsoftware.ftp4j.FTPAbortedException;
+import it.sauronsoftware.ftp4j.FTPListParseException;
+import org.embulk.config.CommitReport;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigInject;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigDiff;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.Task;
+import org.embulk.config.TaskSource;
+import org.embulk.spi.BufferAllocator;
+import org.embulk.spi.Exec;
+import org.embulk.spi.FileInputPlugin;
+import org.embulk.spi.TransactionalFileInput;
+import org.embulk.spi.util.InputStreamFileInput;
+import org.embulk.input.ftp.BlockingTransfer;
+import org.embulk.input.ftp.RetryableInputStream;
+import org.embulk.input.ftp.RetryExecutor.Retryable;
+import org.embulk.input.ftp.RetryExecutor.RetryGiveupException;
+import static org.embulk.input.ftp.RetryExecutor.retryExecutor;
+
+public class FtpFileInputPlugin
+        implements FileInputPlugin
+{
+    private final Logger log = Exec.getLogger(FtpFileInputPlugin.class);
+
+    public interface PluginTask
+            extends Task
+    {
+        @Config("path_prefix")
+        public String getPathPrefix();
+
+        @Config("last_path")
+        @ConfigDefault("null")
+        public Optional<String> getLastPath();
+
+        @Config("host")
+        public String getHost();
+
+        @Config("port")
+        @ConfigDefault("21")
+        public int getPort();
+
+        @Config("user")
+        @ConfigDefault("null")
+        public Optional<String> getUser();
+
+        @Config("password")
+        @ConfigDefault("null")
+        public Optional<String> getPassword();
+
+        @Config("passive_mode")
+        @ConfigDefault("true")
+        public boolean getPassiveMode();
+
+        @Config("ascii_mode")
+        @ConfigDefault("false")
+        public boolean getAsciiMode();
+
+        public List<String> getFiles();
+        public void setFiles(List<String> files);
+
+        @ConfigInject
+        public BufferAllocator getBufferAllocator();
+    }
+
+    @Override
+    public ConfigDiff transaction(ConfigSource config, FileInputPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+
+        // list files recursively
+        List<String> files = listFiles(log, task);
+        task.setFiles(files);
+        log.info("Using files {}", files);
+
+        // TODO what if task.getFiles().isEmpty()?
+
+        // number of processors is same with number of files
+        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);
+
+        // build next config
+        ConfigDiff configDiff = Exec.newConfigDiff();
+
+        // last_path
+        if (task.getFiles().isEmpty()) {
+            // keep the last value
+            if (task.getLastPath().isPresent()) {
+                configDiff.set("last_path", task.getLastPath().get());
+            }
+        } else {
+            List<String> files = new ArrayList<String>(task.getFiles());
+            Collections.sort(files);
+            configDiff.set("last_path", files.get(files.size() - 1));
+        }
+
+        return configDiff;
+    }
+
+    @Override
+    public void cleanup(TaskSource taskSource,
+            int taskCount,
+            List<CommitReport> successCommitReports)
+    {
+        // do nothing
+    }
+
+    private static FTPClient newFTPClient(Logger log, PluginTask task)
+    {
+        FTPClient client = new FTPClient();
+        try {
+            // TODO SSL
+
+            client.addCommunicationListener(new LoggingCommunicationListner(log));
+
+            // TODO configurable timeout parameters
+            client.setAutoNoopTimeout(3000);
+
+            FTPConnector con = client.getConnector();
+            con.setConnectionTimeout(30);
+            con.setReadTimeout(60);
+            con.setCloseTimeout(60);
+
+            // for commons-net client
+            //client.setControlKeepAliveTimeout
+            //client.setConnectTimeout
+            //client.setSoTimeout
+            //client.setDataTimeout
+            //client.setAutodetectUTF8
+
+            log.info("Connecting to "+task.getHost());
+            client.connect(task.getHost(), task.getPort());
+
+            if (task.getUser().isPresent()) {
+                log.info("Logging in with user "+task.getUser().get());
+                client.login(task.getUser().get(), task.getPassword().or(""));
+            }
+
+            log.info("Using passive mode");
+            client.setPassive(task.getPassiveMode());
+
+            if (task.getAsciiMode()) {
+                log.info("Using ASCII mode");
+                client.setType(FTPClient.TYPE_TEXTUAL);
+            } else {
+                log.info("Using binary mode");
+                client.setType(FTPClient.TYPE_BINARY);
+            }
+
+            if (client.isCompressionSupported()) {
+                log.info("Using MODE Z compression");
+                client.setCompressionEnabled(true);
+            }
+
+            FTPClient connected = client;
+            client = null;
+            return connected;
+
+        } catch (FTPException ex) {
+            log.info("FTP command failed: "+ex.getCode()+" "+ex.getMessage());
+            throw Throwables.propagate(ex);
+
+        } catch (FTPIllegalReplyException ex) {
+            log.info("FTP protocol error");
+            throw Throwables.propagate(ex);
+
+        } catch (IOException ex) {
+            log.info("FTP network error: "+ex);
+            throw Throwables.propagate(ex);
+
+        } finally {
+            if (client != null) {
+                disconnectClient(client);
+            }
+        }
+    }
+
+    static void disconnectClient(FTPClient client)
+    {
+        if (client.isConnected()) {
+            try {
+                client.disconnect(false);
+            } catch (FTPException ex) {
+                // do nothing
+            } catch (FTPIllegalReplyException ex) {
+                // do nothing
+            } catch (IOException ex) {
+                // do nothing
+            }
+        }
+    }
+
+    private List<String> listFiles(Logger log, PluginTask task)
+    {
+        FTPClient client = newFTPClient(log, task);
+        try {
+            return listFilesByPrefix(log, client, task.getPathPrefix(), task.getLastPath());
+        } finally {
+            disconnectClient(client);
+        }
+    }
+
+    public static List<String> listFilesByPrefix(Logger log, FTPClient client,
+            String prefix, Optional<String> lastPath)
+    {
+        String directory;
+        String fileNamePrefix;
+        if (prefix.isEmpty()) {
+            directory = "";
+            fileNamePrefix = "";
+        } else {
+            int pos = prefix.lastIndexOf("/");
+            if (pos < 0) {
+                directory = "";
+                fileNamePrefix = prefix;
+            } else {
+                directory = prefix.substring(0, pos + 1);  // include last "/"
+                fileNamePrefix = prefix.substring(pos + 1);
+            }
+        }
+
+        ImmutableList.Builder<String> builder = ImmutableList.builder();
+
+        try {
+            String currentDirectory = client.currentDirectory();
+            log.info("Listing ftp files at directory '{}' filtering filename by prefix '{}'", directory.isEmpty() ? currentDirectory : directory, fileNamePrefix);
+
+            if (!directory.isEmpty()) {
+                client.changeDirectory(directory);
+                currentDirectory = directory;
+            }
+
+            for (FTPFile file : client.list()) {
+                if (file.getName().startsWith(fileNamePrefix)) {
+                    listFilesRecursive(client, currentDirectory, file, builder);
+                }
+            }
+
+        } catch (FTPListParseException ex) {
+            log.info("FTP listing files failed");
+            throw Throwables.propagate(ex);
+
+        } catch (FTPAbortedException ex) {
+            log.info("FTP listing files failed");
+            throw Throwables.propagate(ex);
+
+        } catch (FTPDataTransferException ex) {
+            log.info("FTP data transfer failed");
+            throw Throwables.propagate(ex);
+
+        } catch (FTPException ex) {
+            log.info("FTP command failed: "+ex.getCode()+" "+ex.getMessage());
+            throw Throwables.propagate(ex);
+
+        } catch (FTPIllegalReplyException ex) {
+            log.info("FTP protocol error");
+            throw Throwables.propagate(ex);
+
+        } catch (IOException ex) {
+            log.info("FTP network error: "+ex);
+            throw Throwables.propagate(ex);
+        }
+
+        return builder.build();
+    }
+
+    private static void listFilesRecursive(FTPClient client,
+            String baseDirectoryPath, FTPFile file,
+            ImmutableList.Builder<String> builder)
+        throws IOException, FTPException, FTPIllegalReplyException, FTPDataTransferException, FTPAbortedException, FTPListParseException
+    {
+        if (!baseDirectoryPath.endsWith("/")) {
+            baseDirectoryPath = baseDirectoryPath + "/";
+        }
+        String path = baseDirectoryPath + file.getName();
+
+        switch (file.getType()) {
+        case FTPFile.TYPE_FILE:
+            builder.add(path);
+            break;
+        case FTPFile.TYPE_DIRECTORY:
+            client.changeDirectory(path);
+            for (FTPFile subFile : client.list()) {
+                listFilesRecursive(client, path, subFile, builder);
+            }
+            client.changeDirectory(baseDirectoryPath);
+            break;
+        case FTPFile.TYPE_LINK:
+            // TODO
+        }
+    }
+
+    @Override
+    public TransactionalFileInput open(TaskSource taskSource, int taskIndex)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+        return new FtpFileInput(log, task, taskIndex);
+    }
+
+    private static class LoggingCommunicationListner
+            implements FTPCommunicationListener
+    {
+        private final Logger log;
+
+        public LoggingCommunicationListner(Logger log)
+        {
+            this.log = log;
+        }
+
+        public void received(String statement)
+        {
+            log.info("< "+statement);
+        }
+
+        public void sent(String statement)
+        {
+            if (statement.startsWith("PASS")) {
+                // don't show password
+                return;
+            }
+            log.info("> "+statement);
+        }
+    }
+
+    private static class LoggingTransferListener
+            implements FTPDataTransferListener
+    {
+        private final Logger log;
+        private final long transferNoticeBytes;
+
+        private long totalTransfer;
+        private long nextTransferNotice;
+
+        public LoggingTransferListener(Logger log, long transferNoticeBytes)
+        {
+            this.log = log;
+            this.transferNoticeBytes = transferNoticeBytes;
+            this.nextTransferNotice = transferNoticeBytes;
+        }
+
+        public void started()
+        {
+            log.info("Transfer started");
+        }
+
+        public void transferred(int length)
+        {
+            totalTransfer += length;
+            if (totalTransfer > nextTransferNotice) {
+                log.info("Transferred "+totalTransfer+" bytes");
+                nextTransferNotice = ((totalTransfer / transferNoticeBytes)+1) * transferNoticeBytes;
+            }
+        }
+
+        public void completed()
+        {
+            log.info("Transfer completed "+totalTransfer+" bytes");
+        }
+
+        public void aborted()
+        {
+            log.info("Transfer aborted");
+        }
+
+        public void failed()
+        {
+            log.info("Transfer failed");
+        }
+    }
+
+    private static final long TRANSFER_NOTICE_BYTES = 100*1024*1024;
+
+    private static InputStream startDownload(final Logger log, final FTPClient client,
+            final String path, final long offset, ExecutorService executor)
+    {
+        BlockingTransfer t = BlockingTransfer.submit(executor,
+                new Function<BlockingTransfer, Runnable>()
+                {
+                    public Runnable apply(final BlockingTransfer transfer)
+                    {
+                        return new Runnable() {
+                            public void run()
+                            {
+                                try {
+                                    client.download(path, Channels.newOutputStream(transfer.getWriterChannel()), offset, new LoggingTransferListener(log, TRANSFER_NOTICE_BYTES));
+
+                                } catch (FTPException ex) {
+                                    log.info("FTP command failed: "+ex.getCode()+" "+ex.getMessage());
+                                    throw Throwables.propagate(ex);
+
+                                } catch (FTPDataTransferException ex) {
+                                    log.info("FTP data transfer failed");
+                                    throw Throwables.propagate(ex);
+
+                                } catch (FTPAbortedException ex) {
+                                    log.info("FTP listing files failed");
+                                    throw Throwables.propagate(ex);
+
+                                } catch (FTPIllegalReplyException ex) {
+                                    log.info("FTP protocol error");
+                                    throw Throwables.propagate(ex);
+
+                                } catch (IOException ex) {
+                                    throw Throwables.propagate(ex);
+
+                                } finally {
+                                    try {
+                                        transfer.getWriterChannel().close();
+                                    } catch (IOException ex) {
+                                        throw new RuntimeException(ex);
+                                    }
+                                }
+                            }
+                        };
+                    }
+                });
+        return Channels.newInputStream(t.getReaderChannel());
+    }
+
+    private static class FtpRetryableOpener
+            implements RetryableInputStream.Opener
+    {
+        private final Logger log;
+        private final FTPClient client;
+        private final ExecutorService executor;
+        private final String path;
+
+        public FtpRetryableOpener(Logger log, FTPClient client, ExecutorService executor, String path)
+        {
+            this.log = log;
+            this.client = client;
+            this.executor = executor;
+            this.path = path;
+        }
+
+        @Override
+        public InputStream open(final long offset, final Exception exception) throws IOException
+        {
+            try {
+                return retryExecutor()
+                    .withRetryLimit(3)
+                    .withInitialRetryWait(500)
+                    .withMaxRetryWait(30*1000)
+                    .runInterruptible(new Retryable<InputStream>() {
+                        @Override
+                        public InputStream call() throws InterruptedIOException
+                        {
+                            log.warn(String.format("FTP read failed. Retrying GET request with %,d bytes offset", offset), exception);
+                            return startDownload(log, client, path, offset, executor);
+                        }
+
+                        @Override
+                        public boolean isRetryableException(Exception exception)
+                        {
+                            return true;  // TODO
+                        }
+
+                        @Override
+                        public void onRetry(Exception exception, int retryCount, int retryLimit, int retryWait)
+                                throws RetryGiveupException
+                        {
+                            String message = String.format("FTP GET request failed. Retrying %d/%d after %d seconds. Message: %s",
+                                    retryCount, retryLimit, retryWait/1000, exception.getMessage());
+                            if (retryCount % 3 == 0) {
+                                log.warn(message, exception);
+                            } else {
+                                log.warn(message);
+                            }
+                        }
+
+                        @Override
+                        public void onGiveup(Exception firstException, Exception lastException)
+                                throws RetryGiveupException
+                        {
+                        }
+                    });
+            } catch (RetryGiveupException ex) {
+                Throwables.propagateIfInstanceOf(ex.getCause(), IOException.class);
+                throw Throwables.propagate(ex.getCause());
+            } catch (InterruptedException ex) {
+                throw new InterruptedIOException();
+            }
+        }
+    }
+
+    // TODO create single-file InputStreamFileInput utility
+    private static class SingleFileProvider
+            implements InputStreamFileInput.Provider
+    {
+        private final Logger log;
+        private final FTPClient client;
+        private final ExecutorService executor;
+        private final String path;
+        private boolean opened = false;
+
+        public SingleFileProvider(Logger log, PluginTask task, int taskIndex)
+        {
+            this.log = log;
+            this.client = newFTPClient(log, task);
+            this.executor = Executors.newCachedThreadPool(
+                    new ThreadFactoryBuilder()
+                        .setNameFormat("embulk-input-ftp-%d")
+                        .setDaemon(true)
+                        .build());
+            this.path = task.getFiles().get(taskIndex);
+        }
+
+        @Override
+        public InputStream openNext() throws IOException
+        {
+            if (opened) {
+                return null;
+            }
+            opened = true;
+
+            return new RetryableInputStream(
+                    startDownload(log, client, path, 0L, executor),
+                    new FtpRetryableOpener(log, client, executor, path));
+        }
+
+        @Override
+        public void close()
+        {
+            try {
+                executor.shutdownNow();
+            } finally {
+                disconnectClient(client);
+            }
+        }
+    }
+
+    public static class FtpFileInput
+            extends InputStreamFileInput
+            implements TransactionalFileInput
+    {
+        public FtpFileInput(Logger log, PluginTask task, int taskIndex)
+        {
+            super(task.getBufferAllocator(), new SingleFileProvider(log, task, taskIndex));
+        }
+
+        public void abort() { }
+
+        public CommitReport commit()
+        {
+            return Exec.newCommitReport();
+        }
+    }
+}