algorithm improved

ud.py

@@ -86,6 +86,20 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
           v[i-1]=(v[i-1][0],v.pop(i)[1])
           q.pop(i)
     t=model_outputs["sentence"].replace("\n"," ")
+    for i,(s,e) in reversed(list(enumerate(v))):
+      d=t[s:e]
+      j=len(d)-len(d.lstrip())
+      if j>0:
+        d=d.lstrip()
+        v[i]=(v[i][0]+j,v[i][1])
+      j=len(d)-len(d.rstrip())
+      if j>0:
+        d=d.rstrip()
+        v[i]=(v[i][0],v[i][1]-j)
+      if d.strip()=="":
+        h=[b if i>b else b-1 for a,b in enumerate(h) if i!=a]
+        v.pop(i)
+        q.pop(i)
     u="# text = "+t+"\n"
     for i,(s,e) in enumerate(v):
       u+="\t".join([str(i+1),t[s:e],"_",q[i][0].replace(".",""),"_","_" if len(q[i])<3 else "|".join(q[i][1:-1]),str(0 if h[i]==i else h[i]+1),q[i][-1][1:-1],"_","_" if i+1<len(v) and e<v[i+1][0] else "SpaceAfter=No"])+"\n"