Document splitters behavior

  import 
  
 com.google.cloud.documentai.v1beta3.Document 
 ; 
 import 
  
 com.google.cloud.documentai.v1beta3.DocumentProcessorServiceClient 
 ; 
 import 
  
 com.google.cloud.documentai.v1beta3.DocumentProcessorServiceSettings 
 ; 
 import 
  
 com.google.cloud.documentai.v1beta3.ProcessRequest 
 ; 
 import 
  
 com.google.cloud.documentai.v1beta3.ProcessResponse 
 ; 
 import 
  
 com.google.cloud.documentai.v1beta3.RawDocument 
 ; 
 import 
  
 com.google.protobuf. ByteString 
 
 ; 
 import 
  
 java.io.IOException 
 ; 
 import 
  
 java.nio.file.Files 
 ; 
 import 
  
 java.nio.file.Paths 
 ; 
 import 
  
 java.util.List 
 ; 
 import 
  
 java.util.concurrent.ExecutionException 
 ; 
 import 
  
 java.util.concurrent.TimeoutException 
 ; 
 public 
  
 class 
 ProcessSplitterDocument 
  
 { 
  
 public 
  
 static 
  
 void 
  
 processSplitterDocument 
 () 
  
 throws 
  
 IOException 
 , 
  
 InterruptedException 
 , 
  
 ExecutionException 
 , 
  
 TimeoutException 
  
 { 
  
 // TODO(developer): Replace these variables before running the sample. 
  
 String 
  
 projectId 
  
 = 
  
 "your-project-id" 
 ; 
  
 String 
  
 location 
  
 = 
  
 "your-project-location" 
 ; 
  
 // Format is "us" or "eu". 
  
 String 
  
 processerId 
  
 = 
  
 "your-processor-id" 
 ; 
  
 String 
  
 filePath 
  
 = 
  
 "path/to/input/file.pdf" 
 ; 
  
 processSplitterDocument 
 ( 
 projectId 
 , 
  
 location 
 , 
  
 processerId 
 , 
  
 filePath 
 ); 
  
 } 
  
 public 
  
 static 
  
 void 
  
 processSplitterDocument 
 ( 
  
 String 
  
 projectId 
 , 
  
 String 
  
 location 
 , 
  
 String 
  
 processorId 
 , 
  
 String 
  
 filePath 
 ) 
  
 throws 
  
 IOException 
 , 
  
 InterruptedException 
 , 
  
 ExecutionException 
 , 
  
 TimeoutException 
  
 { 
  
 // Initialize client that will be used to send requests. This client only needs 
  
 // to be created 
  
 // once, and can be reused for multiple requests. After completing all of your 
  
 // requests, call 
  
 // the "close" method on the client to safely clean up any remaining background 
  
 // resources. 
  
 String 
  
 endpoint 
  
 = 
  
 String 
 . 
 format 
 ( 
 "%s-documentai.googleapis.com:443" 
 , 
  
 location 
 ); 
  
 DocumentProcessorServiceSettings 
  
 settings 
  
 = 
  
 DocumentProcessorServiceSettings 
 . 
 newBuilder 
 (). 
 setEndpoint 
 ( 
 endpoint 
 ). 
 build 
 (); 
  
 try 
  
 ( 
 DocumentProcessorServiceClient 
  
 client 
  
 = 
  
 DocumentProcessorServiceClient 
 . 
 create 
 ( 
 settings 
 )) 
  
 { 
  
 // The full resource name of the processor, e.g.: 
  
 // projects/project-id/locations/location/processor/processor-id 
  
 // You must create new processors in the Cloud Console first 
  
 String 
  
 name 
  
 = 
  
 String 
 . 
 format 
 ( 
 "projects/%s/locations/%s/processors/%s" 
 , 
  
 projectId 
 , 
  
 location 
 , 
  
 processorId 
 ); 
  
 // Read the file. 
  
 byte 
 [] 
  
 imageFileData 
  
 = 
  
 Files 
 . 
 readAllBytes 
 ( 
 Paths 
 . 
 get 
 ( 
 filePath 
 )); 
  
 // Convert the image data to a Buffer and base64 encode it. 
  
  ByteString 
 
  
 content 
  
 = 
  
  ByteString 
 
 . 
  copyFrom 
 
 ( 
 imageFileData 
 ); 
  
 RawDocument 
  
 document 
  
 = 
  
 RawDocument 
 . 
 newBuilder 
 (). 
 setContent 
 ( 
 content 
 ). 
 setMimeType 
 ( 
 "application/pdf" 
 ). 
 build 
 (); 
  
 // Configure the process request. 
  
 ProcessRequest 
  
 request 
  
 = 
  
 ProcessRequest 
 . 
 newBuilder 
 (). 
 setName 
 ( 
 name 
 ). 
 setRawDocument 
 ( 
 document 
 ). 
 build 
 (); 
  
 // Recognizes text entities in the PDF document 
  
 ProcessResponse 
  
 result 
  
 = 
  
 client 
 . 
 processDocument 
 ( 
 request 
 ); 
  
 Document 
  
 documentResponse 
  
 = 
  
 result 
 . 
 getDocument 
 (); 
  
 System 
 . 
 out 
 . 
 println 
 ( 
 "Document processing complete." 
 ); 
  
 // Read the splitter output from the document splitter processor: 
  
 // https://cloud.google.com/document-ai/docs/processors-list#processor_doc-splitter 
  
 // This processor only provides text for the document and information on how 
  
 // to split the document on logical boundaries. To identify and extract text, 
  
 // form elements, and entities please see other processors like the OCR, form, 
  
 // and specalized processors. 
  
 List<Document 
 . 
 Entity 
>  
 entities 
  
 = 
  
 documentResponse 
 . 
 getEntitiesList 
 (); 
  
 System 
 . 
 out 
 . 
 printf 
 ( 
 "Found %d subdocuments:\n" 
 , 
  
 entities 
 . 
 size 
 ()); 
  
 for 
  
 ( 
 Document 
 . 
 Entity 
  
 entity 
  
 : 
  
 entities 
 ) 
  
 { 
  
 float 
  
 entityConfidence 
  
 = 
  
 entity 
 . 
 getConfidence 
 (); 
  
 String 
  
 pagesRangeText 
  
 = 
  
 pageRefsToString 
 ( 
 entity 
 . 
 getPageAnchor 
 (). 
 getPageRefsList 
 ()); 
  
 String 
  
 subdocumentType 
  
 = 
  
 entity 
 . 
 getType 
 (); 
  
 if 
  
 ( 
 subdocumentType 
 . 
 isEmpty 
 ()) 
  
 { 
  
 System 
 . 
 out 
 . 
 printf 
 ( 
  
 "%.2f%% confident that %s a subdocument.\n" 
 , 
  
 entityConfidence 
  
 * 
  
 100 
 , 
  
 pagesRangeText 
 ); 
  
 } 
  
 else 
  
 { 
  
 System 
 . 
 out 
 . 
 printf 
 ( 
  
 "%.2f%% confident that %s a '%s' subdocument.\n" 
 , 
  
 entityConfidence 
  
 * 
  
 100 
 , 
  
 pagesRangeText 
 , 
  
 subdocumentType 
 ); 
  
 } 
  
 } 
  
 } 
  
 } 
  
 // Converts page reference(s) to a string describing the page or page range. 
  
 private 
  
 static 
  
 String 
  
 pageRefsToString 
 ( 
 List<Document 
 . 
 PageAnchor 
 . 
 PageRef 
>  
 pageRefs 
 ) 
  
 { 
  
 if 
  
 ( 
 pageRefs 
 . 
 size 
 () 
  
 == 
  
 1 
 ) 
  
 { 
  
 return 
  
 String 
 . 
 format 
 ( 
 "page %d is" 
 , 
  
 pageRefs 
 . 
 get 
 ( 
 0 
 ). 
 getPage 
 () 
  
 + 
  
 1 
 ); 
  
 } 
  
 else 
  
 { 
  
 long 
  
 start 
  
 = 
  
 pageRefs 
 . 
 get 
 ( 
 0 
 ). 
 getPage 
 () 
  
 + 
  
 1 
 ; 
  
 long 
  
 end 
  
 = 
  
 pageRefs 
 . 
 get 
 ( 
 1 
 ). 
 getPage 
 () 
  
 + 
  
 1 
 ; 
  
 return 
  
 String 
 . 
 format 
 ( 
 "pages %d to %d are" 
 , 
  
 start 
 , 
  
 end 
 ); 
  
 } 
  
 } 
 } 
 

  /** 
 * TODO(developer): Uncomment these variables before running the sample. 
 */ 
 // const projectId = 'YOUR_PROJECT_ID'; 
 // const location = 'YOUR_PROJECT_LOCATION'; // Format is 'us' or 'eu' 
 // const processorId = 'YOUR_PROCESSOR_ID'; // Create processor in Cloud Console 
 // const filePath = '/path/to/local/pdf'; 
 const 
  
 { 
 DocumentProcessorServiceClient 
 } 
  
 = 
  
 require 
 ( 
 ' @google-cloud/documentai 
' 
 ). 
 v1beta3 
 ; 
 // Instantiates a client 
 const 
  
 client 
  
 = 
  
 new 
  
  DocumentProcessorServiceClient 
 
 (); 
 async 
  
 function 
  
 processDocument 
 () 
  
 { 
  
 // The full resource name of the processor, e.g.: 
  
 // projects/project-id/locations/location/processor/processor-id 
  
 // You must create new processors in the Cloud Console first 
  
 const 
  
 name 
  
 = 
  
 `projects/ 
 ${ 
 projectId 
 } 
 /locations/ 
 ${ 
 location 
 } 
 /processors/ 
 ${ 
 processorId 
 } 
 ` 
 ; 
  
 // Read the file into memory. 
  
 const 
  
 fs 
  
 = 
  
 require 
 ( 
 'fs' 
 ). 
 promises 
 ; 
  
 const 
  
 imageFile 
  
 = 
  
 await 
  
 fs 
 . 
 readFile 
 ( 
 filePath 
 ); 
  
 // Convert the image data to a Buffer and base64 encode it. 
  
 const 
  
 encodedImage 
  
 = 
  
 Buffer 
 . 
 from 
 ( 
 imageFile 
 ). 
 toString 
 ( 
 'base64' 
 ); 
  
 const 
  
 request 
  
 = 
  
 { 
  
 name 
 , 
  
 rawDocument 
 : 
  
 { 
  
 content 
 : 
  
 encodedImage 
 , 
  
 mimeType 
 : 
  
 'application/pdf' 
 , 
  
 }, 
  
 }; 
  
 // Recognizes text entities in the PDF document 
  
 const 
  
 [ 
 result 
 ] 
  
 = 
  
 await 
  
 client 
 . 
 processDocument 
 ( 
 request 
 ); 
  
 console 
 . 
 log 
 ( 
 'Document processing complete.' 
 ); 
  
 // Read fields specificly from the specalized US drivers license processor: 
  
 // https://cloud.google.com/document-ai/docs/processors-list#processor_us-driver-license-parser 
  
 // retriving data from other specalized processors follow a similar pattern. 
  
 // For a complete list of processors see: 
  
 // https://cloud.google.com/document-ai/docs/processors-list 
  
 // 
  
 // OCR and other data is also present in the quality processor's response. 
  
 // Please see the OCR and other samples for how to parse other data in the 
  
 // response. 
  
 const 
  
 { 
 document 
 } 
  
 = 
  
 result 
 ; 
  
 console 
 . 
 log 
 ( 
 `Found 
 ${ 
 document 
 . 
 entities 
 . 
 length 
 } 
 subdocuments:` 
 ); 
  
 for 
  
 ( 
 const 
  
 entity 
  
 of 
  
 document 
 . 
 entities 
 ) 
  
 { 
  
 const 
  
 conf 
  
 = 
  
 entity 
 . 
 confidence 
  
 * 
  
 100 
 ; 
  
 const 
  
 pagesRange 
  
 = 
  
 pageRefsToRange 
 ( 
 entity 
 . 
 pageAnchor 
 . 
 pageRefs 
 ); 
  
 if 
  
 ( 
 entity 
 . 
 type 
  
 !== 
  
 '' 
 ) 
  
 { 
  
 console 
 . 
 log 
 ( 
  
 ` 
 ${ 
 conf 
 . 
 toFixed 
 ( 
 2 
 ) 
 } 
 % confident that 
 ${ 
 pagesRange 
 } 
 a " 
 ${ 
  
 entity 
 . 
 type 
  
 } 
 " subdocument.` 
  
 ); 
  
 } 
  
 else 
  
 { 
  
 console 
 . 
 log 
 ( 
  
 ` 
 ${ 
 conf 
 . 
 toFixed 
 ( 
 2 
 ) 
 } 
 % confident that 
 ${ 
 pagesRange 
 } 
 a subdocument.` 
  
 ); 
  
 } 
  
 } 
 } 
 // Converts a page ref to a string describing the page or page range. 
 const 
  
 pageRefsToRange 
  
 = 
  
 pageRefs 
  
 = 
>  
 { 
  
 if 
  
 ( 
 pageRefs 
 . 
 length 
  
 === 
  
 1 
 ) 
  
 { 
  
 const 
  
 num 
  
 = 
  
 parseInt 
 ( 
 pageRefs 
 [ 
 0 
 ]. 
 page 
 ) 
  
 + 
  
 1 
  
 || 
  
 1 
 ; 
  
 return 
  
 `page 
 ${ 
 num 
 } 
 is` 
 ; 
  
 } 
  
 else 
  
 { 
  
 const 
  
 start 
  
 = 
  
 parseInt 
 ( 
 pageRefs 
 [ 
 0 
 ]. 
 page 
 ) 
  
 + 
  
 1 
  
 || 
  
 1 
 ; 
  
 const 
  
 end 
  
 = 
  
 parseInt 
 ( 
 pageRefs 
 [ 
 1 
 ]. 
 page 
 ) 
  
 + 
  
 1 
 ; 
  
 return 
  
 `pages 
 ${ 
 start 
 } 
 to 
 ${ 
 end 
 } 
 are` 
 ; 
  
 } 
 }; 
 

  from 
  
 typing 
  
 import 
 Optional 
 , 
 Sequence 
 from 
  
 google.api_core.client_options 
  
 import 
 ClientOptions 
 from 
  
 google.cloud 
  
 import 
 documentai 
 # TODO(developer): Uncomment these variables before running the sample. 
 # project_id = "YOUR_PROJECT_ID" 
 # location = "YOUR_PROCESSOR_LOCATION" # Format is "us" or "eu" 
 # processor_id = "YOUR_PROCESSOR_ID" # Create processor before running sample 
 # processor_version = "rc" # Refer to https://cloud.google.com/document-ai/docs/manage-processor-versions for more information 
 # file_path = "/path/to/local/pdf" 
 # mime_type = "application/pdf" # Refer to https://cloud.google.com/document-ai/docs/file-types for supported file types 
 def 
  
 process_document_splitter_sample 
 ( 
 project_id 
 : 
 str 
 , 
 location 
 : 
 str 
 , 
 processor_id 
 : 
 str 
 , 
 processor_version 
 : 
 str 
 , 
 file_path 
 : 
 str 
 , 
 mime_type 
 : 
 str 
 , 
 ) 
 - 
> None 
 : 
 # Online processing request to Document AI 
 document 
 = 
 process_document 
 ( 
 project_id 
 , 
 location 
 , 
 processor_id 
 , 
 processor_version 
 , 
 file_path 
 , 
 mime_type 
 ) 
 # Read the splitter output from a document splitter/classifier processor: 
 # e.g. https://cloud.google.com/document-ai/docs/processors-list#processor_procurement-document-splitter 
 # This processor only provides text for the document and information on how 
 # to split the document on logical boundaries. To identify and extract text, 
 # form elements, and entities please see other processors like the OCR, form, 
 # and specalized processors. 
 print 
 ( 
 f 
 "Found 
 { 
 len 
 ( 
  document 
 
 . 
 entities 
 ) 
 } 
 subdocuments:" 
 ) 
 for 
 entity 
 in 
  document 
 
 . 
 entities 
 : 
 conf_percent 
 = 
 f 
 " 
 { 
  entity 
 
 . 
 confidence 
 : 
 .1% 
 } 
 " 
 pages_range 
 = 
 page_refs_to_string 
 ( 
  entity 
 
 . 
 page_anchor 
 . 
 page_refs 
 ) 
 # Print subdocument type information, if available 
 if 
  entity 
 
 . 
 type_ 
 : 
 print 
 ( 
 f 
 " 
 { 
 conf_percent 
 } 
 confident that 
 { 
 pages_range 
 } 
 a ' 
 { 
  entity 
 
 . 
 type_ 
 } 
 ' subdocument." 
 ) 
 else 
 : 
 print 
 ( 
 f 
 " 
 { 
 conf_percent 
 } 
 confident that 
 { 
 pages_range 
 } 
 a subdocument." 
 ) 
 def 
  
 page_refs_to_string 
 ( 
 page_refs 
 : 
 Sequence 
 [ 
 documentai 
 . 
 Document 
 . 
  PageAnchor 
 
 . 
  PageRef 
 
 ], 
 ) 
 - 
> str 
 : 
  
 """Converts a page ref to a string describing the page or page range.""" 
 pages 
 = 
 [ 
 str 
 ( 
 int 
 ( 
 page_ref 
 . 
  page 
 
 ) 
 + 
 1 
 ) 
 for 
 page_ref 
 in 
 page_refs 
 ] 
 if 
 len 
 ( 
 pages 
 ) 
 == 
 1 
 : 
 return 
 f 
 "page 
 { 
 pages 
 [ 
 0 
 ] 
 } 
 is" 
 else 
 : 
 return 
 f 
 "pages 
 { 
 ', ' 
 . 
 join 
 ( 
 pages 
 ) 
 } 
 are" 
 def 
  
 process_document 
 ( 
 project_id 
 : 
 str 
 , 
 location 
 : 
 str 
 , 
 processor_id 
 : 
 str 
 , 
 processor_version 
 : 
 str 
 , 
 file_path 
 : 
 str 
 , 
 mime_type 
 : 
 str 
 , 
 process_options 
 : 
 Optional 
 [ 
 documentai 
 . 
  ProcessOptions 
 
 ] 
 = 
 None 
 , 
 ) 
 - 
> documentai 
 . 
 Document 
 : 
 # You must set the `api_endpoint` if you use a location other than "us". 
 client 
 = 
 documentai 
 . 
  DocumentProcessorServiceClient 
 
 ( 
 client_options 
 = 
 ClientOptions 
 ( 
 api_endpoint 
 = 
 f 
 " 
 { 
 location 
 } 
 -documentai.googleapis.com" 
 ) 
 ) 
 # The full resource name of the processor version, e.g.: 
 # `projects/{project_id}/locations/{location}/processors/{processor_id}/processorVersions/{processor_version_id}` 
 # You must create a processor before running this sample. 
 name 
 = 
 client 
 . 
  processor_version_path 
 
 ( 
 project_id 
 , 
 location 
 , 
 processor_id 
 , 
 processor_version 
 ) 
 # Read the file into memory 
 with 
 open 
 ( 
 file_path 
 , 
 "rb" 
 ) 
 as 
 image 
 : 
 image_content 
 = 
 image 
 . 
 read 
 () 
 # Configure the process request 
 request 
 = 
 documentai 
 . 
  ProcessRequest 
 
 ( 
 name 
 = 
 name 
 , 
 raw_document 
 = 
 documentai 
 . 
  RawDocument 
 
 ( 
 content 
 = 
 image_content 
 , 
 mime_type 
 = 
 mime_type 
 ), 
 # Only supported for Document OCR processor 
 process_options 
 = 
 process_options 
 , 
 ) 
 result 
 = 
 client 
 . 
  process_document 
 
 ( 
 request 
 = 
 request 
 ) 
 # For a full list of `Document` object attributes, reference this page: 
 # https://cloud.google.com/document-ai/docs/reference/rest/v1/Document 
 return 
 result 
 . 
  document