dongjoon-hyun commented on a change in pull request #24851: [SPARK-27303][GRAPH] Add Spark Graph API URL: https://github.com/apache/spark/pull/24851#discussion_r334569158
########## File path: graph/api/src/main/scala/org/apache/spark/graph/api/CypherSession.scala ########## @@ -0,0 +1,285 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.graph.api + +import scala.collection.JavaConverters._ + +import org.slf4j.LoggerFactory + +import org.apache.spark.annotation.Evolving +import org.apache.spark.sql.{Dataset, Row, SparkSession} +import org.apache.spark.sql.types.{BooleanType, StructType} + +/** + * Contains constants used for convention based column naming. + */ +@Evolving +object CypherSession { + + /** + * Naming convention for identifier columns, both node and relationship identifiers. + */ + val ID_COLUMN = "$ID" + + /** + * Naming convention for relationship source identifier. + */ + val SOURCE_ID_COLUMN = "$SOURCE_ID" + + /** + * Naming convention for relationship target identifier. + */ + val TARGET_ID_COLUMN = "$TARGET_ID" + + /** + * Naming convention both for node label and relationship type prefixes. + */ + val LABEL_COLUMN_PREFIX = ":" + + /** + * Extracts [[NodeDataset]]s from a [[Dataset]] using column name conventions. + * + * For information about naming conventions, see [[CypherSession.createGraph]]. + * + * @param nodes node dataset + * @since 3.0.0 + */ + def extractNodeDataset(nodes: Dataset[Row]): Set[NodeDataset] = { + val labelColumns = nodes.columns.filter(_.startsWith(LABEL_COLUMN_PREFIX)).toSet + validateLabelColumns(nodes.schema, labelColumns) + + val nodeProperties = (nodes.columns.toSet - ID_COLUMN -- labelColumns) + .map(col => col -> col) + .toMap + + val labelCount = labelColumns.size + if (labelCount > 5) { + LoggerFactory.getLogger(CypherSession.getClass).warn( + s"$labelCount label columns will result in ${Math.pow(labelCount, 2)} node frames.") + if (labelCount > 10) { + throw new IllegalArgumentException( + s"Expected number of label columns to be less than or equal to 10, was $labelCount.") + } + } + + val labelSets = labelColumns.subsets().toSet + + labelSets.map { labelSet => + val predicate = labelColumns + .map { labelColumn => + if (labelSet.contains(labelColumn)) { + nodes.col(labelColumn) + } else { + !nodes.col(labelColumn) + } + } + .reduce(_ && _) + + NodeDataset(nodes.filter(predicate), ID_COLUMN, labelSet.map(_.substring(1)), nodeProperties) + } + } + + /** + * Extracts [[RelationshipDataset]]s from a [[Dataset]] using column name conventions. + * + * For information about naming conventions, see [[CypherSession.createGraph]]. + * + * @param relationships relationship dataset + * @since 3.0.0 + */ + def extractRelationshipDataset(relationships: Dataset[Row]): Set[RelationshipDataset] = { Review comment: +1 for your suggestion, `extractRelationshipDataset` -> `extractRelationshipDatasets`. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
