init: WordFileParse docx→HTML 解析服务(含 Word EQ 域公式修复)
服务:Spring Boot 3.2 + docx4j 8.3.9,POST /api/v3/server_office_file/file/parse
接受 .docx,返回 HTML(公式 → LaTeX,图片 → RustFS 外链)
公式支持三类来源:
- OMML(Word 2007+ 公式) → Python omml_mathml2latex
- MathType OLE 对象 → Ruby mathtype2mathml → MathML → LaTeX
- Word EQ 域(老教辅主力) → EqToLatexUtil(本次新增)
本次改动:
1. 新增 java-svc/.../core/EqToLatexUtil.java:
移植自 jby backend-services office-core,EQ 语法 → LaTeX
(\f→\dfrac、\r→\sqrt、\i→\int/\sum/\prod、\s→^{}/_{}、\b→\left\right、
\a→array、\x→\boxed/\overline、\o\al 堆叠、圈码、化学符号、极限、连等式)
品牌标记 JBYU* → WPU*,与采集端一致
2. CtoMathFinder:接上 EQ 分支(原为 not-ported 桩),域代码经
EqToLatexUtil.convert 转 LaTeX 写入 eqLatexMap(WPEQNUM 占位符)
3. WordParseUtil.dealPlaceholder:EQ 的 LaTeX 同样加 \( \) 包裹
(原先因 WPEQNUM 例外不加包裹,前端/MathJax 不渲染)
修前症状:教辅 Word 里分式/方程组/上下标整段丢失(如 {−1/3, 1} 变成 {-,1})
修后实测:46 份教辅 2908 处 EQ 域全部还原,公式总数 2954 处、零未包裹残留
安全:application.yml(含 RustFS 密钥)不入库,提供 application.yml.example;
OssService 的 @Value 默认密钥已清空
This commit is contained in:
148
scripts/omml_mathml2latex/visitors/visitor_registry.py
Normal file
148
scripts/omml_mathml2latex/visitors/visitor_registry.py
Normal file
@@ -0,0 +1,148 @@
|
||||
"""
|
||||
Visitor registry/factory for MathML element visitors.
|
||||
|
||||
This module provides a centralized registry for mapping MathML element
|
||||
names to their corresponding visitor classes.
|
||||
"""
|
||||
|
||||
from typing import Dict, Type, Optional, List
|
||||
from ..core.interfaces import Visitor, Strategy, VisitorRegistry as IVisitorRegistry
|
||||
from ..core.context import ConversionContext
|
||||
|
||||
|
||||
class VisitorRegistry(IVisitorRegistry):
|
||||
"""
|
||||
Registry for MathML element visitors.
|
||||
|
||||
This class maintains a mapping of element names (e.g., 'mi', 'mo', 'mn')
|
||||
to their corresponding visitor classes. It provides visitor instances
|
||||
on demand with the appropriate strategy and context injected.
|
||||
|
||||
Example:
|
||||
>>> registry = VisitorRegistry()
|
||||
>>> registry.register('mi', MiVisitor)
|
||||
>>> registry.register('mo', MoVisitor)
|
||||
>>> strategy = MathStrategy()
|
||||
>>> context = ConversionContext(input_type='mathml')
|
||||
>>> mi_visitor = registry.get_visitor('mi', strategy, context)
|
||||
"""
|
||||
|
||||
def __init__(self, context: Optional[ConversionContext] = None):
|
||||
"""
|
||||
Initialize the registry with empty mappings.
|
||||
|
||||
Args:
|
||||
context: Optional shared conversion context for all visitors
|
||||
"""
|
||||
self._visitors: Dict[str, Type[Visitor]] = {}
|
||||
self._default_visitor: Type[Visitor] | None = None
|
||||
self.context = context
|
||||
|
||||
def register(self, element_name: str, visitor_class: type) -> None:
|
||||
"""
|
||||
Register a visitor class for a specific element type.
|
||||
|
||||
Args:
|
||||
element_name: MathML element name (e.g., 'mi', 'mo', 'mn')
|
||||
visitor_class: The visitor class to handle this element
|
||||
|
||||
Raises:
|
||||
TypeError: If visitor_class is not a subclass of Visitor
|
||||
"""
|
||||
if not issubclass(visitor_class, Visitor):
|
||||
raise TypeError(
|
||||
f"visitor_class must be a subclass of Visitor, "
|
||||
f"got {type(visitor_class)}"
|
||||
)
|
||||
|
||||
self._visitors[element_name] = visitor_class
|
||||
|
||||
def get_visitor(self, element_name: str, strategy: Strategy, context: Optional[ConversionContext] = None) -> Visitor:
|
||||
"""
|
||||
Get a visitor instance for the given element type.
|
||||
|
||||
Args:
|
||||
element_name: MathML element name (e.g., 'mi', 'mo')
|
||||
strategy: The conversion strategy to inject into the visitor
|
||||
context: Optional conversion context (uses registry's context if not provided)
|
||||
|
||||
Returns:
|
||||
Visitor instance configured with the strategy and context
|
||||
|
||||
Raises:
|
||||
ValueError: If no visitor registered for element_name and no default set
|
||||
"""
|
||||
visitor_class = self._visitors.get(element_name)
|
||||
|
||||
if visitor_class is None:
|
||||
if self._default_visitor is not None:
|
||||
visitor_class = self._default_visitor
|
||||
else:
|
||||
raise ValueError(
|
||||
f"No visitor registered for element '{element_name}' "
|
||||
f"and no default visitor configured"
|
||||
)
|
||||
|
||||
# Use provided context or fall back to registry's context
|
||||
ctx = context if context is not None else self.context
|
||||
|
||||
# Try to instantiate with context, fall back to strategy-only if needed
|
||||
try:
|
||||
return visitor_class(strategy, ctx)
|
||||
except TypeError:
|
||||
# Visitor doesn't accept context parameter yet
|
||||
return visitor_class(strategy)
|
||||
|
||||
def has_visitor(self, element_name: str) -> bool:
|
||||
"""
|
||||
Check if a visitor is registered for the element type.
|
||||
|
||||
Args:
|
||||
element_name: MathML element name
|
||||
|
||||
Returns:
|
||||
True if visitor is registered or default exists, False otherwise
|
||||
"""
|
||||
return element_name in self._visitors or self._default_visitor is not None
|
||||
|
||||
def set_default_visitor(self, visitor_class: Type[Visitor]) -> None:
|
||||
"""
|
||||
Set a default visitor for unregistered element types.
|
||||
|
||||
Args:
|
||||
visitor_class: The visitor class to use as default
|
||||
|
||||
Raises:
|
||||
TypeError: If visitor_class is not a subclass of Visitor
|
||||
"""
|
||||
if not issubclass(visitor_class, Visitor):
|
||||
raise TypeError(
|
||||
f"visitor_class must be a subclass of Visitor, "
|
||||
f"got {type(visitor_class)}"
|
||||
)
|
||||
|
||||
self._default_visitor = visitor_class
|
||||
|
||||
def get_registered_elements(self) -> List[str]:
|
||||
"""
|
||||
Get list of all registered element names.
|
||||
|
||||
Returns:
|
||||
List of element names with registered visitors
|
||||
"""
|
||||
return list(self._visitors.keys())
|
||||
|
||||
def clear(self) -> None:
|
||||
"""Clear all registered visitors."""
|
||||
self._visitors.clear()
|
||||
self._default_visitor = None
|
||||
|
||||
def __repr__(self) -> str:
|
||||
"""String representation for debugging."""
|
||||
elements = ', '.join(self._visitors.keys()) if self._visitors else 'none'
|
||||
default = f", default={self._default_visitor.__name__}" if self._default_visitor else ""
|
||||
return f"VisitorRegistry(registered=[{elements}]{default})"
|
||||
|
||||
def __len__(self) -> int:
|
||||
"""Get number of registered visitors."""
|
||||
return len(self._visitors)
|
||||
Reference in New Issue
Block a user