Add support to extract BGI ._bsi file

extract_bsi.py

@@ -0,0 +1,100 @@
+import argparse
+import os
+import json
+
+def read_binary_strings(filename):
+    results = {}
+    
+    try:
+        with open(filename, 'rb') as f:
+            content = f.read()
+    except IOError as e:
+        print(f"Error opening file: {e}")
+        return []
+    
+    section_count = None
+    section_name = None
+    section_len = None
+    section_current = 0
+    section_data = None
+    key = None
+    i = 0
+    while i < len(content):
+        start_position = i
+        # 查找下一个0，即字符串结束的位置
+        end_position = content.find(b'\x00', i)
+        if end_position == -1:
+            # 如果没有找到结束标记，则结束循环
+            break
+        
+        # 提取字符串内容
+        string_bytes = content[i:end_position]
+        try:
+            if section_count is None:
+                # 如果没有找到节数，则从文件头部读取节数
+                section_count = int.from_bytes(string_bytes[:4], 'little')
+                i += 4
+                continue
+            text = string_bytes.decode('utf-8')
+            if section_name is None:
+                # 如果没有找到节名，则从文件头部读取节名
+                section_name = text
+                i = end_position + 1
+                section_len = int.from_bytes(content[i:i+4], 'little')
+                i += 4
+                section_current = 0
+                section_data = {}
+                continue
+            if key is None:
+                key = text
+            else:
+                section_data[key] = text
+                section_current += 1
+                key = None
+            if section_current >= section_len:
+                # 如果当前节的数据已经读取完毕，则将其添加到结果中
+                results[section_name] = section_data
+                section_name = None
+                section_len = None
+                section_current = 0
+                section_data = None
+        except UnicodeDecodeError:
+            # 如果解码失败，则跳过这部分数据
+            pass
+        
+        # 移动到下一个字符串的开始位置（跳过终止符）
+        i = end_position + 1
+    
+    if section_name is not None:
+        raise ValueError(f"Error: Section '{section_name}' not fully read. Expected {section_len} strings, but only found {section_current}.")
+
+    return results
+
+def main():
+    # 设置命令行参数解析
+    parser = argparse.ArgumentParser(description='Extract UTF-8 strings from a binary file')
+    parser.add_argument('input_file', help='Input binary file')
+    
+    args = parser.parse_args()
+    
+    # 检查输入文件是否存在
+    if not os.path.exists(args.input_file):
+        print(f"Error: Input file '{args.input_file}' does not exist.")
+        return
+    
+    # 生成输出文件名
+    output_file = args.input_file + '.json'
+    
+    # 读取并解析二进制文件
+    string_data = read_binary_strings(args.input_file)
+    
+    # 写入输出文件
+    try:
+        with open(output_file, 'w', encoding='utf-8') as f:
+            json.dump(string_data, f, ensure_ascii=False, indent=4)
+        
+    except IOError as e:
+        print(f"Error writing to output file: {e}")
+
+if __name__ == '__main__':
+    main()