osdu-python-models 0.5.0__py3-none-any.whl

osdu_models/dataset/file_collection_tgs_mdio/v1_0_0.py

@@ -0,0 +1,262 @@
+# generated by datamodel-codegen:
+#   filename:  dataset/file_collection_tgs_mdio/v1_0_0.json
+
+from __future__ import annotations
+from enum import Enum
+from pydantic import BaseModel, ConfigDict, Field, constr
+from ...abstract.abstract_file_source_info import v1_0_1
+from typing import Any
+
+
+class Endian(Enum):
+    """
+    Endianness of binary value.  Enumeration: "BIG", "LITTLE".  If absent, applications will need to interpret from context indicators.
+    """
+
+    BIG = 'BIG'
+    LITTLE = 'LITTLE'
+
+
+class GridOverrides(BaseModel):
+    """
+    GridOverrides supports processes to re-index and sort seismic data to a logical grid (e.g. 3D Shot Grid or CDP Grid) for SEGY files that lack certain required information in their headers. This is usually used for prestack seismic data.
+    """
+
+    model_config = ConfigDict(
+        extra='allow',
+    )
+    ApplyChannelWrap: bool | None = None
+    """
+    Setting this to “true” directs the system to apply a transformation that maps unwrapped (e.g. one cable ends at channel 20, next cable starts at channel 21) sequential channel header "channel" into a wrapped layout (meaning every cable starts at channel 1) when converting from SEGY to MDIO. This process relies on the total number of channels per cable, specified by “ChannelsPerCable.” Because it overrides the default header-parsing logic, it cannot be enabled at the same time as “AutoChannelWrap.”
+
+    It is recommended to use ApplyChannelWrap when ingesting 3D Streamer Shots with sequential "channel" numbers in the headers and unknown "cable" number identifiers. Designed to be run in after (and in conjunction with) "CalculateCable".
+    """
+    ChannelsPerCable: float | None = None
+    """
+    This attribute specifies the total number of channels (often corresponding to receivers) in each cable used for 3D seismic streamer acquisition. This number is required whenever “ApplyChannelWrap” or "CalculateCable" are "true", as it determines how unwrapped (e.g. one cable ends at channel 20, next cable starts at channel 21) channel numbers are folded into their corresponding cables.
+    """
+    CalculateCable: bool | None = None
+    """
+    Setting this to “true” directs the system to compute the cable number identifier using the unwrapped (e.g. one cable ends at 20, next cable starts at 21) channel index and the “ChannelsPerCable.” This calculation helps ensure each channel is assigned to the correct cable.
+
+    It is recommended to use this setting when ingesting 3D Streamer Shots with sequential "channel" numbers in the headers and unknown "cable" number identifiers. Designed to be run in prior to (and in conjunction with) "ApplyChannelWrap" when cable numbers are needed.
+    """
+    ApplyAutoChannelWrap: bool | None = None
+    """
+    Setting this to “true” directs the system to apply a channel-numbering transformation based solely on values found in the seismic headers. Unlike “ApplyChannelWrap,” which requires an explicit “ChannelsPerCable” value, “AutoChannelWrap” uses built-in header data (cable number key "cable" and channel header key "channel"). Cannot be enabled at the same time as “ApplyChannelWrap.”
+    """
+
+
+class DatasetProperties(BaseModel):
+    """
+    The dataset properties for a file collection.
+    """
+
+    model_config = ConfigDict(
+        extra='allow',
+    )
+    FileCollectionPath: str = Field(
+        ...,
+        examples=['s3://default_bucket/opendes/data/vds-dataset/'],
+        title='File Collection Path',
+    )
+    """
+    The mandatory path to the file collection. A FileCollectionPath should represent folder level access to a set of files.
+    """
+    IndexFilePath: str | None = Field(
+        None,
+        examples=['s3://default_bucket/opendes/data/vds-dataset/vds-dataset.index'],
+        title='Index File Path',
+    )
+    """
+    An optional path to an index file.
+    """
+    FileSourceInfos: list[v1_0_1.AbstractFileSourceInfo] | None = Field(
+        None,
+        examples=[
+            [
+                {
+                    'FileSource': 's3://default_bucket/opendes/data/vds-dataset/vds-file-1',
+                    'PreloadFilePath': 's3://staging-area/r7/raw-data/provided/documents/vds-file-1',
+                    'Name': 'vds-file-1',
+                    'PreloadFileCreateUser': 'somebody@acme.org',
+                    'PreloadFileCreateDate': '2019-12-16T11:46:20.163Z',
+                    'PreloadFileModifyUser': 'somebody.else@acme.org',
+                    'PreloadFileModifyDate': '2019-12-20T17:20:05.356Z',
+                    'FileSize': '439452464',
+                    'Checksum': 'd41d8cd98f00b204e9800998ecf8427e',
+                    'ChecksumAlgorithm': 'MD5',
+                },
+                {
+                    'FileSource': 's3://default_bucket/opendes/data/vds-dataset/vds-file-2',
+                    'PreloadFilePath': 's3://staging-area/r7/raw-data/provided/documents/vds-file-2',
+                    'Name': 'vds-file-2',
+                    'PreloadFileCreateUser': 'somebody@acme.org',
+                    'PreloadFileCreateDate': '2019-12-16T11:50:40.321Z',
+                    'PreloadFileModifyUser': 'somebody.else@acme.org',
+                    'PreloadFileModifyDate': '2019-12-20T17:59:03.456Z',
+                    'FileSize': '433645463',
+                    'Checksum': '204e9800998ecf8427ed41d8cd98f00b',
+                    'ChecksumAlgorithm': 'MD5',
+                },
+            ]
+        ],
+        title='File Source Info Array',
+    )
+    """
+    Array of file collection members as FileSourceInfo.
+    """
+    Checksum: constr(pattern=r'^[0-9a-fA-F]{32}') | None = Field(
+        None, examples=['d41d8cd98f00b204e9800998ecf8427e'], title='MD5 Checksum'
+    )
+    """
+    MD5 checksum of file bytes - a 32 byte hexadecimal number.
+    """
+
+
+class Data(BaseModel):
+    """
+    The schema fragment representing file collections.
+    """
+
+    model_config = ConfigDict(
+        extra='allow',
+    )
+    ResourceHomeRegionID: (
+        constr(pattern=r'^[\w\-\.]+:reference-data\-\-OSDURegion:[\w\-\.\:\%]+:[0-9]*$')
+        | None
+    ) = Field(None, title='Resource Home Region ID')
+    """
+    The name of the home [cloud environment] region for this OSDU resource object.
+    """
+    ResourceHostRegionIDs: (
+        list[
+            constr(
+                pattern=r'^[\w\-\.]+:reference-data\-\-OSDURegion:[\w\-\.\:\%]+:[0-9]*$'
+            )
+        ]
+        | None
+    ) = Field(None, title='Resource Host Region ID')
+    """
+    The name of the host [cloud environment] region(s) for this OSDU resource object.
+    """
+    ResourceCurationStatus: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-ResourceCurationStatus:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Resource Curation Status')
+    """
+    Describes the current Curation status.
+    """
+    ResourceLifecycleStatus: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-ResourceLifecycleStatus:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Resource Lifecycle Status')
+    """
+    Describes the current Resource Lifecycle status.
+    """
+    ResourceSecurityClassification: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-ResourceSecurityClassification:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Resource Security Classification')
+    """
+    Classifies the security level of the resource.
+    """
+    Source: str | None = Field(None, title='Data Source')
+    """
+    The entity that produced the record, or from which it is received; could be an organization, agency, system, internal team, or individual. For informational purposes only, the list of sources is not governed.
+    """
+    ExistenceKind: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-ExistenceKind:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Existence Kind')
+    """
+    Where does this data resource sit in the cradle-to-grave span of its existence?
+    """
+    TechnicalAssuranceID: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-TechnicalAssuranceType:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Technical Assurance ID')
+    """
+    DEPRECATED: Describes a record's overall suitability for general business consumption based on data quality. Clarifications: Since Certified is the highest classification of suitable quality, any further change or versioning of a Certified record should be carefully considered and justified. If a Technical Assurance value is not populated then one can assume the data has not been evaluated or its quality is unknown (=Unevaluated). Technical Assurance values are not intended to be used for the identification of a single "preferred" or "definitive" record by comparison with other records.
+    """
+    Name: str | None = Field(None, examples=['Dataset X221/15'], title='Name')
+    """
+    An optional name of the dataset, e.g. a user friendly file or file collection name.
+    """
+    Description: str | None = Field(
+        None, examples=['As originally delivered by ACME.com.'], title='Description'
+    )
+    """
+    An optional, textual description of the dataset.
+    """
+    TotalSize: constr(pattern=r'^[0-9]+$') | None = Field(
+        None, examples=['42949672960'], title='Total Size'
+    )
+    """
+    Total size of the dataset in bytes; for files it is the same as declared in FileSourceInfo.FileSize or the sum of all individual files. Implemented as string. The value must be convertible to a long integer (sizes can become very large).
+    """
+    EncodingFormatTypeID: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-EncodingFormatType:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(
+        None,
+        examples=['namespace:reference-data--EncodingFormatType:text%2Fcsv:'],
+        title='Encoding Format Type ID',
+    )
+    """
+    EncodingFormatType ID reference value relationship. It can be a mime-type or media-type.
+    """
+    SchemaFormatTypeID: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-SchemaFormatType:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(
+        None,
+        examples=['namespace:reference-data--SchemaFormatType:CWLS%20LAS3:'],
+        title='Schema Format Type ID',
+    )
+    """
+    Relationship to the SchemaFormatType reference value.
+    """
+    Endian_1: Endian | None = Field(None, alias='Endian')
+    """
+    Endianness of binary value.  Enumeration: "BIG", "LITTLE".  If absent, applications will need to interpret from context indicators.
+    """
+    DatasetProperties_1: DatasetProperties = Field(
+        ..., alias='DatasetProperties', examples=[{}], title='Dataset Properties'
+    )
+    """
+    The dataset properties for a file collection.
+    """
+    ChunkSize: list[int] | None = None
+    """
+    The size of the data chunks (commonly called "brick size") into which the seismic data is divided. Populate one array entry per dimension.
+    """
+    IsLossless: bool | None = None
+    """
+    A "true" flag indicates that the data compression applied does not lose data (aka lossless), and therefore can be perfectly reconstructed. "False" indicates the compression is "lossy".
+    """
+    CompressionTolerance: float | None = None
+    """
+    This tolerance ensures that values (e.g. seismic amplitudes) in the decompressed array differ from the input array by no more than this tolerance. CompressionTolerance is only used when IsLossless = false.
+    """
+    GridOverrides_1: GridOverrides | None = Field(
+        None, alias='GridOverrides', title='Grid Overrides'
+    )
+    """
+    GridOverrides supports processes to re-index and sort seismic data to a logical grid (e.g. 3D Shot Grid or CDP Grid) for SEGY files that lack certain required information in their headers. This is usually used for prestack seismic data.
+    """
+    ExtensionProperties: dict[str, Any] | None = None

osdu_models/dataset/file_compressed_vector_headers/__init__.py

@@ -0,0 +1,2 @@
+# generated by datamodel-codegen:
+#   filename:  tmp4rfivwe4

osdu_models/dataset/file_compressed_vector_headers/v1_0_0.py

@@ -0,0 +1,255 @@
+# generated by datamodel-codegen:
+#   filename:  dataset/file_compressed_vector_headers/v1_0_0.json
+
+from __future__ import annotations
+from enum import Enum
+from pydantic import BaseModel, ConfigDict, Field, constr
+from ...abstract.abstract_file_source_info import v1_0_0
+from typing import Any
+
+
+class Endian(Enum):
+    """
+    Endianness of binary value.  Enumeration: "BIG", "LITTLE".  If absent, applications will need to interpret from context indicators.
+    """
+
+    BIG = 'BIG'
+    LITTLE = 'LITTLE'
+
+
+class ScalarIndicator(Enum):
+    """
+    Enumerated string indicating whether to use the normal scalar field for scaling this field (STANDARD), no scaling (NOSCALE), or override scalar (OVERRIDE).  Default is current STANDARD (such as SEG-Y rev2).
+    """
+
+    STANDARD = 'STANDARD'
+    NOSCALE = 'NOSCALE'
+    OVERRIDE = 'OVERRIDE'
+
+
+class VectorHeaderMappingItem(BaseModel):
+    """
+    Array of objects which define the meaning and format of a tabular structure used in a binary file as a header.  The initial use case is the trace headers of a SEG-Y file.  Note that some of this information may be repeated in the SEG-Y EBCDIC header.
+    """
+
+    model_config = ConfigDict(
+        extra='allow',
+    )
+    KeyName: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-HeaderKeyName:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Key Name')
+    """
+    Relationship to a reference value for a name of a property header such as INLINE, CDPX.
+    """
+    WordFormat: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-WordFormatType:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Word Format')
+    """
+    Relationship to a reference value for binary data types, such as INT, UINT, FLOAT, IBM_FLOAT, ASCII, EBCDIC.
+    """
+    WordWidth: int | None = Field(None, title='Word Width')
+    """
+    Size of the word in bytes.
+    """
+    Position: int | None = None
+    """
+    Beginning byte position of header value, 1 indexed.
+    """
+    UoM: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-UnitOfMeasure:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Unit of Measure')
+    """
+    Relationship to units of measure reference if header standard is not followed.
+    """
+    ScalarIndicator_1: ScalarIndicator | None = Field(
+        None, alias='ScalarIndicator', title='Scalar Indicator'
+    )
+    """
+    Enumerated string indicating whether to use the normal scalar field for scaling this field (STANDARD), no scaling (NOSCALE), or override scalar (OVERRIDE).  Default is current STANDARD (such as SEG-Y rev2).
+    """
+    ScalarOverride: float | None = Field(None, title='Scalar Override')
+    """
+    Scalar value (as defined by standard) when a value present in the header needs to be overwritten for this value.
+    """
+
+
+class DatasetProperties(BaseModel):
+    """
+    The dataset properties for a single file.
+    """
+
+    model_config = ConfigDict(
+        extra='allow',
+    )
+    FileSourceInfo: v1_0_0.AbstractFileSourceInfo | None = Field(
+        None, title='File Source Info'
+    )
+    """
+    Information about the single file.
+    """
+
+
+class Data(BaseModel):
+    """
+    Array of objects which define the meaning and format of a tabular structure used in a binary file as a header.  The initial use case is the trace headers of a SEG-Y file.  Note that some of this information may be repeated in the SEG-Y EBCDIC header.
+    """
+
+    model_config = ConfigDict(
+        extra='allow',
+    )
+    ResourceHomeRegionID: (
+        constr(pattern=r'^[\w\-\.]+:reference-data\-\-OSDURegion:[\w\-\.\:\%]+:[0-9]*$')
+        | None
+    ) = Field(None, title='Resource Home Region ID')
+    """
+    The name of the home [cloud environment] region for this OSDU resource object.
+    """
+    ResourceHostRegionIDs: (
+        list[
+            constr(
+                pattern=r'^[\w\-\.]+:reference-data\-\-OSDURegion:[\w\-\.\:\%]+:[0-9]*$'
+            )
+        ]
+        | None
+    ) = Field(None, title='Resource Host Region ID')
+    """
+    The name of the host [cloud environment] region(s) for this OSDU resource object.
+    """
+    ResourceCurationStatus: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-ResourceCurationStatus:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Resource Curation Status')
+    """
+    Describes the current Curation status.
+    """
+    ResourceLifecycleStatus: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-ResourceLifecycleStatus:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Resource Lifecycle Status')
+    """
+    Describes the current Resource Lifecycle status.
+    """
+    ResourceSecurityClassification: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-ResourceSecurityClassification:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Resource Security Classification')
+    """
+    Classifies the security level of the resource.
+    """
+    Source: str | None = Field(None, title='Data Source')
+    """
+    The entity that produced the record, or from which it is received; could be an organization, agency, system, internal team, or individual. For informational purposes only, the list of sources is not governed.
+    """
+    ExistenceKind: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-ExistenceKind:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Existence Kind')
+    """
+    Where does this data resource sit in the cradle-to-grave span of its existence?
+    """
+    TechnicalAssuranceID: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-TechnicalAssuranceType:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(None, title='Technical Assurance ID')
+    """
+    DEPRECATED: Describes a record's overall suitability for general business consumption based on data quality. Clarifications: Since Certified is the highest classification of suitable quality, any further change or versioning of a Certified record should be carefully considered and justified. If a Technical Assurance value is not populated then one can assume the data has not been evaluated or its quality is unknown (=Unevaluated). Technical Assurance values are not intended to be used for the identification of a single "preferred" or "definitive" record by comparison with other records.
+    """
+    Name: str | None = Field(None, examples=['Dataset X221/15'], title='Name')
+    """
+    An optional name of the dataset, e.g. a user friendly file or file collection name.
+    """
+    Description: str | None = Field(
+        None, examples=['As originally delivered by ACME.com.'], title='Description'
+    )
+    """
+    An optional, textual description of the dataset.
+    """
+    TotalSize: constr(pattern=r'^[0-9]+$') | None = Field(
+        None, examples=[13245217273], title='Total Size'
+    )
+    """
+    Total size of the dataset in bytes; for files it is the same as declared in FileSourceInfo.FileSize or the sum of all individual files. Implemented as string. The value must be convertible to a long integer (sizes can become very large).
+    """
+    EncodingFormatTypeID: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-EncodingFormatType:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(
+        None,
+        examples=['namespace:reference-data--EncodingFormatType:text%2Fcsv:'],
+        title='Encoding Format Type ID',
+    )
+    """
+    EncodingFormatType ID reference value relationship. It can be a mime-type or media-type.
+    """
+    SchemaFormatTypeID: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-SchemaFormatType:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = Field(
+        None,
+        examples=['namespace:reference-data--SchemaFormatType:CWLS%20LAS3:'],
+        title='Schema Format Type ID',
+    )
+    """
+    Relationship to the SchemaFormatType reference value.
+    """
+    Endian_1: Endian | None = Field(None, alias='Endian')
+    """
+    Endianness of binary value.  Enumeration: "BIG", "LITTLE".  If absent, applications will need to interpret from context indicators.
+    """
+    DatasetProperties_1: DatasetProperties = Field(
+        ..., alias='DatasetProperties', examples=[{}], title='Dataset Properties'
+    )
+    """
+    The dataset properties for a single file.
+    """
+    Checksum: constr(pattern=r'^[0-9a-fA-F]{32}') | None = Field(
+        None, examples=['d41d8cd98f00b204e9800998ecf8427e'], title='MD5 Checksum'
+    )
+    """
+    MD5 checksum of file bytes - a 32 byte hexadecimal number.
+    """
+    LossyCompressionIndicator: bool | None = None
+    """
+    Boolean that warns that an imperfect compression algorithm has been applied to the bulk binary data.  Details of the compression method need to be discovered from the format properties and file access methods.
+    """
+    CompressionMethodTypeID: (
+        constr(
+            pattern=r'^[\w\-\.]+:reference-data\-\-CompressionMethodType:[\w\-\.\:\%]+:[0-9]*$'
+        )
+        | None
+    ) = None
+    """
+    Name of a compression algorithm applied to the data as stored.
+    """
+    CompressionLevel: float | None = None
+    """
+    Number indicating degree of fidelity present in bulk data resulting from compression.  Meaning of number depends on algorithm.
+    """
+    VectorHeaderMapping: list[VectorHeaderMappingItem] | None = None
+    """
+    Array of objects which define the meaning and format of a tabular structure used in a binary file as a header.  The initial use case is the trace headers of a SEG-Y file.  Note that some of this information may be repeated in the SEG-Y EBCDIC header.
+    """
+    ExtensionProperties: dict[str, Any] | None = None