Adding an example table schema to showcase mapping (#99)

Co-authored-by: Madhavan Sridharan <[email protected]>

Author: msmygit

pom.xml

@@ -8,7 +8,7 @@
 
   <properties>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
-    <revision>3.2.2</revision>
+    <revision>3.2.3</revision>
     <scala.version>2.12.17</scala.version>
     <scala.main.version>2.12</scala.main.version>
     <spark.version>3.3.1</spark.version>

src/resources/sparkConf.properties

@@ -68,10 +68,32 @@ spark.query.types                                 9,1,4,3
 
 # The tool adds TTL & Writetime at row-level (not field-level).
 # The largest TTL & Writetime values are used if multiple indexes are listed (comma separated)
-# Comma separated column indexes from "spark.query.origin" used to find largest TTL or Writetime
+# Comma separated column indexes from "spark.query.origin" used to find largest TTL or Writetime. This is zero-based index which starts at 0
+# Primary keys (partition & clustering) will not have TTLs/writetimes. Also, we don't use collection columns here for pulling TTL/writetime.
 spark.query.ttl.cols                              2,3
 spark.query.writetime.cols                        2,3
 
+############################### EXAMPLE MAPPING USING A DEMO TABLE ##########################################
+# If the origin and target clusters have a schema such as below,
+# CREATE TABLE cycling.cyclist_name (
+#     pk1 uuid,
+#     pk2 date,
+#     cc1 boolean,
+#     firstname text,
+#     lastname text,
+#     phones list<text>,
+#     PRIMARY KEY((pk1,pk2),cc1)
+# );
+# 
+# then, our mapping would look like below,
+# spark.query.origin                                pk1,pk2,cc1,firstname,lastname,phones
+# spark.query.origin.partitionKey                   pk1,pk2
+# spark.query.target.id                             pk1,pk2,cc1
+# spark.query.types                                 9,15,10,0,0,6%0
+# spark.query.ttl.cols                              3,4
+# spark.query.writetime.cols                        3,4
+#############################################################################################################
+
 # ENABLE ONLY IF YOU WANT TO MIGRATE/VALIDATE ROWS BASED ON CQL FILTER
 #spark.query.condition