Interface DocumentProcessingConfig.ParsingConfig.LayoutParsingConfigOrBuilder (0.60.0)

public static interface DocumentProcessingConfig.ParsingConfig.LayoutParsingConfigOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getEnableImageAnnotation()

public abstract boolean getEnableImageAnnotation()

Optional. If true, the LLM based annotation is added to the image during parsing.

bool enable_image_annotation = 2 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
boolean

The enableImageAnnotation.

getEnableTableAnnotation()

public abstract boolean getEnableTableAnnotation()

Optional. If true, the LLM based annotation is added to the table during parsing.

bool enable_table_annotation = 1 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
boolean

The enableTableAnnotation.

getExcludeHtmlClasses(int index)

public abstract String getExcludeHtmlClasses(int index)

Optional. List of HTML classes to exclude from the parsed content.

repeated string exclude_html_classes = 11 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The excludeHtmlClasses at the given index.

getExcludeHtmlClassesBytes(int index)

public abstract ByteString getExcludeHtmlClassesBytes(int index)

Optional. List of HTML classes to exclude from the parsed content.

repeated string exclude_html_classes = 11 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the excludeHtmlClasses at the given index.

getExcludeHtmlClassesCount()

public abstract int getExcludeHtmlClassesCount()

Optional. List of HTML classes to exclude from the parsed content.

repeated string exclude_html_classes = 11 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The count of excludeHtmlClasses.

getExcludeHtmlClassesList()

public abstract List getExcludeHtmlClassesList()

Optional. List of HTML classes to exclude from the parsed content.

repeated string exclude_html_classes = 11 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
List<String>

A list containing the excludeHtmlClasses.

getExcludeHtmlElements(int index)

public abstract String getExcludeHtmlElements(int index)

Optional. List of HTML elements to exclude from the parsed content.

repeated string exclude_html_elements = 10 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The excludeHtmlElements at the given index.

getExcludeHtmlElementsBytes(int index)

public abstract ByteString getExcludeHtmlElementsBytes(int index)

Optional. List of HTML elements to exclude from the parsed content.

repeated string exclude_html_elements = 10 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the excludeHtmlElements at the given index.

getExcludeHtmlElementsCount()

public abstract int getExcludeHtmlElementsCount()

Optional. List of HTML elements to exclude from the parsed content.

repeated string exclude_html_elements = 10 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The count of excludeHtmlElements.

getExcludeHtmlElementsList()

public abstract List getExcludeHtmlElementsList()

Optional. List of HTML elements to exclude from the parsed content.

repeated string exclude_html_elements = 10 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
List<String>

A list containing the excludeHtmlElements.

getExcludeHtmlIds(int index)

public abstract String getExcludeHtmlIds(int index)

Optional. List of HTML ids to exclude from the parsed content.

repeated string exclude_html_ids = 12 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The excludeHtmlIds at the given index.

getExcludeHtmlIdsBytes(int index)

public abstract ByteString getExcludeHtmlIdsBytes(int index)

Optional. List of HTML ids to exclude from the parsed content.

repeated string exclude_html_ids = 12 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the excludeHtmlIds at the given index.

getExcludeHtmlIdsCount()

public abstract int getExcludeHtmlIdsCount()

Optional. List of HTML ids to exclude from the parsed content.

repeated string exclude_html_ids = 12 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The count of excludeHtmlIds.

getExcludeHtmlIdsList()

public abstract List getExcludeHtmlIdsList()

Optional. List of HTML ids to exclude from the parsed content.

repeated string exclude_html_ids = 12 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
List<String>

A list containing the excludeHtmlIds.

getStructuredContentTypes(int index)

public abstract String getStructuredContentTypes(int index)

Optional. Contains the required structure types to extract from the document. Supported values:

  • shareholder-structure

repeated string structured_content_types = 9 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The structuredContentTypes at the given index.

getStructuredContentTypesBytes(int index)

public abstract ByteString getStructuredContentTypesBytes(int index)

Optional. Contains the required structure types to extract from the document. Supported values:

  • shareholder-structure

repeated string structured_content_types = 9 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the structuredContentTypes at the given index.

getStructuredContentTypesCount()

public abstract int getStructuredContentTypesCount()

Optional. Contains the required structure types to extract from the document. Supported values:

  • shareholder-structure

repeated string structured_content_types = 9 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The count of structuredContentTypes.

getStructuredContentTypesList()

public abstract List getStructuredContentTypesList()

Optional. Contains the required structure types to extract from the document. Supported values:

  • shareholder-structure

repeated string structured_content_types = 9 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
List<String>

A list containing the structuredContentTypes.