apache · acezen · Jun 7, 2024 · Jun 7, 2024 · Jun 7, 2024 · Jun 7, 2024
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -97,8 +97,7 @@ For small or first-time contributions, we recommend the dev container method. An
 ### Using a dev container environment
 
 GraphAr provides a pre-configured [dev container](https://containers.dev/)
-that could be used in [GitHub Codespaces](https://github.com/features/codespaces),
-[VSCode](https://code.visualstudio.com/docs/devcontainers/containers), [JetBrains](https://www.jetbrains.com/remote-development/gateway/),
+that could be used in [VSCode](https://code.visualstudio.com/docs/devcontainers/containers), [JetBrains](https://www.jetbrains.com/remote-development/gateway/),
 [JupyterLab](https://jupyterlab.readthedocs.io/en/stable/).
 Please pick up your favorite runtime environment.
 
@@ -107,6 +106,10 @@ Please pick up your favorite runtime environment.
 Different components of GraphAr may require different setup steps. Please refer to their respective `README` documentation for more details.
 
 - [C++ Library](cpp/README.md)
-- [Java Library](java/README.md)
-- [Spark Library](spark/README.md)
-- [PySpark Library](pyspark/README.md)
+- [Scala with Spark Library](spark/README.md)
+- [Python with PySpark Library](pyspark/README.md) (under development)
+- [Java Library](java/README.md) (under development)
+
+----
+
+This doc refer from [Apache OpenDAL](https://opendal.apache.org/)
diff --git a/README.md b/README.md
@@ -207,24 +207,29 @@ See [GraphAr C++
 Library](./cpp) for
 details about the building of the C++ library.
 
+
+### The Scala with Spark Library
+
+See [GraphAr Spark
+Library](./maven-projects/spark)
+for details about the Scala with Spark library.
+
 ### The Java Library
 
+The Java library is under development. 
+
 The GraphAr Java library is created with bindings to the C++ library
 (currently at version v0.10.0), utilizing
 [Alibaba-FastFFI](https://github.com/alibaba/fastFFI) for
 implementation. See [GraphAr Java
 Library](./maven-projects/java) for
 details about the building of the Java library.
 
-### The Spark Library
-
-See [GraphAr Spark
-Library](./maven-projects/spark)
-for details about the Spark library.
+### The Python with PySpark Library
 
-### The PySpark Library
+The Python with PySpark library is under development.
 
-The GraphAr PySpark library is developed as bindings to the GraphAr
+The PySpark library is developed as bindings to the GraphAr
 Spark library. See [GraphAr PySpark
 Library](./pyspark)
 for details about the PySpark library.

diff --git a/cpp/CMakeLists.txt b/cpp/CMakeLists.txt
@@ -32,8 +32,8 @@ if (CMAKE_VERSION VERSION_GREATER_EQUAL "3.24.0")
 endif()
 
 set(GRAPHAR_MAJOR_VERSION 0)
-set(GRAPHAR_MINOR_VERSION 11)
-set(GRAPHAR_PATCH_VERSION 4)
+set(GRAPHAR_MINOR_VERSION 12)
+set(GRAPHAR_PATCH_VERSION 0)
 set(GREAPHAR_VERSION ${GRAPHAR_MAJOR_VERSION}.${GRAPHAR_MINOR_VERSION}.${GRAPHAR_PATCH_VERSION})
 project(graphar-cpp LANGUAGES C CXX VERSION ${GREAPHAR_VERSION})
 

diff --git a/cpp/README.md b/cpp/README.md
@@ -67,9 +67,7 @@ repository and navigated to the ``cpp`` subdirectory with:
 
 ```bash
     $ git clone https://github.com/apache/graphar.git
-    $ cd graphar
-    $ git submodule update --init
-    $ cd cpp
+    $ cd graphar/cpp
 ```
 
 Release build:

diff --git a/cpp/test/test_arrow_chunk_reader.cc b/cpp/test/test_arrow_chunk_reader.cc
@@ -158,8 +158,7 @@ TEST_CASE_METHOD(GlobalFixture, "ArrowChunkReader") {
                       << '\n';
             std::cout << "Column Nums: " << table->num_columns() << "\n";
             std::cout << "Column Names: ";
-            for (int i = 0;
-                 i < table->num_columns() && i < expected_cols.size(); i++) {
+            for (int i = 0; i < table->num_columns(); i++) {
               REQUIRE(table->ColumnNames()[i] == expected_cols[i]);
               std::cout << "`" << table->ColumnNames()[i] << "` ";
             }

diff --git a/maven-projects/info/pom.xml b/maven-projects/info/pom.xml
@@ -34,6 +34,7 @@
 
     <artifactId>info</artifactId>
     <packaging>jar</packaging>
+    <version>0.13.0.dev-SNAPSHOT</version>
 
     <name>info</name>
 

diff --git a/maven-projects/java/README.md b/maven-projects/java/README.md
@@ -1,4 +1,4 @@
-# GraphAr Java
+# GraphAr Java (under development)
 
 This directory contains the code and build system for the GraphAr Java library which powered by [Alibaba-FastFFI](https://github.com/alibaba/fastFFI).
 

diff --git a/maven-projects/java/pom.xml b/maven-projects/java/pom.xml
@@ -34,6 +34,7 @@
 
     <artifactId>java</artifactId>
     <packaging>jar</packaging>
+    <version>0.13.0.dev-SNAPSHOT</version>
 
     <name>java</name>
 

diff --git a/maven-projects/pom.xml b/maven-projects/pom.xml
@@ -69,7 +69,7 @@
         <url>https://github.com/apache/graphar</url>
     </scm>-->
     <properties>
-        <graphar.version>0.1.0-SNAPSHOT</graphar.version>
+        <graphar.version>0.12.0-SNAPSHOT</graphar.version>
     </properties>
     <modules>
         <module>java</module>

diff --git a/maven-projects/spark/README.md b/maven-projects/spark/README.md
@@ -21,8 +21,7 @@ repository and navigated to the ``spark`` subdirectory:
 ```bash
     $ git clone https://github.com/apache/incubator-graphar.git
     $ cd incubator-graphar
-    $ git submodule update --init
-    $ cd maven-projects/spark
+    $ cd mavens-projects/spark
 ```
 
 

diff --git a/maven-projects/spark/graphar/pom.xml b/maven-projects/spark/graphar/pom.xml
@@ -32,6 +32,7 @@
     </parent>
 
     <artifactId>graphar-commons</artifactId>
+    <version>${graphar.version}</version>
     <packaging>jar</packaging>
 
     <dependencies>

diff --git a/maven-projects/spark/import/neo4j.sh b/maven-projects/spark/import/neo4j.sh
@@ -20,7 +20,7 @@
 set -eu
 
 cur_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-jar_file="${cur_dir}/../graphar/target/graphar-commons-0.1.0-SNAPSHOT-shaded.jar"
+jar_file="${cur_dir}/../graphar/target/graphar-commons-0.12.0-SNAPSHOT-shaded.jar"
 conf_path="$(readlink -f $1)"
 
 spark-submit --class org.apache.graphar.importer.Neo4j ${jar_file} \

diff --git a/maven-projects/spark/pom.xml b/maven-projects/spark/pom.xml
@@ -33,6 +33,7 @@
 
     <artifactId>spark</artifactId>
     <packaging>pom</packaging>
+    <version>${graphar.version}</version>
 
     <profiles>
         <profile>

diff --git a/maven-projects/spark/scripts/run-graphar2nebula.sh b/maven-projects/spark/scripts/run-graphar2nebula.sh
@@ -20,7 +20,7 @@
 set -eu
 
 cur_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-jar_file="${cur_dir}/../graphar/target/graphar-commons-0.1.0-SNAPSHOT-shaded.jar"
+jar_file="${cur_dir}/../graphar/target/graphar-commons-0.12.0-SNAPSHOT-shaded.jar"
 
 graph_info_path="${GRAPH_INFO_PATH:-/tmp/graphar/nebula2graphar/basketballplayergraph.graph.yml}"
 spark-submit --class org.apache.graphar.example.GraphAr2Nebula ${jar_file} \

diff --git a/maven-projects/spark/scripts/run-graphar2neo4j.sh b/maven-projects/spark/scripts/run-graphar2neo4j.sh
@@ -21,7 +21,7 @@
 set -eu
 
 cur_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-jar_file="${cur_dir}/../graphar/target/graphar-commons-0.1.0-SNAPSHOT-shaded.jar"
+jar_file="${cur_dir}/../graphar/target/graphar-commons-0.12.0-SNAPSHOT-shaded.jar"
 
 graph_info_path="${GRAPH_INFO_PATH:-/tmp/graphar/neo4j2graphar/MovieGraph.graph.yml}"
 spark-submit --class org.apache.graphar.example.GraphAr2Neo4j ${jar_file} \

diff --git a/maven-projects/spark/scripts/run-ldbc-sample2graphar.sh b/maven-projects/spark/scripts/run-ldbc-sample2graphar.sh
@@ -21,7 +21,7 @@
 set -eu
 
 cur_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-jar_file="${cur_dir}/../graphar/target/graphar-commons-0.1.0-SNAPSHOT-shaded.jar"
+jar_file="${cur_dir}/../graphar/target/graphar-commons-0.12.0-SNAPSHOT-shaded.jar"
 person_input_file="${GAR_TEST_DATA}/ldbc_sample/person_0_0.csv"
 person_knows_person_input_file="${GAR_TEST_DATA}/ldbc_sample/person_knows_person_0_0.csv"
 output_dir="/tmp/graphar/ldbc_sample"

diff --git a/maven-projects/spark/scripts/run-nebula2graphar.sh b/maven-projects/spark/scripts/run-nebula2graphar.sh
@@ -20,7 +20,7 @@
 set -eu
 
 cur_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-jar_file="${cur_dir}/../graphar/target/graphar-commons-0.1.0-SNAPSHOT-shaded.jar"
+jar_file="${cur_dir}/../graphar/target/graphar-commons-0.12.0-SNAPSHOT-shaded.jar"
 
 vertex_chunk_size=100
 edge_chunk_size=1024

diff --git a/maven-projects/spark/scripts/run-neo4j2graphar.sh b/maven-projects/spark/scripts/run-neo4j2graphar.sh
@@ -21,7 +21,7 @@
 set -eu
 
 cur_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-jar_file="${cur_dir}/../graphar/target/graphar-commons-0.1.0-SNAPSHOT-shaded.jar"
+jar_file="${cur_dir}/../graphar/target/graphar-commons-0.12.0-SNAPSHOT-shaded.jar"
 
 vertex_chunk_size=100
 edge_chunk_size=1024

diff --git a/pyspark/README.md b/pyspark/README.md
@@ -1,4 +1,4 @@
-# GraphAr PySpark
+# GraphAr PySpark (under development)
 
 This directory contains the code and build system for the GraphAr PySpark library. Library is implemented as bindings to GraphAr Scala Spark library and does not contain any real logic.
 

diff --git a/pyspark/graphar_pyspark/__init__.py b/pyspark/graphar_pyspark/__init__.py
@@ -21,6 +21,7 @@
 
 from graphar_pyspark.errors import GraphArIsNotInitializedError
 
+__version__ = "0.13.0.dev"
 
 class _GraphArSession:
     """Singleton GraphAr helper object, that contains SparkSession and JVM.