[Feature][ConnectorV2]add file excel sink

docs/en/connector-v2/sink/HdfsFile.md

@@ -19,6 +19,7 @@ By default, we use 2PC commit to ensure `exactly-once`
   - [x] parquet
   - [x] orc
   - [x] json
+  - [x] excel
 
 ## Options
 
@@ -59,7 +60,7 @@ Please note that, If `is_enable_transaction` is `true`, we will auto add `${tran
 
 We supported as the following file types:
 
-`text` `csv` `parquet` `orc` `json`
+`text` `csv` `parquet` `orc` `json` `excel`
 
 Please note that, The final file name will ends with the file_format's suffix, the suffix of the text file is `txt`.
 
@@ -86,6 +87,10 @@ The separator between columns in a row of data. Only needed by `text` and `csv`
 
 The separator between rows in a file. Only needed by `text` and `csv` file format.
 
+### max_rows_in_memory [int]
+
+When File Format is Excel,The maximum number of data items that can be cached in the memory.Note that you need to install fonts when using openjdk.
+
 ### partition_by [array]
 
 Partition data based on selected fields
@@ -180,6 +185,26 @@ HdfsFile {
 
 ```
 
+For excel file format
+
+```bash
+
+HdfsFile {
+    fs.defaultFS="hdfs://hadoopcluster"
+    path="/tmp/hive/warehouse/test2"
+    partition_by=["age"]
+    partition_dir_expression="${k0}=${v0}"
+    is_partition_field_write_in_file=true
+    file_name_expression="${transactionId}_${now}"
+    file_format="excel"
+    max_rows_in_memory=10000
+    sink_columns=["name","age"]
+    filename_time_format="yyyy.MM.dd"
+    is_enable_transaction=true
+}
+
+```
+
 ## Changelog
 
 ### 2.2.0-beta 2022-09-26

docs/en/connector-v2/sink/LocalFile.md

@@ -14,11 +14,11 @@ By default, we use 2PC commit to ensure `exactly-once`
 
 - [ ] [schema projection](../../concept/connector-v2-features.md)
 - [x] file format
-    - [x] text
-    - [x] csv
-    - [x] parquet
-    - [x] orc
-    - [x] json
+  - [x] text
+  - [x] csv
+  - [x] parquet
+  - [x] orc
+  - [x] json
 
 ## Options
 

seatunnel-connectors-v2/connector-file/connector-file-base/pom.xml

@@ -36,6 +36,8 @@
         <commons.lang3.version>3.4</commons.lang3.version>
         <flink.hadoop.version>2.7.5-7.0</flink.hadoop.version>
         <parquet-avro.version>1.12.3</parquet-avro.version>
+        <poi.version>4.1.2</poi.version>
+        <poi-ooxml.version>4.1.2</poi-ooxml.version>
     </properties>
 
     <dependencyManagement>
@@ -144,6 +146,17 @@
                 </exclusion>
             </exclusions>
         </dependency>
+        <dependency>
+            <groupId>org.apache.poi</groupId>
+            <artifactId>poi</artifactId>
+            <version>${poi.version}</version>
+        </dependency>
+
+        <dependency>
+            <groupId>org.apache.poi</groupId>
+            <artifactId>poi-ooxml</artifactId>
+            <version>${poi-ooxml.version}</version>
+        </dependency>
     </dependencies>
 
     <build>

seatunnel-connectors-v2/connector-file/connector-file-base/src/main/java/org/apache/seatunnel/connectors/seatunnel/file/config/Constant.java

@@ -39,4 +39,5 @@ public class Constant {
     public static final String SINK_COLUMNS = "sink_columns";
     public static final String FILENAME_TIME_FORMAT = "filename_time_format";
     public static final String IS_ENABLE_TRANSACTION = "is_enable_transaction";
+    public static final String MAX_ROWS_IN_MEMORY = "max_rows_in_memory";
 }

seatunnel-connectors-v2/connector-file/connector-file-base/src/main/java/org/apache/seatunnel/connectors/seatunnel/file/config/FileFormat.java

@@ -18,11 +18,13 @@
 package org.apache.seatunnel.connectors.seatunnel.file.config;
 
 import org.apache.seatunnel.connectors.seatunnel.file.sink.config.TextFileSinkConfig;
+import org.apache.seatunnel.connectors.seatunnel.file.sink.writer.ExcelWriteStrategy;
 import org.apache.seatunnel.connectors.seatunnel.file.sink.writer.JsonWriteStrategy;
 import org.apache.seatunnel.connectors.seatunnel.file.sink.writer.OrcWriteStrategy;
 import org.apache.seatunnel.connectors.seatunnel.file.sink.writer.ParquetWriteStrategy;
 import org.apache.seatunnel.connectors.seatunnel.file.sink.writer.TextWriteStrategy;
 import org.apache.seatunnel.connectors.seatunnel.file.sink.writer.WriteStrategy;
+import org.apache.seatunnel.connectors.seatunnel.file.source.reader.ExcelReadStrategy;
 import org.apache.seatunnel.connectors.seatunnel.file.source.reader.JsonReadStrategy;
 import org.apache.seatunnel.connectors.seatunnel.file.source.reader.OrcReadStrategy;
 import org.apache.seatunnel.connectors.seatunnel.file.source.reader.ParquetReadStrategy;
@@ -87,6 +89,17 @@ public WriteStrategy getWriteStrategy(TextFileSinkConfig textFileSinkConfig) {
         public ReadStrategy getReadStrategy() {
             return new JsonReadStrategy();
         }
+    },
+    EXCEL("xlsx") {
+        @Override
+        public WriteStrategy getWriteStrategy(TextFileSinkConfig textFileSinkConfig) {
+            return new ExcelWriteStrategy(textFileSinkConfig);
+        }
+
+        @Override
+        public ReadStrategy getReadStrategy() {
+            return new ExcelReadStrategy();
+        }
     };
 
     private final String suffix;

seatunnel-connectors-v2/connector-file/connector-file-base/src/main/java/org/apache/seatunnel/connectors/seatunnel/file/sink/config/TextFileSinkConfig.java

@@ -64,6 +64,8 @@ public class TextFileSinkConfig extends BaseTextFileConfig implements PartitionC
 
     private List<Integer> partitionFieldsIndexInRow;
 
+    private int maxRowsInMemory;
+
     public TextFileSinkConfig(@NonNull Config config, @NonNull SeaTunnelRowType seaTunnelRowTypeInfo) {
         super(config);
         checkArgument(!CollectionUtils.isEmpty(Arrays.asList(seaTunnelRowTypeInfo.getFieldNames())));
@@ -143,5 +145,9 @@ public TextFileSinkConfig(@NonNull Config config, @NonNull SeaTunnelRowType seaT
                 .map(columnsMap::get)
                 .collect(Collectors.toList());
         }
+
+        if (config.hasPath(Constant.MAX_ROWS_IN_MEMORY)) {
+            this.maxRowsInMemory = config.getInt(Constant.MAX_ROWS_IN_MEMORY);
+        }
     }
 }