This is an automated email from the ASF dual-hosted git repository.
weibin pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-graphar-testing.git
The following commit(s) were added to refs/heads/main by this push:
new 955596c change import config file (#27)
955596c is described below
commit 955596c325ceba7b607e285738e3dd0ce4ff424e
Author: Liu Jiajun <[email protected]>
AuthorDate: Thu Oct 31 07:26:16 2024 +0800
change import config file (#27)
* add import config file
* change import config file
---
neo4j/data/import.full.json | 214 --------------------------------------------
neo4j/data/import.full.yml | 138 ++++++++++++++++++++++++++++
neo4j/data/import.mini.json | 130 ---------------------------
neo4j/data/import.mini.yml | 71 +++++++++++++++
4 files changed, 209 insertions(+), 344 deletions(-)
diff --git a/neo4j/data/import.full.json b/neo4j/data/import.full.json
deleted file mode 100644
index 479c508..0000000
--- a/neo4j/data/import.full.json
+++ /dev/null
@@ -1,214 +0,0 @@
-{
- "graphar": {
- "path": "/workspaces/incubator-graphar/graphar/movie",
- "name": "MovieGraph",
- "vertex_chunk_size": 100,
- "edge_chunk_size": 1024,
- "file_type": "parquet",
- "adj_list_type": "ordered_by_source",
- "validate_level": "weak",
- "version": "gar/v1"
- },
- "import_schema": {
- "vertices": [
- {
- "type": "Person",
- "labels": [
- "Person"
- ],
- "chunk_size": 100,
- "validate_level": "no",
- "prefix": "vertex/Person/",
- "property_groups": [
- {
- "file_type": "parquet",
- "properties": [
- {
- "name": "name",
- "data_type": "string",
- "is_primary": true,
- "nullable": false
- },
- {
- "name": "born",
- "data_type": "int64",
- "is_primary": false,
- "nullable": true
- }
- ]
- }
- ],
- "sources": [
- {
- "file_type": "parquet",
- "path":
"/workspaces/incubator-graphar/testing/neo4j/data/Person.parquet",
- "columns": {
- "name": "name",
- "born": "born"
- }
- }
- ]
- },
- {
- "type": "Movie",
- "labels": [
- "Movie"
- ],
- "chunk_size": 100,
- "validate_level": "no",
- "prefix": "vertex/Movie/",
- "property_groups": [
- {
- "file_type": "parquet",
- "properties": [
- {
- "name": "title",
- "data_type": "string",
- "is_primary": true,
- "nullable": false
- },
- {
- "name": "tagline",
- "data_type": "string",
- "is_primary": false,
- "nullable": true
- }
- ]
- }
- ],
- "sources": [
- {
- "file_type": "orc",
- "path":
"/workspaces/incubator-graphar/testing/neo4j/data/Movie.orc",
- "columns": {
- "title": "title",
- "tagline": "tagline"
- }
- }
- ]
- }
- ],
- "edges": [
- {
- "edge_type": "WROTE",
- "src_type": "Person",
- "src_prop": "name",
- "dst_type": "Movie",
- "dst_prop": "title",
- "chunk_size": 1024,
- "validate_level": "no",
- "prefix": "edge/Person_WROTE_Movie/",
- "adj_lists": [
- {
- "ordered": true,
- "aligned_by": "src",
- "file_type": "parquet"
- },
- {
- "ordered": true,
- "aligned_by": "dst",
- "file_type": "parquet"
- }
- ],
- "sources": [
- {
- "file_type": "csv",
- "delimiter": ",",
- "path":
"/workspaces/incubator-graphar/testing/neo4j/data/Person_WROTE_Movie.csv",
- "columns": {
- "name": "name",
- "title": "title"
- }
- }
- ]
- },
- {
- "edge_type": "ACTED_IN",
- "src_type": "Person",
- "src_prop": "name",
- "dst_type": "Movie",
- "dst_prop": "title",
- "validate_level": "no",
- "chunk_size": 1024,
- "prefix": "edge/Person_ACTED_IN_Movie/",
- "adj_lists": [
- {
- "ordered": true,
- "aligned_by": "src",
- "file_type": "parquet"
- },
- {
- "ordered": true,
- "aligned_by": "dst",
- "file_type": "parquet"
- }
- ],
- "sources": [
- {
- "file_type": "json",
- "delimiter": ",",
- "path":
"/workspaces/incubator-graphar/testing/neo4j/data/Person_ACTED_IN_Movie.json",
- "columns": {
- "name": "name",
- "title": "title"
- }
- }
- ]
- },
- {
- "edge_type": "REVIEWED",
- "src_type": "Person",
- "src_prop": "name",
- "dst_type": "Movie",
- "dst_prop": "title",
- "chunk_size": 1024,
- "validate_level": "no",
- "prefix": "edge/Person_REVIEWED_Movie/",
- "property_groups": [
- {
- "file_type": "parquet",
- "properties": [
- {
- "name": "rating",
- "data_type": "int64",
- "is_primary": false,
- "nullable": true
- },
- {
- "name": "summary",
- "data_type": "string",
- "is_primary": false,
- "nullable": true
- }
- ]
- }
- ],
- "adj_lists": [
- {
- "ordered": true,
- "aligned_by": "src",
- "file_type": "parquet"
- },
- {
- "ordered": true,
- "aligned_by": "dst",
- "file_type": "parquet"
- }
- ],
- "sources": [
- {
- "file_type": "csv",
- "delimiter": ",",
- "path":
"/workspaces/incubator-graphar/testing/neo4j/data/Person_REVIEWED_Movie.csv",
- "columns": {
- "name": "name",
- "title": "title",
- "summary": "summary",
- "rating": "rating"
- }
- }
- ]
- }
- ]
- }
-}
\ No newline at end of file
diff --git a/neo4j/data/import.full.yml b/neo4j/data/import.full.yml
new file mode 100644
index 0000000..a4dbd71
--- /dev/null
+++ b/neo4j/data/import.full.yml
@@ -0,0 +1,138 @@
+graphar: # Global configuration
of imported data
+ path: /tmp/graphar/movie # (Required) Path to the
graphar directory
+ name: MovieGraph # (Required) Name of the
graph
+ vertex_chunk_size: 100 # Number of vertices per
chunk
+ edge_chunk_size: 1024 # Number of edges per
chunk
+ file_type: parquet # Default file type for
vertices and edges, can be "parquet", "orc", "csv", "json"
+ adj_list_type: ordered_by_source # Default adjacency list
type, can be "ordered_by_source", "ordered_by_dest", "unordered_by_source",
"unordered_by_dest"
+ validate_level: weak # Default validation
level for vertices and edges, can be "no", "weak", "strong"
+ version: gar/v1 # Version of the graphar
schema
+
+import_schema:
+ vertices:
+ - type: Person
+ labels:
+ - Person
+ chunk_size: 100
+ validate_level: "no"
+ prefix: vertex/Person/
+ property_groups:
+ - file_type: parquet
+ properties:
+ - name: name
+ data_type: string
+ is_primary: true
+ nullable: false
+ - name: born
+ data_type: int64
+ is_primary: false
+ nullable: true
+ sources:
+ - file_type: parquet
+ - path: ../testing/neo4j/data/Person.parquet
+ columns:
+ name: name
+ born: born
+ - type: Movie
+ labels:
+ - Movie
+ chunk_size: 100
+ validate_level: "no"
+ prefix: vertex/Movie/
+ property_groups:
+ - file_type: parquet
+ properties:
+ - name: title
+ data_type: string
+ is_primary: true
+ nullable: false
+ - name: tagline
+ data_type: string
+ is_primary: false
+ nullable: true
+ sources:
+ - file_type: orc
+ - path: ../testing/neo4j/data/Movie.orc
+ columns:
+ title: title
+ tagline: tagline
+ edges:
+ - edge_type: WROTE
+ src_type: Person
+ src_prop: name
+ dst_type: Movie
+ dst_prop: title
+ chunk_size: 1024
+ validate_level: "no"
+ prefix: edge/Person_WROTE_Movie/
+ adj_lists:
+ - ordered: true
+ aligned_by: src
+ file_type: parquet
+ - ordered: true
+ aligned_by: dst
+ file_type: parquet
+ sources:
+ - file_type: csv
+ delimiter: ","
+ path: ../testing/neo4j/data/Person_WROTE_Movie.csv
+ columns:
+ name: name
+ title: title
+ - edge_type: ACTED_IN
+ src_type: Person
+ src_prop: name
+ dst_type: Movie
+ dst_prop: title
+ validate_level: "no"
+ chunk_size: 1024
+ prefix: edge/Person_ACTED_IN_Movie/
+ adj_lists:
+ - ordered: true
+ aligned_by: src
+ file_type: parquet
+ - ordered: true
+ aligned_by: dst
+ file_type: parquet
+ sources:
+ - file_type: json
+ delimiter: "," # will be ignored
+ path: ../testing/neo4j/data/Person_ACTED_IN_Movie.json
+ columns:
+ name: name
+ title: title
+ - edge_type: REVIEWED
+ src_type: Person
+ src_prop: name
+ dst_type: Movie
+ dst_prop: title
+ chunk_size: 1024
+ validate_level: "no"
+ prefix: edge/Person_REVIEWED_Movie/
+ property_groups:
+ - file_type: parquet
+ properties:
+ - name: rating
+ data_type: int64
+ is_primary: false
+ nullable: true
+ - name: summary
+ data_type: string
+ is_primary: false
+ nullable: true
+ adj_lists:
+ - ordered: true
+ aligned_by: src
+ file_type: parquet
+ - ordered: true
+ aligned_by: dst
+ file_type: parquet
+ sources:
+ - file_type: csv
+ delimiter: ","
+ path: ../testing/neo4j/data/Person_REVIEWED_Movie.csv
+ columns:
+ name: name
+ title: title
+ summary: summary
+ rating: rating
diff --git a/neo4j/data/import.mini.json b/neo4j/data/import.mini.json
deleted file mode 100644
index 8d85c77..0000000
--- a/neo4j/data/import.mini.json
+++ /dev/null
@@ -1,130 +0,0 @@
-{
- "graphar": {
- "path": "/workspaces/incubator-graphar/graphar/movie",
- "name": "MovieGraph"
- },
- "import_schema": {
- "vertices": [
- {
- "type": "Person",
- "property_groups": [
- {
- "properties": [
- {
- "name": "name",
- "data_type": "string",
- "is_primary": true
- },
- {
- "name": "born",
- "data_type": "int64"
- }
- ]
- }
- ],
- "sources": [
- {
- "path":
"/workspaces/incubator-graphar/testing/neo4j/data/Person.parquet",
- "columns": {
- "name": "name",
- "born": "born"
- }
- }
- ]
- },
- {
- "type": "Movie",
- "property_groups": [
- {
- "properties": [
- {
- "name": "title",
- "data_type": "string",
- "is_primary": true
- },
- {
- "name": "tagline",
- "data_type": "string"
- }
- ]
- }
- ],
- "sources": [
- {
- "path":
"/workspaces/incubator-graphar/testing/neo4j/data/Movie.orc",
- "columns": {
- "title": "title",
- "tagline": "tagline"
- }
- }
- ]
- }
- ],
- "edges": [
- {
- "edge_type": "WROTE",
- "src_type": "Person",
- "src_prop": "name",
- "dst_type": "Movie",
- "dst_prop": "title",
- "sources": [
- {
- "path":
"/workspaces/incubator-graphar/testing/neo4j/data/Person_WROTE_Movie.csv",
- "columns": {
- "name": "name",
- "title": "title"
- }
- }
- ]
- },
- {
- "edge_type": "ACTED_IN",
- "src_type": "Person",
- "src_prop": "name",
- "dst_type": "Movie",
- "dst_prop": "title",
- "sources": [
- {
- "path":
"/workspaces/incubator-graphar/testing/neo4j/data/Person_ACTED_IN_Movie.csv",
- "columns": {
- "name": "name",
- "title": "title"
- }
- }
- ]
- },
- {
- "edge_type": "REVIEWED",
- "src_type": "Person",
- "src_prop": "name",
- "dst_type": "Movie",
- "dst_prop": "title",
- "property_groups": [
- {
- "properties": [
- {
- "name": "rating",
- "data_type": "int64"
- },
- {
- "name": "summary",
- "data_type": "string"
- }
- ]
- }
- ],
- "sources": [
- {
- "path":
"/workspaces/incubator-graphar/testing/neo4j/data/Person_REVIEWED_Movie.csv",
- "columns": {
- "name": "name",
- "title": "title",
- "summary": "summary",
- "rating": "rating"
- }
- }
- ]
- }
- ]
- }
-}
\ No newline at end of file
diff --git a/neo4j/data/import.mini.yml b/neo4j/data/import.mini.yml
new file mode 100644
index 0000000..86cf92f
--- /dev/null
+++ b/neo4j/data/import.mini.yml
@@ -0,0 +1,71 @@
+graphar:
+ path: /tmp/graphar/movie
+ name: MovieGraph
+
+import_schema:
+ vertices:
+ - type: Person
+ property_groups:
+ - properties:
+ - name: name
+ data_type: string
+ is_primary: true
+ - name: born
+ data_type: int64
+ sources:
+ - path: ../testing/neo4j/data/Person.parquet
+ columns:
+ name: name
+ born: born
+ - type: Movie
+ property_groups:
+ - properties:
+ - name: title
+ data_type: string
+ is_primary: true
+ - name: tagline
+ data_type: string
+ sources:
+ - path: ../testing/neo4j/data/Movie.orc
+ columns:
+ title: title
+ tagline: tagline
+ edges:
+ - edge_type: WROTE
+ src_type: Person
+ src_prop: name
+ dst_type: Movie
+ dst_prop: title
+ sources:
+ - path: ../testing/neo4j/data/Person_WROTE_Movie.csv
+ columns:
+ name: name
+ title: title
+ - edge_type: ACTED_IN
+ src_type: Person
+ src_prop: name
+ dst_type: Movie
+ dst_prop: title
+ sources:
+ - path: ../testing/neo4j/data/Person_ACTED_IN_Movie.json
+ columns:
+ name: name
+ title: title
+ - edge_type: REVIEWED
+ src_type: Person
+ src_prop: name
+ dst_type: Movie
+ dst_prop: title
+ property_groups:
+ - properties:
+ - name: rating
+ data_type: int64
+ - name: summary
+ data_type: string
+ sources:
+ - path: ../testing/neo4j/data/Person_REVIEWED_Movie.csv
+ columns:
+ name: name
+ title: title
+ summary: summary
+ rating: rating
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
