from typing import Optional, Sequence from google.api_core.client_options import ClientOptions from google.cloud import documentai def process_document_ocr_sample( project_id: str, location: str, processor_id: str, processor_version: str, file_path: str, mime_type: str, ) -> None: # Optional: Additional configurations for Document OCR Processor. # For more information: https://cloud.google.com/document-ai/docs/document-ocr process_options = documentai.ProcessOptions( ocr_config=documentai.OcrConfig( enable_native_pdf_parsing=True, enable_image_quality_scores=True, ) ) # Online processing request to Document AI document = process_document( project_id, location, processor_id, processor_version, file_path, mime_type, process_options=process_options, ) text = document.text print(f"Full document text: {text}\n") print(f"There are {len(document.pages)} page(s) in this document.\n") for page in document.pages: print(f"Page {page.page_number}:") print_page_dimensions(page.dimension) print_detected_langauges(page.detected_languages) print_blocks(page.blocks, text) print_paragraphs(page.paragraphs, text) print_lines(page.lines, text) print_tokens(page.tokens, text) if page.image_quality_scores: print_image_quality_scores(page.image_quality_scores) def print_page_dimensions(dimension: documentai.Document.Page.Dimension) -> None: print(f" Width: {str(dimension.width)}") print(f" Height: {str(dimension.height)}") def print_detected_langauges( detected_languages: Sequence[documentai.Document.Page.DetectedLanguage], ) -> None: print(" Detected languages:") for lang in detected_languages: print(f" {lang.language_code} ({lang.confidence:.1%} confidence)") def print_blocks(blocks: Sequence[documentai.Document.Page.Block], text: str) -> None: print(f" {len(blocks)} blocks detected:") first_block_text = layout_to_text(blocks[0].layout, text) print(f" First text block: {repr(first_block_text)}") last_block_text = layout_to_text(blocks[-1].layout, text) print(f" Last text block: {repr(last_block_text)}") def print_paragraphs( paragraphs: Sequence[documentai.Document.Page.Paragraph], text: str ) -> None: print(f" {len(paragraphs)} paragraphs detected:") first_paragraph_text = layout_to_text(paragraphs[0].layout, text) print(f" First paragraph text: {repr(first_paragraph_text)}") last_paragraph_text = layout_to_text(paragraphs[-1].layout, text) print(f" Last paragraph text: {repr(last_paragraph_text)}") def print_lines(lines: Sequence[documentai.Document.Page.Line], text: str) -> None: print(f" {len(lines)} lines detected:") first_line_text = layout_to_text(lines[0].layout, text) print(f" First line text: {repr(first_line_text)}") last_line_text = layout_to_text(lines[-1].layout, text) print(f" Last line text: {repr(last_line_text)}") def print_tokens(tokens: Sequence[documentai.Document.Page.Token], text: str) -> None: print(f" {len(tokens)} tokens detected:") first_token_text = layout_to_text(tokens[0].layout, text) first_token_break_type = tokens[0].detected_break.type_.name print(f" First token text: {repr(first_token_text)}") print(f" First token break type: {repr(first_token_break_type)}") last_token_text = layout_to_text(tokens[-1].layout, text) last_token_break_type = tokens[-1].detected_break.type_.name print(f" Last token text: {repr(last_token_text)}") print(f" Last token break type: {repr(last_token_break_type)}") def print_image_quality_scores( image_quality_scores: documentai.Document.Page.ImageQualityScores, ) -> None: print(f" Quality score: {image_quality_scores.quality_score:.1%}") print(" Detected defects:") for detected_defect in image_quality_scores.detected_defects: print(f" {detected_defect.type_}: {detected_defect.confidence:.1%}") 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 def layout_to_text(layout: documentai.Document.Page.Layout, text: str) -> str: """ Document AI identifies text in different parts of the document by their offsets in the entirety of the document"s text. This function converts offsets to a string. """ # If a text segment spans several lines, it will # be stored in different text segments. return "".join( text[int(segment.start_index) : int(segment.end_index)] for segment in layout.text_anchor.text_segments ) # TODO(developer): Edit 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 = "pretrained-ocr-v2.0-2023-06-02" file_path = "DeclarationOfIndependence-Cursive.pdf" mime_type = "application/pdf" # Refer to https://cloud.google.com/document-ai/docs/file-types for supported file types process_document_ocr_sample( project_id=project_id, location=location, processor_id=processor_id, processor_version=processor_version, file_path=file_path, mime_type=mime_type, )