Update app.py via AI Editor

app.py

@@ -463,15 +463,7 @@ def update_uploaded_doc_name(contents, filename, id_dict):
         return filename, contents, "uploaded"
     return "", None, "loaded"
 
-def markdown_table_preview(md_text):
-    # Always use dcc.Markdown to render markdown tables, which supports tables natively
-    return dcc.Markdown(md_text, dangerously_allow_html=True, style={'whiteSpace': 'pre-wrap', 'fontFamily': 'monospace', 'overflowX': 'auto'})
-
-def markdown_narrative_preview(md_text):
-    return html.Div(dcc.Markdown(md_text, dangerously_allow_html=True, style={'whiteSpace': 'pre-wrap', 'fontFamily': 'sans-serif'}))
-
 def extract_markdown_tables(md_text):
-    # Extract all markdown tables from md_text as list of strings
     tables = []
     lines = md_text.split('\n')
     in_table = False
@@ -492,12 +484,10 @@ def extract_markdown_tables(md_text):
     return tables
 
 def markdown_table_to_df(md_table):
-    # Convert a single markdown table string to pandas DataFrame
     lines = [line.strip() for line in md_table.split('\n') if line.strip()]
     if len(lines) < 2:
         return None
     header = [h.strip() for h in lines[0].strip('|').split('|')]
-    # Find the first line with at least 3 dashes, that's the separator
     sep_idx = 1
     while sep_idx < len(lines) and not re.match(r'^\|\s*:?-+:?\s*(\|\s*:?-+:?\s*)+\|?$', lines[sep_idx]):
         sep_idx += 1
@@ -507,7 +497,6 @@ def markdown_table_to_df(md_table):
         if not row.strip() or not row.strip().startswith('|'):
             continue
         cells = [c.strip() for c in row.strip('|').split('|')]
-        # Pad or trim cells to header length
         if len(cells) < len(header):
             cells += [''] * (len(header) - len(cells))
         elif len(cells) > len(header):
@@ -516,6 +505,32 @@ def markdown_table_to_df(md_table):
     df = pd.DataFrame(rows, columns=header)
     return df
 
+def markdown_table_preview(md_text):
+    tables = extract_markdown_tables(md_text)
+    if not tables:
+        return html.Div("No table found.")
+    table_divs = []
+    for i, table in enumerate(tables):
+        df = markdown_table_to_df(table)
+        if df is not None and not df.empty:
+            table_divs.append(
+                html.Div([
+                    DataTable(
+                        columns=[{"name": str(col), "id": str(col)} for col in df.columns],
+                        data=df.to_dict('records'),
+                        style_table={'overflowX': 'auto'},
+                        style_cell={'whiteSpace': 'normal', 'height': 'auto', 'textAlign': 'left', 'fontFamily': 'monospace', 'fontSize': '14px', 'maxWidth': '400px', 'minWidth': '80px', 'wordBreak': 'break-word'},
+                        style_header={'fontWeight': 'bold'},
+                        page_size=100,
+                        id={'type': 'datatable-preview', 'index': i}
+                    )
+                ], className="mb-4")
+            )
+    return html.Div(table_divs)
+
+def markdown_narrative_preview(md_text):
+    return html.Div(dcc.Markdown(md_text, dangerously_allow_html=True, style={'whiteSpace': 'pre-wrap', 'fontFamily': 'sans-serif'}))
+
 def markdown_tables_to_xlsx(md_text):
     tables = extract_markdown_tables(md_text)
     output = BytesIO()
@@ -659,7 +674,6 @@ def download_document(n_clicks, selected_doc_type):
 
     if selected_doc_type in spreadsheet_types:
         try:
-            # Convert markdown tables to xlsx
             xlsx_bytes = markdown_tables_to_xlsx(current_document)
             logging.info(f"{selected_doc_type} document downloaded as Excel.")
             return dcc.send_bytes(xlsx_bytes.read(), f"{selected_doc_type}.xlsx")