Create app.py

app.py

@@ -0,0 +1,46 @@
+import streamlit as st
+import nltk
+from nltk.tree import Tree
+from nltk import pos_tag, word_tokenize
+from nltk.parse import CoreNLPParser
+import os
+import base64
+from graphviz import Source
+
+# Ensure necessary NLTK resources are downloaded
+nltk.download('punkt')
+nltk.download('averaged_perceptron_tagger')
+
+# Define a function to generate and render a syntax tree
+def generate_syntax_tree(sentence):
+    # Tokenize and part-of-speech tag the sentence
+    tokens = word_tokenize(sentence)
+    tagged_tokens = pos_tag(tokens)
+
+    # Use NLTK's CoreNLPParser to parse the sentence
+    parser = CoreNLPParser(url='http://localhost:9000')  # Make sure CoreNLP server is running
+    parsed_tree = next(parser.parse(tagged_tokens))
+
+    # Convert the tree to a DOT format for visualization
+    dot_format = parsed_tree._repr_svg_()
+    return dot_format
+
+# Function to display syntax tree image
+def display_tree(dot_format):
+    src = Source(dot_format)
+    svg = src.pipe(format='svg')
+    svg_base64 = base64.b64encode(svg).decode('utf-8')
+    svg_html = f"<div style='width:100%;height:100%;'><img src='data:image/svg+xml;base64,{svg_base64}'></div>"
+    return svg_html
+
+# Set up the Streamlit interface
+st.title("Syntax Tree Generator for English")
+sentence = st.text_input("Enter a sentence:", "")
+
+if sentence:
+    try:
+        dot_format = generate_syntax_tree(sentence)
+        svg_html = display_tree(dot_format)
+        st.markdown(svg_html, unsafe_allow_html=True)
+    except Exception as e:
+        st.error(f"An error occurred: {e}")