mirror of
https://github.com/docling-project/docling-core.git
synced 2026-05-17 13:10:44 +00:00
Peter W. J. Staar
ef49fd3f34
Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Christoph Auer <cau@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
1467 lines
34 KiB
JSON
1467 lines
34 KiB
JSON
{
|
|
"$defs": {
|
|
"BoundingBox": {
|
|
"description": "BoundingBox.",
|
|
"properties": {
|
|
"l": {
|
|
"title": "L",
|
|
"type": "number"
|
|
},
|
|
"t": {
|
|
"title": "T",
|
|
"type": "number"
|
|
},
|
|
"r": {
|
|
"title": "R",
|
|
"type": "number"
|
|
},
|
|
"b": {
|
|
"title": "B",
|
|
"type": "number"
|
|
},
|
|
"coord_origin": {
|
|
"$ref": "#/$defs/CoordOrigin",
|
|
"default": "TOPLEFT"
|
|
}
|
|
},
|
|
"required": [
|
|
"l",
|
|
"t",
|
|
"r",
|
|
"b"
|
|
],
|
|
"title": "BoundingBox",
|
|
"type": "object"
|
|
},
|
|
"ChartBar": {
|
|
"description": "Represents a bar in a bar chart.\n\nAttributes:\n label (str): The label for the bar.\n values (float): The value associated with the bar.",
|
|
"properties": {
|
|
"label": {
|
|
"title": "Label",
|
|
"type": "string"
|
|
},
|
|
"values": {
|
|
"title": "Values",
|
|
"type": "number"
|
|
}
|
|
},
|
|
"required": [
|
|
"label",
|
|
"values"
|
|
],
|
|
"title": "ChartBar",
|
|
"type": "object"
|
|
},
|
|
"ChartLine": {
|
|
"description": "Represents a line in a line chart.\n\nAttributes:\n label (str): The label for the line.\n values (List[Tuple[float, float]]): A list of (x, y) coordinate pairs\n representing the line's data points.",
|
|
"properties": {
|
|
"label": {
|
|
"title": "Label",
|
|
"type": "string"
|
|
},
|
|
"values": {
|
|
"items": {
|
|
"maxItems": 2,
|
|
"minItems": 2,
|
|
"prefixItems": [
|
|
{
|
|
"type": "number"
|
|
},
|
|
{
|
|
"type": "number"
|
|
}
|
|
],
|
|
"type": "array"
|
|
},
|
|
"title": "Values",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"label",
|
|
"values"
|
|
],
|
|
"title": "ChartLine",
|
|
"type": "object"
|
|
},
|
|
"ChartPoint": {
|
|
"description": "Represents a point in a scatter chart.\n\nAttributes:\n value (Tuple[float, float]): A (x, y) coordinate pair representing a point in a\n chart.",
|
|
"properties": {
|
|
"value": {
|
|
"maxItems": 2,
|
|
"minItems": 2,
|
|
"prefixItems": [
|
|
{
|
|
"type": "number"
|
|
},
|
|
{
|
|
"type": "number"
|
|
}
|
|
],
|
|
"title": "Value",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"value"
|
|
],
|
|
"title": "ChartPoint",
|
|
"type": "object"
|
|
},
|
|
"ChartSlice": {
|
|
"description": "Represents a slice in a pie chart.\n\nAttributes:\n label (str): The label for the slice.\n value (float): The value represented by the slice.",
|
|
"properties": {
|
|
"label": {
|
|
"title": "Label",
|
|
"type": "string"
|
|
},
|
|
"value": {
|
|
"title": "Value",
|
|
"type": "number"
|
|
}
|
|
},
|
|
"required": [
|
|
"label",
|
|
"value"
|
|
],
|
|
"title": "ChartSlice",
|
|
"type": "object"
|
|
},
|
|
"ChartStackedBar": {
|
|
"description": "Represents a stacked bar in a stacked bar chart.\n\nAttributes:\n label (List[str]): The labels for the stacked bars. Multiple values are stored\n in cases where the chart is \"double stacked,\" meaning bars are stacked both\n horizontally and vertically.\n values (List[Tuple[str, int]]): A list of values representing different segments\n of the stacked bar along with their label.",
|
|
"properties": {
|
|
"label": {
|
|
"items": {
|
|
"type": "string"
|
|
},
|
|
"title": "Label",
|
|
"type": "array"
|
|
},
|
|
"values": {
|
|
"items": {
|
|
"maxItems": 2,
|
|
"minItems": 2,
|
|
"prefixItems": [
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "integer"
|
|
}
|
|
],
|
|
"type": "array"
|
|
},
|
|
"title": "Values",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"label",
|
|
"values"
|
|
],
|
|
"title": "ChartStackedBar",
|
|
"type": "object"
|
|
},
|
|
"CoordOrigin": {
|
|
"description": "CoordOrigin.",
|
|
"enum": [
|
|
"TOPLEFT",
|
|
"BOTTOMLEFT"
|
|
],
|
|
"title": "CoordOrigin",
|
|
"type": "string"
|
|
},
|
|
"DocItemLabel": {
|
|
"description": "DocItemLabel.",
|
|
"enum": [
|
|
"caption",
|
|
"footnote",
|
|
"formula",
|
|
"list_item",
|
|
"page_footer",
|
|
"page_header",
|
|
"picture",
|
|
"section_header",
|
|
"table",
|
|
"text",
|
|
"title",
|
|
"document_index",
|
|
"code",
|
|
"checkbox_selected",
|
|
"checkbox_unselected",
|
|
"form",
|
|
"key_value_region",
|
|
"paragraph",
|
|
"reference"
|
|
],
|
|
"title": "DocItemLabel",
|
|
"type": "string"
|
|
},
|
|
"DocumentOrigin": {
|
|
"description": "FileSource.",
|
|
"properties": {
|
|
"mimetype": {
|
|
"title": "Mimetype",
|
|
"type": "string"
|
|
},
|
|
"binary_hash": {
|
|
"maximum": 18446744073709551615,
|
|
"minimum": 0,
|
|
"title": "Binary Hash",
|
|
"type": "integer"
|
|
},
|
|
"filename": {
|
|
"title": "Filename",
|
|
"type": "string"
|
|
},
|
|
"uri": {
|
|
"anyOf": [
|
|
{
|
|
"format": "uri",
|
|
"minLength": 1,
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"title": "Uri"
|
|
}
|
|
},
|
|
"required": [
|
|
"mimetype",
|
|
"binary_hash",
|
|
"filename"
|
|
],
|
|
"title": "DocumentOrigin",
|
|
"type": "object"
|
|
},
|
|
"GroupItem": {
|
|
"additionalProperties": false,
|
|
"description": "GroupItem.",
|
|
"properties": {
|
|
"self_ref": {
|
|
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
|
|
"title": "Self Ref",
|
|
"type": "string"
|
|
},
|
|
"parent": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"children": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Children",
|
|
"type": "array"
|
|
},
|
|
"name": {
|
|
"default": "group",
|
|
"title": "Name",
|
|
"type": "string"
|
|
},
|
|
"label": {
|
|
"$ref": "#/$defs/GroupLabel",
|
|
"default": "unspecified"
|
|
}
|
|
},
|
|
"required": [
|
|
"self_ref"
|
|
],
|
|
"title": "GroupItem",
|
|
"type": "object"
|
|
},
|
|
"GroupLabel": {
|
|
"description": "GroupLabel.",
|
|
"enum": [
|
|
"unspecified",
|
|
"list",
|
|
"ordered_list",
|
|
"chapter",
|
|
"section",
|
|
"sheet",
|
|
"slide"
|
|
],
|
|
"title": "GroupLabel",
|
|
"type": "string"
|
|
},
|
|
"ImageRef": {
|
|
"description": "ImageRef.",
|
|
"properties": {
|
|
"mimetype": {
|
|
"title": "Mimetype",
|
|
"type": "string"
|
|
},
|
|
"dpi": {
|
|
"title": "Dpi",
|
|
"type": "integer"
|
|
},
|
|
"size": {
|
|
"$ref": "#/$defs/Size"
|
|
},
|
|
"uri": {
|
|
"anyOf": [
|
|
{
|
|
"format": "uri",
|
|
"minLength": 1,
|
|
"type": "string"
|
|
},
|
|
{
|
|
"format": "path",
|
|
"type": "string"
|
|
}
|
|
],
|
|
"title": "Uri"
|
|
}
|
|
},
|
|
"required": [
|
|
"mimetype",
|
|
"dpi",
|
|
"size",
|
|
"uri"
|
|
],
|
|
"title": "ImageRef",
|
|
"type": "object"
|
|
},
|
|
"KeyValueItem": {
|
|
"additionalProperties": false,
|
|
"description": "KeyValueItem.",
|
|
"properties": {
|
|
"self_ref": {
|
|
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
|
|
"title": "Self Ref",
|
|
"type": "string"
|
|
},
|
|
"parent": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"children": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Children",
|
|
"type": "array"
|
|
},
|
|
"label": {
|
|
"$ref": "#/$defs/DocItemLabel"
|
|
},
|
|
"prov": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/ProvenanceItem"
|
|
},
|
|
"title": "Prov",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"self_ref",
|
|
"label"
|
|
],
|
|
"title": "KeyValueItem",
|
|
"type": "object"
|
|
},
|
|
"ListItem": {
|
|
"additionalProperties": false,
|
|
"description": "SectionItem.",
|
|
"properties": {
|
|
"self_ref": {
|
|
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
|
|
"title": "Self Ref",
|
|
"type": "string"
|
|
},
|
|
"parent": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"children": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Children",
|
|
"type": "array"
|
|
},
|
|
"label": {
|
|
"const": "list_item",
|
|
"default": "list_item",
|
|
"enum": [
|
|
"list_item"
|
|
],
|
|
"title": "Label",
|
|
"type": "string"
|
|
},
|
|
"prov": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/ProvenanceItem"
|
|
},
|
|
"title": "Prov",
|
|
"type": "array"
|
|
},
|
|
"orig": {
|
|
"title": "Orig",
|
|
"type": "string"
|
|
},
|
|
"text": {
|
|
"title": "Text",
|
|
"type": "string"
|
|
},
|
|
"enumerated": {
|
|
"default": false,
|
|
"title": "Enumerated",
|
|
"type": "boolean"
|
|
},
|
|
"marker": {
|
|
"title": "Marker",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"self_ref",
|
|
"orig",
|
|
"text",
|
|
"marker"
|
|
],
|
|
"title": "ListItem",
|
|
"type": "object"
|
|
},
|
|
"PageItem": {
|
|
"description": "PageItem.",
|
|
"properties": {
|
|
"size": {
|
|
"$ref": "#/$defs/Size"
|
|
},
|
|
"image": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/ImageRef"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"page_no": {
|
|
"title": "Page No",
|
|
"type": "integer"
|
|
}
|
|
},
|
|
"required": [
|
|
"size",
|
|
"page_no"
|
|
],
|
|
"title": "PageItem",
|
|
"type": "object"
|
|
},
|
|
"PictureBarChartData": {
|
|
"description": "Represents data of a bar chart.\n\nAttributes:\n kind (Literal[\"bar_chart_data\"]): The type of the chart.\n x_axis_label (str): The label for the x-axis.\n y_axis_label (str): The label for the y-axis.\n bars (List[ChartBar]): A list of bars in the chart.",
|
|
"properties": {
|
|
"title": {
|
|
"title": "Title",
|
|
"type": "string"
|
|
},
|
|
"kind": {
|
|
"const": "bar_chart_data",
|
|
"default": "bar_chart_data",
|
|
"enum": [
|
|
"bar_chart_data"
|
|
],
|
|
"title": "Kind",
|
|
"type": "string"
|
|
},
|
|
"x_axis_label": {
|
|
"title": "X Axis Label",
|
|
"type": "string"
|
|
},
|
|
"y_axis_label": {
|
|
"title": "Y Axis Label",
|
|
"type": "string"
|
|
},
|
|
"bars": {
|
|
"items": {
|
|
"$ref": "#/$defs/ChartBar"
|
|
},
|
|
"title": "Bars",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"title",
|
|
"x_axis_label",
|
|
"y_axis_label",
|
|
"bars"
|
|
],
|
|
"title": "PictureBarChartData",
|
|
"type": "object"
|
|
},
|
|
"PictureClassificationClass": {
|
|
"description": "PictureClassificationData.",
|
|
"properties": {
|
|
"class_name": {
|
|
"title": "Class Name",
|
|
"type": "string"
|
|
},
|
|
"confidence": {
|
|
"title": "Confidence",
|
|
"type": "number"
|
|
}
|
|
},
|
|
"required": [
|
|
"class_name",
|
|
"confidence"
|
|
],
|
|
"title": "PictureClassificationClass",
|
|
"type": "object"
|
|
},
|
|
"PictureClassificationData": {
|
|
"description": "PictureClassificationData.",
|
|
"properties": {
|
|
"kind": {
|
|
"const": "classification",
|
|
"default": "classification",
|
|
"enum": [
|
|
"classification"
|
|
],
|
|
"title": "Kind",
|
|
"type": "string"
|
|
},
|
|
"provenance": {
|
|
"title": "Provenance",
|
|
"type": "string"
|
|
},
|
|
"predicted_classes": {
|
|
"items": {
|
|
"$ref": "#/$defs/PictureClassificationClass"
|
|
},
|
|
"title": "Predicted Classes",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"provenance",
|
|
"predicted_classes"
|
|
],
|
|
"title": "PictureClassificationData",
|
|
"type": "object"
|
|
},
|
|
"PictureDescriptionData": {
|
|
"description": "PictureDescriptionData.",
|
|
"properties": {
|
|
"kind": {
|
|
"const": "description",
|
|
"default": "description",
|
|
"enum": [
|
|
"description"
|
|
],
|
|
"title": "Kind",
|
|
"type": "string"
|
|
},
|
|
"text": {
|
|
"title": "Text",
|
|
"type": "string"
|
|
},
|
|
"provenance": {
|
|
"title": "Provenance",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"text",
|
|
"provenance"
|
|
],
|
|
"title": "PictureDescriptionData",
|
|
"type": "object"
|
|
},
|
|
"PictureItem": {
|
|
"additionalProperties": false,
|
|
"description": "PictureItem.",
|
|
"properties": {
|
|
"self_ref": {
|
|
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
|
|
"title": "Self Ref",
|
|
"type": "string"
|
|
},
|
|
"parent": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"children": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Children",
|
|
"type": "array"
|
|
},
|
|
"label": {
|
|
"const": "picture",
|
|
"default": "picture",
|
|
"enum": [
|
|
"picture"
|
|
],
|
|
"title": "Label",
|
|
"type": "string"
|
|
},
|
|
"prov": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/ProvenanceItem"
|
|
},
|
|
"title": "Prov",
|
|
"type": "array"
|
|
},
|
|
"captions": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Captions",
|
|
"type": "array"
|
|
},
|
|
"references": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "References",
|
|
"type": "array"
|
|
},
|
|
"footnotes": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Footnotes",
|
|
"type": "array"
|
|
},
|
|
"image": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/ImageRef"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"annotations": {
|
|
"default": [],
|
|
"items": {
|
|
"discriminator": {
|
|
"mapping": {
|
|
"bar_chart_data": "#/$defs/PictureBarChartData",
|
|
"classification": "#/$defs/PictureClassificationData",
|
|
"description": "#/$defs/PictureDescriptionData",
|
|
"line_chart_data": "#/$defs/PictureLineChartData",
|
|
"misc": "#/$defs/PictureMiscData",
|
|
"molecule_data": "#/$defs/PictureMoleculeData",
|
|
"pie_chart_data": "#/$defs/PicturePieChartData",
|
|
"scatter_chart_data": "#/$defs/PictureScatterChartData",
|
|
"stacked_bar_chart_data": "#/$defs/PictureStackedBarChartData"
|
|
},
|
|
"propertyName": "kind"
|
|
},
|
|
"oneOf": [
|
|
{
|
|
"$ref": "#/$defs/PictureClassificationData"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/PictureDescriptionData"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/PictureMoleculeData"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/PictureMiscData"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/PictureLineChartData"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/PictureBarChartData"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/PictureStackedBarChartData"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/PicturePieChartData"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/PictureScatterChartData"
|
|
}
|
|
]
|
|
},
|
|
"title": "Annotations",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"self_ref"
|
|
],
|
|
"title": "PictureItem",
|
|
"type": "object"
|
|
},
|
|
"PictureLineChartData": {
|
|
"description": "Represents data of a line chart.\n\nAttributes:\n kind (Literal[\"line_chart_data\"]): The type of the chart.\n x_axis_label (str): The label for the x-axis.\n y_axis_label (str): The label for the y-axis.\n lines (List[ChartLine]): A list of lines in the chart.",
|
|
"properties": {
|
|
"title": {
|
|
"title": "Title",
|
|
"type": "string"
|
|
},
|
|
"kind": {
|
|
"const": "line_chart_data",
|
|
"default": "line_chart_data",
|
|
"enum": [
|
|
"line_chart_data"
|
|
],
|
|
"title": "Kind",
|
|
"type": "string"
|
|
},
|
|
"x_axis_label": {
|
|
"title": "X Axis Label",
|
|
"type": "string"
|
|
},
|
|
"y_axis_label": {
|
|
"title": "Y Axis Label",
|
|
"type": "string"
|
|
},
|
|
"lines": {
|
|
"items": {
|
|
"$ref": "#/$defs/ChartLine"
|
|
},
|
|
"title": "Lines",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"title",
|
|
"x_axis_label",
|
|
"y_axis_label",
|
|
"lines"
|
|
],
|
|
"title": "PictureLineChartData",
|
|
"type": "object"
|
|
},
|
|
"PictureMiscData": {
|
|
"description": "PictureMiscData.",
|
|
"properties": {
|
|
"kind": {
|
|
"const": "misc",
|
|
"default": "misc",
|
|
"enum": [
|
|
"misc"
|
|
],
|
|
"title": "Kind",
|
|
"type": "string"
|
|
},
|
|
"content": {
|
|
"title": "Content",
|
|
"type": "object"
|
|
}
|
|
},
|
|
"required": [
|
|
"content"
|
|
],
|
|
"title": "PictureMiscData",
|
|
"type": "object"
|
|
},
|
|
"PictureMoleculeData": {
|
|
"description": "PictureMoleculeData.",
|
|
"properties": {
|
|
"kind": {
|
|
"const": "molecule_data",
|
|
"default": "molecule_data",
|
|
"enum": [
|
|
"molecule_data"
|
|
],
|
|
"title": "Kind",
|
|
"type": "string"
|
|
},
|
|
"smi": {
|
|
"title": "Smi",
|
|
"type": "string"
|
|
},
|
|
"confidence": {
|
|
"title": "Confidence",
|
|
"type": "number"
|
|
},
|
|
"class_name": {
|
|
"title": "Class Name",
|
|
"type": "string"
|
|
},
|
|
"segmentation": {
|
|
"items": {
|
|
"maxItems": 2,
|
|
"minItems": 2,
|
|
"prefixItems": [
|
|
{
|
|
"type": "number"
|
|
},
|
|
{
|
|
"type": "number"
|
|
}
|
|
],
|
|
"type": "array"
|
|
},
|
|
"title": "Segmentation",
|
|
"type": "array"
|
|
},
|
|
"provenance": {
|
|
"title": "Provenance",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"smi",
|
|
"confidence",
|
|
"class_name",
|
|
"segmentation",
|
|
"provenance"
|
|
],
|
|
"title": "PictureMoleculeData",
|
|
"type": "object"
|
|
},
|
|
"PicturePieChartData": {
|
|
"description": "Represents data of a pie chart.\n\nAttributes:\n kind (Literal[\"pie_chart_data\"]): The type of the chart.\n slices (List[ChartSlice]): A list of slices in the pie chart.",
|
|
"properties": {
|
|
"title": {
|
|
"title": "Title",
|
|
"type": "string"
|
|
},
|
|
"kind": {
|
|
"const": "pie_chart_data",
|
|
"default": "pie_chart_data",
|
|
"enum": [
|
|
"pie_chart_data"
|
|
],
|
|
"title": "Kind",
|
|
"type": "string"
|
|
},
|
|
"slices": {
|
|
"items": {
|
|
"$ref": "#/$defs/ChartSlice"
|
|
},
|
|
"title": "Slices",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"title",
|
|
"slices"
|
|
],
|
|
"title": "PicturePieChartData",
|
|
"type": "object"
|
|
},
|
|
"PictureScatterChartData": {
|
|
"description": "Represents data of a scatter chart.\n\nAttributes:\n kind (Literal[\"scatter_chart_data\"]): The type of the chart.\n x_axis_label (str): The label for the x-axis.\n y_axis_label (str): The label for the y-axis.\n points (List[ChartPoint]): A list of points in the scatter chart.",
|
|
"properties": {
|
|
"title": {
|
|
"title": "Title",
|
|
"type": "string"
|
|
},
|
|
"kind": {
|
|
"const": "scatter_chart_data",
|
|
"default": "scatter_chart_data",
|
|
"enum": [
|
|
"scatter_chart_data"
|
|
],
|
|
"title": "Kind",
|
|
"type": "string"
|
|
},
|
|
"x_axis_label": {
|
|
"title": "X Axis Label",
|
|
"type": "string"
|
|
},
|
|
"y_axis_label": {
|
|
"title": "Y Axis Label",
|
|
"type": "string"
|
|
},
|
|
"points": {
|
|
"items": {
|
|
"$ref": "#/$defs/ChartPoint"
|
|
},
|
|
"title": "Points",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"title",
|
|
"x_axis_label",
|
|
"y_axis_label",
|
|
"points"
|
|
],
|
|
"title": "PictureScatterChartData",
|
|
"type": "object"
|
|
},
|
|
"PictureStackedBarChartData": {
|
|
"description": "Represents data of a stacked bar chart.\n\nAttributes:\n kind (Literal[\"stacked_bar_chart_data\"]): The type of the chart.\n x_axis_label (str): The label for the x-axis.\n y_axis_label (str): The label for the y-axis.\n stacked_bars (List[ChartStackedBar]): A list of stacked bars in the chart.",
|
|
"properties": {
|
|
"title": {
|
|
"title": "Title",
|
|
"type": "string"
|
|
},
|
|
"kind": {
|
|
"const": "stacked_bar_chart_data",
|
|
"default": "stacked_bar_chart_data",
|
|
"enum": [
|
|
"stacked_bar_chart_data"
|
|
],
|
|
"title": "Kind",
|
|
"type": "string"
|
|
},
|
|
"x_axis_label": {
|
|
"title": "X Axis Label",
|
|
"type": "string"
|
|
},
|
|
"y_axis_label": {
|
|
"title": "Y Axis Label",
|
|
"type": "string"
|
|
},
|
|
"stacked_bars": {
|
|
"items": {
|
|
"$ref": "#/$defs/ChartStackedBar"
|
|
},
|
|
"title": "Stacked Bars",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"title",
|
|
"x_axis_label",
|
|
"y_axis_label",
|
|
"stacked_bars"
|
|
],
|
|
"title": "PictureStackedBarChartData",
|
|
"type": "object"
|
|
},
|
|
"ProvenanceItem": {
|
|
"description": "ProvenanceItem.",
|
|
"properties": {
|
|
"page_no": {
|
|
"title": "Page No",
|
|
"type": "integer"
|
|
},
|
|
"bbox": {
|
|
"$ref": "#/$defs/BoundingBox"
|
|
},
|
|
"charspan": {
|
|
"maxItems": 2,
|
|
"minItems": 2,
|
|
"prefixItems": [
|
|
{
|
|
"type": "integer"
|
|
},
|
|
{
|
|
"type": "integer"
|
|
}
|
|
],
|
|
"title": "Charspan",
|
|
"type": "array"
|
|
}
|
|
},
|
|
"required": [
|
|
"page_no",
|
|
"bbox",
|
|
"charspan"
|
|
],
|
|
"title": "ProvenanceItem",
|
|
"type": "object"
|
|
},
|
|
"RefItem": {
|
|
"description": "RefItem.",
|
|
"properties": {
|
|
"$ref": {
|
|
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
|
|
"title": "$Ref",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"$ref"
|
|
],
|
|
"title": "RefItem",
|
|
"type": "object"
|
|
},
|
|
"SectionHeaderItem": {
|
|
"additionalProperties": false,
|
|
"description": "SectionItem.",
|
|
"properties": {
|
|
"self_ref": {
|
|
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
|
|
"title": "Self Ref",
|
|
"type": "string"
|
|
},
|
|
"parent": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"children": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Children",
|
|
"type": "array"
|
|
},
|
|
"label": {
|
|
"const": "section_header",
|
|
"default": "section_header",
|
|
"enum": [
|
|
"section_header"
|
|
],
|
|
"title": "Label",
|
|
"type": "string"
|
|
},
|
|
"prov": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/ProvenanceItem"
|
|
},
|
|
"title": "Prov",
|
|
"type": "array"
|
|
},
|
|
"orig": {
|
|
"title": "Orig",
|
|
"type": "string"
|
|
},
|
|
"text": {
|
|
"title": "Text",
|
|
"type": "string"
|
|
},
|
|
"level": {
|
|
"maximum": 100,
|
|
"minimum": 1,
|
|
"title": "Level",
|
|
"type": "integer"
|
|
}
|
|
},
|
|
"required": [
|
|
"self_ref",
|
|
"orig",
|
|
"text",
|
|
"level"
|
|
],
|
|
"title": "SectionHeaderItem",
|
|
"type": "object"
|
|
},
|
|
"Size": {
|
|
"description": "Size.",
|
|
"properties": {
|
|
"width": {
|
|
"default": 0.0,
|
|
"title": "Width",
|
|
"type": "number"
|
|
},
|
|
"height": {
|
|
"default": 0.0,
|
|
"title": "Height",
|
|
"type": "number"
|
|
}
|
|
},
|
|
"title": "Size",
|
|
"type": "object"
|
|
},
|
|
"TableCell": {
|
|
"description": "TableCell.",
|
|
"properties": {
|
|
"bbox": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/BoundingBox"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"row_span": {
|
|
"default": 1,
|
|
"title": "Row Span",
|
|
"type": "integer"
|
|
},
|
|
"col_span": {
|
|
"default": 1,
|
|
"title": "Col Span",
|
|
"type": "integer"
|
|
},
|
|
"start_row_offset_idx": {
|
|
"title": "Start Row Offset Idx",
|
|
"type": "integer"
|
|
},
|
|
"end_row_offset_idx": {
|
|
"title": "End Row Offset Idx",
|
|
"type": "integer"
|
|
},
|
|
"start_col_offset_idx": {
|
|
"title": "Start Col Offset Idx",
|
|
"type": "integer"
|
|
},
|
|
"end_col_offset_idx": {
|
|
"title": "End Col Offset Idx",
|
|
"type": "integer"
|
|
},
|
|
"text": {
|
|
"title": "Text",
|
|
"type": "string"
|
|
},
|
|
"column_header": {
|
|
"default": false,
|
|
"title": "Column Header",
|
|
"type": "boolean"
|
|
},
|
|
"row_header": {
|
|
"default": false,
|
|
"title": "Row Header",
|
|
"type": "boolean"
|
|
},
|
|
"row_section": {
|
|
"default": false,
|
|
"title": "Row Section",
|
|
"type": "boolean"
|
|
}
|
|
},
|
|
"required": [
|
|
"start_row_offset_idx",
|
|
"end_row_offset_idx",
|
|
"start_col_offset_idx",
|
|
"end_col_offset_idx",
|
|
"text"
|
|
],
|
|
"title": "TableCell",
|
|
"type": "object"
|
|
},
|
|
"TableData": {
|
|
"description": "BaseTableData.",
|
|
"properties": {
|
|
"table_cells": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/TableCell"
|
|
},
|
|
"title": "Table Cells",
|
|
"type": "array"
|
|
},
|
|
"num_rows": {
|
|
"default": 0,
|
|
"title": "Num Rows",
|
|
"type": "integer"
|
|
},
|
|
"num_cols": {
|
|
"default": 0,
|
|
"title": "Num Cols",
|
|
"type": "integer"
|
|
}
|
|
},
|
|
"title": "TableData",
|
|
"type": "object"
|
|
},
|
|
"TableItem": {
|
|
"additionalProperties": false,
|
|
"description": "TableItem.",
|
|
"properties": {
|
|
"self_ref": {
|
|
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
|
|
"title": "Self Ref",
|
|
"type": "string"
|
|
},
|
|
"parent": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"children": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Children",
|
|
"type": "array"
|
|
},
|
|
"label": {
|
|
"const": "table",
|
|
"default": "table",
|
|
"enum": [
|
|
"table"
|
|
],
|
|
"title": "Label",
|
|
"type": "string"
|
|
},
|
|
"prov": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/ProvenanceItem"
|
|
},
|
|
"title": "Prov",
|
|
"type": "array"
|
|
},
|
|
"captions": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Captions",
|
|
"type": "array"
|
|
},
|
|
"references": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "References",
|
|
"type": "array"
|
|
},
|
|
"footnotes": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Footnotes",
|
|
"type": "array"
|
|
},
|
|
"image": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/ImageRef"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"data": {
|
|
"$ref": "#/$defs/TableData"
|
|
}
|
|
},
|
|
"required": [
|
|
"self_ref",
|
|
"data"
|
|
],
|
|
"title": "TableItem",
|
|
"type": "object"
|
|
},
|
|
"TextItem": {
|
|
"additionalProperties": false,
|
|
"description": "TextItem.",
|
|
"properties": {
|
|
"self_ref": {
|
|
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
|
|
"title": "Self Ref",
|
|
"type": "string"
|
|
},
|
|
"parent": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"children": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/RefItem"
|
|
},
|
|
"title": "Children",
|
|
"type": "array"
|
|
},
|
|
"label": {
|
|
"$ref": "#/$defs/DocItemLabel"
|
|
},
|
|
"prov": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/ProvenanceItem"
|
|
},
|
|
"title": "Prov",
|
|
"type": "array"
|
|
},
|
|
"orig": {
|
|
"title": "Orig",
|
|
"type": "string"
|
|
},
|
|
"text": {
|
|
"title": "Text",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"self_ref",
|
|
"label",
|
|
"orig",
|
|
"text"
|
|
],
|
|
"title": "TextItem",
|
|
"type": "object"
|
|
}
|
|
},
|
|
"description": "DoclingDocument.",
|
|
"properties": {
|
|
"schema_name": {
|
|
"const": "DoclingDocument",
|
|
"default": "DoclingDocument",
|
|
"enum": [
|
|
"DoclingDocument"
|
|
],
|
|
"title": "Schema Name",
|
|
"type": "string"
|
|
},
|
|
"version": {
|
|
"default": "1.0.0",
|
|
"pattern": "^(?P<major>0|[1-9]\\d*)\\.(?P<minor>0|[1-9]\\d*)\\.(?P<patch>0|[1-9]\\d*)(?:-(?P<prerelease>(?:0|[1-9]\\d*|\\d*[a-zA-Z-][0-9a-zA-Z-]*)(?:\\.(?:0|[1-9]\\d*|\\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\\+(?P<buildmetadata>[0-9a-zA-Z-]+(?:\\.[0-9a-zA-Z-]+)*))?$",
|
|
"title": "Version",
|
|
"type": "string"
|
|
},
|
|
"name": {
|
|
"title": "Name",
|
|
"type": "string"
|
|
},
|
|
"origin": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/DocumentOrigin"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null
|
|
},
|
|
"furniture": {
|
|
"$ref": "#/$defs/GroupItem",
|
|
"default": {
|
|
"self_ref": "#/furniture",
|
|
"parent": null,
|
|
"children": [],
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
}
|
|
},
|
|
"body": {
|
|
"$ref": "#/$defs/GroupItem",
|
|
"default": {
|
|
"self_ref": "#/body",
|
|
"parent": null,
|
|
"children": [],
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
}
|
|
},
|
|
"groups": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/GroupItem"
|
|
},
|
|
"title": "Groups",
|
|
"type": "array"
|
|
},
|
|
"texts": {
|
|
"default": [],
|
|
"items": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/$defs/SectionHeaderItem"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/ListItem"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/TextItem"
|
|
}
|
|
]
|
|
},
|
|
"title": "Texts",
|
|
"type": "array"
|
|
},
|
|
"pictures": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/PictureItem"
|
|
},
|
|
"title": "Pictures",
|
|
"type": "array"
|
|
},
|
|
"tables": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/TableItem"
|
|
},
|
|
"title": "Tables",
|
|
"type": "array"
|
|
},
|
|
"key_value_items": {
|
|
"default": [],
|
|
"items": {
|
|
"$ref": "#/$defs/KeyValueItem"
|
|
},
|
|
"title": "Key Value Items",
|
|
"type": "array"
|
|
},
|
|
"pages": {
|
|
"additionalProperties": {
|
|
"$ref": "#/$defs/PageItem"
|
|
},
|
|
"default": {},
|
|
"title": "Pages",
|
|
"type": "object"
|
|
}
|
|
},
|
|
"required": [
|
|
"name"
|
|
],
|
|
"title": "DoclingDocument",
|
|
"type": "object"
|
|
} |