增加两个 udf: Exploded StrToArray (#6)

lzshlzsh · web-flow · commit eeccb34fc73d · 2023-04-09T20:16:49.000+08:00
Add `Exploded` and `StrToArray` UDFs
diff --git a/README.md b/README.md
@@ -16,6 +16,8 @@ Flink 示例程序包（自定义函数 UDF、自定义 Source 和 Sink 等）
 3. PrintChar
 4. EnhancedSplitIndex
 5. ArrayAgg (示例参考 IntArrayAgg, RowArrayAgg1)
+6. Exploded
+7. StrToArray
 
 
 ## Sink 示例
diff --git a/src/main/java/com/tencent/cloud/oceanus/udf/Exploded.java b/src/main/java/com/tencent/cloud/oceanus/udf/Exploded.java
@@ -0,0 +1,24 @@
+package com.tencent.cloud.oceanus.udf;
+
+import org.apache.flink.table.annotation.DataTypeHint;
+import org.apache.flink.table.annotation.FunctionHint;
+import org.apache.flink.table.functions.TableFunction;
+import org.apache.flink.types.Row;
+
+/**
+ * 生成多行整数.
+ *
+ * <p>SQL 代码声明方式: CREATE TEMPORARY SYSTEM FUNCTION Exploded AS
+ * 'com.tencent.cloud.oceanus.udf.Exploded' LANGUAGE JAVA;
+ *
+ * <p>常用于数据倾斜时的数据打散，把小表数据复制 n 份。例如： CREATE VIEW v_small AS SELECT * FROM small, LATERAL
+ * TABLE(Exploded(50)) as t(`random_index`);
+ */
+@FunctionHint(output = @DataTypeHint("ROW<exploded_id int>"))
+public class Exploded extends TableFunction<Row> {
+    public void eval(Integer n) {
+        for (int i = 0; i < n; i++) {
+            collect(Row.of(i));
+        }
+    }
+}
diff --git a/src/main/java/com/tencent/cloud/oceanus/udf/StrToArray.java b/src/main/java/com/tencent/cloud/oceanus/udf/StrToArray.java
@@ -0,0 +1,22 @@
+package com.tencent.cloud.oceanus.udf;
+
+import org.apache.flink.table.functions.ScalarFunction;
+
+import org.apache.commons.lang3.StringUtils;
+
+/**
+ * 将 str 表示的字符串以 separator 指定的分隔符拆分，返回值拆分后的数组.
+ *
+ * <p>SQL 代码声明方式:：CREATE TEMPORARY SYSTEM FUNCTION STR_TO_ARRAY AS
+ * 'com.tencent.cloud.oceanus.udf.StrToArray' LANGUAGE JAVA;
+ *
+ * <p>注意相邻的分割符拆分出空字符串，例如 SELECT STR_TO_ARRAY('a,b,,c,d', ','); 返回 [a, b, , c, d].
+ */
+public class StrToArray extends ScalarFunction {
+    public String[] eval(String str, String separator) {
+        if (str == null) {
+            return null;
+        }
+        return StringUtils.splitByWholeSeparatorPreserveAllTokens(str, separator);
+    }
+}
