embulk-input-bigquery_extract_files 0.0.3

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" "$@"

data/gradlew.bat

@@ -0,0 +1,84 @@
+@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
+
+set DIRNAME=%~dp0
+if "%DIRNAME%" == "" set DIRNAME=.
+set APP_BASE_NAME=%~n0
+set APP_HOME=%DIRNAME%
+
+@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=
+
+@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 Windows variants
+
+if not "%OS%" == "Windows_NT" goto win9xME_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=%*
+
+: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/bigquery_extract_files.rb

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

data/src/main/java/org/embulk/input/bigquery_export_gcs/BigqueryExportGcsFileInputPlugin.java

@@ -0,0 +1,340 @@
+package org.embulk.input.bigquery_export_gcs;
+
+import java.io.File;
+import java.io.IOException;
+import java.io.InputStream;
+import java.nio.file.Path;
+import java.util.List;
+
+import org.codehaus.plexus.util.StringUtils;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigDiff;
+import org.embulk.config.ConfigInject;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.Task;
+import org.embulk.config.TaskReport;
+import org.embulk.config.TaskSource;
+import org.embulk.exec.ConfigurableGuessInputPlugin;
+import org.embulk.exec.GuessExecutor;
+import org.embulk.spi.BufferAllocator;
+import org.embulk.spi.Exec;
+import org.embulk.spi.FileInputPlugin;
+import org.embulk.spi.Schema;
+import org.embulk.spi.TransactionalFileInput;
+import org.embulk.spi.util.InputStreamTransactionalFileInput;
+import org.slf4j.Logger;
+
+import com.google.api.services.bigquery.Bigquery;
+import com.google.common.base.Optional;
+
+import io.airlift.slice.RuntimeIOException;
+
+/**
+ * 
+ * 
+ * 
+ * #reference : 
+ * 
+ * # https://github.com/embulk/embulk
+ * # https://github.com/embulk/embulk-input-s3
+ * # https://github.com/embulk/embulk-input-gcs
+ * # https://github.com/embulk/embulk-input-jdbc
+ * # https://github.com/GoogleCloudPlatform/java-docs-samples/blob/master/storage/json-api/src/main/java/StorageSample.java
+ * 
+ * 
+ * @author george 2017. 11. 16.
+ *
+ */
+public class BigqueryExportGcsFileInputPlugin
+        implements FileInputPlugin, ConfigurableGuessInputPlugin
+{
+	private static final Logger log = Exec.getLogger(BigqueryExportGcsFileInputPlugin.class);
+	
+    public interface PluginTask
+            extends Task
+    {
+        @Config("project")
+        public String getProject();
+
+        @Config("json_keyfile")
+        public String getJsonKeyfile();
+        
+        @Config("dataset")
+        @ConfigDefault("null")
+        public Optional<String> getDataset();
+        
+        @Config("table")
+        @ConfigDefault("null")
+        public Optional<String> getTable();
+        
+        @Config("query")
+        @ConfigDefault("null")
+        public Optional<String> getQuery();
+        
+        @Config("file_format")
+        @ConfigDefault("\"CSV\"")
+        public Optional<String> getFileFormat();
+        
+        @Config("compression")
+        @ConfigDefault("\"GZIP\"")
+        public Optional<String> getCompression();
+
+        @Config("gcs_uri")
+        public String getGcsUri();
+
+        @Config("temp_dataset")
+        @ConfigDefault("null")
+        public Optional<String> getTempDataset();
+        public void setTempDataset(Optional<String> tempDataset);
+        
+        @Config("temp_table")
+        @ConfigDefault("null")
+        public Optional<String> getTempTable();
+        public void setTempTable(Optional<String> tempTable);
+
+        @Config("cache")
+        @ConfigDefault("true")
+        public boolean getQueryCache();
+
+        @Config("use_legacy_sql")
+        @ConfigDefault("false")
+        public boolean getUseLegacySql(); 
+
+        @Config("create_disposition")
+        @ConfigDefault("\"CREATE_IF_NEEDED\"")
+        public String getCreateDisposition();
+        
+        @Config("write_disposition")
+        @ConfigDefault("\"WRITE_APPEND\"")
+        public String getWriteDisposition();
+
+        @Config("temp_local_path")
+        public String getTempLocalPath();
+        
+        @Config("temp_schema_file_path")
+        @ConfigDefault("null")
+        public Optional<String> getTempSchemaFilePath();
+        
+        @Config("temp_schema_file_tpye")
+        @ConfigDefault("null")
+        public Optional<String> getTempSchemaFileType();
+        
+        
+        @Config("cleanup_gcs_files")
+        @ConfigDefault("false")
+        public boolean getCleanupGcsTempFile(); 
+        
+        @Config("cleanup_temp_table")
+        @ConfigDefault("true")
+        public boolean getCleanupTempTable(); 
+        
+        public List<String> getFiles();
+        public void setFiles(List<String> files);
+
+        @ConfigInject
+        public BufferAllocator getBufferAllocator();
+        
+        public String getGcsBucket();
+        public void setGcsBucket(String bucket);
+        
+        public String getGcsBlobNamePrefix();
+        public void setGcsBlobNamePrefix(String blobName);
+
+        public String getWorkDataset();
+        public void setWorkDataset(String dataset);
+        
+        public String getWorkTable();
+        public void setWorkTable(String table);
+
+        public String getWorkId();
+        public void setWorkId(String temp);
+        
+        //public Schema getSchemaConfig();
+        //public void setSchameConfig(SchemaConfig schema);
+    }
+    
+    @Override
+	public ConfigDiff guess(ConfigSource execConfig, ConfigSource inputConfig) {
+
+        GuessExecutor guessExecutor = Exec.getInjector().getInstance(GuessExecutor.class);
+        return guessExecutor.guessParserConfig(null, inputConfig, execConfig);
+	}
+
+	@Override
+    public ConfigDiff transaction(ConfigSource config, FileInputPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+
+        checkLocalPath(task);
+        
+        executeBigqueryApi(task);
+                
+        int taskCount = task.getFiles().size();
+
+        return resume(task.dump(), taskCount, control);
+    }
+	
+	public void checkLocalPath(PluginTask task){
+        File localPath = new File(task.getTempLocalPath());
+        if(localPath.exists() == false){
+        	log.error("local download path not exists : {}",localPath);
+        	log.info("create local downlaod path : {}", localPath);
+        	boolean ok = localPath.mkdirs();
+        	if(!ok){
+        		throw new RuntimeIOException(new IOException("local path create fail : " + localPath));
+        	}
+        }
+	}
+	
+	public void executeBigqueryApi(PluginTask task) {
+
+        BigqueryExportUtils.parseGcsUri(task);
+
+        Schema schema = extractBigqueryToGcs(task);
+        
+        log.info("Schema : {}",schema.toString());
+        
+        writeSchemaFileIfSpecified(schema, task);
+        
+        List<String> files = listFilesOfGcs(task);
+        
+        task.setFiles(files);
+        
+	}
+	
+	public void writeSchemaFileIfSpecified(Schema schema, PluginTask task) {
+		if(task.getTempSchemaFilePath().isPresent()) {
+			log.info("generate temp {} schema file to ... {}", task.getTempSchemaFileType().or(""), task.getTempSchemaFilePath().orNull());
+			BigqueryExportUtils.writeSchemaFile(schema, task.getTempSchemaFileType().orNull(), new File(task.getTempSchemaFilePath().get()));
+        }
+	}
+	
+    public Schema extractBigqueryToGcs(PluginTask task){
+    	try {
+    		Bigquery bigquery = BigqueryExportUtils.newBigqueryClient(task);
+    		
+    		// query init or execute query
+    		BigqueryExportUtils.initWorkTableWithExecuteQuery(bigquery,task);
+    		
+    		// extract table and get schema
+    		Schema schema = BigqueryExportUtils.extractWorkTable(bigquery, task);
+    		
+    		return schema;
+		} catch (IOException e) {
+			log.error("bigquery io error",e);
+			throw new RuntimeIOException(e);
+		} catch (InterruptedException e) {
+			log.error("bigquery job error",e);
+			throw new RuntimeException(e);
+		}
+    }
+    // usually, you have an method to create list of files
+    List<String> listFilesOfGcs(PluginTask task)
+    {
+    	log.info("get file list in to gcs of ... {}.{} -> gs://{}/{}", task.getDataset(), task.getWorkTable(),task.getGcsBucket(),task.getGcsBlobNamePrefix());
+    	
+    	try {
+			return BigqueryExportUtils.getFileListFromGcs(task);
+		} catch (IOException e) {
+			log.error("GCS api call error");
+			throw new RuntimeIOException(e);
+		}
+		
+    }
+    
+
+    @Override
+    public ConfigDiff resume(TaskSource taskSource,
+            int taskCount,
+            FileInputPlugin.Control control)
+    {
+        control.run(taskSource, taskCount);
+
+        ConfigDiff configDiff = Exec.newConfigDiff();
+        //configDiff.has(attrName)
+        
+        
+        // usually, yo uset last_path
+        //if (task.getFiles().isEmpty()) {
+        //    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<TaskReport> successTaskReports)
+    {
+    	final PluginTask task = taskSource.loadTask(PluginTask.class);
+    	
+    	// remove query temp table when exists 
+    	if(task.getCleanupTempTable() && 
+    			task.getTempTable().isPresent() && 
+    			task.getQuery().isPresent() && 
+    			task.getTempDataset().isPresent()){
+    		BigqueryExportUtils.removeTempTable(task);
+    	}
+    	
+    	for(int i=0; i < successTaskReports.size(); i++){
+    		TaskReport report = successTaskReports.get(i);
+    		if( report.isEmpty() ){
+    			String file = task.getFiles().get(i);
+    	    	
+    			Path p = BigqueryExportUtils.getFullPath(task,file);
+    			
+    			log.info("delete temp file...{}",p);
+    			p.toFile().delete();
+    	    	
+    			if(task.getCleanupGcsTempFile()){
+    				//TODO : delete temp file in gcs
+    				log.info("delete temp gcs file... {} ... not now... ", file);
+    			}
+    			
+    			//		
+    		}else{
+    			log.error("datasource not empty : {}", report);
+    		}
+    	}
+    	
+    }
+    
+
+    @Override
+    public TransactionalFileInput open(TaskSource taskSource, int taskIndex)
+    {
+        final PluginTask task = taskSource.loadTask(PluginTask.class);
+
+        // Write your code here :)
+        //throw new UnsupportedOperationException("BigquerycsvFileInputPlugin.open method is not implemented yet");
+
+        // if you expect InputStream, you can use this code:
+        
+        InputStream input = BigqueryExportUtils.openInputStream(task, task.getFiles().get(taskIndex));
+        
+        return new InputStreamTransactionalFileInput(task.getBufferAllocator(), input) {
+            @Override
+            public void abort()
+            { }
+        
+            @Override
+            public TaskReport commit()
+            {
+                return Exec.newTaskReport();
+            }
+        };
+    }
+    
+//////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+    
+}