cribl-control-plane 0.0.21__py3-none-any.whl → 0.4.0b23__py3-none-any.whl

cribl_control_plane/models/outputdatabricks.py

@@ -0,0 +1,501 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from cribl_control_plane import models, utils
+from cribl_control_plane.types import BaseModel
+from cribl_control_plane.utils import validate_open_enum
+from enum import Enum
+import pydantic
+from pydantic import field_serializer
+from pydantic.functional_validators import PlainValidator
+from typing import List, Optional
+from typing_extensions import Annotated, NotRequired, TypedDict
+
+
+class OutputDatabricksType(str, Enum):
+    DATABRICKS = "databricks"
+
+
+class OutputDatabricksDataFormat(str, Enum, metaclass=utils.OpenEnumMeta):
+    r"""Format of the output data"""
+
+    # JSON
+    JSON = "json"
+    # Raw
+    RAW = "raw"
+    # Parquet
+    PARQUET = "parquet"
+
+
+class OutputDatabricksBackpressureBehavior(str, Enum, metaclass=utils.OpenEnumMeta):
+    r"""How to handle events when all receivers are exerting backpressure"""
+
+    # Block
+    BLOCK = "block"
+    # Drop
+    DROP = "drop"
+
+
+class OutputDatabricksDiskSpaceProtection(str, Enum, metaclass=utils.OpenEnumMeta):
+    r"""How to handle events when disk space is below the global 'Min free disk space' limit"""
+
+    # Block
+    BLOCK = "block"
+    # Drop
+    DROP = "drop"
+
+
+class OutputDatabricksCompression(str, Enum, metaclass=utils.OpenEnumMeta):
+    r"""Data compression format to apply to HTTP content before it is delivered"""
+
+    NONE = "none"
+    GZIP = "gzip"
+
+
+class OutputDatabricksCompressionLevel(str, Enum, metaclass=utils.OpenEnumMeta):
+    r"""Compression level to apply before moving files to final destination"""
+
+    # Best Speed
+    BEST_SPEED = "best_speed"
+    # Normal
+    NORMAL = "normal"
+    # Best Compression
+    BEST_COMPRESSION = "best_compression"
+
+
+class OutputDatabricksParquetVersion(str, Enum, metaclass=utils.OpenEnumMeta):
+    r"""Determines which data types are supported and how they are represented"""
+
+    # 1.0
+    PARQUET_1_0 = "PARQUET_1_0"
+    # 2.4
+    PARQUET_2_4 = "PARQUET_2_4"
+    # 2.6
+    PARQUET_2_6 = "PARQUET_2_6"
+
+
+class OutputDatabricksDataPageVersion(str, Enum, metaclass=utils.OpenEnumMeta):
+    r"""Serialization format of data pages. Note that some reader implementations use Data page V2's attributes to work more efficiently, while others ignore it."""
+
+    # V1
+    DATA_PAGE_V1 = "DATA_PAGE_V1"
+    # V2
+    DATA_PAGE_V2 = "DATA_PAGE_V2"
+
+
+class OutputDatabricksKeyValueMetadatumTypedDict(TypedDict):
+    value: str
+    key: NotRequired[str]
+
+
+class OutputDatabricksKeyValueMetadatum(BaseModel):
+    value: str
+
+    key: Optional[str] = ""
+
+
+class OutputDatabricksTypedDict(TypedDict):
+    type: OutputDatabricksType
+    workspace_id: str
+    r"""Databricks workspace ID"""
+    client_id: str
+    r"""OAuth client ID for Unity Catalog authentication"""
+    client_text_secret: str
+    r"""OAuth client secret for Unity Catalog authentication"""
+    id: NotRequired[str]
+    r"""Unique ID for this output"""
+    pipeline: NotRequired[str]
+    r"""Pipeline to process data before sending out to this output"""
+    system_fields: NotRequired[List[str]]
+    r"""Fields to automatically add to events, such as cribl_pipe. Supports wildcards."""
+    environment: NotRequired[str]
+    r"""Optionally, enable this config only on a specified Git branch. If empty, will be enabled everywhere."""
+    streamtags: NotRequired[List[str]]
+    r"""Tags for filtering and grouping in @{product}"""
+    dest_path: NotRequired[str]
+    r"""Optional path to prepend to files before uploading."""
+    stage_path: NotRequired[str]
+    r"""Filesystem location in which to buffer files before compressing and moving to final destination. Use performant, stable storage."""
+    add_id_to_stage_path: NotRequired[bool]
+    r"""Add the Output ID value to staging location"""
+    remove_empty_dirs: NotRequired[bool]
+    r"""Remove empty staging directories after moving files"""
+    partition_expr: NotRequired[str]
+    r"""JavaScript expression defining how files are partitioned and organized. Default is date-based. If blank, Stream will fall back to the event's __partition field value – if present – otherwise to each location's root directory."""
+    format_: NotRequired[OutputDatabricksDataFormat]
+    r"""Format of the output data"""
+    base_file_name: NotRequired[str]
+    r"""JavaScript expression to define the output filename prefix (can be constant)"""
+    file_name_suffix: NotRequired[str]
+    r"""JavaScript expression to define the output filename suffix (can be constant).  The `__format` variable refers to the value of the `Data format` field (`json` or `raw`).  The `__compression` field refers to the kind of compression being used (`none` or `gzip`)."""
+    max_file_size_mb: NotRequired[float]
+    r"""Maximum uncompressed output file size. Files of this size will be closed and moved to final output location."""
+    max_file_open_time_sec: NotRequired[float]
+    r"""Maximum amount of time to write to a file. Files open for longer than this will be closed and moved to final output location."""
+    max_file_idle_time_sec: NotRequired[float]
+    r"""Maximum amount of time to keep inactive files open. Files open for longer than this will be closed and moved to final output location."""
+    max_open_files: NotRequired[float]
+    r"""Maximum number of files to keep open concurrently. When exceeded, @{product} will close the oldest open files and move them to the final output location."""
+    header_line: NotRequired[str]
+    r"""If set, this line will be written to the beginning of each output file"""
+    write_high_water_mark: NotRequired[float]
+    r"""Buffer size used to write to a file"""
+    on_backpressure: NotRequired[OutputDatabricksBackpressureBehavior]
+    r"""How to handle events when all receivers are exerting backpressure"""
+    deadletter_enabled: NotRequired[bool]
+    r"""If a file fails to move to its final destination after the maximum number of retries, move it to a designated directory to prevent further errors"""
+    on_disk_full_backpressure: NotRequired[OutputDatabricksDiskSpaceProtection]
+    r"""How to handle events when disk space is below the global 'Min free disk space' limit"""
+    force_close_on_shutdown: NotRequired[bool]
+    r"""Force all staged files to close during an orderly Node shutdown. This triggers immediate upload of in-progress data — regardless of idle time, file age, or size thresholds — to minimize data loss."""
+    scope: NotRequired[str]
+    r"""OAuth scope for Unity Catalog authentication"""
+    catalog: NotRequired[str]
+    r"""Name of the catalog to use for the output"""
+    schema_: NotRequired[str]
+    r"""Name of the catalog schema to use for the output"""
+    events_volume_name: NotRequired[str]
+    r"""Name of the events volume in Databricks"""
+    timeout_sec: NotRequired[float]
+    r"""Amount of time, in seconds, to wait for a request to complete before canceling it"""
+    description: NotRequired[str]
+    compress: NotRequired[OutputDatabricksCompression]
+    r"""Data compression format to apply to HTTP content before it is delivered"""
+    compression_level: NotRequired[OutputDatabricksCompressionLevel]
+    r"""Compression level to apply before moving files to final destination"""
+    automatic_schema: NotRequired[bool]
+    r"""Automatically calculate the schema based on the events of each Parquet file generated"""
+    parquet_schema: NotRequired[str]
+    r"""To add a new schema, navigate to Processing > Knowledge > Parquet Schemas"""
+    parquet_version: NotRequired[OutputDatabricksParquetVersion]
+    r"""Determines which data types are supported and how they are represented"""
+    parquet_data_page_version: NotRequired[OutputDatabricksDataPageVersion]
+    r"""Serialization format of data pages. Note that some reader implementations use Data page V2's attributes to work more efficiently, while others ignore it."""
+    parquet_row_group_length: NotRequired[float]
+    r"""The number of rows that every group will contain. The final group can contain a smaller number of rows."""
+    parquet_page_size: NotRequired[str]
+    r"""Target memory size for page segments, such as 1MB or 128MB. Generally, lower values improve reading speed, while higher values improve compression."""
+    should_log_invalid_rows: NotRequired[bool]
+    r"""Log up to 3 rows that @{product} skips due to data mismatch"""
+    key_value_metadata: NotRequired[List[OutputDatabricksKeyValueMetadatumTypedDict]]
+    r"""The metadata of files the Destination writes will include the properties you add here as key-value pairs. Useful for tagging. Examples: \"key\":\"OCSF Event Class\", \"value\":\"9001\" """
+    enable_statistics: NotRequired[bool]
+    r"""Statistics profile an entire file in terms of minimum/maximum values within data, numbers of nulls, etc. You can use Parquet tools to view statistics."""
+    enable_write_page_index: NotRequired[bool]
+    r"""One page index contains statistics for one data page. Parquet readers use statistics to enable page skipping."""
+    enable_page_checksum: NotRequired[bool]
+    r"""Parquet tools can use the checksum of a Parquet page to verify data integrity"""
+    empty_dir_cleanup_sec: NotRequired[float]
+    r"""How frequently, in seconds, to clean up empty directories"""
+    directory_batch_size: NotRequired[float]
+    r"""Number of directories to process in each batch during cleanup of empty directories. Minimum is 10, maximum is 10000. Higher values may require more memory."""
+    deadletter_path: NotRequired[str]
+    r"""Storage location for files that fail to reach their final destination after maximum retries are exceeded"""
+    max_retry_num: NotRequired[float]
+    r"""The maximum number of times a file will attempt to move to its final destination before being dead-lettered"""
+
+
+class OutputDatabricks(BaseModel):
+    type: OutputDatabricksType
+
+    workspace_id: Annotated[str, pydantic.Field(alias="workspaceId")]
+    r"""Databricks workspace ID"""
+
+    client_id: Annotated[str, pydantic.Field(alias="clientId")]
+    r"""OAuth client ID for Unity Catalog authentication"""
+
+    client_text_secret: Annotated[str, pydantic.Field(alias="clientTextSecret")]
+    r"""OAuth client secret for Unity Catalog authentication"""
+
+    id: Optional[str] = None
+    r"""Unique ID for this output"""
+
+    pipeline: Optional[str] = None
+    r"""Pipeline to process data before sending out to this output"""
+
+    system_fields: Annotated[
+        Optional[List[str]], pydantic.Field(alias="systemFields")
+    ] = None
+    r"""Fields to automatically add to events, such as cribl_pipe. Supports wildcards."""
+
+    environment: Optional[str] = None
+    r"""Optionally, enable this config only on a specified Git branch. If empty, will be enabled everywhere."""
+
+    streamtags: Optional[List[str]] = None
+    r"""Tags for filtering and grouping in @{product}"""
+
+    dest_path: Annotated[Optional[str], pydantic.Field(alias="destPath")] = ""
+    r"""Optional path to prepend to files before uploading."""
+
+    stage_path: Annotated[Optional[str], pydantic.Field(alias="stagePath")] = (
+        "$CRIBL_HOME/state/outputs/staging"
+    )
+    r"""Filesystem location in which to buffer files before compressing and moving to final destination. Use performant, stable storage."""
+
+    add_id_to_stage_path: Annotated[
+        Optional[bool], pydantic.Field(alias="addIdToStagePath")
+    ] = True
+    r"""Add the Output ID value to staging location"""
+
+    remove_empty_dirs: Annotated[
+        Optional[bool], pydantic.Field(alias="removeEmptyDirs")
+    ] = True
+    r"""Remove empty staging directories after moving files"""
+
+    partition_expr: Annotated[Optional[str], pydantic.Field(alias="partitionExpr")] = (
+        "C.Time.strftime(_time ? _time : Date.now()/1000, '%Y/%m/%d')"
+    )
+    r"""JavaScript expression defining how files are partitioned and organized. Default is date-based. If blank, Stream will fall back to the event's __partition field value – if present – otherwise to each location's root directory."""
+
+    format_: Annotated[
+        Annotated[
+            Optional[OutputDatabricksDataFormat],
+            PlainValidator(validate_open_enum(False)),
+        ],
+        pydantic.Field(alias="format"),
+    ] = OutputDatabricksDataFormat.JSON
+    r"""Format of the output data"""
+
+    base_file_name: Annotated[Optional[str], pydantic.Field(alias="baseFileName")] = (
+        "`CriblOut`"
+    )
+    r"""JavaScript expression to define the output filename prefix (can be constant)"""
+
+    file_name_suffix: Annotated[
+        Optional[str], pydantic.Field(alias="fileNameSuffix")
+    ] = '`.${C.env["CRIBL_WORKER_ID"]}.${__format}${__compression === "gzip" ? ".gz" : ""}`'
+    r"""JavaScript expression to define the output filename suffix (can be constant).  The `__format` variable refers to the value of the `Data format` field (`json` or `raw`).  The `__compression` field refers to the kind of compression being used (`none` or `gzip`)."""
+
+    max_file_size_mb: Annotated[
+        Optional[float], pydantic.Field(alias="maxFileSizeMB")
+    ] = 32
+    r"""Maximum uncompressed output file size. Files of this size will be closed and moved to final output location."""
+
+    max_file_open_time_sec: Annotated[
+        Optional[float], pydantic.Field(alias="maxFileOpenTimeSec")
+    ] = 300
+    r"""Maximum amount of time to write to a file. Files open for longer than this will be closed and moved to final output location."""
+
+    max_file_idle_time_sec: Annotated[
+        Optional[float], pydantic.Field(alias="maxFileIdleTimeSec")
+    ] = 30
+    r"""Maximum amount of time to keep inactive files open. Files open for longer than this will be closed and moved to final output location."""
+
+    max_open_files: Annotated[Optional[float], pydantic.Field(alias="maxOpenFiles")] = (
+        100
+    )
+    r"""Maximum number of files to keep open concurrently. When exceeded, @{product} will close the oldest open files and move them to the final output location."""
+
+    header_line: Annotated[Optional[str], pydantic.Field(alias="headerLine")] = ""
+    r"""If set, this line will be written to the beginning of each output file"""
+
+    write_high_water_mark: Annotated[
+        Optional[float], pydantic.Field(alias="writeHighWaterMark")
+    ] = 64
+    r"""Buffer size used to write to a file"""
+
+    on_backpressure: Annotated[
+        Annotated[
+            Optional[OutputDatabricksBackpressureBehavior],
+            PlainValidator(validate_open_enum(False)),
+        ],
+        pydantic.Field(alias="onBackpressure"),
+    ] = OutputDatabricksBackpressureBehavior.BLOCK
+    r"""How to handle events when all receivers are exerting backpressure"""
+
+    deadletter_enabled: Annotated[
+        Optional[bool], pydantic.Field(alias="deadletterEnabled")
+    ] = False
+    r"""If a file fails to move to its final destination after the maximum number of retries, move it to a designated directory to prevent further errors"""
+
+    on_disk_full_backpressure: Annotated[
+        Annotated[
+            Optional[OutputDatabricksDiskSpaceProtection],
+            PlainValidator(validate_open_enum(False)),
+        ],
+        pydantic.Field(alias="onDiskFullBackpressure"),
+    ] = OutputDatabricksDiskSpaceProtection.BLOCK
+    r"""How to handle events when disk space is below the global 'Min free disk space' limit"""
+
+    force_close_on_shutdown: Annotated[
+        Optional[bool], pydantic.Field(alias="forceCloseOnShutdown")
+    ] = False
+    r"""Force all staged files to close during an orderly Node shutdown. This triggers immediate upload of in-progress data — regardless of idle time, file age, or size thresholds — to minimize data loss."""
+
+    scope: Optional[str] = "all-apis"
+    r"""OAuth scope for Unity Catalog authentication"""
+
+    catalog: Optional[str] = "main"
+    r"""Name of the catalog to use for the output"""
+
+    schema_: Annotated[Optional[str], pydantic.Field(alias="schema")] = "external"
+    r"""Name of the catalog schema to use for the output"""
+
+    events_volume_name: Annotated[
+        Optional[str], pydantic.Field(alias="eventsVolumeName")
+    ] = "events"
+    r"""Name of the events volume in Databricks"""
+
+    timeout_sec: Annotated[Optional[float], pydantic.Field(alias="timeoutSec")] = 60
+    r"""Amount of time, in seconds, to wait for a request to complete before canceling it"""
+
+    description: Optional[str] = None
+
+    compress: Annotated[
+        Optional[OutputDatabricksCompression], PlainValidator(validate_open_enum(False))
+    ] = OutputDatabricksCompression.GZIP
+    r"""Data compression format to apply to HTTP content before it is delivered"""
+
+    compression_level: Annotated[
+        Annotated[
+            Optional[OutputDatabricksCompressionLevel],
+            PlainValidator(validate_open_enum(False)),
+        ],
+        pydantic.Field(alias="compressionLevel"),
+    ] = OutputDatabricksCompressionLevel.BEST_SPEED
+    r"""Compression level to apply before moving files to final destination"""
+
+    automatic_schema: Annotated[
+        Optional[bool], pydantic.Field(alias="automaticSchema")
+    ] = False
+    r"""Automatically calculate the schema based on the events of each Parquet file generated"""
+
+    parquet_schema: Annotated[Optional[str], pydantic.Field(alias="parquetSchema")] = (
+        None
+    )
+    r"""To add a new schema, navigate to Processing > Knowledge > Parquet Schemas"""
+
+    parquet_version: Annotated[
+        Annotated[
+            Optional[OutputDatabricksParquetVersion],
+            PlainValidator(validate_open_enum(False)),
+        ],
+        pydantic.Field(alias="parquetVersion"),
+    ] = OutputDatabricksParquetVersion.PARQUET_2_6
+    r"""Determines which data types are supported and how they are represented"""
+
+    parquet_data_page_version: Annotated[
+        Annotated[
+            Optional[OutputDatabricksDataPageVersion],
+            PlainValidator(validate_open_enum(False)),
+        ],
+        pydantic.Field(alias="parquetDataPageVersion"),
+    ] = OutputDatabricksDataPageVersion.DATA_PAGE_V2
+    r"""Serialization format of data pages. Note that some reader implementations use Data page V2's attributes to work more efficiently, while others ignore it."""
+
+    parquet_row_group_length: Annotated[
+        Optional[float], pydantic.Field(alias="parquetRowGroupLength")
+    ] = 10000
+    r"""The number of rows that every group will contain. The final group can contain a smaller number of rows."""
+
+    parquet_page_size: Annotated[
+        Optional[str], pydantic.Field(alias="parquetPageSize")
+    ] = "1MB"
+    r"""Target memory size for page segments, such as 1MB or 128MB. Generally, lower values improve reading speed, while higher values improve compression."""
+
+    should_log_invalid_rows: Annotated[
+        Optional[bool], pydantic.Field(alias="shouldLogInvalidRows")
+    ] = None
+    r"""Log up to 3 rows that @{product} skips due to data mismatch"""
+
+    key_value_metadata: Annotated[
+        Optional[List[OutputDatabricksKeyValueMetadatum]],
+        pydantic.Field(alias="keyValueMetadata"),
+    ] = None
+    r"""The metadata of files the Destination writes will include the properties you add here as key-value pairs. Useful for tagging. Examples: \"key\":\"OCSF Event Class\", \"value\":\"9001\" """
+
+    enable_statistics: Annotated[
+        Optional[bool], pydantic.Field(alias="enableStatistics")
+    ] = True
+    r"""Statistics profile an entire file in terms of minimum/maximum values within data, numbers of nulls, etc. You can use Parquet tools to view statistics."""
+
+    enable_write_page_index: Annotated[
+        Optional[bool], pydantic.Field(alias="enableWritePageIndex")
+    ] = True
+    r"""One page index contains statistics for one data page. Parquet readers use statistics to enable page skipping."""
+
+    enable_page_checksum: Annotated[
+        Optional[bool], pydantic.Field(alias="enablePageChecksum")
+    ] = False
+    r"""Parquet tools can use the checksum of a Parquet page to verify data integrity"""
+
+    empty_dir_cleanup_sec: Annotated[
+        Optional[float], pydantic.Field(alias="emptyDirCleanupSec")
+    ] = 300
+    r"""How frequently, in seconds, to clean up empty directories"""
+
+    directory_batch_size: Annotated[
+        Optional[float], pydantic.Field(alias="directoryBatchSize")
+    ] = 1000
+    r"""Number of directories to process in each batch during cleanup of empty directories. Minimum is 10, maximum is 10000. Higher values may require more memory."""
+
+    deadletter_path: Annotated[
+        Optional[str], pydantic.Field(alias="deadletterPath")
+    ] = "$CRIBL_HOME/state/outputs/dead-letter"
+    r"""Storage location for files that fail to reach their final destination after maximum retries are exceeded"""
+
+    max_retry_num: Annotated[Optional[float], pydantic.Field(alias="maxRetryNum")] = 20
+    r"""The maximum number of times a file will attempt to move to its final destination before being dead-lettered"""
+
+    @field_serializer("format_")
+    def serialize_format_(self, value):
+        if isinstance(value, str):
+            try:
+                return models.OutputDatabricksDataFormat(value)
+            except ValueError:
+                return value
+        return value
+
+    @field_serializer("on_backpressure")
+    def serialize_on_backpressure(self, value):
+        if isinstance(value, str):
+            try:
+                return models.OutputDatabricksBackpressureBehavior(value)
+            except ValueError:
+                return value
+        return value
+
+    @field_serializer("on_disk_full_backpressure")
+    def serialize_on_disk_full_backpressure(self, value):
+        if isinstance(value, str):
+            try:
+                return models.OutputDatabricksDiskSpaceProtection(value)
+            except ValueError:
+                return value
+        return value
+
+    @field_serializer("compress")
+    def serialize_compress(self, value):
+        if isinstance(value, str):
+            try:
+                return models.OutputDatabricksCompression(value)
+            except ValueError:
+                return value
+        return value
+
+    @field_serializer("compression_level")
+    def serialize_compression_level(self, value):
+        if isinstance(value, str):
+            try:
+                return models.OutputDatabricksCompressionLevel(value)
+            except ValueError:
+                return value
+        return value
+
+    @field_serializer("parquet_version")
+    def serialize_parquet_version(self, value):
+        if isinstance(value, str):
+            try:
+                return models.OutputDatabricksParquetVersion(value)
+            except ValueError:
+                return value
+        return value
+
+    @field_serializer("parquet_data_page_version")
+    def serialize_parquet_data_page_version(self, value):
+        if isinstance(value, str):
+            try:
+                return models.OutputDatabricksDataPageVersion(value)
+            except ValueError:
+                return value
+        return value