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:
2026-09-29 09:43:13 +08:00
commit 3271fee5cc
360 changed files with 86082 additions and 0 deletions

View File

@@ -0,0 +1,288 @@
r"""
Visitor for <mmultiscripts> (tensor notation) MathML elements.
The <mmultiscripts> element is used to attach prescripts and postscripts to a base element.
It's commonly used in physics and chemistry for tensor notation, nuclear notation, etc.
Structure:
<mmultiscripts>
<base/> <!-- Base element -->
<sub1/> <sup1/> <!-- First postscript pair -->
<sub2/> <sup2/> <!-- Second postscript pair -->
<mprescripts/> <!-- Separator -->
<presub1/> <presup1/> <!-- First prescript pair -->
<presub2/> <presup2/> <!-- Second prescript pair -->
</mmultiscripts>
This visitor handles both prescripts (left side) and postscripts (right side) with \sideset.
"""
from lxml import etree as ET
from ..core.interfaces import Visitor, Strategy
from ..utils import local_name as _local
class MmultiscriptsVisitor(Visitor):
r"""
Handles <mmultiscripts> (tensor notation) MathML elements.
Converts prescripts and postscripts to LaTeX using \sideset for bidirectional scripts.
Examples:
Only postscripts:
<mmultiscripts>
<mi>R</mi>
<mn>1</mn><mn>2</mn>
</mmultiscripts>
→ R_{1}^{2}
Only prescripts:
<mmultiscripts>
<mi>R</mi>
<mprescripts/>
<mn>1</mn><mn>2</mn>
</mmultiscripts>
→ _{1}^{2}R
Both prescripts and postscripts:
<mmultiscripts>
<mi>R</mi>
<mn>3</mn><mn>4</mn>
<mprescripts/>
<mn>1</mn><mn>2</mn>
</mmultiscripts>
→ \sideset{_{1}^{2}}{_{3}^{4}}{R}
Multiple postscripts:
<mmultiscripts>
<mi>R</mi>
<mi>i</mi><mi>j</mi>
<mi>k</mi><mi>l</mi>
</mmultiscripts>
→ R_{i}^{j}_{k}^{l}
None elements (empty script positions):
<mmultiscripts>
<mi>R</mi>
<none/><mn>2</mn>
<mprescripts/>
<mn>1</mn><none/>
</mmultiscripts>
→ \sideset{_{1}}{^{2}}{R}
"""
def __init__(self, strategy: Strategy):
"""Initialize the Mmultiscripts visitor."""
super().__init__(strategy)
def visit(self, node: ET.Element) -> str:
r"""
Convert <mmultiscripts> element to LaTeX with tensor notation.
Args:
node: The <mmultiscripts> element to convert
Returns:
LaTeX string with prescripts and postscripts
Raises:
ValueError: If node is not a <mmultiscripts> element
"""
if not self.can_handle(node):
raise ValueError(f"MmultiscriptsVisitor cannot handle element '{node.tag}'")
if len(node) == 0:
return ""
# First child is the base element
base = self._convert_child(node[0])
scripts = list(node)[1:] # Skip base element
# Find mprescripts separator
prescript_idx = None
for i, child in enumerate(scripts):
if _local(child.tag) == "mprescripts":
prescript_idx = i
break
if prescript_idx is None:
# Only postscripts
postscripts = scripts
prescripts = []
else:
postscripts = scripts[:prescript_idx]
prescripts = scripts[prescript_idx + 1:]
# Process postscripts (pairs of sub/sup)
postscript_parts = self._process_script_pairs(postscripts)
# Process prescripts (pairs of sub/sup)
prescript_parts = self._process_script_pairs(prescripts)
# Use \sideset when there are scripts on both sides
if prescript_parts and postscript_parts:
left_scripts = "".join(prescript_parts)
right_scripts = "".join(postscript_parts)
return f"\\sideset{{{left_scripts}}}{{{right_scripts}}}{{{base}}}"
elif prescript_parts:
# Only left scripts - direct positioning
return f"{''.join(prescript_parts)}{base}"
elif postscript_parts:
# Only right scripts
return f"{base}{''.join(postscript_parts)}"
else:
return base
def _process_script_pairs(self, scripts: list) -> list:
"""
Process script pairs (sub/sup) from the scripts list.
Scripts come in pairs: subscript, superscript, subscript, superscript, ...
<none/> elements represent empty positions.
Args:
scripts: List of script elements (pairs of sub/sup)
Returns:
List of LaTeX script strings
"""
parts = []
for i in range(0, len(scripts), 2):
sub = self._convert_script(scripts[i]) if i < len(scripts) else ""
sup = self._convert_script(scripts[i + 1]) if i + 1 < len(scripts) else ""
if sub and sup:
parts.append(f"_{{{sub}}}^{{{sup}}}")
elif sub:
parts.append(f"_{{{sub}}}")
elif sup:
parts.append(f"^{{{sup}}}")
return parts
def _convert_script(self, child: ET.Element) -> str:
"""
Convert a script element to LaTeX.
Handles <none/> elements (empty script positions).
Args:
child: Script element to convert
Returns:
LaTeX string for the script (empty for <none/>)
"""
if _local(child.tag) == "none":
return ""
return self._convert_child(child)
def _convert_child(self, child: ET.Element) -> str:
"""Convert a child element to LaTeX."""
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':
from .msqrt_visitor import MsqrtVisitor
return MsqrtVisitor(self.strategy).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 mmultiscripts, using text fallback", file=sys.stderr)
return _text_content(child)
def can_handle(self, node: ET.Element) -> bool:
"""Check if this visitor can handle the given node."""
return _local(node.tag) == 'mmultiscripts'
@property
def element_name(self) -> str:
"""Get the element name this visitor handles."""
return 'mmultiscripts'
def __repr__(self) -> str:
"""String representation for debugging."""
return f"MmultiscriptsVisitor(strategy={self.strategy.name})"