Struct PdfIngester 

pub struct PdfIngester { /* private fields */ }

PDF document ingester for extracting text and metadata.

Implementations

impl PdfIngester

pub fn new() -> Self

Create a new PDF ingester with default configuration.

pub fn with_config(config: PdfIngesterConfig) -> Self

Create a new PDF ingester with custom configuration.

pub fn ingest_file(&self, path: &Path) -> Result<PdfDocument>

Ingest a single PDF file.

Arguments

• path - Path to the PDF file

Returns

A PdfDocument containing the extracted content and metadata.

Errors

Returns an error if the file cannot be read or parsed as a PDF.

pub fn ingest_bytes(&self, data: &[u8], path: PathBuf) -> Result<PdfDocument>

Ingest PDF content from raw bytes.

Arguments

• data - Raw PDF file bytes
• path - Path to associate with the document (for reference)

Returns

A PdfDocument containing the extracted content and metadata.

pub fn chunk_text(text: &str, max_chunk_size: usize) -> Vec<String>

Chunk text into segments of maximum size, breaking at paragraph or sentence boundaries.

Arguments

• text - The text to chunk
• max_chunk_size - Maximum size of each chunk in characters

Returns

A vector of text chunks.

pub fn ingest_directory( &self, dir: &Path, recursive: bool, ) -> Result<Vec<PdfDocument>>

Ingest all PDF files in a directory.

Arguments

• dir - Directory path to search
• recursive - Whether to search subdirectories

Returns

A vector of successfully parsed PDF documents.

Errors

Returns an error if the directory cannot be read.

Trait Implementations

impl Clone for PdfIngester

fn clone(&self) -> PdfIngester

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for PdfIngester

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for PdfIngester

fn default() -> Self

Returns the “default value” for a type.