update

app.py

@@ -1,5 +1,5 @@
 import streamlit as st
-from parse import parse_text
+# from parse import parse_text
 from nltk import Tree
 import pandas as pd
 import re

parse.py

@@ -0,0 +1,27 @@
+import re
+import sys
+import benepar
+from huggingface_hub import hf_hub_download
+
+model_path = "ParserModels/ENHG/new-convbert-german-europeana0_dev=83.03.pt"
+ hf_hub_download(repo_id=model_path, filename='german-delex-parser_dev=83.10.pt')
+parser = benepar.Parser(model_path)
+    
+def parse(words):
+    words = [word.replace('(','-LRB-').replace(')','-RRB-') for word in words]
+    input_sentence = benepar.InputSentence(words=words)
+    tree = parser.parse(input_sentence)
+    tree = str(tree).replace('-LRB-','\\(').replace('-RRB-','\\)').replace('-LSB-','\\[').replace('-RSB-','\\]').replace('($(-','($\\(-')
+    # put the whole parse tree on a single line
+    tree = re.sub(r'\s+', ' ', tree.strip())
+    tree = re.sub(r' \(', '(', tree)
+    return tree
+            
+            
+with open(sys.argv[1]) as file:
+    for line in file:
+        line = re.sub(r'(\S)([.,;:?!)"])', r'\1 \2', line.strip())
+        line = re.sub(r'(["(])(\S)', r'\1 \2', line)
+        words = line.split()
+        tree = parse(words)
+        print(tree)