Class RegexChunking

crawl4ai/chunking_strategy.py:19–32

    
# Regex-based chunking
class RegexChunking(ChunkingStrategy):
    def __init__(self, patterns=None, **kwargs):
        if patterns is None:
            patterns = [r'\n\n']  # Default split pattern
        self.patterns = patterns

    def chunk(self, text: str) -> list:
        paragraphs = [text]
        for pattern in self.patterns:
            new_paragraphs = []
            for paragraph in paragraphs:
                new_paragraphs.extend(re.split(pattern, paragraph))
            paragraphs = new_paragraphs
        return paragraphs
    
# NLP-based sentence chunking 
class NlpSentenceChunking(ChunkingStrategy):