Update app.py

app.py

@@ -2,6 +2,8 @@ import streamlit as st
 from transformers import pipeline
 import spacy
 from io import StringIO
+import PyPDF2
+import docx
 
 # Load Hugging Face's pre-trained NER model
 nlp = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english")
@@ -12,9 +14,24 @@ regulations = {
     "waste_management": "Waste should be sorted into recyclable and non-recyclable categories.",
 }
 
+# Function to extract text from PDF
+def extract_text_from_pdf(file):
+    pdf_reader = PyPDF2.PdfReader(file)
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
+
+# Function to extract text from DOCX
+def extract_text_from_docx(file):
+    doc = docx.Document(file)
+    text = ""
+    for para in doc.paragraphs:
+        text += para.text + "\n"
+    return text
+
 # Function to check compliance with regulations
 def check_compliance(document_text):
-    entities = nlp(document_text)
     compliance_feedback = []
     
     # Check for pollution limit violations
@@ -34,26 +51,38 @@ st.title("🌱 Environmental Compliance Checker")
 uploaded_file = st.file_uploader("Upload Environmental Report", type=["txt", "pdf", "docx"])
 
 if uploaded_file is not None:
-    # Read the file content
-    file_content = uploaded_file.read().decode("utf-8")  # assuming it's a text file
-    st.text_area("Uploaded Document", file_content, height=300)
-
-    # Check compliance with regulations
-    st.subheader("Compliance Feedback")
-    feedback = check_compliance(file_content)
-    
-    if feedback:
-        for item in feedback:
-            st.write(f"- {item}")
+    # Extract text based on file type
+    file_extension = uploaded_file.name.split('.')[-1].lower()
+    if file_extension == "pdf":
+        file_content = extract_text_from_pdf(uploaded_file)
+    elif file_extension == "docx":
+        file_content = extract_text_from_docx(uploaded_file)
+    elif file_extension == "txt":
+        file_content = uploaded_file.read().decode("utf-8")
     else:
-        st.write("No compliance issues found.")
-    
-    # Optional: Provide NLP-based analysis or highlight regulations mentioned in the document
-    st.subheader("Regulation Mentions in Document")
-    entities = nlp(file_content)
-    for entity in entities:
-        st.write(f"Entity: {entity['word']} - Label: {entity['entity']}")
+        st.error("Unsupported file type!")
+        file_content = ""
+
+    if file_content:
+        st.text_area("Uploaded Document", file_content, height=300)
+
+        # Check compliance with regulations
+        st.subheader("Compliance Feedback")
+        feedback = check_compliance(file_content)
+        
+        if feedback:
+            for item in feedback:
+                st.write(f"- {item}")
+        else:
+            st.write("No compliance issues found.")
+        
+        # Optional: Provide NLP-based analysis or highlight regulations mentioned in the document
+        st.subheader("Regulation Mentions in Document")
+        entities = nlp(file_content)
+        for entity in entities:
+            st.write(f"Entity: {entity['word']} - Label: {entity['entity']}")
 
 else:
     st.write("Please upload a document to check compliance.")
 
+