erp5_receipt_recognition Add function to load model from datastream

This commit allow the erp5_receipt_recogniton module to unpickle its
model from wendelin datastream.

Loading model from datastream is a bit slower.

bt5/erp5_receipt_recognition/ExtensionTemplateItem/portal_components/extension.erp5.ReceiptRecognition.py

@@ -14,9 +14,10 @@ from matplotlib import pylab
 import matplotlib.image as mpimg
 import scipy.stats as stats
 import re
+import cPickle
 import ocrolib
 
-def getReceiptValue(self, image_data):
+def getReceiptValue(self, image_data, model_name = "en-default.pyrnn", from_stream=False):
   """
   Function called from an erp5 script through externalMethod
   that take an image and its name and save its binarized
@@ -29,7 +30,7 @@ def getReceiptValue(self, image_data):
       - image_data:
           base64 representation of the image to analyse
     @return:
-      - ret: float
+      - anon: float
           Represent total value paid on the receipt
   ----------------------------
   This function return the total value of the receipt in euros.
@@ -39,8 +40,36 @@ def getReceiptValue(self, image_data):
   line_list, cleared = getLinesFromPicture(image_as_array)
 
   # Start the neural network
-  network, lnorm = initRnnModel()
+  if not from_stream:
+    network, lnorm = initRnnModel(model_name)
+  else:
+    network, lnorm = getRnnModelFromDataStream(self, model_name)
+  return findReceiptValue(line_list, cleared, network, lnorm)
 
+def findReceiptValue(line_list, cleared, network, lnorm):
+  """
+  Function that run the neural network through the receipt and extract
+  meaningfull value
+  -----------------------------
+    @args:
+      - lines: array list
+          Represent lines of text that will be extracted
+          from the image
+      - cleared:2D array
+          Represent binarized image cropped and cleaned,
+          from which we will extract text lines
+      - network: lstm object
+          Represent the trained neural net
+      - lnorm: method from lstm object
+          Represent the size of the lstm object. Is used to scale the objects
+          to recognize from original size to the average network object.
+    @return:
+      - anon: float
+          Represent total value paid on the receipt
+  -----------------------------
+  This function can bemodified to add more field to detect. It might be
+  possible to run a classification neural net on the result.
+  """
   value_list = []
   tofind = r"(EUR)|€|(TOT)"
   for _, line in enumerate(line_list):
@@ -48,15 +77,32 @@ def getReceiptValue(self, image_data):
     # Corner case: he dewarping function from the normalizer fail
     # sometimes on empty lines. Can be corrected with better segmentation
     try:
-      evaluate = getStringFromImage(binline, lnorm, network)
+      evaluate  = getStringFromImage(binline, lnorm, network)
       if re.search(tofind, evaluate.upper()):
         number = re.findall(r"\d+[\.|,]\d\d", evaluate)
         value_list += [float(char.replace(',', '.')) for char in number]
     except ValueError:
       pass
-
   return round(max(value_list), 2)
 
+def getRnnModelFromDataStream(self, model_name="en-default.pyrnn"):
+  """
+  This function load a neural network from a dataStream
+  ----------------------------
+    @args:
+      - model_name: string, default: en-default.pyrnn
+          Id of the object in data_stream_module that contain the rnn model
+    @return:
+      - network: lstm object
+          Represent the trained neural net
+      - lnorm: method from lstm object
+          Represent the size of the lstm object. Is used to scale the objects
+          to recognize from original size to the average network object.
+  ----------------------------
+  """
+  network = cPickle.loads(self.data_stream_module[model_name].getData())
+  lnorm = getattr(network, "lnorm", None)
+  return network, lnorm
 
 def initRnnModel(model_name = "en-default.pyrnn"):
   """

bt5/erp5_receipt_recognition/ExtensionTemplateItem/portal_components/extension.erp5.ReceiptRecognition.xml

@@ -46,8 +46,8 @@
             <key> <string>text_content_warning_message</string> </key>
             <value>
               <tuple>
-                <string>W:243,  2: Attempting to unpack a non-sequence defined at line 181 of scipy.ndimage.measurements (unpacking-non-sequence)</string>
-                <string>W:272,  2: Attempting to unpack a non-sequence defined at line 181 of scipy.ndimage.measurements (unpacking-non-sequence)</string>
+                <string>W:289,  2: Attempting to unpack a non-sequence defined at line 181 of scipy.ndimage.measurements (unpacking-non-sequence)</string>
+                <string>W:318,  2: Attempting to unpack a non-sequence defined at line 181 of scipy.ndimage.measurements (unpacking-non-sequence)</string>
               </tuple>
             </value>
         </item>