DoLuEdu-WordFileParse/scripts/omml_mathml2latex/core/context.py

"""
Conversion context data structure.

This module defines the ConversionContext dataclass that holds all state
and intermediate results throughout the conversion pipeline.
"""

from dataclasses import dataclass, field
from typing import Optional, List, Dict, Any


@dataclass
class ConversionContext:
    """
    Shared state for the conversion pipeline.

    This context object flows through all pipeline stages, accumulating
    intermediate results and maintaining conversion state.

    Attributes:
        input_type: Type of input ('docx', 'omml', 'mathml', 'stdin')
        subject_mode: Subject area hint ('math', 'chemistry', 'physics', 'statistics', 'auto')
        wrap_identifiers: Whether to wrap identifiers in \\mathrm{} (default: True)
        prefer_xlongequal: Use \\xlongequal for overset equals (default: True)

        # Intermediate results
        omml: OMML XML string (if applicable)
        mathml: MathML XML string
        latex: Generated LaTeX string

        # Validation state
        validation_errors: List of validation error messages
        validation_warnings: List of validation warning messages
        is_valid: Whether MathML passed validation

        # Color optimization state
        uniform_equation_color: Hex color if entire equation uses same color, else empty
        suppress_leaf_colors: Flag to suppress individual element colors when uniform color detected

        # Metadata
        equation_count: Number of equations processed
        current_equation_index: Index of current equation being processed
        context_hints: Additional context information

        # Performance metrics
        stage_timings: Dict mapping stage name to execution time (seconds)
        total_time: Total processing time (seconds)
    """

    # Configuration
    input_type: str
    subject_mode: str = "math"
    wrap_identifiers: bool = True
    prefer_xlongequal: bool = True

    # Intermediate results
    omml: Optional[str] = None
    mathml: Optional[str] = None
    latex: Optional[str] = None

    # Validation results
    validation_errors: List[str] = field(default_factory=list)
    validation_warnings: List[str] = field(default_factory=list)
    is_valid: bool = True

    # Color optimization state
    uniform_equation_color: str = ""
    suppress_leaf_colors: bool = False

    # Script context tracking (for fraction sizing)
    script_context_stack: List[str] = field(default_factory=list)
    display_style_context: bool = False

    # Set theory mode (for unclosed set notation)
    set_theory_mode: bool = False

    # Chemistry equation detection (cached)
    is_chemistry_equation: Optional[bool] = None

    # Metadata
    equation_count: int = 0
    current_equation_index: int = 0
    context_hints: Dict[str, Any] = field(default_factory=dict)

    # Performance metrics
    stage_timings: Dict[str, float] = field(default_factory=dict)
    total_time: float = 0.0

    def add_error(self, error: str) -> None:
        """Add a validation error."""
        self.validation_errors.append(error)
        self.is_valid = False

    def add_warning(self, warning: str) -> None:
        """Add a validation warning."""
        self.validation_warnings.append(warning)

    def record_stage_time(self, stage_name: str, time_seconds: float) -> None:
        """Record execution time for a stage."""
        self.stage_timings[stage_name] = time_seconds

    def has_errors(self) -> bool:
        """Check if any errors were recorded."""
        return len(self.validation_errors) > 0

    def has_warnings(self) -> bool:
        """Check if any warnings were recorded."""
        return len(self.validation_warnings) > 0

    def clear_validation_state(self) -> None:
        """Clear validation errors and warnings."""
        self.validation_errors.clear()
        self.validation_warnings.clear()
        self.is_valid = True

    def push_script_context(self, element_type: str) -> None:
        """
        Push a script context (msup/msub/msubsup) onto the stack.

        Args:
            element_type: The element type entering script context
        """
        self.script_context_stack.append(element_type)

    def pop_script_context(self) -> Optional[str]:
        """
        Pop a script context from the stack.

        Returns:
            The popped element type, or None if stack was empty
        """
        return self.script_context_stack.pop() if self.script_context_stack else None

    def in_script_context(self) -> bool:
        """Check if currently inside a script context (superscript/subscript)."""
        return len(self.script_context_stack) > 0

    def __str__(self) -> str:
        """String representation for debugging."""
        status = "valid" if self.is_valid else "invalid"
        return (
            f"ConversionContext("
            f"input_type={self.input_type}, "
            f"subject_mode={self.subject_mode}, "
            f"status={status}, "
            f"equations={self.equation_count})"
        )

    def __repr__(self) -> str:
        """Detailed representation for debugging."""
        return (
            f"ConversionContext(\n"
            f"  input_type={self.input_type!r},\n"
            f"  subject_mode={self.subject_mode!r},\n"
            f"  wrap_identifiers={self.wrap_identifiers},\n"
            f"  prefer_xlongequal={self.prefer_xlongequal},\n"
            f"  is_valid={self.is_valid},\n"
            f"  equation_count={self.equation_count},\n"
            f"  errors={len(self.validation_errors)},\n"
            f"  warnings={len(self.validation_warnings)},\n"
            f"  total_time={self.total_time:.4f}s\n"
            f")"
        )