DoLuEdu-WordFileParse/scripts/omml_mathml2latex/visitors/mi_visitor.py

"""
Visitor for <mi> (identifier) MathML elements.

The <mi> element represents identifiers in MathML, including:
- Mathematical functions (sin, cos, log)
- Variables (x, y, z)
- Constants (e, π)
- Multi-letter identifiers (velocity, pressure)
"""

from lxml import etree as ET
from ..core.interfaces import Visitor, Strategy
from ..utils import text_content as _text_content, convert_spaces_to_latex, escape_latex_special_chars
from ..data import CHEMICAL_ELEMENTS, COMMON_UNITS, UNICODE_TO_LATEX, UNICODE_PASSTHROUGH
from ..converters.post_processor import PostProcessor


class MiVisitor(Visitor):
    """
    Handles <mi> (identifier) MathML elements.

    This is the most common MathML element type (~40% of all elements).
    It converts identifiers to LaTeX format using subject-specific strategies.

    Examples:
        Math mode:
            <mi>sin</mi> → \\sin
            <mi>x</mi> → x
            <mi>α</mi> → \\alpha

        Chemistry mode:
            <mi>Fe</mi> → \\mathrm{Fe}
            <mi>H</mi> → \\mathrm{H}
    """

    def __init__(self, strategy: Strategy, context=None):
        """
        Initialize the Mi visitor.

        Args:
            strategy: The formatting strategy to use
            context: Optional ConversionContext for script context tracking
        """
        super().__init__(strategy)
        self._converter_context = None
        self.context = context

    def set_converter_context(self, converter):
        """Set converter context for color suppression checking."""
        self._converter_context = converter

    def visit(self, node: ET.Element) -> str:
        """
        Convert <mi> element to LaTeX.

        Args:
            node: The <mi> element to convert

        Returns:
            LaTeX string representation

        Raises:
            ValueError: If node is not an <mi> element
        """
        if not self.can_handle(node):
            raise ValueError(f"MiVisitor cannot handle element '{node.tag}'")

        # Get text content
        content = _text_content(node)

        # Handle empty content
        if not content:
            return ""

        # Escape LaTeX special characters before any other processing
        content = escape_latex_special_chars(content)

        # CRITICAL: Check for mathvariant BEFORE reclassifying as operator
        # This preserves explicit mathvariant="normal" for units like "N/m"
        mathvariant = node.get('mathvariant')

        # PHASE 1 FIX: Detect delimiters and operators misclassified as identifiers
        # This handles malformed MathML from OMML2MML.xsl where operators are tagged as <mi>
        # instead of <mo>. Common issue with Word documents.
        # EXCEPTION: If mathvariant="normal" is present, handle it specially to preserve mathrm wrapping
        if self._contains_delimiter_or_operator(content):
            if mathvariant == 'normal':
                # Special case: mathvariant="normal" with operators (e.g., "N/m" units)
                # Split by operators but wrap identifier parts in \mathrm{}
                result = self._reclassify_with_mathrm(content, node)
                return result
            else:
                # Normal reclassification without mathrm wrapping
                result = self._reclassify_as_operator(content, node)
                return result

        # Handle spaces (NBSP → ~, space → \ )
        # Must be done before function recognition
        if '\xa0' in content or ' ' in content:
            converted = convert_spaces_to_latex(content)

            # If content was ONLY spaces, return directly
            if not content.strip():
                return self._wrap_with_color(converted, node)

            # Update content with converted spaces
            content = converted

        # Check for explicit mathvariant (overrides strategy logic)
        # Note: mathvariant already extracted earlier (line 78) for operator reclassification check
        if mathvariant:
            return self._handle_mathvariant(content, mathvariant, node)

        # Check for explicit LaTeX font command
        latex_font_cmd = node.get('latex-font-cmd')
        if latex_font_cmd:
            return self._wrap_with_color(f"\\{latex_font_cmd}{{{content}}}", node)

        # Delegate to strategy for subject-specific formatting
        result = self.strategy.format_identifier(content, node)

        return self._wrap_with_color(result, node)

    def _handle_mathvariant(self, content: str, mathvariant: str, node: ET.Element) -> str:
        """
        Handle explicit mathvariant attributes.

        Args:
            content: The text content
            mathvariant: The mathvariant attribute value
            node: The element node

        Returns:
            LaTeX string with appropriate font command
        """
        # CRITICAL: Strip whitespace and check for mathematical functions FIRST
        # Original converter checks functions before applying mathvariant wrapping
        from ..data import MATH_FUNCTIONS
        clean_content = content.strip()

        # CRITICAL FIX: When mathvariant="normal" is present with mixed-case content,
        # do NOT treat it as a simple math function. Examples:
        # - "Asin" → should be split to "\mathrm{A}\sin" (not "\Asin")
        # - "sin" → should still be "\sin" (lowercase function names are always functions)
        # - "max" → should still be "\max" (lowercase function names are always functions)

        # Check if content is mixed case (has both uppercase and lowercase)
        has_upper = any(c.isupper() for c in clean_content)
        has_lower = any(c.islower() for c in clean_content)
        is_mixed_case = has_upper and has_lower

        # Skip function recognition ONLY for mixed-case content with mathvariant="normal"
        # This allows "Asin" to be handled later by _split_uppercase_and_function
        if mathvariant == 'normal' and len(clean_content) > 1 and is_mixed_case:
            # Mixed-case content like "Asin" should NOT be treated as function
            # Fall through to the mathvariant handling logic below
            pass
        else:
            # Enhanced function recognition: detect functions with inline subscripts
            # Pattern to match function + subscript (like "limn→∞" or "max0≤x≤1")
            import re
            for func in ['lim', 'limsup', 'liminf', 'sup', 'inf', 'max', 'min']:
                if clean_content.startswith(func):
                    remaining = clean_content[len(func):]
                    if remaining:
                        # We found a function with trailing content - this should be a subscript
                        # Use _convert_unicode_in_content to handle all Unicode symbols
                        remaining_converted = self._convert_unicode_in_content(remaining)
                        return f"\\{func}\\limits_{{{remaining_converted}}}"
                    else:
                        return f"\\{func}"

            # If it's a mathematical function, ignore mathvariant and use function command
            # This handles lowercase function names like "sin", "cos", "max", "lim"
            if clean_content.lower() in MATH_FUNCTIONS:
                return f"\\{clean_content.lower()}"

        # For other functions with trailing content
        for func in MATH_FUNCTIONS:
            if clean_content.startswith(func) and len(clean_content) > len(func):
                # Make sure it's not just a substring (e.g., 'limits' shouldn't match 'lim')
                if not clean_content[len(func)].isalpha():
                    remaining = clean_content[len(func):]
                    # CRITICAL FIX: Convert Unicode symbols in the remaining content
                    # Example: "sin∠" → "sin" + "∠" → "\sin" + "\angle" → "\sin \angle"
                    # Without this fix, "sin∠" becomes "\sin∠" (unconverted ∠)
                    remaining_converted = self._convert_unicode_in_content(remaining)
                    return f"\\{func} {remaining_converted}".strip()

        # Special case: Im, Re with mathvariant="normal" → \Im, \Re
        if mathvariant == 'normal' and content in ['Im', 'Re']:
            return f"\\{content}"

        # CRITICAL FIX: For multi-character content with mathvariant, apply same logic as original:
        # 1. Convert each character individually (Unicode → LaTeX)
        # 2. Apply mathvariant ONLY to non-LaTeX-command characters
        # 3. Join with spaces
        #
        # This handles cases like:
        #   <mi mathvariant="double-struck">ℵRZCQN</mi> → \aleph \mathbb{R} \mathbb{Z} \mathbb{C} \mathbb{Q} \mathbb{N}
        #   <mi mathvariant="script">ℏl</mi> → \hbar \ell

        if len(content) > 1 and any(char in UNICODE_TO_LATEX or char in UNICODE_PASSTHROUGH or char.isalpha() for char in content):
            # Step 1: Convert each character individually (UNICODE_PASSTHROUGH first)
            converted_parts = []
            for char in content:
                if char in UNICODE_PASSTHROUGH:
                    # Keep passthrough symbols as Unicode
                    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)

            # Step 2: Apply mathvariant wrapping selectively
            if mathvariant == 'double-struck':
                result_parts = []
                for part in converted_parts:
                    if part.startswith('\\'):
                        # Already a LaTeX command (like \aleph) - use as-is
                        result_parts.append(part)
                    elif part.strip():  # Skip empty strings and spaces
                        # Regular letter - wrap in \mathbb{}
                        result_parts.append(f"\\mathbb{{{part}}}")
                    # Note: spaces are intentionally skipped - we join with spaces anyway
                return self._wrap_with_color(' '.join(result_parts), node)

            elif mathvariant == 'script':
                result_parts = []
                for part in converted_parts:
                    if part.startswith('\\'):
                        # Already a LaTeX command (like \hbar) - use as-is
                        result_parts.append(part)
                    elif part == 'l':
                        # Special case: script 'l' is \ell, not \mathscr{l}
                        result_parts.append('\\ell')
                    elif part.strip():  # Skip empty strings and spaces
                        # Regular letter - wrap in \mathscr{}
                        result_parts.append(f"\\mathscr{{{part}}}")
                    # Note: spaces are intentionally skipped - we join with spaces anyway
                return self._wrap_with_color(' '.join(result_parts), node)

            elif mathvariant in ['fraktur', 'sans-serif', 'monospace', 'bold', 'bold-italic']:
                # For other mathvariants, apply to all non-LaTeX-command parts
                result_parts = []
                font_cmd_map = {
                    'fraktur': 'mathfrak',
                    'sans-serif': 'mathsf',
                    'monospace': 'mathtt',
                    'bold': 'mathbf',
                    'bold-italic': 'boldsymbol'
                }
                font_cmd = font_cmd_map[mathvariant]
                for part in converted_parts:
                    if part.startswith('\\'):
                        result_parts.append(part)
                    elif part.strip():  # Skip empty strings and spaces
                        result_parts.append(f"\\{font_cmd}{{{part}}}")
                    # Note: spaces are intentionally skipped - we join with spaces anyway
                return self._wrap_with_color(' '.join(result_parts), node)

            elif mathvariant == 'normal':
                # Multi-character content with mathvariant="normal" - always wrap in \mathrm{}
                # Combine the converted parts with intelligent spacing
                # When a LaTeX command (like \Delta) is followed by a letter, add a space
                # Otherwise, LaTeX interprets \DeltaH as a single undefined command
                combined = self._join_with_command_spacing(converted_parts)

                # DISABLED: "Smart" logic that ignored mathvariant="normal" for simple variables
                # This was causing issues where explicit mathvariant="normal" was not respected
                # Keeping _is_simple_math_variable for potential future use
                # if self.strategy.name == 'math':
                #     is_simple = self._is_simple_math_variable(combined)
                #     if is_simple:
                #         return self._wrap_with_color(combined, node)

                # CRITICAL FIX: Check if content starts with uppercase letter(s) followed by a known function
                # Example: "Asin" → "\mathrm{A}\sin", "ABcos" → "\mathrm{AB}\cos"
                # This handles the case where Word's "Text Mode" is used for mixed content
                result = self._split_uppercase_and_function(content)
                if result:
                    return self._wrap_with_color(result, node)

                # Always respect mathvariant="normal" - wrap in \mathrm{}
                return self._wrap_with_color(f"\\mathrm{{{combined}}}", node)

            else:
                # No mathvariant or unknown - just join the converted parts
                return self._wrap_with_color(' '.join(converted_parts), node)

        # Fallback: single character or simple cases
        # IMPORTANT: Convert Unicode symbols BEFORE wrapping in font commands
        # e.g., ℵ → \aleph, ℏ → \hbar
        content_converted = self._convert_unicode_in_content(content)

        # Map mathvariant values to LaTeX font commands
        if mathvariant == 'double-struck':
            # If already converted to LaTeX command, use as-is
            if content in UNICODE_TO_LATEX:
                return content_converted
            return f"\\mathbb{{{content_converted}}}"
        elif mathvariant == 'script':
            # Special case: script lowercase 'l' → \ell
            if content == 'l':
                return "\\ell"
            # If already converted to LaTeX command, use as-is
            if content in UNICODE_TO_LATEX:
                return content_converted
            return f"\\mathscr{{{content_converted}}}"
        elif mathvariant == 'fraktur':
            return f"\\mathfrak{{{content_converted}}}"
        elif mathvariant == 'sans-serif':
            return f"\\mathsf{{{content_converted}}}"
        elif mathvariant == 'monospace':
            return f"\\mathtt{{{content_converted}}}"
        elif mathvariant == 'bold':
            return f"\\mathbf{{{content_converted}}}"
        elif mathvariant == 'bold-italic':
            # Bold italic - use \boldsymbol for math-mode bold italic
            # Alternative: \bm from bm package, but \boldsymbol is standard
            return f"\\boldsymbol{{{content_converted}}}"
        elif mathvariant == 'italic':
            # Explicitly italic - return as-is (LaTeX default)
            return content_converted
        elif mathvariant == 'normal':
            # INTELLIGENT HANDLING of mathvariant="normal" based on subject mode and content
            # This handles the <m:nor/> tag from Word's "Text Mode" button

            # Special cases first: Im, Re → \Im, \Re
            if content in ['Im', 'Re']:
                return f"\\{content}"

            # CRITICAL: If content was a Unicode symbol (like π → \pi), don't wrap in \mathrm{}
            # The _convert_unicode_in_content() already converted it to LaTeX command
            if content.strip() in UNICODE_TO_LATEX:
                return content_converted  # Already converted to LaTeX (e.g., \pi)

            # DISABLED: "Smart" logic that ignored mathvariant="normal" for simple variables
            # This was causing issues where explicit mathvariant="normal" was not respected
            # Keeping _is_simple_math_variable for potential future use
            # if self.strategy.name == 'math':
            #     if self._is_simple_math_variable(content_converted):
            #         return content_converted

            # Always respect mathvariant="normal" - wrap in \mathrm{}
            return f"\\mathrm{{{content_converted}}}"
        else:
            # Unknown mathvariant - return as-is
            return content_converted

    def _is_simple_math_variable(self, content: str) -> bool:
        """
        Check if content is a simple mathematical variable that should be italic.

        Simple math variables include:
        - Single lowercase letters: x, y, z, a, b, etc.
        - Single uppercase letters: X, Y, Z, A, B, etc. (but NOT chemical elements)
        - Greek letters (already converted to LaTeX commands like \\alpha)
        - Common mathematical notations like single letters with primes: x', y''

        This is used to intelligently handle mathvariant="normal" in math mode:
        - Simple variables should remain italic (ignore mathvariant="normal")
        - Complex identifiers should be upright (respect mathvariant="normal")

        Args:
            content: The identifier content to check

        Returns:
            True if content is a simple math variable, False otherwise
        """
        if not content:
            return False

        # Strip whitespace and LaTeX commands for checking
        clean_content = content.strip()

        # If it starts with a LaTeX command (like \alpha, \beta), it's a simple variable
        if clean_content.startswith('\\'):
            return True

        # CRITICAL: If content contains mathematical operators, it's an expression (not an identifier)
        # Examples: "x+2", "a-b", "n*m" should NOT be wrapped in \mathrm{}
        # These are parsed as single <mi> elements by XSL but should remain italic
        math_operators = {'+', '-', '*', '/', '=', '<', '>', '≤', '≥', '≠', '±'}
        if any(op in clean_content for op in math_operators):
            return True  # Treat expressions as "simple" (don't wrap in \mathrm{})

        # Single letter (a-z, A-Z) - simple variable
        if len(clean_content) == 1 and clean_content.isalpha():
            # BUT: exclude known chemical elements in non-math contexts
            if self.strategy.name == 'chemistry' and clean_content in CHEMICAL_ELEMENTS:
                return False
            return True

        # Single letter with primes (x', y'', etc.)
        if len(clean_content) >= 2:
            base = clean_content.rstrip("'")
            primes = clean_content[len(base):]
            if len(base) == 1 and base.isalpha() and all(c == "'" for c in primes):
                return True

        # Multi-character content that's NOT a math function is considered complex
        # Examples: "velocity", "pressure", "Mn", "Fe" - should be upright if mathvariant="normal"
        return False

    def _convert_unicode_in_content(self, content: str) -> str:
        """
        Convert Unicode symbols within identifier content to LaTeX equivalents.

        For multi-character identifiers with Unicode symbols mixed in,
        we need to convert each Unicode character individually.

        Args:
            content: Identifier text that may contain Unicode symbols

        Returns:
            Content with Unicode symbols converted to LaTeX, preserving spaces
        """
        if not content:
            return content

        # Check if any Unicode symbols are present (passthrough or convertible)
        has_unicode = any(char in UNICODE_TO_LATEX for char in content)
        has_passthrough = any(char in UNICODE_PASSTHROUGH for char in content)
        if not has_unicode and not has_passthrough:
            return content

        # Convert character by character, preserving spaces (PASSTHROUGH first)
        result = []
        for char in content:
            if char in UNICODE_PASSTHROUGH:
                # Keep passthrough symbols as Unicode
                result.append(char)
            elif char in UNICODE_TO_LATEX:
                # Add space before/after LaTeX command if needed
                latex_cmd = UNICODE_TO_LATEX[char]
                result.append(latex_cmd)
            else:
                result.append(char)

        # Join parts with space separator for multi-symbol content
        # e.g., "ℵR" → "\aleph R" not "\alephR"
        joined = ' '.join(result)

        # Clean up multiple spaces
        import re
        joined = re.sub(r'\s+', ' ', joined)

        return joined

    def _join_with_command_spacing(self, parts: list) -> str:
        """
        Join converted parts with intelligent spacing for LaTeX commands.

        When a LaTeX command (like \\Delta) is followed by a letter, a space must
        be inserted. Otherwise, LaTeX interprets \\DeltaH as a single undefined
        command instead of \\Delta followed by H.

        Args:
            parts: List of converted parts (may contain LaTeX commands and letters)

        Returns:
            Joined string with appropriate spacing between commands and letters

        Examples:
            ['\\\\Delta', 'H'] → '\\\\Delta H' (space needed)
            ['a', 'b', 'c'] → 'abc' (no space needed)
            ['\\\\alpha', '\\\\beta'] → '\\\\alpha\\\\beta' (commands can be adjacent)
            ['\\\\Delta', '1'] → '\\\\Delta 1' (space before number)
        """
        if not parts:
            return ''

        result = []
        for i, part in enumerate(parts):
            result.append(part)

            # Check if we need to add a space after this part
            if i < len(parts) - 1:
                next_part = parts[i + 1]

                # If current part is a LaTeX command (starts with \)
                # and next part starts with a letter or digit, add space
                if part.startswith('\\') and next_part and (next_part[0].isalpha() or next_part[0].isdigit()):
                    result.append(' ')

        return ''.join(result)

    def _wrap_with_color(self, latex: str, node: ET.Element) -> str:
        """
        Wrap LaTeX with color command if node has color attribute.

        Args:
            latex: The LaTeX string to wrap
            node: The element node

        Returns:
            LaTeX string, optionally wrapped with color command
        """
        # Use the centralized color wrapping utility with suppression support
        from ..utils.color_helpers import wrap_element_with_color

        # Get converter context from multiple sources (for backward compatibility):
        # 1. Direct visitor context (set by legacy_adapter)
        # 2. Strategy context (shared across all visitors, including child visitors)
        context = getattr(self, '_converter_context', None)
        if context is None and hasattr(self.strategy, '_converter_context'):
            context = self.strategy._converter_context

        return wrap_element_with_color(latex, node, context)

    def _contains_delimiter_or_operator(self, content: str) -> bool:
        """
        Check if content contains delimiter or operator characters that should be <mo> not <mi>.

        This detects malformed MathML from OMML2MML.xsl where operators are misclassified
        as identifiers (e.g., <mi>(</mi> instead of <mo fence="true">(</mo>).

        Args:
            content: Text content of the <mi> element

        Returns:
            True if content contains delimiters or operators
        """
        # Delimiters that should be fences
        delimiters = set('()[]{}<>')

        # Common operators (excluding - which might be minus sign or hyphen)
        # Note: We include = and < > which are often misclassified
        operators = set('+=*/|≤≥≠≈∈∉∪∩⊂⊃∧∨¬→↔×÷±')

        # Check if ANY character is a delimiter or operator
        return any(char in delimiters or char in operators for char in content)

    def _reclassify_with_mathrm(self, content: str, node: ET.Element) -> str:
        """
        Reclassify content with operators while preserving mathvariant="normal" (mathrm wrapping).

        This handles cases like:
        - <mi mathvariant="normal">N/m</mi> → \mathrm{N}/\mathrm{m}
        - <mi mathvariant="normal">kg·m/s</mi> → \mathrm{kg}·\mathrm{m}/\mathrm{s}

        Args:
            content: Text content with mathvariant="normal" that contains operators
            node: Original <mi> element node

        Returns:
            LaTeX string with mathrm-wrapped identifiers and properly classified operators
        """
        # Delimiters that should have fence="true"
        fence_chars = set('()[]{}')

        # Operators that should be <mo> but NOT fences
        operator_chars = set('+=*/|<>≤≥≠≈∈∉∪∩⊂⊃∧∨¬→↔×÷±·')

        # Multi-character content: split and classify each character
        # Identifier parts get wrapped in \mathrm{}
        parts = []
        for char in content:
            if char in fence_chars:
                parts.append(self._convert_as_fence(char, node))
            elif char in operator_chars:
                parts.append(self._convert_as_operator(char, node))
            elif char.isspace():
                # Preserve spaces
                from ..utils import convert_spaces_to_latex
                parts.append(convert_spaces_to_latex(char))
            else:
                # Regular identifier character - wrap in \mathrm{} for mathvariant="normal"
                parts.append(f"\\mathrm{{{char}}}")

        return ''.join(parts)

    def _reclassify_as_operator(self, content: str, node: ET.Element) -> str:
        """
        Reclassify misclassified operators/delimiters and convert them properly.

        Handles cases like:
        - <mi>(</mi> → treat as <mo fence="true">(</mo>
        - <mi>)+</mi> → treat as <mo fence="true">)</mo><mo>+</mo>
        - <mi>=</mi> → treat as <mo>=</mo>

        Args:
            content: Text content that contains operators/delimiters
            node: Original <mi> element node

        Returns:
            LaTeX string with properly classified operators
        """
        # Import MoVisitor for operator handling
        from .mo_visitor import MoVisitor

        # Delimiters that should have fence="true"
        fence_chars = set('()[]{}')

        # Operators that should be <mo> but NOT fences
        operator_chars = set('+=*/|<>≤≥≠≈∈∉∪∩⊂⊃∧∨¬→↔×÷±')

        # If content is a single character, handle directly
        if len(content) == 1:
            if content in fence_chars:
                return self._convert_as_fence(content, node)
            elif content in operator_chars:
                return self._convert_as_operator(content, node)
            else:
                # Shouldn't happen, but fallback to identifier
                return self.strategy.format_identifier(content, node)

        # Multi-character content: split and classify each character
        parts = []
        for char in content:
            if char in fence_chars:
                parts.append(self._convert_as_fence(char, node))
            elif char in operator_chars:
                parts.append(self._convert_as_operator(char, node))
            elif char.isspace():
                # Preserve spaces
                from ..utils import convert_spaces_to_latex
                parts.append(convert_spaces_to_latex(char))
            else:
                # Regular identifier character
                parts.append(self.strategy.format_identifier(char, node))

        return ''.join(parts)

    def _convert_as_fence(self, char: str, node: ET.Element) -> str:
        """
        Convert a character as a fence delimiter (with fence="true").

        Fence delimiters are marked with __DELIM__ to indicate they should be paired
        by the post-processor (e.g., ( and ) become \left( and \right)).

        Args:
            char: Single delimiter character
            node: Original element node (for color preservation)

        Returns:
            Delimiter wrapped in __DELIM__ markers for post-processing
        """
        # Map fence characters to LaTeX (handle escaped braces)
        fence_map = {
            '(': '(',
            ')': ')',
            '[': '[',
            ']': ']',
            '{': '\\{',  # Must be escaped in LaTeX
            '}': '\\}',  # Must be escaped in LaTeX
        }

        latex_char = fence_map.get(char, char)

        # Wrap in __DELIM__ markers so post-processor knows to add \left and \right
        return f"__DELIM__{latex_char}__DELIM__"

    def _convert_as_operator(self, char: str, node: ET.Element) -> str:
        """
        Convert a character as an operator (without fence="true").

        Operators like +, =, |, < are NOT marked with __DELIM__ because they should NOT
        be paired as delimiters. For example, | in P(A|B) is an operator, not a delimiter.

        Args:
            char: Single operator character
            node: Original element node (for color preservation)

        Returns:
            LaTeX operator string (plain, no markers)
        """
        # Map operators to LaTeX equivalents
        operator_map = {
            '+': '+',
            '-': '-',
            '*': '*',
            '/': '/',
            '=': '=',
            '<': '<',
            '>': '>',
            '|': '|',  # IMPORTANT: | as operator (conditional probability), NOT delimiter
            '×': '\\times ',
            '÷': '\\div ',
            '±': '\\pm ',
            '≤': '\\leqslant ',
            '≥': '\\geqslant ',
            '≠': '\\ne ',
            '≈': '\\approx ',
            '∈': '\\in ',
            '∉': '\\notin ',
            '∪': '\\cup ',
            '∩': '\\cap ',
            '⊂': '\\subset ',
            '⊃': '\\supset ',
            '∧': '\\wedge ',
            '∨': '\\vee ',
            '¬': '\\neg ',
            '→': '\\to ',
            '↔': '\\leftrightarrow ',
        }

        latex_char = operator_map.get(char, char)

        # Return as-is (NO __DELIM__ markers - should not be paired)
        return latex_char

    def _split_uppercase_and_function(self, content: str) -> str:
        """
        Split content that starts with uppercase letter(s) followed by a known function.

        This handles cases like:
        - "Asin" → "\\mathrm{A}\\sin"
        - "ABcos" → "\\mathrm{AB}\\cos"
        - "Xlog" → "\\mathrm{X}\\log"

        Args:
            content: The identifier content to check

        Returns:
            LaTeX string with split content, or None if no split is needed
        """
        from ..data import MATH_FUNCTIONS

        if not content or len(content) < 2:
            return None

        # Check if content starts with uppercase letter(s)
        if not content[0].isupper():
            return None

        # Find where the uppercase letters end
        uppercase_end = 0
        for i, char in enumerate(content):
            if char.isupper():
                uppercase_end = i + 1
            else:
                break

        if uppercase_end == 0 or uppercase_end >= len(content):
            return None

        # Split into uppercase part and remaining part
        uppercase_part = content[:uppercase_end]
        remaining_part = content[uppercase_end:]

        # Check if remaining part is a known math function
        if remaining_part in MATH_FUNCTIONS:
            # Split: uppercase in \mathrm{} + function as \function
            return f"\\mathrm{{{uppercase_part}}}\\{remaining_part}"

        return None

    def can_handle(self, node: ET.Element) -> bool:
        """
        Check if this visitor can handle the given node.

        Args:
            node: The MathML element to check

        Returns:
            True if node is an <mi> element, False otherwise
        """
        from ..utils import local_name as _local
        return _local(node.tag) == 'mi'

    @property
    def element_name(self) -> str:
        """Get the element name this visitor handles."""
        return 'mi'

    def __repr__(self) -> str:
        """String representation for debugging."""
        return f"MiVisitor(strategy={self.strategy.name})"