commit d06988ab17e655f8a191042b09476ba29f612b3f
Author: vivekvardhanadepu <vivekvicky839@gmail.com>
Date:   Sat Aug 21 18:05:10 2021 +0530

    scripts:moving ambiguous to common

diff --git a/scripts/common.py b/scripts/common.py
index d0f4d08..4d4031f 100644
--- a/scripts/common.py
+++ b/scripts/common.py
@@ -7,6 +7,15 @@ import re
 import sys
 
 re_start = re.compile('(^[^\^]*)');
+
+def ambiguous(bt):
+    # legislation<n><sg>/legislación<n><f><sg>/ordenamiento<n><m><sg>
+    for token in bt:
+        if len(token['tls']) > 1:
+            return True
+
+    return False
+	
 def wrap (x):
 	return '^' + x + '$'
 
diff --git a/scripts/extract-biltrans-candidates.py b/scripts/extract-biltrans-candidates.py
index 665988a..6b08d04 100644
--- a/scripts/extract-biltrans-candidates.py
+++ b/scripts/extract-biltrans-candidates.py
@@ -47,21 +47,6 @@ def pos_equal(s, t):
 
 	return spos == tpos;
 
-
-def ambiguous(bt): #{
-	# legislation<n><sg>/legislación<n><f><sg>/ordenamiento<n><m><sg>
-
-	ambig = False;
-	for token in bt: #{
-		tls = token['tls']
-		if len(tls) > 1: #{
-			return True;
-		#}
-	#}
-
-	return ambig;
-#}
-
 reading = True;
 lineno = 0;
 total_valid = 0;
@@ -82,7 +67,7 @@ while reading: #{
 		alignments = row[2].strip();
 		bt = common.tokenise_biltrans_line(bt_line);
 
-		if not ambiguous(bt): #{
+		if not common.ambiguous(bt): #{
 			continue;
 		#}
 		if len(sl) < 2 and len(tl) < 2: #{
diff --git a/scripts/extract-sentences.py b/scripts/extract-sentences.py
index 03392fe..4796976 100755
--- a/scripts/extract-sentences.py
+++ b/scripts/extract-sentences.py
@@ -5,16 +5,6 @@
 import sys
 import common
 
-
-def ambiguous(bt):
-    # legislation<n><sg>/legislación<n><f><sg>/ordenamiento<n><m><sg>
-    for token in bt:
-        if len(token['tls']) > 1:
-            return True
-
-    return False
-
-
 def extract_sentences(phrase_table_file, biltrans_out_file):
     lineno = 0
     total_valid = 0
@@ -38,7 +28,7 @@ def extract_sentences(phrase_table_file, biltrans_out_file):
                 sl = common.tokenise_tagger_line(row[1].strip())
                 tl = common.tokenise_tagger_line(row[0].strip())
 
-                if not ambiguous(bt):
+                if not common.ambiguous(bt):
                     not_ambiguous.append(str(lineno))
                     if len(not_ambiguous) >= 10:
                         print("not ambiguous:", ' '.join(