Class: Google::Cloud::AutoML::V1beta1::Document

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/automl/v1beta1/data_items.rb

Overview

A structured text document e.g. a PDF.

Defined Under Namespace

Classes: Layout

Instance Attribute Summary collapse

Instance Attribute Details

#document_dimensions ⇒ ::Google::Cloud::AutoML::V1beta1::DocumentDimensions

Returns The dimensions of the page in the document.

Returns:



107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
 
# File 'proto_docs/google/cloud/automl/v1beta1/data_items.rb', line 107

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

  # Describes the layout information of a {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the document.
  # @!attribute [rw] text_segment
  #   @return [::Google::Cloud::AutoML::V1beta1::TextSegment]
  #     Text Segment that represents a segment in
  #     {::Google::Cloud::AutoML::V1beta1::Document#document_text document_text}.
  # @!attribute [rw] page_number
  #   @return [::Integer]
  #     Page number of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the original document, starts
  #     from 1.
  # @!attribute [rw] bounding_poly
  #   @return [::Google::Cloud::AutoML::V1beta1::BoundingPoly]
  #     The position of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the page.
  #     Contains exactly 4
  #
  #     {::Google::Cloud::AutoML::V1beta1::BoundingPoly#normalized_vertices normalized_vertices}
  #     and they are connected by edges in the order provided, which will
  #     represent a rectangle parallel to the frame. The
  #     {::Google::Cloud::AutoML::V1beta1::NormalizedVertex NormalizedVertex-s} are
  #     relative to the page.
  #     Coordinates are based on top-left as point (0,0).
  # @!attribute [rw] text_segment_type
  #   @return [::Google::Cloud::AutoML::V1beta1::Document::Layout::TextSegmentType]
  #     The type of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in document.
  class Layout
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The type of TextSegment in the context of the original document.
    module TextSegmentType
      # Should not be used.
      TEXT_SEGMENT_TYPE_UNSPECIFIED = 0

      # The text segment is a token. e.g. word.
      TOKEN = 1

      # The text segment is a paragraph.
      PARAGRAPH = 2

      # The text segment is a form field.
      FORM_FIELD = 3

      # The text segment is the name part of a form field. It will be treated
      # as child of another FORM_FIELD TextSegment if its span is subspan of
      # another TextSegment with type FORM_FIELD.
      FORM_FIELD_NAME = 4

      # The text segment is the text content part of a form field. It will be
      # treated as child of another FORM_FIELD TextSegment if its span is
      # subspan of another TextSegment with type FORM_FIELD.
      FORM_FIELD_CONTENTS = 5

      # The text segment is a whole table, including headers, and all rows.
      TABLE = 6

      # The text segment is a table's headers. It will be treated as child of
      # another TABLE TextSegment if its span is subspan of another TextSegment
      # with type TABLE.
      TABLE_HEADER = 7

      # The text segment is a row in table. It will be treated as child of
      # another TABLE TextSegment if its span is subspan of another TextSegment
      # with type TABLE.
      TABLE_ROW = 8

      # The text segment is a cell in table. It will be treated as child of
      # another TABLE_ROW TextSegment if its span is subspan of another
      # TextSegment with type TABLE_ROW.
      TABLE_CELL = 9
    end
  end
end

#document_text ⇒ ::Google::Cloud::AutoML::V1beta1::TextSnippet

Returns The plain text version of this document.

Returns:



107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
 
# File 'proto_docs/google/cloud/automl/v1beta1/data_items.rb', line 107

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

  # Describes the layout information of a {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the document.
  # @!attribute [rw] text_segment
  #   @return [::Google::Cloud::AutoML::V1beta1::TextSegment]
  #     Text Segment that represents a segment in
  #     {::Google::Cloud::AutoML::V1beta1::Document#document_text document_text}.
  # @!attribute [rw] page_number
  #   @return [::Integer]
  #     Page number of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the original document, starts
  #     from 1.
  # @!attribute [rw] bounding_poly
  #   @return [::Google::Cloud::AutoML::V1beta1::BoundingPoly]
  #     The position of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the page.
  #     Contains exactly 4
  #
  #     {::Google::Cloud::AutoML::V1beta1::BoundingPoly#normalized_vertices normalized_vertices}
  #     and they are connected by edges in the order provided, which will
  #     represent a rectangle parallel to the frame. The
  #     {::Google::Cloud::AutoML::V1beta1::NormalizedVertex NormalizedVertex-s} are
  #     relative to the page.
  #     Coordinates are based on top-left as point (0,0).
  # @!attribute [rw] text_segment_type
  #   @return [::Google::Cloud::AutoML::V1beta1::Document::Layout::TextSegmentType]
  #     The type of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in document.
  class Layout
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The type of TextSegment in the context of the original document.
    module TextSegmentType
      # Should not be used.
      TEXT_SEGMENT_TYPE_UNSPECIFIED = 0

      # The text segment is a token. e.g. word.
      TOKEN = 1

      # The text segment is a paragraph.
      PARAGRAPH = 2

      # The text segment is a form field.
      FORM_FIELD = 3

      # The text segment is the name part of a form field. It will be treated
      # as child of another FORM_FIELD TextSegment if its span is subspan of
      # another TextSegment with type FORM_FIELD.
      FORM_FIELD_NAME = 4

      # The text segment is the text content part of a form field. It will be
      # treated as child of another FORM_FIELD TextSegment if its span is
      # subspan of another TextSegment with type FORM_FIELD.
      FORM_FIELD_CONTENTS = 5

      # The text segment is a whole table, including headers, and all rows.
      TABLE = 6

      # The text segment is a table's headers. It will be treated as child of
      # another TABLE TextSegment if its span is subspan of another TextSegment
      # with type TABLE.
      TABLE_HEADER = 7

      # The text segment is a row in table. It will be treated as child of
      # another TABLE TextSegment if its span is subspan of another TextSegment
      # with type TABLE.
      TABLE_ROW = 8

      # The text segment is a cell in table. It will be treated as child of
      # another TABLE_ROW TextSegment if its span is subspan of another
      # TextSegment with type TABLE_ROW.
      TABLE_CELL = 9
    end
  end
end

#input_config ⇒ ::Google::Cloud::AutoML::V1beta1::DocumentInputConfig

Returns An input config specifying the content of the document.

Returns:



107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
 
# File 'proto_docs/google/cloud/automl/v1beta1/data_items.rb', line 107

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

  # Describes the layout information of a {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the document.
  # @!attribute [rw] text_segment
  #   @return [::Google::Cloud::AutoML::V1beta1::TextSegment]
  #     Text Segment that represents a segment in
  #     {::Google::Cloud::AutoML::V1beta1::Document#document_text document_text}.
  # @!attribute [rw] page_number
  #   @return [::Integer]
  #     Page number of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the original document, starts
  #     from 1.
  # @!attribute [rw] bounding_poly
  #   @return [::Google::Cloud::AutoML::V1beta1::BoundingPoly]
  #     The position of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the page.
  #     Contains exactly 4
  #
  #     {::Google::Cloud::AutoML::V1beta1::BoundingPoly#normalized_vertices normalized_vertices}
  #     and they are connected by edges in the order provided, which will
  #     represent a rectangle parallel to the frame. The
  #     {::Google::Cloud::AutoML::V1beta1::NormalizedVertex NormalizedVertex-s} are
  #     relative to the page.
  #     Coordinates are based on top-left as point (0,0).
  # @!attribute [rw] text_segment_type
  #   @return [::Google::Cloud::AutoML::V1beta1::Document::Layout::TextSegmentType]
  #     The type of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in document.
  class Layout
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The type of TextSegment in the context of the original document.
    module TextSegmentType
      # Should not be used.
      TEXT_SEGMENT_TYPE_UNSPECIFIED = 0

      # The text segment is a token. e.g. word.
      TOKEN = 1

      # The text segment is a paragraph.
      PARAGRAPH = 2

      # The text segment is a form field.
      FORM_FIELD = 3

      # The text segment is the name part of a form field. It will be treated
      # as child of another FORM_FIELD TextSegment if its span is subspan of
      # another TextSegment with type FORM_FIELD.
      FORM_FIELD_NAME = 4

      # The text segment is the text content part of a form field. It will be
      # treated as child of another FORM_FIELD TextSegment if its span is
      # subspan of another TextSegment with type FORM_FIELD.
      FORM_FIELD_CONTENTS = 5

      # The text segment is a whole table, including headers, and all rows.
      TABLE = 6

      # The text segment is a table's headers. It will be treated as child of
      # another TABLE TextSegment if its span is subspan of another TextSegment
      # with type TABLE.
      TABLE_HEADER = 7

      # The text segment is a row in table. It will be treated as child of
      # another TABLE TextSegment if its span is subspan of another TextSegment
      # with type TABLE.
      TABLE_ROW = 8

      # The text segment is a cell in table. It will be treated as child of
      # another TABLE_ROW TextSegment if its span is subspan of another
      # TextSegment with type TABLE_ROW.
      TABLE_CELL = 9
    end
  end
end

#layout ⇒ ::Array<::Google::Cloud::AutoML::V1beta1::Document::Layout>

Returns Describes the layout of the document. Sorted by [page_number][].

Returns:



107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
 
# File 'proto_docs/google/cloud/automl/v1beta1/data_items.rb', line 107

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

  # Describes the layout information of a {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the document.
  # @!attribute [rw] text_segment
  #   @return [::Google::Cloud::AutoML::V1beta1::TextSegment]
  #     Text Segment that represents a segment in
  #     {::Google::Cloud::AutoML::V1beta1::Document#document_text document_text}.
  # @!attribute [rw] page_number
  #   @return [::Integer]
  #     Page number of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the original document, starts
  #     from 1.
  # @!attribute [rw] bounding_poly
  #   @return [::Google::Cloud::AutoML::V1beta1::BoundingPoly]
  #     The position of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the page.
  #     Contains exactly 4
  #
  #     {::Google::Cloud::AutoML::V1beta1::BoundingPoly#normalized_vertices normalized_vertices}
  #     and they are connected by edges in the order provided, which will
  #     represent a rectangle parallel to the frame. The
  #     {::Google::Cloud::AutoML::V1beta1::NormalizedVertex NormalizedVertex-s} are
  #     relative to the page.
  #     Coordinates are based on top-left as point (0,0).
  # @!attribute [rw] text_segment_type
  #   @return [::Google::Cloud::AutoML::V1beta1::Document::Layout::TextSegmentType]
  #     The type of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in document.
  class Layout
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The type of TextSegment in the context of the original document.
    module TextSegmentType
      # Should not be used.
      TEXT_SEGMENT_TYPE_UNSPECIFIED = 0

      # The text segment is a token. e.g. word.
      TOKEN = 1

      # The text segment is a paragraph.
      PARAGRAPH = 2

      # The text segment is a form field.
      FORM_FIELD = 3

      # The text segment is the name part of a form field. It will be treated
      # as child of another FORM_FIELD TextSegment if its span is subspan of
      # another TextSegment with type FORM_FIELD.
      FORM_FIELD_NAME = 4

      # The text segment is the text content part of a form field. It will be
      # treated as child of another FORM_FIELD TextSegment if its span is
      # subspan of another TextSegment with type FORM_FIELD.
      FORM_FIELD_CONTENTS = 5

      # The text segment is a whole table, including headers, and all rows.
      TABLE = 6

      # The text segment is a table's headers. It will be treated as child of
      # another TABLE TextSegment if its span is subspan of another TextSegment
      # with type TABLE.
      TABLE_HEADER = 7

      # The text segment is a row in table. It will be treated as child of
      # another TABLE TextSegment if its span is subspan of another TextSegment
      # with type TABLE.
      TABLE_ROW = 8

      # The text segment is a cell in table. It will be treated as child of
      # another TABLE_ROW TextSegment if its span is subspan of another
      # TextSegment with type TABLE_ROW.
      TABLE_CELL = 9
    end
  end
end

#page_count ⇒ ::Integer

Returns Number of pages in the document.

Returns:

  • (::Integer) —

    Number of pages in the document.



107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
 
# File 'proto_docs/google/cloud/automl/v1beta1/data_items.rb', line 107

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

  # Describes the layout information of a {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the document.
  # @!attribute [rw] text_segment
  #   @return [::Google::Cloud::AutoML::V1beta1::TextSegment]
  #     Text Segment that represents a segment in
  #     {::Google::Cloud::AutoML::V1beta1::Document#document_text document_text}.
  # @!attribute [rw] page_number
  #   @return [::Integer]
  #     Page number of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the original document, starts
  #     from 1.
  # @!attribute [rw] bounding_poly
  #   @return [::Google::Cloud::AutoML::V1beta1::BoundingPoly]
  #     The position of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in the page.
  #     Contains exactly 4
  #
  #     {::Google::Cloud::AutoML::V1beta1::BoundingPoly#normalized_vertices normalized_vertices}
  #     and they are connected by edges in the order provided, which will
  #     represent a rectangle parallel to the frame. The
  #     {::Google::Cloud::AutoML::V1beta1::NormalizedVertex NormalizedVertex-s} are
  #     relative to the page.
  #     Coordinates are based on top-left as point (0,0).
  # @!attribute [rw] text_segment_type
  #   @return [::Google::Cloud::AutoML::V1beta1::Document::Layout::TextSegmentType]
  #     The type of the {::Google::Cloud::AutoML::V1beta1::Document::Layout#text_segment text_segment} in document.
  class Layout
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The type of TextSegment in the context of the original document.
    module TextSegmentType
      # Should not be used.
      TEXT_SEGMENT_TYPE_UNSPECIFIED = 0

      # The text segment is a token. e.g. word.
      TOKEN = 1

      # The text segment is a paragraph.
      PARAGRAPH = 2

      # The text segment is a form field.
      FORM_FIELD = 3

      # The text segment is the name part of a form field. It will be treated
      # as child of another FORM_FIELD TextSegment if its span is subspan of
      # another TextSegment with type FORM_FIELD.
      FORM_FIELD_NAME = 4

      # The text segment is the text content part of a form field. It will be
      # treated as child of another FORM_FIELD TextSegment if its span is
      # subspan of another TextSegment with type FORM_FIELD.
      FORM_FIELD_CONTENTS = 5

      # The text segment is a whole table, including headers, and all rows.
      TABLE = 6

      # The text segment is a table's headers. It will be treated as child of
      # another TABLE TextSegment if its span is subspan of another TextSegment
      # with type TABLE.
      TABLE_HEADER = 7

      # The text segment is a row in table. It will be treated as child of
      # another TABLE TextSegment if its span is subspan of another TextSegment
      # with type TABLE.
      TABLE_ROW = 8

      # The text segment is a cell in table. It will be treated as child of
      # another TABLE_ROW TextSegment if its span is subspan of another
      # TextSegment with type TABLE_ROW.
      TABLE_CELL = 9
    end
  end
end