Class: Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/documentai/v1beta3/document.rb

Overview

Represents the parsed layout of a document as a collection of blocks that the document is divided into.

Defined Under Namespace

Classes: DocumentLayoutBlock

Instance Attribute Summary collapse

Instance Attribute Details

#blocks ⇒ ::Array<::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock>

Returns List of blocks in the document.

Returns:



1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
 
# File 'proto_docs/google/cloud/documentai/v1beta3/document.rb', line 1100

class DocumentLayout
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Represents a block. A block could be one of the various types (text,
  # table, list) supported.
  # @!attribute [rw] text_block
  #   @return [::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock::LayoutTextBlock]
  #     Block consisting of text content.
  #
  #     Note: The following fields are mutually exclusive: `text_block`, `table_block`, `list_block`, `image_block`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  # @!attribute [rw] table_block
  #   @return [::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock::LayoutTableBlock]
  #     Block consisting of table content/structure.
  #
  #     Note: The following fields are mutually exclusive: `table_block`, `text_block`, `list_block`, `image_block`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  # @!attribute [rw] list_block
  #   @return [::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock::LayoutListBlock]
  #     Block consisting of list content/structure.
  #
  #     Note: The following fields are mutually exclusive: `list_block`, `text_block`, `table_block`, `image_block`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  # @!attribute [rw] image_block
  #   @return [::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock::LayoutImageBlock]
  #     Block consisting of image content.
  #
  #     Note: The following fields are mutually exclusive: `image_block`, `text_block`, `table_block`, `list_block`. If a field in that set is populated, all other fields in the set will automatically be cleared.
  # @!attribute [rw] block_id
  #   @return [::String]
  #     ID of the block.
  # @!attribute [rw] page_span
  #   @return [::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock::LayoutPageSpan]
  #     Page span of the block.
  # @!attribute [rw] bounding_box
  #   @return [::Google::Cloud::DocumentAI::V1beta3::BoundingPoly]
  #     Identifies the bounding box for the block.
  class DocumentLayoutBlock
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Represents where the block starts and ends in the document.
    # @!attribute [rw] page_start
    #   @return [::Integer]
    #     Page where block starts in the document.
    # @!attribute [rw] page_end
    #   @return [::Integer]
    #     Page where block ends in the document.
    class LayoutPageSpan
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Represents a text type block.
    # @!attribute [rw] text
    #   @return [::String]
    #     Text content stored in the block.
    # @!attribute [rw] type
    #   @return [::String]
    #     Type of the text in the block. Available options are: `paragraph`,
    #     `subtitle`, `heading-1`, `heading-2`, `heading-3`, `heading-4`,
    #     `heading-5`, `header`, `footer`.
    # @!attribute [rw] blocks
    #   @return [::Array<::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock>]
    #     A text block could further have child blocks.
    #     Repeated blocks support further hierarchies and nested blocks.
    class LayoutTextBlock
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Represents a table type block.
    # @!attribute [rw] header_rows
    #   @return [::Array<::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock::LayoutTableRow>]
    #     Header rows at the top of the table.
    # @!attribute [rw] body_rows
    #   @return [::Array<::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock::LayoutTableRow>]
    #     Body rows containing main table content.
    # @!attribute [rw] caption
    #   @return [::String]
    #     Table caption/title.
    class LayoutTableBlock
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Represents a row in a table.
    # @!attribute [rw] cells
    #   @return [::Array<::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock::LayoutTableCell>]
    #     A table row is a list of table cells.
    class LayoutTableRow
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Represents a cell in a table row.
    # @!attribute [rw] blocks
    #   @return [::Array<::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock>]
    #     A table cell is a list of blocks.
    #     Repeated blocks support further hierarchies and nested blocks.
    # @!attribute [rw] row_span
    #   @return [::Integer]
    #     How many rows this cell spans.
    # @!attribute [rw] col_span
    #   @return [::Integer]
    #     How many columns this cell spans.
    class LayoutTableCell
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Represents a list type block.
    # @!attribute [rw] list_entries
    #   @return [::Array<::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock::LayoutListEntry>]
    #     List entries that constitute a list block.
    # @!attribute [rw] type
    #   @return [::String]
    #     Type of the list_entries (if exist). Available options are `ordered`
    #     and `unordered`.
    class LayoutListBlock
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Represents an entry in the list.
    # @!attribute [rw] blocks
    #   @return [::Array<::Google::Cloud::DocumentAI::V1beta3::Document::DocumentLayout::DocumentLayoutBlock>]
    #     A list entry is a list of blocks.
    #     Repeated blocks support further hierarchies and nested blocks.
    class LayoutListEntry
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Represents an image type block.
    # @!attribute [rw] blob_asset_id
    #   @return [::String]
    #     Optional. Asset id of the inline image. If set, find the image
    #     content in the blob_assets field.
    #
    #     Note: The following fields are mutually exclusive: `blob_asset_id`, `gcs_uri`, `data_uri`. If a field in that set is populated, all other fields in the set will automatically be cleared.
    # @!attribute [rw] gcs_uri
    #   @return [::String]
    #     Optional. Google Cloud Storage uri of the image.
    #
    #     Note: The following fields are mutually exclusive: `gcs_uri`, `blob_asset_id`, `data_uri`. If a field in that set is populated, all other fields in the set will automatically be cleared.
    # @!attribute [rw] data_uri
    #   @return [::String]
    #     Optional. Data uri of the image.
    #     It is composed of four parts: a prefix (data:), a MIME type
    #     indicating the type of data, an optional base64 token if
    #     non-textual, and the data itself:
    #     data:[<mediatype>][;base64],<data>
    #
    #     Note: The following fields are mutually exclusive: `data_uri`, `blob_asset_id`, `gcs_uri`. If a field in that set is populated, all other fields in the set will automatically be cleared.
    # @!attribute [rw] mime_type
    #   @return [::String]
    #     Mime type of the image. An IANA published [media type (MIME type)]
    #     (https://www.iana.org/assignments/media-types/media-types.xhtml).
    # @!attribute [rw] image_text
    #   @return [::String]
    #     Text extracted from the image using OCR or alt text describing the
    #     image.
    # @!attribute [rw] annotations
    #   @return [::Google::Cloud::DocumentAI::V1beta3::Document::Annotations]
    #     Annotation of the image block.
    class LayoutImageBlock
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end