Quentin
3271fee5cc
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
464 lines
18 KiB
Python
464 lines
18 KiB
Python
r"""
|
||
Visitor for <munderover> (under+over script) MathML elements.
|
||
|
||
The <munderover> element represents content with both something above and below it:
|
||
- Large operators with limits: summation, integral, product with both bounds
|
||
- \sum_{i=1}^{n}, \int_{a}^{b}, \prod_{i=1}^{n}
|
||
- Union/intersection with limits
|
||
- General underover scripts
|
||
|
||
This visitor is CRITICAL because it handles \limits properly, unlike msubsup.
|
||
"""
|
||
|
||
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 MunderoverVisitor(Visitor):
|
||
r"""
|
||
Handles <munderover> (under+over script) MathML elements.
|
||
|
||
Converts under+over notation to appropriate LaTeX commands, especially
|
||
for large operators with both upper and lower limits.
|
||
|
||
Examples:
|
||
Summation with limits:
|
||
<munderover>
|
||
<mo>∑</mo>
|
||
<mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow>
|
||
<mi>n</mi>
|
||
</munderover> → \sum_{i=1}^{n}
|
||
|
||
Integral with bounds:
|
||
<munderover>
|
||
<mo>∫</mo>
|
||
<mi>a</mi>
|
||
<mi>b</mi>
|
||
</munderover> → \int_{a}^{b}
|
||
|
||
Product with limits:
|
||
<munderover>
|
||
<mo>∏</mo>
|
||
<mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow>
|
||
<mi>n</mi>
|
||
</munderover> → \prod_{i=1}^{n}
|
||
|
||
Union with limits:
|
||
<munderover>
|
||
<mo>⋃</mo>
|
||
<mi>i</mi>
|
||
<mi>n</mi>
|
||
</munderover> → \bigcup_{i}^{n}
|
||
|
||
General underover:
|
||
<munderover>
|
||
<mi>X</mi>
|
||
<mi>a</mi>
|
||
<mi>b</mi>
|
||
</munderover> → \overset{b}{\underset{a}{X}}
|
||
"""
|
||
|
||
def __init__(self, strategy: Strategy):
|
||
"""Initialize the Munderover visitor."""
|
||
super().__init__(strategy)
|
||
|
||
def visit(self, node: ET.Element) -> str:
|
||
r"""
|
||
Convert <munderover> element to LaTeX.
|
||
|
||
Args:
|
||
node: The <munderover> element to convert
|
||
|
||
Returns:
|
||
LaTeX string with appropriate under+over notation
|
||
|
||
Raises:
|
||
ValueError: If node is not an <munderover> element
|
||
ValueError: If munderover has fewer than 3 children
|
||
"""
|
||
if not self.can_handle(node):
|
||
raise ValueError(f"MunderoverVisitor cannot handle element '{node.tag}'")
|
||
|
||
children = list(node)
|
||
|
||
# munderover must have exactly 3 children: base, underscript, overscript
|
||
if len(children) < 3:
|
||
raise ValueError(
|
||
f"munderover element must have 3 children (base, under, over), "
|
||
f"got {len(children)}"
|
||
)
|
||
|
||
base = self._convert_child(children[0])
|
||
under = self._convert_child(children[1])
|
||
over = self._convert_child(children[2])
|
||
|
||
# Check if base is a large operator (sum, integral, product, etc.)
|
||
if self._is_large_operator(children[0]):
|
||
# Use subscript/superscript notation for operator limits with \limits
|
||
# \sum\limits_{i=1}^{n}
|
||
return f"{base}\\limits_{self._brace(under)}^{self._brace(over)}"
|
||
|
||
# Check if this should use \limits explicitly
|
||
# (for operators that don't default to limit placement)
|
||
if self._should_use_limits(children[0]):
|
||
return f"{base}\\limits_{self._brace(under)}^{self._brace(over)}"
|
||
|
||
# Check for extensible arrow patterns (arrows/equals with text above and below)
|
||
# This is commonly used for chemical reactions and annotated arrows
|
||
# First, unwrap mrow if the base is wrapped (Word often does this)
|
||
base_node = children[0]
|
||
if _local(base_node.tag) == 'mrow':
|
||
# Check if mrow contains a single operator/arrow
|
||
mrow_children = list(base_node)
|
||
if len(mrow_children) == 1 and _local(mrow_children[0].tag) in ('mo', 'mi', 'mtext'):
|
||
base_node = mrow_children[0]
|
||
|
||
xarrow_cmd = self._get_xarrow_command(base_node)
|
||
if xarrow_cmd:
|
||
# Check if original content had \mathrm{} (indicates mathvariant="normal")
|
||
# We need to preserve this semantic after cleaning
|
||
over_had_mathrm = '\\mathrm{' in over
|
||
under_had_mathrm = '\\mathrm{' in under
|
||
|
||
# Clean up the text (remove \phantom{}, \mathrm{}, \text{}, extra spaces)
|
||
over_clean = self._clean_arrow_text(over)
|
||
under_clean = self._clean_arrow_text(under)
|
||
|
||
# Re-wrap text in \mathrm{} if:
|
||
# 1. Original content had \mathrm{} (from mathvariant="normal")
|
||
# 2. Or in chemistry mode for non-command text
|
||
# This preserves the mathvariant="normal" semantic from the input MathML
|
||
# Skip if it's already a LaTeX command (starts with \) or empty
|
||
# Also skip pure numbers (like "1", "222", "2121") - they should remain plain
|
||
|
||
def should_wrap_mathrm(text: str, had_mathrm: bool) -> bool:
|
||
if not text or not text.strip():
|
||
return False
|
||
if text.startswith("\\"):
|
||
return False # Already a LaTeX command
|
||
if text.replace('.', '', 1).isdigit():
|
||
return False # Pure number
|
||
# Wrap if original had \mathrm{} OR in chemistry mode
|
||
if had_mathrm:
|
||
return True
|
||
if hasattr(self.strategy, 'name') and self.strategy.name == "chemistry":
|
||
return True
|
||
return False
|
||
|
||
if should_wrap_mathrm(over_clean, over_had_mathrm):
|
||
over_clean = f"\\mathrm{{{over_clean}}}"
|
||
if should_wrap_mathrm(under_clean, under_had_mathrm):
|
||
under_clean = f"\\mathrm{{{under_clean}}}"
|
||
|
||
# Use \quad for empty positions (from <mphantom> elements)
|
||
# This creates proper spacing in chemical equations
|
||
if not under_clean or under_clean.strip() == "":
|
||
under_clean = "\\quad"
|
||
if not over_clean or over_clean.strip() == "":
|
||
over_clean = "\\quad"
|
||
|
||
return f"\\{xarrow_cmd}[{under_clean}]{{{over_clean}}}"
|
||
|
||
# Default: general under+over using nested \overset and \underset
|
||
# \overset{b}{\underset{a}{X}}
|
||
return f"\\overset{self._brace(over)}{{\\underset{self._brace(under)}{self._brace(base)}}}"
|
||
|
||
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 munderover, using text fallback", file=sys.stderr)
|
||
return _text_content(child)
|
||
|
||
def _is_large_operator(self, base_node: ET.Element) -> bool:
|
||
"""
|
||
Check if base is a large operator that uses limits by default.
|
||
|
||
Recursively searches through wrapper elements like <mstyle>, <mrow>, <mpadded>
|
||
to find the actual operator, since Word often wraps large operators in
|
||
<mstyle mathsize="140%"><mrow><mo>∑</mo></mrow></mstyle>.
|
||
"""
|
||
if base_node is None:
|
||
return False
|
||
|
||
tag = _local(base_node.tag)
|
||
|
||
# Large operators that display limits above/below in display mode
|
||
large_ops = [
|
||
"∑", "\\sum", # Summation
|
||
"∏", "\\prod", # Product
|
||
"∐", "\\coprod", # Coproduct
|
||
"∫", "\\int", # Integral
|
||
"∬", "\\iint", # Double integral
|
||
"∭", "\\iiint", # Triple integral
|
||
"∮", "\\oint", # Contour integral
|
||
"⋃", "\\bigcup", # Union
|
||
"⋂", "\\bigcap", # Intersection
|
||
"⋁", "\\bigvee", # Logical OR
|
||
"⋀", "\\bigwedge", # Logical AND
|
||
"⨁", "\\bigoplus", # Direct sum
|
||
"⨂", "\\bigotimes", # Tensor product
|
||
"⨄", "\\biguplus", # Multiset union
|
||
]
|
||
|
||
# Check direct <mo> or <mi> elements
|
||
if tag in ('mo', 'mi'):
|
||
base_text = _text_content(base_node).strip()
|
||
return base_text in large_ops
|
||
|
||
# Recursively search through wrapper elements (mstyle, mrow, mpadded, menclose)
|
||
# This handles Word's pattern: <munderover><mstyle><mrow><mo>∑</mo></mrow></mstyle>...
|
||
if tag in ('mstyle', 'mrow', 'mpadded', 'menclose'):
|
||
for child in base_node:
|
||
if self._is_large_operator(child):
|
||
return True
|
||
|
||
return False
|
||
|
||
def _should_use_limits(self, base_node: ET.Element) -> bool:
|
||
"""Check if operator should explicitly use \\limits."""
|
||
if _local(base_node.tag) != 'mo':
|
||
return False
|
||
|
||
base_text = _text_content(base_node).strip()
|
||
|
||
# Operators that need explicit \limits to display limits above/below
|
||
limits_ops = [
|
||
"lim", "\\lim", # Limit
|
||
"sup", "\\sup", # Supremum
|
||
"inf", "\\inf", # Infimum
|
||
"max", "\\max", # Maximum
|
||
"min", "\\min", # Minimum
|
||
"limsup", "\\limsup", # Limit superior
|
||
"liminf", "\\liminf", # Limit inferior
|
||
"det", "\\det", # Determinant
|
||
"gcd", "\\gcd", # Greatest common divisor
|
||
]
|
||
|
||
return base_text in limits_ops
|
||
|
||
def _brace(self, content: str) -> str:
|
||
"""Wrap content in braces."""
|
||
return f"{{{content}}}"
|
||
|
||
def _get_xarrow_command(self, base_node: ET.Element) -> str:
|
||
"""
|
||
Get extensible arrow command for the base element.
|
||
|
||
Returns command name (without backslash) if base is an arrow/equals,
|
||
otherwise returns empty string.
|
||
|
||
Supported arrows:
|
||
- = → xlongequal
|
||
- → → xrightarrow
|
||
- ← → xleftarrow
|
||
- ↔ → xleftrightarrow
|
||
- ⇌ → xrightleftharpoons
|
||
"""
|
||
# Accept <mo> (operator), <mi> (identifier), and <mtext> (text) elements for arrows
|
||
# Word's XSLT sometimes produces <mi> for arrows instead of <mo>
|
||
if _local(base_node.tag) not in ('mo', 'mi', 'mtext'):
|
||
return ""
|
||
|
||
base_text = _text_content(base_node).strip()
|
||
|
||
# Map arrow symbols to xarrow commands
|
||
arrow_map = {
|
||
"=": "xlongequal",
|
||
"→": "xrightarrow",
|
||
"\\rightarrow": "xrightarrow",
|
||
"←": "xleftarrow",
|
||
"\\leftarrow": "xleftarrow",
|
||
"↔": "xleftrightarrow",
|
||
"\\leftrightarrow": "xleftrightarrow",
|
||
"⟷": "xleftrightarrow", # U+27F7 long left-right arrow
|
||
"\\longleftrightarrow": "xleftrightarrow",
|
||
"⇌": "xrightleftharpoons",
|
||
"\\rightleftharpoons": "xrightleftharpoons",
|
||
}
|
||
|
||
return arrow_map.get(base_text, "")
|
||
|
||
def _clean_arrow_text(self, text: str) -> str:
|
||
"""
|
||
Clean up text for use in arrow labels.
|
||
|
||
Removes:
|
||
- \\phantom{} wrappers (Word uses these for arrow labels)
|
||
- \\mathrm{} wrappers (with proper nested brace handling)
|
||
- \\text{} wrappers
|
||
- Extra spaces between characters
|
||
"""
|
||
import re
|
||
|
||
# Helper function to remove LaTeX commands with balanced braces
|
||
def remove_command(text: str, command: str) -> str:
|
||
"""Remove LaTeX command with proper brace balancing.
|
||
|
||
Args:
|
||
text: Input text with LaTeX commands
|
||
command: Command to remove (e.g., "\\mathrm" or "mathrm")
|
||
"""
|
||
# Normalize command: ensure it starts with backslash
|
||
if not command.startswith('\\'):
|
||
command = '\\' + command
|
||
|
||
while command in text:
|
||
# Find the command
|
||
idx = text.find(command)
|
||
if idx == -1:
|
||
break
|
||
|
||
# Find the opening brace (should be right after command)
|
||
brace_start = idx + len(command)
|
||
if brace_start >= len(text) or text[brace_start] != '{':
|
||
break # Malformed - no opening brace
|
||
|
||
# Match balanced braces
|
||
brace_count = 1
|
||
pos = brace_start + 1
|
||
while pos < len(text) and brace_count > 0:
|
||
if text[pos] == '{' and (pos == 0 or text[pos-1] != '\\'):
|
||
brace_count += 1
|
||
elif text[pos] == '}' and (pos == 0 or text[pos-1] != '\\'):
|
||
brace_count -= 1
|
||
pos += 1
|
||
|
||
if brace_count == 0:
|
||
# Successfully matched braces
|
||
content = text[brace_start+1:pos-1]
|
||
text = text[:idx] + content + text[pos:]
|
||
else:
|
||
break # Malformed braces
|
||
|
||
return text
|
||
|
||
# Remove \phantom{} wrappers (Word's equation editor uses these for arrow labels)
|
||
text = remove_command(text, '\\phantom')
|
||
|
||
# Remove \mathrm{} wrappers (with nested brace handling)
|
||
text = remove_command(text, '\\mathrm')
|
||
|
||
# Remove \text{} wrappers (but keep the content)
|
||
# For Chinese text, we want to preserve it as-is
|
||
text = remove_command(text, '\\text')
|
||
|
||
# Remove extra spaces between individual characters
|
||
# "高 压" → "高压", but preserve intentional spaces in phrases
|
||
text = re.sub(r'(?<=[\u4e00-\u9fff])\s+(?=[\u4e00-\u9fff])', '', text)
|
||
|
||
# For non-Chinese text with spaces between each char, remove spaces
|
||
# "a b c" → "abc", but "word1 word2" stays as-is
|
||
if len(text.replace(' ', '')) > 0:
|
||
# Check if it's all single chars separated by spaces
|
||
parts = text.split()
|
||
if all(len(p) == 1 for p in parts):
|
||
text = ''.join(parts)
|
||
|
||
return text.strip()
|
||
|
||
def can_handle(self, node: ET.Element) -> bool:
|
||
"""Check if this visitor can handle the given node."""
|
||
return _local(node.tag) == 'munderover'
|
||
|
||
@property
|
||
def element_name(self) -> str:
|
||
"""Get the element name this visitor handles."""
|
||
return 'munderover'
|
||
|
||
def __repr__(self) -> str:
|
||
"""String representation for debugging."""
|
||
return f"MunderoverVisitor(strategy={self.strategy.name})"
|