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

"""
Input parser factory for auto-detecting and creating appropriate parsers.

This module provides centralized parser creation with auto-detection
support for determining the most appropriate parser based on input source.
"""

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


class InputParserFactory:
    """
    Factory for creating input parsers based on source content.

    This factory provides centralized parser creation with support for:
    - Auto-detection based on file extension or content
    - Explicit parser selection by type
    - Clear error messages for unsupported formats
    """

    @staticmethod
    def create_parser(source: str, parser_type: Union[str, None] = None) -> Parser:
        """
        Create an appropriate parser for the input source.

        Args:
            source: Input source (file path or content string)
            parser_type: Optional explicit parser type
                        ("docx", "omml", "mathml", or None for auto-detection)

        Returns:
            Parser instance appropriate for the source

        Raises:
            ValueError: If input format cannot be determined or is unsupported

        Examples:
            >>> factory = InputParserFactory()
            >>> parser = factory.create_parser("equations.docx")
            >>> isinstance(parser, DocxParser)
            True

            >>> parser = factory.create_parser("<math><mi>x</mi></math>")
            >>> isinstance(parser, MathMLParser)
            True

            >>> parser = factory.create_parser(xml_content, parser_type="omml")
            >>> isinstance(parser, OmmlParser)
            True
        """
        # Import here to avoid circular dependencies
        from .docx_parser import DocxParser
        from .omml_parser import OmmlParser
        from .mathml_parser import MathMLParser

        # Explicit parser type specified
        if parser_type:
            parser_type = parser_type.lower()
            if parser_type == "docx":
                return DocxParser()
            elif parser_type == "omml":
                return OmmlParser()
            elif parser_type == "mathml":
                return MathMLParser()
            else:
                raise ValueError(f"Unknown parser type: {parser_type}")

        # Auto-detection based on source
        # Check file extension first (most common case)
        if source.endswith('.docx') or (os.path.exists(source) and source.lower().endswith('.docx')):
            return DocxParser()

        # Check content for XML markers
        # Strip whitespace for reliable detection
        content_start = source.strip()[:200]  # Check first 200 chars

        # Check for OMML namespace
        if '<m:oMath' in content_start or '<m:oMathPara' in content_start:
            return OmmlParser()

        # Check for MathML namespace
        if '<math' in content_start or '<mml:math' in content_start:
            return MathMLParser()

        # If it's a file path but not .docx, check file content
        if os.path.exists(source):
            try:
                with open(source, 'r', encoding='utf-8') as f:
                    file_content = f.read(500)  # Read first 500 chars
                    if '<m:oMath' in file_content:
                        return OmmlParser()
                    elif '<math' in file_content or '<mml:math' in file_content:
                        return MathMLParser()
            except (UnicodeDecodeError, IOError):
                # Binary file or read error - not a supported format
                pass

        # Unable to determine format
        preview = source if len(source) <= 100 else source[:100] + "..."
        raise ValueError(
            f"Unable to determine input format for source: '{preview}'. "
            f"Supported formats: .docx files, OMML XML (<m:oMath), MathML XML (<math)"
        )

    @staticmethod
    def detect_parser_type(source: str) -> str:
        """
        Detect the parser type needed for the input source.

        Args:
            source: Input source (file path or content string)

        Returns:
            Parser type string ("docx", "omml", or "mathml")

        Raises:
            ValueError: If input format cannot be determined

        Examples:
            >>> factory = InputParserFactory()
            >>> factory.detect_parser_type("equations.docx")
            'docx'

            >>> factory.detect_parser_type("<math><mi>x</mi></math>")
            'mathml'
        """
        parser = InputParserFactory.create_parser(source)
        return parser.parser_type

    @staticmethod
    def get_supported_formats() -> List[str]:
        """
        Get list of supported input formats.

        Returns:
            List of format identifiers that can be parsed
        """
        return ["docx", "omml", "mathml"]

    def __repr__(self) -> str:
        """String representation for debugging."""
        return "InputParserFactory(docx, omml, mathml)"