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

"""
Visitor for <mfrac> (fraction) MathML elements.

The <mfrac> element represents fractions in MathML:
- Standard fractions: \\frac{numerator}{denominator}
- Display fractions: \\dfrac{numerator}{denominator}
- Bevelled fractions (line fractions): numerator/denominator
"""

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 MfracVisitor(Visitor):
    """
    Handles <mfrac> (fraction) MathML elements.

    This visitor converts fractions to LaTeX format using \\frac or \\dfrac
    commands depending on context.

    Examples:
        Standard fraction:
            <mfrac><mn>1</mn><mn>2</mn></mfrac> → \\dfrac{1}{2}

        Algebraic fraction:
            <mfrac><mi>x</mi><mi>y</mi></mfrac> → \\dfrac{x}{y}

        Complex fraction:
            <mfrac>
              <mrow><mi>x</mi><mo>+</mo><mn>1</mn></mrow>
              <mrow><mi>y</mi><mo>-</mo><mn>1</mn></mrow>
            </mfrac>
            → \\dfrac{x + 1}{y - 1}

        Bevelled fraction (bevelled="true"):
            <mfrac bevelled="true"><mn>1</mn><mn>2</mn></mfrac> → 1/2

        No-bar stacked fraction (linethickness="0"):
            <mfrac linethickness="0"><mi>n</mi><mi>k</mi></mfrac> → \genfrac{}{}{0pt}{}{n}{k}

    Note:
        For full compatibility with the original converter, we need to:
        1. Detect xlongequal pattern (special chemistry notation)
        2. Handle script context (use \\frac in superscripts/subscripts)
        3. Handle display style context (use \\dfrac in display mode)

        Currently implements basic functionality. Advanced features TODO.
    """

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

        Args:
            strategy: The formatting strategy to use
            context: Shared conversion context for state tracking
        """
        super().__init__(strategy)
        self.context = context
        # We'll need a reference to the visitor registry to convert children
        # This will be set by the conversion stage
        self._visitor_registry = None

    def set_visitor_registry(self, registry):
        """
        Set the visitor registry for converting child elements.

        Args:
            registry: The VisitorRegistry instance

        Note:
            This is called by the conversion stage to enable child conversion.
        """
        self._visitor_registry = registry

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

        Args:
            node: The <mfrac> element to convert

        Returns:
            LaTeX fraction string

        Raises:
            ValueError: If node is not an <mfrac> element
            ValueError: If mfrac has fewer than 2 children
        """
        if not self.can_handle(node):
            raise ValueError(f"MfracVisitor cannot handle element '{node.tag}'")

        # mfrac should have exactly 2 children: numerator and denominator
        children = list(node)
        if len(children) < 2:
            # Malformed mfrac - handle gracefully for MathJax compatibility
            # \frac{} or \frac{x}{} should work; \frac without braces won't
            if len(children) == 0:
                return "\\dfrac{}{}"
            elif len(children) == 1:
                # Only numerator provided
                numerator = self._convert_child(children[0])
                return f"\\dfrac{{{numerator}}}{{}}"

        # Check for xlongequal pattern with === in denominator FIRST (BUG-009 fix)
        # This MUST come before linethickness check because noBar fractions
        # with === in denominator should produce \xlongequal, not bevelled fraction
        # Pattern: <mfrac linethickness="0"><text>高温</text><mo>===</mo></mfrac>
        if self._is_xlongequal_with_equals_denominator(children):
            # Extract text from numerator (goes in braces)
            numerator = self._convert_child(children[0])
            return f"\\xlongequal[\\quad]{{{numerator}}}"

        # Check for xlongequal pattern WITH both upper and lower text
        # Pattern: <mfrac><munder><text1><mo>‾</mo></munder><text2></mfrac>
        # This represents \xlongequal[text2]{text1} (text above and below equals)
        if self._is_xlongequal_with_both_texts(children):
            # Extract text from numerator (goes in braces) and denominator (goes in brackets)
            upper_text = self._extract_reaction_condition_text(children[0])
            lower_text = self._convert_child(children[1])

            # Strip any \mathrm{} or \text{} wrappers from both texts
            # Note: The post-processing will handle space removal
            lower_clean = self._strip_latex_wrappers(lower_text)
            upper_clean = self._strip_latex_wrappers(upper_text)

            return f"\\xlongequal[{lower_clean}]{{{upper_clean}}}"

        # Check for xlongequal pattern (chemistry reaction condition)
        # Pattern: <mfrac><munder><text><mo>‾</mo></munder><empty/></mfrac>
        # This is Word's way of representing reaction conditions like "点燃" above an arrow
        if self._is_chemical_reaction_condition(children):
            # Extract the text from the underlined numerator
            condition_text = self._extract_reaction_condition_text(children[0])
            return f"\\xlongequal[\\quad]{{{condition_text}}}"

        # Check for bevelled fraction (bevelled="true" attribute triggers inline fraction)
        # Note: bevelled="true" means inline fraction with slash (a/b)
        bevelled = node.get('bevelled')
        if bevelled == 'true':
            return self._convert_bevelled_fraction(children)

        # Check for no-bar stacking (linethickness="0")
        # Note: linethickness="0" means no-bar stacking (like binomial), NOT bevelled
        # This is for binomial-style stacking without a fraction bar
        linethickness = node.get('linethickness')
        if linethickness == '0':
            return self._convert_nobar_stack(children)

        # Convert numerator and denominator
        numerator = self._convert_child(children[0])
        denominator = self._convert_child(children[1])

        # Context-aware fraction command selection
        # Priority: Script context > display style context > default
        if self.context and self.context.in_script_context():
            # Use \frac in script contexts (superscript/subscript) for proper sizing
            frac_command = "\\frac"
        elif self.context and self.context.display_style_context:
            # Use \dfrac if in display style context (from mstyle)
            frac_command = "\\dfrac"
        else:
            # Default to \dfrac for main equations
            frac_command = "\\dfrac"

        # Wrap in braces and return
        return f"{frac_command}{self._brace(numerator)}{self._brace(denominator)}"

    def _convert_bevelled_fraction(self, children: list) -> str:
        """
        Convert bevelled (inline) fraction.

        Bevelled fractions display as numerator/denominator in a single line.
        This is triggered by bevelled="true" attribute.

        Note: This is different from linethickness="0" which produces stacking
        without a fraction bar (like binomial coefficients).

        Args:
            children: List of child elements [numerator, denominator]

        Returns:
            LaTeX string with / separator

        Examples:
            1/2, x/y, (x+1)/(y-1)
        """
        numerator = self._convert_child(children[0])
        denominator = self._convert_child(children[1])

        # For bevelled fractions, use simple / separator
        # May need parentheses for complex expressions
        # TODO: Add intelligent parenthesization
        return f"{numerator}/{denominator}"

    def _convert_nobar_stack(self, children: list) -> str:
        """
        Convert no-bar stacked fraction (linethickness="0").

        This is for stacking like binomial coefficients where numerator
        is above denominator but without a fraction bar.

        Args:
            children: List of child elements [numerator, denominator]

        Returns:
            LaTeX string for stacked notation

        Note:
            We use \\begin{array}{c}...\\end{array} for proper stacking.
            This is more user-friendly and widely understood than \\genfrac syntax.

        Examples:
            <mfrac linethickness="0"><mi>n</mi><mi>k</mi></mfrac>
            → \\begin{array}{c} n \\\\ k \\end{array}
        """
        numerator = self._convert_child(children[0])
        denominator = self._convert_child(children[1])

        # Use array environment for proper no-bar stacking
        # Format: \begin{array}{c} top \\ bottom \end{array}
        # Center-aligned single column with line break between elements
        # Note: No space after \\ to avoid it being converted to \~
        return f"\\begin{{array}}{{c}} {numerator} \\\\\\\\{denominator} \\end{{array}}"

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

        Args:
            child: The child element to convert

        Returns:
            LaTeX string

        Note:
            For now, we directly instantiate the appropriate visitor.
            In the future, this should use the visitor registry.
        """
        from ..utils import local_name as _local
        tag = _local(child.tag)

        if tag == 'mi':
            from .mi_visitor import MiVisitor
            visitor = MiVisitor(self.strategy)
            return visitor.visit(child)
        elif tag == 'mo':
            from .mo_visitor import MoVisitor
            visitor = MoVisitor(self.strategy)
            return visitor.visit(child)
        elif tag == 'mn':
            from .mn_visitor import MnVisitor
            visitor = MnVisitor(self.strategy)
            return visitor.visit(child)
        elif tag == 'mrow':
            from .mrow_visitor import MrowVisitor
            return MrowVisitor(self.strategy).visit(child)
        elif tag == 'mfrac':
            from .mfrac_visitor import MfracVisitor
            return MfracVisitor(self.strategy).visit(child)
        elif tag == 'msup':
            from .msup_visitor import MsupVisitor
            return MsupVisitor(self.strategy).visit(child)
        elif tag == 'msub':
            from .msub_visitor import MsubVisitor
            return MsubVisitor(self.strategy).visit(child)
        elif tag == 'msubsup':
            from .msubsup_visitor import MsubsupVisitor
            return MsubsupVisitor(self.strategy).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 == '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 for unknown elements: return text content
            import sys
            print(f"[WARNING] Unknown element <{tag}> in mfrac, using text fallback", file=sys.stderr)
            return _text_content(child)

    def _brace(self, content: str) -> str:
        """
        Wrap content in braces if needed.

        Args:
            content: The content to wrap

        Returns:
            Content wrapped in braces

        Note:
            Always wraps in braces for fractions to ensure proper LaTeX parsing.
        """
        return f"{{{content}}}"

    def _is_chemical_reaction_condition(self, children: list) -> bool:
        """
        Check if this fraction represents a chemical reaction condition.

        Pattern: numerator is munder with underline OR mover with overline,
        denominator is empty/whitespace

        Args:
            children: [numerator, denominator] child elements

        Returns:
            True if this is a chemical reaction condition pattern
        """
        if len(children) != 2:
            return False

        numerator = children[0]
        denominator = children[1]

        # Unwrap mrow if present (Word often wraps in mrow)
        numerator_tag = _local(numerator.tag)
        if numerator_tag == "mrow" and len(numerator) == 1:
            numerator = numerator[0]
            numerator_tag = _local(numerator.tag)

        # Check if numerator is munder with underline OR mover with overline
        if numerator_tag in ("munder", "mover") and len(numerator) >= 2:
            line_node = numerator[1]  # Second child is the line (under or over)
            if _local(line_node.tag) == "mo":
                text = line_node.text or ""
                # Check for line character (same character used for both over and under)
                if "‾" in text or text.strip() in ["¯", "―", "−", "_", "-"]:
                    # Check if denominator is empty
                    denom_tag = _local(denominator.tag)

                    # Empty <mo> tag
                    if denom_tag == "mo":
                        denom_text = denominator.text or ""
                        if denom_text.strip() == "":
                            return True

                    # Empty <mrow/> tag
                    elif denom_tag == "mrow":
                        # Check if mrow has no children or only whitespace
                        if len(denominator) == 0:
                            return True
                        # Check if mrow has only whitespace text nodes
                        if len(denominator) == 1 and _local(denominator[0].tag) == "mo":
                            mo_text = denominator[0].text or ""
                            if mo_text.strip() == "":
                                return True

        return False

    def _extract_reaction_condition_text(self, numerator_node: ET.Element) -> str:
        """
        Extract text from underlined/overlined numerator for reaction condition.

        Args:
            numerator_node: The munder or mover element (or mrow wrapping it) containing the condition text

        Returns:
            LaTeX content with user-specified formatting preserved (e.g., \\mathbf{})
            but subject-determined formatting removed (e.g., \\mathrm{})
        """
        numerator_tag = _local(numerator_node.tag)

        # Unwrap mrow if present
        if numerator_tag == "mrow" and len(numerator_node) == 1:
            numerator_node = numerator_node[0]
            numerator_tag = _local(numerator_node.tag)

        # Handle both munder and mover
        if numerator_tag not in ("munder", "mover"):
            return ""

        # The first child contains the actual content (same for both munder and mover)
        if len(numerator_node) > 0:
            content_node = numerator_node[0]

            # Convert to LaTeX, preserving user-specified formatting (like \mathbf{})
            content = self._convert_child(content_node)

            # Only strip subject-determined formatting (\mathrm{} for chemistry mode)
            # Preserve user-specified formatting like \mathbf{}, \textbf{}, \textit{}, etc.
            if content.startswith("\\mathrm{") and content.endswith("}"):
                content = content[8:-1]  # Remove \mathrm{ and }
            # Strip \text{} wrapper if present
            elif content.startswith("\\text{") and content.endswith("}"):
                content = content[6:-1]  # Remove \text{ and }

            # Clean up extra spaces
            return content.strip()

        return ""

    def _is_xlongequal_with_equals_denominator(self, children: list) -> bool:
        """
        Check if this fraction represents xlongequal with === in denominator.

        Pattern: numerator has content, denominator contains only consecutive equals signs
        This pattern is used in chemistry for reaction arrows with conditions above.

        Args:
            children: [numerator, denominator] child elements

        Returns:
            True if denominator contains only === (or ==, ====, etc.)

        Examples:
            <mfrac>
                <mi>高温</mi>
                <mo>===</mo>
            </mfrac>
            → \\xlongequal[\\quad]{高温}

            <mfrac>
                <mtext>heat</mtext>
                <mo>==</mo>
            </mfrac>
            → \\xlongequal[\\quad]{heat}
        """
        if len(children) != 2:
            return False

        numerator = children[0]
        denominator = children[1]

        # Get text content from denominator
        denom_text = _text_content(denominator).strip()

        # Check if denominator contains only equals signs (2 or more)
        # Pattern: ==, ===, ====, = = =, etc. (with or without spaces)
        import re
        # Remove all spaces to check if it's only equals signs
        denom_text_no_spaces = denom_text.replace(' ', '')
        if denom_text_no_spaces and re.match(r'^=+$', denom_text_no_spaces) and len(denom_text_no_spaces) >= 2:
            # Check if numerator has actual content
            num_text = _text_content(numerator).strip()
            if num_text and num_text != "":
                return True

        return False

    def _is_xlongequal_with_both_texts(self, children: list) -> bool:
        """
        Check if this fraction represents xlongequal with both upper and lower text.

        Pattern: numerator is munder with underline OR mover with overline,
        denominator has actual content

        Args:
            children: [numerator, denominator] child elements

        Returns:
            True if this is xlongequal with both texts pattern

        Examples:
            <mfrac>
                <munder><mi>abc</mi><mo>‾</mo></munder>
                <mi>defg</mi>
            </mfrac>
            → \\xlongequal[defg]{abc}

            <mfrac>
                <mover><mi>abc</mi><mo>‾</mo></mover>
                <mi>defg</mi>
            </mfrac>
            → \\xlongequal[defg]{abc}

            <mfrac>
                <mrow><mover><mrow><mi>abc</mi></mrow><mo>‾</mo></mover></mrow>
                <mrow><mi>defg</mi></mrow>
            </mfrac>
            → \\xlongequal[defg]{abc}
        """
        if len(children) != 2:
            return False

        numerator = children[0]
        denominator = children[1]

        # Unwrap mrow if present (Word often wraps in mrow)
        numerator_tag = _local(numerator.tag)
        if numerator_tag == "mrow" and len(numerator) == 1:
            numerator = numerator[0]
            numerator_tag = _local(numerator.tag)

        # Check if numerator is munder with underline OR mover with overline
        if numerator_tag in ("munder", "mover") and len(numerator) >= 2:
            line_node = numerator[1]  # Second child is the line (under or over)
            if _local(line_node.tag) == "mo":
                text = line_node.text or ""
                # Check for line character (same character used for both over and under)
                if "‾" in text or text.strip() in ["¯", "―", "−", "_", "-"]:
                    # Check if denominator is NOT empty (has actual content)
                    denom_text = _text_content(denominator).strip()
                    if denom_text and denom_text != "":
                        return True

        return False

    def _strip_latex_wrappers(self, latex: str) -> str:
        """
        Strip LaTeX wrapper commands like \\mathrm{}, \\text{}, etc.

        Args:
            latex: LaTeX string that might have wrappers

        Returns:
            Clean text without wrappers

        Examples:
            \\mathrm{abc} → abc
            \\text{hello} → hello
            \\mathrm{d e f g} → d e f g (spaces preserved)
        """
        latex = latex.strip()

        # Strip \mathrm{} wrapper
        if latex.startswith("\\mathrm{") and latex.endswith("}"):
            latex = latex[8:-1]

        # Strip \text{} wrapper
        if latex.startswith("\\text{") and latex.endswith("}"):
            latex = latex[6:-1]

        # Strip \mathbf{} wrapper
        if latex.startswith("\\mathbf{") and latex.endswith("}"):
            latex = latex[8:-1]

        return latex.strip()

    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 <mfrac> element, False otherwise
        """
        return _local(node.tag) == 'mfrac'

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

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