Commit 5bcfb89f authored by Abdelwahab HEBA's avatar Abdelwahab HEBA
Browse files

fix parse : mohammed v to mohammed cinq | mohammed vi to mohammed six etc..

parent f61a95f2
......@@ -9,6 +9,11 @@ import re
import os.path
def transformation_text(text):
# ESTER Problem "Mohamed v" ===> "Mohammed cinq"
text=re.sub("mohammed vi","mohamed six",text)
text=re.sub("mohammed v","mohamed cinq",text)
# map all "mohamed" to "mohammed"
text=re.sub("mohamed","mohammed",text)
# character normalization:
text=re.sub("&","et",text)
text=re.sub("\+","plus",text)
......
......@@ -9,6 +9,11 @@ import re
import os.path
def transformation_text(text):
# ESTER Problem "Mohamed v" ===> "Mohammed cinq"
text=re.sub("mohammed vi","mohamed six",text)
text=re.sub("mohammed v","mohamed cinq",text)
# map all "mohamed" to "mohammed"
text=re.sub("mohamed","mohammed",text)
# character normalization:
text=re.sub("&","et",text)
text=re.sub("æ","ae",text)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment