new update

app.py

@@ -8,40 +8,36 @@ from langdetect import detect
 # Load a summarization model
 summarizer = pipeline("summarization")
 
-def word_and_char_counter(text):
-    # Clean and split text into words and sentences
-    words = re.findall(r'\w+', text.lower())  # Remove punctuation and make lowercase
-    sentences = re.split(r'[.!?]+', text)  # Split text into sentences
-    num_sentences = len(sentences) - 1  # Adjusting for the last split being empty if text ends with a punctuation
+def text_analysis(text):
+    # Analyze text: word count, character count, language detection, and readability
+    words = re.findall(r'\w+', text.lower())
+    sentences = re.split(r'[.!?]+', text)
+    num_sentences = len(sentences) - 1
     num_words = len(words)
-    num_chars = len("".join(words))  # Count characters excluding spaces and punctuation
-
-    # Count the frequency of each word
-    word_freq = Counter(words)
-    most_common_words = word_freq.most_common(3)
-    unique_words = [word for word, count in word_freq.items() if count == 1]
-
-    # Calculate Flesch Reading Ease score
+    num_chars = len("".join(words))
     reading_ease = textstat.flesch_reading_ease(text)
-
-    # Detect language of the text
     language = detect(text)
 
-    # Generate summary of the text using the transformer model
-    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)[0]['summary_text']
-
     # Format the results
-    freq_results = ', '.join([f"'{word}': {count}" for word, count in most_common_words])
-    unique_words_result = ', '.join(unique_words)
-
-    return f"Language: {language}. {num_sentences} sentences, {num_words} words, {num_chars} characters. Most common words: {freq_results}. Unique words: {unique_words_result}. Readability (Flesch Reading Ease): {reading_ease:.2f}. Summary: {summary}"
+    return {
+        "Language": language,
+        "Sentences": num_sentences,
+        "Words": num_words,
+        "Characters": num_chars,
+        "Readability (Flesch Reading Ease)": reading_ease
+    }
+
+def text_summarization(text):
+    # Summarize text using the transformer model
+    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)[0]['summary_text']
+    return summary
 
-# Define your interface
+# Define your interface with two output components
 interface = gr.Interface(
-    fn=word_and_char_counter,
+    fn=[text_analysis, text_summarization],
     inputs=gr.Textbox(lines=4, placeholder="Type something here..."),
-    outputs="text",
-    title="Comprehensive Text Analysis with Language Detection",
+    outputs=[gr.JSON(label="Text Analysis"), "text"],
+    title="Comprehensive Text Analysis with Language Detection and Summarization",
     description="This app provides detailed analysis including language detection, sentence, word, and character counts, lists the most common and unique words, calculates readability, and provides a concise summary of the text."
 )