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

"""
Visitor for <mn> (number) MathML elements.

The <mn> element represents numeric literals in MathML, including:
- Integers (1, 2, 3, ...)
- Decimals (3.14, 2.718, ...)
- Scientific notation (1.5×10⁻³)
- Fractions in decimal form (0.5)
"""

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
from ..converters.post_processor import PostProcessor


class MnVisitor(Visitor):
    """
    Handles <mn> (number) MathML elements.

    This visitor converts numbers to LaTeX format. Most numbers
    are returned as-is, but the strategy can customize formatting
    for specific subjects (e.g., chemistry, physics).

    Examples:
        Standard numbers:
            <mn>123</mn> → 123
            <mn>3.14</mn> → 3.14
            <mn>0.5</mn> → 0.5

        Scientific notation (handled at operator level):
            <mn>1.5</mn><mo>×</mo><mn>10</mn><msup><mn>-3</mn></msup>
            → 1.5 \\times 10^{-3}
    """

    def __init__(self, strategy: Strategy):
        """
        Initialize the Mn visitor.

        Args:
            strategy: The formatting strategy to use
        """
        super().__init__(strategy)
        self._converter_context = None

    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 <mn> element to LaTeX.

        Args:
            node: The <mn> element to convert

        Returns:
            LaTeX string representation

        Raises:
            ValueError: If node is not an <mn> element
        """
        if not self.can_handle(node):
            raise ValueError(f"MnVisitor 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)

        # Handle spaces (NBSP → ~, space → \ )
        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

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

        return self._wrap_with_color(result, node)

    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 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 <mn> element, False otherwise
        """
        from ..utils import local_name as _local
        return _local(node.tag) == 'mn'

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

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