Merge pull request #3 from overcuriousity/claude/fix-umlaut-support-01NVHwQkPasDs5ZPySfRqZgE

Fix UTF-8/umlaut support in note input

trace/cli.py

@@ -69,7 +69,7 @@ def export_markdown(output_file: str = "export.md"):
     try:
         storage = Storage()
 
-        with open(output_file, "w") as f:
+        with open(output_file, "w", encoding='utf-8') as f:
             f.write("# Forensic Notes Export\n\n")
             f.write(f"Generated on: {time.ctime()}\n\n")
 

trace/storage.py

@@ -166,7 +166,7 @@ Attachment: invoice.pdf.exe (double extension trick) #email-forensics #phishing-
         if not self.data_file.exists():
             return []
         try:
-            with open(self.data_file, 'r') as f:
+            with open(self.data_file, 'r', encoding='utf-8') as f:
                 data = json.load(f)
                 return [Case.from_dict(c) for c in data]
         except (json.JSONDecodeError, IOError):
@@ -176,8 +176,8 @@ Attachment: invoice.pdf.exe (double extension trick) #email-forensics #phishing-
         data = [c.to_dict() for c in self.cases]
         # Write to temp file then rename for atomic-ish write
         temp_file = self.data_file.with_suffix(".tmp")
-        with open(temp_file, 'w') as f:
-            json.dump(data, f, indent=2)
+        with open(temp_file, 'w', encoding='utf-8') as f:
+            json.dump(data, f, indent=2, ensure_ascii=False)
         temp_file.replace(self.data_file)
 
     def add_case(self, case: Case):
@@ -225,15 +225,15 @@ class StateManager:
         state["evidence_id"] = evidence_id
         # Atomic write: write to temp file then rename
         temp_file = self.state_file.with_suffix(".tmp")
-        with open(temp_file, 'w') as f:
-            json.dump(state, f)
+        with open(temp_file, 'w', encoding='utf-8') as f:
+            json.dump(state, f, ensure_ascii=False)
         temp_file.replace(self.state_file)
 
     def get_active(self) -> dict:
         if not self.state_file.exists():
             return {"case_id": None, "evidence_id": None}
         try:
-            with open(self.state_file, 'r') as f:
+            with open(self.state_file, 'r', encoding='utf-8') as f:
                 return json.load(f)
         except (json.JSONDecodeError, IOError):
             return {"case_id": None, "evidence_id": None}
@@ -242,7 +242,7 @@ class StateManager:
         if not self.settings_file.exists():
             return {"pgp_enabled": True}
         try:
-            with open(self.settings_file, 'r') as f:
+            with open(self.settings_file, 'r', encoding='utf-8') as f:
                 return json.load(f)
         except (json.JSONDecodeError, IOError):
             return {"pgp_enabled": True}
@@ -252,6 +252,6 @@ class StateManager:
         settings[key] = value
         # Atomic write: write to temp file then rename
         temp_file = self.settings_file.with_suffix(".tmp")
-        with open(temp_file, 'w') as f:
-            json.dump(settings, f)
+        with open(temp_file, 'w', encoding='utf-8') as f:
+            json.dump(settings, f, ensure_ascii=False)
         temp_file.replace(self.settings_file)

trace/tui.py

@@ -1911,6 +1911,42 @@ class TUI:
                     if cursor_line >= scroll_offset + input_height:
                         scroll_offset = cursor_line - input_height + 1
 
+            elif ch > 127:
+                # UTF-8 multi-byte character (umlauts, etc.)
+                # curses returns the first byte, we need to read the rest
+                try:
+                    # Try to decode as UTF-8
+                    # For multibyte UTF-8, we need to collect all bytes
+                    bytes_collected = [ch]
+
+                    # Determine how many bytes we need based on the first byte
+                    if ch >= 0xF0:  # 4-byte character
+                        num_bytes = 4
+                    elif ch >= 0xE0:  # 3-byte character
+                        num_bytes = 3
+                    elif ch >= 0xC0:  # 2-byte character
+                        num_bytes = 2
+                    else:
+                        num_bytes = 1
+
+                    # Read remaining bytes
+                    for _ in range(num_bytes - 1):
+                        next_ch = win.getch()
+                        bytes_collected.append(next_ch)
+
+                    # Convert to character
+                    char_bytes = bytes([b & 0xFF for b in bytes_collected])
+                    char = char_bytes.decode('utf-8')
+
+                    # Insert character at cursor
+                    line = lines[cursor_line]
+                    lines[cursor_line] = line[:cursor_col] + char + line[cursor_col:]
+                    cursor_col += 1
+
+                except (UnicodeDecodeError, ValueError):
+                    # If decode fails, ignore the character
+                    pass
+
     def dialog_confirm(self, message):
         curses.curs_set(0)
         h = 5
@@ -2643,7 +2679,7 @@ class TUI:
 
         # Write to file
         try:
-            with open(filepath, 'w') as f:
+            with open(filepath, 'w', encoding='utf-8') as f:
                 f.write('\n'.join(lines))
             self.show_message(f"IOCs exported to: {filepath}")
         except Exception as e: