Add support for YAML import specifications

README.md

@@ -7,7 +7,7 @@
 This library provides a uniform configuration facade for tools running imports to Neo4j.
 In particular, it offers:
 
- - a user-friendly configuration surface, backed by a JSON schema
+ - a user-friendly configuration surface (in JSON or YAML), called import specification, backed by a JSON schema
  - the Java equivalent of the import specification, a.k.a. `org.neo4j.importer.v1.ImportSpecification`
  - validation plugins (soon)
  - pre-processing plugins (soon)

pom.xml

@@ -37,6 +37,13 @@
     </properties>
     <dependencyManagement>
         <dependencies>
+            <dependency>
+                <groupId>com.fasterxml.jackson</groupId>
+                <artifactId>jackson-bom</artifactId>
+                <version>2.16.1</version>
+                <type>pom</type>
+                <scope>import</scope>
+            </dependency>
             <dependency>
                 <groupId>org.junit</groupId>
                 <artifactId>junit-bom</artifactId>
@@ -54,6 +61,10 @@
         </dependencies>
     </dependencyManagement>
     <dependencies>
+        <dependency>
+            <groupId>com.fasterxml.jackson.dataformat</groupId>
+            <artifactId>jackson-dataformat-yaml</artifactId>
+        </dependency>
         <dependency>
             <groupId>com.networknt</groupId>
             <artifactId>json-schema-validator</artifactId>
@@ -215,7 +226,6 @@
             </plugin>
         </plugins>
     </build>
-
     <profiles>
         <profile>
             <id>licensing</id>

src/main/java/org/neo4j/importer/v1/ImportSpecificationDeserializer.java

@@ -17,13 +17,13 @@
 package org.neo4j.importer.v1;
 
 import com.fasterxml.jackson.databind.MapperFeature;
-import com.fasterxml.jackson.databind.json.JsonMapper;
+import com.fasterxml.jackson.dataformat.yaml.YAMLMapper;
 import java.io.IOException;
 import java.io.Reader;
 
 public class ImportSpecificationDeserializer {
 
-    private static final JsonMapper MAPPER = JsonMapper.builder()
+    private static final YAMLMapper MAPPER = YAMLMapper.builder()
             .enable(MapperFeature.ACCEPT_CASE_INSENSITIVE_ENUMS)
             .build();
 

src/test/java/org/neo4j/importer/v1/e2e/AdminImportIT.java

@@ -37,7 +37,8 @@
 import java.util.function.Function;
 import org.junit.jupiter.api.AfterEach;
 import org.junit.jupiter.api.BeforeEach;
-import org.junit.jupiter.api.Test;
+import org.junit.jupiter.params.ParameterizedTest;
+import org.junit.jupiter.params.provider.ValueSource;
 import org.neo4j.driver.AuthTokens;
 import org.neo4j.driver.Driver;
 import org.neo4j.driver.GraphDatabase;
@@ -75,7 +76,8 @@ public class AdminImportIT {
 
     private static final String TARGET_DATABASE = "northwind";
     private static final String JDBC_POSTGRES_URL =
-            "jdbc:tc:postgresql:15.5-alpine:///%s?TC_INITSCRIPT=e2e/northwind_pg_dump.sql".formatted(TARGET_DATABASE);
+            "jdbc:tc:postgresql:15.5-alpine:///%s?TC_INITSCRIPT=e2e/admin-import/northwind_pg_dump.sql"
+                    .formatted(TARGET_DATABASE);
 
     private Driver neo4jDriver;
 
@@ -95,9 +97,11 @@ void cleanUp() {
      * This is **not** production-ready.
      * This only serves as a proof that the spec format is descriptive enough to run neo4j-admin imports.
      */
-    @Test
-    void runs_import() throws Exception {
-        var importSpec = read("/e2e/spec.json", ImportSpecificationDeserializer::deserialize);
+    @ParameterizedTest
+    @ValueSource(strings = {"json", "yaml"})
+    void runs_import(String extension) throws Exception {
+        var importSpec =
+                read("/e2e/admin-import/spec.%s".formatted(extension), ImportSpecificationDeserializer::deserialize);
         Map<String, Source> sources =
                 importSpec.getSources().stream().collect(toMap(Source::getName, Function.identity()));
         File csvFolder = csvFolderPathFor("/e2e/admin-import");
@@ -118,26 +122,30 @@ void runs_import() throws Exception {
             Neo4jAdmin.writeData(csvFolder, relationshipTarget, nodeTargets, SourceExecutor.read(source));
         }
         // note: custom query targets are ignored for now
+        var targetNeo4jDatabase = "%s-from-%s".formatted(TARGET_DATABASE, extension);
 
-        Neo4jAdmin.executeImport(NEO4J, neo4jDriver, importSpec, TARGET_DATABASE);
+        Neo4jAdmin.executeImport(NEO4J, neo4jDriver, importSpec, targetNeo4jDatabase);
 
         var productCount = neo4jDriver
                 .executableQuery("MATCH (p:Product) RETURN count(p) AS count")
-                .withConfig(QueryConfig.builder().withDatabase(TARGET_DATABASE).build())
+                .withConfig(
+                        QueryConfig.builder().withDatabase(targetNeo4jDatabase).build())
                 .execute()
                 .records();
         assertThat(productCount).hasSize(1);
         assertThat(productCount.getFirst().get("count").asLong()).isEqualTo(77L);
         var categoryCount = neo4jDriver
                 .executableQuery("MATCH (c:Category) RETURN count(c) AS count")
-                .withConfig(QueryConfig.builder().withDatabase(TARGET_DATABASE).build())
+                .withConfig(
+                        QueryConfig.builder().withDatabase(targetNeo4jDatabase).build())
                 .execute()
                 .records();
         assertThat(categoryCount).hasSize(1);
         assertThat(categoryCount.getFirst().get("count").asLong()).isEqualTo(8L);
         var productInCategoryCount = neo4jDriver
                 .executableQuery("MATCH (:Product)-[btc:BELONGS_TO_CATEGORY]->(:Category) RETURN count(btc) AS count")
-                .withConfig(QueryConfig.builder().withDatabase(TARGET_DATABASE).build())
+                .withConfig(
+                        QueryConfig.builder().withDatabase(targetNeo4jDatabase).build())
                 .execute()
                 .records();
         assertThat(productInCategoryCount).hasSize(1);

src/test/resources/e2e/admin-import/spec.yaml

@@ -0,0 +1,51 @@
+sources:
+  - name: "products"
+    type: "jdbc"
+    data_source: "northwind"
+    query: "SELECT productname, unitprice FROM products ORDER BY productname ASC"
+  - name: "categories"
+    type: "jdbc"
+    data_source: "northwind"
+    query: "SELECT categoryname, description FROM categories ORDER BY categoryname ASC"
+  - name: "products_in_categories"
+    type: "jdbc"
+    data_source: "northwind"
+    query: "SELECT p.productname AS productname, c.categoryname AS categoryname FROM products p NATURAL JOIN categories c ORDER BY p.productname ASC "
+targets:
+  nodes:
+    - source: "products"
+      name: "product_nodes"
+      labels:
+        - "Product"
+      properties:
+        - source_field: "productname"
+          target_property: "name"
+        - source_field: "unitprice"
+          target_property: "unitPrice"
+      schema:
+        key_constraints:
+          - name: "name_key_constraint"
+            label: "Product"
+            properties:
+              - "name"
+    - source: "categories"
+      name: "category_nodes"
+      labels:
+        - "Category"
+      properties:
+        - source_field: "categoryname"
+          target_property: "name"
+        - source_field: "description"
+          target_property: "description"
+      schema:
+        key_constraints:
+          - name: "name_key_constraint"
+            label: "Category"
+            properties:
+              - "name"
+  relationships:
+    - source: "products_in_categories"
+      name: "product_in_category_relationships"
+      type: "BELONGS_TO_CATEGORY"
+      start_node_reference: "product_nodes"
+      end_node_reference: "category_nodes"