DoLuEdu-WordFileParse/scripts/omml_mathml2latex/processing/docx_processor.py

"""
DOCX file processing and end-to-end conversion.

This module provides the DocxProcessor class which orchestrates the complete
conversion pipeline from DOCX to LaTeX, including OMML extraction, MathML
transformation, and LaTeX conversion.
"""

import logging
import time
from typing import List
from .result import ConversionResult
from .omml_extractor import OMMLExtractor

logger = logging.getLogger(__name__)


class DocxProcessor:
    """Process DOCX files and convert all OMML equations to LaTeX.

    This class coordinates:
    - OMML extraction from DOCX (via OMMLExtractor)
    - OMML → MathML transformation (via omml_to_mathml function)
    - MathML → LaTeX conversion (via MathMLToTeXConverter)

    Example:
        >>> from omml2tex.compat import LegacyMathMLToTeXConverter
        >>> processor = DocxProcessor(
        ...     xsl_path='OMML2MML.xsl',
        ...     converter=MathMLToTeXConverter()
        ... )
        >>> results = processor.process_docx('document.docx')
        >>> for result in results:
        ...     if result.success:
        ...         print(result.latex)
    """

    def __init__(self, xsl_path: str, converter, subject_mode: str = "auto"):
        """Initialize DOCX processor.

        Args:
            xsl_path: Path to OMML2MML.xsl transformation file
            converter: MathMLToTeXConverter instance
            subject_mode: Subject mode for conversion ('auto', 'math', 'chemistry', 'physics')
        """
        self.extractor = OMMLExtractor()
        self.xsl_path = xsl_path
        self.converter = converter
        self.subject_mode = subject_mode

    def process_docx(self, docx_path: str, omml_to_mathml_func=None) -> List[ConversionResult]:
        """Process a DOCX file and convert all equations.

        Args:
            docx_path: Path to DOCX file
            omml_to_mathml_func: Function to convert OMML to MathML (for dependency injection)

        Returns:
            List of ConversionResult objects

        Example:
            >>> results = processor.process_docx('test.docx')
            >>> successful = [r for r in results if r.success]
            >>> print(f"{len(successful)}/{len(results)} equations converted")
        """
        results = []

        try:
            # Extract OMML equations
            equations = self.extractor.extract_from_docx(docx_path)
            logger.info(f"Found {len(equations)} equations in {docx_path}")

            for eq_data in equations:
                result = ConversionResult()
                result.omml = eq_data['cleaned_omml']
                result.context = eq_data['context']
                result.position = eq_data['position']
                result.source_file = eq_data['source_file']
                result.display_mode = eq_data.get('display_mode', False)

                try:
                    start_time = time.time()

                    # Convert OMML to MathML
                    if omml_to_mathml_func is None:
                        # Import here to avoid circular dependency
                        from ..core.xslt_transformer import omml_to_mathml
                        omml_to_mathml_func = omml_to_mathml

                    mathml_xml = omml_to_mathml_func(eq_data['cleaned_omml'], self.xsl_path)
                    result.mathml = mathml_xml

                    # Convert MathML to LaTeX
                    latex = self.converter.convert(mathml_xml)
                    result.latex = latex

                    result.processing_time = time.time() - start_time
                    result.success = True

                except Exception as e:
                    result.error = str(e)
                    result.success = False
                    logger.error(f"Failed to convert equation {result.position}: {e}")

                results.append(result)

        except Exception as e:
            logger.error(f"Failed to process DOCX file: {e}")
            # Return empty results with error
            result = ConversionResult()
            result.error = f"DOCX processing failed: {e}"
            results.append(result)

        return results

    def detect_subject_mode(self, results: List[ConversionResult]) -> str:
        """Auto-detect subject mode based on content.

        Analyzes context text from equations to determine if document
        is primarily chemistry, physics, or general math.

        Args:
            results: List of conversion results with context

        Returns:
            Detected subject mode: 'chemistry', 'physics', or 'math'

        Example:
            >>> results = processor.process_docx('chem_doc.docx')
            >>> mode = processor.detect_subject_mode(results)
            >>> print(f"Detected mode: {mode}")
        """
        chemistry_indicators = 0
        physics_indicators = 0
        total_context = ""

        for result in results:
            if result.success and result.context:
                total_context += " " + result.context.lower()

        # Simple heuristic detection
        chemistry_words = ['reaction', 'equation', 'chemical', 'compound', 'element', 'molecule', 'ion', 'acid', 'base']
        physics_words = ['force', 'energy', 'velocity', 'acceleration', 'wave', 'field', 'quantum', 'particle']

        for word in chemistry_words:
            chemistry_indicators += total_context.count(word)

        for word in physics_words:
            physics_indicators += total_context.count(word)

        if chemistry_indicators > physics_indicators and chemistry_indicators > 2:
            return "chemistry"
        elif physics_indicators > chemistry_indicators and physics_indicators > 2:
            return "physics"
        else:
            return "math"