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

"""
DOCX parser for Microsoft Word documents.

This parser handles .docx files, extracting OMML equations and converting
them to MathML format using the existing DOCX processing pipeline.
"""

import os
from typing import List
from ..core.interfaces import Parser


class DocxParser(Parser):
    """
    Parser for Microsoft Word .docx files.

    This parser handles .docx files by extracting OMML equations and
    converting them to MathML using the existing DOCX processing pipeline.

    Examples:
        Parse DOCX file:
            >>> parser = DocxParser()
            >>> results = parser.parse("equations.docx")
            >>> isinstance(results, list)
            True
    """

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

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

        Args:
            source: Path to .docx file

        Returns:
            List of MathML equation strings (extracted from DOCX)

        Raises:
            FileNotFoundError: If DOCX file doesn't exist
            ValueError: If file is not a valid .docx file
            RuntimeError: If DOCX processing fails

        Examples:
            >>> parser = DocxParser()
            >>> # Assuming test.docx exists with equations
            >>> results = parser.parse("test.docx")
            >>> all(isinstance(eq, str) for eq in results)
            True
        """
        # Validate file exists
        if not os.path.exists(source):
            raise FileNotFoundError(f"DOCX file not found: {source}")

        # Validate file extension
        if not source.lower().endswith('.docx'):
            raise ValueError(f"File must have .docx extension: {source}")

        # Import here to avoid circular dependencies
        from ..processing import OMMLExtractor
        from ..core import omml_to_mathml
        from ..utils.styling_postprocessor import apply_styling_to_mathml_from_omml

        # Get XSL path (in core module)
        current_dir = os.path.dirname(os.path.abspath(__file__))
        core_dir = os.path.join(os.path.dirname(current_dir), 'core')
        xsl_path = os.path.join(core_dir, 'OMML2MML.xsl')

        try:
            # Extract OMML from DOCX using OMMLExtractor
            extractor = OMMLExtractor()
            equation_dicts = extractor.extract_from_docx(source)

            if not equation_dicts:
                # No equations found
                return []

            # Convert each OMML to MathML
            results = []
            for eq_dict in equation_dicts:
                try:
                    # Extract the cleaned OMML string from the dictionary
                    omml_str = eq_dict.get('cleaned_omml', eq_dict.get('omml', ''))
                    if not omml_str:
                        continue

                    # Step 1: XSLT transformation
                    mathml_str = omml_to_mathml(omml_str, xsl_path)

                    # Step 2: Post-process to fix table structure and add styling
                    # CRITICAL: This fixes the OMML2MML.xsl bug where <mtr><mrow> should be <mtr><mtd>
                    mathml_str = apply_styling_to_mathml_from_omml(omml_str, mathml_str)

                    if mathml_str and mathml_str.strip():
                        results.append(mathml_str)
                except Exception as e:
                    # Log error but continue with other equations
                    print(f"Warning: Failed to convert OMML equation: {e}")
                    continue

            return results

        except Exception as e:
            raise RuntimeError(f"DOCX processing failed: {e}")

    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 is a .docx file, False otherwise

        Examples:
            >>> parser = DocxParser()
            >>> parser.can_handle("equations.docx")
            True
            >>> parser.can_handle("<math><mi>x</mi></math>")
            False
        """
        # Check file extension
        if source.lower().endswith('.docx'):
            return True

        # Check if it's an existing file with .docx extension
        if os.path.exists(source) and source.lower().endswith('.docx'):
            return True

        return False

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

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