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

r"""
Visitor for <mfenced> (fenced/delimited expressions) MathML elements.

The <mfenced> element represents expressions enclosed by delimiters:
- Auto-scaling parentheses: \left( ... \right)
- Custom brackets: \left[ ... \right]
- Custom braces: \left\{ ... \right\}
- Cases environment: single left brace
- Separators: commas, semicolons between elements

This visitor handles delimiter scaling and separator insertion.
"""

from typing import Optional, List
from lxml import etree as ET
from ..core.interfaces import Visitor, Strategy
from ..utils import text_content as _text_content, local_name as _local


class MfencedVisitor(Visitor):
    r"""
    Handles <mfenced> (fenced/delimited) MathML elements.

    Converts fenced expressions to LaTeX with auto-scaling delimiters.

    Examples:
        Default parentheses:
            <mfenced><mi>x</mi><mi>y</mi></mfenced> → \left(x,y\right)

        Custom brackets:
            <mfenced open="[" close="]"><mi>a</mi></mfenced> → \left[a\right]

        Custom braces:
            <mfenced open="{" close="}"><mi>x</mi></mfenced> → \left\{x\right\}

        Angle brackets:
            <mfenced open="⟨" close="⟩"><mi>v</mi></mfenced> → \left\langle v\right\rangle

        Single left brace (piecewise/cases):
            <mfenced open="{" close="">
              <mtable>...</mtable>
            </mfenced> → \left\{\begin{array}{...}...\end{array}\right.

        Custom separator (semicolon):
            <mfenced separators=";"><mi>a</mi><mi>b</mi></mfenced> → \left(a;b\right)

        Multiple separators:
            <mfenced separators="; "><mi>a</mi><mi>b</mi><mi>c</mi></mfenced>
            → \left(a;b c\right)
    """

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

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

        Args:
            node: The <mfenced> element to convert

        Returns:
            LaTeX string with auto-scaling delimiters

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

        # Get opening and closing delimiters (default: parentheses)
        open_delim = node.get('open', '(')
        close_delim = node.get('close', ')')

        # Get separator (default: comma)
        separators = node.get('separators', ',')

        # Convert children
        children = list(node)
        if not children:
            # Empty mfenced
            left = self._get_left_delimiter(open_delim)
            right = self._get_right_delimiter(close_delim)
            return f"{left}{right}"

        # NOTE: We NO LONGER use cases environment for better compatibility
        # Instead, we use explicit \left\{ and \right. notation
        # (Cases environment is not universally supported)

        # Check if this is set notation: { pattern | condition }
        if open_delim == '{' and close_delim == '}':
            set_notation_result = self._try_convert_as_set_notation(node, children)
            if set_notation_result:
                return set_notation_result

        # Check if this is an interval with nested mfenced for the closing delimiter
        # Pattern: <mfenced open="(" close=""> ... <mfenced open="" close="]">
        # This should merge into a single interval: \left( ... \right]
        if self._is_split_interval(node, children, open_delim, close_delim):
            return self._merge_split_interval(node, children, open_delim)

        # Convert each child, tracking which are operators
        converted_children = []
        child_types = []
        for child in children:
            converted = self._convert_child(child)
            converted_children.append(converted)
            child_types.append(_local(child.tag))

        # Determine if this is a continuous expression or a list
        # If there are explicit separator operators (mo elements with separator chars),
        # treat as continuous expression (join with spaces)
        # Otherwise, use the separators attribute for list formatting
        content = self._smart_join(converted_children, child_types, separators)

        # Get LaTeX delimiters
        left = self._get_left_delimiter(open_delim)
        right = self._get_right_delimiter(close_delim)

        return f"{left}{content}{right}"

    def _try_convert_as_set_notation(self, node: ET.Element, children: List) -> Optional[str]:
        r"""
        Try to convert as set notation: { pattern | condition }.

        Set notation has the pattern:
        - { (x, y) | x+y < 2 }  →  \left\{ (x, y) \mid x+y < 2 \right\}
        - { x | x > 0 }  →  \left\{ x \mid x > 0 \right\}

        Detection heuristics:
        1. First child (or first few children) form the "pattern" (variable/tuple)
        2. There's a nested <mfenced open="|" close="|"> that's really a separator
           OR there are exactly 2 distinct groups of children
        3. Last children form the "condition"

        Args:
            node: The outer mfenced element with open="{" close="}"
            children: List of child elements

        Returns:
            LaTeX string if this is set notation, None otherwise
        """
        if len(children) < 2:
            return None

        # Strategy 1: Look for nested mfenced with | delimiters
        # If the second or third child is <mfenced open="|" close="|">,
        # and there's content after it OR before it, treat as set notation
        # BUT keep the |...| as absolute value brackets in the output
        for i, child in enumerate(children):
            if _local(child.tag) == 'mfenced':
                child_open = child.get('open', '(')
                child_close = child.get('close', ')')

                if child_open == '|' and child_close == '|':
                    # Found nested | delimiters
                    # Check if there's content before this (the pattern) or after (condition)
                    has_content_before = i >= 1
                    has_content_after = i < len(children) - 1

                    if has_content_before or has_content_after:
                        # This looks like set notation!
                        # Split into: pattern (before), |...|, and rest
                        pattern_parts = children[:i]
                        pipe_element = child  # The entire <mfenced open="|" close="|"> element
                        condition_parts = children[i+1:]

                        # Convert pattern
                        pattern_latex = ' '.join(self._convert_child(c) for c in pattern_parts if c is not None)

                        # Convert the |...| element as absolute value (keep the delimiters!)
                        pipe_latex = self._convert_child(pipe_element)

                        # Convert remaining condition
                        condition_latex = ' '.join(self._convert_child(c) for c in condition_parts if c is not None)

                        # Assemble: { pattern \mid |pipe_content| condition }
                        parts = []
                        if pattern_latex:
                            parts.append(pattern_latex)
                        parts.append('\\mid')
                        if pipe_latex:
                            parts.append(pipe_latex)
                        if condition_latex:
                            parts.append(condition_latex)

                        content = ' '.join(parts)
                        return f"\\left\\{{{content}\\right\\}}"

        # Strategy 2: Check if there are exactly 2 "groups" of elements
        # where the first group is a single identifier/tuple, suggesting { x | condition }
        # This handles cases like { x x+1<2 } where x and x+1<2 should be separated by \mid
        if len(children) >= 2:
            first_child_type = _local(children[0].tag)

            # If first child is a single identifier (mi) or a tuple (mfenced with parens)
            if first_child_type in ['mi', 'mfenced']:
                # Check if this looks like a pattern followed by a condition
                # Heuristic: if first child is simple (mi or mfenced), and there are more elements,
                # and those elements form an expression/condition, insert \mid

                # For now, check if we have exactly these patterns:
                # 1. First child is <mfenced open="(" close=")"> (tuple)
                # 2. OR first child is <mi> (variable)
                # 3. Rest form a condition

                if first_child_type == 'mi':
                    # Check if second element is also mi (likely the start of condition)
                    if len(children) >= 2 and _local(children[1].tag) == 'mi':
                        # Likely: { x x+1<2 } should be { x | x+1<2 }
                        pattern_latex = self._convert_child(children[0])
                        condition_latex = ' '.join(self._convert_child(c) for c in children[1:])
                        return f"\\left\\{{{pattern_latex} \\mid {condition_latex}\\right\\}}"

                elif first_child_type == 'mfenced':
                    first_child_open = children[0].get('open', '(')
                    first_child_close = children[0].get('close', ')')

                    # Check if it's a tuple (parentheses)
                    if first_child_open == '(' and first_child_close == ')':
                        # Pattern: { (x,y) ... } - check if ... is a condition
                        pattern_latex = self._convert_child(children[0])

                        # Check if remaining children don't start with a comma
                        # (which would indicate list notation, not set notation)
                        if len(children) >= 2:
                            second_type = _local(children[1].tag)
                            if second_type != 'mo' or (second_type == 'mo' and _text_content(children[1]).strip() != ','):
                                # Not a list, likely set notation
                                condition_latex = ' '.join(self._convert_child(c) for c in children[1:])
                                return f"\\left\\{{{pattern_latex} \\mid {condition_latex}\\right\\}}"

        return None

    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).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).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 == 'mrow':
            from .mrow_visitor import MrowVisitor
            return MrowVisitor(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 == '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 mfenced, using text fallback", file=sys.stderr)
            return _text_content(child)

    def _smart_join(self, items: list, types: list, separators: str) -> str:
        """
        Intelligently join items based on whether they form a continuous expression.

        Args:
            items: Converted LaTeX strings
            types: Element types (mi, mo, mn, etc.)
            separators: Separator string from mfenced attribute

        Returns:
            Joined LaTeX string
        """
        if len(items) == 0:
            return ''
        if len(items) == 1:
            return items[0]

        # Check if this looks like a continuous expression:
        # - Contains 'mo' (operator) elements
        # - Separators not explicitly set (or default comma)
        has_operators = 'mo' in types

        if has_operators and separators == ',':
            # Continuous expression: join with spaces, no extra separators
            # Filter out empty items
            return ' '.join(item for item in items if item)
        else:
            # List of items: use traditional separator insertion
            return self._insert_separators(items, separators)

    def _insert_separators(self, items: list, separators: str) -> str:
        """Insert separators between items for list-style formatting."""
        if len(items) == 0:
            return ''
        if len(items) == 1:
            return items[0]

        # Parse separator string
        # If multiple characters, each is used for successive separators
        # If fewer separators than gaps, last separator is reused
        sep_list = list(separators) if separators else [',']

        result = [items[0]]
        for i, item in enumerate(items[1:], start=0):
            # Get appropriate separator (reuse last if not enough)
            sep_idx = min(i, len(sep_list) - 1)
            separator = sep_list[sep_idx]
            result.append(separator)
            result.append(item)

        return ''.join(result)

    def _get_left_delimiter(self, delim: str) -> str:
        """Map opening delimiter to LaTeX \\left command."""
        delimiter_map = {
            '(': '\\left(',
            '[': '\\left[',
            '{': '\\left\\{',
            '⟨': '\\left\\langle',
            '⌈': '\\left\\lceil',
            '⌊': '\\left\\lfloor',
            '|': '\\left|',
            '‖': '\\left\\|',
            '': '\\left.',  # Invisible left delimiter
        }

        return delimiter_map.get(delim, f'\\left{delim}')

    def _get_right_delimiter(self, delim: str) -> str:
        """Map closing delimiter to LaTeX \\right command."""
        delimiter_map = {
            ')': '\\right)',
            ']': '\\right]',
            '}': '\\right\\}',
            '⟩': '\\right\\rangle',
            '⌉': '\\right\\rceil',
            '⌋': '\\right\\rfloor',
            '|': '\\right|',
            '‖': '\\right\\|',
            '': '\\right.',  # Invisible right delimiter
        }

        return delimiter_map.get(delim, f'\\right{delim}')

    def _is_split_interval(self, node: ET.Element, children: list, open_delim: str, close_delim: str) -> bool:
        """
        Detect if this is a split interval notation pattern.

        Pattern: <mfenced open="(" close=""> ... <mfenced open="" close="]">
        This represents an interval like (0, 1/4] split across two mfenced elements.

        Also handles case where content is wrapped in mrow:
        <mfenced open="(" close=""><mrow> ... <mfenced open="" close="]">...</mfenced></mrow></mfenced>

        Returns True if:
        1. Outer has opening delimiter but NO closing delimiter (close="")
        2. Last child is <mfenced> with NO opening delimiter (open="") but HAS closing delimiter
        3. There are other children before the last mfenced (the interval content)

        Args:
            node: The outer mfenced element
            children: List of child elements
            open_delim: Opening delimiter of outer mfenced
            close_delim: Closing delimiter of outer mfenced

        Returns:
            True if this is a split interval pattern
        """
        # Check pattern: outer has open delim but no close delim
        if not (open_delim in '([{' and close_delim == ''):
            return False

        # Handle case where content is wrapped in a single mrow
        actual_children = children
        if len(children) == 1 and _local(children[0].tag) == 'mrow':
            actual_children = list(children[0])

        # Need at least 2 children (content + nested mfenced)
        if len(actual_children) < 2:
            return False

        # Check if last child is mfenced with complementary delimiters
        last_child = actual_children[-1]
        if _local(last_child.tag) != 'mfenced':
            return False

        # Last mfenced should have no open delimiter but have close delimiter
        last_open = last_child.get('open', '(')
        last_close = last_child.get('close', ')')

        if last_open == '' and last_close in ')]}\u232A\u2309\u230B':  # Closing delimiters
            return True

        return False

    def _merge_split_interval(self, node: ET.Element, children: list, open_delim: str) -> str:
        """
        Merge split interval into a single LaTeX interval.

        Pattern: <mfenced open="(" close=""> <content> <mfenced open="" close="]">
        Output: \\left( <content> \\right]

        Also handles case where content is wrapped in mrow:
        <mfenced open="(" close=""><mrow> ... <mfenced open="" close="]">...</mfenced></mrow></mfenced>

        Args:
            node: The outer mfenced element
            children: List of child elements
            open_delim: Opening delimiter (e.g., '(', '[')

        Returns:
            LaTeX string for merged interval
        """
        # Handle case where content is wrapped in a single mrow
        actual_children = children
        if len(children) == 1 and _local(children[0].tag) == 'mrow':
            actual_children = list(children[0])

        # Get the closing delimiter from the last child (which is the nested mfenced)
        last_child = actual_children[-1]
        close_delim = last_child.get('close', ')')

        # Convert all children except the last (which is the nested mfenced)
        content_children = actual_children[:-1]

        # Also convert the CONTENT of the last mfenced (not the mfenced itself)
        last_mfenced_children = list(last_child)

        # Combine content from both outer and inner mfenced
        all_content_children = content_children + last_mfenced_children

        # Convert all content
        converted_parts = []
        for child in all_content_children:
            part = self._convert_child(child)
            if part:
                converted_parts.append(part)

        # Join with spaces (standard interval notation)
        content = ' '.join(converted_parts)

        # Build result with merged delimiters
        left = self._get_left_delimiter(open_delim)
        right = self._get_right_delimiter(close_delim)

        return f"{left}{content}{right}"

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

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

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