Struct TextExtractor 

pub struct TextExtractor { /* private fields */ }

Text extraction component

Implementations

impl TextExtractor

pub fn new(config: TextExtractionConfig) -> RragResult<Self>

Create new text extractor

pub async fn extract_from_pdf( &self, file_path: &Path, ) -> RragResult<ExtractedContent>

Extract from PDF

pub async fn extract_from_word( &self, file_path: &Path, ) -> RragResult<ExtractedContent>

Extract from Word document

pub async fn extract_from_ppt( &self, file_path: &Path, ) -> RragResult<ExtractedContent>

Extract from PowerPoint

pub async fn extract_from_html( &self, file_path: &Path, ) -> RragResult<ExtractedContent>

Extract from HTML

pub async fn extract_from_markdown( &self, file_path: &Path, ) -> RragResult<ExtractedContent>

Extract from Markdown

pub async fn extract_from_text( &self, file_path: &Path, ) -> RragResult<ExtractedContent>

Extract from plain text

pub async fn extract_auto_detect( &self, file_path: &Path, ) -> RragResult<ExtractedContent>

Auto-detect and extract