Enable volume on data loading

.github/workflows/gss.yml

@@ -76,7 +76,7 @@ jobs:
         export RUSTC_WRAPPER=/usr/local/bin/sccache
         sccache --start-server
         cd ${GITHUB_WORKSPACE}/interactive_engine
-        mvn clean install -P groot,groot-assembly -Drust.compile.mode=debug -DskipTests -Dgroot.compile.feature="column_filter_push_down" --quiet
+        mvn clean install -P groot -Drust.compile.mode=debug -DskipTests -Dgroot.compile.feature="column_filter_push_down" --quiet
 
         sccache --show-stats
 
@@ -92,7 +92,7 @@ jobs:
         export SCCACHE_DIR=~/.cache/sccache
         export RUSTC_WRAPPER=/usr/local/bin/sccache
         cd ${GITHUB_WORKSPACE}/interactive_engine
-        mvn clean install -P groot,groot-assembly -Drust.compile.mode=debug -DskipTests --quiet
+        mvn clean install -P groot -Drust.compile.mode=debug -DskipTests --quiet
 
         sccache --show-stats
 

.github/workflows/k8s-ci.yml

@@ -692,7 +692,7 @@ jobs:
           minikube image load graphscope/learning:${SHORT_SHA}
 
           export PYTHONPATH=${GITHUB_WORKSPACE}/python:${PYTHONPATH}
-          cd ${GITHUB_WORKSPACE}/interactive_engine && mvn clean install --quiet -DskipTests -Drust.compile.skip=true -P graphscope,graphscope-assembly
+          cd ${GITHUB_WORKSPACE}/interactive_engine && mvn clean install --quiet -DskipTests -Drust.compile.skip=true -P graphscope
           cd ${GITHUB_WORKSPACE}/interactive_engine/tests
           # ./function_test.sh 8111 1
           ./function_test.sh 8112 2

Makefile

@@ -135,7 +135,7 @@ interactive: $(INTERACTIVE_DIR)/assembly/target/graphscope.tar.gz
 
 $(INTERACTIVE_DIR)/assembly/target/graphscope.tar.gz:
 	cd $(INTERACTIVE_DIR) && \
-	mvn package -DskipTests -Drust.compile.mode=$(BUILD_TYPE) -P graphscope,graphscope-assembly -Drevision=$(VERSION) --quiet
+	mvn package -DskipTests -Drust.compile.mode=$(BUILD_TYPE) -P graphscope -Drevision=$(VERSION) --quiet
 
 learning-install: learning
 	mkdir -p $(INSTALL_PREFIX)

interactive_engine/assembly/README.md

@@ -2,5 +2,5 @@
 This will build graphscope or groot into an assembly archive.
 
 # Usage
-`mvn package -P graphscope,graphscope-assembly` will generate a graphscope.tar.gz under `target/`.
-`mvn package -P groot,groot-assembly` will generate a groot.tar.gz under `target/`.
+`mvn package -P graphscope` will generate a graphscope.tar.gz under `target/`.
+`mvn package -P groot` will generate a groot.tar.gz under `target/`.

interactive_engine/assembly/groot.xml

@@ -1,7 +1,7 @@
 <assembly xmlns="http://maven.apache.org/ASSEMBLY/2.0.0"
           xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
           xsi:schemaLocation="http://maven.apache.org/ASSEMBLY/2.0.0 http://maven.apache.org/xsd/assembly-2.0.0.xsd">
-    <id>groot-assembly</id>
+    <id>groot</id>
     <formats>
         <format>tar.gz</format>
     </formats>

interactive_engine/assembly/pom.xml

@@ -20,7 +20,7 @@
       </activation>
     </profile>
     <profile>
-      <id>graphscope-assembly</id>
+      <id>graphscope</id>
       <build>
         <plugins>
           <plugin>
@@ -49,7 +49,7 @@
       </dependencies>
     </profile>
     <profile>
-      <id>groot-assembly</id>
+      <id>groot</id>
       <build>
         <plugins>
           <plugin>

interactive_engine/assembly/src/bin/groot/store_ctl.sh

@@ -2,9 +2,7 @@
 #
 # groot command tool
 
-set -x
-set -e
-set -o pipefail
+set -xeo pipefail
 
 usage() {
 cat <<END
@@ -20,7 +18,6 @@ cat <<END
 
     start_max_node                            start max_node of gaia
     start_server                              start individual groot server
-    start_load_tools                          start load_tools
 END
 }
 
@@ -91,12 +88,6 @@ start_max_node() {
        "$@" > >(tee -a "${LOG_DIR}/${LOG_NAME}.out") 2> >(tee -a "${LOG_DIR}/${LOG_NAME}.err" >&2)
 }
 
-start_load_tools() {
-  _setup_env
-  java -cp "${GROOT_HOME}/lib/data-load-tool-0.0.1-SNAPSHOT.jar" \
-       com.alibaba.graphscope.groot.dataload.LoadTool "$@"
-}
-
 # start groot server
 start_server() {
   _setup_env
@@ -138,13 +129,10 @@ while test $# -ne 0; do
     -h|--help) usage; exit ;;
     start_max_node) start_max_node "gaia" "$@"; exit;;
     start_server) start_server "$@"; exit;;
-    start_load_tools) start_load_tools "$@"; exit;;
     *)
       echo "unrecognized option or command '${arg}'"
       usage; exit;;
   esac
 done
 
-set +e
-set +o pipefail
-set +x
+set +xeo pipefail

interactive_engine/common/src/main/java/com/alibaba/graphscope/groot/common/config/DataLoadConfig.java

@@ -0,0 +1,67 @@
+package com.alibaba.graphscope.groot.common.config;
+
+public class DataLoadConfig {
+
+    // Get property
+
+    /** universal configurations **/
+    public static final String GRAPH_ENDPOINT = "graph.endpoint";
+
+    public static final String COLUMN_MAPPING_CONFIG = "column.mapping.config";
+
+    public static final String LOAD_AFTER_BUILD = "load.after.build";
+
+    public static final String SPLIT_SIZE = "split.size";
+
+    public static final String UNIQUE_PATH = "unique.path"; // generated automatically for each task
+    public static final String USER_NAME = "auth.username";
+    public static final String PASS_WORD = "auth.password";
+
+    /** job on HDFS configurations **/
+
+    // Input and output
+    public static final String INPUT_PATH = "input.path";
+
+    public static final String OUTPUT_PATH = "output.path";
+    public static final String SEPARATOR = "separator";
+    public static final String SKIP_HEADER = "skip.header";
+    public static final String LDBC_CUSTOMIZE = "ldbc.customize";
+    /* end */
+
+    /** job on ODPS configurations **/
+    public static final String DATA_SINK_TYPE = "data.sink.type"; // hdfs, oss, volume
+    // The table format is `project.table` or `table`;
+    // For partitioned table, the format is `project.table|p1=1/p2=2` or `table|p1=1/p2=2`
+    public static final String OUTPUT_TABLE = "output.table"; // a dummy table
+    /* end */
+
+    // Set property
+    public static final String SCHEMA_JSON = "schema.json";
+    public static final String COLUMN_MAPPINGS = "column.mappings";
+    public static final String META_INFO = "meta.info";
+
+    public static final String META_FILE_NAME = "META";
+
+    /** OSS configurations **/
+    public static final String OSS_ENDPOINT = "oss.endpoint";
+
+    public static final String OSS_ACCESS_ID = "oss.access.id";
+    public static final String OSS_ACCESS_KEY = "oss.access.key";
+
+    public static final String OSS_BUCKET_NAME = "oss.bucket.name";
+    public static final String OSS_OBJECT_NAME = "oss.object.name";
+    public static final String OSS_INFO_URL = "oss.info.url";
+    /* end */
+
+    /** ODPS Volume configurations **/
+    public static final String ODPS_VOLUME_PROJECT = "odps.volume.project";
+
+    public static final String ODPS_VOLUME_NAME = "odps.volume.name";
+    public static final String ODPS_VOLUME_PARTSPEC = "odps.volume.partspec";
+
+    public static final String ODPS_ACCESS_ID = "odps.access.id";
+    public static final String ODPS_ACCESS_KEY = "odps.access.key";
+    public static final String ODPS_ENDPOINT = "odps.endpoint";
+    /* end */
+
+}