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:
426
scripts/omml_mathml2latex/visitors/menclose_visitor.py
Normal file
426
scripts/omml_mathml2latex/visitors/menclose_visitor.py
Normal file
@@ -0,0 +1,426 @@
|
||||
r"""
|
||||
Visitor for <menclose> (box/cancel notation) MathML elements.
|
||||
|
||||
The <menclose> element is used to enclose mathematical content with
|
||||
various notations including boxes, circles, strike-throughs, and partial frames.
|
||||
|
||||
This visitor handles notation attribute values like:
|
||||
- box: Full box around content
|
||||
- circle: Circle around content
|
||||
- horizontalstrike, verticalstrike: Strike-through lines
|
||||
- updiagonalstrike, downdiagonalstrike: Diagonal strike-through
|
||||
- top, bottom, left, right: Partial box sides
|
||||
- actuarial, longdiv, radical: Specialized notations
|
||||
"""
|
||||
|
||||
from lxml import etree as ET
|
||||
from ..core.interfaces import Visitor, Strategy
|
||||
from ..utils import local_name as _local
|
||||
|
||||
|
||||
class MencloseVisitor(Visitor):
|
||||
r"""
|
||||
Handles <menclose> (box/cancel notation) MathML elements.
|
||||
|
||||
Converts various notation attributes to appropriate LaTeX commands.
|
||||
|
||||
Examples:
|
||||
Box notation:
|
||||
<menclose notation="box"><mi>x</mi></menclose>
|
||||
→ \boxed{x}
|
||||
|
||||
Horizontal strike:
|
||||
<menclose notation="horizontalstrike"><mi>x</mi></menclose>
|
||||
→ \cancel{x}
|
||||
|
||||
Diagonal strike (up):
|
||||
<menclose notation="updiagonalstrike"><mi>x</mi></menclose>
|
||||
→ \cancel{x}
|
||||
|
||||
Diagonal strike (down):
|
||||
<menclose notation="downdiagonalstrike"><mi>x</mi></menclose>
|
||||
→ \bcancel{x}
|
||||
|
||||
Combined diagonal strikes:
|
||||
<menclose notation="updiagonalstrike downdiagonalstrike"><mi>x</mi></menclose>
|
||||
→ \xcancel{x}
|
||||
|
||||
Top line only:
|
||||
<menclose notation="top"><mi>x</mi></menclose>
|
||||
→ \overline{x}
|
||||
|
||||
Bottom line only:
|
||||
<menclose notation="bottom"><mi>x</mi></menclose>
|
||||
→ \underline{x}
|
||||
|
||||
Left delimiter:
|
||||
<menclose notation="left"><mi>x</mi></menclose>
|
||||
→ \left| x \right.
|
||||
|
||||
Right delimiter:
|
||||
<menclose notation="right"><mi>x</mi></menclose>
|
||||
→ \left. x \right|
|
||||
|
||||
Circle notation:
|
||||
<menclose notation="circle"><mi>x</mi></menclose>
|
||||
→ \circled{x}
|
||||
|
||||
Actuarial notation:
|
||||
<menclose notation="actuarial"><mi>x</mi></menclose>
|
||||
→ \overline{\underline{x}}
|
||||
|
||||
Long division:
|
||||
<menclose notation="longdiv"><mi>x</mi></menclose>
|
||||
→ \enclose{longdiv}{x}
|
||||
|
||||
Radical notation:
|
||||
<menclose notation="radical"><mi>x</mi></menclose>
|
||||
→ \sqrt{x}
|
||||
"""
|
||||
|
||||
def __init__(self, strategy: Strategy):
|
||||
"""Initialize the Menclose visitor."""
|
||||
super().__init__(strategy)
|
||||
|
||||
def visit(self, node: ET.Element) -> str:
|
||||
r"""
|
||||
Convert <menclose> element to LaTeX with appropriate notation.
|
||||
|
||||
Args:
|
||||
node: The <menclose> element to convert
|
||||
|
||||
Returns:
|
||||
LaTeX string with notation applied to content
|
||||
|
||||
Raises:
|
||||
ValueError: If node is not a <menclose> element
|
||||
"""
|
||||
if not self.can_handle(node):
|
||||
raise ValueError(f"MencloseVisitor cannot handle element '{node.tag}'")
|
||||
|
||||
notation = node.get("notation", "box")
|
||||
|
||||
# Special case: box containing mfrac with underlined/overlined numerator (like chemical reaction conditions)
|
||||
# Pattern: <menclose notation="box"><mfrac><munder>text<mo>‾</mo></munder><empty/></mfrac></menclose>
|
||||
# Remove the box but preserve the fraction structure: \dfrac{\underline{text}}{}
|
||||
# Also handles: <menclose notation="box"><mrow><mfrac>...</mfrac></mrow></menclose>
|
||||
mfrac_node = None
|
||||
if notation == "box" and len(node) == 1:
|
||||
child = node[0]
|
||||
child_tag = _local(child.tag)
|
||||
|
||||
# Direct mfrac child
|
||||
if child_tag == "mfrac":
|
||||
mfrac_node = child
|
||||
# mfrac wrapped in mrow (Word often does this)
|
||||
elif child_tag == "mrow" and len(child) == 1 and _local(child[0].tag) == "mfrac":
|
||||
mfrac_node = child[0]
|
||||
|
||||
if mfrac_node is not None and len(mfrac_node) >= 2:
|
||||
numerator_node = mfrac_node[0]
|
||||
# Check if numerator contains underlined text (munder with line character)
|
||||
if self._contains_underlined_text(numerator_node):
|
||||
# Convert the fraction directly without the box
|
||||
# This preserves the \dfrac structure with underlined numerator
|
||||
return self._convert_child(mfrac_node)
|
||||
|
||||
content = self._convert_children(node)
|
||||
|
||||
# Skip boxing for assignment expressions
|
||||
if notation == "box" and self._contains_assignment(content):
|
||||
return content
|
||||
|
||||
# Parse notation (could be space-separated multi-value)
|
||||
notations = notation.split()
|
||||
|
||||
# === COMBINED STRIKE NOTATIONS (check these FIRST) ===
|
||||
|
||||
# Combined diagonal strikes → \xcancel
|
||||
if "updiagonalstrike" in notations and "downdiagonalstrike" in notations:
|
||||
return f"\\xcancel{{{content}}}"
|
||||
|
||||
# Combined horizontal and vertical strikes → \cancel
|
||||
if "horizontalstrike" in notations and "verticalstrike" in notations:
|
||||
return f"\\cancel{{{content}}}"
|
||||
|
||||
# === SIDE-SPECIFIC NOTATIONS FOR PARTIAL BOXES ===
|
||||
|
||||
sides = [n for n in notations if n in ["top", "bottom", "left", "right"]]
|
||||
side_count = len(sides)
|
||||
|
||||
# Single side visible
|
||||
if side_count == 1:
|
||||
side = sides[0]
|
||||
|
||||
if side == "top":
|
||||
return f"\\overline{{{content}}}"
|
||||
elif side == "bottom":
|
||||
return f"\\underline{{{content}}}"
|
||||
elif side == "left":
|
||||
return f"\\left| {content} \\right."
|
||||
elif side == "right":
|
||||
return f"\\left. {content} \\right|"
|
||||
|
||||
# Full box (4 sides or explicit "box" notation)
|
||||
elif "box" in notations or side_count == 4:
|
||||
return f"\\boxed{{{content}}}"
|
||||
|
||||
# Partial box (2-3 sides)
|
||||
elif side_count >= 2:
|
||||
notation_str = " ".join(sides)
|
||||
return f"\\enclose{{{notation_str}}}{{{content}}}"
|
||||
|
||||
# === INDIVIDUAL STRIKE NOTATIONS ===
|
||||
|
||||
if notation == "horizontalstrike":
|
||||
return f"\\cancel{{{content}}}"
|
||||
|
||||
if notation == "verticalstrike":
|
||||
return f"\\bcancel{{{content}}}"
|
||||
|
||||
if notation == "updiagonalstrike":
|
||||
return f"\\cancel{{{content}}}"
|
||||
|
||||
if notation == "downdiagonalstrike":
|
||||
return f"\\bcancel{{{content}}}"
|
||||
|
||||
# === OTHER NOTATIONS ===
|
||||
|
||||
if notation == "circle":
|
||||
return f"\\circled{{{content}}}"
|
||||
|
||||
if notation == "roundedbox":
|
||||
return f"\\boxed{{{content}}}"
|
||||
|
||||
if notation == "actuarial":
|
||||
return f"\\overline{{\\underline{{{content}}}}}"
|
||||
|
||||
if notation == "longdiv":
|
||||
return f"\\enclose{{longdiv}}{{{content}}}"
|
||||
|
||||
if notation == "radical":
|
||||
return f"\\sqrt{{{content}}}"
|
||||
|
||||
# Default: just return content without notation
|
||||
return content
|
||||
|
||||
def _convert_children(self, node: ET.Element) -> str:
|
||||
"""
|
||||
Convert all child elements to LaTeX.
|
||||
|
||||
Args:
|
||||
node: The <menclose> element
|
||||
|
||||
Returns:
|
||||
LaTeX string with all children converted
|
||||
"""
|
||||
parts = []
|
||||
for child in node:
|
||||
parts.append(self._convert_child(child))
|
||||
return ''.join(parts).strip()
|
||||
|
||||
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 menclose, using text fallback", file=sys.stderr)
|
||||
return _text_content(child)
|
||||
|
||||
def _is_empty_denominator(self, node: ET.Element) -> bool:
|
||||
"""
|
||||
Check if denominator node is empty (no content or only whitespace).
|
||||
|
||||
Args:
|
||||
node: MathML denominator element to check
|
||||
|
||||
Returns:
|
||||
True if denominator is empty
|
||||
"""
|
||||
if node is None:
|
||||
return True
|
||||
|
||||
tag = _local(node.tag)
|
||||
|
||||
# Empty <mo> tag
|
||||
if tag == "mo":
|
||||
text = node.text or ""
|
||||
return text.strip() == ""
|
||||
|
||||
# Empty <mrow/> tag
|
||||
if tag == "mrow":
|
||||
# No children
|
||||
if len(node) == 0:
|
||||
return True
|
||||
# Only whitespace <mo> child
|
||||
if len(node) == 1 and _local(node[0].tag) == "mo":
|
||||
mo_text = node[0].text or ""
|
||||
return mo_text.strip() == ""
|
||||
|
||||
return False
|
||||
|
||||
def _contains_assignment(self, content: str) -> bool:
|
||||
"""
|
||||
Check if content contains assignment operators.
|
||||
|
||||
Assignment expressions should not be boxed.
|
||||
Note: We only skip boxing for explicit assignment operators like :=
|
||||
NOT for regular equality = which is often used in boxed theorems.
|
||||
|
||||
Args:
|
||||
content: LaTeX content to check
|
||||
|
||||
Returns:
|
||||
True if content contains assignment operators
|
||||
"""
|
||||
# Only specific assignment operators - NOT plain = which appears in boxed theorems
|
||||
assignment_ops = [":=", ": =", "∶=", "∶ =", "≔", "\\coloneqq"]
|
||||
return any(op in content for op in assignment_ops)
|
||||
|
||||
def _contains_underlined_text(self, node: ET.Element) -> bool:
|
||||
"""
|
||||
Check if node contains underlined text (munder with line character)
|
||||
OR overlined text (mover with line character).
|
||||
|
||||
This is used to detect chemical reaction conditions and malformed equals.
|
||||
|
||||
Args:
|
||||
node: MathML element to check
|
||||
|
||||
Returns:
|
||||
True if node contains underlined or overlined text
|
||||
"""
|
||||
if node is None:
|
||||
return False
|
||||
|
||||
tag = _local(node.tag)
|
||||
|
||||
# Check if this node itself is an underlined element (munder with line)
|
||||
if tag == "munder" and len(node) > 1:
|
||||
under_node = node[1]
|
||||
if _local(under_node.tag) == "mo":
|
||||
# Get text content
|
||||
text = under_node.text or ""
|
||||
if "‾" in text: # Line character
|
||||
return True
|
||||
|
||||
# Check if this node is an overlined element (mover with line)
|
||||
# This handles the "malformed equal" pattern where users put overline in fraction
|
||||
if tag == "mover" and len(node) > 1:
|
||||
over_node = node[1]
|
||||
if _local(over_node.tag) == "mo":
|
||||
# Get text content
|
||||
text = over_node.text or ""
|
||||
# Check for overline/bar characters
|
||||
if text.strip() in ["¯", "‾", "―", "−", "⎺", "⎻", "-", "_"]:
|
||||
return True
|
||||
|
||||
# Recursively check children
|
||||
for child in node:
|
||||
if self._contains_underlined_text(child):
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def can_handle(self, node: ET.Element) -> bool:
|
||||
"""Check if this visitor can handle the given node."""
|
||||
return _local(node.tag) == 'menclose'
|
||||
|
||||
@property
|
||||
def element_name(self) -> str:
|
||||
"""Get the element name this visitor handles."""
|
||||
return 'menclose'
|
||||
|
||||
def __repr__(self) -> str:
|
||||
"""String representation for debugging."""
|
||||
return f"MencloseVisitor(strategy={self.strategy.name})"
|
||||
Reference in New Issue
Block a user