"""
Operator and symbol set definitions for MathML to LaTeX conversion.

This module provides:
- Mathematical symbol sets for symbol detection
- Summation symbol mappings
- Font to LaTeX command mappings
- Large operator definitions (Unicode versions)
"""

# Mathematical symbol set for symbol detection
MATH_SYMBOLS_SET = {
    "↑", "↓", "→", "←", "↔", "×", "⋅", "·", "÷", "∕", "−",  # Added U+2212 MINUS SIGN
    "∩", "∪", "⊂", "⊃", "⊆", "⊇", "∈", "∉", "∋", "∌",
    "≤", "≥", "≠", "≈", "≅", "≡", "≢", "∼", "≃", "≄",
    "≜", "≝", "≞", "≟", "≦", "≧", "≨", "≩", "≲", "≳", "≴", "≵", "≶", "≷", "≸", "≹",
    "≺", "≻", "⪯", "⪰", "∝", "⊥",
    "∥", "∦", "±", "∓", "∗", "∘", "∙", "√", "∞",
    "∂", "∇", "∆", "∫", "∬", "∭", "∮", "∯", "∰",
    "∑", "∏", "∐", "⋃", "⋂", "⋁", "⋀", "⨁", "⨂", "⨄",
    "∀", "∃", "∄", "⊢", "⊣", "⊤", "⊥", "¬", "∧", "∨",
    "⟨", "⟩", "⌊", "⌋", "⌈", "⌉", "⏞", "⏟", "∠", "∁"
}

# Summation symbols for specific processing
SUMMATION_SYMBOLS = {
    '∑': 'sum',
    '∏': 'prod',
    '∫': 'integral',
    'Σ': 'sum',
    'Π': 'prod'
}

# Font family to LaTeX command mapping
FONT_TO_LATEX = {
    'Times New Roman': 'mathrm',   # Roman/upright text
    'Times': 'mathrm',             # Times font variant
    'Cambria Math': None,          # Default math font (no special formatting)
    'Cambria': None,               # Cambria variant
    'Arial': 'mathsf',             # Sans-serif
    'Helvetica': 'mathsf',         # Helvetica sans-serif
    'Courier New': 'mathtt',       # Typewriter/monospace
    'Courier': 'mathtt',           # Courier variant
    'Computer Modern': None,       # LaTeX default math font
    'Latin Modern Math': None,     # Modern LaTeX math font
}

# Large operators that should use \limits in display mode (LaTeX commands)
LARGE_OPERATORS = [
    "\\sum", "\\prod", "\\int", "\\iint", "\\iiint", "\\oint",
    "\\bigcup", "\\bigcap", "\\bigvee", "\\bigwedge",
    "\\bigoplus", "\\bigotimes", "\\biguplus", "\\coprod",
    "\\lim", "\\limsup", "\\liminf", "\\sup", "\\inf",
    "\\max", "\\min"
]

# Unicode large operators for detection
LARGE_OPERATORS_UNICODE = [
    "∑", "Σ",        # Summation
    "∏", "Π",        # Product
    "∫",             # Integral
    "⋃", "⋂",        # Union, Intersection
    "⋁", "⋀",        # Logical OR, AND
    "⨁", "⨂", "⨄",  # Direct sum, tensor product, union
]