File size: 13,058 Bytes
fbd9d3d cc826a1 fbd9d3d cc826a1 fbd9d3d cc826a1 fbd9d3d cc826a1 fbd9d3d cc826a1 fbd9d3d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 | """
JSON内容提取插件 MCP工具定义
"""
from app.mcp.decorators import mcp_tool
from pydantic import BaseModel, Field
from typing import Any, List, Optional
class ExtractFromJsonInput(BaseModel):
"""从JSON数据提取content的输入参数"""
json_data: Any = Field(description="JSON数据对象")
output_file: Optional[str] = Field(
default=None,
description="输出文件路径（可选，不提供则返回格式化文本）"
)
class ExtractFromJsonOutput(BaseModel):
"""从JSON数据提取content的输出结果"""
success: bool = Field(description="操作是否成功")
contents: List[str] = Field(default=[], description="提取的content列表")
formatted_output: str = Field(default="", description="格式化后的输出")
count: int = Field(default=0, description="提取的content数量")
error: Optional[str] = Field(default=None, description="错误信息")
class ExtractFromFileInput(BaseModel):
"""从JSON文件提取content的输入参数"""
file_path: str = Field(description="JSON文件路径")
output_file: Optional[str] = Field(
default=None,
description="输出文件路径（可选）"
)
class ExtractFromFileOutput(BaseModel):
"""从JSON文件提取content的输出结果"""
success: bool = Field(description="操作是否成功")
file_path: str = Field(description="源文件路径")
contents: List[str] = Field(default=[], description="提取的content列表")
formatted_output: str = Field(default="", description="格式化后的输出")
count: int = Field(default=0, description="提取的content数量")
error: Optional[str] = Field(default=None, description="错误信息")
class ExtractFromDirectoryInput(BaseModel):
"""从目录批量提取content的输入参数"""
dir_path: str = Field(description="包含JSON文件的目录路径")
output_file: Optional[str] = Field(
default=None,
description="输出文件路径（可选）"
)
class ExtractFromDirectoryOutput(BaseModel):
"""从目录批量提取content的输出结果"""
success: bool = Field(description="操作是否成功")
dir_path: str = Field(description="源目录路径")
file_count: int = Field(default=0, description="处理的文件数量")
result: str = Field(default="", description="提取结果")
error: Optional[str] = Field(default=None, description="错误信息")
class ConversationMessage(BaseModel):
"""对话消息结构"""
role: str = Field(description="消息角色（system/user/assistant）")
content: str = Field(description="消息内容")
class ExtractConversationFromJsonInput(BaseModel):
"""从JSON数据提取对话的输入参数"""
json_data: Any = Field(description="JSON数据对象")
class ExtractConversationFromJsonOutput(BaseModel):
"""从JSON数据提取对话的输出结果"""
success: bool = Field(description="操作是否成功")
is_conversation: bool = Field(description="是否为对话格式")
messages: List[ConversationMessage] = Field(default=[], description="对话消息列表")
formatted_output: str = Field(default="", description="格式化后的对话记录")
count: int = Field(default=0, description="消息数量")
error: Optional[str] = Field(default=None, description="错误信息")
class ExtractConversationFromFileInput(BaseModel):
"""从JSON文件提取对话的输入参数"""
file_path: str = Field(description="JSON文件路径")
class ExtractConversationFromFileOutput(BaseModel):
"""从JSON文件提取对话的输出结果"""
success: bool = Field(description="操作是否成功")
file_path: str = Field(description="源文件路径")
is_conversation: bool = Field(description="是否为对话格式")
messages: List[ConversationMessage] = Field(default=[], description="对话消息列表")
formatted_output: str = Field(default="", description="格式化后的对话记录")
count: int = Field(default=0, description="消息数量")
error: Optional[str] = Field(default=None, description="错误信息")
# 全局核心逻辑实例
_core = None
def _get_core():
"""获取核心逻辑实例"""
global _core
if _core is None:
from .core import JsonContentExtractorCore
_core = JsonContentExtractorCore()
return _core
@mcp_tool(
name="json-content",
title="从JSON数据提取content",
description="从JSON数据对象中递归提取所有content字段的内容。如果是OpenAI对话格式，会自动识别并按对话格式输出。",
annotations={
"readOnlyHint": True,
"destructiveHint": False,
}
)
async def extract_from_json(params: ExtractFromJsonInput) -> ExtractFromJsonOutput:
"""
从JSON数据中提取content字段
支持递归提取嵌套的content字段，包括处理OpenAI API格式的content数组。
如果是OpenAI对话格式（包含messages数组），会自动识别并按对话格式输出。
Args:
params: 包含JSON数据
Returns:
ExtractFromJsonOutput: 提取的内容
"""
core = _get_core()
try:
# 检测是否为对话格式
if core._is_conversation_format(params.json_data):
formatted_output = core._format_conversation(params.json_data)
messages = core._extract_conversation(params.json_data)
contents = [msg["content"] for msg in messages]
else:
contents = core.extract_content_from_json(params.json_data)
formatted_contents = []
for i, content in enumerate(contents, 1):
formatted = core.format_content(content)
formatted_contents.append(f"=== Content {i} ===\n{formatted}")
formatted_output = "\n\n".join(formatted_contents) if formatted_contents else "未找到content内容"
# 如果指定了输出文件，保存结果
if params.output_file and contents:
try:
with open(params.output_file, 'w', encoding='utf-8') as f:
f.write(formatted_output)
except Exception as e:
return ExtractFromJsonOutput(
success=False,
contents=contents,
formatted_output=formatted_output,
count=len(contents),
error=f"保存文件失败: {str(e)}"
)
return ExtractFromJsonOutput(
success=True,
contents=contents,
formatted_output=formatted_output,
count=len(contents)
)
except Exception as e:
return ExtractFromJsonOutput(
success=False,
error=str(e)
)
@mcp_tool(
name="json-file",
title="从JSON文件提取content",
description="从JSON文件中递归提取所有content字段的内容。如果是OpenAI对话格式，会自动识别并按对话格式输出。",
annotations={
"readOnlyHint": True,
"destructiveHint": False,
}
)
async def extract_from_file(params: ExtractFromFileInput) -> ExtractFromFileOutput:
"""
从JSON文件中提取content字段
如果是OpenAI对话格式，会自动识别并按对话格式输出。
Args:
params: 包含文件路径
Returns:
ExtractFromFileOutput: 提取的内容
"""
core = _get_core()
try:
import os
if not os.path.exists(params.file_path):
return ExtractFromFileOutput(
success=False,
file_path=params.file_path,
error=f"文件不存在: {params.file_path}"
)
contents = core.extract_content_from_file(params.file_path)
result = core.process_single_file(params.file_path, output_file=params.output_file)
return ExtractFromFileOutput(
success=True,
file_path=params.file_path,
contents=contents,
formatted_output=result,
count=len(contents)
)
except Exception as e:
return ExtractFromFileOutput(
success=False,
file_path=params.file_path,
error=str(e)
)
@mcp_tool(
name="json-dir",
title="从目录批量提取content",
description="从目录中所有JSON文件递归提取content字段的内容",
annotations={
"readOnlyHint": True,
"destructiveHint": False,
}
)
async def extract_from_directory(params: ExtractFromDirectoryInput) -> ExtractFromDirectoryOutput:
"""
从目录中批量提取content字段
Args:
params: 包含目录路径
Returns:
ExtractFromDirectoryOutput: 提取的结果
"""
core = _get_core()
try:
import os
import glob
if not os.path.exists(params.dir_path):
return ExtractFromDirectoryOutput(
success=False,
dir_path=params.dir_path,
error=f"目录不存在: {params.dir_path}"
)
json_files = glob.glob(os.path.join(params.dir_path, "*.json"))
result = core.process_directory(params.dir_path, output_file=params.output_file)
return ExtractFromDirectoryOutput(
success=True,
dir_path=params.dir_path,
file_count=len(json_files),
result=result
)
except Exception as e:
return ExtractFromDirectoryOutput(
success=False,
dir_path=params.dir_path,
error=str(e)
)
@mcp_tool(
name="json-chat",
title="从JSON数据提取对话",
description="从JSON数据中提取OpenAI格式的对话消息，返回结构化的对话记录",
annotations={
"readOnlyHint": True,
"destructiveHint": False,
}
)
async def extract_conversation_from_json(params: ExtractConversationFromJsonInput) -> ExtractConversationFromJsonOutput:
"""
从JSON数据中提取对话消息
专门用于处理OpenAI格式的对话JSON，返回结构化的消息列表。
如果不是对话格式，is_conversation会返回false。
Args:
params: 包含JSON数据
Returns:
ExtractConversationFromJsonOutput: 结构化的对话消息
"""
core = _get_core()
try:
messages = core.extract_conversation_from_json(params.json_data)
is_conversation = len(messages) > 0
if is_conversation:
formatted_output = core._format_conversation(params.json_data)
else:
formatted_output = "该数据不是对话格式"
return ExtractConversationFromJsonOutput(
success=True,
is_conversation=is_conversation,
messages=[ConversationMessage(**msg) for msg in messages],
formatted_output=formatted_output,
count=len(messages)
)
except Exception as e:
return ExtractConversationFromJsonOutput(
success=False,
error=str(e)
)
@mcp_tool(
name="json-chatfile",
title="从JSON文件提取对话",
description="从JSON文件中提取OpenAI格式的对话消息，返回结构化的对话记录",
annotations={
"readOnlyHint": True,
"destructiveHint": False,
}
)
async def extract_conversation_from_file(params: ExtractConversationFromFileInput) -> ExtractConversationFromFileOutput:
"""
从JSON文件中提取对话消息
专门用于处理OpenAI格式的对话JSON，返回结构化的消息列表。
如果不是对话格式，is_conversation会返回false。
Args:
params: 包含文件路径
Returns:
ExtractConversationFromFileOutput: 结构化的对话消息
"""
core = _get_core()
try:
import os
if not os.path.exists(params.file_path):
return ExtractConversationFromFileOutput(
success=False,
file_path=params.file_path,
error=f"文件不存在: {params.file_path}"
)
messages = core.extract_conversation_from_file(params.file_path)
is_conversation = len(messages) > 0
if is_conversation:
import json
with open(params.file_path, 'r', encoding='utf-8') as f:
json_data = json.load(f)
formatted_output = core._format_conversation(json_data)
else:
formatted_output = "该文件不是对话格式"
return ExtractConversationFromFileOutput(
success=True,
file_path=params.file_path,
is_conversation=is_conversation,
messages=[ConversationMessage(**msg) for msg in messages],
formatted_output=formatted_output,
count=len(messages)
)
except Exception as e:
return ExtractConversationFromFileOutput(
success=False,
file_path=params.file_path,
error=str(e)
)
|