Update app.py

app.py

@@ -12,8 +12,6 @@ from pygments.formatters import HtmlFormatter
 from pygments.styles import get_all_styles
 
 app = Flask(__name__)
-
-# Corrected line to use the universally writable /tmp directory
 TEMP_DIR = "/tmp/markdown_temp"
 os.makedirs(TEMP_DIR, exist_ok=True)
 
@@ -24,7 +22,7 @@ def parse_repo2markdown(text):
     if first_match:
         intro_text = text[:first_match.start()].strip()
         if intro_text:
-            components.append({'type': 'intro', 'filename': 'Introduction', 'content': intro_text, 'is_code_block': False, 'language': ''})
+            components.append({'type': 'intro', 'filename': 'Introduction', 'content': intro_text})
     for match in pattern.finditer(text):
         filename = match.group(1).strip()
         raw_content = match.group(2).strip()
@@ -32,15 +30,14 @@ def parse_repo2markdown(text):
         if code_match:
             components.append({'type': 'file', 'filename': filename, 'content': code_match.group(2).strip(), 'is_code_block': True, 'language': code_match.group(1)})
         else:
-            components.append({'type': 'file', 'filename': filename, 'content': raw_content, 'is_code_block': False, 'language': ''})
+            components.append({'type': 'file', 'filename': filename, 'content': raw_content, 'is_code_block': False})
     return components
 
 def parse_standard_readme(text):
     components = []
     parts = re.split(r'^(## .*?)$', text, flags=re.MULTILINE)
-    intro_content = parts[0].strip()
-    if intro_content:
-        components.append({'type': 'intro', 'filename': 'Introduction', 'content': intro_content})
+    if parts[0].strip():
+        components.append({'type': 'intro', 'filename': 'Header', 'content': parts[0].strip()})
     for i in range(1, len(parts), 2):
         components.append({'type': 'section', 'filename': parts[i].replace('##', '').strip(), 'content': parts[i+1].strip()})
     return components
@@ -48,47 +45,63 @@ def parse_standard_readme(text):
 def parse_changelog(text):
     components = []
     parts = re.split(r'^(## \[\d+\.\d+\.\d+.*?\].*?)$', text, flags=re.MULTILINE)
-    intro_content = parts[0].strip()
-    if intro_content:
-        components.append({'type': 'intro', 'filename': 'Changelog Header', 'content': intro_content})
+    if parts[0].strip():
+        components.append({'type': 'intro', 'filename': 'Changelog Header', 'content': parts[0].strip()})
     for i in range(1, len(parts), 2):
         components.append({'type': 'version', 'filename': parts[i].replace('##', '').strip(), 'content': parts[i+1].strip()})
     return components
 
 def parse_agent_action(text):
     components = []
-    
-    # Extract Actions
     action_pattern = re.compile(r'^### HF_ACTION: (.*)$', re.MULTILINE)
     for match in action_pattern.finditer(text):
         components.append({'type': 'action', 'filename': 'Agent Command', 'content': match.group(1).strip()})
-    
-    # Extract File Structure
-    structure_match = re.search(r'## File Structure\n(```[\s\S]*?```)', text)
-    if structure_match:
-        components.append({'type': 'structure', 'filename': 'Project Structure', 'content': structure_match.group(1).strip()})
-        
-    # Extract Files (using the existing logic from Repo2Markdown)
     file_pattern = re.compile(r'### File: (.*?)\n([\s\S]*?)(?=\n### File:|\n## File Structure|\n### HF_ACTION:|\Z)', re.MULTILINE)
     for match in file_pattern.finditer(text):
-        filename = match.group(1).strip()
-        content = match.group(2).strip()
-        is_code = "```" in content
-        components.append({'type': 'file', 'filename': filename, 'content': content, 'is_code_block': is_code})
-
-    # Instructions (Everything else)
-    if not components:
-        components.append({'type': 'instruction', 'filename': 'Instructions', 'content': text})
-        
+        components.append({'type': 'file', 'filename': match.group(1).strip(), 'content': match.group(2).strip()})
+    struct_match = re.search(r'## File Structure\n(```[\s\S]*?```)', text)
+    if struct_match:
+        components.append({'type': 'structure', 'filename': 'File Structure', 'content': struct_match.group(1).strip()})
     return components
 
+def build_full_html(markdown_text, styles, include_fontawesome):
+    wrapper_id = "#output-wrapper"
+    font_family = styles.get('font_family', "'Inter', sans-serif")
+    google_font_name = font_family.split(',')[0].strip("'\"")
+    google_font_link = f'<link href="https://fonts.googleapis.com/css2?family={google_font_name.replace(" ", "+")}:wght@400;700&display=swap" rel="stylesheet">'
+    
+    highlight_theme = styles.get('highlight_theme', 'monokai')
+    pygments_css = ""
+    if highlight_theme != 'none':
+        formatter = HtmlFormatter(style=highlight_theme, cssclass="codehilite")
+        pygments_css = formatter.get_style_defs(f' {wrapper_id}')
+
+    scoped_css = f"""
+        body {{ background-color: {styles.get('background_color', '#ffffff')}; margin: 0; padding: 0; }}
+        {wrapper_id} {{
+            font-family: {font_family};
+            font-size: {styles.get('font_size', '16')}px;
+            line-height: {styles.get('line_height', '1.6')};
+            color: {styles.get('text_color', '#333')};
+            background-color: {styles.get('background_color', '#fff')};
+            padding: {styles.get('page_padding', '40')}px;
+        }}
+        {wrapper_id} table {{ border-collapse: collapse; width: 100%; margin-bottom: 1em; }}
+        {wrapper_id} th, {wrapper_id} td {{ border: 1px solid #ddd; padding: 12px; text-align: left; }}
+        {wrapper_id} pre {{ padding: {styles.get('code_padding', '15')}px; border-radius: 8px; overflow-x: auto; }}
+        {wrapper_id} h1, {wrapper_id} h2, {wrapper_id} h3 {{ border-bottom: 1px solid #eee; padding-bottom: 5px; }}
+        {pygments_css}
+        {styles.get('custom_css', '')}
+    """
+    html_content = markdown.markdown(markdown_text, extensions=['fenced_code', 'tables', 'codehilite', 'nl2br'])
+    fa = '<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.5.1/css/all.min.css">' if include_fontawesome else ""
+    return f"<!DOCTYPE html><html><head><meta charset='UTF-8'>{google_font_link}{fa}<style>{scoped_css}</style></head><body><div id='output-wrapper'>{html_content}</div></body></html>"
+
 @app.route('/parse', methods=['POST'])
 def parse_endpoint():
     text = request.form.get('markdown_text', '')
     if 'markdown_file' in request.files and request.files['markdown_file'].filename != '':
         text = request.files['markdown_file'].read().decode('utf-8')
-    if not text: return jsonify({'error': 'No text or file provided.'}), 400
-    
     try:
         if "### HF_ACTION:" in text or "File and Code Formatting:" in text:
             format_name, components = "Agent Action", parse_agent_action(text)
@@ -100,79 +113,25 @@ def parse_endpoint():
             format_name, components = "Standard README", parse_standard_readme(text)
         else:
             format_name, components = "Unknown", [{'type': 'text', 'filename': 'Full Text', 'content': text}]
-            
         return jsonify({'format': format_name, 'components': components})
     except Exception as e:
-        return jsonify({'error': f'Failed to parse: {e}'}), 500
-
-def build_full_html(markdown_text, styles, include_fontawesome):
-    wrapper_id = "#output-wrapper"
-    font_family = styles.get('font_family', "'Arial', sans-serif")
-    google_font_name = font_family.split(',')[0].strip("'\"")
-    google_font_link = ""
-    if " " in google_font_name and google_font_name not in ["Times New Roman", "Courier New"]:
-        google_font_link = f'<link href="https://fonts.googleapis.com/css2?family={google_font_name.replace(" ", "+")}:wght@400;700&display=swap" rel="stylesheet">'
-    
-    highlight_theme = styles.get('highlight_theme', 'default')
-    pygments_css = ""
-    if highlight_theme != 'none':
-        formatter = HtmlFormatter(style=highlight_theme, cssclass="codehilite")
-        pygments_css = formatter.get_style_defs(f' {wrapper_id}')
-    
-    scoped_css = f"""
-        {wrapper_id} {{
-            font-family: {font_family}; font-size: {styles.get('font_size', '16')}px;
-            color: {styles.get('text_color', '#333')}; background-color: {styles.get('background_color', '#fff')};
-        }}
-        {wrapper_id} table {{ border-collapse: collapse; width: 100%; }}
-        {wrapper_id} th, {wrapper_id} td {{ border: 1px solid #ddd; padding: 8px; text-align: left; }}
-        {wrapper_id} th {{ background-color: #f2f2f2; }}
-        {wrapper_id} img {{ max-width: 100%; height: auto; }}
-        {wrapper_id} pre {{ padding: {styles.get('code_padding', '15')}px; border-radius: 5px; white-space: pre-wrap; word-wrap: break-word; }}
-        {wrapper_id} h1, {wrapper_id} h2, {wrapper_id} h3 {{ border-bottom: 1px solid #eee; padding-bottom: 5px; margin-top: 1.5em; }}
-        {wrapper_id} :not(pre) > code {{ font-family: 'Courier New', monospace; background-color: #eef; padding: .2em .4em; border-radius: 3px; }}
-        {pygments_css} {styles.get('custom_css', '')}
-    """
-    
-    md_extensions = ['fenced_code', 'tables', 'codehilite']
-    html_content = markdown.markdown(markdown_text, extensions=md_extensions, extension_configs={'codehilite': {'css_class': 'codehilite'}})
-    final_html_body = f'<div id="output-wrapper">{html_content}</div>'
-    
-    fontawesome_link = '<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.5.1/css/all.min.css">' if include_fontawesome else ""
-    
-    full_html = f"""<!DOCTYPE html>
-    <html><head><meta charset="UTF-8">{google_font_link}{fontawesome_link}<style>
-    #ouput-wrapper {{ background-color: {styles.get('background_color', '#fff')}; padding: 25px; display: inline-block;}}
-    {scoped_css}
-    </style></head><body>{final_html_body}</body></html>"""
-    
-    return full_html
+        return jsonify({'error': str(e)}), 500
 
 @app.route('/convert', methods=['POST'])
 def convert_endpoint():
     data = request.json
     try:
-        full_html = build_full_html(
-            markdown_text=data.get('markdown_text', ''),
-            styles=data.get('styles', {}),
-            include_fontawesome=data.get('include_fontawesome', False)
-        )
-        options = {"quiet": "", 'encoding': "UTF-8"}
-        
+        full_html = build_full_html(data.get('markdown_text', ''), data.get('styles', {}), data.get('include_fontawesome', False))
+        options = {"quiet": "", "encoding": "UTF-8", "width": 1024, "disable-smart-width": ""}
         if data.get('download', False):
-            download_type = data.get('download_type', 'png')
-            if download_type == 'html':
+            if data.get('download_type') == 'html':
                 return send_file(BytesIO(full_html.encode("utf-8")), as_attachment=True, download_name="output.html", mimetype="text/html")
-            else:
-                png_bytes = imgkit.from_string(full_html, False, options=options)
-                return send_file(BytesIO(png_bytes), as_attachment=True, download_name="output.png", mimetype="image/png")
-        else:
             png_bytes = imgkit.from_string(full_html, False, options=options)
-            png_base64 = base64.b64encode(png_bytes).decode('utf-8')
-            return jsonify({'preview_html': full_html, 'preview_png_base64': png_base64})
+            return send_file(BytesIO(png_bytes), as_attachment=True, download_name="output.png", mimetype="image/png")
+        png_bytes = imgkit.from_string(full_html, False, options=options)
+        return jsonify({'preview_html': full_html, 'preview_png_base64': base64.b64encode(png_bytes).decode('utf-8')})
     except Exception as e:
-        traceback.print_exc()
-        return jsonify({'error': f'Failed to convert content: {str(e)}'}), 500
+        return jsonify({'error': str(e)}), 500
 
 @app.route('/')
 def index():