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

"""Visitor for <msub> (subscript) MathML elements."""

from lxml import etree as ET
from ..core.interfaces import Visitor, Strategy
from ..core.context import ConversionContext
from ..utils import text_content as _text_content, local_name as _local


class MsubVisitor(Visitor):
    """Handles <msub> (subscript) MathML elements.

    Examples:
        Simple: <msub><mi>x</mi><mn>1</mn></msub> → x_{1}
        Index: <msub><mi>a</mi><mi>i</mi></msub> → a_{i}
    """

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

        Args:
            strategy: The formatting strategy to use
            context: Shared conversion context for state tracking
        """
        super().__init__(strategy)
        self.context = context

    def visit(self, node: ET.Element) -> str:
        if not self.can_handle(node):
            raise ValueError(f"MsubVisitor cannot handle element '{node.tag}'")

        children = list(node)
        if len(children) < 2:
            raise ValueError(f"msub element must have 2 children, got {len(children)}")

        # Convert base (not in script context)
        base = self._convert_child(children[0])

        # Push script context before converting subscript
        if self.context:
            self.context.push_script_context('msub')

        try:
            # Convert subscript (in script context)
            subscript = self._convert_child(children[1])
        finally:
            # Always pop context, even if conversion fails
            if self.context:
                self.context.pop_script_context()

        # Special case: Empty subscript - just return the base
        if not subscript or not subscript.strip():
            base = self._wrap_if_needed(base)
            return base

        base = self._wrap_if_needed(base)

        # Special case: If base contains a superscript (like f^{\prime}),
        # wrap it in braces to prevent syntax errors
        # Example: f^{\prime} should become {f^{\prime}}_{x}, not f^{\prime}_{x}
        if self._contains_superscript(base):
            base = f"{{{base}}}"

        return f"{base}_{self._brace(subscript)}"

    def _convert_child(self, child: ET.Element) -> str:
        """Convert a child element to LaTeX."""
        tag = _local(child.tag)

        # Import visitors as needed to avoid circular imports
        if tag == 'mi':
            from .mi_visitor import MiVisitor
            return MiVisitor(self.strategy, self.context).visit(child)
        elif tag == 'mo':
            from .mo_visitor import MoVisitor
            return MoVisitor(self.strategy).visit(child)
        elif tag == 'mn':
            from .mn_visitor import MnVisitor
            return MnVisitor(self.strategy).visit(child)
        elif tag == 'mfrac':
            from .mfrac_visitor import MfracVisitor
            return MfracVisitor(self.strategy, self.context).visit(child)
        elif tag == 'msup':
            from .msup_visitor import MsupVisitor
            return MsupVisitor(self.strategy).visit(child)
        elif tag == 'msub':
            # Recursive: msub can contain other msub elements
            return self.visit(child)
        elif tag == 'mrow':
            from .mrow_visitor import MrowVisitor
            return MrowVisitor(self.strategy, self.context).visit(child)
        elif tag == 'msqrt':
            from .msqrt_visitor import MsqrtVisitor
            return MsqrtVisitor(self.strategy).visit(child)
        elif tag == 'mroot':
            from .mroot_visitor import MrootVisitor
            return MrootVisitor(self.strategy).visit(child)
        elif tag == 'msubsup':
            from .msubsup_visitor import MsubsupVisitor
            return MsubsupVisitor(self.strategy).visit(child)
        elif tag == 'munder':
            from .munder_visitor import MunderVisitor
            return MunderVisitor(self.strategy).visit(child)
        elif tag == 'mover':
            from .mover_visitor import MoverVisitor
            return MoverVisitor(self.strategy).visit(child)
        elif tag == 'munderover':
            from .munderover_visitor import MunderoverVisitor
            return MunderoverVisitor(self.strategy).visit(child)
        elif tag == 'mfenced':
            from .mfenced_visitor import MfencedVisitor
            return MfencedVisitor(self.strategy).visit(child)
        elif tag == 'mtable':
            from .mtable_visitor import MtableVisitor
            return MtableVisitor(self.strategy).visit(child)
        elif tag == 'mtext':
            from .mtext_visitor import MtextVisitor
            return MtextVisitor(self.strategy).visit(child)
        elif tag == 'mstyle':
            from .mstyle_visitor import MstyleVisitor
            return MstyleVisitor(self.strategy).visit(child)
        elif tag == 'mspace':
            from .mspace_visitor import MspaceVisitor
            return MspaceVisitor(self.strategy).visit(child)
        elif tag == 'menclose':
            from .menclose_visitor import MencloseVisitor
            return MencloseVisitor(self.strategy).visit(child)
        elif tag == 'mmultiscripts':
            from .mmultiscripts_visitor import MmultiscriptsVisitor
            return MmultiscriptsVisitor(self.strategy).visit(child)
        elif tag == 'maction':
            from .maction_visitor import MactionVisitor
            return MactionVisitor(self.strategy).visit(child)
        elif tag == 'merror':
            from .merror_visitor import MerrorVisitor
            return MerrorVisitor(self.strategy).visit(child)
        elif tag == 'mpadded':
            from .mpadded_visitor import MpaddedVisitor
            return MpaddedVisitor(self.strategy).visit(child)
        elif tag == 'mphantom':
            from .mphantom_visitor import MphantomVisitor
            return MphantomVisitor(self.strategy).visit(child)
        elif tag == 'ms':
            from .ms_visitor import MsVisitor
            return MsVisitor(self.strategy).visit(child)
        elif tag == 'mglyph':
            from .mglyph_visitor import MglyphVisitor
            return MglyphVisitor(self.strategy).visit(child)
        elif tag == 'maligngroup':
            from .maligngroup_visitor import MaligngroupVisitor
            return MaligngroupVisitor(self.strategy).visit(child)
        elif tag == 'malignmark':
            from .malignmark_visitor import MalignmarkVisitor
            return MalignmarkVisitor(self.strategy).visit(child)
        elif tag == 'mlabeledtr':
            from .mlabeledtr_visitor import MlabeledtrVisitor
            return MlabeledtrVisitor(self.strategy).visit(child)
        else:
            # Fallback: return text content for unknown elements
            import sys
            print(f"[WARNING] Unknown element <{tag}> in msub, using text fallback", file=sys.stderr)
            return _text_content(child)

    def _wrap_if_needed(self, base: str) -> str:
        """Wrap base in parentheses if needed, avoiding double-wrapping."""
        # Check if base already has delimiters (starts and ends with matching delimiters)
        base_stripped = base.strip()
        if base_stripped:
            # Check for matching delimiters
            delimiter_pairs = {
                '(': ')',
                '[': ']',
                '{': '}',
                '\\left(': '\\right)',
                '\\left[': '\\right]',
                '\\left\\{': '\\right\\}',
            }

            for open_delim, close_delim in delimiter_pairs.items():
                if base_stripped.startswith(open_delim) and base_stripped.endswith(close_delim):
                    # Already has delimiters, no need to wrap
                    return base

        # Check if base needs grouping for proper subscript application
        # In LaTeX, x_2 applies subscript to x, but "a + b_2" applies only to b
        # We need to brace multi-element bases: {a + b}_2
        #
        # Use braces {} for grouping (invisible) not parentheses () (visible)
        # Only wrap if base contains operators that indicate a true multi-element expression
        # Don't wrap for spaces alone (e.g., "\Delta H" has space but is semantically single)
        math_operators = {'=', '+', '-', '/', '*', '\\times', '\\cdot', '\\pm', '\\to'}
        if ' ' in base and any(op in base for op in math_operators):
            return f"{{{base}}}"
        return base

    def _brace(self, content: str) -> str:
        return f"{{{content}}}"

    def _contains_superscript(self, base: str) -> bool:
        """
        Check if base contains a LaTeX superscript (^{...} or ^X).

        This is important for proper grouping when adding subscripts.
        For example: f^{\\prime} must be wrapped as {f^{\\prime}} before
        adding subscripts to avoid invalid syntax.

        Args:
            base: The base LaTeX string

        Returns:
            True if base contains an unbraced superscript
        """
        if not base or '^' not in base:
            return False

        # If the entire base is already wrapped in braces, it's safe
        base_stripped = base.strip()
        if base_stripped.startswith('{') and base_stripped.endswith('}'):
            # Check if these braces wrap the entire expression
            depth = 0
            for i, char in enumerate(base_stripped):
                if char == '{':
                    depth += 1
                elif char == '}':
                    depth -= 1
                # If depth hits 0 before the end, the braces don't wrap everything
                if depth == 0 and i < len(base_stripped) - 1:
                    break
            # If we maintained depth > 0 until the last character, it's wrapped
            if i == len(base_stripped) - 1:
                return False

        # Base contains ^ and is not fully wrapped
        return True

    def can_handle(self, node: ET.Element) -> bool:
        return _local(node.tag) == 'msub'

    @property
    def element_name(self) -> str:
        return 'msub'

    def __repr__(self) -> str:
        return f"MsubVisitor(strategy={self.strategy.name})"