-
Notifications
You must be signed in to change notification settings - Fork 68
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Adds loaders target-parquet (automattic) (#1678)
- Loading branch information
1 parent
c540e82
commit 6af8d25
Showing
3 changed files
with
113 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,110 @@ | ||
capabilities: | ||
- about | ||
- schema-flattening | ||
- stream-maps | ||
- validate-records | ||
description: Columnar Storage Format | ||
domain_url: https://parquet.apache.org/ | ||
executable: target-parquet | ||
keywords: | ||
- file | ||
- meltano_sdk | ||
label: Parquet | ||
logo_url: /assets/logos/loaders/parquet.png | ||
maintenance_status: active | ||
name: target-parquet | ||
namespace: target_parquet | ||
next_steps: '' | ||
pip_url: git+https://github.com/Automattic/target-parquet.git | ||
quality: silver | ||
repo: https://github.com/Automattic/target-parquet | ||
settings: | ||
- description: Add metadata to records. | ||
kind: boolean | ||
label: Add Record Metadata | ||
name: add_record_metadata | ||
- description: (default - gzip) Compression methods have to be supported by Pyarrow, | ||
and currently the compression modes available are - snappy, zstd, brotli and gzip. | ||
kind: string | ||
label: Compression Method | ||
name: compression_method | ||
value: gzip | ||
- description: Destination Path | ||
kind: string | ||
label: Destination Path | ||
name: destination_path | ||
- description: Extra fields to add to the flattened record. (e.g. extra_col1=value1,extra_col2=value2) | ||
kind: string | ||
label: Extra Fields | ||
name: extra_fields | ||
- description: Extra fields types. (e.g. extra_col1=string,extra_col2=integer) | ||
kind: string | ||
label: Extra Fields Types | ||
name: extra_fields_types | ||
- description: 'One or more LCID locale strings to produce localized output for: https://faker.readthedocs.io/en/master/#localization' | ||
kind: array | ||
label: Faker Config Locale | ||
name: faker_config.locale | ||
- description: 'Value to seed the Faker generator for deterministic output: https://faker.readthedocs.io/en/master/#seeding-the-generator' | ||
kind: string | ||
label: Faker Config Seed | ||
name: faker_config.seed | ||
- description: "'True' to enable schema flattening and automatically expand nested | ||
properties." | ||
kind: boolean | ||
label: Flattening Enabled | ||
name: flattening_enabled | ||
- description: The max depth to flatten schemas. | ||
kind: integer | ||
label: Flattening Max Depth | ||
name: flattening_max_depth | ||
- description: The method to use when loading data into the destination. `append-only` | ||
will always write all input records whether that records already exists or not. | ||
`upsert` will update existing records and insert new records. `overwrite` will | ||
delete all existing records and insert all input records. | ||
kind: options | ||
label: Load Method | ||
name: load_method | ||
options: | ||
- label: Append Only | ||
value: append-only | ||
- label: Upsert | ||
value: upsert | ||
- label: Overwrite | ||
value: overwrite | ||
value: append-only | ||
- description: Max records to write in one batch. It can control the memory usage | ||
of the target. | ||
kind: integer | ||
label: Max Batch Size | ||
name: max_batch_size | ||
value: 10000 | ||
- description: Max size of pyarrow table in MB (before writing to parquet file). It | ||
can control the memory usage of the target. | ||
kind: integer | ||
label: Max Pyarrow Table Size | ||
name: max_pyarrow_table_size | ||
value: 800 | ||
- description: Extra fields to add to the flattened record. (e.g. extra_col1,extra_col2) | ||
kind: string | ||
label: Partition Cols | ||
name: partition_cols | ||
- description: User-defined config values to be used within map expressions. | ||
kind: object | ||
label: Stream Map Config | ||
name: stream_map_config | ||
- description: Config object for stream maps capability. For more information check | ||
out [Stream Maps](https://sdk.meltano.com/en/latest/stream_maps.html). | ||
kind: object | ||
label: Stream Maps | ||
name: stream_maps | ||
- description: Whether to validate the schema of the incoming streams. | ||
kind: boolean | ||
label: Validate Records | ||
name: validate_records | ||
value: true | ||
settings_group_validation: | ||
- [] | ||
settings_preamble: '' | ||
usage: '' | ||
variant: automattic |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters