Files
Quentin 3271fee5cc 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
2026-09-29 09:43:13 +08:00

195 lines
7.2 KiB
Python

r"""
Visitor for <msqrt> (square root) MathML elements.
The <msqrt> element represents square roots (√).
The LaTeX conversion uses \sqrt{...} notation.
"""
from lxml import etree as ET
from ..core.interfaces import Visitor, Strategy
from ..utils import text_content as _text_content, local_name as _local
class MsqrtVisitor(Visitor):
r"""
Handles <msqrt> (square root) MathML elements.
Converts square root expressions to LaTeX \sqrt notation.
Examples:
Simple number:
<msqrt><mn>2</mn></msqrt> → \sqrt{2}
Variable:
<msqrt><mi>x</mi></msqrt> → \sqrt{x}
Complex expression:
<msqrt>
<mrow><mi>x</mi><mo>+</mo><mn>1</mn></mrow>
</msqrt>
→ \sqrt{x + 1}
Nested root:
<msqrt><msqrt><mi>x</mi></msqrt></msqrt> → \sqrt{\sqrt{x}}
Fraction under root:
<msqrt><mfrac><mn>1</mn><mn>2</mn></mfrac></msqrt> → \sqrt{\dfrac{1}{2}}
"""
def __init__(self, strategy: Strategy):
"""Initialize the Msqrt visitor."""
super().__init__(strategy)
def visit(self, node: ET.Element) -> str:
r"""
Convert <msqrt> element to LaTeX.
Args:
node: The <msqrt> element to convert
Returns:
LaTeX square root string (\sqrt{content})
Raises:
ValueError: If node is not an <msqrt> element
"""
if not self.can_handle(node):
raise ValueError(f"MsqrtVisitor cannot handle element '{node.tag}'")
children = list(node)
# Empty msqrt (edge case)
if not children:
return "\\sqrt{}"
# Convert all children and join with spaces
parts = []
for child in children:
part = self._convert_child(child)
if part: # Only add non-empty parts
parts.append(part)
radicand = ' '.join(parts).strip()
# Return \sqrt{radicand}
return f"\\sqrt{self._brace(radicand)}"
def _convert_child(self, child: ET.Element) -> str:
"""
Convert a child element to LaTeX.
This method instantiates the appropriate visitor for each child type.
"""
tag = _local(child.tag)
# Import visitors as needed to avoid circular imports
if tag == 'mi':
from .mi_visitor import MiVisitor
return MiVisitor(self.strategy).visit(child)
elif tag == 'mo':
from .mo_visitor import MoVisitor
return MoVisitor(self.strategy).visit(child)
elif tag == 'mn':
from .mn_visitor import MnVisitor
return MnVisitor(self.strategy).visit(child)
elif tag == 'mfrac':
from .mfrac_visitor import MfracVisitor
return MfracVisitor(self.strategy).visit(child)
elif tag == 'msup':
from .msup_visitor import MsupVisitor
return MsupVisitor(self.strategy).visit(child)
elif tag == 'msub':
from .msub_visitor import MsubVisitor
return MsubVisitor(self.strategy).visit(child)
elif tag == 'mrow':
from .mrow_visitor import MrowVisitor
return MrowVisitor(self.strategy).visit(child)
elif tag == 'msqrt':
# Recursive: msqrt can contain other msqrt elements
return self.visit(child)
elif tag == 'mroot':
from .mroot_visitor import MrootVisitor
return MrootVisitor(self.strategy).visit(child)
elif tag == 'msubsup':
from .msubsup_visitor import MsubsupVisitor
return MsubsupVisitor(self.strategy).visit(child)
elif tag == 'munder':
from .munder_visitor import MunderVisitor
return MunderVisitor(self.strategy).visit(child)
elif tag == 'mover':
from .mover_visitor import MoverVisitor
return MoverVisitor(self.strategy).visit(child)
elif tag == 'munderover':
from .munderover_visitor import MunderoverVisitor
return MunderoverVisitor(self.strategy).visit(child)
elif tag == 'mfenced':
from .mfenced_visitor import MfencedVisitor
return MfencedVisitor(self.strategy).visit(child)
elif tag == 'mtable':
from .mtable_visitor import MtableVisitor
return MtableVisitor(self.strategy).visit(child)
elif tag == 'mtext':
from .mtext_visitor import MtextVisitor
return MtextVisitor(self.strategy).visit(child)
elif tag == 'mstyle':
from .mstyle_visitor import MstyleVisitor
return MstyleVisitor(self.strategy).visit(child)
elif tag == 'mspace':
from .mspace_visitor import MspaceVisitor
return MspaceVisitor(self.strategy).visit(child)
elif tag == 'menclose':
from .menclose_visitor import MencloseVisitor
return MencloseVisitor(self.strategy).visit(child)
elif tag == 'mmultiscripts':
from .mmultiscripts_visitor import MmultiscriptsVisitor
return MmultiscriptsVisitor(self.strategy).visit(child)
elif tag == 'maction':
from .maction_visitor import MactionVisitor
return MactionVisitor(self.strategy).visit(child)
elif tag == 'merror':
from .merror_visitor import MerrorVisitor
return MerrorVisitor(self.strategy).visit(child)
elif tag == 'mpadded':
from .mpadded_visitor import MpaddedVisitor
return MpaddedVisitor(self.strategy).visit(child)
elif tag == 'mphantom':
from .mphantom_visitor import MphantomVisitor
return MphantomVisitor(self.strategy).visit(child)
elif tag == 'ms':
from .ms_visitor import MsVisitor
return MsVisitor(self.strategy).visit(child)
elif tag == 'mglyph':
from .mglyph_visitor import MglyphVisitor
return MglyphVisitor(self.strategy).visit(child)
elif tag == 'maligngroup':
from .maligngroup_visitor import MaligngroupVisitor
return MaligngroupVisitor(self.strategy).visit(child)
elif tag == 'malignmark':
from .malignmark_visitor import MalignmarkVisitor
return MalignmarkVisitor(self.strategy).visit(child)
elif tag == 'mlabeledtr':
from .mlabeledtr_visitor import MlabeledtrVisitor
return MlabeledtrVisitor(self.strategy).visit(child)
else:
# Fallback: return text content for unknown elements
import sys
print(f"[WARNING] Unknown element <{tag}> in msqrt, using text fallback", file=sys.stderr)
return _text_content(child)
def _brace(self, content: str) -> str:
"""Wrap content in braces."""
return f"{{{content}}}"
def can_handle(self, node: ET.Element) -> bool:
"""Check if this visitor can handle the given node."""
return _local(node.tag) == 'msqrt'
@property
def element_name(self) -> str:
"""Get the element name this visitor handles."""
return 'msqrt'
def __repr__(self) -> str:
"""String representation for debugging."""
return f"MsqrtVisitor(strategy={self.strategy.name})"