Update app.py

app.py

@@ -1,243 +1,243 @@
-import os
-import io
-from flask import Flask, render_template, request, jsonify, send_file
-from werkzeug.utils import secure_filename
-import PyPDF2
-from io import BytesIO
-from reportlab.pdfgen import canvas
-from reportlab.lib.pagesizes import letter
-import nltk
-from nltk.tokenize import sent_tokenize, word_tokenize
-from nltk.corpus import stopwords
-from collections import defaultdict
-import heapq
-import tempfile
-import json
-
-# ==============================
-# FIXED NLTK DOWNLOAD SECTION
-# ==============================
-
-def download_nltk_resources():
-    resources = ['punkt', 'punkt_tab', 'stopwords']
-    
-    for resource in resources:
-        try:
-            nltk.data.find(f'tokenizers/{resource}')
-        except LookupError:
-            try:
-                nltk.data.find(f'corpora/{resource}')
-            except LookupError:
-                nltk.download(resource)
-
-download_nltk_resources()
-
-# ==============================
-
-app = Flask(__name__)
-app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024  # 16MB max file size
-app.config['UPLOAD_FOLDER'] = tempfile.gettempdir()
-app.config['SECRET_KEY'] = 'your-secret-key-here'
-
-ALLOWED_EXTENSIONS = {'pdf'}
-
-def allowed_file(filename):
-    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
-
-
-def extract_text_from_pdf(pdf_file):
-    """Extract text from uploaded PDF file"""
-    pdf_reader = PyPDF2.PdfReader(pdf_file)
-    text = ""
-    for page in pdf_reader.pages:
-        page_text = page.extract_text()
-        if page_text:
-            text += page_text + "\n"
-    return text
-
-
-def summarize_text(text, num_sentences=5):
-    """Summarize text using frequency-based scoring"""
-    
-    sentences = sent_tokenize(text)
-
-    if len(sentences) <= num_sentences:
-        return text
-
-    stop_words = set(stopwords.words('english'))
-    words = word_tokenize(text.lower())
-    words = [word for word in words if word.isalnum() and word not in stop_words]
-
-    word_freq = defaultdict(int)
-    for word in words:
-        word_freq[word] += 1
-
-    sentence_scores = defaultdict(int)
-    for i, sentence in enumerate(sentences):
-        sentence_words = word_tokenize(sentence.lower())
-        for word in sentence_words:
-            if word in word_freq:
-                sentence_scores[i] += word_freq[word]
-
-    top_sentences = heapq.nlargest(num_sentences, sentence_scores, key=sentence_scores.get)
-    top_sentences.sort()
-
-    summary = [sentences[i] for i in top_sentences]
-    return ' '.join(summary)
-
-
-def analyze_pdf_statistics(text):
-    """Analyze PDF and return statistics"""
-    sentences = sent_tokenize(text)
-    words = word_tokenize(text)
-    characters = len(text)
-
-    return {
-        'page_count': text.count('\f') + 1,
-        'sentence_count': len(sentences),
-        'word_count': len(words),
-        'character_count': characters,
-        'avg_sentence_length': round(len(words) / len(sentences), 2) if sentences else 0,
-        'avg_word_length': round(sum(len(word) for word in words) / len(words), 2) if words else 0
-    }
-
-
-def create_summary_pdf(summary, filename="summary.pdf"):
-    """Create a downloadable PDF from summary"""
-    buffer = BytesIO()
-    pdf = canvas.Canvas(buffer, pagesize=letter)
-    pdf.setTitle("PDF Summary")
-
-    pdf.setFont("Helvetica-Bold", 16)
-    pdf.drawString(72, 750, "PDF Document Summary")
-    pdf.line(72, 745, 540, 745)
-
-    pdf.setFont("Helvetica", 12)
-    y_position = 720
-    max_width = 500
-    words = summary.split()
-    line = []
-
-    for word in words:
-        line.append(word)
-        test_line = ' '.join(line)
-
-        if pdf.stringWidth(test_line, "Helvetica", 12) > max_width:
-            line.pop()
-            pdf.drawString(72, y_position, ' '.join(line))
-            y_position -= 20
-            line = [word]
-
-            if y_position < 50:
-                pdf.showPage()
-                pdf.setFont("Helvetica", 12)
-                y_position = 750
-
-    if line:
-        pdf.drawString(72, y_position, ' '.join(line))
-
-    pdf.save()
-    buffer.seek(0)
-    return buffer
-
-
-@app.route('/')
-def index():
-    return render_template('index.html')
-
-
-@app.route('/upload', methods=['POST'])
-def upload_pdf():
-    if 'pdf_file' not in request.files:
-        return jsonify({'error': 'No file uploaded'}), 400
-
-    file = request.files['pdf_file']
-
-    if file.filename == '':
-        return jsonify({'error': 'No file selected'}), 400
-
-    if not allowed_file(file.filename):
-        return jsonify({'error': 'Only PDF files are allowed'}), 400
-
-    try:
-        text = extract_text_from_pdf(file)
-
-        if not text.strip():
-            return jsonify({'error': 'Could not extract text from PDF. The PDF might be scanned or image-based.'}), 400
-
-        summary_ratio = float(request.form.get('summary_ratio', 0.3))
-        total_sentences = len(sent_tokenize(text))
-        num_sentences = max(3, int(total_sentences * summary_ratio))
-
-        summary = summarize_text(text, num_sentences)
-        stats = analyze_pdf_statistics(text)
-
-        original_words = len(word_tokenize(text))
-        summary_words = len(word_tokenize(summary))
-
-        compression_ratio = (
-            ((original_words - summary_words) / original_words) * 100
-            if original_words > 0 else 0
-        )
-
-        return jsonify({
-            'success': True,
-            'summary': summary,
-            'statistics': stats,
-            'compression_ratio': round(compression_ratio, 2),
-            'summary_length': summary_words,
-            'filename': secure_filename(file.filename)
-        })
-
-    except Exception as e:
-        return jsonify({'error': f'Error processing PDF: {str(e)}'}), 500
-
-
-@app.route('/download', methods=['POST'])
-def download_summary():
-    data = request.json
-    summary = data.get('summary', '')
-    filename = data.get('filename', 'summary.pdf')
-
-    if not summary:
-        return jsonify({'error': 'No summary to download'}), 400
-
-    try:
-        pdf_buffer = create_summary_pdf(summary, filename)
-
-        return send_file(
-            pdf_buffer,
-            as_attachment=True,
-            download_name=filename.replace('.pdf', '_summary.pdf'),
-            mimetype='application/pdf'
-        )
-
-    except Exception as e:
-        return jsonify({'error': f'Error creating PDF: {str(e)}'}), 500
-
-
-@app.route('/export', methods=['POST'])
-def export_summary():
-    data = request.json
-    summary = data.get('summary', '')
-
-    if not summary:
-        return jsonify({'error': 'No summary to export'}), 400
-
-    return send_file(
-        BytesIO(summary.encode()),
-        as_attachment=True,
-        download_name='summary.txt',
-        mimetype='text/plain'
-    )
-
-
-if __name__ == '__main__':
-    os.makedirs('uploads', exist_ok=True)
-    os.makedirs('templates', exist_ok=True)
-    os.makedirs('static', exist_ok=True)
-
-    print("Starting PDF Summarizer Server...")
-    print("Open your browser and navigate to: http://localhost:5000")
-
-    app.run(debug=True, host='0.0.0.0', port=5000)
+import os
+import io
+from flask import Flask, render_template, request, jsonify, send_file
+from werkzeug.utils import secure_filename
+import PyPDF2
+from io import BytesIO
+from reportlab.pdfgen import canvas
+from reportlab.lib.pagesizes import letter
+import nltk
+from nltk.tokenize import sent_tokenize, word_tokenize
+from nltk.corpus import stopwords
+from collections import defaultdict
+import heapq
+import tempfile
+import json
+
+# ==============================
+# FIXED NLTK DOWNLOAD SECTION
+# ==============================
+
+def download_nltk_resources():
+    resources = ['punkt', 'punkt_tab', 'stopwords']
+    
+    for resource in resources:
+        try:
+            nltk.data.find(f'tokenizers/{resource}')
+        except LookupError:
+            try:
+                nltk.data.find(f'corpora/{resource}')
+            except LookupError:
+                nltk.download(resource)
+
+download_nltk_resources()
+
+# ==============================
+
+app = Flask(__name__)
+app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024  # 16MB max file size
+app.config['UPLOAD_FOLDER'] = tempfile.gettempdir()
+app.config['SECRET_KEY'] = 'your-secret-key-here'
+
+ALLOWED_EXTENSIONS = {'pdf'}
+
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+
+def extract_text_from_pdf(pdf_file):
+    """Extract text from uploaded PDF file"""
+    pdf_reader = PyPDF2.PdfReader(pdf_file)
+    text = ""
+    for page in pdf_reader.pages:
+        page_text = page.extract_text()
+        if page_text:
+            text += page_text + "\n"
+    return text
+
+
+def summarize_text(text, num_sentences=5):
+    """Summarize text using frequency-based scoring"""
+    
+    sentences = sent_tokenize(text)
+
+    if len(sentences) <= num_sentences:
+        return text
+
+    stop_words = set(stopwords.words('english'))
+    words = word_tokenize(text.lower())
+    words = [word for word in words if word.isalnum() and word not in stop_words]
+
+    word_freq = defaultdict(int)
+    for word in words:
+        word_freq[word] += 1
+
+    sentence_scores = defaultdict(int)
+    for i, sentence in enumerate(sentences):
+        sentence_words = word_tokenize(sentence.lower())
+        for word in sentence_words:
+            if word in word_freq:
+                sentence_scores[i] += word_freq[word]
+
+    top_sentences = heapq.nlargest(num_sentences, sentence_scores, key=sentence_scores.get)
+    top_sentences.sort()
+
+    summary = [sentences[i] for i in top_sentences]
+    return ' '.join(summary)
+
+
+def analyze_pdf_statistics(text):
+    """Analyze PDF and return statistics"""
+    sentences = sent_tokenize(text)
+    words = word_tokenize(text)
+    characters = len(text)
+
+    return {
+        'page_count': text.count('\f') + 1,
+        'sentence_count': len(sentences),
+        'word_count': len(words),
+        'character_count': characters,
+        'avg_sentence_length': round(len(words) / len(sentences), 2) if sentences else 0,
+        'avg_word_length': round(sum(len(word) for word in words) / len(words), 2) if words else 0
+    }
+
+
+def create_summary_pdf(summary, filename="summary.pdf"):
+    """Create a downloadable PDF from summary"""
+    buffer = BytesIO()
+    pdf = canvas.Canvas(buffer, pagesize=letter)
+    pdf.setTitle("PDF Summary")
+
+    pdf.setFont("Helvetica-Bold", 16)
+    pdf.drawString(72, 750, "PDF Document Summary")
+    pdf.line(72, 745, 540, 745)
+
+    pdf.setFont("Helvetica", 12)
+    y_position = 720
+    max_width = 500
+    words = summary.split()
+    line = []
+
+    for word in words:
+        line.append(word)
+        test_line = ' '.join(line)
+
+        if pdf.stringWidth(test_line, "Helvetica", 12) > max_width:
+            line.pop()
+            pdf.drawString(72, y_position, ' '.join(line))
+            y_position -= 20
+            line = [word]
+
+            if y_position < 50:
+                pdf.showPage()
+                pdf.setFont("Helvetica", 12)
+                y_position = 750
+
+    if line:
+        pdf.drawString(72, y_position, ' '.join(line))
+
+    pdf.save()
+    buffer.seek(0)
+    return buffer
+
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+
+@app.route('/upload', methods=['POST'])
+def upload_pdf():
+    if 'pdf_file' not in request.files:
+        return jsonify({'error': 'No file uploaded'}), 400
+
+    file = request.files['pdf_file']
+
+    if file.filename == '':
+        return jsonify({'error': 'No file selected'}), 400
+
+    if not allowed_file(file.filename):
+        return jsonify({'error': 'Only PDF files are allowed'}), 400
+
+    try:
+        text = extract_text_from_pdf(file)
+
+        if not text.strip():
+            return jsonify({'error': 'Could not extract text from PDF. The PDF might be scanned or image-based.'}), 400
+
+        summary_ratio = float(request.form.get('summary_ratio', 0.3))
+        total_sentences = len(sent_tokenize(text))
+        num_sentences = max(3, int(total_sentences * summary_ratio))
+
+        summary = summarize_text(text, num_sentences)
+        stats = analyze_pdf_statistics(text)
+
+        original_words = len(word_tokenize(text))
+        summary_words = len(word_tokenize(summary))
+
+        compression_ratio = (
+            ((original_words - summary_words) / original_words) * 100
+            if original_words > 0 else 0
+        )
+
+        return jsonify({
+            'success': True,
+            'summary': summary,
+            'statistics': stats,
+            'compression_ratio': round(compression_ratio, 2),
+            'summary_length': summary_words,
+            'filename': secure_filename(file.filename)
+        })
+
+    except Exception as e:
+        return jsonify({'error': f'Error processing PDF: {str(e)}'}), 500
+
+
+@app.route('/download', methods=['POST'])
+def download_summary():
+    data = request.json
+    summary = data.get('summary', '')
+    filename = data.get('filename', 'summary.pdf')
+
+    if not summary:
+        return jsonify({'error': 'No summary to download'}), 400
+
+    try:
+        pdf_buffer = create_summary_pdf(summary, filename)
+
+        return send_file(
+            pdf_buffer,
+            as_attachment=True,
+            download_name=filename.replace('.pdf', '_summary.pdf'),
+            mimetype='application/pdf'
+        )
+
+    except Exception as e:
+        return jsonify({'error': f'Error creating PDF: {str(e)}'}), 500
+
+
+@app.route('/export', methods=['POST'])
+def export_summary():
+    data = request.json
+    summary = data.get('summary', '')
+
+    if not summary:
+        return jsonify({'error': 'No summary to export'}), 400
+
+    return send_file(
+        BytesIO(summary.encode()),
+        as_attachment=True,
+        download_name='summary.txt',
+        mimetype='text/plain'
+    )
+
+
+if __name__ == '__main__':
+    os.makedirs('uploads', exist_ok=True)
+    os.makedirs('templates', exist_ok=True)
+    os.makedirs('static', exist_ok=True)
+
+    print("Starting PDF Summarizer Server...")
+    print("Open your browser and navigate to: http://localhost:5000")
+
+    app.run(debug=True, host='0.0.0.0', port = 7860)