From 5e8322ffe7e3ce66ae316b1cd1bfa63da8feddad Mon Sep 17 00:00:00 2001 From: liuxiao Date: Fri, 4 Aug 2023 01:02:19 +0800 Subject: [PATCH] fix: Spark Loader example schema and struct mismatch --- .../static/example/spark/schema.groovy | 6 +- .../static/example/spark/struct-hbase.json | 56 +++++++++++++++++++ .../assembly/static/example/spark/struct.json | 10 +--- .../static/example/spark/vertex_person.json | 12 ++-- .../static/example/spark/vertex_software.json | 4 +- 5 files changed, 68 insertions(+), 20 deletions(-) create mode 100644 hugegraph-loader/assembly/static/example/spark/struct-hbase.json diff --git a/hugegraph-loader/assembly/static/example/spark/schema.groovy b/hugegraph-loader/assembly/static/example/spark/schema.groovy index 3203d95f1..46126b888 100644 --- a/hugegraph-loader/assembly/static/example/spark/schema.groovy +++ b/hugegraph-loader/assembly/static/example/spark/schema.groovy @@ -26,13 +26,13 @@ schema.propertyKey("price").asDouble().ifNotExist().create(); schema.vertexLabel("person") .properties("name", "age", "city") - .primaryKeys("name") + .useCustomizeStringId() .nullableKeys("age", "city") .ifNotExist() .create(); schema.vertexLabel("software") - .properties("name", "lang", "price") - .primaryKeys("name") + .properties("name", "lang", "price") + .useCustomizeStringId() .ifNotExist() .create(); diff --git a/hugegraph-loader/assembly/static/example/spark/struct-hbase.json b/hugegraph-loader/assembly/static/example/spark/struct-hbase.json new file mode 100644 index 000000000..6b909ff35 --- /dev/null +++ b/hugegraph-loader/assembly/static/example/spark/struct-hbase.json @@ -0,0 +1,56 @@ +{ + "vertices": [ + { + "label": "person", + "input": { + "type": "file", + "path": "example/spark/vertex_person.json", + "format": "JSON", + "header": ["name", "age", "city"], + "charset": "UTF-8", + "skipped_line": { + "regex": "(^#|^//).*" + } + }, + "id": "name", + "null_values": ["NULL", "null", ""] + }, + { + "label": "software", + "input": { + "type": "file", + "path": "example/spark/vertex_software.json", + "format": "JSON", + "header": ["id","name", "lang", "price","ISBN"], + "charset": "GBK" + }, + "id": "name", + "ignored": ["ISBN"] + } + ], + "edges": [ + { + "label": "knows", + "source": ["source_name"], + "target": ["target_name"], + "input": { + "type": "file", + "path": "example/spark/edge_knows.json", + "format": "JSON", + "date_format": "yyyyMMdd", + "header": ["source_name","target_name", "date", "weight"] + }, + "field_mapping": { + "source_name": "name", + "target_name": "name" + } + } + ], + "backendStoreInfo": { + "edge_tablename": "hugegraph:g_oe", + "vertex_tablename": "hugegraph:g_v", + "hbase_zookeeper_quorum": "127.0.0.1", + "hbase_zookeeper_property_clientPort": "2181", + "zookeeper_znode_parent": "/hbase" + } +} diff --git a/hugegraph-loader/assembly/static/example/spark/struct.json b/hugegraph-loader/assembly/static/example/spark/struct.json index 275bdbd32..7f3b7e556 100644 --- a/hugegraph-loader/assembly/static/example/spark/struct.json +++ b/hugegraph-loader/assembly/static/example/spark/struct.json @@ -45,13 +45,5 @@ "target_name": "name" } } - ], - "backendStoreInfo": - { - "edge_tablename": "hugegraph:g_oe", - "vertex_tablename": "hugegraph:g_v", - "hbase_zookeeper_quorum": "127.0.0.1", - "hbase_zookeeper_property_clientPort": "2181", - "zookeeper_znode_parent": "/hbase" - } + ] } diff --git a/hugegraph-loader/assembly/static/example/spark/vertex_person.json b/hugegraph-loader/assembly/static/example/spark/vertex_person.json index e018df411..93e41a960 100644 --- a/hugegraph-loader/assembly/static/example/spark/vertex_person.json +++ b/hugegraph-loader/assembly/static/example/spark/vertex_person.json @@ -1,6 +1,6 @@ -{"name": "marko", "age": "29", "city": "Beijing"} -{"name": "vadas", "age": "27", "city": "Hongkong"} -{"name": "josh", "age": "32", "city": "Beijing"} -{"name": "peter", "age": "35", "city": "Shanghai"} -{"name": "li,nary", "age": "26", "city": "Wu,han"} -{"name": "tom", "age": "null", "city": "NULL"} +{"name": "marko", "age": "29", "city": "Beijing"} +{"name": "vadas", "age": "27", "city": "Hongkong"} +{"name": "josh", "age": "32", "city": "Beijing"} +{"name": "peter", "age": "35", "city": "Shanghai"} +{"name": "li,nary", "age": "26", "city": "Wu,han"} +{"name": "tom", "age": "null", "city": "NULL"} diff --git a/hugegraph-loader/assembly/static/example/spark/vertex_software.json b/hugegraph-loader/assembly/static/example/spark/vertex_software.json index cd9dbf3cb..5ee271d16 100644 --- a/hugegraph-loader/assembly/static/example/spark/vertex_software.json +++ b/hugegraph-loader/assembly/static/example/spark/vertex_software.json @@ -1,2 +1,2 @@ -{ "name": "lop", "lang": "java","price": "328","ISBN": "ISBN978-7-107-18618-5"} -{ "name": "ripple", "lang": "java","price": "199","ISBN": "ISBN978-7-100-13678-5"} +{"name": "lop", "lang": "java", "price": "328", "ISBN": "ISBN978-7-107-18618-5"} +{"name": "ripple", "lang": "java", "price": "199", "ISBN": "ISBN978-7-100-13678-5"}