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:
304
scripts/omml_mathml2latex/strategies/statistics_strategy.py
Normal file
304
scripts/omml_mathml2latex/strategies/statistics_strategy.py
Normal file
@@ -0,0 +1,304 @@
|
||||
"""
|
||||
Statistics strategy for statistical notation.
|
||||
|
||||
This strategy handles formatting for statistical equations, including
|
||||
probability operators, distribution notation, and statistical symbols.
|
||||
"""
|
||||
|
||||
from lxml import etree as ET
|
||||
from typing import Set
|
||||
from ..core.interfaces import Strategy
|
||||
|
||||
# Import from existing data modules
|
||||
from ..data import UNICODE_TO_LATEX, MATH_FUNCTIONS, UNICODE_PASSTHROUGH
|
||||
|
||||
|
||||
class StatisticsStrategy(Strategy):
|
||||
"""
|
||||
Statistical notation strategy.
|
||||
|
||||
This strategy provides formatting for statistical content:
|
||||
- Probability operators → \\Pr, \\operatorname{Var}, \\operatorname{Cov}
|
||||
- Expected value E remains italic (use mathvariant="double-struck" for \\mathbb{E})
|
||||
- Distribution notation → proper formatting
|
||||
- Statistical symbols → Greek letters, operators
|
||||
- Variables remain italic (LaTeX default)
|
||||
"""
|
||||
|
||||
# Mathematical functions that get special LaTeX commands
|
||||
FUNCTIONS: Set[str] = MATH_FUNCTIONS
|
||||
|
||||
# Statistical functions and operators (upright)
|
||||
# CRITICAL: 'E' is NOT in this list - it's just a regular identifier
|
||||
# Only use \mathbb{E} when there's explicit mathvariant="double-struck" attribute
|
||||
STATISTICAL_OPERATORS: Set[str] = {
|
||||
'Pr', # Probability
|
||||
# 'E', # Expected value - REMOVED: should remain italic unless mathvariant specified
|
||||
'Var', # Variance
|
||||
'Cov', # Covariance
|
||||
'Cor', # Correlation
|
||||
'SD', # Standard deviation
|
||||
'SE', # Standard error
|
||||
'MSE', # Mean squared error
|
||||
'RSS', # Residual sum of squares
|
||||
'SSE', # Sum of squared errors
|
||||
'Bias', # Bias
|
||||
'df', # degrees of freedom
|
||||
'logit', # Logit function
|
||||
'probit', # Probit function
|
||||
}
|
||||
|
||||
# Distribution names (upright)
|
||||
DISTRIBUTIONS: Set[str] = {
|
||||
'Normal',
|
||||
'Binomial',
|
||||
'Poisson',
|
||||
'Exponential',
|
||||
'Uniform',
|
||||
'Gamma',
|
||||
'Beta',
|
||||
'Bernoulli',
|
||||
'Geometric',
|
||||
'Hypergeometric',
|
||||
'Multinomial',
|
||||
'NegativeBinomial',
|
||||
'Chi',
|
||||
'ChiSquared',
|
||||
'Student',
|
||||
'F',
|
||||
'Weibull',
|
||||
'Cauchy',
|
||||
'Laplace',
|
||||
'Logistic',
|
||||
'Pareto',
|
||||
}
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the statistics strategy."""
|
||||
pass
|
||||
|
||||
def format_identifier(self, text: str, node: ET.Element) -> str:
|
||||
"""
|
||||
Format an identifier (<mi> element) for statistics.
|
||||
|
||||
Args:
|
||||
text: The identifier text content
|
||||
node: The <mi> element node
|
||||
|
||||
Returns:
|
||||
Formatted LaTeX string
|
||||
|
||||
Logic:
|
||||
1. Mathematical functions → \\function (e.g., "sin" → "\\sin")
|
||||
2. Statistical operators → \\operatorname{op} (e.g., "Var" → "\\operatorname{Var}")
|
||||
3. Distribution names → \\mathrm{dist} (e.g., "Normal" → "\\mathrm{Normal}")
|
||||
4. Single letters → unchanged (variables remain italic)
|
||||
5. Greek letters → LaTeX symbols
|
||||
|
||||
Examples:
|
||||
"Pr" → "\\Pr"
|
||||
"E" → "E" (expected value - remains italic unless mathvariant="double-struck")
|
||||
"Var" → "\\operatorname{Var}"
|
||||
"Normal" → "\\mathrm{Normal}"
|
||||
"μ" → "\\mu"
|
||||
"σ" → "\\sigma"
|
||||
"x" → "x" (random variable)
|
||||
"""
|
||||
# Check if it's a mathematical function
|
||||
if text in self.FUNCTIONS:
|
||||
return f"\\{text}"
|
||||
|
||||
# Special statistical operators with LaTeX commands
|
||||
if text == 'Pr':
|
||||
return '\\Pr'
|
||||
elif text in self.STATISTICAL_OPERATORS:
|
||||
# CRITICAL: Do NOT automatically convert 'E' to \mathbb{E}!
|
||||
# Only apply \mathbb{} when there's explicit mathvariant="double-struck" attribute
|
||||
# The mi_visitor will handle mathvariant attributes properly.
|
||||
# In statistics mode, treat 'E' like other operators (upright but not blackboard bold)
|
||||
return f"\\operatorname{{{text}}}"
|
||||
|
||||
# Distribution names (upright)
|
||||
if text in self.DISTRIBUTIONS:
|
||||
return f"\\mathrm{{{text}}}"
|
||||
|
||||
# UNICODE_PASSTHROUGH: Keep certain symbols as Unicode for MathJax compatibility
|
||||
if text in UNICODE_PASSTHROUGH:
|
||||
return text
|
||||
|
||||
# Check for Unicode symbols (Greek letters)
|
||||
if text in UNICODE_TO_LATEX:
|
||||
return UNICODE_TO_LATEX[text]
|
||||
|
||||
# Handle multi-character strings
|
||||
if len(text) > 1:
|
||||
# Check if it contains Unicode (passthrough or convertible)
|
||||
has_unicode = any(char in UNICODE_TO_LATEX for char in text)
|
||||
has_passthrough = any(char in UNICODE_PASSTHROUGH for char in text)
|
||||
if has_unicode or has_passthrough:
|
||||
converted_parts = []
|
||||
for char in text:
|
||||
if char in UNICODE_PASSTHROUGH:
|
||||
converted_parts.append(char)
|
||||
elif char in UNICODE_TO_LATEX:
|
||||
converted_parts.append(UNICODE_TO_LATEX[char])
|
||||
elif char.isspace():
|
||||
converted_parts.append(' ')
|
||||
else:
|
||||
converted_parts.append(char)
|
||||
return ' '.join(converted_parts)
|
||||
|
||||
# Default: return as-is (variables remain italic in LaTeX)
|
||||
return text
|
||||
|
||||
def format_operator(self, text: str, node: ET.Element) -> str:
|
||||
"""
|
||||
Format an operator (<mo> element) for statistics.
|
||||
|
||||
Args:
|
||||
text: The operator text content
|
||||
node: The <mo> element node
|
||||
|
||||
Returns:
|
||||
Formatted LaTeX string
|
||||
|
||||
Logic:
|
||||
1. Delimiters → __DELIM__ markers for later processing
|
||||
2. Unicode symbols → LaTeX equivalents (via UNICODE_TO_LATEX)
|
||||
3. Statistical symbols → proper notation (~, ∼, ≈, etc.)
|
||||
4. Standard operators → unchanged (+, -, *, /, =)
|
||||
|
||||
Examples:
|
||||
"(" → "__DELIM__(__DELIM__"
|
||||
"~" → "\\sim" (distributed as)
|
||||
"∼" → "\\sim"
|
||||
"≈" → "\\approx"
|
||||
"∝" → "\\propto" (proportional to)
|
||||
"∈" → "\\in"
|
||||
"""
|
||||
# CRITICAL: Mark delimiters for potential scaling
|
||||
# This matches MathStrategy behavior
|
||||
if text in ("(", ")", "[", "]", "{", "}"):
|
||||
return f"__DELIM__{text}__DELIM__"
|
||||
|
||||
# Special case: pipe can be absolute value delimiter
|
||||
if text == "|":
|
||||
return f"__DELIM__|__DELIM__"
|
||||
|
||||
# Handle < and > specifically (LaTeX convention)
|
||||
if text == "<":
|
||||
return "\\lt"
|
||||
if text == ">":
|
||||
return "\\gt"
|
||||
|
||||
# Tilde (distributed as)
|
||||
if text == '~' or text == '∼':
|
||||
return '\\sim'
|
||||
|
||||
# UNICODE_PASSTHROUGH: Keep certain symbols as Unicode for MathJax compatibility
|
||||
if text in UNICODE_PASSTHROUGH:
|
||||
return text
|
||||
|
||||
# Check for Unicode symbol mapping
|
||||
if text in UNICODE_TO_LATEX:
|
||||
return UNICODE_TO_LATEX[text]
|
||||
|
||||
# Handle multi-character operators with Unicode
|
||||
if len(text) > 1:
|
||||
has_unicode = any(char in UNICODE_TO_LATEX for char in text)
|
||||
has_passthrough = any(char in UNICODE_PASSTHROUGH for char in text)
|
||||
if has_unicode or has_passthrough:
|
||||
converted_parts = []
|
||||
for char in text:
|
||||
if char in UNICODE_PASSTHROUGH:
|
||||
converted_parts.append(char)
|
||||
elif char in UNICODE_TO_LATEX:
|
||||
converted_parts.append(UNICODE_TO_LATEX[char])
|
||||
else:
|
||||
converted_parts.append(char)
|
||||
return ' '.join(converted_parts)
|
||||
|
||||
# Default: return as-is
|
||||
return text
|
||||
|
||||
def format_number(self, text: str, node: ET.Element) -> str:
|
||||
"""
|
||||
Format a number (<mn> element) for statistics.
|
||||
|
||||
Args:
|
||||
text: The number text content
|
||||
node: The <mn> element node
|
||||
|
||||
Returns:
|
||||
Formatted LaTeX string
|
||||
|
||||
Logic:
|
||||
Numbers are returned as-is in statistics mode.
|
||||
|
||||
Examples:
|
||||
"0.05" → "0.05" (p-value)
|
||||
"95" → "95" (confidence level)
|
||||
"""
|
||||
# Numbers are returned as-is
|
||||
return text
|
||||
|
||||
def detect_context(self, equation_text: str) -> bool:
|
||||
"""
|
||||
Detect if an equation is statistical content.
|
||||
|
||||
Args:
|
||||
equation_text: The full equation text
|
||||
|
||||
Returns:
|
||||
True if likely statistics, False otherwise
|
||||
|
||||
Detection indicators:
|
||||
- Statistical operators (Pr, E, Var, Cov)
|
||||
- Distribution notation (Normal, Binomial, etc.)
|
||||
- Greek letters commonly used in stats (μ, σ, β, α)
|
||||
- Tilde notation (X ~ Normal)
|
||||
- Statistical symbols (≈, ∝, ∼)
|
||||
|
||||
Examples:
|
||||
"X ~ Normal(μ, σ²)" → True
|
||||
"E[X] = μ" → True
|
||||
"Var(X) = σ²" → True
|
||||
"sin(x) + cos(x)" → False
|
||||
"""
|
||||
# Check for statistical operators
|
||||
op_count = sum(1 for op in self.STATISTICAL_OPERATORS if op in equation_text)
|
||||
if op_count >= 1:
|
||||
return True
|
||||
|
||||
# Check for distribution names
|
||||
dist_count = sum(1 for dist in self.DISTRIBUTIONS if dist in equation_text)
|
||||
if dist_count >= 1:
|
||||
return True
|
||||
|
||||
# Check for tilde notation (distributed as)
|
||||
if '~' in equation_text or '∼' in equation_text:
|
||||
return True
|
||||
|
||||
# Check for common Greek letters in statistics context
|
||||
stats_greek = ['μ', 'σ', 'β', 'α', 'θ', 'λ', 'ρ', 'τ', 'χ']
|
||||
greek_count = sum(1 for letter in stats_greek if letter in equation_text)
|
||||
if greek_count >= 2: # At least 2 Greek letters
|
||||
return True
|
||||
|
||||
# Check for statistical patterns (p-value, confidence interval)
|
||||
import re
|
||||
if re.search(r'p\s*[<>=]?\s*0\.\d+', equation_text): # p-value
|
||||
return True
|
||||
if re.search(r'\d+%\s*(CI|confidence)', equation_text, re.IGNORECASE):
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
@property
|
||||
def name(self) -> str:
|
||||
"""Get the strategy name."""
|
||||
return "statistics"
|
||||
|
||||
def __repr__(self) -> str:
|
||||
"""String representation for debugging."""
|
||||
return f"StatisticsStrategy(operators={len(self.STATISTICAL_OPERATORS)}, distributions={len(self.DISTRIBUTIONS)})"
|
||||
Reference in New Issue
Block a user