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

5bcfb89f · Abdelwahab HEBA · f61a95f2 · 5bcfb89f · 5bcfb89f
Commit 5bcfb89f authored Sep 21, 2017 by Abdelwahab HEBA
Hide whitespace changes
Inline Side-by-side

Showing with 10 additions and 0 deletions

local/lm/parseESTERSyncV2_text.py local/lm/parseESTERSyncV2_text.py +5 -0

local/parseESTERSyncV2.py local/parseESTERSyncV2.py +5 -0

No files found.
--- a/local/lm/parseESTERSyncV2_text.py
+++ b/local/lm/parseESTERSyncV2_text.py
@@ -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)

--- a/local/parseESTERSyncV2.py
+++ b/local/parseESTERSyncV2.py
@@ -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)