embulk-input-sftp 0.1.0

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Wed Jan 13 12:41:02 JST 2016
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-2.10-bin.zip

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/input/sftp.rb

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

data/src/main/java/org/embulk/input/sftp/PluginTask.java

@@ -0,0 +1,67 @@
+package org.embulk.input.sftp;
+
+import com.google.common.base.Optional;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigInject;
+import org.embulk.config.Task;
+import org.embulk.spi.BufferAllocator;
+import org.embulk.spi.unit.LocalFile;
+
+import java.util.List;
+
+public interface PluginTask
+        extends Task
+{
+    @Config("host")
+    String getHost();
+
+    @Config("port")
+    @ConfigDefault("22")
+    int getPort();
+
+    @Config("user")
+    String getUser();
+
+    @Config("password")
+    @ConfigDefault("null")
+    Optional<String> getPassword();
+
+    @Config("secret_key_file")
+    @ConfigDefault("null")
+    Optional<LocalFile> getSecretKeyFile();
+    void setSecretKeyFile(Optional<LocalFile> secretKeyFile);
+
+    @Config("secret_key_passphrase")
+    @ConfigDefault("\"\"")
+    String getSecretKeyPassphrase();
+
+    @Config("user_directory_is_root")
+    @ConfigDefault("true")
+    Boolean getUserDirIsRoot();
+
+    @Config("timeout")
+    @ConfigDefault("600") // 10 minutes
+    int getSftpConnectionTimeout();
+
+    @Config("max_connection_retry")
+    @ConfigDefault("5") // 5 times retry to connect sftp server if failed.
+    int getMaxConnectionRetry();
+
+    @Config("path_prefix")
+    String getPathPrefix();
+
+    @Config("last_path")
+    @ConfigDefault("null")
+    Optional<String> getLastPath();
+
+    @Config("proxy")
+    @ConfigDefault("null")
+    Optional<ProxyTask> getProxy();
+
+    List<String> getFiles();
+    void setFiles(List<String> files);
+
+    @ConfigInject
+    BufferAllocator getBufferAllocator();
+}

data/src/main/java/org/embulk/input/sftp/ProxyTask.java

@@ -0,0 +1,85 @@
+package org.embulk.input.sftp;
+
+import com.fasterxml.jackson.annotation.JsonCreator;
+import com.fasterxml.jackson.annotation.JsonValue;
+import com.google.common.base.Optional;
+import org.apache.commons.vfs2.FileSystemOptions;
+import org.apache.commons.vfs2.provider.sftp.SftpFileSystemConfigBuilder;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigException;
+import org.embulk.config.Task;
+
+import java.util.Locale;
+
+interface ProxyTask
+        extends Task
+{
+    @Config("type")
+    ProxyType getType();
+
+    @Config("host")
+    Optional<String> getHost();
+
+    @Config("user")
+    @ConfigDefault("null")
+    Optional<String> getUser();
+
+    @Config("password")
+    @ConfigDefault("null")
+    Optional<String> getPassword();
+
+    @Config("port")
+    @ConfigDefault("22")
+    int getPort();
+
+    @Config("command")
+    @ConfigDefault("null")
+    Optional<String> getCommand();
+
+    enum ProxyType
+    {
+        HTTP,
+        SOCKS,
+        STREAM;
+
+        @JsonValue
+        @Override
+        public String toString()
+        {
+            return name().toLowerCase(Locale.ENGLISH);
+        }
+
+        @JsonCreator
+        public static ProxyType fromString(String value)
+        {
+            switch (value) {
+                case "http":
+                    return HTTP;
+                case "socks":
+                    return SOCKS;
+                case "stream":
+                    return STREAM;
+                default:
+                    throw new ConfigException(String.format("Unknown proxy type '%s'. Supported proxy types are http, socks, stream", value));
+            }
+        }
+
+        public static SftpFileSystemConfigBuilder setProxyType(SftpFileSystemConfigBuilder builder, FileSystemOptions fsOptions, ProxyTask.ProxyType type)
+        {
+            SftpFileSystemConfigBuilder.ProxyType setType = null;
+            switch (type) {
+                case HTTP:
+                    setType = SftpFileSystemConfigBuilder.PROXY_HTTP;
+                    break;
+                case SOCKS:
+                    setType = SftpFileSystemConfigBuilder.PROXY_SOCKS5;
+                    break;
+                case STREAM:
+                    setType = SftpFileSystemConfigBuilder.PROXY_STREAM;
+            }
+            builder.setProxyType(fsOptions, setType);
+            return builder;
+        }
+    }
+}

data/src/main/java/org/embulk/input/sftp/SftpFileInput.java

@@ -0,0 +1,217 @@
+package org.embulk.input.sftp;
+
+import com.google.common.base.Function;
+import com.google.common.base.Throwables;
+import com.google.common.collect.ImmutableList;
+import org.apache.commons.io.FilenameUtils;
+import org.apache.commons.vfs2.FileObject;
+import org.apache.commons.vfs2.FileSystemException;
+import org.apache.commons.vfs2.FileSystemOptions;
+import org.apache.commons.vfs2.impl.StandardFileSystemManager;
+import org.apache.commons.vfs2.provider.sftp.IdentityInfo;
+import org.apache.commons.vfs2.provider.sftp.SftpFileSystemConfigBuilder;
+import org.embulk.config.ConfigException;
+import org.embulk.config.TaskReport;
+import org.embulk.spi.Exec;
+import org.embulk.spi.TransactionalFileInput;
+import org.embulk.spi.unit.LocalFile;
+import org.embulk.spi.util.InputStreamFileInput;
+import org.slf4j.Logger;
+
+import java.io.File;
+import java.net.URI;
+import java.net.URISyntaxException;
+import java.util.List;
+
+public class SftpFileInput
+        extends InputStreamFileInput
+        implements TransactionalFileInput
+{
+    private static final Logger log = Exec.getLogger(SftpFileInput.class);
+
+    public SftpFileInput(PluginTask task, int taskIndex)
+    {
+        super(task.getBufferAllocator(), new SingleFileProvider(task, taskIndex, initializeStandardFileSystemManager()));
+    }
+
+    public void abort()
+    {
+    }
+
+    public TaskReport commit()
+    {
+        return Exec.newTaskReport();
+    }
+
+    @Override
+    public void close()
+    {
+    }
+
+    private static StandardFileSystemManager initializeStandardFileSystemManager()
+    {
+        if (!log.isDebugEnabled()) {
+            // TODO: change logging format: org.apache.commons.logging.Log
+            System.setProperty("org.apache.commons.logging.Log", "org.apache.commons.logging.impl.NoOpLog");
+        }
+
+        StandardFileSystemManager manager = new StandardFileSystemManager();
+        try {
+            manager.init();
+        }
+        catch (FileSystemException ex) {
+            Throwables.propagate(ex);
+        }
+
+        return manager;
+    }
+
+    private static String initializeUserInfo(PluginTask task)
+    {
+        String userInfo = task.getUser();
+        if (task.getPassword().isPresent()) {
+            userInfo += ":" + task.getPassword().get();
+        }
+        return userInfo;
+    }
+
+    public static FileSystemOptions initializeFsOptions(PluginTask task)
+    {
+        FileSystemOptions fsOptions = new FileSystemOptions();
+
+        try {
+            SftpFileSystemConfigBuilder builder = SftpFileSystemConfigBuilder.getInstance();
+            builder.setUserDirIsRoot(fsOptions, task.getUserDirIsRoot());
+            builder.setTimeout(fsOptions, task.getSftpConnectionTimeout());
+            builder.setStrictHostKeyChecking(fsOptions, "no");
+
+            if (task.getSecretKeyFile().isPresent()) {
+                IdentityInfo identityInfo = new IdentityInfo(
+                        new File((task.getSecretKeyFile().transform(localFileToPathString()).get())),
+                        task.getSecretKeyPassphrase().getBytes()
+                );
+                builder.setIdentityInfo(fsOptions, identityInfo);
+                log.info("set identity: {}", task.getSecretKeyFile().get());
+            }
+
+            if (task.getProxy().isPresent()) {
+                ProxyTask proxy = task.getProxy().get();
+
+                ProxyTask.ProxyType.setProxyType(builder, fsOptions, proxy.getType());
+
+                if (proxy.getHost().isPresent()) {
+                    builder.setProxyHost(fsOptions, proxy.getHost().get());
+                    builder.setProxyPort(fsOptions, proxy.getPort());
+                }
+
+                if (proxy.getUser().isPresent()) {
+                    builder.setProxyUser(fsOptions, proxy.getUser().get());
+                }
+
+                if (proxy.getPassword().isPresent()) {
+                    builder.setProxyPassword(fsOptions, proxy.getPassword().get());
+                }
+
+                if (proxy.getCommand().isPresent()) {
+                    builder.setProxyCommand(fsOptions, proxy.getCommand().get());
+                }
+            }
+        }
+        catch (FileSystemException ex) {
+            Throwables.propagate(ex);
+        }
+
+        return fsOptions;
+    }
+
+    public static String getSftpFileUri(PluginTask task)
+    {
+        try {
+            return new URI("sftp", initializeUserInfo(task), task.getHost(), task.getPort(), task.getPathPrefix(), null, null).toString();
+        }
+        catch (URISyntaxException ex) {
+            throw new ConfigException(ex);
+        }
+    }
+
+    public static List<String> listFilesByPrefix(PluginTask task)
+    {
+        ImmutableList.Builder<String> builder = ImmutableList.builder();
+        int maxConnectionRetry = task.getMaxConnectionRetry();
+
+        StandardFileSystemManager manager = null;
+        int count = 0;
+        while (true) {
+            try {
+                manager = initializeStandardFileSystemManager();
+                FileObject files = manager.resolveFile(getSftpFileUri(task), initializeFsOptions(task));
+                String basename = FilenameUtils.getBaseName(task.getPathPrefix());
+
+                if (files.isFolder()) {
+                    for (FileObject f : files.getChildren()) {
+                        if (f.isFile()) {
+                            addFileToList(builder, f.toString(), "");
+                        }
+                    }
+                }
+                else {
+                    FileObject parent = files.getParent();
+                    for (FileObject f : parent.getChildren()) {
+                        if (f.isFile()) {
+                            addFileToList(builder, f.toString(), basename);
+                        }
+                    }
+                }
+                return builder.build();
+            }
+            catch (FileSystemException ex) {
+                if (++count == maxConnectionRetry) {
+                    Throwables.propagate(ex);
+                }
+                log.warn("failed to connect sftp server: " + ex.getMessage(), ex);
+
+                try {
+                    long sleepTime = ((long) Math.pow(2, count) * 1000);
+                    log.warn("sleep in next connection retry: {} milliseconds", sleepTime);
+                    Thread.sleep(sleepTime); // milliseconds
+                }
+                catch (InterruptedException ex2) {
+                    // Ignore this exception because this exception is just about `sleep`.
+                    log.warn(ex2.getMessage(), ex2);
+                }
+                log.warn("retrying to connect sftp server: " + count + " times");
+            }
+            finally {
+                if (manager != null) {
+                    manager.close();
+                }
+            }
+        }
+    }
+
+    private static void addFileToList(ImmutableList.Builder<String> builder, String fileName, String basename)
+    {
+        if (!basename.isEmpty()) {
+            String remoteBasename = FilenameUtils.getBaseName(fileName);
+            if (remoteBasename.startsWith(basename)) {
+                builder.add(fileName);
+                log.info("add file to the request list: {}", fileName);
+            }
+        }
+        else {
+            builder.add(fileName);
+            log.info("add file to the request list: {}", fileName);
+        }
+    }
+
+    private static Function<LocalFile, String> localFileToPathString()
+    {
+        return new Function<LocalFile, String>()
+        {
+            public String apply(LocalFile file)
+            {
+                return file.getPath().toString();
+            }
+        };
+    }
+}