{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "$id": "https://aws.amazon.com/textract/schemas/documentanalysis",
  "title": "DocumentAnalysis",
  "description": "Schema for an Amazon Textract document analysis response containing detected blocks of text, tables, forms, and layout elements extracted from a document.",
  "type": "object",
  "properties": {
    "DocumentMetadata": {
      "type": "object",
      "description": "Metadata about the analyzed document.",
      "properties": {
        "Pages": {
          "type": "integer",
          "description": "The number of pages detected in the document.",
          "minimum": 1
        }
      },
      "required": ["Pages"]
    },
    "Blocks": {
      "type": "array",
      "description": "The items detected in the document, including text lines, words, tables, and form elements.",
      "items": {
        "type": "object",
        "properties": {
          "BlockType": {
            "type": "string",
            "description": "The type of text item detected.",
            "enum": [
              "KEY_VALUE_SET",
              "PAGE",
              "LINE",
              "WORD",
              "TABLE",
              "CELL",
              "SELECTION_ELEMENT",
              "MERGED_CELL",
              "TITLE",
              "QUERY",
              "QUERY_RESULT",
              "SIGNATURE",
              "TABLE_TITLE",
              "TABLE_FOOTER",
              "LAYOUT_TEXT",
              "LAYOUT_TITLE",
              "LAYOUT_HEADER",
              "LAYOUT_FOOTER",
              "LAYOUT_SECTION_HEADER",
              "LAYOUT_PAGE_NUMBER",
              "LAYOUT_LIST",
              "LAYOUT_FIGURE",
              "LAYOUT_TABLE",
              "LAYOUT_KEY_VALUE"
            ]
          },
          "Confidence": {
            "type": "number",
            "description": "The confidence that Amazon Textract has in the accuracy of the detected block.",
            "minimum": 0,
            "maximum": 100
          },
          "Text": {
            "type": "string",
            "description": "The word or line of text that is recognized by Amazon Textract."
          },
          "TextType": {
            "type": "string",
            "description": "The kind of text detected.",
            "enum": ["HANDWRITING", "PRINTED"]
          },
          "RowIndex": {
            "type": "integer",
            "description": "The row in which a table cell is located.",
            "minimum": 1
          },
          "ColumnIndex": {
            "type": "integer",
            "description": "The column in which a table cell appears.",
            "minimum": 1
          },
          "RowSpan": {
            "type": "integer",
            "description": "The number of rows that a table cell spans.",
            "minimum": 1
          },
          "ColumnSpan": {
            "type": "integer",
            "description": "The number of columns that a table cell spans.",
            "minimum": 1
          },
          "Geometry": {
            "type": "object",
            "description": "The location of the detected block on the document page.",
            "properties": {
              "BoundingBox": {
                "type": "object",
                "description": "An axis-aligned bounding box for the detected block.",
                "properties": {
                  "Width": {
                    "type": "number",
                    "description": "The width of the bounding box as a ratio of the overall document page width."
                  },
                  "Height": {
                    "type": "number",
                    "description": "The height of the bounding box as a ratio of the overall document page height."
                  },
                  "Left": {
                    "type": "number",
                    "description": "The left coordinate of the bounding box."
                  },
                  "Top": {
                    "type": "number",
                    "description": "The top coordinate of the bounding box."
                  }
                },
                "required": ["Width", "Height", "Left", "Top"]
              },
              "Polygon": {
                "type": "array",
                "description": "A fine-grained polygon around the detected block.",
                "items": {
                  "type": "object",
                  "properties": {
                    "X": {
                      "type": "number"
                    },
                    "Y": {
                      "type": "number"
                    }
                  },
                  "required": ["X", "Y"]
                }
              }
            }
          },
          "Id": {
            "type": "string",
            "description": "The identifier for the recognized text block."
          },
          "Relationships": {
            "type": "array",
            "description": "A list of relationship objects that describe how blocks are related to each other.",
            "items": {
              "type": "object",
              "properties": {
                "Type": {
                  "type": "string",
                  "description": "The type of relationship.",
                  "enum": ["VALUE", "CHILD", "COMPLEX_FEATURES", "MERGED_CELL", "TITLE", "ANSWER", "TABLE", "TABLE_TITLE", "TABLE_FOOTER"]
                },
                "Ids": {
                  "type": "array",
                  "description": "An array of IDs for related blocks.",
                  "items": {
                    "type": "string"
                  }
                }
              },
              "required": ["Type", "Ids"]
            }
          },
          "EntityTypes": {
            "type": "array",
            "description": "The type of entity such as KEY or VALUE.",
            "items": {
              "type": "string",
              "enum": ["KEY", "VALUE", "COLUMN_HEADER", "TABLE_TITLE", "TABLE_FOOTER", "TABLE_SECTION_TITLE", "TABLE_SUMMARY", "STRUCTURED_TABLE", "SEMI_STRUCTURED_TABLE"]
            }
          },
          "SelectionStatus": {
            "type": "string",
            "description": "The selection status of a selection element.",
            "enum": ["SELECTED", "NOT_SELECTED"]
          },
          "Page": {
            "type": "integer",
            "description": "The page on which the block was detected.",
            "minimum": 1
          },
          "Query": {
            "type": "object",
            "description": "The query that was used for query-based analysis.",
            "properties": {
              "Text": {
                "type": "string"
              },
              "Alias": {
                "type": "string"
              },
              "Pages": {
                "type": "array",
                "items": {
                  "type": "string"
                }
              }
            },
            "required": ["Text"]
          }
        },
        "required": ["BlockType"]
      }
    },
    "AnalyzeDocumentModelVersion": {
      "type": "string",
      "description": "The version of the model used to analyze the document."
    }
  },
  "required": ["DocumentMetadata", "Blocks"]
}