handle ocr to bytes with rpc

ocr_request.go

@@ -1,6 +1,7 @@
 package ocrworker
 
 import "fmt"
+import "encoding/base64"
 
 type OcrRequest struct {
 	ImgUrl            string                 `json:"img_url"`
@@ -27,7 +28,25 @@ func (ocrRequest *OcrRequest) nextPreprocessor(processorRoutingKey string) strin
 		ocrRequest.PreprocessorChain = s
 		return x
 	}
+}
+
+func (ocrRequest *OcrRequest) decodeBase64() error {
+
+	bytes, decodeError := base64.StdEncoding.DecodeString(ocrRequest.ImgBase64)
+
+	if decodeError != nil {
+		return decodeError
+	}
+
+	ocrRequest.ImgBytes = bytes
+	ocrRequest.ImgBase64 = ""
+
+	return nil
+}
+
+func (ocrRequest *OcrRequest) hasBase64() error {
 
+	return ocrRequest.ImgBase64 != ""
 }
 
 func (ocrRequest *OcrRequest) downloadImgUrl() error {

ocr_rpc_client.go

@@ -86,12 +86,25 @@ func (c *OcrRpcClient) DecodeImage(ocrRequest OcrRequest) (OcrResult, error) {
 	// any preprocessors.  if rabbitmq isn't in same data center
 	// as open-ocr, it will be expensive in terms of bandwidth
 	// to have image binary in messages
-	if ocrRequest.ImgBytes == nil && ocrRequest.ImgBase64 == "" {
-		// if we already have image bytes, ignore image url
-		err = ocrRequest.downloadImgUrl()
-		if err != nil {
-			logg.LogTo("OCR_CLIENT", "Error downloading img url: %v", err)
-			return OcrResult{}, err
+	if ocrRequest.ImgBytes == nil {
+
+		// if we do not have bytes use base 64 file by converting it to bytes
+		if ocrRequest.hasBase64() {
+
+			logg.LogTo("OCR_CLIENT", "OCR request has base 64 convert it to bytes")
+
+			err = ocrRequest.decodeBase64()
+			if err != nil {
+				logg.LogTo("OCR_CLIENT", "Error decoding base64: %v", err)
+				return OcrResult{}, err
+			}
+		} else {
+			// if we do not have base 64 or bytes download the file
+			err = ocrRequest.downloadImgUrl()
+			if err != nil {
+				logg.LogTo("OCR_CLIENT", "Error downloading img url: %v", err)
+				return OcrResult{}, err
+			}
 		}
 	}
 

tesseract_engine.go

@@ -98,10 +98,10 @@ func (t TesseractEngineArgs) Export() []string {
 func (t TesseractEngine) ProcessRequest(ocrRequest OcrRequest) (OcrResult, error) {
 
 	tmpFileName, err := func() (string, error) {
-		if ocrRequest.ImgUrl != "" {
-			return t.tmpFileFromImageUrl(ocrRequest.ImgUrl)
-		} else if ocrRequest.ImgBase64 != "" {
+		if ocrRequest.ImgBase64 != "" {
 			return t.tmpFileFromImageBase64(ocrRequest.ImgBase64)
+		} else if ocrRequest.ImgUrl != "" {
+			return t.tmpFileFromImageUrl(ocrRequest.ImgUrl)
 		} else {
 			return t.tmpFileFromImageBytes(ocrRequest.ImgBytes)
 		}