-
Notifications
You must be signed in to change notification settings - Fork 2.8k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Beta feature : Vision : PDF/TIFF/GIF document feature detection (#1349)
* Beta feature : Vision : PDF/TIFF/GIF document feature detection * Beta feature : Vision : PDF/TIFF/GIF document feature detection : Add AsyncBatchAnnotateImages sample * Update after review comments * Update after review comments
- Loading branch information
1 parent
e30c014
commit a700bbf
Showing
6 changed files
with
413 additions
and
8 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Binary file not shown.
155 changes: 155 additions & 0 deletions
155
vision/beta/cloud-client/src/main/java/com/example/vision/AsyncBatchAnnotateImagesGcs.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,155 @@ | ||
| /* | ||
| * Copyright 2019 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 | ||
| * | ||
| * http://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. | ||
| */ | ||
|
|
||
| package com.example.vision; | ||
|
|
||
| // [START vision_async_batch_annotate_images_beta] | ||
| import com.google.api.core.ApiFuture; | ||
| import com.google.api.gax.paging.Page; | ||
| import com.google.cloud.storage.Blob; | ||
| import com.google.cloud.storage.Bucket; | ||
| import com.google.cloud.storage.Storage; | ||
| import com.google.cloud.storage.Storage.BlobListOption; | ||
| import com.google.cloud.storage.StorageOptions; | ||
| import com.google.cloud.vision.v1p4beta1.AnnotateImageRequest; | ||
| import com.google.cloud.vision.v1p4beta1.AsyncBatchAnnotateImagesRequest; | ||
| import com.google.cloud.vision.v1p4beta1.BatchAnnotateImagesResponse.Builder; | ||
| import com.google.cloud.vision.v1p4beta1.BatchAnnotateImagesResponse; | ||
| import com.google.cloud.vision.v1p4beta1.Feature; | ||
| import com.google.cloud.vision.v1p4beta1.Feature.Type; | ||
| import com.google.cloud.vision.v1p4beta1.GcsDestination; | ||
| import com.google.cloud.vision.v1p4beta1.Image; | ||
| import com.google.cloud.vision.v1p4beta1.ImageAnnotatorClient; | ||
| import com.google.cloud.vision.v1p4beta1.ImageSource; | ||
| import com.google.cloud.vision.v1p4beta1.OutputConfig; | ||
|
|
||
| import com.google.longrunning.Operation; | ||
| import com.google.protobuf.util.JsonFormat; | ||
| import java.util.ArrayList; | ||
| import java.util.List; | ||
| import java.util.concurrent.TimeUnit; | ||
| import java.util.regex.Matcher; | ||
| import java.util.regex.Pattern; | ||
|
|
||
| public class AsyncBatchAnnotateImagesGcs { | ||
|
|
||
| // Performs asynchronous batch annotation of images on Google Cloud Storage | ||
| public static void asyncBatchAnnotateImagesGcs(String gcsSourcePath, String gcsDestinationPath) | ||
| throws Exception { | ||
| // String gcsSourcePath = "gs://YOUR_BUCKET_ID/path_to_your_data"; | ||
| // String gcsDestinationPath = "gs://YOUR_BUCKET_ID/path_to_store_annotation"; | ||
|
|
||
| try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) { | ||
| List<AnnotateImageRequest> requests = new ArrayList<>(); | ||
|
|
||
| ImageSource imgSource = ImageSource.newBuilder().setImageUri(gcsSourcePath).build(); | ||
|
|
||
| Image image = Image.newBuilder().setSource(imgSource).build(); | ||
|
|
||
| // Set the GCS destination path for where to save the results. | ||
| GcsDestination gcsDestination = | ||
| GcsDestination.newBuilder().setUri(gcsDestinationPath).build(); | ||
|
|
||
| // Create the configuration for the output with the batch size. | ||
| // The batch size sets how many pages should be grouped into each json output file. | ||
| OutputConfig outputConfig = | ||
| OutputConfig.newBuilder().setGcsDestination(gcsDestination).setBatchSize(2).build(); | ||
|
|
||
| // Select the Features required by the vision API | ||
| Feature features = | ||
| Feature.newBuilder() | ||
| .setType(Type.LABEL_DETECTION) | ||
| .setType(Type.TEXT_DETECTION) | ||
| .setType(Type.IMAGE_PROPERTIES) | ||
| .build(); | ||
|
|
||
| // Build the request | ||
| AnnotateImageRequest annotateImageRequest = | ||
| AnnotateImageRequest.newBuilder().setImage(image).addFeatures(features).build(); | ||
|
|
||
| requests.add(annotateImageRequest); | ||
| AsyncBatchAnnotateImagesRequest request = | ||
| AsyncBatchAnnotateImagesRequest.newBuilder() | ||
| .addAllRequests(requests) | ||
| .setOutputConfig(outputConfig) | ||
| .build(); | ||
|
|
||
| ApiFuture<Operation> future = client.asyncBatchAnnotateImagesCallable().futureCall(request); | ||
| // Wait for the request to finish. (The result is not used, since the API saves the result to | ||
| // the specified location on GCS.) | ||
| Operation response = future.get(180, TimeUnit.SECONDS); | ||
|
|
||
| System.out.println("Waiting for the operation to finish."); | ||
|
|
||
| // Once the request has completed and the output has been | ||
| // written to GCS, we can list all the output files. | ||
| Storage storage = StorageOptions.getDefaultInstance().getService(); | ||
|
|
||
| // Get the destination location from the gcsDestinationPath | ||
| Pattern pattern = Pattern.compile("gs://([^/]+)/(.+)"); | ||
| Matcher matcher = pattern.matcher(gcsDestinationPath); | ||
|
|
||
| if (matcher.find()) { | ||
| String bucketName = matcher.group(1); | ||
| String prefix = matcher.group(2); | ||
|
|
||
| // Get the list of objects with the given prefix from the GCS bucket | ||
| Bucket bucket = storage.get(bucketName); | ||
| Page<Blob> pageList = bucket.list(BlobListOption.prefix(prefix)); | ||
|
|
||
| Blob firstOutputFile = null; | ||
|
|
||
| // List objects with the given prefix. | ||
| System.out.println("Output files:"); | ||
| for (Blob blob : pageList.iterateAll()) { | ||
| System.out.println(blob.getName()); | ||
|
|
||
| // Process the first output file from GCS. | ||
| // Since we specified batch size = 2, the first response contains | ||
| // the first two image requests | ||
| if (firstOutputFile == null) { | ||
| firstOutputFile = blob; | ||
| } | ||
| } | ||
|
|
||
| // Get the contents of the file and convert the JSON contents to an | ||
| // BatchAnnotateImagesResponse | ||
| // object. If the Blob is small read all its content in one request | ||
| // (Note: the file is a .json file) | ||
| // Storage guide: https://cloud.google.com/storage/docs/downloading-objects | ||
| String jsonContents = new String(firstOutputFile.getContent()); | ||
| Builder builder = BatchAnnotateImagesResponse.newBuilder(); | ||
| JsonFormat.parser().merge(jsonContents, builder); | ||
|
|
||
| // Build the AnnotateFileResponse object | ||
| BatchAnnotateImagesResponse batchAnnotateImagesResponse = builder.build(); | ||
|
|
||
| // Here we print the response for the first image | ||
| // The response contains more information: | ||
| // annotation/pages/blocks/paragraphs/words/symbols/colors | ||
| // including confidence score and bounding boxes | ||
| System.out.format("\nResponse: %s\n", batchAnnotateImagesResponse.getResponses(0)); | ||
|
|
||
| } else { | ||
| System.out.println("No MATCH"); | ||
| } | ||
| } catch (Exception e) { | ||
| System.out.println("Error during asyncBatchAnnotateImagesGcs: \n" + e.toString()); | ||
| } | ||
| } | ||
| } | ||
|
|
||
| // [END vision_async_batch_annotate_images_beta] |
110 changes: 110 additions & 0 deletions
110
vision/beta/cloud-client/src/main/java/com/example/vision/DetectBatchAnnotateFiles.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,110 @@ | ||
| /* | ||
| * Copyright 2019 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 | ||
| * | ||
| * http://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. | ||
| */ | ||
|
|
||
| package com.example.vision; | ||
|
|
||
| // [START vision_batch_annotate_files_beta] | ||
| import com.google.api.core.ApiFuture; | ||
| import com.google.cloud.vision.v1p4beta1.AnnotateFileRequest; | ||
| import com.google.cloud.vision.v1p4beta1.AnnotateFileResponse; | ||
| import com.google.cloud.vision.v1p4beta1.BatchAnnotateFilesRequest; | ||
| import com.google.cloud.vision.v1p4beta1.BatchAnnotateFilesResponse; | ||
| import com.google.cloud.vision.v1p4beta1.Block; | ||
| import com.google.cloud.vision.v1p4beta1.Feature; | ||
| import com.google.cloud.vision.v1p4beta1.Feature.Type; | ||
| import com.google.cloud.vision.v1p4beta1.ImageAnnotatorClient; | ||
| import com.google.cloud.vision.v1p4beta1.InputConfig; | ||
| import com.google.cloud.vision.v1p4beta1.Page; | ||
| import com.google.cloud.vision.v1p4beta1.Paragraph; | ||
| import com.google.cloud.vision.v1p4beta1.Symbol; | ||
| import com.google.cloud.vision.v1p4beta1.TextAnnotation; | ||
| import com.google.cloud.vision.v1p4beta1.Word; | ||
| import com.google.protobuf.ByteString; | ||
|
|
||
| import java.io.FileInputStream; | ||
| import java.util.ArrayList; | ||
| import java.util.Arrays; | ||
| import java.util.List; | ||
|
|
||
| public class DetectBatchAnnotateFiles { | ||
|
|
||
| // Performs document feature detection on a local PDF/TIFF/GIF file. | ||
| public static void detectBatchAnnotateFiles(String filePath) { | ||
| // String filePath = "path/to/your_file"; | ||
|
|
||
| try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) { | ||
| // Annotate the first two pages and the last one (max 5 pages) | ||
| // First page starts at 1, and not 0. Last page is -1. | ||
| List<Integer> pages = Arrays.asList(1, 2, -1); | ||
| ByteString pdfBytes = ByteString.readFrom(new FileInputStream(filePath)); | ||
| Feature feat = Feature.newBuilder().setType(Type.DOCUMENT_TEXT_DETECTION).build(); | ||
| // Other supported mime types : 'image/tiff' or 'image/gif' | ||
| InputConfig inputConfig = | ||
| InputConfig.newBuilder().setMimeType("application/pdf").setContent(pdfBytes).build(); | ||
| AnnotateFileRequest request = | ||
| AnnotateFileRequest.newBuilder() | ||
| .addFeatures(feat) | ||
| .setInputConfig(inputConfig) | ||
| .addAllPages(pages) | ||
| .build(); | ||
| List<AnnotateFileRequest> requests = new ArrayList<>(); | ||
| requests.add(request); | ||
|
|
||
| BatchAnnotateFilesRequest batchAnnotateFilesRequest = | ||
| BatchAnnotateFilesRequest.newBuilder().addAllRequests(requests).build(); | ||
| ApiFuture<BatchAnnotateFilesResponse> future = | ||
| client.batchAnnotateFilesCallable().futureCall(batchAnnotateFilesRequest); | ||
| BatchAnnotateFilesResponse response = future.get(); | ||
|
|
||
| // Getting the first response | ||
| AnnotateFileResponse annotateFileResponse = response.getResponses(0); | ||
|
|
||
| // For full list of available annotations, see http://g.co/cloud/vision/docs | ||
| TextAnnotation textAnnotation = annotateFileResponse.getResponses(0).getFullTextAnnotation(); | ||
| for (Page page : textAnnotation.getPagesList()) { | ||
| String pageText = ""; | ||
| for (Block block : page.getBlocksList()) { | ||
| String blockText = ""; | ||
| for (Paragraph para : block.getParagraphsList()) { | ||
| String paraText = ""; | ||
| for (Word word : para.getWordsList()) { | ||
| String wordText = ""; | ||
| for (Symbol symbol : word.getSymbolsList()) { | ||
| wordText = wordText + symbol.getText(); | ||
| System.out.format( | ||
| "Symbol text: %s (Confidence: %f)\n", symbol.getText(), symbol.getConfidence()); | ||
| } | ||
| System.out.format( | ||
| "Word text: %s (Confidence: %f)\n\n", wordText, word.getConfidence()); | ||
| paraText = String.format("%s %s", paraText, wordText); | ||
| } | ||
| // Output Example using Paragraph: | ||
| System.out.println("\nParagraph: \n" + paraText); | ||
| System.out.format("Paragraph Confidence: %f\n", para.getConfidence()); | ||
| blockText = blockText + paraText; | ||
| } | ||
| pageText = pageText + blockText; | ||
| } | ||
| } | ||
| System.out.println("\nComplete annotation:"); | ||
| System.out.println(textAnnotation.getText()); | ||
|
|
||
| } catch (Exception e) { | ||
| System.out.println("Error during detectPdfText: \n" + e.toString()); | ||
| } | ||
| } | ||
| } | ||
| // [END vision_batch_annotate_files_beta] |
109 changes: 109 additions & 0 deletions
109
vision/beta/cloud-client/src/main/java/com/example/vision/DetectBatchAnnotateFilesGcs.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,109 @@ | ||
| /* | ||
| * Copyright 2019 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 | ||
| * | ||
| * http://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. | ||
| */ | ||
|
|
||
| package com.example.vision; | ||
|
|
||
| // [START vision_batch_annotate_files_gcs_beta] | ||
| import com.google.api.core.ApiFuture; | ||
| import com.google.cloud.vision.v1p4beta1.AnnotateFileRequest; | ||
| import com.google.cloud.vision.v1p4beta1.AnnotateFileResponse; | ||
| import com.google.cloud.vision.v1p4beta1.BatchAnnotateFilesRequest; | ||
| import com.google.cloud.vision.v1p4beta1.BatchAnnotateFilesResponse; | ||
| import com.google.cloud.vision.v1p4beta1.Block; | ||
| import com.google.cloud.vision.v1p4beta1.Feature; | ||
| import com.google.cloud.vision.v1p4beta1.Feature.Type; | ||
| import com.google.cloud.vision.v1p4beta1.GcsSource; | ||
| import com.google.cloud.vision.v1p4beta1.ImageAnnotatorClient; | ||
| import com.google.cloud.vision.v1p4beta1.InputConfig; | ||
| import com.google.cloud.vision.v1p4beta1.Page; | ||
| import com.google.cloud.vision.v1p4beta1.Paragraph; | ||
| import com.google.cloud.vision.v1p4beta1.Symbol; | ||
| import com.google.cloud.vision.v1p4beta1.TextAnnotation; | ||
| import com.google.cloud.vision.v1p4beta1.Word; | ||
|
|
||
| import java.util.ArrayList; | ||
| import java.util.Arrays; | ||
| import java.util.List; | ||
|
|
||
| public class DetectBatchAnnotateFilesGcs { | ||
|
|
||
| // Performs document feature detection on a remote PDF/TIFF/GIF file on Google Cloud Storage. | ||
| public static void detectBatchAnnotateFilesGcs(String gcsPath) { | ||
| // String gcsPath = "gs://Your_BUCKET_ID/path_to_your_data"; | ||
|
|
||
| try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) { | ||
| // Annotate the first two pages and the last one (max 5 pages) | ||
| // First page starts at 1, and not 0. Last page is -1. | ||
| List<Integer> pages = Arrays.asList(1, 2, -1); | ||
| GcsSource gcsSource = GcsSource.newBuilder().setUri(gcsPath).build(); | ||
| Feature feat = Feature.newBuilder().setType(Type.DOCUMENT_TEXT_DETECTION).build(); | ||
| //Other supported mime types : 'image/tiff' or 'image/gif' | ||
| InputConfig inputConfig = | ||
| InputConfig.newBuilder().setMimeType("application/pdf").setGcsSource(gcsSource).build(); | ||
| AnnotateFileRequest request = | ||
| AnnotateFileRequest.newBuilder() | ||
| .addFeatures(feat) | ||
| .setInputConfig(inputConfig) | ||
| .addAllPages(pages) | ||
| .build(); | ||
| List<AnnotateFileRequest> requests = new ArrayList<>(); | ||
| requests.add(request); | ||
|
|
||
| BatchAnnotateFilesRequest batchAnnotateFilesRequest = | ||
| BatchAnnotateFilesRequest.newBuilder().addAllRequests(requests).build(); | ||
| ApiFuture<BatchAnnotateFilesResponse> future = | ||
| client.batchAnnotateFilesCallable().futureCall(batchAnnotateFilesRequest); | ||
| BatchAnnotateFilesResponse response = future.get(); | ||
|
|
||
| // Getting the first response | ||
| AnnotateFileResponse annotateFileResponse = response.getResponses(0); | ||
|
|
||
| // For full list of available annotations, see http://g.co/cloud/vision/docs | ||
| TextAnnotation textAnnotation = annotateFileResponse.getResponses(0).getFullTextAnnotation(); | ||
| for (Page page : textAnnotation.getPagesList()) { | ||
| String pageText = ""; | ||
| for (Block block : page.getBlocksList()) { | ||
| String blockText = ""; | ||
| for (Paragraph para : block.getParagraphsList()) { | ||
| String paraText = ""; | ||
| for (Word word : para.getWordsList()) { | ||
| String wordText = ""; | ||
| for (Symbol symbol : word.getSymbolsList()) { | ||
| wordText = wordText + symbol.getText(); | ||
| System.out.format( | ||
| "Symbol text: %s (Confidence: %f)\n", symbol.getText(), symbol.getConfidence()); | ||
| } | ||
| System.out.format( | ||
| "Word text: %s (Confidence: %f)\n\n", wordText, word.getConfidence()); | ||
| paraText = String.format("%s %s", paraText, wordText); | ||
| } | ||
| // Output Example using Paragraph: | ||
| System.out.println("\nParagraph: \n" + paraText); | ||
| System.out.format("Paragraph Confidence: %f\n", para.getConfidence()); | ||
| blockText = blockText + paraText; | ||
| } | ||
| pageText = pageText + blockText; | ||
| } | ||
| } | ||
| System.out.println("\nComplete annotation:"); | ||
| System.out.println(textAnnotation.getText()); | ||
|
|
||
| } catch (Exception e) { | ||
| System.out.println("Error during detectPdfText: \n" + e.toString()); | ||
| } | ||
| } | ||
| } | ||
| // [END vision_batch_annotate_files_gcs_beta] |
Oops, something went wrong.
a700bbfThere was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi Nirupa Kumar,
I understand you have done changes to read local pdf files. This is really great. However these are in old vision repo (https://github.com/GoogleCloudPlatform/java-docs-samples/tree/master/vision/beta/.)
Now Google has recommended below repo
(https://github.com/GoogleCloudPlatform/java-docs-samples/blob/master/vision/cloud-client/src/main/java/com/example/vision/Detect.java)
Do you have any plans to do same changes in new Repo as going forward it will be used?