[Python] Text summarizer produces second half of exampe text rather than complete text summary...

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.

Continue reading...