new clean and number2word convertion

local/parseESTERSyncV2.py

@@ -84,21 +84,24 @@ def transformation_text(text):
 # remove " character: OK
     text = re.sub(r"\"+", "", text)
     # t 'avais
-    text = re.sub(r"[ ]\'", " ", text)
-    text = re.sub(r"\'", "\' ", text)
+    text = re.sub(r"[ ]\'", "\'", text)
+    #text = re.sub(r"\'", "\' ", text)
     # for example : A43
-    num_list = re.findall("\w+?-?\d+", text)
+    #num_list = re.findall("\w+?-?\d+", text)
+    num_list = re.findall("[a-zA-Z|à|è|é|ù]+\'*[a-zA-Z]*[-]?\d+""", text)
     if len(num_list) > 0:
         for s in num_list:
-            split_between_char_int=re.findall(r'(\w+?)-?(\d+)',s)
+            split_between_char_int=re.findall(r'([a-zA-Z|à|é|è|ù]+\'*[a-zA-Z]*)-?(\d+)',s)
             num_in_word = num2words(int(split_between_char_int[0][1]), lang='fr')
             #num_in_word=normalize('NFKD', num_in_word).encode('ascii', 'ignore')
             #text = re.sub(r"(^|[ ])"+str(s)+"([ ]|$)"," " + str(split_between_char_int[0][0]) +" "+ str(num_in_word) + " ",text)
             text = re.sub(r"(^|[ ])"+str(s)," " + str(split_between_char_int[0][0]) +" "+ str(num_in_word) + " ",text)
-    num_list = re.findall("\d+\w+", text)
+    #num_list = re.findall("\d+\w+", text)
+    num_list = re.findall("\d+[a-zA-Z]+\'*[a-zA-Z]*", text)
     if len(num_list) > 0:
         for s in num_list:
-            split_between_char_int=re.findall(r'\d+\w+',s)
+            split_between_char_int=re.findall(r'(\d+)([a-zA-Z]+\'*[a-zA-Z]*)',s)
+            #re.findall(r'\d+\w+',s)
             num_in_word = num2words(int(split_between_char_int[0][0]), lang='fr')
             #num_in_word=normalize('NFKD', num_in_word).encode('ascii', 'ignore')
             #text = re.sub(r"(^|[ ])"+str(s)+"([ ]|$)"," " + str(split_between_char_int[0][0]) +" "+ str(num_in_word) + " ",text)