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

r"""
Visitor for <mspace> (spacing) MathML elements.

The <mspace> element represents horizontal spacing in mathematical expressions.
It uses the width attribute to specify the amount of space.

Common spacing types:
- Named spaces: thinmathspace, mediummathspace, thickmathspace
- Negative spaces: negativethinmathspace, etc.
- Explicit sizes: 0.1em, 1em, 2em

This visitor maps MathML spacing to LaTeX spacing commands.
"""

from lxml import etree as ET
from ..core.interfaces import Visitor, Strategy
from ..utils import local_name as _local


class MspaceVisitor(Visitor):
    r"""
    Handles <mspace> (spacing) MathML elements.

    Converts spacing specifications to LaTeX spacing commands.

    Examples:
        Thin space:
            <mspace width="thinmathspace"/>
            → \,

        Medium space:
            <mspace width="mediummathspace"/>
            → \:

        Thick space:
            <mspace width="thickmathspace"/>
            → \;

        Quad space:
            <mspace width="1em"/>
            → \quad

        Qquad space:
            <mspace width="2em"/>
            → \qquad

        Negative space:
            <mspace width="negativethinmathspace"/>
            → \!

        Default (no width):
            <mspace/>
            → \, (thin space)
    """

    # Mapping from MathML spacing names to LaTeX commands
    SPACING_MAP = {
        # Named mathematical spaces
        "thinmathspace": "\\,",
        "mediummathspace": "\\:",
        "thickmathspace": "\\;",
        "verythinmathspace": "\\!",
        "veryverythinmathspace": "\\!",

        # Negative spaces (for fine-tuning)
        "negativethinmathspace": "\\!",
        "negativemediummathspace": "\\!",
        "negativethickmathspace": "\\!",

        # Explicit em-based sizes
        "0em": "",  # No space
        "0.1em": "\\,",
        "0.2em": "\\:",
        "0.3em": "\\;",
        "0.5em": "\\;",
        "1em": "\\quad",
        "2em": "\\qquad",

        # Alternative common values
        "thin": "\\,",
        "medium": "\\:",
        "thick": "\\;",
    }

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

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

        Args:
            node: The <mspace> element to convert

        Returns:
            LaTeX spacing command (e.g., \,, \:, \;, \quad, \qquad)

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

        # Get width attribute
        width = node.get("width", "")

        # Handle empty width (default to thin space)
        if not width:
            return "\\,"

        # Check if width is in our mapping
        if width in self.SPACING_MAP:
            return self.SPACING_MAP[width]

        # Try to parse numeric width (e.g., "0.5em", "1.5em")
        spacing_cmd = self._parse_numeric_width(width)
        if spacing_cmd:
            return spacing_cmd

        # Default: thin space
        return "\\,"

    def _parse_numeric_width(self, width: str) -> str:
        """
        Parse numeric width values and convert to LaTeX spacing.

        Args:
            width: Width string (e.g., "0.5em", "1.5em")

        Returns:
            LaTeX spacing command, or empty string if cannot parse
        """
        # Remove whitespace
        width = width.strip()

        # Try to extract numeric value from em-based widths
        if width.endswith("em"):
            try:
                value = float(width[:-2])

                # Map numeric values to spacing commands
                if value <= 0:
                    return ""
                elif value < 0.15:
                    return "\\,"  # thin
                elif value < 0.25:
                    return "\\:"  # medium
                elif value < 0.6:
                    return "\\;"  # thick
                elif value < 1.5:
                    return "\\quad"
                else:
                    return "\\qquad"
            except ValueError:
                pass

        # Try to extract numeric value from pt-based widths
        if width.endswith("pt"):
            try:
                value = float(width[:-2])

                # Map pt values to spacing (rough approximation)
                # 1em ≈ 10pt in typical math fonts
                if value <= 0:
                    return ""
                elif value < 2:
                    return "\\,"
                elif value < 4:
                    return "\\:"
                elif value < 6:
                    return "\\;"
                elif value < 12:
                    return "\\quad"
                else:
                    return "\\qquad"
            except ValueError:
                pass

        # Could not parse
        return ""

    def can_handle(self, node: ET.Element) -> bool:
        """Check if this visitor can handle the given node."""
        return _local(node.tag) == 'mspace'

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

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