Update app.py via AI Editor

app.py

@@ -7,12 +7,14 @@ from io import BytesIO, StringIO
 import dash
 import dash_bootstrap_components as dbc
 from dash import html, dcc, Input, Output, State, callback_context, MATCH, ALL
+from dash.dash_table import DataTable
 from docx.shared import Pt
 from docx.enum.style import WD_STYLE_TYPE
 from PyPDF2 import PdfReader
 import openai
 import logging
 import threading
+import re
 
 logging.basicConfig(level=logging.INFO, format='%(asctime)s %(levelname)s %(message)s')
 
@@ -52,7 +54,6 @@ def get_right_col_content(selected_type):
         type="dot",
         children=[html.Div(id="loading-output")]
     ))
-    # Generate and Download buttons at the top
     controls.append(
         dbc.Row([
             dbc.Col(
@@ -68,7 +69,6 @@ def get_right_col_content(selected_type):
     )
     controls.append(html.Hr())
     controls.append(html.Div(id='document-preview', className="border p-3 mb-3"))
-    # Upload and radio only for non-shred
     if selected_type != "Shred":
         controls.append(html.Div([
             html.Label(f"Upload {selected_type} Document"),
@@ -102,7 +102,6 @@ def get_right_col_content(selected_type):
     return dbc.Card(dbc.CardBody(controls))
 
 def get_left_col_content():
-    # Chat card under doc-type buttons
     chat_card = dbc.Card(
         dbc.CardBody([
             html.H5("AI Chat", className="mb-2"),
@@ -334,7 +333,6 @@ def generate_any_doc(n_clicks_list, btn_ids, radio_values, upload_contents, uplo
     doc_type = btn_ids[idx]['index']
     document_type = doc_type
 
-    # SHRED CASE: Use uploaded_files directly, no radio or upload needed
     if doc_type == "Shred":
         if not uploaded_files:
             logging.info("No uploaded files for Shred. Aborting.")
@@ -406,13 +404,13 @@ def generate_any_doc(n_clicks_list, btn_ids, radio_values, upload_contents, uplo
         elif doc_type in ["Pink", "Red", "Gold"]:
             generated = generate_document(doc_type, [doc_content])
             current_document = generated
-            preview = dcc.Markdown(generated)
+            preview = narrative_preview(generated)
             logging.info(f"{doc_type} document generated.")
             return preview, f"{doc_type} generated"
         else:
             generated = generate_document(doc_type, [doc_content])
             current_document = generated
-            preview = dcc.Markdown(generated)
+            preview = narrative_preview(generated)
             logging.info(f"{doc_type} document generated.")
             return preview, f"{doc_type} generated"
     except Exception as e:
@@ -437,24 +435,41 @@ def update_uploaded_doc_name(contents, filename, id_dict):
 def spreadsheet_preview(text, doc_type=None):
     if doc_type is None:
         doc_type = ""
-    if doc_type in spreadsheet_types:
-        try:
-            df = pd.read_csv(StringIO(text))
-            table = dbc.Table.from_dataframe(df, striped=True, bordered=True, hover=True, size="sm")
-            return html.Div(table)
-        except Exception as e:
-            logging.error(f"Error parsing CSV for preview: {str(e)}")
-            return html.Div([
-                html.Div("Unable to display spreadsheet preview. Raw output:", style={'fontWeight': 'bold'}),
-                html.Pre(text, style={'whiteSpace': 'pre-wrap', 'fontFamily': 'monospace'})
-            ])
-    else:
-        try:
-            df = pd.read_csv(StringIO(text))
-            table = dbc.Table.from_dataframe(df, striped=True, bordered=True, hover=True, size="sm")
-            return html.Div(table)
-        except Exception:
-            return html.Pre(text, style={'whiteSpace': 'pre-wrap', 'fontFamily': 'monospace'})
+    try:
+        df = pd.read_csv(StringIO(text))
+        table = DataTable(
+            columns=[{"name": i, "id": i} for i in df.columns],
+            data=df.to_dict('records'),
+            style_table={'overflowX': 'auto', 'maxHeight': '500px', 'overflowY': 'auto'},
+            style_cell={'textAlign': 'left', 'whiteSpace': 'normal', 'height': 'auto', 'minWidth': '120px', 'maxWidth': '320px'},
+            page_size=15
+        )
+        return html.Div(table)
+    except Exception as e:
+        logging.error(f"Error parsing CSV for preview: {str(e)}")
+        return html.Div([
+            html.Div("Unable to display spreadsheet preview. Raw output:", style={'fontWeight': 'bold'}),
+            html.Pre(text, style={'whiteSpace': 'pre-wrap', 'fontFamily': 'monospace'})
+        ])
+
+def narrative_preview(text):
+    plain = strip_markdown(text)
+    return html.Pre(plain, style={'whiteSpace': 'pre-wrap', 'fontFamily': 'sans-serif'})
+
+def strip_markdown(text):
+    text = re.sub(r'(\*\*|__)(.*?)\1', r'\2', text)
+    text = re.sub(r'(\*|_)(.*?)\1', r'\2', text)
+    text = re.sub(r'`{1,3}[^`]*`{1,3}', '', text)
+    text = re.sub(r'^#+ ', '', text, flags=re.MULTILINE)
+    text = re.sub(r'^> ', '', text, flags=re.MULTILINE)
+    text = re.sub(r'!\[.*?\]\(.*?\)', '', text)
+    text = re.sub(r'\[([^\]]+)\]\([^)]+\)', r'\1', text)
+    text = re.sub(r'^\s*[-*+] ', '', text, flags=re.MULTILINE)
+    text = re.sub(r'^\s*\d+\.\s+', '', text, flags=re.MULTILINE)
+    text = text.replace('---', '')
+    text = text.replace('___', '')
+    text = text.replace('***', '')
+    return text.strip()
 
 def generate_document(document_type, file_contents):
     if document_type in spreadsheet_types:
@@ -548,7 +563,7 @@ Now, provide the updated {selected_doc_type}:
         if selected_doc_type in spreadsheet_types:
             preview = spreadsheet_preview(current_document, selected_doc_type)
         else:
-            preview = dcc.Markdown(current_document)
+            preview = narrative_preview(current_document)
         return f"Document updated based on: {chat_input}", preview
     except Exception as e:
         logging.error(f"Error updating document via chat: {str(e)}")
@@ -579,8 +594,10 @@ def download_document(n_clicks, selected_doc_type):
             return dcc.send_string(f"Error downloading {selected_doc_type}: {str(e)}", f"{selected_doc_type}_error.txt")
     else:
         try:
+            plain = strip_markdown(current_document)
             doc = Document()
-            doc.add_paragraph(current_document)
+            for para in plain.split('\n'):
+                doc.add_paragraph(para)
             output = BytesIO()
             doc.save(output)
             logging.info(f"{selected_doc_type} document downloaded as Word.")