DoLuEdu-WordFileParse/scripts/omml_mathml2latex/data/patterns.py

"""
Pattern-based replacements and regex patterns for LaTeX processing.

This module provides regex patterns for:
- Spacing cleanup and normalization
- Delimiter marker cleanup
- LaTeX structure fixes
- Assignment operator normalization
"""

# Assignment operator normalization (line 5529-5530)
ASSIGNMENT_OPERATOR_REPLACEMENTS = [
    ('∶ =', ':='),   # U+2236 RATIO with space and equals
    (': =', ':='),    # Colon with space and equals
]

# ========================================================================
# Pattern-Based Replacements (Regex Patterns)
# ========================================================================

# Spacing cleanup patterns (consolidated from lines 1289, 1292-1293, 1296, 5566-5567)
SPACING_CLEANUP_PATTERNS = [
    # Reduce excessive spaces (line 1289)
    (r' {3,}', '  ', 'Reduce 3+ spaces to double space'),

    # Remove spaces before delimiters (lines 1292-1293)
    (r'\\left\s+\\{', r'\\left\\{', 'Remove space before left brace'),
    (r'\\right\s+\\}', r'\\right\\}', 'Remove space before right brace'),

    # Remove space between command and braces (line 1296)
    (r'\\([a-zA-Z]+)\s+\{', r'\\\1{', 'Remove space between command and opening brace'),

    # Add space after set operations when not followed by braces (lines 5566-5567)
    (r'\\cap(?![{])', r'\\cap ', 'Add space after \\cap'),
    (r'\\cup(?![{])', r'\\cup ', 'Add space after \\cup'),
]

# Delimiter marker cleanup patterns (consolidated from lines 1491-1502, 5433-5447)
# These clean up __DELIM__ markers left from OMML processing
DELIMITER_CLEANUP_PATTERNS = [
    # Paired delimiters with content (line 5433)
    (r'__DELIM__(.+?)__DELIM__', r'\1', 'Remove paired __DELIM__ markers'),

    # Corrupted paired delimiters (lines 5436-5438)
    (r'__DELIM_(.+?)__DELIM_', r'\1', 'Remove corrupted paired markers (single underscore)'),
    (r'__DELIM__(.+?)__DELIM_', r'\1', 'Remove mixed paired markers (full+corrupted)'),
    (r'__DELIM_(.+?)__DELIM__', r'\1', 'Remove mixed paired markers (corrupted+full)'),

    # Orphaned markers with single character (lines 5441-5444)
    (r'__DELIM__(.)', r'\1', 'Remove orphaned opening marker with character'),
    (r'(.)__DELIM__', r'\1', 'Remove orphaned closing marker with character'),
    (r'__DELIM_(.)', r'\1', 'Remove corrupted opening marker with character'),
    (r'(.)__DELIM_', r'\1', 'Remove corrupted closing marker with character'),

    # Standalone markers (lines 5445-5447)
    (r'__DELIM__', '', 'Remove any remaining full markers'),
    (r'__DELIM_', '', 'Remove any remaining corrupted markers'),
    (r'_DELIM__', '', 'Remove reverse corrupted markers'),

    # Specific delimiter characters (lines 1491-1497)
    (r'__DELIM[_]*\([_]*', '(', 'Clean opening paren markers'),
    (r'[_]*\)__DELIM[_]*', ')', 'Clean closing paren markers'),
    (r'__DELIM[_]*\[[_]*', '[', 'Clean opening bracket markers'),
    (r'[_]*\]__DELIM[_]*', ']', 'Clean closing bracket markers'),
    (r'__DELIM[_]*\{[_]*', '{', 'Clean opening brace markers'),
    (r'[_]*\}__DELIM[_]*', '}', 'Clean closing brace markers'),
    (r'__DELIM[_]*\|[_]*', '|', 'Clean pipe markers (absolute value)'),

    # Fragments (lines 1500-1502)
    (r'LIM__', '', 'Remove LIM__ fragment'),
    (r'LIM_', '', 'Remove LIM_ fragment'),
]

# Simple structure fix patterns (these don't need complex logic)
SIMPLE_STRUCTURE_FIX_PATTERNS = [
    # Convert \overset{\dot}{X} to \dot{X} (lines 5570-5571)
    (r'\\overset\{\\dot\}\{([a-zA-Z0-9])\}', r'\\dot{\1}', 'Simplify dot overset to \\dot command'),
    (r'\\overset\{\.\}\{([a-zA-Z0-9])\}', r'\\dot{\1}', 'Simplify literal dot overset to \\dot command'),

    # Fix array column specification (line 5574)
    (r'\\begin\{array\{([^}]+)\}\}', r'\\begin{array}{\1}', 'Fix array column specification braces'),

    # Convert incorrect fraction to reaction arrow (line 5579)
    (r'\\dfrac\{\\underline\{([^}]+)\}\}\{\}', r'\\xlongequal[\\quad]{\1}', 'Convert underline fraction to reaction arrow'),

    # Fix nested underset with underbrace (lines 5744-5747)
    (r'\\underset\{([^{}]+)\}\{\\underset\{\\underbrace\}\{([^{}]+)\}\}', r'\\underbrace{\2}_{\1}', 'Fix nested underset underbrace pattern'),

    # Fix overset with \hat over numbers to \overline (lines 5753-5756)
    (r'\\overset\{\\hat\}\{(\\mathrm\{)?(\d+)\}?\}', r'\\overline{\2}', 'Convert hat overset to overline for numbers'),

    # Fix underset with textemdash patterns (lines 5802-5823)
    (r'\\underset\{\\textemdash\}\{\\underset\{\\textemdash\}\{([^{}]+)\}\}', r'\\underline{\\underline{\1}}', 'Convert nested textemdash underset to double underline'),
    (r'\\underset\{\\textemdash\}\{\\underline\{([^{}]+)\}\}', r'\\underline{\\underline{\1}}', 'Convert textemdash underset with underline to double underline'),
    (r'\\underset\{\\textemdash\}\{([^{}]+)\}', r'\\underline{\1}', 'Convert textemdash underset to underline'),
]

# ========================================================================
# Additional Symbol Classification Data
# ========================================================================

# Mathematical symbols for classification
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
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
    "∮",             # Contour integral
    "∬",             # Double integral
    "∭",             # Triple integral
    "⋂",             # Intersection
    "⋃",             # Union
    "⋁",             # Logical OR
    "⋀",             # Logical AND
    "⊕",             # Direct sum
    "⊗",             # Tensor product
    "⊎",             # Multiset sum
    "⨁",             # Large direct sum
    "⨂",             # Large tensor product
    "⨃",             # Large union with plus
    "⨆",             # Large square union
    "⨄",             # Large union with plus
]