def __extract_all_pages()

in sources/lambda/async/text_extractor.py [0:0]

• 22 lines of code
• 6 McCabe index (conditional complexity)

    def __extract_all_pages(self, jobId, textract_result, pages, page_numbers):
        """ extract page content: build the pages array,
        recurse if response is too big (when NextToken is provided by textract)
        """

        blocks = [x for x in textract_result['Blocks']
                  if x['BlockType'] == "LINE"]
        for block in blocks:
            if block['Page'] not in page_numbers:
                page_numbers.append(block['Page'])
                pages[block['Page']] = {
                    "Number": block['Page'],
                    "Content": block['Text']
                }
            else:
                pages[block['Page']]['Content'] += " " + block['Text']

        nextToken = textract_result.get("NextToken", "")
        if nextToken != '':
            textract_result = textract.get_document_text_detection(
                JobId=jobId,
                NextToken=nextToken
            )
            self.__extract_all_pages(jobId,
                                     textract_result,
                                     pages,
                                     page_numbers)