Update app.py

app.py

@@ -98,9 +98,9 @@ def categorize_frames(frame_list):
     sorted_frames = sorted(frame_counter.items(), key=lambda x: x[1], reverse=True)
     
     for i, (frame, count) in enumerate(sorted_frames):
-        if i == 0:  # Highest frequency frame
+        if i == 0:  
             categorized_frames["Major Focus"].append(frame)
-        elif i < 3:  # Top 3 most mentioned frames
+        elif i < 3:  
             categorized_frames["Significant Focus"].append(frame)
         else:
             categorized_frames["Minor Mention"].append(frame)
@@ -143,39 +143,40 @@ def extract_metadata_from_excel(excel_file):
         logging.error(f"Error processing Excel file: {e}")
         return []
 
-# Merge metadata with generated analysis
-def merge_metadata_with_generated_data(generated_data, excel_metadata):
-    for post_data in excel_metadata:
-        post_number = f"Post {post_data.get('Post Number', len(generated_data) + 1)}"
-        if post_number in generated_data:
-            generated_data[post_number].update(post_data)
-        else:
-            generated_data[post_number] = post_data  
-    return generated_data
-
-# Create DOCX file matching the uploaded format
+# Create DOCX file in the required format
 def create_docx_from_data(extracted_data):
     doc = Document()
 
-    for post_number, data in extracted_data.items():
-        doc.add_heading(post_number, level=1)
+    for index, data in enumerate(extracted_data, start=1):
+        doc.add_heading(f"Sr No {index}:", level=1)
 
-        ordered_keys = [
-            "Post Number", "Date of Post", "Media Type", "Number of Pictures",
-            "Number of Videos", "Number of Audios", "Likes", "Comments", "Tagged Audience",
-            "Full Caption", "Language", "Tone", "Hashtags", "Frames"
+        metadata_fields = [
+            "Date of Post", "Media Type", "Number of Pictures", "Number of Videos",
+            "Number of Audios", "Likes", "Comments", "Tagged Audience"
         ]
 
-        for key in ordered_keys:
-            value = data.get(key, "N/A")
+        for field in metadata_fields:
+            value = data.get(field, "N/A")
+            doc.add_paragraph(f"**{field}:** {value}")
+
+        caption_text = data.get("Full Caption", "N/A")
+        doc.add_paragraph(f"**Caption:** {caption_text}")
+
+        language = data.get("Language", "N/A")
+        doc.add_paragraph(f"**Language:** {language}")
+
+        tone = ", ".join(data.get("Tone", ["N/A"]))
+        doc.add_paragraph(f"**Tone:** {tone}")
+
+        hashtags = ", ".join(data.get("Hashtags", []))
+        doc.add_paragraph(f"**Hashtags:** {hashtags}")
 
-            if key in ["Tone", "Hashtags"]:
-                value = ", ".join(value) if isinstance(value, list) else value
-            elif key == "Frames" and isinstance(value, dict):
-                frame_text = "\n".join([f"  {category}: {', '.join(frames)}" for category, frames in value.items() if frames])
-                value = f"\n{frame_text}" if frame_text else "N/A"
+        frames = data.get("Frames", {})
+        doc.add_paragraph("**Frames:**")
 
-            doc.add_paragraph(f"**{key}:** {value}")
+        for category, frame_list in frames.items():
+            if frame_list:
+                doc.add_paragraph(f"  {category}: {', '.join(frame_list)}")
 
         doc.add_paragraph("\n")
 
@@ -190,31 +191,32 @@ input_text = st.text_area("Input Text", height=200)
 uploaded_docx = st.file_uploader("Upload a DOCX file", type=["docx"])
 uploaded_excel = st.file_uploader("Upload an Excel file", type=["xlsx"])
 
-output_data = {}
+output_data = []
+
+if uploaded_excel:
+    output_data = extract_metadata_from_excel(uploaded_excel)
 
 if input_text:
-    output_data["Manual Input"] = {
+    text_analysis = {
         "Full Caption": input_text,
         "Language": detect_language(input_text),
         "Tone": extract_tone(input_text),
         "Hashtags": extract_hashtags(input_text),
         "Frames": extract_frames_fallback(input_text),
     }
+    output_data.append(text_analysis)
 
 if uploaded_docx:
     captions = extract_captions_from_docx(uploaded_docx)
     for caption, text in captions.items():
-        output_data[caption] = {
+        text_analysis = {
             "Full Caption": text,
             "Language": detect_language(text),
             "Tone": extract_tone(text),
             "Hashtags": extract_hashtags(text),
             "Frames": extract_frames_fallback(text),
         }
-
-if uploaded_excel:
-    excel_metadata = extract_metadata_from_excel(uploaded_excel)
-    output_data = merge_metadata_with_generated_data(output_data, excel_metadata)
+        output_data.append(text_analysis)
 
 if output_data:
     docx_output = create_docx_from_data(output_data)
@@ -222,4 +224,3 @@ if output_data:
     docx_output.save(docx_io)
     docx_io.seek(0)
     st.download_button("Download Merged Analysis as DOCX", data=docx_io, file_name="merged_analysis.docx")
-