DoLuEdu-WordFileParse/scripts/omml_mathml2latex/parsers/mathml_parser.py

"""
MathML parser for direct MathML input.

This parser handles MathML XML input, performing validation and extraction
of individual math equations.
"""

import sys
from typing import List
from pathlib import Path
from lxml import etree as ET
from ..core.interfaces import Parser

# Import utilities from omml_to_tex package for HTML entity decoding and equation extraction
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
from ..utils import decode_html_entities, extract_math_equations


class MathMLParser(Parser):
    """
    Parser for MathML XML input.

    This parser handles direct MathML XML input, performing basic validation
    and extracting individual <math> elements.

    Examples:
        Single equation:
            >>> parser = MathMLParser()
            >>> mathml = "<math><mi>x</mi></math>"
            >>> results = parser.parse(mathml)
            >>> len(results)
            1

        Multiple equations:
            >>> parser = MathMLParser()
            >>> mathml = "<root><math><mi>x</mi></math><math><mi>y</mi></math></root>"
            >>> results = parser.parse(mathml)
            >>> len(results)
            2
    """

    def __init__(self):
        """Initialize the MathML parser."""
        pass

    def parse(self, source: str) -> List[str]:
        """
        Parse MathML input and return list of MathML equation strings.

        Args:
            source: MathML XML string or file path

        Returns:
            List of MathML equation strings (one per <math> element)

        Raises:
            ValueError: If input is not valid MathML XML
            RuntimeError: If parsing fails

        Examples:
            >>> parser = MathMLParser()
            >>> mathml = "<math><mi>x</mi><mo>+</mo><mi>y</mi></math>"
            >>> results = parser.parse(mathml)
            >>> len(results)
            1
            >>> '<mi>x</mi>' in results[0]
            True
        """
        import os

        # Check if source is a file path
        if os.path.exists(source):
            try:
                with open(source, 'r', encoding='utf-8') as f:
                    source = f.read()
            except (IOError, UnicodeDecodeError) as e:
                raise ValueError(f"Failed to read MathML file: {e}")

        # STRATEGY 1: Try regex-based extraction first (handles multi-equation files + HTML entities)
        # This is the same approach as the original omml_to_tex.py
        try:
            equations = extract_math_equations(source)
            if equations:
                return equations
        except Exception:
            # If regex extraction fails, fall through to XML parsing
            pass

        # STRATEGY 2: Try XML parsing as fallback (single well-formed document)
        try:
            root = ET.fromstring(source.encode('utf-8'))
        except ET.XMLSyntaxError as e:
            raise ValueError(f"Invalid XML syntax: {e}")

        # Find all <math> elements
        math_elements = []

        # Check if root itself is a <math> element
        if self._is_math_element(root):
            math_elements.append(root)
        else:
            # Search for <math> elements (with or without namespace)
            math_elements.extend(root.findall('.//{http://www.w3.org/1998/Math/MathML}math'))
            math_elements.extend(root.findall('.//math'))

        if not math_elements:
            # No <math> elements found - treat entire document as one equation if it looks like MathML
            if self._looks_like_mathml(root):
                math_elements.append(root)
            else:
                raise ValueError("No <math> elements found in MathML input")

        # Convert each <math> element to string
        results = []
        for math_elem in math_elements:
            mathml_str = ET.tostring(math_elem, encoding='unicode')
            results.append(mathml_str)

        return results

    def can_handle(self, source: str) -> bool:
        """
        Check if this parser can handle the given input source.

        Args:
            source: Input source to check

        Returns:
            True if source appears to be MathML, False otherwise

        Examples:
            >>> parser = MathMLParser()
            >>> parser.can_handle("<math><mi>x</mi></math>")
            True
            >>> parser.can_handle("<m:oMath>...</m:oMath>")
            False
        """
        # Check for MathML markers
        content_start = source.strip()[:200]
        return '<math' in content_start or '<mml:math' in content_start

    @property
    def parser_type(self) -> str:
        """Get the parser type identifier."""
        return "mathml"

    def _is_math_element(self, element: ET.Element) -> bool:
        """Check if element is a <math> element."""
        local_name = element.tag.split('}')[-1] if '}' in element.tag else element.tag
        return local_name == 'math'

    def _looks_like_mathml(self, element: ET.Element) -> bool:
        """Check if element tree looks like MathML content."""
        # Check for common MathML element tags
        mathml_tags = {'mi', 'mo', 'mn', 'mrow', 'mfrac', 'msup', 'msub', 'mtext'}

        # Get all element tags in tree
        all_tags = set()
        for elem in element.iter():
            local_name = elem.tag.split('}')[-1] if '}' in elem.tag else elem.tag
            all_tags.add(local_name)

        # If at least 2 MathML tags present, consider it MathML
        return len(all_tags & mathml_tags) >= 2

    def __repr__(self) -> str:
        """String representation for debugging."""
        return "MathMLParser()"