init rep
This commit is contained in:
13
modules/parser_adapters/__init__.py
Normal file
13
modules/parser_adapters/__init__.py
Normal file
@@ -0,0 +1,13 @@
|
||||
# @line_count 50
|
||||
"""JSON解析器适配器包"""
|
||||
from .base_adapter import BaseParserAdapter
|
||||
from .parser_factory import ParserFactory
|
||||
from .section_array_adapter import SectionArrayAdapter
|
||||
from .requirement_tree_adapter import RequirementTreeAdapter
|
||||
|
||||
__all__ = [
|
||||
'BaseParserAdapter',
|
||||
'ParserFactory',
|
||||
'SectionArrayAdapter',
|
||||
'RequirementTreeAdapter',
|
||||
]
|
||||
81
modules/parser_adapters/base_adapter.py
Normal file
81
modules/parser_adapters/base_adapter.py
Normal file
@@ -0,0 +1,81 @@
|
||||
# @line_count 100
|
||||
"""JSON解析器适配器基类"""
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import List, Dict, Any
|
||||
|
||||
|
||||
class BaseParserAdapter(ABC):
|
||||
"""解析器适配器抽象基类"""
|
||||
|
||||
def __init__(self, data: Dict[str, Any]):
|
||||
"""
|
||||
初始化适配器
|
||||
|
||||
Args:
|
||||
data: 解析后的JSON数据
|
||||
"""
|
||||
self.data = data
|
||||
|
||||
@abstractmethod
|
||||
def extract_function_points(self) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
提取功能点列表
|
||||
|
||||
Returns:
|
||||
功能点列表，统一格式：
|
||||
- module_name: 所属模块
|
||||
- function_name: 功能名称
|
||||
- description: 功能描述
|
||||
- operation_steps: 操作步骤（可选）
|
||||
- requirement_id: 需求编号（可选）
|
||||
- requirement_type: 需求类型（可选）
|
||||
"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def get_document_info(self) -> Dict[str, Any]:
|
||||
"""
|
||||
获取文档基本信息
|
||||
|
||||
Returns:
|
||||
文档信息字典，统一格式：
|
||||
- title: 文档标题
|
||||
- version: 版本（可选）
|
||||
- date: 日期（可选）
|
||||
- section_count: 章节数量
|
||||
"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def get_sections(self) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
获取所有章节信息
|
||||
|
||||
Returns:
|
||||
章节列表
|
||||
"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def get_module_summary(self) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
获取模块摘要
|
||||
|
||||
Returns:
|
||||
模块摘要列表
|
||||
"""
|
||||
pass
|
||||
|
||||
@staticmethod
|
||||
@abstractmethod
|
||||
def can_parse(data: Dict[str, Any]) -> bool:
|
||||
"""
|
||||
检测是否能解析该格式
|
||||
|
||||
Args:
|
||||
data: JSON数据
|
||||
|
||||
Returns:
|
||||
是否能解析
|
||||
"""
|
||||
pass
|
||||
53
modules/parser_adapters/parser_factory.py
Normal file
53
modules/parser_adapters/parser_factory.py
Normal file
@@ -0,0 +1,53 @@
|
||||
# @line_count 100
|
||||
"""解析器工厂"""
|
||||
from typing import Dict, Any, Type, List
|
||||
from .base_adapter import BaseParserAdapter
|
||||
from .section_array_adapter import SectionArrayAdapter
|
||||
from .requirement_tree_adapter import RequirementTreeAdapter
|
||||
|
||||
|
||||
class ParserFactory:
|
||||
"""解析器工厂，自动检测格式并创建合适的适配器"""
|
||||
|
||||
# 注册所有适配器（按优先级排序）
|
||||
_adapters: List[Type[BaseParserAdapter]] = [
|
||||
RequirementTreeAdapter, # 新格式优先
|
||||
SectionArrayAdapter, # 旧格式
|
||||
# 未来可以在这里添加更多适配器
|
||||
]
|
||||
|
||||
@classmethod
|
||||
def create_adapter(cls, data: Dict[str, Any]) -> BaseParserAdapter:
|
||||
"""
|
||||
创建合适的适配器
|
||||
|
||||
Args:
|
||||
data: JSON数据
|
||||
|
||||
Returns:
|
||||
适配器实例
|
||||
|
||||
Raises:
|
||||
ValueError: 如果无法识别格式
|
||||
"""
|
||||
for adapter_class in cls._adapters:
|
||||
if adapter_class.can_parse(data):
|
||||
return adapter_class(data)
|
||||
|
||||
raise ValueError(
|
||||
"无法识别JSON格式。支持的格式：\n"
|
||||
"- 需求树格式（包含'需求内容'和'文档元数据'）\n"
|
||||
"- 章节数组格式（包含'sections'数组）"
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def register_adapter(cls, adapter_class: Type[BaseParserAdapter],
|
||||
priority: int = 0):
|
||||
"""
|
||||
注册新的适配器
|
||||
|
||||
Args:
|
||||
adapter_class: 适配器类
|
||||
priority: 优先级（越小越优先，0为最高优先级）
|
||||
"""
|
||||
cls._adapters.insert(priority, adapter_class)
|
||||
139
modules/parser_adapters/requirement_tree_adapter.py
Normal file
139
modules/parser_adapters/requirement_tree_adapter.py
Normal file
@@ -0,0 +1,139 @@
|
||||
# @line_count 200
|
||||
"""新格式适配器（需求树格式）"""
|
||||
from typing import List, Dict, Any
|
||||
from .base_adapter import BaseParserAdapter
|
||||
|
||||
|
||||
class RequirementTreeAdapter(BaseParserAdapter):
|
||||
"""处理新格式：需求树结构"""
|
||||
|
||||
def extract_function_points(self) -> List[Dict[str, Any]]:
|
||||
"""从需求树中提取功能点"""
|
||||
function_points = []
|
||||
requirement_content = self.data.get('需求内容', {})
|
||||
|
||||
# 递归遍历章节
|
||||
self._traverse_requirements(requirement_content, [], function_points)
|
||||
|
||||
return function_points
|
||||
|
||||
def _traverse_requirements(self, sections: Dict, path: List[str],
|
||||
function_points: List[Dict]):
|
||||
"""递归遍历章节，提取需求"""
|
||||
for section_key, section_data in sections.items():
|
||||
section_info = section_data.get('章节信息', {})
|
||||
section_title = section_info.get('章节标题', '')
|
||||
current_path = path + [section_title]
|
||||
|
||||
# 如果有需求列表，提取需求
|
||||
if '需求列表' in section_data:
|
||||
requirements = section_data['需求列表']
|
||||
for req in requirements:
|
||||
function_points.append({
|
||||
'module_name': ' > '.join(current_path[:-1]) if len(current_path) > 1 else section_title,
|
||||
'function_name': req.get('需求编号', ''),
|
||||
'description': req.get('需求描述', ''),
|
||||
'requirement_id': req.get('需求编号', ''),
|
||||
'requirement_type': self._parse_requirement_type(
|
||||
req.get('需求编号', '')
|
||||
),
|
||||
'interface_info': {
|
||||
k: v for k, v in req.items()
|
||||
if k in ['接口名称', '接口类型', '来源', '目的地']
|
||||
} if any(k in req for k in ['接口名称', '接口类型']) else None
|
||||
})
|
||||
|
||||
# 递归处理子章节
|
||||
if '子章节' in section_data:
|
||||
self._traverse_requirements(
|
||||
section_data['子章节'],
|
||||
current_path,
|
||||
function_points
|
||||
)
|
||||
|
||||
def _parse_requirement_type(self, req_id: str) -> str:
|
||||
"""从需求编号解析需求类型"""
|
||||
if req_id.startswith('FR-'):
|
||||
return '功能需求'
|
||||
elif req_id.startswith('IR-'):
|
||||
return '接口需求'
|
||||
elif req_id.startswith('OR-'):
|
||||
return '其他需求'
|
||||
return '未知'
|
||||
|
||||
def get_document_info(self) -> Dict[str, Any]:
|
||||
"""获取文档信息"""
|
||||
metadata = self.data.get('文档元数据', {})
|
||||
return {
|
||||
'title': metadata.get('标题', ''),
|
||||
'version': '', # 新格式可能没有版本
|
||||
'date': metadata.get('生成时间', ''),
|
||||
'section_count': self._count_sections(self.data.get('需求内容', {}))
|
||||
}
|
||||
|
||||
def _count_sections(self, sections: Dict) -> int:
|
||||
"""递归统计章节数量"""
|
||||
count = 0
|
||||
for section_data in sections.values():
|
||||
count += 1
|
||||
if '子章节' in section_data:
|
||||
count += self._count_sections(section_data['子章节'])
|
||||
return count
|
||||
|
||||
def get_sections(self) -> List[Dict[str, Any]]:
|
||||
"""获取章节列表（转换为扁平结构）"""
|
||||
sections = []
|
||||
self._flatten_sections(self.data.get('需求内容', {}), sections)
|
||||
return sections
|
||||
|
||||
def _flatten_sections(self, sections: Dict, result: List[Dict]):
|
||||
"""递归扁平化章节结构"""
|
||||
for section_data in sections.values():
|
||||
section_info = section_data.get('章节信息', {})
|
||||
result.append({
|
||||
'title': section_info.get('章节标题', ''),
|
||||
'number': section_info.get('章节编号', ''),
|
||||
'level': section_info.get('章节级别', 0),
|
||||
'requirement_count': len(section_data.get('需求列表', []))
|
||||
})
|
||||
if '子章节' in section_data:
|
||||
self._flatten_sections(section_data['子章节'], result)
|
||||
|
||||
def get_module_summary(self) -> List[Dict[str, Any]]:
|
||||
"""获取模块摘要"""
|
||||
modules = []
|
||||
sections_dict = {}
|
||||
|
||||
# 遍历需求内容，构建模块统计
|
||||
self._build_module_summary(self.data.get('需求内容', {}), sections_dict)
|
||||
|
||||
for module_name, info in sections_dict.items():
|
||||
modules.append({
|
||||
'name': module_name,
|
||||
'function_count': info['requirement_count'],
|
||||
'description': info.get('description', '')
|
||||
})
|
||||
|
||||
return modules
|
||||
|
||||
def _build_module_summary(self, sections: Dict, result: Dict):
|
||||
"""递归构建模块摘要"""
|
||||
for section_data in sections.values():
|
||||
section_info = section_data.get('章节信息', {})
|
||||
section_title = section_info.get('章节标题', '')
|
||||
|
||||
if '需求列表' in section_data:
|
||||
if section_title not in result:
|
||||
result[section_title] = {
|
||||
'requirement_count': 0,
|
||||
'description': ''
|
||||
}
|
||||
result[section_title]['requirement_count'] += len(section_data['需求列表'])
|
||||
|
||||
if '子章节' in section_data:
|
||||
self._build_module_summary(section_data['子章节'], result)
|
||||
|
||||
@staticmethod
|
||||
def can_parse(data: Dict[str, Any]) -> bool:
|
||||
"""检测是否为新格式"""
|
||||
return '需求内容' in data and '文档元数据' in data
|
||||
164
modules/parser_adapters/section_array_adapter.py
Normal file
164
modules/parser_adapters/section_array_adapter.py
Normal file
@@ -0,0 +1,164 @@
|
||||
# @line_count 150
|
||||
"""旧格式适配器（sections数组格式）"""
|
||||
from typing import List, Dict, Any
|
||||
from .base_adapter import BaseParserAdapter
|
||||
|
||||
|
||||
class SectionArrayAdapter(BaseParserAdapter):
|
||||
"""处理旧格式：sections数组"""
|
||||
|
||||
def extract_function_points(self) -> List[Dict[str, Any]]:
|
||||
"""从sections数组中提取功能点"""
|
||||
function_points = []
|
||||
sections = self.data.get('sections', [])
|
||||
|
||||
for section in sections:
|
||||
module_name = section.get('title', '')
|
||||
content = section.get('content', [])
|
||||
|
||||
# 提取模块总体描述（第一个较长的文本内容）
|
||||
module_description = ""
|
||||
for item in content:
|
||||
if item.get('type') == 'text':
|
||||
text = item.get('content', '').strip()
|
||||
if len(text) > 50: # 较长的文本通常是模块描述
|
||||
module_description = text
|
||||
break
|
||||
|
||||
# 识别功能点
|
||||
# 功能点通常是较短的文本（标题），后面跟着描述
|
||||
current_function = None
|
||||
function_description_parts = []
|
||||
|
||||
for i, item in enumerate(content):
|
||||
if item.get('type') != 'text':
|
||||
continue
|
||||
|
||||
text = item.get('content', '').strip()
|
||||
if not text:
|
||||
continue
|
||||
|
||||
# 判断是否是功能点标题
|
||||
# 规则：短文本（通常<20字符），且不是描述性文本
|
||||
is_function_title = (
|
||||
len(text) < 20 and
|
||||
not text.endswith('。') and
|
||||
not text.endswith('，') and
|
||||
not ('如下' in text or '所示' in text)
|
||||
)
|
||||
|
||||
if is_function_title:
|
||||
# 保存之前的功能点
|
||||
if current_function:
|
||||
function_points.append({
|
||||
'module_name': module_name,
|
||||
'module_description': module_description,
|
||||
'function_name': current_function,
|
||||
'description': ' '.join(function_description_parts),
|
||||
'operation_steps': self._extract_steps(function_description_parts)
|
||||
})
|
||||
|
||||
# 开始新功能点
|
||||
current_function = text
|
||||
function_description_parts = []
|
||||
else:
|
||||
# 添加到当前功能点的描述
|
||||
if current_function:
|
||||
function_description_parts.append(text)
|
||||
elif not module_description:
|
||||
# 如果还没有模块描述，这可能是模块描述的一部分
|
||||
pass
|
||||
|
||||
# 保存最后一个功能点
|
||||
if current_function:
|
||||
function_points.append({
|
||||
'module_name': module_name,
|
||||
'module_description': module_description,
|
||||
'function_name': current_function,
|
||||
'description': ' '.join(function_description_parts),
|
||||
'operation_steps': self._extract_steps(function_description_parts)
|
||||
})
|
||||
|
||||
# 如果没有识别到功能点，将整个模块作为一个功能点
|
||||
if not current_function and module_description:
|
||||
function_points.append({
|
||||
'module_name': module_name,
|
||||
'module_description': module_description,
|
||||
'function_name': module_name,
|
||||
'description': module_description,
|
||||
'operation_steps': []
|
||||
})
|
||||
|
||||
return function_points
|
||||
|
||||
def _extract_steps(self, description_parts: List[str]) -> List[str]:
|
||||
"""
|
||||
从描述中提取操作步骤
|
||||
|
||||
Args:
|
||||
description_parts: 描述文本列表
|
||||
|
||||
Returns:
|
||||
操作步骤列表
|
||||
"""
|
||||
steps = []
|
||||
for part in description_parts:
|
||||
# 查找包含操作动词的句子
|
||||
if any(keyword in part for keyword in ['点击', '选择', '输入', '打开', '关闭', '设置', '查看']):
|
||||
# 移除"如下图所示"等描述性文字
|
||||
cleaned = part.replace('如下图所示', '').replace('如下图所示：', '').strip()
|
||||
if cleaned:
|
||||
steps.append(cleaned)
|
||||
return steps
|
||||
|
||||
def get_document_info(self) -> Dict[str, Any]:
|
||||
"""获取文档信息"""
|
||||
return {
|
||||
'title': self.data.get('document_title', ''),
|
||||
'version': self.data.get('version', ''),
|
||||
'date': self.data.get('date', ''),
|
||||
'section_count': len(self.data.get('sections', []))
|
||||
}
|
||||
|
||||
def get_sections(self) -> List[Dict[str, Any]]:
|
||||
"""获取章节列表"""
|
||||
return self.data.get('sections', [])
|
||||
|
||||
def get_module_summary(self) -> List[Dict[str, Any]]:
|
||||
"""获取模块摘要"""
|
||||
modules = []
|
||||
sections = self.data.get('sections', [])
|
||||
|
||||
for section in sections:
|
||||
module_info = {
|
||||
'name': section.get('title', ''),
|
||||
'function_count': 0,
|
||||
'description': ''
|
||||
}
|
||||
|
||||
# 查找模块描述
|
||||
content = section.get('content', [])
|
||||
for item in content:
|
||||
if item.get('type') == 'text':
|
||||
text = item.get('content', '').strip()
|
||||
if len(text) > 50:
|
||||
module_info['description'] = text
|
||||
break
|
||||
|
||||
# 统计功能点数量（简单统计）
|
||||
function_names = []
|
||||
for item in content:
|
||||
if item.get('type') == 'text':
|
||||
text = item.get('content', '').strip()
|
||||
if len(text) < 20 and text and not text.endswith('。'):
|
||||
function_names.append(text)
|
||||
|
||||
module_info['function_count'] = len(set(function_names))
|
||||
modules.append(module_info)
|
||||
|
||||
return modules
|
||||
|
||||
@staticmethod
|
||||
def can_parse(data: Dict[str, Any]) -> bool:
|
||||
"""检测是否为旧格式"""
|
||||
return 'sections' in data and isinstance(data['sections'], list)
|
||||
Reference in New Issue
Block a user