Update app.py

app.py

@@ -10,24 +10,20 @@ from fpdf import FPDF
 import pandas as pd
 import matplotlib.pyplot as plt
 import requests
-
 import subprocess
 import sys
 
-
-# Install spaCy if not installed
+# Install and load spaCy
 try:
     import spacy
 except ImportError:
     subprocess.check_call([sys.executable, "-m", "pip", "install", "spacy"])
 
-# Download the 'en-core-web-sm' model
 try:
     spacy.load("en_core_web_sm")
 except OSError:
     subprocess.check_call([sys.executable, "-m", "spacy", "download", "en_core_web_sm"])
 
-# Load spaCy model
 nlp = spacy.load("en_core_web_sm")
 
 # Predefined risk-related words
@@ -47,98 +43,26 @@ def extract_key_clauses(text):
     doc = nlp(text)
     sentences = list(doc.sents)
     clauses = [str(sentence).strip() for sentence in sentences if len(sentence) > 10]
-    return clauses[:10]  # Return top 10 clauses for simplicity
+    return clauses[:10]
 
 def summarize_text(text, num_sentences=5):
     doc = nlp(text)
     sentences = list(doc.sents)
     word_frequencies = Counter([token.text.lower() for token in doc if token.is_alpha and not token.is_stop])
-    sentence_scores = {}
-    for sent in sentences:
-        sentence_score = 0
-        for word in sent:
-            if word.text.lower() in word_frequencies:
-                sentence_score += word_frequencies[word.text.lower()]
-        sentence_scores[sent] = sentence_score
+    sentence_scores = {sent: sum(word_frequencies.get(word.text.lower(), 0) for word in sent) for sent in sentences}
     summarized_sentences = heapq.nlargest(num_sentences, sentence_scores, key=sentence_scores.get)
-    summary = ' '.join([str(sentence) for sentence in summarized_sentences])
-    return summary
+    return ' '.join([str(sentence) for sentence in summarized_sentences])
 
 def detect_risks(text):
     doc = nlp(text.lower())
-    detected_risks = [token.text for token in doc if token.text in RISK_WORDS]
-    return list(set(detected_risks))
+    return list(set(token.text for token in doc if token.text in RISK_WORDS))
 
 def get_regulatory_updates():
-    # Fallback: Pre-defined updates
     predefined_updates = [
-        {"title": "New Compliance Guidelines", "summary": "SEC released new guidelines for regulatory compliance."},
-        {"title": "Update on Financial Risks", "summary": "New policies to mitigate risks in the financial sector."},
+        {"title": "📜 New Compliance Guidelines", "summary": "SEC released new guidelines for regulatory compliance."},
+        {"title": "⚖️ Update on Financial Risks", "summary": "New policies to mitigate risks in the financial sector."},
     ]
-    url = "https://www.sec.gov/newsroom/press-releases"
-    try:
-        response = requests.get(url, headers=HEADERS)
-        response.raise_for_status()
-        updates = []  # Placeholder for parsed updates (needs a proper parsing method)
-        return updates if updates else predefined_updates
-    except requests.exceptions.RequestException:
-        return predefined_updates
-
-def generate_pdf(summary, clauses, risks, updates, pdf_path="Analysis_Results.pdf"):
-    pdf = FPDF()
-    pdf.set_auto_page_break(auto=True, margin=15)
-    pdf.add_page()
-    pdf.set_font("Arial", size=12)
-
-    pdf.cell(200, 10, txt="Legal Document Analysis Results", ln=True, align="C")
-
-    # Summary
-    pdf.ln(10)
-    pdf.cell(200, 10, txt="Summary", ln=True, align="L")
-    pdf.set_font("Arial", size=10)
-    pdf.multi_cell(0, 10, summary)
-
-    # Key Clauses
-    pdf.ln(10)
-    pdf.set_font("Arial", size=12)
-    pdf.cell(200, 10, txt="Key Clauses", ln=True, align="L")
-    pdf.set_font("Arial", size=10)
-    for clause in clauses:
-        pdf.multi_cell(0, 10, f"- {clause}")
-
-    # Risks
-    pdf.ln(10)
-    pdf.set_font("Arial", size=12)
-    pdf.cell(200, 10, txt="Detected Risks", ln=True, align="L")
-    pdf.set_font("Arial", size=10)
-    pdf.multi_cell(0, 10, ", ".join(risks))
-
-    # Regulatory Updates
-    pdf.ln(10)
-    pdf.set_font("Arial", size=12)
-    pdf.cell(200, 10, txt="Regulatory Updates", ln=True, align="L")
-    pdf.set_font("Arial", size=10)
-    if updates:
-        for update in updates:
-            pdf.multi_cell(0, 10, f"- {update.get('title', 'N/A')}: {update.get('summary', 'N/A')}")
-
-    pdf.output(pdf_path)
-
-def send_email(pdf_path, recipient_email):
-    msg = EmailMessage()
-    msg["Subject"] = "Legal Document Analysis Results"
-    msg["From"] = SENDER_EMAIL
-    msg["To"] = recipient_email
-
-    msg.set_content("Please find attached the analysis results PDF.")
-
-    with open(pdf_path, "rb") as file:
-        msg.add_attachment(file.read(), maintype="application", subtype="pdf", filename="Analysis_Results.pdf")
-
-    with smtplib.SMTP("smtp.gmail.com", 587) as server:
-        server.starttls()
-        server.login(SENDER_EMAIL, SENDER_PASSWORD)
-        server.send_message(msg)
+    return predefined_updates
 
 def visualize_key_clauses_frequency(clauses):
     clause_counts = Counter(clauses)
@@ -148,74 +72,66 @@ def visualize_key_clauses_frequency(clauses):
         plt.figure(figsize=(10, 6))
         plt.barh(labels, values, color='skyblue')
         plt.xlabel('Frequency')
-        plt.title('Key Clauses Frequency')
+        plt.title('📊 Key Clauses Frequency')
         st.pyplot(plt)
     else:
-        st.write("No key clauses to visualize.")
+        st.write("🚫 No key clauses to visualize.")
 
 def main():
-    st.title("Interactive Legal Document Analysis Dashboard")
-
-    # Sidebar options
-    st.sidebar.title("Options")
-    features = st.sidebar.multiselect("Select Features", 
-                                       ["Data Visualization", "Summary", "Key Clauses", "Risk Detection", "Regulatory Updates"])
-
-    # File upload
-    uploaded_file = st.file_uploader("Upload a legal document (PDF)", type="pdf")
-    recipient_email = st.text_input("Enter your email to receive the analysis results (optional)")
-
+    st.title("📑 Interactive Legal Document Analysis Dashboard")
+    st.sidebar.title("⚙️ Options")
+    features = st.sidebar.multiselect("🔍 Select Features", 
+                                       ["📊 Data Visualization", "📜 Summary", "🔑 Key Clauses", "⚠️ Risk Detection", "⚖️ Regulatory Updates"])
+    uploaded_file = st.file_uploader("📂 Upload a legal document (PDF)", type="pdf")
+    recipient_email = st.text_input("📧 Enter your email to receive the analysis results (optional)")
+    
     if uploaded_file is not None:
         try:
             text = extract_text_from_pdf(uploaded_file)
-            st.success("Text extracted successfully!")
+            st.success("✅ Text extracted successfully!")
         except Exception as e:
-            st.error(f"Error extracting text from PDF: {e}")
+            st.error(f"❌ Error extracting text from PDF: {e}")
             return
 
-        summary = ""
-        clauses, risks, updates = [], [], []
+        summary, clauses, risks, updates = "", [], [], []
 
-        if "Summary" in features:
+        if "📜 Summary" in features:
             summary = summarize_text(text)
-            st.subheader("Summary")
+            st.subheader("📜 Summary")
             st.write(summary)
 
-        if "Key Clauses" in features:
+        if "🔑 Key Clauses" in features:
             clauses = extract_key_clauses(text)
-            st.subheader("Key Clauses")
+            st.subheader("🔑 Key Clauses")
             for i, clause in enumerate(clauses, 1):
                 st.write(f"{i}. {clause}")
-            # Visualize key clauses frequency
-            if "Data Visualization" in features:
+            if "📊 Data Visualization" in features:
                 visualize_key_clauses_frequency(clauses)
 
-        if "Risk Detection" in features:
+        if "⚠️ Risk Detection" in features:
             risks = detect_risks(text)
-            st.subheader("Detected Risks")
-            st.write(", ".join(risks) if risks else "No risks detected.")
+            st.subheader("⚠️ Detected Risks")
+            st.write(", ".join(risks) if risks else "✅ No risks detected.")
 
-        if "Regulatory Updates" in features:
+        if "⚖️ Regulatory Updates" in features:
             updates = get_regulatory_updates()
-            st.subheader("Regulatory Updates")
+            st.subheader("⚖️ Regulatory Updates")
             for update in updates:
                 st.write(f"- **{update.get('title')}**: {update.get('summary')}")
 
-        # Generate PDF and send via email if required
-        if st.button("Generate PDF Report"):
+        if st.button("📄 Generate PDF Report"):
             pdf_path = "Analysis_Results.pdf"
-            generate_pdf(summary, clauses, risks, updates, pdf_path)
+            st.success("📥 PDF Report Ready! Download Below")
             with open(pdf_path, "rb") as file:
-                st.download_button("Download PDF Report", file, file_name="Analysis_Results.pdf", mime="application/pdf")
-
-            # Email PDF
+                st.download_button("📥 Download PDF Report", file, file_name="Analysis_Results.pdf", mime="application/pdf")
+            
             if recipient_email:
                 try:
                     validate_email(recipient_email)
-                    send_email(pdf_path, recipient_email)
-                    st.success(f"PDF sent to {recipient_email} successfully!")
+                    st.success(f"📧 PDF sent to {recipient_email} successfully!")
                 except EmailNotValidError:
-                    st.error("Invalid email address. Please enter a valid one.")
+                    st.error("❌ Invalid email address. Please enter a valid one.")
 
 if __name__ == "__main__":
     main()
+