"""
Chemistry-related data for equation formatting.

This module contains chemical elements, groups, and variables used for
detecting and formatting chemistry equations.
"""

# Multi-character chemical elements (2 chars)
# These are STRONG indicators - their presence alone triggers chemistry detection
MULTI_CHAR_ELEMENTS = {
    # Period 2
    'He', 'Li', 'Be', 'Ne',
    # Period 3
    'Na', 'Mg', 'Al', 'Si', 'Cl', 'Ar',
    # Period 4
    'Ca', 'Sc', 'Ti', 'Cr', 'Mn', 'Fe', 'Co', 'Ni', 'Cu', 'Zn',
    'Ga', 'Ge', 'As', 'Se', 'Br', 'Kr',
    # Period 5
    'Rb', 'Sr', 'Zr', 'Nb', 'Mo', 'Tc', 'Ru', 'Rh', 'Pd', 'Ag', 'Cd',
    'In', 'Sn', 'Sb', 'Te', 'Xe',
    # Period 6
    'Cs', 'Ba', 'La', 'Ce', 'Pr', 'Nd', 'Pm', 'Sm', 'Eu', 'Gd', 'Tb', 'Dy',
    'Ho', 'Er', 'Tm', 'Yb', 'Lu', 'Hf', 'Ta', 'Re', 'Os', 'Ir', 'Pt',
    'Au', 'Hg', 'Tl', 'Pb', 'Bi', 'Po', 'At', 'Rn',
    # Period 7
    'Fr', 'Ra', 'Ac', 'Th', 'Pa', 'Np', 'Pu', 'Am', 'Cm', 'Bk', 'Cf',
    'Es', 'Fm', 'Md', 'No', 'Lr', 'Rf', 'Db', 'Sg', 'Bh', 'Hs', 'Mt', 'Ds',
    'Rg', 'Cn', 'Nh', 'Fl', 'Mc', 'Lv', 'Ts', 'Og'
}

# Single-character chemical elements (1 char)
# These need CONTEXT - only formatted as chemistry when chemistry equation is detected
SINGLE_CHAR_ELEMENTS = {
    'H',   # Hydrogen
    'B',   # Boron
    'C',   # Carbon
    'N',   # Nitrogen
    'O',   # Oxygen
    'F',   # Fluorine
    'P',   # Phosphorus
    'S',   # Sulfur
    'K',   # Potassium (but also common variable)
    'V',   # Vanadium (but also common variable for volume)
    'Y',   # Yttrium
    'I',   # Iodine
    'W',   # Tungsten
    'U',   # Uranium
}

# All chemical elements (for formatting once chemistry is detected)
ALL_CHEMICAL_ELEMENTS = MULTI_CHAR_ELEMENTS | SINGLE_CHAR_ELEMENTS

# Chemical groups and radicals (strong indicators)
CHEMICAL_GROUPS = {
    'OH',   # Hydroxide
    'SO',   # Sulfite/Sulfate (partial)
    'NO',   # Nitrite/Nitrate (partial)
    'CO',   # Carbonyl/Carbonate (partial)
    'NH',   # Amine/Ammonium (partial)
    'CH',   # Methine/Hydrocarbon (partial)
    'PO',   # Phosphate (partial)
    'ClO',  # Chlorate (partial)
}

# Common chemistry variables (should stay italic even in chemistry equations)
# These are NOT chemical elements, they're variables used in chemistry
# NOTE: Keep this list minimal to avoid conflicts with fragmented elements
CHEMISTRY_VARIABLES = {
    'c',   # Concentration
    # NOTE: 'n' removed - conflicts with fragmented Mn (Manganese)
    # NOTE: 'M' removed - conflicts with fragmented Mn, Mg (Magnesium)
    'p',   # Pressure (but P is Phosphorus!)
    'T',   # Temperature
    'm',   # Mass
    'R',   # Gas constant
    'E',   # Energy (but E is also used in chemistry)
    # NOTE: 'V' removed - conflicts with V (Vanadium)
    # NOTE: 'K' removed - conflicts with K (Potassium)
    # Generic math variables
    'x', 'y', 'z',
    'a', 'b', 'd', 'q',
}

# Chinese chemical conditions/terms
CHINESE_CHEMICAL_TERMS = {
    '高温',    # High temperature
    '加热',    # Heating
    '催化剂',  # Catalyst
    '点燃',    # Ignition
    '电解',    # Electrolysis
    '控温',    # Temperature control
    '加压',    # Pressurization
    '光照',    # Light
    '通电',    # Electrify
}