Skip to content

cdm_data_loaders.converters.cli.xsd_to_pyarrow

CLI interface for generating static Python PyArrow schema modules from XSD schemas.

SchemaCodegenConfig pydantic-model

Bases: BaseModel

Configuration for generating a component-based PyArrow schema.py module from an XSD file.

Show JSON schema: 
{
  "description": "Configuration for generating a component-based PyArrow ``schema.py`` module from an XSD file.",
  "properties": {
    "xsd_file": {
      "format": "path",
      "title": "Xsd File",
      "type": "string"
    },
    "output": {
      "format": "path",
      "title": "Output",
      "type": "string"
    },
    "docstring": {
      "title": "Docstring",
      "type": "string"
    },
    "xml_level": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": 1,
      "title": "Xml Level"
    },
    "xml_tag": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Xml Tag"
    },
    "root_tag": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Root Tag"
    },
    "max_recursion_depth": {
      "default": 2,
      "title": "Max Recursion Depth",
      "type": "integer"
    }
  },
  "required": [
    "xsd_file",
    "output",
    "docstring"
  ],
  "title": "SchemaCodegenConfig",
  "type": "object"
}

Config:

  • frozen: True

Fields:

  • xsd_file (Path)
  • output (Path)
  • docstring (str)
  • xml_level (int | None)
  • xml_tag (str | None)
  • root_tag (str | None)
  • max_recursion_depth (int)
Source code in src/cdm_data_loaders/converters/cli/xsd_to_pyarrow.py 
30
31
32
33
34
35
36
37
38
39
40
41
class SchemaCodegenConfig(BaseModel):
    """Configuration for generating a component-based PyArrow ``schema.py`` module from an XSD file."""

    model_config = ConfigDict(frozen=True)

    xsd_file: Path
    output: Path
    docstring: str
    xml_level: int | None = 1
    xml_tag: str | None = None
    root_tag: str | None = None
    max_recursion_depth: int = DEFAULT_MAX_RECURSION_DEPTH

XsdToPyArrowCliSettings

Bases: LoggerSettings

Settings for generating a static Python PyArrow schema module from an XSD file.

Source code in src/cdm_data_loaders/converters/cli/xsd_to_pyarrow.py 
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
class XsdToPyArrowCliSettings(LoggerSettings):
    """Settings for generating a static Python PyArrow schema module from an XSD file."""

    model_config: SettingsConfigDict = default_settings_with_shortcuts(
        cli_prog_name=PIPELINE_NAME,
        cli_shortcuts=XSD_TO_PYARROW_CLI_SHORTCUTS,
    )

    xsd_file: Annotated[
        FilePath,
        Field(description="Path to the input XSD file"),
    ]
    output: Annotated[
        Path,
        Field(description="Destination Python file path for the generated schema module"),
    ]
    xml_level: Annotated[
        PositiveInt,
        Field(
            default=1,
            description="Element depth relative to root (default: 1)",
        ),
    ]
    xml_tag: Annotated[
        NonEmptyStr | None,
        Field(
            default=None,
            description="Single target XML tag (overrides --xml-level)",
        ),
    ]
    root_tag: Annotated[
        NonEmptyStr | None,
        Field(
            default=None,
            description="Explicit root XML tag for level discovery",
        ),
    ]
    max_recursion_depth: Annotated[
        PositiveInt,
        Field(
            default=DEFAULT_MAX_RECURSION_DEPTH,
            description="Maximum recursion depth before JSON string truncation",
        ),
    ]

render_schema_module 

render_schema_module(config: SchemaCodegenConfig) -> str

Render a complete, formatted Python schema module from config.

Parameters:

Name Type Description Default
config SchemaCodegenConfig

Code generation configuration.

 required

Returns:

Type Description
str

Formatted Python module source code.
Source code in src/cdm_data_loaders/converters/cli/xsd_to_pyarrow.py 
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
def render_schema_module(config: SchemaCodegenConfig) -> str:
    """Render a complete, formatted Python schema module from ``config``.

    :param config: Code generation configuration.
    :type config: SchemaCodegenConfig
    :return: Formatted Python module source code.
    :rtype: str
    """
    converter = XsdToPyArrow(
        xml_tag=config.xml_tag,
        max_recursion_depth=config.max_recursion_depth,
    )
    if config.xml_tag is not None:
        return converter.convert_to_python(config.xsd_file, docstring=config.docstring)
    level = config.xml_level if config.xml_level is not None else 1
    return converter.convert_level_to_python(
        config.xsd_file,
        level,
        root_tag=config.root_tag,
        docstring=config.docstring,
    )

generate_python_schema 

generate_python_schema(
    settings: XsdToPyArrowCliSettings,
) -> None

Generate and write a static Python PyArrow schema module from an XSD file.

Parameters:

Name Type Description Default
settings XsdToPyArrowCliSettings

XSD-to-PyArrow CLI settings.

 required
Source code in src/cdm_data_loaders/converters/cli/xsd_to_pyarrow.py 
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
def generate_python_schema(settings: XsdToPyArrowCliSettings) -> None:
    """Generate and write a static Python PyArrow schema module from an XSD file.

    :param settings: XSD-to-PyArrow CLI settings.
    :type settings: XsdToPyArrowCliSettings
    """
    config = SchemaCodegenConfig(
        xsd_file=settings.xsd_file,
        output=settings.output,
        docstring=f"PyArrow schemas and reusable struct components generated from {settings.xsd_file.name}.",
        xml_level=None if settings.xml_tag else settings.xml_level,
        xml_tag=settings.xml_tag,
        root_tag=settings.root_tag,
        max_recursion_depth=settings.max_recursion_depth,
    )
    text = render_schema_module(config)
    settings.output.parent.mkdir(parents=True, exist_ok=True)
    write_schema_text(text, settings.output, logger)