markitect-main/examples/plugins/example_processor.py

"""
Example processor plugin for MarkiTect.

This demonstrates how to create a custom processor plugin.
"""

import re
from markitect.plugins.base import ProcessorPlugin, PluginMetadata, PluginType
from markitect.plugins.decorators import register_plugin


@register_plugin("example_processor")
class ExampleProcessor(ProcessorPlugin):
    """
    Example processor that demonstrates various text processing capabilities.

    This processor can:
    - Convert text to different cases
    - Clean up whitespace
    - Remove or replace patterns
    - Add prefixes/suffixes to lines
    """

    @property
    def metadata(self) -> PluginMetadata:
        return PluginMetadata(
            name="example_processor",
            version="1.0.0",
            description="Example processor demonstrating text transformations",
            author="MarkiTect Team",
            plugin_type=PluginType.PROCESSOR
        )

    def process(self, content: str, **kwargs) -> str:
        """
        Process content with various transformations.

        Args:
            content: Input content to process
            **kwargs: Processing options:
                - case: 'upper', 'lower', 'title', 'sentence'
                - clean_whitespace: bool
                - remove_pattern: regex pattern to remove
                - replace_pattern: dict with 'pattern' and 'replacement'
                - line_prefix: string to add to start of each line
                - line_suffix: string to add to end of each line

        Returns:
            Processed content
        """
        if not isinstance(content, str):
            return content

        result = content

        # Case transformations
        case = kwargs.get('case', '').lower()
        if case == 'upper':
            result = result.upper()
        elif case == 'lower':
            result = result.lower()
        elif case == 'title':
            result = result.title()
        elif case == 'sentence':
            result = self._sentence_case(result)

        # Clean whitespace
        if kwargs.get('clean_whitespace', False):
            result = self._clean_whitespace(result)

        # Remove pattern
        remove_pattern = kwargs.get('remove_pattern')
        if remove_pattern:
            result = re.sub(remove_pattern, '', result)

        # Replace pattern
        replace_pattern = kwargs.get('replace_pattern')
        if replace_pattern and isinstance(replace_pattern, dict):
            pattern = replace_pattern.get('pattern')
            replacement = replace_pattern.get('replacement', '')
            if pattern:
                result = re.sub(pattern, replacement, result)

        # Line prefix/suffix
        line_prefix = kwargs.get('line_prefix', '')
        line_suffix = kwargs.get('line_suffix', '')
        if line_prefix or line_suffix:
            lines = result.split('\n')
            lines = [f"{line_prefix}{line}{line_suffix}" for line in lines]
            result = '\n'.join(lines)

        return result

    def can_process(self, content: str, **kwargs) -> bool:
        """Check if content can be processed (any string content)."""
        return isinstance(content, str)

    def _sentence_case(self, text: str) -> str:
        """Convert text to sentence case (first letter capitalized)."""
        if not text:
            return text
        return text[0].upper() + text[1:].lower()

    def _clean_whitespace(self, text: str) -> str:
        """Clean up whitespace in text."""
        # Remove trailing whitespace from each line
        lines = [line.rstrip() for line in text.split('\n')]

        # Remove multiple consecutive empty lines
        cleaned_lines = []
        prev_empty = False
        for line in lines:
            if line.strip():
                cleaned_lines.append(line)
                prev_empty = False
            elif not prev_empty:
                cleaned_lines.append(line)
                prev_empty = True

        return '\n'.join(cleaned_lines)

    def validate_config(self) -> list:
        """Validate plugin configuration."""
        errors = []

        case = self.config.get('case', '').lower()
        if case and case not in ['upper', 'lower', 'title', 'sentence']:
            errors.append(f"Invalid case option: {case}")

        replace_pattern = self.config.get('replace_pattern')
        if replace_pattern and not isinstance(replace_pattern, dict):
            errors.append("replace_pattern must be a dictionary with 'pattern' and 'replacement' keys")

        return errors


# Example usage:
if __name__ == '__main__':
    # Test the processor
    processor = ExampleProcessor()

    test_content = """  Hello World
    This is a test.


    Multiple empty lines above.  """

    # Test case conversion
    result = processor.process(test_content, case='upper')
    print("Upper case:")
    print(result)
    print()

    # Test whitespace cleaning
    result = processor.process(test_content, clean_whitespace=True)
    print("Cleaned whitespace:")
    print(repr(result))
    print()

    # Test pattern replacement
    result = processor.process(
        test_content,
        replace_pattern={'pattern': r'\s+', 'replacement': ' '}
    )
    print("Normalized spaces:")
    print(repr(result))
    print()

    # Test line prefix
    result = processor.process(
        "Line 1\nLine 2\nLine 3",
        line_prefix=">> "
    )
    print("With prefix:")
    print(result)