How to Build an Android Document Scanner App with OCR

    // Add callback to handle returned image from scanner
    val scannerLauncher = registerForActivityResult(ScannerContract()) { uri ->
        if (uri != null) {
            // Obtain the bitmap and save as a local image file
            var bitmap: Bitmap? = null
            bitmap = MediaStore.Images.Media.getBitmap(contentResolver, uri)
            contentResolver.delete(uri!!, null, null)

            // Save bitmap to local cache as image then upload for processing
            val localJpeg = Utils.saveBitmapAsJpeg(bitmap)

            // Process image using ML Kit
            processOCR(imgWidth, imgHeight, image, localJpeg)
        }
    }

    ...

    // Launch the scanner activity
    scannerLauncher.launch(ScanConstants.OPEN_CAMERA)
    

    private fun processOCR(
        imgWidth: Double,
        imgHeight: Double,
        image: InputImage,
        localJpeg: File
    ) {
        val result = TextRecognition.getClient().process(image)
            .addOnSuccessListener { visionText ->

                // Create the PDF containing the recognized text
                val outputPath = createPDF(imgWidth, imgHeight, localJpeg, visionText)

                // Open the document in the viewer
                val config =
                    ViewerConfig.Builder().openUrlCachePath(cacheDir.absolutePath).build()
                DocumentActivity.openDocument(
                    this@MainActivity,
                    Uri.fromFile(outputPath),
                    config
                )
            }
    }

    private fun createPDF(
        imgWidth: Double,
        imgHeight: Double,
        localJpeg: File,
        visionText: com.google.mlkit.vision.text.Text
    ): File {
        
        val doc = PDFDoc()
        val outputFile = File(
            this.filesDir, com.pdftron.pdf.utils.Utils.getFileNameNotInUse(
                "scanned_doc_output.pdf"
            )
        )

        // First convert the image to a PDF Doc
        Convert.toPdf(doc, localJpeg.absolutePath)

        val page = doc.getPage(1) // currently this sample only supports 1 page
        val ratio = page.pageWidth / imgWidth;

        // We will need to generate a JSON containing the text data, which will be used
        // to insert the text information into the PDF document
        val jsonWords = JSONArray()
        for (block in visionText.textBlocks) {
            for (line in block.lines) {
                for (element in line.elements) {
                    val elementText = element.text
                    val elementFrame = element.boundingBox

                    val pdfRect =
                        androidRectToPdfRect(elementFrame!!, ratio, imgHeight)
                    pdfRect.normalize()

                    val word = JSONObject()
                    word.put("font-size", (pdfRect.y2 - pdfRect.y1).toInt())
                    word.put("length", (pdfRect.x2 - pdfRect.x1).toInt())
                    word.put("text", elementText)
                    word.put("orientation", "U")
                    word.put("x", pdfRect.x1.toInt())
                    word.put("y", pdfRect.y1.toInt())
                    jsonWords.put(word)
                }
            }
        }

        val jsonObj = JSONObject()
        val jsonPages = JSONArray()

        val jsonPage = JSONObject()
        jsonPage.put("Word", jsonWords)
        jsonPage.put("num", 1) // Only supports one page
        jsonPage.put("dpi", 96)
        jsonPage.put("origin", "BottomLeft")

        jsonPages.put(jsonPage)
        jsonObj.put("Page", jsonPages)

        OCRModule.applyOCRJsonToPDF(doc, jsonObj.toString());
        doc.save(outputFile.absolutePath, SDFDoc.SaveMode.LINEARIZED, null)
        return outputFile
    }