Class OcrConfig (2.47.0)

public final class OcrConfig extends GeneratedMessageV3 implements OcrConfigOrBuilder

Config for Document OCR.

Protobuf type google.cloud.documentai.v1beta3.OcrConfig

Implements

OcrConfigOrBuilder

Static Fields

ADVANCED_OCR_OPTIONS_FIELD_NUMBER

public static final int ADVANCED_OCR_OPTIONS_FIELD_NUMBER
Field Value
Type Description
int

COMPUTE_STYLE_INFO_FIELD_NUMBER

public static final int COMPUTE_STYLE_INFO_FIELD_NUMBER
Field Value
Type Description
int

DISABLE_CHARACTER_BOXES_DETECTION_FIELD_NUMBER

public static final int DISABLE_CHARACTER_BOXES_DETECTION_FIELD_NUMBER
Field Value
Type Description
int

ENABLE_IMAGE_QUALITY_SCORES_FIELD_NUMBER

public static final int ENABLE_IMAGE_QUALITY_SCORES_FIELD_NUMBER
Field Value
Type Description
int

ENABLE_NATIVE_PDF_PARSING_FIELD_NUMBER

public static final int ENABLE_NATIVE_PDF_PARSING_FIELD_NUMBER
Field Value
Type Description
int

ENABLE_SYMBOL_FIELD_NUMBER

public static final int ENABLE_SYMBOL_FIELD_NUMBER
Field Value
Type Description
int

HINTS_FIELD_NUMBER

public static final int HINTS_FIELD_NUMBER
Field Value
Type Description
int

PREMIUM_FEATURES_FIELD_NUMBER

public static final int PREMIUM_FEATURES_FIELD_NUMBER
Field Value
Type Description
int

Static Methods

getDefaultInstance()

public static OcrConfig getDefaultInstance()
Returns
Type Description
OcrConfig

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
Type Description
Descriptor

newBuilder()

public static OcrConfig.Builder newBuilder()
Returns
Type Description
OcrConfig.Builder

newBuilder(OcrConfig prototype)

public static OcrConfig.Builder newBuilder(OcrConfig prototype)
Parameter
Name Description
prototype OcrConfig
Returns
Type Description
OcrConfig.Builder

parseDelimitedFrom(InputStream input)

public static OcrConfig parseDelimitedFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
OcrConfig
Exceptions
Type Description
IOException

parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static OcrConfig parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
OcrConfig
Exceptions
Type Description
IOException

parseFrom(byte[] data)

public static OcrConfig parseFrom(byte[] data)
Parameter
Name Description
data byte[]
Returns
Type Description
OcrConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)

public static OcrConfig parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data byte[]
extensionRegistry ExtensionRegistryLite
Returns
Type Description
OcrConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data)

public static OcrConfig parseFrom(ByteString data)
Parameter
Name Description
data ByteString
Returns
Type Description
OcrConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)

public static OcrConfig parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteString
extensionRegistry ExtensionRegistryLite
Returns
Type Description
OcrConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(CodedInputStream input)

public static OcrConfig parseFrom(CodedInputStream input)
Parameter
Name Description
input CodedInputStream
Returns
Type Description
OcrConfig
Exceptions
Type Description
IOException

parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public static OcrConfig parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input CodedInputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
OcrConfig
Exceptions
Type Description
IOException

parseFrom(InputStream input)

public static OcrConfig parseFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
OcrConfig
Exceptions
Type Description
IOException

parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static OcrConfig parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
OcrConfig
Exceptions
Type Description
IOException

parseFrom(ByteBuffer data)

public static OcrConfig parseFrom(ByteBuffer data)
Parameter
Name Description
data ByteBuffer
Returns
Type Description
OcrConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)

public static OcrConfig parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteBuffer
extensionRegistry ExtensionRegistryLite
Returns
Type Description
OcrConfig
Exceptions
Type Description
InvalidProtocolBufferException

parser()

public static Parser<OcrConfig> parser()
Returns
Type Description
Parser<OcrConfig>

Methods

equals(Object obj)

public boolean equals(Object obj)
Parameter
Name Description
obj Object
Returns
Type Description
boolean
Overrides

getAdvancedOcrOptions(int index)

public String getAdvancedOcrOptions(int index)

A list of advanced OCR options to further fine-tune OCR behavior. Current valid values are:

  • legacy_layout: a heuristics layout detection algorithm, which serves as an alternative to the current ML-based layout detection algorithm. Customers can choose the best suitable layout algorithm based on their situation.

repeated string advanced_ocr_options = 5;

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The advancedOcrOptions at the given index.

getAdvancedOcrOptionsBytes(int index)

public ByteString getAdvancedOcrOptionsBytes(int index)

A list of advanced OCR options to further fine-tune OCR behavior. Current valid values are:

  • legacy_layout: a heuristics layout detection algorithm, which serves as an alternative to the current ML-based layout detection algorithm. Customers can choose the best suitable layout algorithm based on their situation.

repeated string advanced_ocr_options = 5;

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the advancedOcrOptions at the given index.

getAdvancedOcrOptionsCount()

public int getAdvancedOcrOptionsCount()

A list of advanced OCR options to further fine-tune OCR behavior. Current valid values are:

  • legacy_layout: a heuristics layout detection algorithm, which serves as an alternative to the current ML-based layout detection algorithm. Customers can choose the best suitable layout algorithm based on their situation.

repeated string advanced_ocr_options = 5;

Returns
Type Description
int

The count of advancedOcrOptions.

getAdvancedOcrOptionsList()

public ProtocolStringList getAdvancedOcrOptionsList()

A list of advanced OCR options to further fine-tune OCR behavior. Current valid values are:

  • legacy_layout: a heuristics layout detection algorithm, which serves as an alternative to the current ML-based layout detection algorithm. Customers can choose the best suitable layout algorithm based on their situation.

repeated string advanced_ocr_options = 5;

Returns
Type Description
ProtocolStringList

A list containing the advancedOcrOptions.

getComputeStyleInfo() (deprecated)

public boolean getComputeStyleInfo()

Deprecated. google.cloud.documentai.v1beta3.OcrConfig.compute_style_info is deprecated. See google/cloud/documentai/v1beta3/document_io.proto;l=165

Turn on font identification model and return font style information. Deprecated, use PremiumFeatures.compute_style_info instead.

bool compute_style_info = 8 [deprecated = true];

Returns
Type Description
boolean

The computeStyleInfo.

getDefaultInstanceForType()

public OcrConfig getDefaultInstanceForType()
Returns
Type Description
OcrConfig

getDisableCharacterBoxesDetection()

public boolean getDisableCharacterBoxesDetection()

Turn off character box detector in OCR engine. Character box detection is enabled by default in OCR 2.0 (and later) processors.

bool disable_character_boxes_detection = 10;

Returns
Type Description
boolean

The disableCharacterBoxesDetection.

getEnableImageQualityScores()

public boolean getEnableImageQualityScores()

Enables intelligent document quality scores after OCR. Can help with diagnosing why OCR responses are of poor quality for a given input. Adds additional latency comparable to regular OCR to the process call.

bool enable_image_quality_scores = 4;

Returns
Type Description
boolean

The enableImageQualityScores.

getEnableNativePdfParsing()

public boolean getEnableNativePdfParsing()

Enables special handling for PDFs with existing text information. Results in better text extraction quality in such PDF inputs.

bool enable_native_pdf_parsing = 3;

Returns
Type Description
boolean

The enableNativePdfParsing.

getEnableSymbol()

public boolean getEnableSymbol()

Includes symbol level OCR information if set to true.

bool enable_symbol = 6;

Returns
Type Description
boolean

The enableSymbol.

getHints()

public OcrConfig.Hints getHints()

Hints for the OCR model.

.google.cloud.documentai.v1beta3.OcrConfig.Hints hints = 2;

Returns
Type Description
OcrConfig.Hints

The hints.

getHintsOrBuilder()

public OcrConfig.HintsOrBuilder getHintsOrBuilder()

Hints for the OCR model.

.google.cloud.documentai.v1beta3.OcrConfig.Hints hints = 2;

Returns
Type Description
OcrConfig.HintsOrBuilder

getParserForType()

public Parser<OcrConfig> getParserForType()
Returns
Type Description
Parser<OcrConfig>
Overrides

getPremiumFeatures()

public OcrConfig.PremiumFeatures getPremiumFeatures()

Configurations for premium OCR features.

.google.cloud.documentai.v1beta3.OcrConfig.PremiumFeatures premium_features = 11;

Returns
Type Description
OcrConfig.PremiumFeatures

The premiumFeatures.

getPremiumFeaturesOrBuilder()

public OcrConfig.PremiumFeaturesOrBuilder getPremiumFeaturesOrBuilder()

Configurations for premium OCR features.

.google.cloud.documentai.v1beta3.OcrConfig.PremiumFeatures premium_features = 11;

Returns
Type Description
OcrConfig.PremiumFeaturesOrBuilder

getSerializedSize()

public int getSerializedSize()
Returns
Type Description
int
Overrides

hasHints()

public boolean hasHints()

Hints for the OCR model.

.google.cloud.documentai.v1beta3.OcrConfig.Hints hints = 2;

Returns
Type Description
boolean

Whether the hints field is set.

hasPremiumFeatures()

public boolean hasPremiumFeatures()

Configurations for premium OCR features.

.google.cloud.documentai.v1beta3.OcrConfig.PremiumFeatures premium_features = 11;

Returns
Type Description
boolean

Whether the premiumFeatures field is set.

hashCode()

public int hashCode()
Returns
Type Description
int
Overrides

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Type Description
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

newBuilderForType()

public OcrConfig.Builder newBuilderForType()
Returns
Type Description
OcrConfig.Builder

newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protected OcrConfig.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Name Description
parent BuilderParent
Returns
Type Description
OcrConfig.Builder
Overrides

newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Name Description
unused UnusedPrivateParameter
Returns
Type Description
Object
Overrides

toBuilder()

public OcrConfig.Builder toBuilder()
Returns
Type Description
OcrConfig.Builder

writeTo(CodedOutputStream output)

public void writeTo(CodedOutputStream output)
Parameter
Name Description
output CodedOutputStream
Overrides
Exceptions
Type Description
IOException