com.amazonaws.services.textract.model.Block Maven / Gradle / Ivy
/*
* Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance with
* the License. A copy of the License is located at
*
* http://aws.amazon.com/apache2.0
*
* or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
* CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
* and limitations under the License.
*/
package com.amazonaws.services.textract.model;
import java.io.Serializable;
import javax.annotation.Generated;
import com.amazonaws.protocol.StructuredPojo;
import com.amazonaws.protocol.ProtocolMarshaller;
/**
*
* A Block
represents items that are recognized in a document within a group of pixels close to each other.
* The information returned in a Block
object depends on the type of operation. In text detection for
* documents (for example DetectDocumentText), you get information about the detected words and lines of text. In
* text analysis (for example AnalyzeDocument), you can also get information about the fields, tables, and
* selection elements that are detected in the document.
*
*
* An array of Block
objects is returned by both synchronous and asynchronous operations. In synchronous
* operations, such as DetectDocumentText, the array of Block
objects is the entire set of results.
* In asynchronous operations, such as GetDocumentAnalysis, the array is returned over one or more responses.
*
*
* For more information, see How Amazon
* Textract Works.
*
*
* @see AWS API
* Documentation
*/
@Generated("com.amazonaws:aws-java-sdk-code-generator")
public class Block implements Serializable, Cloneable, StructuredPojo {
/**
*
* The type of text item that's recognized. In operations for text detection, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of the LINE Block
objects that are detected on a document page.
*
*
* -
*
* WORD - A word detected on a document page. A word is one or more ISO basic Latin script characters that
* aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
*
*
* In text analysis operations, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of child Block
objects that are detected on a document page.
*
*
* -
*
* KEY_VALUE_SET - Stores the KEY and VALUE Block
objects for linked text that's detected on a
* document page. Use the EntityType
field to determine if a KEY_VALUE_SET object is a KEY
* Block
object or a VALUE Block
object.
*
*
* -
*
* WORD - A word that's detected on a document page. A word is one or more ISO basic Latin script characters
* that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
* -
*
* TABLE - A table that's detected on a document page. A table is grid-based information with two or more
* rows or columns, with a cell span of one row and one column each.
*
*
* -
*
* TABLE_TITLE - The title of a table. A title is typically a line of text above or below a table, or
* embedded as the first row of a table.
*
*
* -
*
* TABLE_FOOTER - The footer associated with a table. A footer is typically a line or lines of text below a
* table or embedded as the last row of a table.
*
*
* -
*
* CELL - A cell within a detected table. The cell is the parent of the block that contains the text in the
* cell.
*
*
* -
*
* MERGED_CELL - A cell in a table whose content spans more than one row or column. The
* Relationships
array for this cell contain data from individual cells.
*
*
* -
*
* SELECTION_ELEMENT - A selection element such as an option button (radio button) or a check box that's
* detected on a document page. Use the value of SelectionStatus
to determine the status of the
* selection element.
*
*
* -
*
* SIGNATURE - The location and confidence score of a signature detected on a document page. Can be returned
* as part of a Key-Value pair or a detected cell.
*
*
* -
*
* QUERY - A question asked during the call of AnalyzeDocument. Contains an alias and an ID that attaches it
* to its answer.
*
*
* -
*
* QUERY_RESULT - A response to a question asked during the call of analyze document. Comes with an alias and
* ID for ease of locating in a response. Also contains location and confidence score.
*
*
*
*
* The following BlockTypes are only returned for Amazon Textract Layout.
*
*
* -
*
* LAYOUT_TITLE
- The main title of the document.
*
*
* -
*
* LAYOUT_HEADER
- Text located in the top margin of the document.
*
*
* -
*
* LAYOUT_FOOTER
- Text located in the bottom margin of the document.
*
*
* -
*
* LAYOUT_SECTION_HEADER
- The titles of sections within a document.
*
*
* -
*
* LAYOUT_PAGE_NUMBER
- The page number of the documents.
*
*
* -
*
* LAYOUT_LIST
- Any information grouped together in list form.
*
*
* -
*
* LAYOUT_FIGURE
- Indicates the location of an image in a document.
*
*
* -
*
* LAYOUT_TABLE
- Indicates the location of a table in the document.
*
*
* -
*
* LAYOUT_KEY_VALUE
- Indicates the location of form key-values in a document.
*
*
* -
*
* LAYOUT_TEXT
- Text that is present typically as a part of paragraphs in documents.
*
*
*
*/
private String blockType;
/**
*
* The confidence score that Amazon Textract has in the accuracy of the recognized text and the accuracy of the
* geometry points around the recognized text.
*
*/
private Float confidence;
/**
*
* The word or line of text that's recognized by Amazon Textract.
*
*/
private String text;
/**
*
* The kind of text that Amazon Textract has detected. Can check for handwritten text and printed text.
*
*/
private String textType;
/**
*
* The row in which a table cell is located. The first row position is 1. RowIndex
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*/
private Integer rowIndex;
/**
*
* The column in which a table cell appears. The first column position is 1. ColumnIndex
isn't returned
* by DetectDocumentText
and GetDocumentTextDetection
.
*
*/
private Integer columnIndex;
/**
*
* The number of rows that a table cell spans. RowSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*/
private Integer rowSpan;
/**
*
* The number of columns that a table cell spans. ColumnSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*/
private Integer columnSpan;
/**
*
* The location of the recognized text on the image. It includes an axis-aligned, coarse bounding box that surrounds
* the text, and a finer-grain polygon for more accurate spatial information.
*
*/
private Geometry geometry;
/**
*
* The identifier for the recognized text. The identifier is only unique for a single operation.
*
*/
private String id;
/**
*
* A list of relationship objects that describe how blocks are related to each other. For example, a LINE block
* object contains a CHILD relationship type with the WORD blocks that make up the line of text. There aren't
* Relationship objects in the list for relationships that don't exist, such as when the current block has no child
* blocks.
*
*/
private java.util.List relationships;
/**
*
* The type of entity.
*
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section title is a
* cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row corresponds to
* the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
*
*/
private java.util.List entityTypes;
/**
*
* The selection status of a selection element, such as an option button or check box.
*
*/
private String selectionStatus;
/**
*
* The page on which a block was detected. Page
is returned by synchronous and asynchronous operations.
* Page values greater than 1 are only returned for multipage documents that are in PDF or TIFF format. A scanned
* image (JPEG/PNG) provided to an asynchronous operation, even if it contains multiple document pages, is
* considered a single-page document. This means that for scanned images the value of Page
is always 1.
*
*/
private Integer page;
/** */
private Query query;
/**
*
* The type of text item that's recognized. In operations for text detection, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of the LINE Block
objects that are detected on a document page.
*
*
* -
*
* WORD - A word detected on a document page. A word is one or more ISO basic Latin script characters that
* aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
*
*
* In text analysis operations, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of child Block
objects that are detected on a document page.
*
*
* -
*
* KEY_VALUE_SET - Stores the KEY and VALUE Block
objects for linked text that's detected on a
* document page. Use the EntityType
field to determine if a KEY_VALUE_SET object is a KEY
* Block
object or a VALUE Block
object.
*
*
* -
*
* WORD - A word that's detected on a document page. A word is one or more ISO basic Latin script characters
* that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
* -
*
* TABLE - A table that's detected on a document page. A table is grid-based information with two or more
* rows or columns, with a cell span of one row and one column each.
*
*
* -
*
* TABLE_TITLE - The title of a table. A title is typically a line of text above or below a table, or
* embedded as the first row of a table.
*
*
* -
*
* TABLE_FOOTER - The footer associated with a table. A footer is typically a line or lines of text below a
* table or embedded as the last row of a table.
*
*
* -
*
* CELL - A cell within a detected table. The cell is the parent of the block that contains the text in the
* cell.
*
*
* -
*
* MERGED_CELL - A cell in a table whose content spans more than one row or column. The
* Relationships
array for this cell contain data from individual cells.
*
*
* -
*
* SELECTION_ELEMENT - A selection element such as an option button (radio button) or a check box that's
* detected on a document page. Use the value of SelectionStatus
to determine the status of the
* selection element.
*
*
* -
*
* SIGNATURE - The location and confidence score of a signature detected on a document page. Can be returned
* as part of a Key-Value pair or a detected cell.
*
*
* -
*
* QUERY - A question asked during the call of AnalyzeDocument. Contains an alias and an ID that attaches it
* to its answer.
*
*
* -
*
* QUERY_RESULT - A response to a question asked during the call of analyze document. Comes with an alias and
* ID for ease of locating in a response. Also contains location and confidence score.
*
*
*
*
* The following BlockTypes are only returned for Amazon Textract Layout.
*
*
* -
*
* LAYOUT_TITLE
- The main title of the document.
*
*
* -
*
* LAYOUT_HEADER
- Text located in the top margin of the document.
*
*
* -
*
* LAYOUT_FOOTER
- Text located in the bottom margin of the document.
*
*
* -
*
* LAYOUT_SECTION_HEADER
- The titles of sections within a document.
*
*
* -
*
* LAYOUT_PAGE_NUMBER
- The page number of the documents.
*
*
* -
*
* LAYOUT_LIST
- Any information grouped together in list form.
*
*
* -
*
* LAYOUT_FIGURE
- Indicates the location of an image in a document.
*
*
* -
*
* LAYOUT_TABLE
- Indicates the location of a table in the document.
*
*
* -
*
* LAYOUT_KEY_VALUE
- Indicates the location of form key-values in a document.
*
*
* -
*
* LAYOUT_TEXT
- Text that is present typically as a part of paragraphs in documents.
*
*
*
*
* @param blockType
* The type of text item that's recognized. In operations for text detection, the following types are
* returned:
*
* -
*
* PAGE - Contains a list of the LINE Block
objects that are detected on a document page.
*
*
* -
*
* WORD - A word detected on a document page. A word is one or more ISO basic Latin script characters
* that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
*
*
* In text analysis operations, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of child Block
objects that are detected on a document page.
*
*
* -
*
* KEY_VALUE_SET - Stores the KEY and VALUE Block
objects for linked text that's detected
* on a document page. Use the EntityType
field to determine if a KEY_VALUE_SET object is a KEY
* Block
object or a VALUE Block
object.
*
*
* -
*
* WORD - A word that's detected on a document page. A word is one or more ISO basic Latin script
* characters that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
* -
*
* TABLE - A table that's detected on a document page. A table is grid-based information with two or
* more rows or columns, with a cell span of one row and one column each.
*
*
* -
*
* TABLE_TITLE - The title of a table. A title is typically a line of text above or below a table, or
* embedded as the first row of a table.
*
*
* -
*
* TABLE_FOOTER - The footer associated with a table. A footer is typically a line or lines of text
* below a table or embedded as the last row of a table.
*
*
* -
*
* CELL - A cell within a detected table. The cell is the parent of the block that contains the text
* in the cell.
*
*
* -
*
* MERGED_CELL - A cell in a table whose content spans more than one row or column. The
* Relationships
array for this cell contain data from individual cells.
*
*
* -
*
* SELECTION_ELEMENT - A selection element such as an option button (radio button) or a check box
* that's detected on a document page. Use the value of SelectionStatus
to determine the status
* of the selection element.
*
*
* -
*
* SIGNATURE - The location and confidence score of a signature detected on a document page. Can be
* returned as part of a Key-Value pair or a detected cell.
*
*
* -
*
* QUERY - A question asked during the call of AnalyzeDocument. Contains an alias and an ID that
* attaches it to its answer.
*
*
* -
*
* QUERY_RESULT - A response to a question asked during the call of analyze document. Comes with an
* alias and ID for ease of locating in a response. Also contains location and confidence score.
*
*
*
*
* The following BlockTypes are only returned for Amazon Textract Layout.
*
*
* -
*
* LAYOUT_TITLE
- The main title of the document.
*
*
* -
*
* LAYOUT_HEADER
- Text located in the top margin of the document.
*
*
* -
*
* LAYOUT_FOOTER
- Text located in the bottom margin of the document.
*
*
* -
*
* LAYOUT_SECTION_HEADER
- The titles of sections within a document.
*
*
* -
*
* LAYOUT_PAGE_NUMBER
- The page number of the documents.
*
*
* -
*
* LAYOUT_LIST
- Any information grouped together in list form.
*
*
* -
*
* LAYOUT_FIGURE
- Indicates the location of an image in a document.
*
*
* -
*
* LAYOUT_TABLE
- Indicates the location of a table in the document.
*
*
* -
*
* LAYOUT_KEY_VALUE
- Indicates the location of form key-values in a document.
*
*
* -
*
* LAYOUT_TEXT
- Text that is present typically as a part of paragraphs in documents.
*
*
* @see BlockType
*/
public void setBlockType(String blockType) {
this.blockType = blockType;
}
/**
*
* The type of text item that's recognized. In operations for text detection, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of the LINE Block
objects that are detected on a document page.
*
*
* -
*
* WORD - A word detected on a document page. A word is one or more ISO basic Latin script characters that
* aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
*
*
* In text analysis operations, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of child Block
objects that are detected on a document page.
*
*
* -
*
* KEY_VALUE_SET - Stores the KEY and VALUE Block
objects for linked text that's detected on a
* document page. Use the EntityType
field to determine if a KEY_VALUE_SET object is a KEY
* Block
object or a VALUE Block
object.
*
*
* -
*
* WORD - A word that's detected on a document page. A word is one or more ISO basic Latin script characters
* that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
* -
*
* TABLE - A table that's detected on a document page. A table is grid-based information with two or more
* rows or columns, with a cell span of one row and one column each.
*
*
* -
*
* TABLE_TITLE - The title of a table. A title is typically a line of text above or below a table, or
* embedded as the first row of a table.
*
*
* -
*
* TABLE_FOOTER - The footer associated with a table. A footer is typically a line or lines of text below a
* table or embedded as the last row of a table.
*
*
* -
*
* CELL - A cell within a detected table. The cell is the parent of the block that contains the text in the
* cell.
*
*
* -
*
* MERGED_CELL - A cell in a table whose content spans more than one row or column. The
* Relationships
array for this cell contain data from individual cells.
*
*
* -
*
* SELECTION_ELEMENT - A selection element such as an option button (radio button) or a check box that's
* detected on a document page. Use the value of SelectionStatus
to determine the status of the
* selection element.
*
*
* -
*
* SIGNATURE - The location and confidence score of a signature detected on a document page. Can be returned
* as part of a Key-Value pair or a detected cell.
*
*
* -
*
* QUERY - A question asked during the call of AnalyzeDocument. Contains an alias and an ID that attaches it
* to its answer.
*
*
* -
*
* QUERY_RESULT - A response to a question asked during the call of analyze document. Comes with an alias and
* ID for ease of locating in a response. Also contains location and confidence score.
*
*
*
*
* The following BlockTypes are only returned for Amazon Textract Layout.
*
*
* -
*
* LAYOUT_TITLE
- The main title of the document.
*
*
* -
*
* LAYOUT_HEADER
- Text located in the top margin of the document.
*
*
* -
*
* LAYOUT_FOOTER
- Text located in the bottom margin of the document.
*
*
* -
*
* LAYOUT_SECTION_HEADER
- The titles of sections within a document.
*
*
* -
*
* LAYOUT_PAGE_NUMBER
- The page number of the documents.
*
*
* -
*
* LAYOUT_LIST
- Any information grouped together in list form.
*
*
* -
*
* LAYOUT_FIGURE
- Indicates the location of an image in a document.
*
*
* -
*
* LAYOUT_TABLE
- Indicates the location of a table in the document.
*
*
* -
*
* LAYOUT_KEY_VALUE
- Indicates the location of form key-values in a document.
*
*
* -
*
* LAYOUT_TEXT
- Text that is present typically as a part of paragraphs in documents.
*
*
*
*
* @return The type of text item that's recognized. In operations for text detection, the following types are
* returned:
*
* -
*
* PAGE - Contains a list of the LINE Block
objects that are detected on a document
* page.
*
*
* -
*
* WORD - A word detected on a document page. A word is one or more ISO basic Latin script characters
* that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
*
*
* In text analysis operations, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of child Block
objects that are detected on a document page.
*
*
* -
*
* KEY_VALUE_SET - Stores the KEY and VALUE Block
objects for linked text that's
* detected on a document page. Use the EntityType
field to determine if a KEY_VALUE_SET object
* is a KEY Block
object or a VALUE Block
object.
*
*
* -
*
* WORD - A word that's detected on a document page. A word is one or more ISO basic Latin script
* characters that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
* -
*
* TABLE - A table that's detected on a document page. A table is grid-based information with two or
* more rows or columns, with a cell span of one row and one column each.
*
*
* -
*
* TABLE_TITLE - The title of a table. A title is typically a line of text above or below a table, or
* embedded as the first row of a table.
*
*
* -
*
* TABLE_FOOTER - The footer associated with a table. A footer is typically a line or lines of text
* below a table or embedded as the last row of a table.
*
*
* -
*
* CELL - A cell within a detected table. The cell is the parent of the block that contains the text
* in the cell.
*
*
* -
*
* MERGED_CELL - A cell in a table whose content spans more than one row or column. The
* Relationships
array for this cell contain data from individual cells.
*
*
* -
*
* SELECTION_ELEMENT - A selection element such as an option button (radio button) or a check box
* that's detected on a document page. Use the value of SelectionStatus
to determine the status
* of the selection element.
*
*
* -
*
* SIGNATURE - The location and confidence score of a signature detected on a document page. Can be
* returned as part of a Key-Value pair or a detected cell.
*
*
* -
*
* QUERY - A question asked during the call of AnalyzeDocument. Contains an alias and an ID that
* attaches it to its answer.
*
*
* -
*
* QUERY_RESULT - A response to a question asked during the call of analyze document. Comes with an
* alias and ID for ease of locating in a response. Also contains location and confidence score.
*
*
*
*
* The following BlockTypes are only returned for Amazon Textract Layout.
*
*
* -
*
* LAYOUT_TITLE
- The main title of the document.
*
*
* -
*
* LAYOUT_HEADER
- Text located in the top margin of the document.
*
*
* -
*
* LAYOUT_FOOTER
- Text located in the bottom margin of the document.
*
*
* -
*
* LAYOUT_SECTION_HEADER
- The titles of sections within a document.
*
*
* -
*
* LAYOUT_PAGE_NUMBER
- The page number of the documents.
*
*
* -
*
* LAYOUT_LIST
- Any information grouped together in list form.
*
*
* -
*
* LAYOUT_FIGURE
- Indicates the location of an image in a document.
*
*
* -
*
* LAYOUT_TABLE
- Indicates the location of a table in the document.
*
*
* -
*
* LAYOUT_KEY_VALUE
- Indicates the location of form key-values in a document.
*
*
* -
*
* LAYOUT_TEXT
- Text that is present typically as a part of paragraphs in documents.
*
*
* @see BlockType
*/
public String getBlockType() {
return this.blockType;
}
/**
*
* The type of text item that's recognized. In operations for text detection, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of the LINE Block
objects that are detected on a document page.
*
*
* -
*
* WORD - A word detected on a document page. A word is one or more ISO basic Latin script characters that
* aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
*
*
* In text analysis operations, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of child Block
objects that are detected on a document page.
*
*
* -
*
* KEY_VALUE_SET - Stores the KEY and VALUE Block
objects for linked text that's detected on a
* document page. Use the EntityType
field to determine if a KEY_VALUE_SET object is a KEY
* Block
object or a VALUE Block
object.
*
*
* -
*
* WORD - A word that's detected on a document page. A word is one or more ISO basic Latin script characters
* that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
* -
*
* TABLE - A table that's detected on a document page. A table is grid-based information with two or more
* rows or columns, with a cell span of one row and one column each.
*
*
* -
*
* TABLE_TITLE - The title of a table. A title is typically a line of text above or below a table, or
* embedded as the first row of a table.
*
*
* -
*
* TABLE_FOOTER - The footer associated with a table. A footer is typically a line or lines of text below a
* table or embedded as the last row of a table.
*
*
* -
*
* CELL - A cell within a detected table. The cell is the parent of the block that contains the text in the
* cell.
*
*
* -
*
* MERGED_CELL - A cell in a table whose content spans more than one row or column. The
* Relationships
array for this cell contain data from individual cells.
*
*
* -
*
* SELECTION_ELEMENT - A selection element such as an option button (radio button) or a check box that's
* detected on a document page. Use the value of SelectionStatus
to determine the status of the
* selection element.
*
*
* -
*
* SIGNATURE - The location and confidence score of a signature detected on a document page. Can be returned
* as part of a Key-Value pair or a detected cell.
*
*
* -
*
* QUERY - A question asked during the call of AnalyzeDocument. Contains an alias and an ID that attaches it
* to its answer.
*
*
* -
*
* QUERY_RESULT - A response to a question asked during the call of analyze document. Comes with an alias and
* ID for ease of locating in a response. Also contains location and confidence score.
*
*
*
*
* The following BlockTypes are only returned for Amazon Textract Layout.
*
*
* -
*
* LAYOUT_TITLE
- The main title of the document.
*
*
* -
*
* LAYOUT_HEADER
- Text located in the top margin of the document.
*
*
* -
*
* LAYOUT_FOOTER
- Text located in the bottom margin of the document.
*
*
* -
*
* LAYOUT_SECTION_HEADER
- The titles of sections within a document.
*
*
* -
*
* LAYOUT_PAGE_NUMBER
- The page number of the documents.
*
*
* -
*
* LAYOUT_LIST
- Any information grouped together in list form.
*
*
* -
*
* LAYOUT_FIGURE
- Indicates the location of an image in a document.
*
*
* -
*
* LAYOUT_TABLE
- Indicates the location of a table in the document.
*
*
* -
*
* LAYOUT_KEY_VALUE
- Indicates the location of form key-values in a document.
*
*
* -
*
* LAYOUT_TEXT
- Text that is present typically as a part of paragraphs in documents.
*
*
*
*
* @param blockType
* The type of text item that's recognized. In operations for text detection, the following types are
* returned:
*
* -
*
* PAGE - Contains a list of the LINE Block
objects that are detected on a document page.
*
*
* -
*
* WORD - A word detected on a document page. A word is one or more ISO basic Latin script characters
* that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
*
*
* In text analysis operations, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of child Block
objects that are detected on a document page.
*
*
* -
*
* KEY_VALUE_SET - Stores the KEY and VALUE Block
objects for linked text that's detected
* on a document page. Use the EntityType
field to determine if a KEY_VALUE_SET object is a KEY
* Block
object or a VALUE Block
object.
*
*
* -
*
* WORD - A word that's detected on a document page. A word is one or more ISO basic Latin script
* characters that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
* -
*
* TABLE - A table that's detected on a document page. A table is grid-based information with two or
* more rows or columns, with a cell span of one row and one column each.
*
*
* -
*
* TABLE_TITLE - The title of a table. A title is typically a line of text above or below a table, or
* embedded as the first row of a table.
*
*
* -
*
* TABLE_FOOTER - The footer associated with a table. A footer is typically a line or lines of text
* below a table or embedded as the last row of a table.
*
*
* -
*
* CELL - A cell within a detected table. The cell is the parent of the block that contains the text
* in the cell.
*
*
* -
*
* MERGED_CELL - A cell in a table whose content spans more than one row or column. The
* Relationships
array for this cell contain data from individual cells.
*
*
* -
*
* SELECTION_ELEMENT - A selection element such as an option button (radio button) or a check box
* that's detected on a document page. Use the value of SelectionStatus
to determine the status
* of the selection element.
*
*
* -
*
* SIGNATURE - The location and confidence score of a signature detected on a document page. Can be
* returned as part of a Key-Value pair or a detected cell.
*
*
* -
*
* QUERY - A question asked during the call of AnalyzeDocument. Contains an alias and an ID that
* attaches it to its answer.
*
*
* -
*
* QUERY_RESULT - A response to a question asked during the call of analyze document. Comes with an
* alias and ID for ease of locating in a response. Also contains location and confidence score.
*
*
*
*
* The following BlockTypes are only returned for Amazon Textract Layout.
*
*
* -
*
* LAYOUT_TITLE
- The main title of the document.
*
*
* -
*
* LAYOUT_HEADER
- Text located in the top margin of the document.
*
*
* -
*
* LAYOUT_FOOTER
- Text located in the bottom margin of the document.
*
*
* -
*
* LAYOUT_SECTION_HEADER
- The titles of sections within a document.
*
*
* -
*
* LAYOUT_PAGE_NUMBER
- The page number of the documents.
*
*
* -
*
* LAYOUT_LIST
- Any information grouped together in list form.
*
*
* -
*
* LAYOUT_FIGURE
- Indicates the location of an image in a document.
*
*
* -
*
* LAYOUT_TABLE
- Indicates the location of a table in the document.
*
*
* -
*
* LAYOUT_KEY_VALUE
- Indicates the location of form key-values in a document.
*
*
* -
*
* LAYOUT_TEXT
- Text that is present typically as a part of paragraphs in documents.
*
*
* @return Returns a reference to this object so that method calls can be chained together.
* @see BlockType
*/
public Block withBlockType(String blockType) {
setBlockType(blockType);
return this;
}
/**
*
* The type of text item that's recognized. In operations for text detection, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of the LINE Block
objects that are detected on a document page.
*
*
* -
*
* WORD - A word detected on a document page. A word is one or more ISO basic Latin script characters that
* aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
*
*
* In text analysis operations, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of child Block
objects that are detected on a document page.
*
*
* -
*
* KEY_VALUE_SET - Stores the KEY and VALUE Block
objects for linked text that's detected on a
* document page. Use the EntityType
field to determine if a KEY_VALUE_SET object is a KEY
* Block
object or a VALUE Block
object.
*
*
* -
*
* WORD - A word that's detected on a document page. A word is one or more ISO basic Latin script characters
* that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
* -
*
* TABLE - A table that's detected on a document page. A table is grid-based information with two or more
* rows or columns, with a cell span of one row and one column each.
*
*
* -
*
* TABLE_TITLE - The title of a table. A title is typically a line of text above or below a table, or
* embedded as the first row of a table.
*
*
* -
*
* TABLE_FOOTER - The footer associated with a table. A footer is typically a line or lines of text below a
* table or embedded as the last row of a table.
*
*
* -
*
* CELL - A cell within a detected table. The cell is the parent of the block that contains the text in the
* cell.
*
*
* -
*
* MERGED_CELL - A cell in a table whose content spans more than one row or column. The
* Relationships
array for this cell contain data from individual cells.
*
*
* -
*
* SELECTION_ELEMENT - A selection element such as an option button (radio button) or a check box that's
* detected on a document page. Use the value of SelectionStatus
to determine the status of the
* selection element.
*
*
* -
*
* SIGNATURE - The location and confidence score of a signature detected on a document page. Can be returned
* as part of a Key-Value pair or a detected cell.
*
*
* -
*
* QUERY - A question asked during the call of AnalyzeDocument. Contains an alias and an ID that attaches it
* to its answer.
*
*
* -
*
* QUERY_RESULT - A response to a question asked during the call of analyze document. Comes with an alias and
* ID for ease of locating in a response. Also contains location and confidence score.
*
*
*
*
* The following BlockTypes are only returned for Amazon Textract Layout.
*
*
* -
*
* LAYOUT_TITLE
- The main title of the document.
*
*
* -
*
* LAYOUT_HEADER
- Text located in the top margin of the document.
*
*
* -
*
* LAYOUT_FOOTER
- Text located in the bottom margin of the document.
*
*
* -
*
* LAYOUT_SECTION_HEADER
- The titles of sections within a document.
*
*
* -
*
* LAYOUT_PAGE_NUMBER
- The page number of the documents.
*
*
* -
*
* LAYOUT_LIST
- Any information grouped together in list form.
*
*
* -
*
* LAYOUT_FIGURE
- Indicates the location of an image in a document.
*
*
* -
*
* LAYOUT_TABLE
- Indicates the location of a table in the document.
*
*
* -
*
* LAYOUT_KEY_VALUE
- Indicates the location of form key-values in a document.
*
*
* -
*
* LAYOUT_TEXT
- Text that is present typically as a part of paragraphs in documents.
*
*
*
*
* @param blockType
* The type of text item that's recognized. In operations for text detection, the following types are
* returned:
*
* -
*
* PAGE - Contains a list of the LINE Block
objects that are detected on a document page.
*
*
* -
*
* WORD - A word detected on a document page. A word is one or more ISO basic Latin script characters
* that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
*
*
* In text analysis operations, the following types are returned:
*
*
* -
*
* PAGE - Contains a list of child Block
objects that are detected on a document page.
*
*
* -
*
* KEY_VALUE_SET - Stores the KEY and VALUE Block
objects for linked text that's detected
* on a document page. Use the EntityType
field to determine if a KEY_VALUE_SET object is a KEY
* Block
object or a VALUE Block
object.
*
*
* -
*
* WORD - A word that's detected on a document page. A word is one or more ISO basic Latin script
* characters that aren't separated by spaces.
*
*
* -
*
* LINE - A string of tab-delimited, contiguous words that are detected on a document page.
*
*
* -
*
* TABLE - A table that's detected on a document page. A table is grid-based information with two or
* more rows or columns, with a cell span of one row and one column each.
*
*
* -
*
* TABLE_TITLE - The title of a table. A title is typically a line of text above or below a table, or
* embedded as the first row of a table.
*
*
* -
*
* TABLE_FOOTER - The footer associated with a table. A footer is typically a line or lines of text
* below a table or embedded as the last row of a table.
*
*
* -
*
* CELL - A cell within a detected table. The cell is the parent of the block that contains the text
* in the cell.
*
*
* -
*
* MERGED_CELL - A cell in a table whose content spans more than one row or column. The
* Relationships
array for this cell contain data from individual cells.
*
*
* -
*
* SELECTION_ELEMENT - A selection element such as an option button (radio button) or a check box
* that's detected on a document page. Use the value of SelectionStatus
to determine the status
* of the selection element.
*
*
* -
*
* SIGNATURE - The location and confidence score of a signature detected on a document page. Can be
* returned as part of a Key-Value pair or a detected cell.
*
*
* -
*
* QUERY - A question asked during the call of AnalyzeDocument. Contains an alias and an ID that
* attaches it to its answer.
*
*
* -
*
* QUERY_RESULT - A response to a question asked during the call of analyze document. Comes with an
* alias and ID for ease of locating in a response. Also contains location and confidence score.
*
*
*
*
* The following BlockTypes are only returned for Amazon Textract Layout.
*
*
* -
*
* LAYOUT_TITLE
- The main title of the document.
*
*
* -
*
* LAYOUT_HEADER
- Text located in the top margin of the document.
*
*
* -
*
* LAYOUT_FOOTER
- Text located in the bottom margin of the document.
*
*
* -
*
* LAYOUT_SECTION_HEADER
- The titles of sections within a document.
*
*
* -
*
* LAYOUT_PAGE_NUMBER
- The page number of the documents.
*
*
* -
*
* LAYOUT_LIST
- Any information grouped together in list form.
*
*
* -
*
* LAYOUT_FIGURE
- Indicates the location of an image in a document.
*
*
* -
*
* LAYOUT_TABLE
- Indicates the location of a table in the document.
*
*
* -
*
* LAYOUT_KEY_VALUE
- Indicates the location of form key-values in a document.
*
*
* -
*
* LAYOUT_TEXT
- Text that is present typically as a part of paragraphs in documents.
*
*
* @return Returns a reference to this object so that method calls can be chained together.
* @see BlockType
*/
public Block withBlockType(BlockType blockType) {
this.blockType = blockType.toString();
return this;
}
/**
*
* The confidence score that Amazon Textract has in the accuracy of the recognized text and the accuracy of the
* geometry points around the recognized text.
*
*
* @param confidence
* The confidence score that Amazon Textract has in the accuracy of the recognized text and the accuracy of
* the geometry points around the recognized text.
*/
public void setConfidence(Float confidence) {
this.confidence = confidence;
}
/**
*
* The confidence score that Amazon Textract has in the accuracy of the recognized text and the accuracy of the
* geometry points around the recognized text.
*
*
* @return The confidence score that Amazon Textract has in the accuracy of the recognized text and the accuracy of
* the geometry points around the recognized text.
*/
public Float getConfidence() {
return this.confidence;
}
/**
*
* The confidence score that Amazon Textract has in the accuracy of the recognized text and the accuracy of the
* geometry points around the recognized text.
*
*
* @param confidence
* The confidence score that Amazon Textract has in the accuracy of the recognized text and the accuracy of
* the geometry points around the recognized text.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withConfidence(Float confidence) {
setConfidence(confidence);
return this;
}
/**
*
* The word or line of text that's recognized by Amazon Textract.
*
*
* @param text
* The word or line of text that's recognized by Amazon Textract.
*/
public void setText(String text) {
this.text = text;
}
/**
*
* The word or line of text that's recognized by Amazon Textract.
*
*
* @return The word or line of text that's recognized by Amazon Textract.
*/
public String getText() {
return this.text;
}
/**
*
* The word or line of text that's recognized by Amazon Textract.
*
*
* @param text
* The word or line of text that's recognized by Amazon Textract.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withText(String text) {
setText(text);
return this;
}
/**
*
* The kind of text that Amazon Textract has detected. Can check for handwritten text and printed text.
*
*
* @param textType
* The kind of text that Amazon Textract has detected. Can check for handwritten text and printed text.
* @see TextType
*/
public void setTextType(String textType) {
this.textType = textType;
}
/**
*
* The kind of text that Amazon Textract has detected. Can check for handwritten text and printed text.
*
*
* @return The kind of text that Amazon Textract has detected. Can check for handwritten text and printed text.
* @see TextType
*/
public String getTextType() {
return this.textType;
}
/**
*
* The kind of text that Amazon Textract has detected. Can check for handwritten text and printed text.
*
*
* @param textType
* The kind of text that Amazon Textract has detected. Can check for handwritten text and printed text.
* @return Returns a reference to this object so that method calls can be chained together.
* @see TextType
*/
public Block withTextType(String textType) {
setTextType(textType);
return this;
}
/**
*
* The kind of text that Amazon Textract has detected. Can check for handwritten text and printed text.
*
*
* @param textType
* The kind of text that Amazon Textract has detected. Can check for handwritten text and printed text.
* @return Returns a reference to this object so that method calls can be chained together.
* @see TextType
*/
public Block withTextType(TextType textType) {
this.textType = textType.toString();
return this;
}
/**
*
* The row in which a table cell is located. The first row position is 1. RowIndex
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @param rowIndex
* The row in which a table cell is located. The first row position is 1. RowIndex
isn't
* returned by DetectDocumentText
and GetDocumentTextDetection
.
*/
public void setRowIndex(Integer rowIndex) {
this.rowIndex = rowIndex;
}
/**
*
* The row in which a table cell is located. The first row position is 1. RowIndex
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @return The row in which a table cell is located. The first row position is 1. RowIndex
isn't
* returned by DetectDocumentText
and GetDocumentTextDetection
.
*/
public Integer getRowIndex() {
return this.rowIndex;
}
/**
*
* The row in which a table cell is located. The first row position is 1. RowIndex
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @param rowIndex
* The row in which a table cell is located. The first row position is 1. RowIndex
isn't
* returned by DetectDocumentText
and GetDocumentTextDetection
.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withRowIndex(Integer rowIndex) {
setRowIndex(rowIndex);
return this;
}
/**
*
* The column in which a table cell appears. The first column position is 1. ColumnIndex
isn't returned
* by DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @param columnIndex
* The column in which a table cell appears. The first column position is 1. ColumnIndex
isn't
* returned by DetectDocumentText
and GetDocumentTextDetection
.
*/
public void setColumnIndex(Integer columnIndex) {
this.columnIndex = columnIndex;
}
/**
*
* The column in which a table cell appears. The first column position is 1. ColumnIndex
isn't returned
* by DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @return The column in which a table cell appears. The first column position is 1. ColumnIndex
isn't
* returned by DetectDocumentText
and GetDocumentTextDetection
.
*/
public Integer getColumnIndex() {
return this.columnIndex;
}
/**
*
* The column in which a table cell appears. The first column position is 1. ColumnIndex
isn't returned
* by DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @param columnIndex
* The column in which a table cell appears. The first column position is 1. ColumnIndex
isn't
* returned by DetectDocumentText
and GetDocumentTextDetection
.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withColumnIndex(Integer columnIndex) {
setColumnIndex(columnIndex);
return this;
}
/**
*
* The number of rows that a table cell spans. RowSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @param rowSpan
* The number of rows that a table cell spans. RowSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*/
public void setRowSpan(Integer rowSpan) {
this.rowSpan = rowSpan;
}
/**
*
* The number of rows that a table cell spans. RowSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @return The number of rows that a table cell spans. RowSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*/
public Integer getRowSpan() {
return this.rowSpan;
}
/**
*
* The number of rows that a table cell spans. RowSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @param rowSpan
* The number of rows that a table cell spans. RowSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withRowSpan(Integer rowSpan) {
setRowSpan(rowSpan);
return this;
}
/**
*
* The number of columns that a table cell spans. ColumnSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @param columnSpan
* The number of columns that a table cell spans. ColumnSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*/
public void setColumnSpan(Integer columnSpan) {
this.columnSpan = columnSpan;
}
/**
*
* The number of columns that a table cell spans. ColumnSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @return The number of columns that a table cell spans. ColumnSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*/
public Integer getColumnSpan() {
return this.columnSpan;
}
/**
*
* The number of columns that a table cell spans. ColumnSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
*
*
* @param columnSpan
* The number of columns that a table cell spans. ColumnSpan
isn't returned by
* DetectDocumentText
and GetDocumentTextDetection
.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withColumnSpan(Integer columnSpan) {
setColumnSpan(columnSpan);
return this;
}
/**
*
* The location of the recognized text on the image. It includes an axis-aligned, coarse bounding box that surrounds
* the text, and a finer-grain polygon for more accurate spatial information.
*
*
* @param geometry
* The location of the recognized text on the image. It includes an axis-aligned, coarse bounding box that
* surrounds the text, and a finer-grain polygon for more accurate spatial information.
*/
public void setGeometry(Geometry geometry) {
this.geometry = geometry;
}
/**
*
* The location of the recognized text on the image. It includes an axis-aligned, coarse bounding box that surrounds
* the text, and a finer-grain polygon for more accurate spatial information.
*
*
* @return The location of the recognized text on the image. It includes an axis-aligned, coarse bounding box that
* surrounds the text, and a finer-grain polygon for more accurate spatial information.
*/
public Geometry getGeometry() {
return this.geometry;
}
/**
*
* The location of the recognized text on the image. It includes an axis-aligned, coarse bounding box that surrounds
* the text, and a finer-grain polygon for more accurate spatial information.
*
*
* @param geometry
* The location of the recognized text on the image. It includes an axis-aligned, coarse bounding box that
* surrounds the text, and a finer-grain polygon for more accurate spatial information.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withGeometry(Geometry geometry) {
setGeometry(geometry);
return this;
}
/**
*
* The identifier for the recognized text. The identifier is only unique for a single operation.
*
*
* @param id
* The identifier for the recognized text. The identifier is only unique for a single operation.
*/
public void setId(String id) {
this.id = id;
}
/**
*
* The identifier for the recognized text. The identifier is only unique for a single operation.
*
*
* @return The identifier for the recognized text. The identifier is only unique for a single operation.
*/
public String getId() {
return this.id;
}
/**
*
* The identifier for the recognized text. The identifier is only unique for a single operation.
*
*
* @param id
* The identifier for the recognized text. The identifier is only unique for a single operation.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withId(String id) {
setId(id);
return this;
}
/**
*
* A list of relationship objects that describe how blocks are related to each other. For example, a LINE block
* object contains a CHILD relationship type with the WORD blocks that make up the line of text. There aren't
* Relationship objects in the list for relationships that don't exist, such as when the current block has no child
* blocks.
*
*
* @return A list of relationship objects that describe how blocks are related to each other. For example, a LINE
* block object contains a CHILD relationship type with the WORD blocks that make up the line of text. There
* aren't Relationship objects in the list for relationships that don't exist, such as when the current
* block has no child blocks.
*/
public java.util.List getRelationships() {
return relationships;
}
/**
*
* A list of relationship objects that describe how blocks are related to each other. For example, a LINE block
* object contains a CHILD relationship type with the WORD blocks that make up the line of text. There aren't
* Relationship objects in the list for relationships that don't exist, such as when the current block has no child
* blocks.
*
*
* @param relationships
* A list of relationship objects that describe how blocks are related to each other. For example, a LINE
* block object contains a CHILD relationship type with the WORD blocks that make up the line of text. There
* aren't Relationship objects in the list for relationships that don't exist, such as when the current block
* has no child blocks.
*/
public void setRelationships(java.util.Collection relationships) {
if (relationships == null) {
this.relationships = null;
return;
}
this.relationships = new java.util.ArrayList(relationships);
}
/**
*
* A list of relationship objects that describe how blocks are related to each other. For example, a LINE block
* object contains a CHILD relationship type with the WORD blocks that make up the line of text. There aren't
* Relationship objects in the list for relationships that don't exist, such as when the current block has no child
* blocks.
*
*
* NOTE: This method appends the values to the existing list (if any). Use
* {@link #setRelationships(java.util.Collection)} or {@link #withRelationships(java.util.Collection)} if you want
* to override the existing values.
*
*
* @param relationships
* A list of relationship objects that describe how blocks are related to each other. For example, a LINE
* block object contains a CHILD relationship type with the WORD blocks that make up the line of text. There
* aren't Relationship objects in the list for relationships that don't exist, such as when the current block
* has no child blocks.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withRelationships(Relationship... relationships) {
if (this.relationships == null) {
setRelationships(new java.util.ArrayList(relationships.length));
}
for (Relationship ele : relationships) {
this.relationships.add(ele);
}
return this;
}
/**
*
* A list of relationship objects that describe how blocks are related to each other. For example, a LINE block
* object contains a CHILD relationship type with the WORD blocks that make up the line of text. There aren't
* Relationship objects in the list for relationships that don't exist, such as when the current block has no child
* blocks.
*
*
* @param relationships
* A list of relationship objects that describe how blocks are related to each other. For example, a LINE
* block object contains a CHILD relationship type with the WORD blocks that make up the line of text. There
* aren't Relationship objects in the list for relationships that don't exist, such as when the current block
* has no child blocks.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withRelationships(java.util.Collection relationships) {
setRelationships(relationships);
return this;
}
/**
*
* The type of entity.
*
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section title is a
* cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row corresponds to
* the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
*
*
* @return The type of entity.
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section
* title is a cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row
* corresponds to the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
* @see EntityType
*/
public java.util.List getEntityTypes() {
return entityTypes;
}
/**
*
* The type of entity.
*
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section title is a
* cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row corresponds to
* the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
*
*
* @param entityTypes
* The type of entity.
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section
* title is a cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row
* corresponds to the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
* @see EntityType
*/
public void setEntityTypes(java.util.Collection entityTypes) {
if (entityTypes == null) {
this.entityTypes = null;
return;
}
this.entityTypes = new java.util.ArrayList(entityTypes);
}
/**
*
* The type of entity.
*
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section title is a
* cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row corresponds to
* the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
*
*
* NOTE: This method appends the values to the existing list (if any). Use
* {@link #setEntityTypes(java.util.Collection)} or {@link #withEntityTypes(java.util.Collection)} if you want to
* override the existing values.
*
*
* @param entityTypes
* The type of entity.
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section
* title is a cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row
* corresponds to the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
* @return Returns a reference to this object so that method calls can be chained together.
* @see EntityType
*/
public Block withEntityTypes(String... entityTypes) {
if (this.entityTypes == null) {
setEntityTypes(new java.util.ArrayList(entityTypes.length));
}
for (String ele : entityTypes) {
this.entityTypes.add(ele);
}
return this;
}
/**
*
* The type of entity.
*
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section title is a
* cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row corresponds to
* the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
*
*
* @param entityTypes
* The type of entity.
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section
* title is a cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row
* corresponds to the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
* @return Returns a reference to this object so that method calls can be chained together.
* @see EntityType
*/
public Block withEntityTypes(java.util.Collection entityTypes) {
setEntityTypes(entityTypes);
return this;
}
/**
*
* The type of entity.
*
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section title is a
* cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row corresponds to
* the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
*
*
* @param entityTypes
* The type of entity.
*
* The following entity types can be returned by FORMS analysis:
*
*
* -
*
* KEY - An identifier for a field on the document.
*
*
* -
*
* VALUE - The field text.
*
*
*
*
* The following entity types can be returned by TABLES analysis:
*
*
* -
*
* COLUMN_HEADER - Identifies a cell that is a header of a column.
*
*
* -
*
* TABLE_TITLE - Identifies a cell that is a title within the table.
*
*
* -
*
* TABLE_SECTION_TITLE - Identifies a cell that is a title of a section within a table. A section
* title is a cell that typically spans an entire row above a section.
*
*
* -
*
* TABLE_FOOTER - Identifies a cell that is a footer of a table.
*
*
* -
*
* TABLE_SUMMARY - Identifies a summary cell of a table. A summary cell can be a row of a table or an
* additional, smaller table that contains summary information for another table.
*
*
* -
*
* STRUCTURED_TABLE - Identifies a table with column headers where the content of each row
* corresponds to the headers.
*
*
* -
*
* SEMI_STRUCTURED_TABLE - Identifies a non-structured table.
*
*
*
*
* EntityTypes
isn't returned by DetectDocumentText
and
* GetDocumentTextDetection
.
* @return Returns a reference to this object so that method calls can be chained together.
* @see EntityType
*/
public Block withEntityTypes(EntityType... entityTypes) {
java.util.ArrayList entityTypesCopy = new java.util.ArrayList(entityTypes.length);
for (EntityType value : entityTypes) {
entityTypesCopy.add(value.toString());
}
if (getEntityTypes() == null) {
setEntityTypes(entityTypesCopy);
} else {
getEntityTypes().addAll(entityTypesCopy);
}
return this;
}
/**
*
* The selection status of a selection element, such as an option button or check box.
*
*
* @param selectionStatus
* The selection status of a selection element, such as an option button or check box.
* @see SelectionStatus
*/
public void setSelectionStatus(String selectionStatus) {
this.selectionStatus = selectionStatus;
}
/**
*
* The selection status of a selection element, such as an option button or check box.
*
*
* @return The selection status of a selection element, such as an option button or check box.
* @see SelectionStatus
*/
public String getSelectionStatus() {
return this.selectionStatus;
}
/**
*
* The selection status of a selection element, such as an option button or check box.
*
*
* @param selectionStatus
* The selection status of a selection element, such as an option button or check box.
* @return Returns a reference to this object so that method calls can be chained together.
* @see SelectionStatus
*/
public Block withSelectionStatus(String selectionStatus) {
setSelectionStatus(selectionStatus);
return this;
}
/**
*
* The selection status of a selection element, such as an option button or check box.
*
*
* @param selectionStatus
* The selection status of a selection element, such as an option button or check box.
* @return Returns a reference to this object so that method calls can be chained together.
* @see SelectionStatus
*/
public Block withSelectionStatus(SelectionStatus selectionStatus) {
this.selectionStatus = selectionStatus.toString();
return this;
}
/**
*
* The page on which a block was detected. Page
is returned by synchronous and asynchronous operations.
* Page values greater than 1 are only returned for multipage documents that are in PDF or TIFF format. A scanned
* image (JPEG/PNG) provided to an asynchronous operation, even if it contains multiple document pages, is
* considered a single-page document. This means that for scanned images the value of Page
is always 1.
*
*
* @param page
* The page on which a block was detected. Page
is returned by synchronous and asynchronous
* operations. Page values greater than 1 are only returned for multipage documents that are in PDF or TIFF
* format. A scanned image (JPEG/PNG) provided to an asynchronous operation, even if it contains multiple
* document pages, is considered a single-page document. This means that for scanned images the value of
* Page
is always 1.
*/
public void setPage(Integer page) {
this.page = page;
}
/**
*
* The page on which a block was detected. Page
is returned by synchronous and asynchronous operations.
* Page values greater than 1 are only returned for multipage documents that are in PDF or TIFF format. A scanned
* image (JPEG/PNG) provided to an asynchronous operation, even if it contains multiple document pages, is
* considered a single-page document. This means that for scanned images the value of Page
is always 1.
*
*
* @return The page on which a block was detected. Page
is returned by synchronous and asynchronous
* operations. Page values greater than 1 are only returned for multipage documents that are in PDF or TIFF
* format. A scanned image (JPEG/PNG) provided to an asynchronous operation, even if it contains multiple
* document pages, is considered a single-page document. This means that for scanned images the value of
* Page
is always 1.
*/
public Integer getPage() {
return this.page;
}
/**
*
* The page on which a block was detected. Page
is returned by synchronous and asynchronous operations.
* Page values greater than 1 are only returned for multipage documents that are in PDF or TIFF format. A scanned
* image (JPEG/PNG) provided to an asynchronous operation, even if it contains multiple document pages, is
* considered a single-page document. This means that for scanned images the value of Page
is always 1.
*
*
* @param page
* The page on which a block was detected. Page
is returned by synchronous and asynchronous
* operations. Page values greater than 1 are only returned for multipage documents that are in PDF or TIFF
* format. A scanned image (JPEG/PNG) provided to an asynchronous operation, even if it contains multiple
* document pages, is considered a single-page document. This means that for scanned images the value of
* Page
is always 1.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withPage(Integer page) {
setPage(page);
return this;
}
/**
*
*
* @param query
*/
public void setQuery(Query query) {
this.query = query;
}
/**
*
*
* @return
*/
public Query getQuery() {
return this.query;
}
/**
*
*
* @param query
* @return Returns a reference to this object so that method calls can be chained together.
*/
public Block withQuery(Query query) {
setQuery(query);
return this;
}
/**
* Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be
* redacted from this string using a placeholder value.
*
* @return A string representation of this object.
*
* @see java.lang.Object#toString()
*/
@Override
public String toString() {
StringBuilder sb = new StringBuilder();
sb.append("{");
if (getBlockType() != null)
sb.append("BlockType: ").append(getBlockType()).append(",");
if (getConfidence() != null)
sb.append("Confidence: ").append(getConfidence()).append(",");
if (getText() != null)
sb.append("Text: ").append(getText()).append(",");
if (getTextType() != null)
sb.append("TextType: ").append(getTextType()).append(",");
if (getRowIndex() != null)
sb.append("RowIndex: ").append(getRowIndex()).append(",");
if (getColumnIndex() != null)
sb.append("ColumnIndex: ").append(getColumnIndex()).append(",");
if (getRowSpan() != null)
sb.append("RowSpan: ").append(getRowSpan()).append(",");
if (getColumnSpan() != null)
sb.append("ColumnSpan: ").append(getColumnSpan()).append(",");
if (getGeometry() != null)
sb.append("Geometry: ").append(getGeometry()).append(",");
if (getId() != null)
sb.append("Id: ").append(getId()).append(",");
if (getRelationships() != null)
sb.append("Relationships: ").append(getRelationships()).append(",");
if (getEntityTypes() != null)
sb.append("EntityTypes: ").append(getEntityTypes()).append(",");
if (getSelectionStatus() != null)
sb.append("SelectionStatus: ").append(getSelectionStatus()).append(",");
if (getPage() != null)
sb.append("Page: ").append(getPage()).append(",");
if (getQuery() != null)
sb.append("Query: ").append(getQuery());
sb.append("}");
return sb.toString();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (obj instanceof Block == false)
return false;
Block other = (Block) obj;
if (other.getBlockType() == null ^ this.getBlockType() == null)
return false;
if (other.getBlockType() != null && other.getBlockType().equals(this.getBlockType()) == false)
return false;
if (other.getConfidence() == null ^ this.getConfidence() == null)
return false;
if (other.getConfidence() != null && other.getConfidence().equals(this.getConfidence()) == false)
return false;
if (other.getText() == null ^ this.getText() == null)
return false;
if (other.getText() != null && other.getText().equals(this.getText()) == false)
return false;
if (other.getTextType() == null ^ this.getTextType() == null)
return false;
if (other.getTextType() != null && other.getTextType().equals(this.getTextType()) == false)
return false;
if (other.getRowIndex() == null ^ this.getRowIndex() == null)
return false;
if (other.getRowIndex() != null && other.getRowIndex().equals(this.getRowIndex()) == false)
return false;
if (other.getColumnIndex() == null ^ this.getColumnIndex() == null)
return false;
if (other.getColumnIndex() != null && other.getColumnIndex().equals(this.getColumnIndex()) == false)
return false;
if (other.getRowSpan() == null ^ this.getRowSpan() == null)
return false;
if (other.getRowSpan() != null && other.getRowSpan().equals(this.getRowSpan()) == false)
return false;
if (other.getColumnSpan() == null ^ this.getColumnSpan() == null)
return false;
if (other.getColumnSpan() != null && other.getColumnSpan().equals(this.getColumnSpan()) == false)
return false;
if (other.getGeometry() == null ^ this.getGeometry() == null)
return false;
if (other.getGeometry() != null && other.getGeometry().equals(this.getGeometry()) == false)
return false;
if (other.getId() == null ^ this.getId() == null)
return false;
if (other.getId() != null && other.getId().equals(this.getId()) == false)
return false;
if (other.getRelationships() == null ^ this.getRelationships() == null)
return false;
if (other.getRelationships() != null && other.getRelationships().equals(this.getRelationships()) == false)
return false;
if (other.getEntityTypes() == null ^ this.getEntityTypes() == null)
return false;
if (other.getEntityTypes() != null && other.getEntityTypes().equals(this.getEntityTypes()) == false)
return false;
if (other.getSelectionStatus() == null ^ this.getSelectionStatus() == null)
return false;
if (other.getSelectionStatus() != null && other.getSelectionStatus().equals(this.getSelectionStatus()) == false)
return false;
if (other.getPage() == null ^ this.getPage() == null)
return false;
if (other.getPage() != null && other.getPage().equals(this.getPage()) == false)
return false;
if (other.getQuery() == null ^ this.getQuery() == null)
return false;
if (other.getQuery() != null && other.getQuery().equals(this.getQuery()) == false)
return false;
return true;
}
@Override
public int hashCode() {
final int prime = 31;
int hashCode = 1;
hashCode = prime * hashCode + ((getBlockType() == null) ? 0 : getBlockType().hashCode());
hashCode = prime * hashCode + ((getConfidence() == null) ? 0 : getConfidence().hashCode());
hashCode = prime * hashCode + ((getText() == null) ? 0 : getText().hashCode());
hashCode = prime * hashCode + ((getTextType() == null) ? 0 : getTextType().hashCode());
hashCode = prime * hashCode + ((getRowIndex() == null) ? 0 : getRowIndex().hashCode());
hashCode = prime * hashCode + ((getColumnIndex() == null) ? 0 : getColumnIndex().hashCode());
hashCode = prime * hashCode + ((getRowSpan() == null) ? 0 : getRowSpan().hashCode());
hashCode = prime * hashCode + ((getColumnSpan() == null) ? 0 : getColumnSpan().hashCode());
hashCode = prime * hashCode + ((getGeometry() == null) ? 0 : getGeometry().hashCode());
hashCode = prime * hashCode + ((getId() == null) ? 0 : getId().hashCode());
hashCode = prime * hashCode + ((getRelationships() == null) ? 0 : getRelationships().hashCode());
hashCode = prime * hashCode + ((getEntityTypes() == null) ? 0 : getEntityTypes().hashCode());
hashCode = prime * hashCode + ((getSelectionStatus() == null) ? 0 : getSelectionStatus().hashCode());
hashCode = prime * hashCode + ((getPage() == null) ? 0 : getPage().hashCode());
hashCode = prime * hashCode + ((getQuery() == null) ? 0 : getQuery().hashCode());
return hashCode;
}
@Override
public Block clone() {
try {
return (Block) super.clone();
} catch (CloneNotSupportedException e) {
throw new IllegalStateException("Got a CloneNotSupportedException from Object.clone() " + "even though we're Cloneable!", e);
}
}
@com.amazonaws.annotation.SdkInternalApi
@Override
public void marshall(ProtocolMarshaller protocolMarshaller) {
com.amazonaws.services.textract.model.transform.BlockMarshaller.getInstance().marshall(this, protocolMarshaller);
}
}