handle bytes extra

compressedContentViewer.py

@@ -4,6 +4,7 @@ import xml.sax.saxutils
 import html
 import io
 import xml.dom.minidom
+from wechatlog.adaptors.pywxdumpAdapter import decode_bytes_extra
 
 # Initialize Panel with Bootstrap design
 pn.extension(design="bootstrap", sizing_mode="stretch_width")
@@ -14,38 +15,44 @@ ICON_URLS = {
     "message-circle": "https://discourse.holoviz.org/",
 }
 
-# Create a function to decompress using the working method from binary_to_text.py
-
-
-def decompress_CompressContent(data):
+def process_content(data):
     """
-    解压缩Msg：CompressContent内容
-    :param data:
-    :return:
+    Process both CompressContent and BytesExtra content.
+    First tries to decompress (for CompressContent), if fails treats as BytesExtra.
+    :param data: bytes data to process
+    :return: tuple (decoded_string, content_type, error_message)
     """
     if data is None or not isinstance(data, bytes):
-        return ""
+        return "", "unknown", "Invalid input: data must be bytes"
+    
+    # First try to decompress (assuming it's CompressContent)
     try:
         dst = lz4.block.decompress(data, uncompressed_size=len(data) << 10)
         decoded_string = dst.decode().replace("\x00", "")  # Remove any null characters
-    except Exception as e:
-        return f"Decompression failed: {str(e)}"
-    return decoded_string
-
-# Function to unescape XML using proper XML tools
-
+        return decoded_string, "CompressContent", None
+    except Exception:  # If decompression fails, try BytesExtra
+        try:
+            # Try to decode as BytesExtra
+            decoded_dict = decode_bytes_extra(data)
+            if isinstance(decoded_dict, dict):
+                # Convert dictionary to a formatted string representation
+                decoded_string = "{\n"
+                for key, value in decoded_dict.items():
+                    decoded_string += f"  {key}: {value}\n"
+                decoded_string += "}"
+                return decoded_string, "BytesExtra", None
+            else:
+                return "", "unknown", "BytesExtra decoding did not return a dictionary"
+        except Exception as decode_error:
+            return "", "unknown", f"Failed to process content: {str(decode_error)}"
 
 def unescape_xml(text):
     # First handle standard XML entities
     text = xml.sax.saxutils.unescape(text)
-
     # Then handle HTML entities that might be present
     text = html.unescape(text)
-
     return text
 
-
-# Function to format XML with proper indentation using lxml
 def format_xml(xml_string):
     try:
         # Parse the XML string
@@ -56,7 +63,6 @@ def format_xml(xml_string):
         # If parsing fails, return the original string with the error
         return f"XML formatting error: {str(e)}\n\nOriginal XML:\n{xml_string}"
 
-
 # Create the UI with modern styling
 file_input = pn.widgets.FileInput(
     accept='.bin',
@@ -64,8 +70,13 @@ file_input = pn.widgets.FileInput(
     sizing_mode="stretch_width"
 )
 
+content_type_indicator = pn.widgets.StaticText(
+    value="",
+    align="center"
+)
+
 status = pn.widgets.StaticText(
-    value="##### 📁 Upload a .bin file to see its decompressed XML content",
+    value="##### 📁 Upload a .bin file to view its content",
     align="center"
 )
 
@@ -86,19 +97,15 @@ unescape_checkbox = pn.widgets.Checkbox(
     margin=(10, 10)
 )
 
-# Function to get the XML content for download
-
-
 def get_xml_content():
     if processed_xml:
         return io.StringIO(processed_xml)
     return None
 
-
 # Modern styled download button
 download_button = pn.widgets.FileDownload(
     callback=get_xml_content,
-    filename="decompressed.xml",
+    filename="content.xml",
     button_type="primary",
     label="📥 Download XML",
     disabled=True,
@@ -109,65 +116,69 @@ download_button = pn.widgets.FileDownload(
 # Global variable to store the processed XML
 processed_xml = None
 
-# Connect the function to the file input
-
-
 def process_file(event):
     global processed_xml
     if event.new is not None:
         status.value = "##### ⚙️ Processing file..."
+        content_type_indicator.value = ""
+        
         try:
-            # Use the working decompression method
-            xml_string = decompress_CompressContent(event.new)
-
-            if xml_string and not xml_string.startswith("Decompression failed"):
-                # Try to format as XML
-                try:
-                    # Unescape XML entities if checkbox is checked
-                    if unescape_checkbox.value:
-                        xml_string = unescape_xml(xml_string)
-
-                    # Format XML with proper indentation using lxml
-                    pretty_xml = format_xml(xml_string)
-
-                    result_area.value = pretty_xml
-                    processed_xml = pretty_xml
-
-                    # Update the download filename based on the input file
-                    if hasattr(file_input, 'filename') and file_input.filename:
-                        base_name = file_input.filename.rsplit('.', 1)[0]
-                        download_button.filename = f"{base_name}.xml"
-
-                    status.value = "##### ✅ File processed successfully!"
-                    download_button.disabled = False
-                except Exception as xml_error:
-                    # If XML parsing fails, just show the raw text
-                    result_area.value = xml_string
-                    processed_xml = xml_string
-                    status.value = f"##### ⚠️ Decompressed, but XML parsing failed: {str(xml_error)}"
-                    download_button.disabled = False
+            # Process the content (either CompressContent or BytesExtra)
+            content, content_type, error = process_content(event.new)
+            
+            if error:
+                status.value = f"##### ❌ {error}"
+                result_area.value = ""
+                content_type_indicator.value = ""
+                download_button.disabled = True
+                processed_xml = None
+                return
+                
+            # Update content type indicator with icon
+            icon = "🗜️" if content_type == "CompressContent" else "📄"
+            content_type_indicator.value = f"##### {icon} Detected type: {content_type}"
+
+            if content:
+                if content_type == "CompressContent":
+                    try:
+                        # Unescape XML entities if checkbox is checked
+                        if unescape_checkbox.value:
+                            content = unescape_xml(content)
+
+                        # Format XML with proper indentation
+                        pretty_content = format_xml(content)
+                        result_area.value = pretty_content
+                        processed_xml = pretty_content
+                        download_button.filename = f"{file_input.filename.rsplit('.', 1)[0]}_xml.xml"
+                    except Exception as xml_error:
+                        result_area.value = content
+                        processed_xml = content
+                        status.value = f"##### ⚠️ Content extracted, but XML formatting failed: {str(xml_error)}"
+                else:  # BytesExtra
+                    result_area.value = content
+                    processed_xml = content
+                    download_button.filename = f"{file_input.filename.rsplit('.', 1)[0]}_dict.txt"
+
+                status.value = "##### ✅ Content processed successfully!"
+                download_button.disabled = False
             else:
-                result_area.value = xml_string
-                status.value = "##### ❌ Decompression failed"
+                status.value = "##### ❌ Processing failed"
+                result_area.value = ""
                 download_button.disabled = True
                 processed_xml = None
         except Exception as e:
             status.value = f"##### ❌ Error: {str(e)}"
             result_area.value = ""
+            content_type_indicator.value = ""
             download_button.disabled = True
             processed_xml = None
 
-
 file_input.param.watch(process_file, 'value')
 
-# Add a callback for the checkbox to reprocess the current file when toggled
-
-
 def toggle_unescape(event):
     if file_input.value is not None:
         process_file(pn.param.ParamEvent(obj=file_input, name='value', old=None, new=file_input.value))
 
-
 unescape_checkbox.param.watch(toggle_unescape, 'value')
 
 # Add footer with social links
@@ -183,13 +194,14 @@ main = pn.WidgetBox(
     pn.Column(
         pn.pane.Markdown("##### 📁 Drop your .bin file here or click to upload"),
         file_input,
+        content_type_indicator,
         pn.Row(
             unescape_checkbox,
             download_button,
             align="center"
         ),
         status,
-        pn.pane.Markdown("##### 📄 Decompressed XML Content"),
+        pn.pane.Markdown("##### 📄 Content Preview"),
         result_area,
         footer_row,
         sizing_mode="stretch_width"
@@ -197,7 +209,7 @@ main = pn.WidgetBox(
 )
 
 # Create the template
-title = "Compressed Content Viewer"
+title = "Content Viewer"
 template = pn.template.BootstrapTemplate(
     title=title,
     main=main,