Method load_document

core/src/document_loader.rs:78–110

Load and extract content from a document

(
        &self,
        source_path: &str,
        document_type: &str,
    )

    /// Load and extract content from a document
    pub async fn load_document(
        &self,
        source_path: &str,
        document_type: &str,
    ) -> GraphBitResult<DocumentContent> {
        // Validate document type
        let supported_types = [
            "pdf", "txt", "docx", "json", "csv", "xml", "html", "xlsb", "xlsx", "xls",
        ];
        if !supported_types.contains(&document_type.to_lowercase().as_str()) {
            return Err(GraphBitError::validation(
                "document_loader",
                format!("Unsupported document type: {document_type}"),
            ));
        }

        // Check if source is a URL or file path
        let content = if source_path.starts_with("http://") || source_path.starts_with("https://") {
            self.load_from_url(source_path, document_type).await?
        } else if source_path.contains("://") {
            // This looks like a URL but not HTTP/HTTPS
            return Err(GraphBitError::validation(
                "document_loader",
                format!(
                    "Invalid URL format: {source_path}. Only HTTP and HTTPS URLs are supported"
                ),
            ));
        } else {
            self.load_from_file(source_path, document_type).await?
        };

        Ok(content)
    }

    /// Load document from file path
    async fn load_from_file(