com.google.cloud.automl.v1.BatchPredictInputConfig Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of proto-google-cloud-automl-v1 Show documentation
Show all versions of proto-google-cloud-automl-v1 Show documentation
PROTO library for proto-google-cloud-automl-v1
/*
* Copyright 2024 Google LLC
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* https://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License 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.
*/
// Generated by the protocol buffer compiler. DO NOT EDIT!
// source: google/cloud/automl/v1/io.proto
// Protobuf Java Version: 3.25.4
package com.google.cloud.automl.v1;
/**
*
*
*
* Input configuration for BatchPredict Action.
*
* The format of input depends on the ML problem of the model used for
* prediction. As input source the
* [gcs_source][google.cloud.automl.v1.InputConfig.gcs_source]
* is expected, unless specified otherwise.
*
* The formats are represented in EBNF with commas being literal and with
* non-terminal symbols defined near the end of this comment. The formats
* are:
*
* <h4>AutoML Vision</h4>
* <div class="ds-selector-tabs"><section><h5>Classification</h5>
*
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH
*
* The Google Cloud Storage location of an image of up to
* 30MB in size. Supported extensions: .JPEG, .GIF, .PNG.
* This path is treated as the ID in the batch predict output.
*
* Sample rows:
*
* gs://folder/image1.jpeg
* gs://folder/image2.gif
* gs://folder/image3.png
*
* </section><section><h5>Object Detection</h5>
*
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH
*
* The Google Cloud Storage location of an image of up to
* 30MB in size. Supported extensions: .JPEG, .GIF, .PNG.
* This path is treated as the ID in the batch predict output.
*
* Sample rows:
*
* gs://folder/image1.jpeg
* gs://folder/image2.gif
* gs://folder/image3.png
* </section>
* </div>
*
* <h4>AutoML Video Intelligence</h4>
* <div class="ds-selector-tabs"><section><h5>Classification</h5>
*
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH,TIME_SEGMENT_START,TIME_SEGMENT_END
*
* `GCS_FILE_PATH` is the Google Cloud Storage location of video up to 50GB in
* size and up to 3h in duration duration.
* Supported extensions: .MOV, .MPEG4, .MP4, .AVI.
*
* `TIME_SEGMENT_START` and `TIME_SEGMENT_END` must be within the
* length of the video, and the end time must be after the start time.
*
* Sample rows:
*
* gs://folder/video1.mp4,10,40
* gs://folder/video1.mp4,20,60
* gs://folder/vid2.mov,0,inf
*
* </section><section><h5>Object Tracking</h5>
*
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH,TIME_SEGMENT_START,TIME_SEGMENT_END
*
* `GCS_FILE_PATH` is the Google Cloud Storage location of video up to 50GB in
* size and up to 3h in duration duration.
* Supported extensions: .MOV, .MPEG4, .MP4, .AVI.
*
* `TIME_SEGMENT_START` and `TIME_SEGMENT_END` must be within the
* length of the video, and the end time must be after the start time.
*
* Sample rows:
*
* gs://folder/video1.mp4,10,40
* gs://folder/video1.mp4,20,60
* gs://folder/vid2.mov,0,inf
* </section>
* </div>
*
* <h4>AutoML Natural Language</h4>
* <div class="ds-selector-tabs"><section><h5>Classification</h5>
*
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH
*
* `GCS_FILE_PATH` is the Google Cloud Storage location of a text file.
* Supported file extensions: .TXT, .PDF, .TIF, .TIFF
*
* Text files can be no larger than 10MB in size.
*
* Sample rows:
*
* gs://folder/text1.txt
* gs://folder/text2.pdf
* gs://folder/text3.tif
*
* </section><section><h5>Sentiment Analysis</h5>
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH
*
* `GCS_FILE_PATH` is the Google Cloud Storage location of a text file.
* Supported file extensions: .TXT, .PDF, .TIF, .TIFF
*
* Text files can be no larger than 128kB in size.
*
* Sample rows:
*
* gs://folder/text1.txt
* gs://folder/text2.pdf
* gs://folder/text3.tif
*
* </section><section><h5>Entity Extraction</h5>
*
* One or more JSONL (JSON Lines) files that either provide inline text or
* documents. You can only use one format, either inline text or documents,
* for a single call to [AutoMl.BatchPredict].
*
* Each JSONL file contains a per line a proto that
* wraps a temporary user-assigned TextSnippet ID (string up to 2000
* characters long) called "id", a TextSnippet proto (in
* JSON representation) and zero or more TextFeature protos. Any given
* text snippet content must have 30,000 characters or less, and also
* be UTF-8 NFC encoded (ASCII already is). The IDs provided should be
* unique.
*
* Each document JSONL file contains, per line, a proto that wraps a Document
* proto with `input_config` set. Each document cannot exceed 2MB in size.
*
* Supported document extensions: .PDF, .TIF, .TIFF
*
* Each JSONL file must not exceed 100MB in size, and no more than 20
* JSONL files may be passed.
*
* Sample inline JSONL file (Shown with artificial line
* breaks. Actual line breaks are denoted by "\n".):
*
* {
* "id": "my_first_id",
* "text_snippet": { "content": "dog car cat"},
* "text_features": [
* {
* "text_segment": {"start_offset": 4, "end_offset": 6},
* "structural_type": PARAGRAPH,
* "bounding_poly": {
* "normalized_vertices": [
* {"x": 0.1, "y": 0.1},
* {"x": 0.1, "y": 0.3},
* {"x": 0.3, "y": 0.3},
* {"x": 0.3, "y": 0.1},
* ]
* },
* }
* ],
* }\n
* {
* "id": "2",
* "text_snippet": {
* "content": "Extended sample content",
* "mime_type": "text/plain"
* }
* }
*
* Sample document JSONL file (Shown with artificial line
* breaks. Actual line breaks are denoted by "\n".):
*
* {
* "document": {
* "input_config": {
* "gcs_source": { "input_uris": [ "gs://folder/document1.pdf" ]
* }
* }
* }
* }\n
* {
* "document": {
* "input_config": {
* "gcs_source": { "input_uris": [ "gs://folder/document2.tif" ]
* }
* }
* }
* }
* </section>
* </div>
*
* <h4>AutoML Tables</h4><div class="ui-datasection-main"><section
* class="selected">
*
* See [Preparing your training
* data](https://cloud.google.com/automl-tables/docs/predict-batch) for more
* information.
*
* You can use either
* [gcs_source][google.cloud.automl.v1.BatchPredictInputConfig.gcs_source]
* or
* [bigquery_source][BatchPredictInputConfig.bigquery_source].
*
* **For gcs_source:**
*
* CSV file(s), each by itself 10GB or smaller and total size must be
* 100GB or smaller, where first file must have a header containing
* column names. If the first row of a subsequent file is the same as
* the header, then it is also treated as a header. All other rows
* contain values for the corresponding columns.
*
* The column names must contain the model's
* [input_feature_column_specs'][google.cloud.automl.v1.TablesModelMetadata.input_feature_column_specs]
* [display_name-s][google.cloud.automl.v1.ColumnSpec.display_name]
* (order doesn't matter). The columns corresponding to the model's
* input feature column specs must contain values compatible with the
* column spec's data types. Prediction on all the rows, i.e. the CSV
* lines, will be attempted.
*
*
* Sample rows from a CSV file:
* <pre>
* "First Name","Last Name","Dob","Addresses"
* "John","Doe","1968-01-22","[{"status":"current","address":"123_First_Avenue","city":"Seattle","state":"WA","zip":"11111","numberOfYears":"1"},{"status":"previous","address":"456_Main_Street","city":"Portland","state":"OR","zip":"22222","numberOfYears":"5"}]"
* "Jane","Doe","1980-10-16","[{"status":"current","address":"789_Any_Avenue","city":"Albany","state":"NY","zip":"33333","numberOfYears":"2"},{"status":"previous","address":"321_Main_Street","city":"Hoboken","state":"NJ","zip":"44444","numberOfYears":"3"}]}
* </pre>
* **For bigquery_source:**
*
* The URI of a BigQuery table. The user data size of the BigQuery
* table must be 100GB or smaller.
*
* The column names must contain the model's
* [input_feature_column_specs'][google.cloud.automl.v1.TablesModelMetadata.input_feature_column_specs]
* [display_name-s][google.cloud.automl.v1.ColumnSpec.display_name]
* (order doesn't matter). The columns corresponding to the model's
* input feature column specs must contain values compatible with the
* column spec's data types. Prediction on all the rows of the table
* will be attempted.
* </section>
* </div>
*
* **Input field definitions:**
*
* `GCS_FILE_PATH`
* : The path to a file on Google Cloud Storage. For example,
* "gs://folder/video.avi".
*
* `TIME_SEGMENT_START`
* : (`TIME_OFFSET`)
* Expresses a beginning, inclusive, of a time segment
* within an example that has a time dimension
* (e.g. video).
*
* `TIME_SEGMENT_END`
* : (`TIME_OFFSET`)
* Expresses an end, exclusive, of a time segment within
* n example that has a time dimension (e.g. video).
*
* `TIME_OFFSET`
* : A number of seconds as measured from the start of an
* example (e.g. video). Fractions are allowed, up to a
* microsecond precision. "inf" is allowed, and it means the end
* of the example.
*
* **Errors:**
*
* If any of the provided CSV files can't be parsed or if more than certain
* percent of CSV rows cannot be processed then the operation fails and
* prediction does not happen. Regardless of overall success or failure the
* per-row failures, up to a certain count cap, will be listed in
* Operation.metadata.partial_failures.
*
*
* Protobuf type {@code google.cloud.automl.v1.BatchPredictInputConfig}
*/
public final class BatchPredictInputConfig extends com.google.protobuf.GeneratedMessageV3
implements
// @@protoc_insertion_point(message_implements:google.cloud.automl.v1.BatchPredictInputConfig)
BatchPredictInputConfigOrBuilder {
private static final long serialVersionUID = 0L;
// Use BatchPredictInputConfig.newBuilder() to construct.
private BatchPredictInputConfig(com.google.protobuf.GeneratedMessageV3.Builder builder) {
super(builder);
}
private BatchPredictInputConfig() {}
@java.lang.Override
@SuppressWarnings({"unused"})
protected java.lang.Object newInstance(UnusedPrivateParameter unused) {
return new BatchPredictInputConfig();
}
public static final com.google.protobuf.Descriptors.Descriptor getDescriptor() {
return com.google.cloud.automl.v1.Io
.internal_static_google_cloud_automl_v1_BatchPredictInputConfig_descriptor;
}
@java.lang.Override
protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable
internalGetFieldAccessorTable() {
return com.google.cloud.automl.v1.Io
.internal_static_google_cloud_automl_v1_BatchPredictInputConfig_fieldAccessorTable
.ensureFieldAccessorsInitialized(
com.google.cloud.automl.v1.BatchPredictInputConfig.class,
com.google.cloud.automl.v1.BatchPredictInputConfig.Builder.class);
}
private int sourceCase_ = 0;
@SuppressWarnings("serial")
private java.lang.Object source_;
public enum SourceCase
implements
com.google.protobuf.Internal.EnumLite,
com.google.protobuf.AbstractMessage.InternalOneOfEnum {
GCS_SOURCE(1),
SOURCE_NOT_SET(0);
private final int value;
private SourceCase(int value) {
this.value = value;
}
/**
* @param value The number of the enum to look for.
* @return The enum associated with the given number.
* @deprecated Use {@link #forNumber(int)} instead.
*/
@java.lang.Deprecated
public static SourceCase valueOf(int value) {
return forNumber(value);
}
public static SourceCase forNumber(int value) {
switch (value) {
case 1:
return GCS_SOURCE;
case 0:
return SOURCE_NOT_SET;
default:
return null;
}
}
public int getNumber() {
return this.value;
}
};
public SourceCase getSourceCase() {
return SourceCase.forNumber(sourceCase_);
}
public static final int GCS_SOURCE_FIELD_NUMBER = 1;
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*
* @return Whether the gcsSource field is set.
*/
@java.lang.Override
public boolean hasGcsSource() {
return sourceCase_ == 1;
}
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*
* @return The gcsSource.
*/
@java.lang.Override
public com.google.cloud.automl.v1.GcsSource getGcsSource() {
if (sourceCase_ == 1) {
return (com.google.cloud.automl.v1.GcsSource) source_;
}
return com.google.cloud.automl.v1.GcsSource.getDefaultInstance();
}
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*/
@java.lang.Override
public com.google.cloud.automl.v1.GcsSourceOrBuilder getGcsSourceOrBuilder() {
if (sourceCase_ == 1) {
return (com.google.cloud.automl.v1.GcsSource) source_;
}
return com.google.cloud.automl.v1.GcsSource.getDefaultInstance();
}
private byte memoizedIsInitialized = -1;
@java.lang.Override
public final boolean isInitialized() {
byte isInitialized = memoizedIsInitialized;
if (isInitialized == 1) return true;
if (isInitialized == 0) return false;
memoizedIsInitialized = 1;
return true;
}
@java.lang.Override
public void writeTo(com.google.protobuf.CodedOutputStream output) throws java.io.IOException {
if (sourceCase_ == 1) {
output.writeMessage(1, (com.google.cloud.automl.v1.GcsSource) source_);
}
getUnknownFields().writeTo(output);
}
@java.lang.Override
public int getSerializedSize() {
int size = memoizedSize;
if (size != -1) return size;
size = 0;
if (sourceCase_ == 1) {
size +=
com.google.protobuf.CodedOutputStream.computeMessageSize(
1, (com.google.cloud.automl.v1.GcsSource) source_);
}
size += getUnknownFields().getSerializedSize();
memoizedSize = size;
return size;
}
@java.lang.Override
public boolean equals(final java.lang.Object obj) {
if (obj == this) {
return true;
}
if (!(obj instanceof com.google.cloud.automl.v1.BatchPredictInputConfig)) {
return super.equals(obj);
}
com.google.cloud.automl.v1.BatchPredictInputConfig other =
(com.google.cloud.automl.v1.BatchPredictInputConfig) obj;
if (!getSourceCase().equals(other.getSourceCase())) return false;
switch (sourceCase_) {
case 1:
if (!getGcsSource().equals(other.getGcsSource())) return false;
break;
case 0:
default:
}
if (!getUnknownFields().equals(other.getUnknownFields())) return false;
return true;
}
@java.lang.Override
public int hashCode() {
if (memoizedHashCode != 0) {
return memoizedHashCode;
}
int hash = 41;
hash = (19 * hash) + getDescriptor().hashCode();
switch (sourceCase_) {
case 1:
hash = (37 * hash) + GCS_SOURCE_FIELD_NUMBER;
hash = (53 * hash) + getGcsSource().hashCode();
break;
case 0:
default:
}
hash = (29 * hash) + getUnknownFields().hashCode();
memoizedHashCode = hash;
return hash;
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseFrom(
java.nio.ByteBuffer data) throws com.google.protobuf.InvalidProtocolBufferException {
return PARSER.parseFrom(data);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseFrom(
java.nio.ByteBuffer data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
throws com.google.protobuf.InvalidProtocolBufferException {
return PARSER.parseFrom(data, extensionRegistry);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseFrom(
com.google.protobuf.ByteString data)
throws com.google.protobuf.InvalidProtocolBufferException {
return PARSER.parseFrom(data);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseFrom(
com.google.protobuf.ByteString data,
com.google.protobuf.ExtensionRegistryLite extensionRegistry)
throws com.google.protobuf.InvalidProtocolBufferException {
return PARSER.parseFrom(data, extensionRegistry);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseFrom(byte[] data)
throws com.google.protobuf.InvalidProtocolBufferException {
return PARSER.parseFrom(data);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseFrom(
byte[] data, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
throws com.google.protobuf.InvalidProtocolBufferException {
return PARSER.parseFrom(data, extensionRegistry);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseFrom(
java.io.InputStream input) throws java.io.IOException {
return com.google.protobuf.GeneratedMessageV3.parseWithIOException(PARSER, input);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseFrom(
java.io.InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
throws java.io.IOException {
return com.google.protobuf.GeneratedMessageV3.parseWithIOException(
PARSER, input, extensionRegistry);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseDelimitedFrom(
java.io.InputStream input) throws java.io.IOException {
return com.google.protobuf.GeneratedMessageV3.parseDelimitedWithIOException(PARSER, input);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseDelimitedFrom(
java.io.InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
throws java.io.IOException {
return com.google.protobuf.GeneratedMessageV3.parseDelimitedWithIOException(
PARSER, input, extensionRegistry);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseFrom(
com.google.protobuf.CodedInputStream input) throws java.io.IOException {
return com.google.protobuf.GeneratedMessageV3.parseWithIOException(PARSER, input);
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig parseFrom(
com.google.protobuf.CodedInputStream input,
com.google.protobuf.ExtensionRegistryLite extensionRegistry)
throws java.io.IOException {
return com.google.protobuf.GeneratedMessageV3.parseWithIOException(
PARSER, input, extensionRegistry);
}
@java.lang.Override
public Builder newBuilderForType() {
return newBuilder();
}
public static Builder newBuilder() {
return DEFAULT_INSTANCE.toBuilder();
}
public static Builder newBuilder(com.google.cloud.automl.v1.BatchPredictInputConfig prototype) {
return DEFAULT_INSTANCE.toBuilder().mergeFrom(prototype);
}
@java.lang.Override
public Builder toBuilder() {
return this == DEFAULT_INSTANCE ? new Builder() : new Builder().mergeFrom(this);
}
@java.lang.Override
protected Builder newBuilderForType(com.google.protobuf.GeneratedMessageV3.BuilderParent parent) {
Builder builder = new Builder(parent);
return builder;
}
/**
*
*
*
* Input configuration for BatchPredict Action.
*
* The format of input depends on the ML problem of the model used for
* prediction. As input source the
* [gcs_source][google.cloud.automl.v1.InputConfig.gcs_source]
* is expected, unless specified otherwise.
*
* The formats are represented in EBNF with commas being literal and with
* non-terminal symbols defined near the end of this comment. The formats
* are:
*
* <h4>AutoML Vision</h4>
* <div class="ds-selector-tabs"><section><h5>Classification</h5>
*
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH
*
* The Google Cloud Storage location of an image of up to
* 30MB in size. Supported extensions: .JPEG, .GIF, .PNG.
* This path is treated as the ID in the batch predict output.
*
* Sample rows:
*
* gs://folder/image1.jpeg
* gs://folder/image2.gif
* gs://folder/image3.png
*
* </section><section><h5>Object Detection</h5>
*
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH
*
* The Google Cloud Storage location of an image of up to
* 30MB in size. Supported extensions: .JPEG, .GIF, .PNG.
* This path is treated as the ID in the batch predict output.
*
* Sample rows:
*
* gs://folder/image1.jpeg
* gs://folder/image2.gif
* gs://folder/image3.png
* </section>
* </div>
*
* <h4>AutoML Video Intelligence</h4>
* <div class="ds-selector-tabs"><section><h5>Classification</h5>
*
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH,TIME_SEGMENT_START,TIME_SEGMENT_END
*
* `GCS_FILE_PATH` is the Google Cloud Storage location of video up to 50GB in
* size and up to 3h in duration duration.
* Supported extensions: .MOV, .MPEG4, .MP4, .AVI.
*
* `TIME_SEGMENT_START` and `TIME_SEGMENT_END` must be within the
* length of the video, and the end time must be after the start time.
*
* Sample rows:
*
* gs://folder/video1.mp4,10,40
* gs://folder/video1.mp4,20,60
* gs://folder/vid2.mov,0,inf
*
* </section><section><h5>Object Tracking</h5>
*
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH,TIME_SEGMENT_START,TIME_SEGMENT_END
*
* `GCS_FILE_PATH` is the Google Cloud Storage location of video up to 50GB in
* size and up to 3h in duration duration.
* Supported extensions: .MOV, .MPEG4, .MP4, .AVI.
*
* `TIME_SEGMENT_START` and `TIME_SEGMENT_END` must be within the
* length of the video, and the end time must be after the start time.
*
* Sample rows:
*
* gs://folder/video1.mp4,10,40
* gs://folder/video1.mp4,20,60
* gs://folder/vid2.mov,0,inf
* </section>
* </div>
*
* <h4>AutoML Natural Language</h4>
* <div class="ds-selector-tabs"><section><h5>Classification</h5>
*
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH
*
* `GCS_FILE_PATH` is the Google Cloud Storage location of a text file.
* Supported file extensions: .TXT, .PDF, .TIF, .TIFF
*
* Text files can be no larger than 10MB in size.
*
* Sample rows:
*
* gs://folder/text1.txt
* gs://folder/text2.pdf
* gs://folder/text3.tif
*
* </section><section><h5>Sentiment Analysis</h5>
* One or more CSV files where each line is a single column:
*
* GCS_FILE_PATH
*
* `GCS_FILE_PATH` is the Google Cloud Storage location of a text file.
* Supported file extensions: .TXT, .PDF, .TIF, .TIFF
*
* Text files can be no larger than 128kB in size.
*
* Sample rows:
*
* gs://folder/text1.txt
* gs://folder/text2.pdf
* gs://folder/text3.tif
*
* </section><section><h5>Entity Extraction</h5>
*
* One or more JSONL (JSON Lines) files that either provide inline text or
* documents. You can only use one format, either inline text or documents,
* for a single call to [AutoMl.BatchPredict].
*
* Each JSONL file contains a per line a proto that
* wraps a temporary user-assigned TextSnippet ID (string up to 2000
* characters long) called "id", a TextSnippet proto (in
* JSON representation) and zero or more TextFeature protos. Any given
* text snippet content must have 30,000 characters or less, and also
* be UTF-8 NFC encoded (ASCII already is). The IDs provided should be
* unique.
*
* Each document JSONL file contains, per line, a proto that wraps a Document
* proto with `input_config` set. Each document cannot exceed 2MB in size.
*
* Supported document extensions: .PDF, .TIF, .TIFF
*
* Each JSONL file must not exceed 100MB in size, and no more than 20
* JSONL files may be passed.
*
* Sample inline JSONL file (Shown with artificial line
* breaks. Actual line breaks are denoted by "\n".):
*
* {
* "id": "my_first_id",
* "text_snippet": { "content": "dog car cat"},
* "text_features": [
* {
* "text_segment": {"start_offset": 4, "end_offset": 6},
* "structural_type": PARAGRAPH,
* "bounding_poly": {
* "normalized_vertices": [
* {"x": 0.1, "y": 0.1},
* {"x": 0.1, "y": 0.3},
* {"x": 0.3, "y": 0.3},
* {"x": 0.3, "y": 0.1},
* ]
* },
* }
* ],
* }\n
* {
* "id": "2",
* "text_snippet": {
* "content": "Extended sample content",
* "mime_type": "text/plain"
* }
* }
*
* Sample document JSONL file (Shown with artificial line
* breaks. Actual line breaks are denoted by "\n".):
*
* {
* "document": {
* "input_config": {
* "gcs_source": { "input_uris": [ "gs://folder/document1.pdf" ]
* }
* }
* }
* }\n
* {
* "document": {
* "input_config": {
* "gcs_source": { "input_uris": [ "gs://folder/document2.tif" ]
* }
* }
* }
* }
* </section>
* </div>
*
* <h4>AutoML Tables</h4><div class="ui-datasection-main"><section
* class="selected">
*
* See [Preparing your training
* data](https://cloud.google.com/automl-tables/docs/predict-batch) for more
* information.
*
* You can use either
* [gcs_source][google.cloud.automl.v1.BatchPredictInputConfig.gcs_source]
* or
* [bigquery_source][BatchPredictInputConfig.bigquery_source].
*
* **For gcs_source:**
*
* CSV file(s), each by itself 10GB or smaller and total size must be
* 100GB or smaller, where first file must have a header containing
* column names. If the first row of a subsequent file is the same as
* the header, then it is also treated as a header. All other rows
* contain values for the corresponding columns.
*
* The column names must contain the model's
* [input_feature_column_specs'][google.cloud.automl.v1.TablesModelMetadata.input_feature_column_specs]
* [display_name-s][google.cloud.automl.v1.ColumnSpec.display_name]
* (order doesn't matter). The columns corresponding to the model's
* input feature column specs must contain values compatible with the
* column spec's data types. Prediction on all the rows, i.e. the CSV
* lines, will be attempted.
*
*
* Sample rows from a CSV file:
* <pre>
* "First Name","Last Name","Dob","Addresses"
* "John","Doe","1968-01-22","[{"status":"current","address":"123_First_Avenue","city":"Seattle","state":"WA","zip":"11111","numberOfYears":"1"},{"status":"previous","address":"456_Main_Street","city":"Portland","state":"OR","zip":"22222","numberOfYears":"5"}]"
* "Jane","Doe","1980-10-16","[{"status":"current","address":"789_Any_Avenue","city":"Albany","state":"NY","zip":"33333","numberOfYears":"2"},{"status":"previous","address":"321_Main_Street","city":"Hoboken","state":"NJ","zip":"44444","numberOfYears":"3"}]}
* </pre>
* **For bigquery_source:**
*
* The URI of a BigQuery table. The user data size of the BigQuery
* table must be 100GB or smaller.
*
* The column names must contain the model's
* [input_feature_column_specs'][google.cloud.automl.v1.TablesModelMetadata.input_feature_column_specs]
* [display_name-s][google.cloud.automl.v1.ColumnSpec.display_name]
* (order doesn't matter). The columns corresponding to the model's
* input feature column specs must contain values compatible with the
* column spec's data types. Prediction on all the rows of the table
* will be attempted.
* </section>
* </div>
*
* **Input field definitions:**
*
* `GCS_FILE_PATH`
* : The path to a file on Google Cloud Storage. For example,
* "gs://folder/video.avi".
*
* `TIME_SEGMENT_START`
* : (`TIME_OFFSET`)
* Expresses a beginning, inclusive, of a time segment
* within an example that has a time dimension
* (e.g. video).
*
* `TIME_SEGMENT_END`
* : (`TIME_OFFSET`)
* Expresses an end, exclusive, of a time segment within
* n example that has a time dimension (e.g. video).
*
* `TIME_OFFSET`
* : A number of seconds as measured from the start of an
* example (e.g. video). Fractions are allowed, up to a
* microsecond precision. "inf" is allowed, and it means the end
* of the example.
*
* **Errors:**
*
* If any of the provided CSV files can't be parsed or if more than certain
* percent of CSV rows cannot be processed then the operation fails and
* prediction does not happen. Regardless of overall success or failure the
* per-row failures, up to a certain count cap, will be listed in
* Operation.metadata.partial_failures.
*
*
* Protobuf type {@code google.cloud.automl.v1.BatchPredictInputConfig}
*/
public static final class Builder extends com.google.protobuf.GeneratedMessageV3.Builder
implements
// @@protoc_insertion_point(builder_implements:google.cloud.automl.v1.BatchPredictInputConfig)
com.google.cloud.automl.v1.BatchPredictInputConfigOrBuilder {
public static final com.google.protobuf.Descriptors.Descriptor getDescriptor() {
return com.google.cloud.automl.v1.Io
.internal_static_google_cloud_automl_v1_BatchPredictInputConfig_descriptor;
}
@java.lang.Override
protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable
internalGetFieldAccessorTable() {
return com.google.cloud.automl.v1.Io
.internal_static_google_cloud_automl_v1_BatchPredictInputConfig_fieldAccessorTable
.ensureFieldAccessorsInitialized(
com.google.cloud.automl.v1.BatchPredictInputConfig.class,
com.google.cloud.automl.v1.BatchPredictInputConfig.Builder.class);
}
// Construct using com.google.cloud.automl.v1.BatchPredictInputConfig.newBuilder()
private Builder() {}
private Builder(com.google.protobuf.GeneratedMessageV3.BuilderParent parent) {
super(parent);
}
@java.lang.Override
public Builder clear() {
super.clear();
bitField0_ = 0;
if (gcsSourceBuilder_ != null) {
gcsSourceBuilder_.clear();
}
sourceCase_ = 0;
source_ = null;
return this;
}
@java.lang.Override
public com.google.protobuf.Descriptors.Descriptor getDescriptorForType() {
return com.google.cloud.automl.v1.Io
.internal_static_google_cloud_automl_v1_BatchPredictInputConfig_descriptor;
}
@java.lang.Override
public com.google.cloud.automl.v1.BatchPredictInputConfig getDefaultInstanceForType() {
return com.google.cloud.automl.v1.BatchPredictInputConfig.getDefaultInstance();
}
@java.lang.Override
public com.google.cloud.automl.v1.BatchPredictInputConfig build() {
com.google.cloud.automl.v1.BatchPredictInputConfig result = buildPartial();
if (!result.isInitialized()) {
throw newUninitializedMessageException(result);
}
return result;
}
@java.lang.Override
public com.google.cloud.automl.v1.BatchPredictInputConfig buildPartial() {
com.google.cloud.automl.v1.BatchPredictInputConfig result =
new com.google.cloud.automl.v1.BatchPredictInputConfig(this);
if (bitField0_ != 0) {
buildPartial0(result);
}
buildPartialOneofs(result);
onBuilt();
return result;
}
private void buildPartial0(com.google.cloud.automl.v1.BatchPredictInputConfig result) {
int from_bitField0_ = bitField0_;
}
private void buildPartialOneofs(com.google.cloud.automl.v1.BatchPredictInputConfig result) {
result.sourceCase_ = sourceCase_;
result.source_ = this.source_;
if (sourceCase_ == 1 && gcsSourceBuilder_ != null) {
result.source_ = gcsSourceBuilder_.build();
}
}
@java.lang.Override
public Builder clone() {
return super.clone();
}
@java.lang.Override
public Builder setField(
com.google.protobuf.Descriptors.FieldDescriptor field, java.lang.Object value) {
return super.setField(field, value);
}
@java.lang.Override
public Builder clearField(com.google.protobuf.Descriptors.FieldDescriptor field) {
return super.clearField(field);
}
@java.lang.Override
public Builder clearOneof(com.google.protobuf.Descriptors.OneofDescriptor oneof) {
return super.clearOneof(oneof);
}
@java.lang.Override
public Builder setRepeatedField(
com.google.protobuf.Descriptors.FieldDescriptor field, int index, java.lang.Object value) {
return super.setRepeatedField(field, index, value);
}
@java.lang.Override
public Builder addRepeatedField(
com.google.protobuf.Descriptors.FieldDescriptor field, java.lang.Object value) {
return super.addRepeatedField(field, value);
}
@java.lang.Override
public Builder mergeFrom(com.google.protobuf.Message other) {
if (other instanceof com.google.cloud.automl.v1.BatchPredictInputConfig) {
return mergeFrom((com.google.cloud.automl.v1.BatchPredictInputConfig) other);
} else {
super.mergeFrom(other);
return this;
}
}
public Builder mergeFrom(com.google.cloud.automl.v1.BatchPredictInputConfig other) {
if (other == com.google.cloud.automl.v1.BatchPredictInputConfig.getDefaultInstance())
return this;
switch (other.getSourceCase()) {
case GCS_SOURCE:
{
mergeGcsSource(other.getGcsSource());
break;
}
case SOURCE_NOT_SET:
{
break;
}
}
this.mergeUnknownFields(other.getUnknownFields());
onChanged();
return this;
}
@java.lang.Override
public final boolean isInitialized() {
return true;
}
@java.lang.Override
public Builder mergeFrom(
com.google.protobuf.CodedInputStream input,
com.google.protobuf.ExtensionRegistryLite extensionRegistry)
throws java.io.IOException {
if (extensionRegistry == null) {
throw new java.lang.NullPointerException();
}
try {
boolean done = false;
while (!done) {
int tag = input.readTag();
switch (tag) {
case 0:
done = true;
break;
case 10:
{
input.readMessage(getGcsSourceFieldBuilder().getBuilder(), extensionRegistry);
sourceCase_ = 1;
break;
} // case 10
default:
{
if (!super.parseUnknownField(input, extensionRegistry, tag)) {
done = true; // was an endgroup tag
}
break;
} // default:
} // switch (tag)
} // while (!done)
} catch (com.google.protobuf.InvalidProtocolBufferException e) {
throw e.unwrapIOException();
} finally {
onChanged();
} // finally
return this;
}
private int sourceCase_ = 0;
private java.lang.Object source_;
public SourceCase getSourceCase() {
return SourceCase.forNumber(sourceCase_);
}
public Builder clearSource() {
sourceCase_ = 0;
source_ = null;
onChanged();
return this;
}
private int bitField0_;
private com.google.protobuf.SingleFieldBuilderV3<
com.google.cloud.automl.v1.GcsSource,
com.google.cloud.automl.v1.GcsSource.Builder,
com.google.cloud.automl.v1.GcsSourceOrBuilder>
gcsSourceBuilder_;
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*
* @return Whether the gcsSource field is set.
*/
@java.lang.Override
public boolean hasGcsSource() {
return sourceCase_ == 1;
}
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*
* @return The gcsSource.
*/
@java.lang.Override
public com.google.cloud.automl.v1.GcsSource getGcsSource() {
if (gcsSourceBuilder_ == null) {
if (sourceCase_ == 1) {
return (com.google.cloud.automl.v1.GcsSource) source_;
}
return com.google.cloud.automl.v1.GcsSource.getDefaultInstance();
} else {
if (sourceCase_ == 1) {
return gcsSourceBuilder_.getMessage();
}
return com.google.cloud.automl.v1.GcsSource.getDefaultInstance();
}
}
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*/
public Builder setGcsSource(com.google.cloud.automl.v1.GcsSource value) {
if (gcsSourceBuilder_ == null) {
if (value == null) {
throw new NullPointerException();
}
source_ = value;
onChanged();
} else {
gcsSourceBuilder_.setMessage(value);
}
sourceCase_ = 1;
return this;
}
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*/
public Builder setGcsSource(com.google.cloud.automl.v1.GcsSource.Builder builderForValue) {
if (gcsSourceBuilder_ == null) {
source_ = builderForValue.build();
onChanged();
} else {
gcsSourceBuilder_.setMessage(builderForValue.build());
}
sourceCase_ = 1;
return this;
}
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*/
public Builder mergeGcsSource(com.google.cloud.automl.v1.GcsSource value) {
if (gcsSourceBuilder_ == null) {
if (sourceCase_ == 1
&& source_ != com.google.cloud.automl.v1.GcsSource.getDefaultInstance()) {
source_ =
com.google.cloud.automl.v1.GcsSource.newBuilder(
(com.google.cloud.automl.v1.GcsSource) source_)
.mergeFrom(value)
.buildPartial();
} else {
source_ = value;
}
onChanged();
} else {
if (sourceCase_ == 1) {
gcsSourceBuilder_.mergeFrom(value);
} else {
gcsSourceBuilder_.setMessage(value);
}
}
sourceCase_ = 1;
return this;
}
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*/
public Builder clearGcsSource() {
if (gcsSourceBuilder_ == null) {
if (sourceCase_ == 1) {
sourceCase_ = 0;
source_ = null;
onChanged();
}
} else {
if (sourceCase_ == 1) {
sourceCase_ = 0;
source_ = null;
}
gcsSourceBuilder_.clear();
}
return this;
}
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*/
public com.google.cloud.automl.v1.GcsSource.Builder getGcsSourceBuilder() {
return getGcsSourceFieldBuilder().getBuilder();
}
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*/
@java.lang.Override
public com.google.cloud.automl.v1.GcsSourceOrBuilder getGcsSourceOrBuilder() {
if ((sourceCase_ == 1) && (gcsSourceBuilder_ != null)) {
return gcsSourceBuilder_.getMessageOrBuilder();
} else {
if (sourceCase_ == 1) {
return (com.google.cloud.automl.v1.GcsSource) source_;
}
return com.google.cloud.automl.v1.GcsSource.getDefaultInstance();
}
}
/**
*
*
*
* Required. The Google Cloud Storage location for the input content.
*
*
*
* .google.cloud.automl.v1.GcsSource gcs_source = 1 [(.google.api.field_behavior) = REQUIRED];
*
*/
private com.google.protobuf.SingleFieldBuilderV3<
com.google.cloud.automl.v1.GcsSource,
com.google.cloud.automl.v1.GcsSource.Builder,
com.google.cloud.automl.v1.GcsSourceOrBuilder>
getGcsSourceFieldBuilder() {
if (gcsSourceBuilder_ == null) {
if (!(sourceCase_ == 1)) {
source_ = com.google.cloud.automl.v1.GcsSource.getDefaultInstance();
}
gcsSourceBuilder_ =
new com.google.protobuf.SingleFieldBuilderV3<
com.google.cloud.automl.v1.GcsSource,
com.google.cloud.automl.v1.GcsSource.Builder,
com.google.cloud.automl.v1.GcsSourceOrBuilder>(
(com.google.cloud.automl.v1.GcsSource) source_, getParentForChildren(), isClean());
source_ = null;
}
sourceCase_ = 1;
onChanged();
return gcsSourceBuilder_;
}
@java.lang.Override
public final Builder setUnknownFields(final com.google.protobuf.UnknownFieldSet unknownFields) {
return super.setUnknownFields(unknownFields);
}
@java.lang.Override
public final Builder mergeUnknownFields(
final com.google.protobuf.UnknownFieldSet unknownFields) {
return super.mergeUnknownFields(unknownFields);
}
// @@protoc_insertion_point(builder_scope:google.cloud.automl.v1.BatchPredictInputConfig)
}
// @@protoc_insertion_point(class_scope:google.cloud.automl.v1.BatchPredictInputConfig)
private static final com.google.cloud.automl.v1.BatchPredictInputConfig DEFAULT_INSTANCE;
static {
DEFAULT_INSTANCE = new com.google.cloud.automl.v1.BatchPredictInputConfig();
}
public static com.google.cloud.automl.v1.BatchPredictInputConfig getDefaultInstance() {
return DEFAULT_INSTANCE;
}
private static final com.google.protobuf.Parser PARSER =
new com.google.protobuf.AbstractParser() {
@java.lang.Override
public BatchPredictInputConfig parsePartialFrom(
com.google.protobuf.CodedInputStream input,
com.google.protobuf.ExtensionRegistryLite extensionRegistry)
throws com.google.protobuf.InvalidProtocolBufferException {
Builder builder = newBuilder();
try {
builder.mergeFrom(input, extensionRegistry);
} catch (com.google.protobuf.InvalidProtocolBufferException e) {
throw e.setUnfinishedMessage(builder.buildPartial());
} catch (com.google.protobuf.UninitializedMessageException e) {
throw e.asInvalidProtocolBufferException().setUnfinishedMessage(builder.buildPartial());
} catch (java.io.IOException e) {
throw new com.google.protobuf.InvalidProtocolBufferException(e)
.setUnfinishedMessage(builder.buildPartial());
}
return builder.buildPartial();
}
};
public static com.google.protobuf.Parser parser() {
return PARSER;
}
@java.lang.Override
public com.google.protobuf.Parser getParserForType() {
return PARSER;
}
@java.lang.Override
public com.google.cloud.automl.v1.BatchPredictInputConfig getDefaultInstanceForType() {
return DEFAULT_INSTANCE;
}
}