Refactor app.py for improved response handling and formatting; update extract_text.py and math_summarizer.py for consistent string encoding

app.py

@@ -4,15 +4,16 @@ import json
 
 def rexplore_summarizer(url, id, access_key):
     response = json.loads(main(url, id, access_key))
+    data = json.dumps(response, indent=4, ensure_ascii=False)
     if response["mindmap_status"] != "success":
-        mindmap = "Error generating Mindmap"
+        mindmap = "error"
     else:
         mindmap = response["mindmap"]
     if response["summary_status"] != "success":
-        summary = "Error generating Summary"
+        summary = "error"
     else:
         summary = response["summary"]
-    return response, summary, mindmap
+    return data, summary, mindmap
 
 def clear_everything(url, id, access_key, raw_data, summary, mindmap):
     return None, None, None, None, None, None
@@ -22,29 +23,29 @@ theme = gr.themes.Soft(
     secondary_hue="cyan",
     neutral_hue="slate",
     font=[
-        gr.themes.GoogleFont('Syne'), 
-        gr.themes.GoogleFont('Poppins'), 
-        gr.themes.GoogleFont('Poppins'), 
-        gr.themes.GoogleFont('Poppins')
+        gr.themes.GoogleFont("Syne"), 
+        gr.themes.GoogleFont("Poppins"), 
+        gr.themes.GoogleFont("Poppins"), 
+        gr.themes.GoogleFont("Poppins")
     ],
 )
 
 with gr.Blocks(theme=theme, title="ReXplore Summarizer", fill_height=True) as app:
     gr.HTML(
-        value ='''
-        <h1 style="text-align: center;">ReXplore Summarizer <p style="text-align: center;">Designed and Developed by <a href='https://raannakasturi.eu.org' target="_blank" rel="nofollow noreferrer external">Nayan Kasturi</a></p> </h1>
+        value ="""
+        <h1 style="text-align: center;">ReXplore Summarizer <p style="text-align: center;">Designed and Developed by <a href="https://raannakasturi.eu.org" target="_blank" rel="nofollow noreferrer external">Nayan Kasturi</a></p> </h1>
         <p style="text-align: center;">This app uses a hybrid approach to summarize PDF documents based on CPU as well as GPU.</p>
         <p style="text-align: center;">The app uses traditional methodologies such as TextRank, LSA, Luhn algorithms as well as large language model (LLM) to generate summaries as well as mindmaps.</p>
         <p style="text-align: center;">The summarization process can take some time depending on the size of the text corpus and the complexity of the content.</p>
-        ''')
+        """)
     with gr.Row():
         with gr.Column():
             url = gr.Textbox(label="PDF URL", placeholder="Paste the PDF URL here")
             id = gr.Textbox(label="DOI/arXiv ID", placeholder="Enter the DOI or arXiv ID of the document")
-            access_key = gr.Textbox(label="Access Key", placeholder="Enter the Access Key", type='password')
+            access_key = gr.Textbox(label="Access Key", placeholder="Enter the Access Key", type="password")
             with gr.Row():
-                clear_btn = gr.Button(value="Clear", variant='stop')
-                summarize_btn = gr.Button(value="Summarize", variant='primary')
+                clear_btn = gr.Button(value="Clear", variant="stop")
+                summarize_btn = gr.Button(value="Summarize", variant="primary")
         raw_data = gr.TextArea(label="Raw Data", placeholder="The generated raw data will be displayed here", lines=7, interactive=False, show_copy_button=True)
     with gr.Row():
         summary = gr.TextArea(label="Summary", placeholder="The generated summary will be displayed here", lines=7, interactive=False, show_copy_button=True)

extract_text.py

@@ -10,7 +10,7 @@ def download_pdf(url, id):
     try:
         response = requests.get(url)
         response.raise_for_status()  # Raise an error for bad responses
-        with open(file_path, 'wb') as file:
+        with open(file_path, "wb") as file:
             file.write(response.content)
     except Exception as e:
         print(f"Error downloading PDF: {e}")

math_summarizer.py

@@ -19,8 +19,8 @@ def generate_luhn_summary(research_paper_text):
 
 def sanitize_text(input_string):
     try:
-        encoded_bytes = input_string.encode('utf-8')
-        decoded_string = encoded_bytes.decode('utf-8')
+        encoded_bytes = input_string.encode("utf-8")
+        decoded_string = encoded_bytes.decode("utf-8")
         return decoded_string
     except UnicodeEncodeError as e:
         print(f"Encoding error: {e}")