Text summarizer produces second half of exampe text rather than complete text summary in 2 sentences plus keywords. Where does the summary fail?Python

App.py runs and produces the spinner feature. However, it outputs the second half of the example wiki text file instead of producing a simple summary generated by the model.py script. App.py and model.py are two separate files. The intention was to produce a language model that uses statistics to produce a results summary. Where is the error?

# -------------------- App.py -------------------- import argparse # Input analysis (parsing) processed with grammar. import sys # System exit. import os # File path. import time # Timestamping. # Import (AI text summarization and load text file) functions from called upon modules. from .model import summarize_text from .utils import load_text # Spinner animation for longer operations. Heighten user experience, (UX). def spinner(): # Function to cycle through characters. while True: for frame in "|/-\\": yield frame # Define main CLI function as script runs. def main(): # Initialize parser (analysis) with description. parser = argparse.ArgumentParser( description="AI-powered text summarizer CLI tool" ) # Input the text file we want to consolidate. parser.add_argument( "input_file", type=str, help="Path to the text file you want to summarize" ) # Output text file naming. parser.add_argument( "-o", "--output", type=str, help="Optional output file to save the summary" ) # Allow for plenty of, (verbose), documentation of each step of process (ideal for teaching and auditing). parser.add_argument( "-v", "--verbose", action="store_true", help="Enable verbose mode for detailed logs" ) # Analyse the user argument. args = parser.parse_args() # Qualify input file. if not os.path.exists(args.input_file): print(f"Error: File not found: {args.input_file}") sys.exit(1) # Load and read text file. if args.verbose: print(f"[INFO] Loading file: {args.input_file}") text = load_text(args.input_file) # Prevent empty file summarization. if not text.strip(): print("Error: File is empty. Cannot summarize an empty text file.") sys.exit(1) # Show summarization is rendering if args.verbose: print("Generating summary...") # Display spinner. spin = spinner() for _ in range(10): sys.stdout.write(next(spin)) sys.stdout.flush() time.sleep(0.05) sys.stdout.write("\b") # Executive AI summarization. summary = summarize_text(text) # Print summary to console. print("\n=== SUMMARY RESULT ===\n") print(summary) # Save output to file if requested. if args.output: with open(args.output, "w", encoding="utf-8") as f: f.write(summary) print(f"\n Summary saved to: {args.output}") # Direct execution only. if __name__ == "__main__": main() # ------------------- Model.py ------------------- import re from collections import Counter def summarize_text(text): """ Lightweight extractive summarizer: - Extracts sentences - Computes keyword frequency - Selects best 1–2 sentences - Produces a clean, grammatical summary """ # --- 1. Split text into sentences --- sentences = [s.strip() for s in re.split(r'(?<=[.!?])\s+', text) if s.strip()] if not sentences: return "No usable sentences found in the text." # --- 2. Count word frequencies --- words = re.findall(r'\b\w+\b', text.lower()) word_counts = Counter(words) stopwords = { "the", "and", "of", "in", "to", "a", "is", "for", "on", "with", "as", "by", "an", "at", "that", "this", "it", "from", "be", "are" } keywords = [w for w, _ in word_counts.most_common(20) if w not in stopwords] if not keywords: keywords = list(word_counts.keys())[:10] # --- 3. Score each sentence --- def sentence_score(sentence): s_words = re.findall(r'\b\w+\b', sentence.lower()) return sum(word_counts.get(w, 0) for w in s_words if w in keywords) ranked = sorted(sentences, key=sentence_score, reverse=True) # --- 4. Take top 1–2 sentences --- best_sentences = ranked[:2] summary = " ".join(best_sentences) # --- 5. Fix spacing, ensure full sentences --- summary = summary.replace(" ", " ").strip() if not summary.endswith((".", "!", "?")): summary += "." # --- 6. Include missing core keywords in English form --- top_keywords = keywords[:5] missing = [k for k in top_keywords if k not in summary.lower()] if missing: if len(missing) == 1: summary += f" Key concept emphasized: {missing[0]}." else: summary += ( " Key concepts emphasized: " + ", ".join(missing[:-1]) + f", and {missing[-1]}." ) return summary

Thank you for your answers.